4.4beta2

This ensures the provided path matches the path PostgreSQL reports as its
data directory.

.gitignore

@@ -42,11 +42,12 @@ lib*.pc
 /regression.diffs
 /regression.out
 
-/doc/Makefile
-
 # other
 /.lineno
 *.dSYM
+*.orig
+*.rej
+
 # generated binaries
 repmgr
 repmgrd

HISTORY

@@ -1,4 +1,36 @@
-4.3     2019-??
+4.4     2019-??-??
+        repmgr: improve "daemon status" output (Ian)
+        repmgr: add "--siblings-follow" option to "standby promote" (Ian)
+        repmgr: add "--repmgrd-force-unpause" option to "standby switchover" (Ian)
+        repmgr: fix data directory permissions issue in barman mode where
+          an existing directory is being overwritten (Ian)
+        repmgr: improve "--dry-run" behaviour for "standby promote" and
+          "standby switchover" (Ian)
+        repmgr: when running "standby clone" with the "--upstream-conninfo" option
+          ensure that "application_name" is set correctly in "primary_conninfo" (Ian)
+        repmgr: ensure "--dry-run" together with --force when running "standby clone"
+          in barman mode does not modify an existing data directory (Ian)
+        repmgr: improve "--dry-run" output when running "standby clone" in
+          basebackup mode (Ian)
+        repmgr: improve upstream walsender checks when running "standby clone" (Ian)
+        repmgr: display node timeline ID in "cluster show" output (Ian)
+        repmgr: in "cluster show" and "daemon status", show upstream node name
+          as reported by each individual node (Ian)
+        repmgr: in "cluster show" and "daemon status", check if a node is attached
+          to its advertised upstream node
+        repmgr: use --compact rather than --terse option in "cluster event" (Ian)
+        repmgr: prevent a standby being cloned from a witness server (Ian)
+        repmgr: prevent a witness server being registered on the cluster primary (John)
+        repmgr: ensure BDR2-specific functionality cannot be used on
+          BDR3 and later (Ian)
+        repmgr: canonicalize the data directory path (Ian)
+        repmgrd: monitor standbys attached to primary (Ian)
+        repmgrd: add "primary visibility consensus" functionality (Ian)
+        repmgrd: fix memory leak which occurs while the monitored PostgreSQL
+           node is not running (Ian)
+        general: documentation converted to DocBook XML format (Ian)
+
+4.3     2019-04-02
         repmgr: add "daemon (start|stop)" command; GitHub #528 (Ian)
         repmgr: add --version-number command line option (Ian)
         repmgr: add --compact option to "cluster show"; GitHub #521 (Ian)
@@ -15,6 +47,8 @@
         repmgr: add sanity check for correct extension version (Ian)
         repmgr: ensure "witness register --dry-run" does not attempt to read node
           tables if repmgr extension not installed; GitHub #513 (Ian)
+        repmgr: ensure "standby register" fails when --upstream-node-id is the
+          same as the local node ID (Ian)
         repmgrd: check binary and extension major versions match; GitHub #515 (Ian)
         repmgrd: on a cascaded standby, don't fail over if "failover=manual";
           GitHub #531 (Ian)
@@ -22,6 +56,9 @@
           candidates (Ian)
         repmgrd: add option "connection_check_type" (Ian)
         repmgrd: improve witness monitoring when primary node not available (Ian)
+		repmgrd: handle situation where a primary has unexpectedly appeared
+		  during failover; GitHub #420 (Ian)
+		general: fix Makefile (John)
 
 4.2     2018-10-24
         repmgr: add parameter "shutdown_check_timeout" for use by "standby switchover";

Makefile.in

@@ -17,7 +17,9 @@ DATA = \
   repmgr--4.1--4.2.sql \
   repmgr--4.2.sql \
   repmgr--4.2--4.3.sql \
-  repmgr--4.3.sql
+  repmgr--4.3.sql \
+  repmgr--4.3--4.4.sql \
+  repmgr--4.4.sql
 
 REGRESS = repmgr_extension
 
@@ -75,10 +77,19 @@ Makefile: Makefile.in config.status configure
 Makefile.global: Makefile.global.in config.status configure
 	./config.status $@
 
-doc:
-	$(MAKE) -C doc all
+doc: repmgr_version.h
+	$(MAKE) -C doc html
 
-install-doc:
+doc-repmgr.html: repmgr_version.h
+	$(MAKE) -C doc repmgr.html
+
+doc-repmgr-A4.pdf: repmgr_version.h
+	$(MAKE) -C doc repmgr-A4.pdf
+
+doc-repmgr-US.pdf: repmgr_version.h
+	$(MAKE) -C doc repmgr-US.pdf
+
+install-doc: doc
 	$(MAKE) -C doc install
 
 clean: additional-clean
@@ -87,6 +98,7 @@ maintainer-clean: additional-maintainer-clean
 
 additional-clean:
 	rm -f *.o
+	$(MAKE) -C doc clean
 
 additional-maintainer-clean: clean
 	$(MAKE) -C doc maintainer-clean
@@ -109,3 +121,4 @@ installdirs-scripts:
 .PHONY: installdirs-scripts
 endif
 
+.PHONY: doc doc-repmgr.html doc-repmgr-A4.pdf doc-repmgr-US.pdf install-doc

README.md

@@ -27,7 +27,7 @@ Documentation
 
 The main `repmgr` documentation is available here:
 
-> [repmgr 4 documentation](https://repmgr.org/docs/4.2/index.html)
+> [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
 The `README` file for `repmgr` 3.x is available here:
 
@@ -72,7 +72,7 @@ Please report bugs and other issues to:
 
 * https://github.com/2ndQuadrant/repmgr
 
-Further information is available at https://www.repmgr.org/
+Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
 news are always welcome. Send us an email at info@2ndQuadrant.com, or
@@ -97,6 +97,7 @@ Thanks from the repmgr core team.
 Further reading
 ---------------
 
+* [repmgr documentation](https://repmgr.org/docs/current/index.html)
 * https://blog.2ndquadrant.com/repmgr-3-2-is-here-barman-support-brand-new-high-availability-features/
 * https://blog.2ndquadrant.com/improvements-in-repmgr-3-1-4/
 * https://blog.2ndquadrant.com/managing-useful-clusters-repmgr/

configfile.c

@@ -344,7 +344,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->failover = FAILOVER_MANUAL;
 	options->priority = DEFAULT_PRIORITY;
 	memset(options->location, 0, sizeof(options->location));
-	strncpy(options->location, DEFAULT_LOCATION, MAXLEN);
+	strncpy(options->location, DEFAULT_LOCATION, sizeof(options->location));
 	memset(options->promote_command, 0, sizeof(options->promote_command));
 	memset(options->follow_command, 0, sizeof(options->follow_command));
 	options->monitor_interval_secs = DEFAULT_MONITORING_INTERVAL;
@@ -365,6 +365,13 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	memset(options->failover_validation_command, 0, sizeof(options->failover_validation_command));
 	options->election_rerun_interval = DEFAULT_ELECTION_RERUN_INTERVAL;
 
+	options->child_nodes_check_interval = DEFAULT_CHILD_NODES_CHECK_INTERVAL;
+	options->child_nodes_disconnect_min_count = DEFAULT_CHILD_NODES_DISCONNECT_MIN_COUNT;
+	options->child_nodes_connected_min_count = DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT;
+	options->child_nodes_connected_include_witness = DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS;
+	options->child_nodes_disconnect_timeout = DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT;
+	memset(options->child_nodes_disconnect_command, 0, sizeof(options->child_nodes_disconnect_command));
+
 	/*-------------
 	 * witness settings
 	 *-------------
@@ -484,21 +491,34 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			node_id_found = true;
 		}
 		else if (strcmp(name, "node_name") == 0)
-			strncpy(options->node_name, value, MAXLEN);
+		{
+			if (strlen(value) < sizeof(options->node_name))
+				strncpy(options->node_name, value, sizeof(options->node_name));
+			else
+				item_list_append_format(error_list,
+										_("value for \"node_name\" must contain fewer than %lu characters"),
+										sizeof(options->node_name));
+		}
 		else if (strcmp(name, "conninfo") == 0)
 			strncpy(options->conninfo, value, MAXLEN);
 		else if (strcmp(name, "data_directory") == 0)
+		{
 			strncpy(options->data_directory, value, MAXPGPATH);
+			canonicalize_path(options->data_directory);
+		}
 		else if (strcmp(name, "config_directory") == 0)
+		{
 			strncpy(options->config_directory, value, MAXPGPATH);
-
+			canonicalize_path(options->config_directory);
+		}
 		else if (strcmp(name, "replication_user") == 0)
 		{
-			if (strlen(value) < NAMEDATALEN)
-				strncpy(options->replication_user, value, NAMEDATALEN);
+			if (strlen(value) < sizeof(options->replication_user))
+				strncpy(options->replication_user, value, sizeof(options->replication_user));
 			else
-				item_list_append(error_list,
-								 _("value for \"replication_user\" must contain fewer than " STR(NAMEDATALEN) " characters"));
+				item_list_append_format(error_list,
+										_("value for \"replication_user\" must contain fewer than %lu characters"),
+										sizeof(options->replication_user));
 		}
 		else if (strcmp(name, "pg_bindir") == 0)
 			strncpy(options->pg_bindir, value, MAXPGPATH);
@@ -645,7 +665,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			else
 			{
 				item_list_append(error_list,
-								 _("value for \"connection_check_type\" must be \"ping\" or \"connection\"\n"));
+								 _("value for \"connection_check_type\" must be \"ping\", \"connection\" or \"query\"\n"));
 			}
 		}
 		else if (strcmp(name, "primary_visibility_consensus") == 0)
@@ -654,6 +674,18 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			strncpy(options->failover_validation_command, value, sizeof(options->failover_validation_command));
 		else if (strcmp(name, "election_rerun_interval") == 0)
 			options->election_rerun_interval = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "child_nodes_check_interval") == 0)
+			options->child_nodes_check_interval = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "child_nodes_disconnect_command") == 0)
+			snprintf(options->child_nodes_disconnect_command, sizeof(options->child_nodes_disconnect_command), "%s", value);
+		else if (strcmp(name, "child_nodes_disconnect_min_count") == 0)
+			options->child_nodes_disconnect_min_count = repmgr_atoi(value, name, error_list, -1);
+		else if (strcmp(name, "child_nodes_connected_min_count") == 0)
+			options->child_nodes_connected_min_count = repmgr_atoi(value, name, error_list, -1);
+		else if (strcmp(name, "child_nodes_connected_include_witness") == 0)
+			options->child_nodes_connected_include_witness = parse_bool(value, name, error_list);
+		else if (strcmp(name, "child_nodes_disconnect_timeout") == 0)
+			options->child_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
 
 		/* witness settings */
 		else if (strcmp(name, "witness_sync_interval") == 0)
@@ -828,15 +860,16 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		conninfo_options = PQconninfoParse(options->conninfo, &conninfo_errmsg);
 		if (conninfo_options == NULL)
 		{
-			char		error_message_buf[MAXLEN] = "";
+			PQExpBufferData error_message_buf;
+			initPQExpBuffer(&error_message_buf);
 
-			snprintf(error_message_buf,
-					 MAXLEN,
-					 _("\"conninfo\": %s	(provided: \"%s\")"),
-					 conninfo_errmsg,
-					 options->conninfo);
+			appendPQExpBuffer(&error_message_buf,
+							  _("\"conninfo\": %s	(provided: \"%s\")"),
+							  conninfo_errmsg,
+							  options->conninfo);
 
-			item_list_append(error_list, error_message_buf);
+			item_list_append(error_list, error_message_buf.data);
+			termPQExpBuffer(&error_message_buf);
 		}
 
 		PQconninfoFree(conninfo_options);
@@ -1085,12 +1118,18 @@ parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemL
  * loop is started up; it therefore only needs to reload options required
  * by repmgrd, which are as follows:
  *
- * changeable options (keep the list in "doc/repmgrd-configuration.sgml" in sync
+ * changeable options (keep the list in "doc/repmgrd-configuration.xml" in sync
  * with these):
  *
  * - async_query_timeout
  * - bdr_local_monitoring_only
  * - bdr_recovery_timeout
+ * - child_nodes_check_interval
+ * - child_nodes_connected_min_count
+ * - child_nodes_connected_include_witness
+ * - child_nodes_disconnect_command
+ * - child_nodes_disconnect_min_count
+ * - child_nodes_disconnect_timeout
  * - connection_check_type
  * - conninfo
  * - degraded_monitoring_timeout
@@ -1196,7 +1235,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		return false;
 	}
 
-	if (strncmp(new_options.node_name, orig_options->node_name, MAXLEN) != 0)
+	if (strncmp(new_options.node_name, orig_options->node_name, sizeof(orig_options->node_name)) != 0)
 	{
 		log_warning(_("\"node_name\" cannot be changed, keeping current configuration"));
 		return false;
@@ -1238,8 +1277,95 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
+	/* child_nodes_check_interval */
+	if (orig_options->child_nodes_check_interval != new_options.child_nodes_check_interval)
+	{
+		if (new_options.child_nodes_check_interval < 0)
+		{
+			log_error(_("\"child_nodes_check_interval\" must be \"0\" or greater; provided: \"%i\""),
+					  new_options.child_nodes_check_interval);
+		}
+		else
+		{
+			orig_options->child_nodes_check_interval = new_options.child_nodes_check_interval;
+			log_info(_("\"child_nodes_check_interval\" is now \"%i\""), new_options.child_nodes_check_interval);
+
+			config_changed = true;
+		}
+	}
+
+	/* child_nodes_disconnect_command */
+	if (strncmp(orig_options->child_nodes_disconnect_command, new_options.child_nodes_disconnect_command, sizeof(orig_options->child_nodes_disconnect_command)) != 0)
+	{
+		snprintf(orig_options->child_nodes_disconnect_command, sizeof(orig_options->child_nodes_disconnect_command),
+				 "%s", new_options.child_nodes_disconnect_command);
+		log_info(_("\"child_nodes_disconnect_command\" is now \"%s\""), new_options.child_nodes_disconnect_command);
+
+		config_changed = true;
+	}
+
+	/* child_nodes_disconnect_min_count */
+	if (orig_options->child_nodes_disconnect_min_count != new_options.child_nodes_disconnect_min_count)
+	{
+		if (new_options.child_nodes_disconnect_min_count < 0)
+		{
+			log_error(_("\"child_nodes_disconnect_min_count\" must be \"0\" or greater; provided: \"%i\""),
+					  new_options.child_nodes_disconnect_min_count);
+		}
+		else
+		{
+			orig_options->child_nodes_disconnect_min_count = new_options.child_nodes_disconnect_min_count;
+			log_info(_("\"child_nodes_disconnect_min_count\" is now \"%i\""), new_options.child_nodes_disconnect_min_count);
+
+			config_changed = true;
+		}
+	}
+
+	/* child_nodes_connected_min_count */
+	if (orig_options->child_nodes_connected_min_count != new_options.child_nodes_connected_min_count)
+	{
+		if (new_options.child_nodes_connected_min_count < 0)
+		{
+			log_error(_("\"child_nodes_connected_min_count\" must be \"0\" or greater; provided: \"%i\""),
+					  new_options.child_nodes_connected_min_count);
+		}
+		else
+		{
+			orig_options->child_nodes_connected_min_count = new_options.child_nodes_connected_min_count;
+			log_info(_("\"child_nodes_connected_min_count\" is now \"%i\""), new_options.child_nodes_connected_min_count);
+
+			config_changed = true;
+		}
+	}
+
+	/* child_nodes_connected_include_witness */
+	if (orig_options->child_nodes_connected_include_witness != new_options.child_nodes_connected_include_witness)
+	{
+		orig_options->child_nodes_connected_include_witness = new_options.child_nodes_connected_include_witness;
+		log_info(_("\"child_nodes_connected_include_witness\" is now \"%i\""), new_options.child_nodes_connected_include_witness);
+
+		config_changed = true;
+	}
+
+	/* child_nodes_disconnect_timeout */
+	if (orig_options->child_nodes_disconnect_timeout != new_options.child_nodes_disconnect_timeout)
+	{
+		if (new_options.child_nodes_disconnect_timeout < 0)
+		{
+			log_error(_("\"child_nodes_disconnect_timeout\" must be \"0\" or greater; provided: \"%i\""),
+					  new_options.child_nodes_disconnect_timeout);
+		}
+		else
+		{
+			orig_options->child_nodes_disconnect_timeout = new_options.child_nodes_disconnect_timeout;
+			log_info(_("\"child_nodes_disconnect_timeout\" is now \"%i\""), new_options.child_nodes_disconnect_timeout);
+
+			config_changed = true;
+		}
+	}
+
 	/* conninfo */
-	if (strncmp(orig_options->conninfo, new_options.conninfo, MAXLEN) != 0)
+	if (strncmp(orig_options->conninfo, new_options.conninfo, sizeof(orig_options->conninfo)) != 0)
 	{
 		/* Test conninfo string works */
 		conn = establish_db_connection(new_options.conninfo, false);
@@ -1249,11 +1375,14 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		}
 		else
 		{
-			strncpy(orig_options->conninfo, new_options.conninfo, MAXLEN);
+			snprintf(orig_options->conninfo, sizeof(orig_options->conninfo),
+					 "%s", new_options.conninfo);
 			log_info(_("\"conninfo\" is now \"%s\""), new_options.conninfo);
 		}
 
 		PQfinish(conn);
+
+		config_changed = true;
 	}
 
 	/* degraded_monitoring_timeout */
@@ -1266,18 +1395,20 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	}
 
 	/* event_notification_command */
-	if (strncmp(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN) != 0)
+	if (strncmp(orig_options->event_notification_command, new_options.event_notification_command, sizeof(orig_options->event_notification_command)) != 0)
 	{
-		strncpy(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN);
+		snprintf(orig_options->event_notification_command, sizeof(orig_options->event_notification_command),
+				 "%s", new_options.event_notification_command);
 		log_info(_("\"event_notification_command\" is now \"%s\""), new_options.event_notification_command);
 
 		config_changed = true;
 	}
 
 	/* event_notifications */
-	if (strncmp(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN) != 0)
+	if (strncmp(orig_options->event_notifications_orig, new_options.event_notifications_orig, sizeof(orig_options->event_notifications_orig)) != 0)
 	{
-		strncpy(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN);
+		snprintf(orig_options->event_notifications_orig, sizeof(orig_options->event_notifications_orig),
+				 "%s", new_options.event_notifications_orig);
 		log_info(_("\"event_notifications\" is now \"%s\""), new_options.event_notifications_orig);
 
 		clear_event_notification_list(orig_options);
@@ -1295,9 +1426,10 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	}
 
 	/* follow_command */
-	if (strncmp(orig_options->follow_command, new_options.follow_command, MAXLEN) != 0)
+	if (strncmp(orig_options->follow_command, new_options.follow_command, sizeof(orig_options->follow_command)) != 0)
 	{
-		strncpy(orig_options->follow_command, new_options.follow_command, MAXLEN);
+		snprintf(orig_options->follow_command, sizeof(orig_options->follow_command),
+				 "%s", new_options.follow_command);
 		log_info(_("\"follow_command\" is now \"%s\""), new_options.follow_command);
 
 		config_changed = true;
@@ -1331,9 +1463,10 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	}
 
 	/* promote_command */
-	if (strncmp(orig_options->promote_command, new_options.promote_command, MAXLEN) != 0)
+	if (strncmp(orig_options->promote_command, new_options.promote_command, sizeof(orig_options->promote_command)) != 0)
 	{
-		strncpy(orig_options->promote_command, new_options.promote_command, MAXLEN);
+		snprintf(orig_options->promote_command, sizeof(orig_options->promote_command),
+				 "%s", new_options.promote_command);
 		log_info(_("\"promote_command\" is now \"%s\""), new_options.promote_command);
 
 		config_changed = true;
@@ -1398,7 +1531,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	{
 		orig_options->connection_check_type = new_options.connection_check_type;
 		log_info(_("\"connection_check_type\" is now \"%s\""),
-				 new_options.connection_check_type == CHECK_PING ? "ping" : "connection");
+				 print_connection_check_type(new_options.connection_check_type));
 		config_changed = true;
 	}
 
@@ -1412,9 +1545,10 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	}
 
 	/* failover_validation_command */
-	if (strncmp(orig_options->failover_validation_command, new_options.failover_validation_command, MAXPGPATH) != 0)
+	if (strncmp(orig_options->failover_validation_command, new_options.failover_validation_command, sizeof(orig_options->failover_validation_command)) != 0)
 	{
-		strncpy(orig_options->failover_validation_command, new_options.failover_validation_command, MAXPGPATH);
+		snprintf(orig_options->failover_validation_command, sizeof(orig_options->failover_validation_command),
+				 "%s", new_options.failover_validation_command);
 		log_info(_("\"failover_validation_command\" is now \"%s\""), new_options.failover_validation_command);
 
 		config_changed = true;
@@ -1425,18 +1559,20 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	 */
 
 	/* log_facility */
-	if (strncmp(orig_options->log_facility, new_options.log_facility, MAXLEN) != 0)
+	if (strncmp(orig_options->log_facility, new_options.log_facility, sizeof(orig_options->log_facility)) != 0)
 	{
-		strncpy(orig_options->log_facility, new_options.log_facility, MAXLEN);
+		snprintf(orig_options->log_facility, sizeof(orig_options->log_facility),
+				 "%s", new_options.log_facility);
 		log_info(_("\"log_facility\" is now \"%s\""), new_options.log_facility);
 
 		log_config_changed = true;
 	}
 
 	/* log_file */
-	if (strncmp(orig_options->log_file, new_options.log_file, MAXLEN) != 0)
+	if (strncmp(orig_options->log_file, new_options.log_file, sizeof(orig_options->log_file)) != 0)
 	{
-		strncpy(orig_options->log_file, new_options.log_file, MAXLEN);
+		snprintf(orig_options->log_file, sizeof(orig_options->log_file),
+				 "%s", new_options.log_file);
 		log_info(_("\"log_file\" is now \"%s\""), new_options.log_file);
 
 		log_config_changed = true;
@@ -1444,9 +1580,10 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 
 
 	/* log_level */
-	if (strncmp(orig_options->log_level, new_options.log_level, MAXLEN) != 0)
+	if (strncmp(orig_options->log_level, new_options.log_level, sizeof(orig_options->log_level)) != 0)
 	{
-		strncpy(orig_options->log_level, new_options.log_level, MAXLEN);
+		snprintf(orig_options->log_level, sizeof(orig_options->log_level),
+				 "%s", new_options.log_level);
 		log_info(_("\"log_level\" is now \"%s\""), new_options.log_level);
 
 		log_config_changed = true;
@@ -1940,18 +2077,10 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 	struct option *long_options = NULL;
 
 
-	/* We're only interested in these options */
-	static struct option long_options_9[] =
-	{
-		{"slot", required_argument, NULL, 'S'},
-		{"xlog-method", required_argument, NULL, 'X'},
-		{NULL, 0, NULL, 0}
-	};
-
 	/*
-	 * From PostgreSQL 10, --xlog-method is renamed --wal-method and there's
-	 * also --no-slot, which we'll want to consider.
+	 * We're only interested in these options.
 	 */
+
 	static struct option long_options_10[] =
 	{
 		{"slot", required_argument, NULL, 'S'},
@@ -1960,6 +2089,17 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 		{NULL, 0, NULL, 0}
 	};
 
+	/*
+	 * Pre-PostgreSQL 10 options
+	 */
+	static struct option long_options_legacy[] =
+	{
+		{"slot", required_argument, NULL, 'S'},
+		{"xlog-method", required_argument, NULL, 'X'},
+		{NULL, 0, NULL, 0}
+	};
+
+
 	/* Don't attempt to tokenise an empty string */
 	if (!strlen(pg_basebackup_options))
 		return backup_options_ok;
@@ -1967,7 +2107,7 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 	if (server_version_num >= 100000)
 		long_options = long_options_10;
 	else
-		long_options = long_options_9;
+		long_options = long_options_legacy;
 
 	argc_item = parse_output_to_argv(pg_basebackup_options, &argv_array);
 
@@ -1986,7 +2126,7 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 				strncpy(backup_options->slot, optarg, MAXLEN);
 				break;
 			case 'X':
-				strncpy(backup_options->xlog_method, optarg, MAXLEN);
+				strncpy(backup_options->wal_method, optarg, MAXLEN);
 				break;
 			case 1:
 				backup_options->no_slot = true;
@@ -2017,3 +2157,21 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 
 	return backup_options_ok;
 }
+
+
+const char *
+print_connection_check_type(ConnectionCheckType type)
+{
+	switch (type)
+	{
+		case CHECK_PING:
+			return "ping";
+		case CHECK_QUERY:
+			return "query";
+		case CHECK_CONNECTION:
+			return "connection";
+	}
+
+	/* should never reach here */
+	return "UNKNOWN";
+}

configfile.h

@@ -76,7 +76,7 @@ typedef struct
 {
 	/* node information */
 	int			node_id;
-	char		node_name[MAXLEN];
+	char		node_name[NAMEDATALEN];
 	char		conninfo[MAXLEN];
 	char		replication_user[NAMEDATALEN];
 	char		data_directory[MAXPGPATH];
@@ -88,7 +88,7 @@ typedef struct
 	/* log settings */
 	char		log_level[MAXLEN];
 	char		log_facility[MAXLEN];
-	char		log_file[MAXLEN];
+	char		log_file[MAXPGPATH];
 	int			log_status_interval;
 
 	/* standby clone settings */
@@ -148,6 +148,12 @@ typedef struct
 	bool		primary_visibility_consensus;
 	char		failover_validation_command[MAXPGPATH];
 	int			election_rerun_interval;
+	int			child_nodes_check_interval;
+	int			child_nodes_disconnect_min_count;
+	int			child_nodes_connected_min_count;
+	bool		child_nodes_connected_include_witness;
+	int			child_nodes_disconnect_timeout;
+	char		child_nodes_disconnect_command[MAXPGPATH];
 
 	/* BDR settings */
 	bool		bdr_local_monitoring_only;
@@ -221,6 +227,11 @@ typedef struct
 		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT, \
 		-1, "", false, DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT, \
 		CHECK_PING, true, "", DEFAULT_ELECTION_RERUN_INTERVAL, \
+		DEFAULT_CHILD_NODES_CHECK_INTERVAL, \
+		DEFAULT_CHILD_NODES_DISCONNECT_MIN_COUNT, \
+		DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT, \
+		DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS, \
+		DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT, "", \
 		/* BDR settings */ \
 		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
@@ -242,7 +253,7 @@ typedef struct
 typedef struct
 {
 	char		slot[MAXLEN];
-	char		xlog_method[MAXLEN];
+	char		wal_method[MAXLEN];
 	bool		no_slot;		/* from PostgreSQL 10 */
 } t_basebackup_options;
 
@@ -329,5 +340,6 @@ void free_parsed_argv(char ***argv_array);
 /* called by repmgr-client and repmgrd */
 void		exit_with_cli_errors(ItemList *error_list, const char *repmgr_command);
 void		print_item_list(ItemList *item_list);
+const char *print_connection_check_type(ConnectionCheckType type);
 
 #endif							/* _REPMGR_CONFIGFILE_H_ */

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.3.
+# Generated by GNU Autoconf 2.69 for repmgr 4.4.
 #
 # Report bugs to <repmgr@googlegroups.com>.
 #
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.3'
-PACKAGE_STRING='repmgr 4.3'
+PACKAGE_VERSION='4.4'
+PACKAGE_STRING='repmgr 4.4'
 PACKAGE_BUGREPORT='repmgr@googlegroups.com'
 PACKAGE_URL='https://repmgr.org/'
 
@@ -1178,7 +1178,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures repmgr 4.3 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.4 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1239,7 +1239,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.3:";;
+     short | recursive ) echo "Configuration of repmgr 4.4:";;
    esac
   cat <<\_ACEOF
 
@@ -1313,7 +1313,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.3
+repmgr configure 4.4
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1332,7 +1332,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by repmgr $as_me 4.3, which was
+It was created by repmgr $as_me 4.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1851,8 +1851,6 @@ ac_config_files="$ac_config_files Makefile"
 
 ac_config_files="$ac_config_files Makefile.global"
 
-ac_config_files="$ac_config_files doc/Makefile"
-
 cat >confcache <<\_ACEOF
 # This file is a shell script that caches the results of configure
 # tests run on this system so they can be shared between configure
@@ -2359,7 +2357,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by repmgr $as_me 4.3, which was
+This file was extended by repmgr $as_me 4.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2422,7 +2420,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-repmgr config.status 4.3
+repmgr config.status 4.4
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 
@@ -2546,7 +2544,6 @@ do
     "config.h") CONFIG_HEADERS="$CONFIG_HEADERS config.h" ;;
     "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;;
     "Makefile.global") CONFIG_FILES="$CONFIG_FILES Makefile.global" ;;
-    "doc/Makefile") CONFIG_FILES="$CONFIG_FILES doc/Makefile" ;;
 
   *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;;
   esac

configure.in

@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.3], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [4.4], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
 AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
 
@@ -59,6 +59,5 @@ AC_SUBST(vpath_build)
 
 AC_CONFIG_FILES([Makefile])
 AC_CONFIG_FILES([Makefile.global])
-AC_CONFIG_FILES([doc/Makefile])
 AC_OUTPUT
 

controldata.c

@@ -301,6 +301,8 @@ get_controlfile(const char *DataDir)
 					ControlFilePath);
 		log_detail("%s", strerror(errno));
 
+		close(fd);
+
 		return control_file_info;
 	}
 
@@ -308,7 +310,18 @@ get_controlfile(const char *DataDir)
 
 	control_file_info->control_file_processed = true;
 
-	if (version_num >= 110000)
+	if (version_num >= 120000)
+	{
+		ControlFileData12 *ptr = (struct ControlFileData12 *)ControlFileDataPtr;
+		control_file_info->system_identifier = ptr->system_identifier;
+		control_file_info->state = ptr->state;
+		control_file_info->checkPoint = ptr->checkPoint;
+		control_file_info->data_checksum_version = ptr->data_checksum_version;
+		control_file_info->timeline = ptr->checkPointCopy.ThisTimeLineID;
+		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
+		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
+	}
+	else if (version_num >= 110000)
 	{
 		ControlFileData11 *ptr = (struct ControlFileData11 *)ControlFileDataPtr;
 		control_file_info->system_identifier = ptr->system_identifier;

controldata.h

@@ -333,6 +333,72 @@ typedef struct ControlFileData11
 } ControlFileData11;
 
 
+/*
+ * Following field added in Pg12:
+ *
+ *   int max_wal_senders;
+ *
+ * Following fields removed:
+ *
+ *   uint32 nextXidEpoch;
+ *   TransactionId nextXid;
+ *
+ * and replaced by:
+ *
+ *   FullTransactionId nextFullXid;
+ */
+
+typedef struct ControlFileData12
+{
+	uint64		system_identifier;
+
+	uint32		pg_control_version; /* PG_CONTROL_VERSION */
+	uint32		catalog_version_no; /* see catversion.h */
+
+	DBState		state;			/* see enum above */
+	pg_time_t	time;			/* time stamp of last pg_control update */
+	XLogRecPtr	checkPoint;		/* last check point record ptr */
+
+	CheckPoint	checkPointCopy; /* copy of last check point record */
+
+	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
+
+	XLogRecPtr	minRecoveryPoint;
+	TimeLineID	minRecoveryPointTLI;
+	XLogRecPtr	backupStartPoint;
+	XLogRecPtr	backupEndPoint;
+	bool		backupEndRequired;
+
+	int			wal_level;
+	bool		wal_log_hints;
+	int			MaxConnections;
+	int			max_worker_processes;
+	int			max_wal_senders;
+	int			max_prepared_xacts;
+	int			max_locks_per_xact;
+	bool		track_commit_timestamp;
+
+	uint32		maxAlign;		/* alignment requirement for tuples */
+	double		floatFormat;	/* constant 1234567.0 */
+
+	uint32		blcksz;			/* data block size for this DB */
+	uint32		relseg_size;	/* blocks per segment of large relation */
+
+	uint32		xlog_blcksz;	/* block size within WAL files */
+	uint32		xlog_seg_size;	/* size of each WAL segment */
+
+	uint32		nameDataLen;	/* catalog name field width */
+	uint32		indexMaxKeys;	/* max number of columns in an index */
+
+	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
+	uint32		loblksize;		/* chunk size in pg_largeobject */
+
+	bool		float4ByVal;	/* float4 pass-by-value? */
+	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
+
+	uint32		data_checksum_version;
+} ControlFileData12;
+
 extern int get_pg_version(const char *data_directory, char *version_string);
 extern DBState get_db_state(const char *data_directory);
 extern const char *describe_db_state(DBState state);

dbutils.c

@@ -43,6 +43,8 @@ int			bdr_version_num = UNKNOWN_BDR_VERSION_NUM;
 static void log_db_error(PGconn *conn, const char *query_text, const char *fmt,...)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 
+static bool _is_server_available(const char *conninfo, bool quiet);
+
 static PGconn *_establish_db_connection(const char *conninfo,
 						 const bool exit_on_error,
 						 const bool log_notice,
@@ -51,6 +53,8 @@ static PGconn *_establish_db_connection(const char *conninfo,
 static PGconn *_get_primary_connection(PGconn *standby_conn, int *primary_id, char *primary_conninfo_out, bool quiet);
 
 static bool _set_config(PGconn *conn, const char *config_param, const char *sqlquery);
+static bool _get_pg_setting(PGconn *conn, const char *setting, char *str_output, int *int_output);
+
 static RecordStatus _get_node_record(PGconn *conn, char *sqlquery, t_node_info *node_info, bool init_defaults);
 static void _populate_node_record(PGresult *res, t_node_info *node_info, int row, bool init_defaults);
 
@@ -67,16 +71,19 @@ void
 log_db_error(PGconn *conn, const char *query_text, const char *fmt,...)
 {
 	va_list		ap;
+	char		buf[MAXLEN];
+	int			retval;
 
 	va_start(ap, fmt);
-
-	log_error(fmt, ap);
-
+	retval = vsnprintf(buf, MAXLEN, fmt, ap);
 	va_end(ap);
 
-	if (conn != NULL && PQstatus(conn) == CONNECTION_OK)
+	if (retval < MAXLEN)
+		log_error("%s", buf);
+
+	if (conn != NULL)
 	{
-		log_detail("%s", PQerrorMessage(conn));
+		log_detail("\n%s", PQerrorMessage(conn));
 	}
 
 	if (query_text != NULL)
@@ -190,13 +197,13 @@ _establish_db_connection(const char *conninfo, const bool exit_on_error, const b
 		{
 			if (log_notice)
 			{
-				log_notice(_("connection to database failed:\n  %s"),
-						   PQerrorMessage(conn));
+				log_notice(_("connection to database failed"));
+				log_detail("\n%s", PQerrorMessage(conn));
 			}
 			else
 			{
-				log_error(_("connection to database failed:\n  %s"),
-						  PQerrorMessage(conn));
+				log_error(_("connection to database failed"));
+				log_detail("\n%s", PQerrorMessage(conn));
 			}
 			log_detail(_("attempted to connect using:\n  %s"),
 					   connection_string);
@@ -287,8 +294,9 @@ establish_db_connection_by_params(t_conninfo_param_list *param_list,
 	/* Check to see that the backend connection was successfully made */
 	if ((PQstatus(conn) != CONNECTION_OK))
 	{
-		log_error(_("connection to database failed:\n	%s"),
-				  PQerrorMessage(conn));
+		log_error(_("connection to database failed"));
+		log_detail("\n%s", PQerrorMessage(conn));
+
 		if (exit_on_error)
 		{
 			PQfinish(conn);
@@ -338,7 +346,9 @@ is_superuser_connection(PGconn *conn, t_connection_user *userinfo)
 
 	if (userinfo != NULL)
 	{
-		strncpy(userinfo->username, current_user, MAXLEN);
+		snprintf(userinfo->username,
+				 sizeof(userinfo->username),
+				 "%s", current_user);
 		userinfo->is_superuser = is_superuser;
 	}
 
@@ -987,52 +997,37 @@ guc_set(PGconn *conn, const char *parameter, const char *op,
 	return retval;
 }
 
-/**
- * Just like guc_set except with an extra parameter containing the name of
- * the pg datatype so that the comparison can be done properly.
- */
-int
-guc_set_typed(PGconn *conn, const char *parameter, const char *op,
-			  const char *value, const char *datatype)
+
+bool
+get_pg_setting(PGconn *conn, const char *setting, char *output)
 {
-	PQExpBufferData query;
-	PGresult   *res = NULL;
-	int			retval = 1;
+	bool success = _get_pg_setting(conn, setting, output, NULL);
 
-	char	   *escaped_parameter = escape_string(conn, parameter);
-	char	   *escaped_value = escape_string(conn, value);
-
-	initPQExpBuffer(&query);
-	appendPQExpBuffer(&query,
-					  "SELECT true FROM pg_catalog.pg_settings "
-					  " WHERE name = '%s' AND setting::%s %s '%s'::%s",
-					  parameter, datatype, op, value, datatype);
-
-	log_verbose(LOG_DEBUG, "guc_set_typed():\n%s", query.data);
-
-	res = PQexec(conn, query.data);
-
-	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	if (success == true)
 	{
-		log_db_error(conn, query.data, _("guc_set_typed(): unable to execute query"));
-		retval = -1;
-	}
-	else if (PQntuples(res) == 0)
-	{
-		retval = 0;
+		log_verbose(LOG_DEBUG, _("get_pg_setting(): returned value is \"%s\""), output);
 	}
 
-	pfree(escaped_parameter);
-	pfree(escaped_value);
-	termPQExpBuffer(&query);
-	PQclear(res);
-
-	return retval;
+	return success;
 }
 
 
 bool
-get_pg_setting(PGconn *conn, const char *setting, char *output)
+get_pg_setting_int(PGconn *conn, const char *setting, int *output)
+{
+	bool success = _get_pg_setting(conn, setting, NULL, output);
+
+	if (success == true)
+	{
+		log_verbose(LOG_DEBUG, _("get_pg_setting_int(): returned value is \"%i\""), *output);
+	}
+
+	return success;
+}
+
+
+bool
+_get_pg_setting(PGconn *conn, const char *setting, char *str_output, int *int_output)
 {
 	PQExpBufferData query;
 	PGresult   *res = NULL;
@@ -1073,7 +1068,11 @@ get_pg_setting(PGconn *conn, const char *setting, char *output)
 	{
 		if (strcmp(PQgetvalue(res, i, 0), setting) == 0)
 		{
-			strncpy(output, PQgetvalue(res, i, 1), MAXLEN);
+			if (str_output != NULL)
+				snprintf(str_output, MAXLEN, "%s", PQgetvalue(res, i, 1));
+			else if (int_output != NULL)
+				*int_output = atoi(PQgetvalue(res, i, 1));
+
 			success = true;
 			break;
 		}
@@ -1084,10 +1083,6 @@ get_pg_setting(PGconn *conn, const char *setting, char *output)
 		}
 	}
 
-	if (success == true)
-	{
-		log_verbose(LOG_DEBUG, _("get_pg_setting(): returned value is \"%s\""), output);
-	}
 
 	termPQExpBuffer(&query);
 	PQclear(res);
@@ -1096,12 +1091,13 @@ get_pg_setting(PGconn *conn, const char *setting, char *output)
 }
 
 
+
 bool
 alter_system_int(PGconn *conn, const char *name, int value)
 {
 	PQExpBufferData query;
 	PGresult   *res = NULL;
-	bool		success = false;
+	bool		success = true;
 
 	initPQExpBuffer(&query);
 	appendPQExpBuffer(&query,
@@ -1117,7 +1113,6 @@ alter_system_int(PGconn *conn, const char *name, int value)
 		success = false;
 	}
 
-
 	termPQExpBuffer(&query);
 	PQclear(res);
 
@@ -1174,7 +1169,7 @@ get_cluster_size(PGconn *conn, char *size)
 	}
 	else
 	{
-		strncpy(size, PQgetvalue(res, 0, 0), MAXLEN);
+		snprintf(size, MAXLEN, "%s", PQgetvalue(res, 0, 0));
 	}
 
 	termPQExpBuffer(&query);
@@ -1222,7 +1217,7 @@ get_server_version(PGconn *conn, char *server_version_buf)
 		 * first space.
 		 */
 
-		strncpy(_server_version_buf, PQgetvalue(res, 0, 1), MAXVERSIONSTR);
+		snprintf(_server_version_buf, MAXVERSIONSTR, "%s", PQgetvalue(res, 0, 1));
 
 		for (i = 0; i < MAXVERSIONSTR; i++)
 		{
@@ -1349,7 +1344,8 @@ _get_primary_connection(PGconn *conn,
 
 		/* initialize with the values of the current node being processed */
 		node_id = atoi(PQgetvalue(res, i, 0));
-		strncpy(remote_conninfo, PQgetvalue(res, i, 1), MAXCONNINFO);
+		snprintf(remote_conninfo, MAXCONNINFO, "%s", PQgetvalue(res, i, 1));
+
 		log_verbose(LOG_INFO,
 					_("checking if node %i is primary"),
 					node_id);
@@ -1513,10 +1509,10 @@ get_ready_archive_files(PGconn *conn, const char *data_directory)
 	while ((arcdir_ent = readdir(arcdir)) != NULL)
 	{
 		struct stat statbuf;
-		char		file_path[MAXPGPATH] = "";
+		char		file_path[MAXPGPATH + sizeof(arcdir_ent->d_name)];
 		int			basenamelen = 0;
 
-		snprintf(file_path, MAXPGPATH,
+		snprintf(file_path, sizeof(file_path),
 				 "%s/%s",
 				 archive_status_dir,
 				 arcdir_ent->d_name);
@@ -1543,12 +1539,12 @@ get_ready_archive_files(PGconn *conn, const char *data_directory)
 }
 
 
-
 bool
 identify_system(PGconn *repl_conn, t_system_identification *identification)
 {
 	PGresult   *res = NULL;
 
+	/* semicolon required here */
 	res = PQexec(repl_conn, "IDENTIFY_SYSTEM;");
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK || !PQntuples(res))
@@ -1567,6 +1563,44 @@ identify_system(PGconn *repl_conn, t_system_identification *identification)
 	return true;
 }
 
+
+/*
+ * Return the system identifier by querying pg_control_system().
+ *
+ * Note there is a similar function in controldata.c ("get_system_identifier()")
+ * which reads the control file.
+ */
+uint64
+system_identifier(PGconn *conn)
+{
+	uint64		system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
+	PGresult   *res = NULL;
+
+	/*
+	 * pg_control_system() was introduced in PostgreSQL 9.6
+	 */
+	if (PQserverVersion(conn) < 90600)
+	{
+		return UNKNOWN_SYSTEM_IDENTIFIER;
+	}
+
+	res = PQexec(conn, "SELECT system_identifier FROM pg_catalog.pg_control_system()");
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, NULL, _("system_identifier(): unable to query pg_control_system()"));
+	}
+	else
+	{
+		system_identifier = atol(PQgetvalue(res, 0, 0));
+	}
+
+	PQclear(res);
+
+	return system_identifier;
+}
+
+
 TimeLineHistoryEntry *
 get_timeline_history(PGconn *repl_conn, TimeLineID tli)
 {
@@ -1664,6 +1698,46 @@ get_timeline_history(PGconn *repl_conn, TimeLineID tli)
 }
 
 
+bool
+get_child_nodes(PGconn *conn, int node_id, NodeInfoList *node_list)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+	bool		success = true;
+
+	initPQExpBuffer(&query);
+
+	appendPQExpBuffer(&query,
+					  "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
+					  "           n.slot_name, n.location, n.priority, n.active, n.config_file, "
+					  "           '' AS upstream_node_name, "
+					  "           CASE WHEN sr.application_name IS NULL THEN FALSE ELSE TRUE END AS attached "
+					  "      FROM repmgr.nodes n "
+					  " LEFT JOIN pg_catalog.pg_stat_replication sr "
+					  "        ON sr.application_name = n.node_name "
+					  "     WHERE n.upstream_node_id = %i ",
+					  node_id);
+
+		log_verbose(LOG_DEBUG, "get_active_sibling_node_records():\n%s", query.data);
+
+	res = PQexec(conn, query.data);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, query.data, _("get_active_sibling_records(): unable to execute query"));
+		success = false;
+	}
+
+	termPQExpBuffer(&query);
+
+	/* this will return an empty list if there was an error executing the query */
+	_populate_node_records(res, node_list);
+
+	PQclear(res);
+
+	return success;
+}
+
 /* =============================== */
 /* repmgrd shared memory functions */
 /* =============================== */
@@ -1932,6 +2006,61 @@ get_wal_receiver_pid(PGconn *conn)
 	return wal_receiver_pid;
 }
 
+
+int
+repmgrd_get_upstream_node_id(PGconn *conn)
+{
+	PGresult   *res = NULL;
+	int upstream_node_id = UNKNOWN_NODE_ID;
+
+	const char *sqlquery = "SELECT repmgr.get_upstream_node_id()";
+
+	res = PQexec(conn, sqlquery);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, sqlquery, _("repmgrd_get_upstream_node_id(): unable to execute query"));
+	}
+	else if (!PQgetisnull(res, 0, 0))
+	{
+		upstream_node_id = atoi(PQgetvalue(res, 0, 0));
+	}
+
+	PQclear(res);
+
+	return upstream_node_id;
+}
+
+
+bool
+repmgrd_set_upstream_node_id(PGconn *conn, int node_id)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+	bool		success = true;
+
+	initPQExpBuffer(&query);
+	appendPQExpBuffer(&query,
+					  " SELECT repmgr.set_upstream_node_id(%i) ",
+					  node_id);
+
+	log_verbose(LOG_DEBUG, "repmgrd_set_upstream_node_id():\n  %s", query.data);
+
+	res = PQexec(conn, query.data);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, query.data,
+					 _("repmgrd_set_upstream_node_id(): unable to set upstream node ID (provided value: %i)"), node_id);
+		success = false;
+	}
+
+	termPQExpBuffer(&query);
+	PQclear(res);
+
+	return success;
+}
+
 /* ================ */
 /* result functions */
 /* ================ */
@@ -1963,9 +2092,9 @@ get_repmgr_extension_status(PGconn *conn, t_extension_versions *extversions)
 	appendPQExpBufferStr(&query,
 						 "	  SELECT ae.name, e.extname, "
 						 "           ae.default_version, "
-						 "           (((ae.default_version::NUMERIC::INT) * 10000) + (ae.default_version::NUMERIC - ae.default_version::NUMERIC::INT) * 1000)::INT AS available, "
+						 "           (((FLOOR(ae.default_version::NUMERIC)::INT) * 10000) + (ae.default_version::NUMERIC - FLOOR(ae.default_version::NUMERIC)::INT) * 1000)::INT AS available, "
 						 "           ae.installed_version, "
-						 "           (((ae.installed_version::NUMERIC::INT) * 10000) + (ae.installed_version::NUMERIC - ae.installed_version::NUMERIC::INT) * 1000)::INT AS installed "
+						 "           (((FLOOR(ae.installed_version::NUMERIC)::INT) * 10000) + (ae.installed_version::NUMERIC - FLOOR(ae.installed_version::NUMERIC)::INT) * 1000)::INT AS installed "
 						 "     FROM pg_catalog.pg_available_extensions ae "
 						 "LEFT JOIN pg_catalog.pg_extension e "
 						 "       ON e.extname=ae.name "
@@ -1994,9 +2123,13 @@ get_repmgr_extension_status(PGconn *conn, t_extension_versions *extversions)
 		/* caller wants to know which versions are installed/available */
 		if (extversions != NULL)
 		{
-			strncpy(extversions->default_version, PQgetvalue(res, 0, 2), 7);
+			snprintf(extversions->default_version,
+					 sizeof(extversions->default_version),
+					 "%s", PQgetvalue(res, 0, 2));
 			extversions->default_version_num = available_version;
-			strncpy(extversions->installed_version, PQgetvalue(res, 0, 4), 7);
+			snprintf(extversions->installed_version,
+					 sizeof(extversions->installed_version),
+					 "%s", PQgetvalue(res, 0, 4));
 			extversions->installed_version_num = installed_version;
 		}
 
@@ -2197,17 +2330,26 @@ _populate_node_record(PGresult *res, t_node_info *node_info, int row, bool init_
 		node_info->upstream_node_id = atoi(PQgetvalue(res, row, 2));
 	}
 
-	strncpy(node_info->node_name, PQgetvalue(res, row, 3), MAXLEN);
-	strncpy(node_info->conninfo, PQgetvalue(res, row, 4), MAXLEN);
-	strncpy(node_info->repluser, PQgetvalue(res, row, 5), NAMEDATALEN);
-	strncpy(node_info->slot_name, PQgetvalue(res, row, 6), MAXLEN);
-	strncpy(node_info->location, PQgetvalue(res, row, 7), MAXLEN);
+	snprintf(node_info->node_name, sizeof(node_info->node_name), "%s", PQgetvalue(res, row, 3));
+	snprintf(node_info->conninfo, sizeof(node_info->conninfo), "%s", PQgetvalue(res, row, 4));
+	snprintf(node_info->repluser, sizeof(node_info->repluser), "%s", PQgetvalue(res, row, 5));
+	snprintf(node_info->slot_name, sizeof(node_info->slot_name), "%s", PQgetvalue(res, row, 6));
+	snprintf(node_info->location, sizeof(node_info->location), "%s", PQgetvalue(res, row, 7));
 	node_info->priority = atoi(PQgetvalue(res, row, 8));
 	node_info->active = atobool(PQgetvalue(res, row, 9));
-	strncpy(node_info->config_file, PQgetvalue(res, row, 10), MAXPGPATH);
+	snprintf(node_info->config_file, sizeof(node_info->config_file), "%s", PQgetvalue(res, row, 10));
 
-	/* This won't normally be set */
-	strncpy(node_info->upstream_node_name, PQgetvalue(res, row, 11), MAXLEN);
+	/* These are only set by certain queries */
+	snprintf(node_info->upstream_node_name, sizeof(node_info->upstream_node_name), "%s", PQgetvalue(res, row, 11));
+
+	if (PQgetisnull(res, row, 12))
+	{
+		node_info->attached = NODE_ATTACHED_UNKNOWN;
+	}
+	else
+	{
+		node_info->attached = atobool(PQgetvalue(res, row, 12)) ? NODE_ATTACHED : NODE_DETACHED;
+	}
 
 	/* Set remaining struct fields with default values */
 
@@ -2330,8 +2472,7 @@ get_node_record_with_upstream(PGconn *conn, int node_id, t_node_info *node_info)
 
 	initPQExpBuffer(&query);
 	appendPQExpBuffer(&query,
-					  "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
-					  "           n.slot_name, n.location, n.priority, n.active, n.config_file, un.node_name AS upstream_node_name "
+					  "    SELECT " REPMGR_NODES_COLUMNS_WITH_UPSTREAM
 					  "      FROM repmgr.nodes n "
 					  " LEFT JOIN repmgr.nodes un "
 					  "        ON un.node_id = n.upstream_node_id"
@@ -2374,7 +2515,7 @@ get_node_record_by_name(PGconn *conn, const char *node_name, t_node_info *node_i
 
 	if (record_status == RECORD_NOT_FOUND)
 	{
-		log_verbose(LOG_DEBUG, "get_node_record_by_name(): no record found for node %s",
+		log_verbose(LOG_DEBUG, "get_node_record_by_name(): no record found for node \"%s\"",
 					node_name);
 	}
 
@@ -2630,8 +2771,7 @@ get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list)
 	initPQExpBuffer(&query);
 
 	appendPQExpBufferStr(&query,
-						 "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
-						 "           n.slot_name, n.location, n.priority, n.active, n.config_file, un.node_name AS upstream_node_name "
+						 "    SELECT " REPMGR_NODES_COLUMNS_WITH_UPSTREAM
 						 "      FROM repmgr.nodes n "
 						 " LEFT JOIN repmgr.nodes un "
 						 "        ON un.node_id = n.upstream_node_id"
@@ -3255,6 +3395,10 @@ clear_node_info_list(NodeInfoList *nodes)
 	while (cell != NULL)
 	{
 		next_cell = cell->next;
+
+		if (cell->node_info->replication_info != NULL)
+			pfree(cell->node_info->replication_info);
+
 		pfree(cell->node_info);
 		pfree(cell);
 		cell = next_cell;
@@ -3461,11 +3605,15 @@ config_file_list_add(t_configfile_list *list, const char *file, const char *file
 	}
 
 
-	strncpy(list->files[list->entries]->filepath, file, MAXPGPATH);
+	snprintf(list->files[list->entries]->filepath,
+			 sizeof(list->files[list->entries]->filepath),
+			 "%s", file);
 	canonicalize_path(list->files[list->entries]->filepath);
 
+	snprintf(list->files[list->entries]->filename,
+			 sizeof(list->files[list->entries]->filename),
+			 "%s", filename);
 
-	strncpy(list->files[list->entries]->filename, filename, MAXPGPATH);
 	list->files[list->entries]->in_data_directory = in_data_dir;
 
 	list->entries++;
@@ -3545,13 +3693,10 @@ _create_event(PGconn *conn, t_configuration_options *options, int node_id, char
 	log_verbose(LOG_DEBUG, "_create_event(): event is \"%s\" for node %i", event, node_id);
 
 	/*
-	 * Only attempt to write a record if a connection handle was provided.
-	 * Also check that the repmgr schema has been properly initialised - if
-	 * not it means no configuration file was provided, which can happen with
-	 * e.g. `repmgr standby clone`, and we won't know which schema to write
-	 * to.
+	 * Only attempt to write a record if a connection handle was provided,
+	 * and the connection handle points to a node which is not in recovery.
 	 */
-	if (conn != NULL && PQstatus(conn) == CONNECTION_OK)
+	if (conn != NULL && PQstatus(conn) == CONNECTION_OK && get_recovery_type(conn) == RECTYPE_PRIMARY)
 	{
 		int			n_node_id = htonl(node_id);
 		char	   *t_successful = successful ? "TRUE" : "FALSE";
@@ -3605,7 +3750,7 @@ _create_event(PGconn *conn, t_configuration_options *options, int node_id, char
 		else
 		{
 			/* Store timestamp to send to the notification command */
-			strncpy(event_timestamp, PQgetvalue(res, 0, 0), MAXLEN);
+			snprintf(event_timestamp, MAXLEN, "%s", PQgetvalue(res, 0, 0));
 		}
 
 		termPQExpBuffer(&query);
@@ -4040,8 +4185,12 @@ get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record)
 	}
 	else
 	{
-		strncpy(record->slot_name, PQgetvalue(res, 0, 0), MAXLEN);
-		strncpy(record->slot_type, PQgetvalue(res, 0, 1), MAXLEN);
+		snprintf(record->slot_name,
+				 sizeof(record->slot_name),
+				 "%s", PQgetvalue(res, 0, 0));
+		snprintf(record->slot_type,
+				 sizeof(record->slot_type),
+				 "%s", PQgetvalue(res, 0, 1));
 		record->active = atobool(PQgetvalue(res, 0, 2));
 	}
 
@@ -4172,7 +4321,8 @@ get_tablespace_name_by_location(PGconn *conn, const char *location, char *name)
 	}
 	else
 	{
-		strncpy(name, PQgetvalue(res, 0, 0), MAXLEN);
+		snprintf(name, MAXLEN,
+				 "%s", PQgetvalue(res, 0, 0));
 	}
 
 	termPQExpBuffer(&query);
@@ -4206,7 +4356,7 @@ cancel_query(PGconn *conn, int timeout)
 	if (PQcancel(pgcancel, errbuf, ERRBUFF_SIZE) == 0)
 	{
 		log_warning(_("unable to cancel current query"));
-		log_detail("%s", errbuf);
+		log_detail("\n%s", errbuf);
 		PQfreeCancel(pgcancel);
 		return false;
 	}
@@ -4236,7 +4386,7 @@ wait_connection_availability(PGconn *conn, int timeout)
 	long long	timeout_ms;
 
 	/* calculate timeout in microseconds */
-	timeout_ms = timeout * 1000000;
+	timeout_ms = (long long) timeout * 1000000;
 
 	while (timeout_ms > 0)
 	{
@@ -4295,13 +4445,33 @@ wait_connection_availability(PGconn *conn, int timeout)
 
 bool
 is_server_available(const char *conninfo)
+{
+	return _is_server_available(conninfo, false);
+}
+
+
+bool
+is_server_available_quiet(const char *conninfo)
+{
+	return _is_server_available(conninfo, true);
+}
+
+
+static bool
+_is_server_available(const char *conninfo, bool quiet)
 {
 	PGPing		status = PQping(conninfo);
 
-	log_verbose(LOG_DEBUG, "is_server_available(): ping status for %s is %i", conninfo, (int)status);
+	log_verbose(LOG_DEBUG, "is_server_available(): ping status for \"%s\" is %s", conninfo, print_pqping_status(status));
 	if (status == PQPING_OK)
 		return true;
 
+	if (quiet == false)
+	{
+		log_warning(_("unable to ping \"%s\""), conninfo);
+		log_detail(_("PQping() returned \"%s\""), print_pqping_status(status));
+	}
+
 	return false;
 }
 
@@ -4314,10 +4484,17 @@ is_server_available_params(t_conninfo_param_list *param_list)
 									  false);
 
 	/* deparsing the param_list adds overhead, so only do it if needed  */
-	if (log_level == LOG_DEBUG)
+	if (log_level == LOG_DEBUG || status != PQPING_OK)
 	{
 		char *conninfo_str = param_list_to_string(param_list);
-		log_verbose(LOG_DEBUG, "is_server_available_params(): ping status for %s is %i", conninfo_str, (int)status);
+		log_verbose(LOG_DEBUG, "is_server_available_params(): ping status for \"%s\" is %s", conninfo_str, print_pqping_status(status));
+
+		if (status != PQPING_OK)
+		{
+			log_warning(_("unable to ping \"%s\""), conninfo_str);
+			log_detail(_("PQping() returned \"%s\""), print_pqping_status(status));
+		}
+
 		pfree(conninfo_str);
 	}
 
@@ -4355,7 +4532,7 @@ connection_ping_reconnect(PGconn *conn)
 	if (PQstatus(conn) != CONNECTION_OK)
 	{
 		log_warning(_("connection error, attempting to reset"));
-		log_detail("%s", PQerrorMessage(conn));
+		log_detail("\n%s", PQerrorMessage(conn));
 		PQreset(conn);
 		ping_result = connection_ping(conn);
 	}
@@ -4887,6 +5064,8 @@ void
 init_replication_info(ReplInfo *replication_info)
 {
 	memset(replication_info->current_timestamp, 0, sizeof(replication_info->current_timestamp));
+	replication_info->in_recovery = false;
+	replication_info->timeline_id = UNKNOWN_TIMELINE_ID;
 	replication_info->last_wal_receive_lsn = InvalidXLogRecPtr;
 	replication_info->last_wal_replay_lsn = InvalidXLogRecPtr;
 	memset(replication_info->last_xact_replay_timestamp, 0, sizeof(replication_info->last_xact_replay_timestamp));
@@ -4907,6 +5086,7 @@ get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replicatio
 	initPQExpBuffer(&query);
 	appendPQExpBufferStr(&query,
 						 " SELECT ts, "
+						 "        in_recovery, "
 						 "        last_wal_receive_lsn, "
 						 "        last_wal_replay_lsn, "
 						 "        last_xact_replay_timestamp, "
@@ -4921,9 +5101,11 @@ get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replicatio
 						 "        END AS replication_lag_time, "
 						 "        last_wal_receive_lsn >= last_wal_replay_lsn AS receiving_streamed_wal, "
 						 "        wal_replay_paused, "
-						 "        upstream_last_seen "
+						 "        upstream_last_seen, "
+						 "        upstream_node_id "
 						 "   FROM ( "
 						 " SELECT CURRENT_TIMESTAMP AS ts, "
+						 "        pg_catalog.pg_is_in_recovery() AS in_recovery, "
 						 "        pg_catalog.pg_last_xact_replay_timestamp() AS last_xact_replay_timestamp, ");
 
 
@@ -4960,10 +5142,12 @@ get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replicatio
 							 "        END AS wal_replay_paused, ");
 	}
 
+	/* Add information about upstream node from shared memory */
 	if (node_type == WITNESS)
 	{
 		appendPQExpBufferStr(&query,
-							 "        repmgr.get_upstream_last_seen() AS upstream_last_seen");
+							 "        repmgr.get_upstream_last_seen() AS upstream_last_seen, "
+							 "        repmgr.get_upstream_node_id() AS upstream_node_id ");
 	}
 	else
 	{
@@ -4971,7 +5155,12 @@ get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replicatio
 							 "        CASE WHEN pg_catalog.pg_is_in_recovery() IS FALSE "
 							 "          THEN -1 "
 							 "          ELSE repmgr.get_upstream_last_seen() "
-							 "        END AS upstream_last_seen ");
+							 "        END AS upstream_last_seen, ");
+		appendPQExpBufferStr(&query,
+							 "        CASE WHEN pg_catalog.pg_is_in_recovery() IS FALSE "
+							 "          THEN -1 "
+							 "          ELSE repmgr.get_upstream_node_id() "
+							 "        END AS upstream_node_id ");
 	}
 
 	appendPQExpBufferStr(&query,
@@ -4989,14 +5178,20 @@ get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replicatio
 	}
 	else
 	{
-		strncpy(replication_info->current_timestamp, PQgetvalue(res, 0, 0), MAXLEN);
-		replication_info->last_wal_receive_lsn = parse_lsn(PQgetvalue(res, 0, 1));
-		replication_info->last_wal_replay_lsn = parse_lsn(PQgetvalue(res, 0, 2));
-		strncpy(replication_info->last_xact_replay_timestamp, PQgetvalue(res, 0, 3), MAXLEN);
-		replication_info->replication_lag_time = atoi(PQgetvalue(res, 0, 4));
-		replication_info->receiving_streamed_wal = atobool(PQgetvalue(res, 0, 5));
-		replication_info->wal_replay_paused = atobool(PQgetvalue(res, 0, 6));
-		replication_info->upstream_last_seen = atoi(PQgetvalue(res, 0, 7));
+		snprintf(replication_info->current_timestamp,
+				 sizeof(replication_info->current_timestamp),
+				 "%s", PQgetvalue(res, 0, 0));
+		replication_info->in_recovery = atobool(PQgetvalue(res, 0, 1));
+		replication_info->last_wal_receive_lsn = parse_lsn(PQgetvalue(res, 0, 2));
+		replication_info->last_wal_replay_lsn = parse_lsn(PQgetvalue(res, 0, 3));
+		snprintf(replication_info->last_xact_replay_timestamp,
+				 sizeof(replication_info->last_xact_replay_timestamp),
+				 "%s", PQgetvalue(res, 0, 4));
+		replication_info->replication_lag_time = atoi(PQgetvalue(res, 0, 5));
+		replication_info->receiving_streamed_wal = atobool(PQgetvalue(res, 0, 6));
+		replication_info->wal_replay_paused = atobool(PQgetvalue(res, 0, 7));
+		replication_info->upstream_last_seen = atoi(PQgetvalue(res, 0, 8));
+		replication_info->upstream_node_id = atoi(PQgetvalue(res, 0, 9));
 	}
 
 	termPQExpBuffer(&query);
@@ -5042,13 +5237,12 @@ get_replication_lag_seconds(PGconn *conn)
 		log_warning("%s", PQerrorMessage(conn));
 		PQclear(res);
 
-		/* XXX magic number */
-		return -1;
+		return UNKNOWN_REPLICATION_LAG;
 	}
 
 	if (!PQntuples(res))
 	{
-		return -1;
+		return UNKNOWN_REPLICATION_LAG;
 	}
 
 	lag_seconds = atoi(PQgetvalue(res, 0, 0));
@@ -5058,6 +5252,38 @@ get_replication_lag_seconds(PGconn *conn)
 }
 
 
+
+TimeLineID
+get_node_timeline(PGconn *conn)
+{
+	TimeLineID timeline_id  = UNKNOWN_TIMELINE_ID;
+	PGresult   *res = NULL;
+
+	/*
+	 * PG_control_checkpoint() was introduced in PostgreSQL 9.6
+	 */
+	if (PQserverVersion(conn) < 90600)
+	{
+		return UNKNOWN_TIMELINE_ID;
+	}
+
+	res = PQexec(conn, "SELECT timeline_id FROM pg_catalog.pg_control_checkpoint()");
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, NULL, _("get_node_timeline(): unable to query pg_control_system()"));
+	}
+	else
+	{
+		timeline_id = atoi(PQgetvalue(res, 0, 0));
+	}
+
+	PQclear(res);
+
+	return timeline_id;
+}
+
+
 void
 get_node_replication_stats(PGconn *conn, t_node_info *node_info)
 {
@@ -5123,7 +5349,7 @@ get_node_replication_stats(PGconn *conn, t_node_info *node_info)
 }
 
 
-bool
+NodeAttached
 is_downstream_node_attached(PGconn *conn, char *node_name)
 {
 	PQExpBufferData query;
@@ -5133,7 +5359,8 @@ is_downstream_node_attached(PGconn *conn, char *node_name)
 	initPQExpBuffer(&query);
 
 	appendPQExpBuffer(&query,
-					  " SELECT pg_catalog.count(*) FROM pg_catalog.pg_stat_replication "
+					  " SELECT pg_catalog.count(*) "
+					  "   FROM pg_catalog.pg_stat_replication "
 					  "  WHERE application_name = '%s'",
 					  node_name);
 
@@ -5148,7 +5375,7 @@ is_downstream_node_attached(PGconn *conn, char *node_name)
 		termPQExpBuffer(&query);
 		PQclear(res);
 
-		return false;
+		return NODE_ATTACHED_UNKNOWN;
 	}
 
 	if (PQntuples(res) != 1)
@@ -5158,7 +5385,7 @@ is_downstream_node_attached(PGconn *conn, char *node_name)
 		termPQExpBuffer(&query);
 		PQclear(res);
 
-		return false;
+		return NODE_ATTACHED_UNKNOWN;
 	}
 
 	c = atoi(PQgetvalue(res, 0, 0));
@@ -5170,27 +5397,28 @@ is_downstream_node_attached(PGconn *conn, char *node_name)
 	{
 		log_verbose(LOG_WARNING, _("node \"%s\" not found in \"pg_stat_replication\""), node_name);
 
-		return false;
+		return NODE_DETACHED;
 	}
 
 	if (c > 1)
 		log_verbose(LOG_WARNING, _("multiple entries with \"application_name\" set to  \"%s\" found in \"pg_stat_replication\""),
 					node_name);
 
-	return true;
+	return NODE_ATTACHED;
 }
 
 
 void
-set_upstream_last_seen(PGconn *conn)
+set_upstream_last_seen(PGconn *conn, int upstream_node_id)
 {
 	PQExpBufferData query;
 	PGresult   *res = NULL;
 
 	initPQExpBuffer(&query);
 
-	appendPQExpBufferStr(&query,
-						 "SELECT repmgr.set_upstream_last_seen()");
+	appendPQExpBuffer(&query,
+					  "SELECT repmgr.set_upstream_last_seen(%i)",
+					  upstream_node_id);
 
 	res = PQexec(conn, query.data);
 
@@ -5506,7 +5734,9 @@ get_default_bdr_replication_set(PGconn *conn)
 		/* For BDR2, we use a custom replication set */
 		namelen = strlen(BDR2_REPLICATION_SET_NAME);
 		default_replication_set = pg_malloc0(namelen + 1);
-		strncpy(default_replication_set, BDR2_REPLICATION_SET_NAME, namelen);
+		snprintf(default_replication_set,
+				 namelen + 1,
+				 "%s", BDR2_REPLICATION_SET_NAME);
 
 		return default_replication_set;
 	}
@@ -5536,7 +5766,9 @@ get_default_bdr_replication_set(PGconn *conn)
 	namelen = strlen(PQgetvalue(res, 0, 0));
 	default_replication_set = pg_malloc0(namelen + 1);
 
-	strncpy(default_replication_set, PQgetvalue(res, 0, 0), namelen);
+	snprintf(default_replication_set,
+			 namelen,
+			 "%s", PQgetvalue(res, 0, 0));
 
 	PQclear(res);
 
@@ -5757,7 +5989,9 @@ get_bdr_other_node_name(PGconn *conn, int node_id, char *node_name)
 
 	if (PQresultStatus(res) == PGRES_TUPLES_OK)
 	{
-		strncpy(node_name, PQgetvalue(res, 0, 0), MAXLEN);
+		snprintf(node_name,
+				 NAMEDATALEN,
+				 "%s", PQgetvalue(res, 0, 0));
 	}
 	else
 	{
@@ -5940,12 +6174,12 @@ _populate_bdr_node_records(PGresult *res, BdrNodeInfoList *node_list)
 static void
 _populate_bdr_node_record(PGresult *res, t_bdr_node_info *node_info, int row)
 {
-	strncpy(node_info->node_sysid, PQgetvalue(res, row, 0), MAXLEN);
+	snprintf(node_info->node_sysid, sizeof(node_info->node_sysid), "%s", PQgetvalue(res, row, 0));
 	node_info->node_timeline = atoi(PQgetvalue(res, row, 1));
 	node_info->node_dboid = atoi(PQgetvalue(res, row, 2));
-	strncpy(node_info->node_name, PQgetvalue(res, row, 3), MAXLEN);
-	strncpy(node_info->node_local_dsn, PQgetvalue(res, row, 4), MAXLEN);
-	strncpy(node_info->peer_state_name, PQgetvalue(res, row, 5), MAXLEN);
+	snprintf(node_info->node_name, sizeof(node_info->node_name), "%s", PQgetvalue(res, row, 3));
+	snprintf(node_info->node_local_dsn, sizeof(node_info->node_local_dsn), "%s", PQgetvalue(res, row, 4));
+	snprintf(node_info->peer_state_name, sizeof(node_info->peer_state_name), "%s", PQgetvalue(res, row, 5));
 }
 
 

dbutils.h

@@ -29,7 +29,38 @@
 #include "strutil.h"
 #include "voting.h"
 
-#define REPMGR_NODES_COLUMNS "n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, n.slot_name, n.location, n.priority, n.active, n.config_file, '' AS upstream_node_name "
+#define REPMGR_NODES_COLUMNS \
+	"n.node_id, " \
+	"n.type, " \
+	"n.upstream_node_id, " \
+	"n.node_name,  " \
+	"n.conninfo, " \
+	"n.repluser, " \
+	"n.slot_name, " \
+	"n.location, " \
+	"n.priority, " \
+	"n.active, " \
+	"n.config_file, " \
+	"'' AS upstream_node_name, " \
+	"NULL AS attached "
+
+#define REPMGR_NODES_COLUMNS_WITH_UPSTREAM \
+	"n.node_id, " \
+	"n.type, " \
+	"n.upstream_node_id, " \
+	"n.node_name, " \
+	"n.conninfo, " \
+	"n.repluser, " \
+	"n.slot_name, " \
+	"n.location, " \
+	"n.priority, " \
+	"n.active, "\
+	"n.config_file, " \
+	"un.node_name AS upstream_node_name, " \
+	"NULL AS attached "
+
+
+
 #define BDR2_NODES_COLUMNS "node_sysid, node_timeline, node_dboid, node_name, node_local_dsn, ''"
 #define BDR3_NODES_COLUMNS "ns.node_id, 0, 0, ns.node_name, ns.interface_connstr, ns.peer_state_name"
 
@@ -92,6 +123,13 @@ typedef enum
 	CONN_ERROR
 } ConnectionStatus;
 
+typedef enum
+{
+	NODE_ATTACHED_UNKNOWN = -1,
+	NODE_DETACHED,
+	NODE_ATTACHED
+} NodeAttached;
+
 typedef enum
 {
 	SLOT_UNKNOWN = -1,
@@ -107,6 +145,7 @@ typedef enum
 } BackupState;
 
 
+
 /*
  * Struct to store extension version information
  */
@@ -125,8 +164,28 @@ typedef struct s_extension_versions {
 	UNKNOWN_SERVER_VERSION_NUM \
 }
 
+
+typedef struct
+{
+	char		current_timestamp[MAXLEN];
+	bool		in_recovery;
+	TimeLineID	timeline_id;
+	XLogRecPtr	last_wal_receive_lsn;
+	XLogRecPtr	last_wal_replay_lsn;
+	char		last_xact_replay_timestamp[MAXLEN];
+	int			replication_lag_time;
+	bool		receiving_streamed_wal;
+	bool		wal_replay_paused;
+	int			upstream_last_seen;
+	int			upstream_node_id;
+} ReplInfo;
+
 /*
- * Struct to store node information
+ * Struct to store node information.
+ *
+ * The first section represents the contents of the "repmgr.nodes"
+ * table; subsequent section contain information collated in
+ * various contexts.
  */
 typedef struct s_node_info
 {
@@ -134,8 +193,8 @@ typedef struct s_node_info
 	int			node_id;
 	int			upstream_node_id;
 	t_server_type type;
-	char		node_name[MAXLEN];
-	char		upstream_node_name[MAXLEN];
+	char		node_name[NAMEDATALEN];
+	char		upstream_node_name[NAMEDATALEN];
 	char		conninfo[MAXLEN];
 	char		repluser[NAMEDATALEN];
 	char		location[MAXLEN];
@@ -152,7 +211,7 @@ typedef struct s_node_info
 	/* for ad-hoc use e.g. when working with a list of nodes */
 	char		details[MAXLEN];
 	bool		reachable;
-	bool		attached;
+	NodeAttached attached;
 	/* various statistics */
 	int			max_wal_senders;
 	int			attached_wal_receivers;
@@ -160,6 +219,8 @@ typedef struct s_node_info
 	int			total_replication_slots;
 	int			active_replication_slots;
 	int			inactive_replication_slots;
+	/* replication info */
+	ReplInfo   *replication_info;
 } t_node_info;
 
 
@@ -186,7 +247,8 @@ typedef struct s_node_info
 	/* for ad-hoc use e.g. when working with a list of nodes */ \
 	"", true, true,	\
 	/* various statistics */ \
-	-1, -1, -1, -1, -1, -1					\
+	-1, -1, -1, -1, -1, -1,	\
+	NULL \
 }
 
 
@@ -299,17 +361,7 @@ typedef struct BdrNodeInfoList
 	0 \
 }
 
-typedef struct
-{
-	char		current_timestamp[MAXLEN];
-	XLogRecPtr	last_wal_receive_lsn;
-	XLogRecPtr	last_wal_replay_lsn;
-	char		last_xact_replay_timestamp[MAXLEN];
-	int			replication_lag_time;
-	bool		receiving_streamed_wal;
-	bool		wal_replay_paused;
-	int			upstream_last_seen;
-} ReplInfo;
+
 
 typedef struct
 {
@@ -413,8 +465,8 @@ bool		rollback_transaction(PGconn *conn);
 bool		set_config(PGconn *conn, const char *config_param, const char *config_value);
 bool		set_config_bool(PGconn *conn, const char *config_param, bool state);
 int		    guc_set(PGconn *conn, const char *parameter, const char *op, const char *value);
-int			guc_set_typed(PGconn *conn, const char *parameter, const char *op, const char *value, const char *datatype);
 bool		get_pg_setting(PGconn *conn, const char *setting, char *output);
+bool		get_pg_setting_int(PGconn *conn, const char *setting, int *output);
 bool		alter_system_int(PGconn *conn, const char *name, int value);
 bool		pg_reload_conf(PGconn *conn);
 
@@ -426,6 +478,7 @@ RecoveryType get_recovery_type(PGconn *conn);
 int			get_primary_node_id(PGconn *conn);
 int			get_ready_archive_files(PGconn *conn, const char *data_directory);
 bool		identify_system(PGconn *repl_conn, t_system_identification *identification);
+uint64		system_identifier(PGconn *conn);
 TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
 
 /* repmgrd shared memory functions */
@@ -439,6 +492,8 @@ bool		repmgrd_is_running(PGconn *conn);
 bool		repmgrd_is_paused(PGconn *conn);
 bool		repmgrd_pause(PGconn *conn, bool pause);
 pid_t		get_wal_receiver_pid(PGconn *conn);
+int			repmgrd_get_upstream_node_id(PGconn *conn);
+bool		repmgrd_set_upstream_node_id(PGconn *conn, int node_id);
 
 /* extension functions */
 ExtensionStatus get_repmgr_extension_status(PGconn *conn, t_extension_versions *extversions);
@@ -467,6 +522,7 @@ bool		get_primary_node_record(PGconn *conn, t_node_info *node_info);
 bool		get_all_node_records(PGconn *conn, NodeInfoList *node_list);
 void		get_downstream_node_records(PGconn *conn, int node_id, NodeInfoList *nodes);
 void		get_active_sibling_node_records(PGconn *conn, int node_id, int upstream_node_id, NodeInfoList *node_list);
+bool		get_child_nodes(PGconn *conn, int node_id, NodeInfoList *node_list);
 void		get_node_records_by_priority(PGconn *conn, NodeInfoList *node_list);
 bool		get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list);
 bool		get_downstream_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *noede_list);
@@ -517,6 +573,7 @@ int			wait_connection_availability(PGconn *conn, int timeout);
 
 /* node availability functions */
 bool		is_server_available(const char *conninfo);
+bool		is_server_available_quiet(const char *conninfo);
 bool		is_server_available_params(t_conninfo_param_list *param_list);
 ExecStatusType	connection_ping(PGconn *conn);
 ExecStatusType	connection_ping_reconnect(PGconn *conn);
@@ -556,10 +613,12 @@ XLogRecPtr	get_last_wal_receive_location(PGconn *conn);
 void		init_replication_info(ReplInfo *replication_info);
 bool		get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replication_info);
 int			get_replication_lag_seconds(PGconn *conn);
+TimeLineID	get_node_timeline(PGconn *conn);
 void		get_node_replication_stats(PGconn *conn, t_node_info *node_info);
-bool		is_downstream_node_attached(PGconn *conn, char *node_name);
-void		set_upstream_last_seen(PGconn *conn);
+NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name);
+void		set_upstream_last_seen(PGconn *conn, int upstream_node_id);
 int			get_upstream_last_seen(PGconn *conn, t_server_type node_type);
+
 bool		is_wal_replay_paused(PGconn *conn, bool check_pending_wal);
 
 /* BDR functions */

dirutil.c

@@ -276,6 +276,8 @@ is_pg_running(const char *path)
 			log_warning(_("invalid data in PostgreSQL PID file \"%s\""), path);
 		}
 
+		fclose(pidf);
+
 		return PG_DIR_NOT_RUNNING;
 	}
 
@@ -334,6 +336,15 @@ create_pg_dir(const char *path, bool force)
 				{
 					log_notice(_("-F/--force provided - deleting existing data directory \"%s\""), path);
 					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+
+					/* recreate the directory ourselves to ensure permissions are correct */
+					if (!create_dir(path))
+					{
+						log_error(_("unable to create directory \"%s\"..."),
+								  path);
+						return false;
+					}
+
 					return true;
 				}
 
@@ -345,6 +356,15 @@ create_pg_dir(const char *path, bool force)
 				{
 					log_notice(_("deleting existing directory \"%s\""), path);
 					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+
+					/* recreate the directory ourselves to ensure permissions are correct */
+					if (!create_dir(path))
+					{
+						log_error(_("unable to create directory \"%s\"..."),
+								  path);
+						return false;
+					}
+
 					return true;
 				}
 				return false;

doc/.gitignore

@@ -1,7 +1,9 @@
 HTML.index
-bookindex.sgml
+bookindex.xml
 html-stamp
 html/
-nochunks.dsl
 repmgr.html
-version.sgml
+version.xml
+*.fo
+*.pdf
+*.sgml

doc/Makefile

@@ -0,0 +1,101 @@
+# Make "html" the default target, since that is what most people tend
+# to want to use.
+html:
+
+all: html
+
+subdir = doc
+repmgr_top_builddir = ..
+include $(repmgr_top_builddir)/Makefile.global
+
+XMLINCLUDE = --path .
+
+ifndef XMLLINT
+XMLLINT = $(missing) xmllint
+endif
+
+ifndef XSLTPROC
+XSLTPROC = $(missing) xsltproc
+endif
+
+ifndef FOP
+FOP = $(missing) fop
+endif
+
+override XSLTPROCFLAGS += --stringparam repmgr.version '$(REPMGR_VERSION)'
+
+GENERATED_XML = version.xml
+ALLXML := $(wildcard $(srcdir)/*.xml) $(GENERATED_XML)
+
+
+version.xml: $(repmgr_top_builddir)/repmgr_version.h
+	{ \
+	  echo "<!ENTITY repmgrversion \"$(REPMGR_VERSION)\">"; \
+	} > $@
+
+##
+## HTML
+##
+
+
+html: html-stamp
+
+html-stamp: stylesheet.xsl repmgr.xml $(ALLXML)
+	$(XMLLINT) $(XMLINCLUDE) --noout --valid $(word 2,$^)
+	$(XSLTPROC) $(XMLINCLUDE) $(XSLTPROCFLAGS) $(XSLTPROC_HTML_FLAGS) $(wordlist 1,2,$^)
+	cp $(srcdir)/stylesheet.css  $(srcdir)/website-docs.css html/
+	touch $@
+
+# single-page HTML
+repmgr.html: stylesheet-html-nochunk.xsl repmgr.xml $(ALLXML)
+	$(XMLLINT) $(XMLINCLUDE) --noout --valid $(word 2,$^)
+	$(XSLTPROC) $(XMLINCLUDE) $(XSLTPROCFLAGS) $(XSLTPROC_HTML_FLAGS) -o $@ $(wordlist 1,2,$^)
+
+
+zip: html
+	cp -r html repmgr-docs-$(REPMGR_VERSION)
+	zip -r repmgr-docs-$(REPMGR_VERSION).zip repmgr-docs-$(REPMGR_VERSION)
+	rm -rf repmgr-docs-$(REPMGR_VERSION)
+
+##
+## Print
+##
+
+repmgr.pdf:
+	$(error Invalid target; use repmgr-A4.pdf or repmgr-US.pdf as targets)
+
+# Standard paper size
+
+repmgr-A4.fo: stylesheet-fo.xsl repmgr.xml $(ALLXML)
+	$(XMLLINT) $(XMLINCLUDE) --noout --valid $(word 2,$^)
+	$(XSLTPROC) $(XMLINCLUDE) $(XSLTPROCFLAGS) --stringparam paper.type A4 -o $@ $(wordlist 1,2,$^)
+
+repmgr-A4.pdf: repmgr-A4.fo
+	$(FOP) -fo $< -pdf $@
+
+# North American paper size
+
+repmgr-US.fo: stylesheet-fo.xsl repmgr.xml $(ALLXML)
+	$(XMLLINT) $(XMLINCLUDE) --noout --valid $(word 2,$^)
+	$(XSLTPROC) $(XMLINCLUDE) $(XSLTPROCFLAGS) --stringparam paper.type USletter -o $@ $(wordlist 1,2,$^)
+
+repmgr-US.pdf: repmgr-US.fo
+	$(FOP) -fo $< -pdf $@
+
+
+install: html
+	@$(MKDIR_P) $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
+	@$(INSTALL_DATA) $(wildcard html/*.html) $(wildcard html/*.css) $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
+	@echo Installed docs to $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
+
+clean:
+	rm -f html-stamp
+	rm -f HTML.index $(GENERATED_XML)
+	rm -f repmgr.html
+	rm -f repmgr-A4.pdf
+	rm -f repmgr-US.pdf
+
+maintainer-clean:
+	rm -rf html
+
+.PHONY: html

doc/Makefile.in

@@ -1,76 +0,0 @@
-repmgr_subdir = doc
-repmgr_top_builddir = ..
-include $(repmgr_top_builddir)/Makefile.global
-
-ifndef JADE
-JADE = $(missing) jade
-endif
-
-SGMLINCLUDE = -D . -D ${srcdir}
-
-SPFLAGS += -wall -wno-unused-param -wno-empty -wfully-tagged
-
-JADE.html.call = $(JADE) $(JADEFLAGS) $(SPFLAGS) $(SGMLINCLUDE) $(CATALOG) -t sgml -i output-html
-
-ALLSGML := $(wildcard $(srcdir)/*.sgml)
-# to build bookindex
-ALMOSTALLSGML := $(filter-out %bookindex.sgml,$(ALLSGML))
-GENERATED_SGML = version.sgml bookindex.sgml
-
-Makefile: Makefile.in
-	cd $(repmgr_top_builddir) && ./config.status doc/Makefile
-
-all: html
-
-html: html-stamp
-
-html-stamp: repmgr.sgml $(ALLSGML) $(GENERATED_SGML) stylesheet.dsl website-docs.css
-	$(MKDIR_P) html
-	$(JADE.html.call) -d stylesheet.dsl -i include-index $<
-	cp $(srcdir)/stylesheet.css $(srcdir)/website-docs.css html/
-	touch $@
-
-repmgr.html: repmgr.sgml $(ALLSGML) $(GENERATED_SGML) stylesheet.dsl website-docs.css
-	sed '/html-index-filename/a\
-(define nochunks  #t)' <stylesheet.dsl >nochunks.dsl
-	$(JADE.html.call) -d nochunks.dsl -i include-index $< >repmgr.html
-
-version.sgml: ${repmgr_top_builddir}/repmgr_version.h
-	{ \
-	  echo "<!ENTITY repmgrversion \"$(REPMGR_VERSION)\">"; \
-	} > $@
-
-HTML.index: repmgr.sgml $(ALMOSTALLSGML) stylesheet.dsl
-	@$(MKDIR_P) html
-	$(JADE.html.call) -d stylesheet.dsl -V html-index $<
-
-website-docs.css:
-	@$(MKDIR_P) html
-	curl http://www.postgresql.org/media/css/docs.css > ${srcdir}/website-docs.css
-
-bookindex.sgml: HTML.index
-ifdef COLLATEINDEX
-	LC_ALL=C $(PERL) $(COLLATEINDEX) -f -g -i 'bookindex' -o $@ $<
-else
-	@$(missing) collateindex.pl $< $@
-endif
-
-clean:
-	rm -f html-stamp
-	rm -f HTML.index $(GENERATED_SGML)
-
-maintainer-clean:
-	rm -rf html
-	rm -f Makefile
-
-zip: html
-	cp -r html repmgr-docs-$(REPMGR_VERSION)
-	zip -r repmgr-docs-$(REPMGR_VERSION).zip repmgr-docs-$(REPMGR_VERSION)
-	rm -rf repmgr-docs-$(REPMGR_VERSION)
-
-install: html
-	@$(MKDIR_P) $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
-	@$(INSTALL_DATA) $(wildcard html/*.html) $(wildcard html/*.css) $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
-	@echo Installed docs to $(DESTDIR)$(docdir)/$(docmoduledir)/repmgr
-
-.PHONY: html all

doc/appendix-faq.xml

@@ -1,9 +1,10 @@
 <appendix id="appendix-faq" xreflabel="FAQ">
- <indexterm>
-  <primary>FAQ (Frequently Asked Questions)</primary>
- </indexterm>
 
- <title>FAQ (Frequently Asked Questions)</title>
+  <title>FAQ (Frequently Asked Questions)</title>
+
+  <indexterm>
+   <primary>FAQ (Frequently Asked Questions)</primary>
+  </indexterm>
 
  <sect1 id="faq-general" xreflabel="General">
   <title>General</title>
@@ -19,7 +20,7 @@
      <para>
       &repmgr; 3.x builds on the improved replication facilities added
       in PostgreSQL 9.3, as well as improved automated failover support
-      via <application>repmgrd</application>, and is not compatible with PostgreSQL 9.2
+      via &repmgrd;, and is not compatible with PostgreSQL 9.2
       and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
       series is no longer maintained.
      </para>
@@ -125,7 +126,7 @@
   <sect2 id="faq-old-packages">
    <title>How can I obtain old versions of &repmgr; packages?</title>
    <para>
-     See appendix <xref linkend="packages-old-versions"> for details.
+     See appendix <xref linkend="packages-old-versions"/> for details.
    </para>
   </sect2>
 
@@ -135,7 +136,7 @@
       No.
     </para>
     <para>
-     &repmgr; (together with <application>repmgrd</application>) assists with
+     &repmgr; (together with &repmgrd;) assists with
      <emphasis>managing</emphasis> replication. It does not actually perform replication, which
      is part of the core PostgreSQL functionality.
     </para>
@@ -152,8 +153,8 @@
    <title>Does it matter if different &repmgr; versions are present in the replication cluster?</title>
    <para>
      Yes. If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x) are present,
-     &repmgr; (in particular <application>repmgrd</application>)
-     may not run, or run properly, or in the worst case (if different <application>repmgrd</application>
+     &repmgr; (in particular &repmgrd;)
+     may not run, or run properly, or in the worst case (if different &repmgrd;
      versions are running and there are differences in the failover implementation) break
      your replication cluster.
    </para>
@@ -251,8 +252,8 @@
    </para>
    <para>
     &repmgr; provides the command <command>repmgr node rejoin</command> which can
-    optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin">
-    documentation for details, in particular the section <xref linkend="repmgr-node-rejoin-pg-rewind">.
+    optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin"/>
+    documentation for details, in particular the section <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
    </para>
    <para>
     If <command>pg_rewind</command> cannot be used, then the data directory will need
@@ -276,25 +277,25 @@
      directory in <filename>/etc</filename>?</title>
    <para>
     Use the command line option <literal>--copy-external-config-files</literal>. For more details
-    see <xref linkend="repmgr-standby-clone-config-file-copying">.
+    see <xref linkend="repmgr-standby-clone-config-file-copying"/>.
    </para>
   </sect2>
 
   <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
     <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
-      in <filename>postgresql.conf</filename> if I'm not using <application>repmgrd</application>?</title>
+      in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
    <para>
-    No, the <literal>repmgr</literal> shared library is only needed when running <application>repmgrd</application>.
-    If you later decide to run <application>repmgrd</application>, you just need to add
+    No, the <literal>repmgr</literal> shared library is only needed when running &repmgrd;.
+    If you later decide to run &repmgrd;, you just need to add
     <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
    </para>
   </sect2>
 
   <sect2 id="faq-repmgr-permissions" xreflabel="Replication permission problems">
    <title>I've provided replication permission for the <literal>repmgr</literal> user in <filename>pg_hba.conf</filename>
-     but <command>repmgr</command>/<application>repmgrd</application> complains it can't connect to the server... Why?</title>
+     but <command>repmgr</command>/&repmgrd; complains it can't connect to the server... Why?</title>
    <para>
-    <command>repmgr</command> and <application>repmgrd</application> need to be able to connect to the repmgr database
+    <command>repmgr</command> and &repmgrd; need to be able to connect to the repmgr database
     with a normal connection to query metadata. The <literal>replication</literal> connection
     permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
    </para>
@@ -317,7 +318,7 @@
    <para>
      Provide the option <literal>--waldir</literal>  (<literal>--xlogdir</literal> in PostgreSQL 9.6
      and earlier) with the absolute path to the WAL directory in <varname>pg_basebackup_options</varname>.
-     For more details see <xref linkend="cloning-advanced-pg-basebackup-options">.
+     For more details see <xref linkend="cloning-advanced-pg-basebackup-options"/>.
    </para>
   </sect2>
 
@@ -349,7 +350,7 @@
  </sect1>
 
  <sect1 id="faq-repmgrd" xreflabel="repmgrd">
-  <title><application>repmgrd</application></title>
+  <title>&repmgrd;</title>
 
 
   <sect2 id="faq-repmgrd-prevent-promotion" xreflabel="Prevent standby from being promoted to primary">
@@ -365,12 +366,12 @@
   </sect2>
 
   <sect2 id="faq-repmgrd-delayed-standby" xreflabel="Delayed standby support">
-   <title>Does <application>repmgrd</application> support delayed standbys?</title>
+   <title>Does &repmgrd; support delayed standbys?</title>
    <para>
-    <application>repmgrd</application> can monitor delayed standbys - those set up with
+    &repmgrd; can monitor delayed standbys - those set up with
     <varname>recovery_min_apply_delay</varname> set to a non-zero value
     in <filename>recovery.conf</filename> - but as it's not currently possible
-    to directly examine the value applied to the standby, <application>repmgrd</application>
+    to directly examine the value applied to the standby, &repmgrd;
     may not be able to properly evaluate the node as a promotion candidate.
    </para>
    <para>
@@ -379,25 +380,25 @@
     <filename>repmgr.conf</filename>.
    </para>
    <para>
-    Note that after registering a delayed standby, <application>repmgrd</application> will only start
+    Note that after registering a delayed standby, &repmgrd; will only start
     once the metadata added in the primary node has been replicated.
    </para>
   </sect2>
 
   <sect2 id="faq-repmgrd-logfile-rotate" xreflabel="repmgrd logfile rotation">
-   <title>How can I get <application>repmgrd</application> to rotate its logfile?</title>
+   <title>How can I get &repmgrd; to rotate its logfile?</title>
    <para>
-     Configure your system's <literal>logrotate</literal> service to do this; see <xref linkend="repmgrd-log-rotation">.
+     Configure your system's <literal>logrotate</literal> service to do this; see <xref linkend="repmgrd-log-rotation"/>.
    </para>
 
   </sect2>
 
   <sect2 id="faq-repmgrd-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
-   <title>I've recloned a failed primary as a standby, but <application>repmgrd</application> refuses to start?</title>
+   <title>I've recloned a failed primary as a standby, but &repmgrd; refuses to start?</title>
    <para>
     Check you registered the standby after recloning. If unregistered, the standby
     cannot be considered as a promotion candidate even if <varname>failover</varname> is set to
-    <literal>automatic</literal>, which is probably not what you want. <application>repmgrd</application> will start if
+    <literal>automatic</literal>, which is probably not what you want. &repmgrd; will start if
     <varname>failover</varname> is set to <literal>manual</literal> so the node's replication status can still
   be monitored, if desired.
    </para>
@@ -405,24 +406,24 @@
 
   <sect2 id="faq-repmgrd-pg-bindir" xreflabel="repmgrd does not apply pg_bindir to promote_command or follow_command">
     <title>
-      <application>repmgrd</application> ignores pg_bindir when executing <varname>promote_command</varname> or <varname>follow_command</varname>
+      &repmgrd; ignores pg_bindir when executing <varname>promote_command</varname> or <varname>follow_command</varname>
     </title>
     <para>
       <varname>promote_command</varname> or <varname>follow_command</varname> can be user-defined scripts,
       so &repmgr; will not apply <option>pg_bindir</option> even if excuting &repmgr;. Always provide the full
-      path; see <xref linkend="repmgrd-automatic-failover-configuration"> for more details.
+      path; see <xref linkend="repmgrd-automatic-failover-configuration"/> for more details.
     </para>
   </sect2>
 
   <sect2 id="faq-repmgrd-startup-no-upstream" xreflabel="repmgrd does not start if upstream node is not running">
     <title>
-      <application>repmgrd</application> aborts startup with the error "<literal>upstream node must be running before repmgrd can start</literal>"
+      &repmgrd; aborts startup with the error "<literal>upstream node must be running before repmgrd can start</literal>"
     </title>
     <para>
-      <application>repmgrd</application> does this to avoid starting up on a replication cluster
-      which is not in a healthy state. If the upstream is unavailable, <application>repmgrd</application>
+      &repmgrd; does this to avoid starting up on a replication cluster
+      which is not in a healthy state. If the upstream is unavailable, &repmgrd;
       may initiate a failover immediately after starting up, which could have unintended side-effects,
-      particularly if <application>repmgrd</application> is not running on other nodes.
+      particularly if &repmgrd; is not running on other nodes.
     </para>
     <para>
       In particular, it's possible that the node's local copy of the <literal>repmgr.nodes</literal> copy
@@ -430,7 +431,7 @@
     </para>
     <para>
       The onus is therefore on the adminstrator to manually set the cluster to a stable, healthy state before
-      starting <application>repmgrd</application>.
+      starting &repmgrd;.
     </para>
   </sect2>
 

doc/appendix-packages.xml

@@ -1,9 +1,11 @@
 <appendix id="appendix-packages" xreflabel="Package details">
+
+  <title>&repmgr; package details</title>
+
   <indexterm>
     <primary>packages</primary>
   </indexterm>
 
-  <title>&repmgr; package details</title>
   <para>
     This section provides technical details about various &repmgr; binary
     packages, such as location of the installed binaries and
@@ -309,8 +311,8 @@
         version number for your installation.
       </para>
       <para>
-        See also <xref linkend="repmgrd-configuration-debian-ubuntu"> for some specifics related
-        to configuring the <application>repmgrd</application> daemon.
+        See also <xref linkend="repmgrd-configuration-debian-ubuntu"/> for some specifics related
+        to configuring the &repmgrd; daemon.
       </para>
 
       <table id="debian-9-packages">
@@ -481,34 +483,12 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
 
     <sect2 id="packages-old-versions-rhel-centos" xreflabel="old RHEL/CentOS package versions">
       <title>RHEL/CentOS</title>
-      <para>
-        Old RPM packages (<literal>3.2</literal> and later) can be retrieved from the
-        (deprecated) 2ndQuadrant repository at
-        <ulink url="http://packages.2ndquadrant.com/">http://packages.2ndquadrant.com/</ulink>
-        by installing the appropriate repository RPM:
-      </para>
-
-      <itemizedlist spacing="compact" mark="bullet">
-
-        <listitem>
-          <simpara>
-            <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm</ulink>
-          </simpara>
-        </listitem>
-
-        <listitem>
-          <simpara>
-            <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm</ulink>
-          </simpara>
-        </listitem>
-
-      </itemizedlist>
 
       <para>
         Old versions can be located with e.g.:
         <programlisting>
           yum --showduplicates list repmgr96</programlisting>
-        (substitute the appropriate package name; see <xref linkend="packages-centos">) and installed with:
+        (substitute the appropriate package name; see <xref linkend="packages-centos"/>) and installed with:
         <programlisting>
           yum install {package_name}-{version}</programlisting>
         where <literal>{package_name}</literal> is the base package name (e.g. <literal>repmgr96</literal>)
@@ -520,6 +500,32 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
           yum install repmgr96-4.0.6-1.rhel6</programlisting>
       </para>
 
+      <sect3 id="packages-old-versions-rhel-centos-repmgr3">
+        <title>repmgr 3 packages</title>
+        <para>
+          Old &repmgr; 3 RPM packages (<literal>3.2</literal> and later) can be retrieved from the
+          (deprecated) 2ndQuadrant repository at
+          <ulink url="http://packages.2ndquadrant.com/repmgr/yum/">http://packages.2ndquadrant.com/repmgr/yum/</ulink>
+          by installing the appropriate repository RPM:
+        </para>
+
+        <itemizedlist spacing="compact" mark="bullet">
+
+          <listitem>
+            <simpara>
+              <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm</ulink>
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm</ulink>
+            </simpara>
+          </listitem>
+
+        </itemizedlist>
+      </sect3>
+
     </sect2>
   </sect1>
 
@@ -546,13 +552,13 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
 		char		package_conf_file[MAXPGPATH] = "";</programlisting>
         </para>
         <para>
-          See also: <xref linkend="configuration-file">
+          See also: <xref linkend="configuration-file"/>
         </para>
       </listitem>
 
       <listitem>
         <para>
-          PID file location: the default <application>repmgrd</application> PID file
+          PID file location: the default &repmgrd; PID file
           location can be hard-coded by patching <varname>package_pid_file</varname>
           in <filename>repmgrd.c</filename>:
           <programlisting>
@@ -560,7 +566,7 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
 		char		package_pid_file[MAXPGPATH] = "";</programlisting>
         </para>
         <para>
-          See also: <xref linkend="repmgrd-pid-file">
+          See also: <xref linkend="repmgrd-pid-file"/>
         </para>
       </listitem>
 

doc/appendix-release-notes.xml

@@ -12,19 +12,296 @@
   </para>
 
   <para>
-    See also: <xref linkend="upgrading-repmgr">
+    See also: <xref linkend="upgrading-repmgr"/>
   </para>
 
+  <sect1 id="release-4.4">
+    <title>Release 4.4</title>
+    <para><emphasis>?? June, 2019</emphasis></para>
+
+	<sect2>
+      <title>repmgr client enhancements</title>
+      <para>
+	    <itemizedlist>
+
+		  <listitem>
+            <para>
+			  <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>:
+			  prevent a standby from being cloned from a witness server (PostgreSQL 9.6 and later only).
+			</para>
+		  </listitem>
+
+		  <listitem>
+            <para>
+			  <link linkend="repmgr-witness-register"><command>repmgr witness register</command></link>:
+			  prevent a witness server from being registered on the replication cluster primary server
+              (PostgreSQL 9.6 and later only).
+			</para>
+            <para>
+              Registering a witness on the primary node would defeat the purpose of having a witness server,
+              which is intended to remain running even if the cluster's primary goes down.
+            </para>
+		  </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+              if <option>--siblings-follow</option> is not supplied, list all nodes which repmgr considers
+              to be siblings (this will include the witness server, if in use), and
+              which will remain attached to the old primary.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+              ignore nodes which are unreachable and marked as inactive.
+              Previously it would abort if any node was unreachable,
+              as that means it was unable to check if repmgrd is running.
+            </para>
+            <para>
+              However if the node has been marked as inactive in the repmgr metadata, it's
+              reasonable to assume the node is no longer part of the replication cluster
+              and does not need to be checked.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>
+              and <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>:
+              when executing with the <option>--dry-run</option> option, continue checks as far as possible
+              even if errors are encountered.
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>:
+              add <option>--siblings-follow</option> (similar to
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>).
+            </para>
+            <note>
+              <para>
+                If using &repmgrd;, when invoking
+                <command>repmgr standby promote</command> (either directly via
+                the <option>promote_command</option>, or in a script called
+                via <option>promote_command</option>), <option>--siblings-follow</option>
+                <emphasis>must not</emphasis> be included as a
+                command line option for <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>.
+              </para>
+            </note>
+          </listitem>
+
+		  <listitem>
+            <para>
+			  <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+			  add <option>--repmgrd-force-unpause</option> to unpause all &repmgrd; instances after executing a switchover.
+			  This will ensure that	any &repmgrd; instances which were paused before the switchover will be
+			  unpaused.
+			</para>
+		  </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+			  make output similar to that of
+			  <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
+			  for consistency and to make it easier to identify nodes not in the expected
+			  state.
+            </para>
+          </listitem>
+
+		  <listitem>
+            <para>
+              <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>:
+			  display each node's timeline ID (PostgreSQL 9.6 and later only).
+			</para>
+		  </listitem>
+
+		  <listitem>
+            <para>
+              <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
+			  and <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+			  show the upstream node name as reported by each individual node - this helps visualise
+			  situations where the cluster is in an unexpected state, and provide a better idea of the
+			  actual cluster state.
+			</para>
+			<para>
+			  For example, if a cluster has divided somehow and a set of nodes are
+			  following a new primary, when running either of these commands, &repmgr;
+			  will now show the name of the primary those nodes are actually
+			  following, rather than the now outdated node name recorded
+			  on the other side of the &quot;split&quot;. A warning will also be issued
+			  about the unexpected situation.
+            </para>
+          </listitem>
+
+		  <listitem>
+            <para>
+              <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
+			  and <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+			  check if a node is attached to its advertised upstream node, and issue a
+			  warning if the node is not attached.
+			</para>
+		  </listitem>
+
+		</itemizedlist>
+	  </para>
+    </sect2>
+
+    <sect2>
+      <title>repmgrd enhancements</title>
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              On the primary node, &repmgrd; is now able to monitor standby connections and,
+              if the number of nodes connected falls below a certain (configurable) value,
+              execute a custom script.
+            </para>
+            <para>
+              This provided an additional method for fencing an isolated primary node, and/or taking
+              other action if one or more standys become disconnected.
+            </para>
+            <para>
+              See section <link linkend="repmgrd-primary-child-disconnection">Monitoring standby disconnections on the primary node</link>
+              for more details.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              In a failover situation, &repmgrd; nodes on the standbys of the failed primary
+              are now able confirm among themselves that none can still see the primary
+              before continuing with the failover.
+            </para>
+            <para>
+              The <filename>repmgr.conf</filename> option <option>primary_visibility_consensus</option> must
+              be set to <literal>true</literal> to enable this functionality.
+            </para>
+            <para>
+              See section <xref linkend="repmgrd-primary-visibility-consensus"/>
+              for more details.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Ensure BDR2-specific functionality cannot be used on BDR3 and later.
+            </para>
+            <para>
+              The BDR support present in &repmgr; is for specific BDR2 use cases.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>
+              in <option>--dry-run</option> mode, ensure provision of the <option>--force</option> option
+              does not result in an existing data directory being modified in any way.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-primary-register"><command>repmgr primary register</command></link>
+              with the <option>--force</option> option, if another primary record exists but the associated node is
+              unreachable (or running as a standby), set that node's record to inactive to enable the current node
+              to be registered as a primary.
+            </para>
+          </listitem>
+
+		  <listitem>
+			<para>
+              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>
+              with the <option>--upstream-conninfo</option>, ensure that <varname>application_name</varname>
+              is set correctly in <varname>primary_conninfo</varname>.
+            </para>
+          </listitem>
+
+		  <listitem>
+			<para>
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+              don't abort if one or more nodes are not reachable <emphasis>and</emphasis>
+			  they are marked as inactive.
+			</para>
+		  </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: canonicalize the data directory path when parsing the configuration file, so
+              the provided path matches the path PostgreSQL reports as its data directory.
+              Otherwise, if e.g. the data directory is configured with a trailing slash,
+              <link linkend="repmgr-node-check"><command>repmgr node check --data-directory-config</command></link>
+              will return a spurious error.
+            </para>
+          </listitem>
+
+		  <listitem>
+			<para>
+              &repmgrd;: fix memory leak which occurs while the monitored PostgreSQL node is <emphasis>not</emphasis>
+              running.
+            </para>
+          </listitem>
+
+        </itemizedlist>
+	  </para>
+    </sect2>
+
+
+   <sect2>
+      <title>Other</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              The &repmgr; documentation has been converted to DocBook XML format,
+              as currently used by the main PostgreSQL project.
+              This means it can now be built against any PostgreSQL version from 9.5
+              (previously it was not possible to build the documentation against
+              PostgreSQL 10 or later), and makes it easier to provide the documentation
+              in other formats such as PDF.
+            </para>
+            <para>
+              For further details see: <xref linkend="installation-build-repmgr-docs"/>
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+   </sect2>
+  </sect1>
+
+
   <sect1 id="release-4.3">
     <title>Release 4.3</title>
-    <para><emphasis>Mar ???, 2019</emphasis></para>
+    <para><emphasis>Tue April 2, 2019</emphasis></para>
     <para>
       &repmgr; 4.3 is a major release.
     </para>
+    <para>
+      For details on how to upgrade an existing &repmgr; instrallation, see
+      documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
+    </para>
+    <para>
+      If &repmgrd; is in use, a PostgreSQL restart <emphasis>is</emphasis> required;
+      in that case we suggest combining this &repmgr; upgrade with the next PostgreSQL
+      minor release, which will require a PostgreSQL restart in any case.
+    </para>
+
 
 	<important>
 	  <para>
-	    On Debian-based systems, including Ubuntu, if using <application>repmgrd</application>
+	    On Debian-based systems, including Ubuntu, if using &repmgrd;
 	    please ensure that in the file <filename>/etc/init.d/repmgrd</filename>, the parameter
 	    <varname>REPMGRD_OPTS</varname> contains &quot;<literal>--daemonize=false</literal>&quot;, e.g.:
 	    <programlisting>
@@ -37,7 +314,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 	</important>
 
     <sect2>
-      <title>repmgr enhancements</title>
+      <title>repmgr client enhancements</title>
       <para>
         <itemizedlist>
 
@@ -67,7 +344,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <para>
               New commands <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link> and
               <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link>:
-              these provide a standardized way of starting and stopping <application>repmgrd</application>.
+              these provide a standardized way of starting and stopping &repmgrd;.
               GitHub #528.
             </para>
             <note>
@@ -83,7 +360,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <para>
               <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>
               additionally displays the node priority and the interval (in seconds) since the
-              <application>repmgrd</application> instance last verified its upstream node was available.
+              &repmgrd; instance last verified its upstream node was available.
             </para>
           </listitem>
 
@@ -151,20 +428,20 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application> will no longer consider nodes where <application>repmgrd</application>
-	      is not running as promotion candidates.
+              &repmgrd; will no longer consider nodes where &repmgrd;
+			  is not running as promotion candidates.
+            </para>
+            <para>
+              Previously, if &repmgrd; was not running on a node, but
+              that node qualified as the promotion candidate, it would never be promoted due to
+              the absence of a running &repmgrd;.
             </para>
-	    <para>
-	      Previously, if <application>repmgrd</application> was not running on a node, but
-	      that node qualified as the promotion candidate, it would never be promoted due to
-	      the absence of a running <application>repmgrd</application>.
-	    </para>
           </listitem>
 
           <listitem>
             <para>
               Add option <option>connection_check_type</option> to enable selection of the method
-              <application>repmgrd</application> uses to determine whether the upstream node is available.
+              &repmgrd; uses to determine whether the upstream node is available.
             </para>
             <para>
               Possible values are <literal>ping</literal> (default; uses <command>PQping()</command> to
@@ -177,7 +454,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
           <listitem>
             <para>
               New configuration option <link linkend="repmgrd-failover-validation"><option>failover_validation_command</option></link>
-              to allow an external mechanism to validate the failover decision made by <application>repmgrd</application>.
+              to allow an external mechanism to validate the failover decision made by &repmgrd;.
             </para>
           </listitem>
 
@@ -188,6 +465,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             </para>
           </listitem>
 
+         <listitem>
+            <para>
+			  In a failover situation, &repmgrd; will not attempt to promote a
+			  node if another primary has already appeared (e.g. by being promoted manually).
+			  GitHub #420.
+			</para>
+          </listitem>
+
 		</itemizedlist>
 	  </para>
 	</sect2>
@@ -197,6 +482,35 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       <para>
         <itemizedlist>
 
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>:
+	          fix display of node IDs with multiple digits.
+            </para>
+	      </listitem>
+
+          <listitem>
+            <para>
+              ensure <command><link linkend="repmgr-primary-unregister">repmgr primary unregister</link></command>
+	          behaves correctly when executed on a witness server. GitHub #548.
+            </para>
+	      </listitem>
+
+          <listitem>
+            <para>
+              ensure <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>
+	          fails when <option>--upstream-node-id</option> is the same as the local node ID.
+            </para>
+	      </listitem>
+
+          <listitem>
+            <para>
+              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>,
+              recheck primary/upstream connection(s) after the data copy operation is complete, as these may
+              have gone away.
+            </para>
+          </listitem>
+
           <listitem>
             <para>
               &repmgr;: when executing <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
@@ -207,16 +521,8 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              &repmgr;: when executing <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>,
-              chech the node to connected is actually the primary (i.e. not the witness server).  GitHub #528.
-            </para>
-          </listitem>
-
-         <listitem>
-            <para>
-              &repmgr;: when executing <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>,
-              recheck primary/upstream connection(s) after the data copy operation is complete, as these may
-              have gone away.
+              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+	          verify the standby (promotion candidate) is currently attached to the primary (demotion candidate). GitHub #519.
             </para>
           </listitem>
 
@@ -224,47 +530,32 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <para>
               &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
               avoid a potential race condition when comparing received WAL on the standby to the primary's shutdown location,
-	      as the standby's walreceiver may not have yet flushed all received WAL to disk. GitHub #518.
-            </para>
-          </listitem>
-
-
-         <listitem>
-            <para>
-              &repmgr;: when executing <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-	      verify the standby (promotion candidate) is currently attached to the primary (demotion candidate). GitHub #519.
+	          as the standby's walreceiver may not have yet flushed all received WAL to disk. GitHub #518.
             </para>
           </listitem>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: on a cascaded standby, don't fail over if
-              <literal>failover=manual</literal>. GitHub #531.
+              &repmgr;: when executing <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>,
+              check the node to connected is actually the primary (i.e. not the witness server).  GitHub #528.
             </para>
           </listitem>
 
-          <listitem>
-            <para>
-              <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>:
-	      fix display of node IDs with multiple digits.
-            </para>
-	  </listitem>
-
-          <listitem>
-            <para>
-              ensure <command><link linkend="repmgr-primary-unregister">repmgr primary unregister</link></command>
-	      behaves correctly when executed on a witness server. GitHub #548.
-            </para>
-	  </listitem>
-
           <listitem>
             <para>
               <command><link linkend="repmgr-node-check">repmgr node check</link></command>
-	      will only consider physical replication slots, as the purpose
-	      of slot checks is to warn about potential issues with
-	      streaming replication standbys which are no longer attached.
-	    </para>
-	  </listitem>
+	          will only consider physical replication slots, as the purpose
+	          of slot checks is to warn about potential issues with
+	          streaming replication standbys which are no longer attached.
+	        </para>
+	      </listitem>
+
+          <listitem>
+            <para>
+              &repmgrd;: on a cascaded standby, don't fail over if
+              <literal>failover=manual</literal>. GitHub #531.
+            </para>
+          </listitem>
 
         </itemizedlist>
       </para>
@@ -290,7 +581,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
 	<important>
 	  <para>
-	    On Debian-based systems, including Ubuntu, if using <application>repmgrd</application>
+	    On Debian-based systems, including Ubuntu, if using &repmgrd;
 	    please ensure that the in the file <filename>/etc/init.d/repmgrd</filename>, the parameter
 	    <varname>REPMGRD_OPTS</varname> contains &quot;<literal>--daemonize=false</literal>&quot;, e.g.:
 	    <programlisting>
@@ -385,12 +676,12 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application> can now be &quot;paused&quot;, i.e. instructed
+              &repmgrd; can now be &quot;paused&quot;, i.e. instructed
               not to take any action such as a failover, even if the prerequisites for such an
               action are detected.
             </para>
             <para>
-              This removes the need to stop <application>repmgrd</application> on all nodes when
+              This removes the need to stop &repmgrd; on all nodes when
               performing a planned operation such as a switchover.
             </para>
             <para>
@@ -416,7 +707,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: fix parsing of <option>-d/--daemonize</option> option.
+              &repmgrd;: fix parsing of <option>-d/--daemonize</option> option.
             </para>
           </listitem>
 
@@ -434,8 +725,8 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
     <para>
 	  We recommend upgrading to this version as soon as possible.
 	  This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.1.0;
-      <application>repmgrd</application> (if running) should be restarted.
-      See <xref linkend="upgrading-repmgr"> for more details.
+      &repmgrd; (if running) should be restarted.
+      See <xref linkend="upgrading-repmgr"/> for more details.
 	</para>
 
     <sect2>
@@ -516,8 +807,8 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <para>
               Check <varname>promote_command</varname> and <varname>follow_command</varname>
               are defined when reloading configuration. These were checked on startup but
-              not reload by <application>repmgrd</application>, which made it possible to
-              make <application>repmgrd</application> with invalid values. It's unlikely
+              not reload by &repmgrd;, which made it possible to
+              make &repmgrd; with invalid values. It's unlikely
               anyone would want to do this, but we should make it impossible anyway.
               (GitHub #486).
             </para>
@@ -558,7 +849,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: fix startup on witness node when local data is stale. (GitHub #488, #489).
+              &repmgrd;: fix startup on witness node when local data is stale. (GitHub #488, #489).
             </para>
           </listitem>
 
@@ -584,7 +875,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
     <title>Release 4.1.0</title>
     <para><emphasis>Tue July 31, 2018</emphasis></para>
     <para>
-      &repmgr; 4.1.0 introduces some changes to <application>repmgrd</application>
+      &repmgr; 4.1.0 introduces some changes to &repmgrd;
       behaviour and some additional configuration parameters.
     </para>
     <para>
@@ -600,7 +891,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
           </listitem>
           <listitem>
             <para>
-              <application>repmgrd</application> must be restarted on all nodes where it is running.
+              &repmgrd; must be restarted on all nodes where it is running.
             </para>
           </listitem>
 
@@ -610,7 +901,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
        for this release (unless upgrading from repmgr 3.x).
     </para>
     <para>
-       See <xref linkend="upgrading-repmgr-extension"> for more details.
+       See <xref linkend="upgrading-repmgr-extension"/> for more details.
     </para>
 
     <para>
@@ -625,7 +916,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       </para>
       <para>
         Coinciding with this release, the 2ndQuadrant repository structure has changed.
-        See section <xref linkend="installation-packages"> for details, particularly
+        See section <xref linkend="installation-packages"/> for details, particularly
         if you are using a RPM-based system.
       </para>
     </note>
@@ -638,7 +929,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              Default for <xref linkend="repmgr-conf-log-level"> is now <option>INFO</option>.
+              Default for <xref linkend="repmgr-conf-log-level"/> is now <option>INFO</option>.
               This produces additional informative log output, without creating excessive additional
               log file volume, and matches the setting assumed for examples in the documentation.
               (GitHub #470).
@@ -722,14 +1013,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: create a PID file by default
-              (GitHub #457). For details, see <xref linkend="repmgrd-pid-file">.
+              &repmgrd;: create a PID file by default
+              (GitHub #457). For details, see <xref linkend="repmgrd-pid-file"/>.
             </para>
           </listitem>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: daemonize process by default.
+              &repmgrd;: daemonize process by default.
 			  In case, for whatever reason, the user does not wish to daemonize the
 			  process, provide <option>--daemonize=false</option>.
 			  (GitHub #458).
@@ -798,7 +1089,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 	<para>
 	  We recommend upgrading to this version as soon as possible.
 	  This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.5;
-      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      &repmgrd; (if running) should be restarted. See <xref linkend="upgrading-repmgr"/>
       for more details.
 	</para>
 
@@ -885,7 +1176,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: ensure local node is counted as quorum member
+              &repmgrd;: ensure local node is counted as quorum member
 			  (GitHub #439)
            </para>
           </listitem>
@@ -902,7 +1193,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
     <para>
       &repmgr; 4.0.5 contains a number of usability enhancements related to
       <application>pg_rewind</application> usage, <filename>recovery.conf</filename>
-      generation and (in <application>repmgrd</application>) handling of various
+      generation and (in &repmgrd;) handling of various
       corner-case situations, as well as a number of bug fixes.
     </para>
 
@@ -934,7 +1225,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
           <listitem>
             <para>
               Add sanity check if <option>--upstream-node-id</option> not supplied when executing
-              <xref linkend="repmgr-standby-register"> (GitHub #395).
+              <xref linkend="repmgr-standby-register"/> (GitHub #395).
             </para>
           </listitem>
 
@@ -967,7 +1258,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: set <literal>connect_timeout=2</literal> (if not explicitly set)
+              &repmgrd;: set <literal>connect_timeout=2</literal> (if not explicitly set)
               when pinging a server.
            </para>
           </listitem>
@@ -1023,20 +1314,20 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: handle <command>pg_ctl promote</command> timeout (GitHub #425).
+              &repmgrd;: handle <command>pg_ctl promote</command> timeout (GitHub #425).
            </para>
           </listitem>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: handle failover situation with only two nodes in the primary
+              &repmgrd;: handle failover situation with only two nodes in the primary
           location, and at least one node in another location (GitHub #407).
             </para>
           </listitem>
 
           <listitem>
             <para>
-               <application>repmgrd</application>: prevent standby connection handle from going stale.
+               &repmgrd;: prevent standby connection handle from going stale.
            </para>
           </listitem>
 
@@ -1060,7 +1351,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
     </para>
     <para>
       This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.3;
-      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      &repmgrd; (if running) should be restarted. See <xref linkend="upgrading-repmgr"/>
       for more details.
     </para>
 
@@ -1139,14 +1430,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: improve detection of status change from primary to
+              &repmgrd;: improve detection of status change from primary to
               standby
            </para>
           </listitem>
 
           <listitem>
             <para>
-              <application>repmgrd</application>:  improve reconnection to the local node after a
+              &repmgrd;:  improve reconnection to the local node after a
               failover (previously a connection error due to the node starting up was being
               interpreted as the node being unavailable)
            </para>
@@ -1154,14 +1445,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: when running on a witness server, correctly connect
+              &repmgrd;: when running on a witness server, correctly connect
               to new primary after a failover
            </para>
           </listitem>
 
           <listitem>
             <para>
-              <application>repmgrd</application>: add <link linkend="event-notifications">event notification</link>
+              &repmgrd;: add <link linkend="event-notifications">event notification</link>
               <literal>repmgrd_shutdown</literal> (GitHub #393)
            </para>
           </listitem>
@@ -1330,7 +1621,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
     </para>
     <para>
       This release can be installed as a simple package upgrade from &repmgr; 4.0.1 or 4.0;
-      <application>repmgrd</application> (if running) should be restarted.
+      &repmgrd; (if running) should be restarted.
     </para>
 
     <sect2>
@@ -1447,14 +1738,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
         <listitem>
           <para>
-            Fix <xref linkend="repmgr-cluster-show"> when <literal>repmgr</literal> schema not set in search path
+            Fix <xref linkend="repmgr-cluster-show"/> when <literal>repmgr</literal> schema not set in search path
             (GitHub #341)
           </para>
         </listitem>
 
         <listitem>
           <para>
-            When using <literal>--force-rewind</literal> with <xref linkend="repmgr-node-rejoin">
+            When using <literal>--force-rewind</literal> with <xref linkend="repmgr-node-rejoin"/>
             delete any replication slots copied by <application>pg_rewind</application>
             (GitHub #334)
           </para>
@@ -1510,7 +1801,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
   </note>
 
   <para>
-    For detailed instructions on upgrading from repmgr 3.x, see <xref linkend="upgrading-from-repmgr-3">.
+    For detailed instructions on upgrading from repmgr 3.x, see <xref linkend="upgrading-from-repmgr-3"/>.
   </para>
 
   <sect2>
@@ -1524,7 +1815,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             the <command>switchover</command> process has been improved and streamlined,
             speeding up the switchover process and can also instruct other standbys
             to follow the new primary once the switchover has completed. See
-             <xref linkend="performing-switchover"> for more details.
+            <xref linkend="performing-switchover"/> for more details.
           </para>
         </listitem>
 
@@ -1550,10 +1841,10 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
         <listitem>
           <para>
             <emphasis>improved logging output</emphasis>:
-            &repmgr; (and <application>repmgrd</application>) now provide more explicit
+            &repmgr; (and &repmgrd;) now provide more explicit
             logging output giving a better picture of what is going on. Where appropriate,
             <literal>DETAIL</literal> and <literal>HINT</literal> log lines provide additional
-            detail and suggestions for resolving problems. Additionally, <application>repmgrd</application>
+            detail and suggestions for resolving problems. Additionally, &repmgrd;
             now emits informational log lines at regular, configurable intervals
             to confirm that it's running correctly and which node(s) it's monitoring.
           </para>
@@ -1575,8 +1866,8 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
         <listitem>
           <para>
             <emphasis>monitoring and status checks</emphasis>:
-            New commands <xref linkend="repmgr-node-check"> and
-            <xref linkend="repmgr-node-status"> providing information
+            New commands <xref linkend="repmgr-node-check"/> and
+            <xref linkend="repmgr-node-status"/> providing information
             about a node's status and replication-related monitoring
             output.
           </para>
@@ -1586,7 +1877,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
         <listitem>
           <para>
             <emphasis>node rejoin</emphasis>:
-            New commands <xref linkend="repmgr-node-rejoin"> enables a failed
+            New commands <xref linkend="repmgr-node-rejoin"/> enables a failed
             primary to be rejoined to a replication cluster, optionally using
             <application>pg_rewind</application> to synchronise its data,
             (note that <application>pg_rewind</application> may not be useable
@@ -1600,11 +1891,11 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <emphasis>automatic failover</emphasis>:
             improved detection of node status; promotion decision based on a consensual
             model, with the promoted primary explicitly informing other standbys to
-            follow it. The <application>repmgrd</application> daemon will continue
+            follow it. The &repmgrd; daemon will continue
             functioning even if the monitored PostgreSQL instance is down, and resume
             monitoring if it reappears. Additionally, if the instance's role has changed
             (typically from a primary to a standby, e.g. following reintegration of a
-            failed primary using <xref linkend="repmgr-node-rejoin">) <application>repmgrd</application>
+            failed primary using <xref linkend="repmgr-node-rejoin"/>) &repmgrd;
             will automatically resume monitoring it as a standby.
           </para>
         </listitem>
@@ -1668,7 +1959,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             by the configuration file option <varname>replication_user</varname>.
             The value (which defaults to the user provided in the <varname>conninfo</varname>
             string) will be stored in the &repmgr; metadata for use by
-            <xref linkend="repmgr-standby-clone"> and <xref linkend="repmgr-standby-follow">.
+            <xref linkend="repmgr-standby-clone"/> and <xref linkend="repmgr-standby-follow"/>.
         </para></listitem>
 
         <listitem><para>
@@ -1683,14 +1974,14 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             to <varname>primary_conninfo</varname> by default; to force the inclusion
             of a password (not recommended), use the new configuration file parameter
             <varname>use_primary_conninfo_password</varname>. For details, ee section
-            <xref linkend="cloning-advanced-managing-passwords">.
+            <xref linkend="cloning-advanced-managing-passwords"/>.
         </para></listitem>
 
       </itemizedlist>
     </para>
 
     <para>
-      <application>repmgrd</application>
+      &repmgrd;
       <itemizedlist>
 
         <listitem><para>
@@ -1812,7 +2103,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       <listitem>
         <simpara>
           new parameter <varname>log_status_interval</varname>, which causes
-          <application>repmgrd</application> to emit a status log
+          &repmgrd; to emit a status log
           line at the specified interval
         </simpara>
       </listitem>

doc/appendix-support.xml

@@ -1,9 +1,11 @@
 <appendix id="appendix-support" xreflabel="repmgr support">
+
+  <title>&repmgr; support</title>
+
   <indexterm>
     <primary>support</primary>
   </indexterm>
 
-  <title>&repmgr; support</title>
   <para>
     <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides 24x7
     production support for &repmgr; and other PostgreSQL
@@ -28,12 +30,13 @@
   </important>
 
   <sect1 id="appendix-support-reporting-issues" xreflabel="Reportins Issues">
+    <title>Reporting Issues</title>
+
     <indexterm>
       <primary>support</primary>
       <secondary>reporting issues</secondary>
     </indexterm>
 
-    <title>Reporting Issues</title>
 
     <para>
       When asking questions or reporting issues, it is extremely helpful if the following information is included:
@@ -48,7 +51,7 @@
 
      <listitem>
       <simpara>
-        How was &repmgr installed? From source? From packages? If
+        How was &repmgr; installed? From source? From packages? If
         so from which repository?
       </simpara>
      </listitem>
@@ -80,7 +83,7 @@
       the maximum level of logging output.
     </para>
     <para>
-      If issues are encountered with <application>repmgrd</application>,
+      If issues are encountered with &repmgrd;,
       please provide relevant extracts from the &repmgr; log files
       and if possible the PostgreSQL log itself. Please ensure these
       logs do not contain any confidential data.

doc/cloning-standbys.xml

@@ -2,6 +2,8 @@
  <title>Cloning standbys</title>
 
  <sect1 id="cloning-from-barman" xreflabel="Cloning from Barman">
+   <title>Cloning a standby from Barman</title>
+
    <indexterm>
     <primary>cloning</primary>
     <secondary>from Barman</secondary>
@@ -11,9 +13,8 @@
     <secondary>cloning a standby</secondary>
    </indexterm>
 
-   <title>Cloning a standby from Barman</title>
    <para>
-    <xref linkend="repmgr-standby-clone"> can use
+    <xref linkend="repmgr-standby-clone"/> can use
     <ulink url="https://www.2ndquadrant.com/">2ndQuadrant</ulink>'s
     <ulink url="https://www.pgbarman.org/">Barman</ulink> application
     to clone a standby (and also as a fallback source for WAL files).
@@ -73,7 +74,7 @@
       <para>
         the <varname>restore_command</varname> setting in <filename>repmgr.conf</filename> is configured to
         use a copy of the <command>barman-wal-restore</command> script shipped with the
-        <literal>barman-cli</literal> package (see section <xref linkend="cloning-from-barman-restore-command">
+        <literal>barman-cli</literal> package (see section <xref linkend="cloning-from-barman-restore-command"/>
         below).
       </para>
      </listitem>
@@ -126,12 +127,13 @@
    </para>
   </sect2>
   <sect2 id="cloning-from-barman-restore-command" xreflabel="Using Barman as a WAL file source">
-  <indexterm>
+   <title>Using Barman as a WAL file source</title>
+
+   <indexterm>
     <primary>Barman</primary>
     <secondary>fetching archived WAL</secondary>
    </indexterm>
 
-   <title>Using Barman as a WAL file source</title>
    <para>
     As a fallback in case streaming replication is interrupted, PostgreSQL can optionally
     retrieve WAL files from an archive, such as that provided by Barman. This is done by
@@ -172,7 +174,9 @@
   </sect2>
  </sect1>
 
-<sect1 id="cloning-replication-slots" xreflabel="Cloning and replication slots">
+ <sect1 id="cloning-replication-slots" xreflabel="Cloning and replication slots">
+   <title>Cloning and replication slots</title>
+
    <indexterm>
      <primary>cloning</primary>
      <secondary>replication slots</secondary>
@@ -182,7 +186,6 @@
      <primary>replication slots</primary>
      <secondary>cloning</secondary>
    </indexterm>
-   <title>Cloning and replication slots</title>
    <para>
     Replication slots were introduced with PostgreSQL 9.4 and are designed to ensure
     that any standby connected to the primary using a replication slot will always
@@ -244,18 +247,20 @@
     <simpara>
      As an alternative we recommend using 2ndQuadrant's <ulink url="https://www.pgbarman.org/">Barman</ulink>,
      which offloads WAL management to a separate server, removing the requirement to use a replication
-     slot for each individual standby to reserve WAL. See section <xref linkend="cloning-from-barman">
+     slot for each individual standby to reserve WAL. See section <xref linkend="cloning-from-barman"/>
      for more details on using &repmgr; together with Barman.
     </simpara>
    </tip>
  </sect1>
 
  <sect1 id="cloning-cascading" xreflabel="Cloning and cascading replication">
+   <title>Cloning and cascading replication</title>
+
    <indexterm>
      <primary>cloning</primary>
      <secondary>cascading replication</secondary>
    </indexterm>
-   <title>Cloning and cascading replication</title>
+
    <para>
     Cascading replication, introduced with PostgreSQL 9.2, enables a standby server
     to replicate from another standby server rather than directly from the primary,
@@ -276,7 +281,7 @@
    </para>
    <para>
     To demonstrate cascading replication, first ensure you have a primary and standby
-    set up as shown in the <xref linkend="quickstart">.
+    set up as shown in the <xref linkend="quickstart"/>.
     Then create an additional standby server with <filename>repmgr.conf</filename> looking
     like this:
     <programlisting>
@@ -339,11 +344,11 @@
  </sect1>
 
  <sect1 id="cloning-advanced" xreflabel="Advanced cloning options">
+   <title>Advanced cloning options</title>
    <indexterm>
      <primary>cloning</primary>
      <secondary>advanced options</secondary>
    </indexterm>
-   <title>Advanced cloning options</title>
 
    <sect2 id="cloning-advanced-pg-basebackup-options" xreflabel="pg_basebackup options when cloning a standby">
     <title>pg_basebackup options when cloning a standby</title>
@@ -365,7 +370,7 @@
       <simpara>
         If <application>Barman</application> is set up for the cluster, it's possible to
         clone the standby directly from Barman, without any impact on the server the standby
-        is being cloned from. For more details see <xref linkend="cloning-from-barman">.
+        is being cloned from. For more details see <xref linkend="cloning-from-barman"/>.
       </simpara>
     </tip>
     <para>
@@ -433,7 +438,7 @@
      (but not <filename>~/.pgpass</filename>) and place it into the <varname>primary_conninfo</varname>
      string in <filename>recovery.conf</filename>. Note that <varname>PGPASSWORD</varname>
      will need to be set during any action which causes <filename>recovery.conf</filename> to be
-     rewritten, e.g. <xref linkend="repmgr-standby-follow">.
+     rewritten, e.g. <xref linkend="repmgr-standby-follow"/>.
     </para>
     <para>
      It is of course also possible to include the password value in the <varname>conninfo</varname>
@@ -460,7 +465,7 @@
      replication connections and generating <filename>recovery.conf</filename>. This
      value will also be stored in the parameter <literal>repmgr.nodes</literal>
      table for each node; it no longer needs to be explicitly specified when
-     cloning a node or executing <xref linkend="repmgr-standby-follow">.
+     cloning a node or executing <xref linkend="repmgr-standby-follow"/>.
     </para>
    </sect2>
  </sect1>

doc/configuration-file-log-settings.xml

@@ -1,4 +1,6 @@
 <sect1 id="configuration-file-log-settings" xreflabel="log settings">
+  <title>Log settings</title>
+
   <indexterm>
     <primary>repmgr.conf</primary>
     <secondary>log settings</secondary>
@@ -7,10 +9,9 @@
     <primary>log settings</primary>
     <secondary>configuration in repmgr.conf</secondary>
   </indexterm>
-  <title>Log settings</title>
 
   <para>
-    By default, &repmgr; and <application>repmgrd</application> write log output to
+    By default, &repmgr; and &repmgrd; write log output to
     <literal>STDERR</literal>. An alternative log destination can be specified
     (either a file or <literal>syslog</literal>).
   </para>
@@ -24,7 +25,7 @@
     <para>
       This behaviour can be overriden with the command line option <option>--log-to-file</option>,
       which will redirect all logging output to the configured log destination. This is recommended
-      when &repmgr; is executed by another application, particularly <application>repmgrd</application>,
+      when &repmgr; is executed by another application, particularly &repmgrd;,
       to enable log output generated by the &repmgr; application to be stored for later reference.
     </para>
   </note>
@@ -32,12 +33,11 @@
   <variablelist>
 
    <varlistentry id="repmgr-conf-log-level" xreflabel="log_level">
-    <term><varname>log_level</varname> (<type>string</type>)
+    <term><varname>log_level</varname> (<type>string</type>)</term>
+    <listitem>
      <indexterm>
       <primary><varname>log_level</varname> configuration file parameter</primary>
      </indexterm>
-    </term>
-    <listitem>
      <para>
        One of <option>DEBUG</option>, <option>INFO</option>, <option>NOTICE</option>,
        <option>WARNING</option>, <option>ERROR</option>, <option>ALERT</option>, <option>CRIT</option>
@@ -76,11 +76,11 @@
     </term>
     <listitem>
      <para>
-       If <xref linkend="repmgr-conf-log-facility"> is set to <option>STDERR</option>, log output
+       If <xref linkend="repmgr-conf-log-facility"/> is set to <option>STDERR</option>, log output
        can be redirected to the specified file.
      </para>
      <para>
-       See <xref linkend="repmgrd-log-rotation"> for information on configuring log rotation.
+       See <xref linkend="repmgrd-log-rotation"/> for information on configuring log rotation.
      </para>
     </listitem>
    </varlistentry>
@@ -93,12 +93,12 @@
     </term>
     <listitem>
      <para>
-       This setting causes <application>repmgrd</application> to emit a status log
+       This setting causes &repmgrd; to emit a status log
        line at the specified interval (in seconds, default <literal>300</literal>)
-       describing <application>repmgrd</application>'s current state, e.g.:
+       describing &repmgrd;'s current state, e.g.:
      </para>
      <programlisting>
-      [2018-07-12 00:47:32] [INFO] monitoring connection to upstream node "node1" (node ID: 1)</programlisting>
+      [2018-07-12 00:47:32] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
     </listitem>
    </varlistentry>
 

doc/configuration-file-required-settings.xml

@@ -1,10 +1,12 @@
 <sect1 id="configuration-file-settings" xreflabel="required configuration file settings">
+
+ <title>Required configuration file settings</title>
+
   <indexterm>
     <primary>repmgr.conf</primary>
     <secondary>required settings</secondary>
   </indexterm>
 
- <title>Required configuration file settings</title>
  <para>
    Each <filename>repmgr.conf</filename> file must contain the following parameters:
  </para>
@@ -39,6 +41,10 @@
        called <varname>standby1</varname> (for example), things will be confusing
        to say the least.
      </para>
+     <para>
+       The string's maximum length is 63 characters and it should
+       contain only printable ASCII characters.
+     </para>
     </listitem>
    </varlistentry>
 
@@ -56,7 +62,7 @@
      </para>
      <para>
        For details on conninfo strings, see section <ulink
-       url="https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING">Connection Strings</>
+       url="https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING">Connection Strings</ulink>
         in the PosgreSQL documentation.
      </para>
      <para>
@@ -65,18 +71,18 @@
         string to determine the length of time which elapses before a network
         connection attempt is abandoned; for details see <ulink
         url="https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT">
-        the PostgreSQL documentation</>.
+        the PostgreSQL documentation</ulink>.
      </para>
     </listitem>
    </varlistentry>
 
    <varlistentry id="repmgr-conf-data-directory" xreflabel="data_directory">
-    <term><varname>data_directory</varname> (<type>string</type>)
-     <indexterm>
-      <primary><varname>data_directory</varname> configuration file parameter</primary>
-     </indexterm>
-    </term>
+    <term><varname>data_directory</varname> (<type>string</type>)</term>
     <listitem>
+      <indexterm>
+        <primary><varname>data_directory</varname> configuration file parameter</primary>
+      </indexterm>
+
      <para>
        The node's data directory. This is needed by repmgr
        when performing operations when the PostgreSQL instance
@@ -90,33 +96,6 @@
   </variablelist>
  </para>
 
-  <para>
-    For a full list of annotated configuration items, see the file
-    <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
-  </para>
-  <para>
-    For <application>repmgrd</application>-specific settings, see <xref linkend="repmgrd-configuration">.
-  </para>
 
-  <note>
-    <para>
-    The following parameters in the configuration file can be overridden with
-    command line options:
-    <itemizedlist>
-     <listitem>
-       <simpara>
-         <literal>-L/--log-level</literal> overrides <literal>log_level</literal> in
-         <filename>repmgr.conf</filename>
-       </simpara>
-     </listitem>
-     <listitem>
-       <simpara>
-         <literal>-b/--pg_bindir</literal> overrides <literal>pg_bindir</literal> in
-         <filename>repmgr.conf</filename>
-       </simpara>
-     </listitem>
-    </itemizedlist>
-    </para>
-  </note>
 
 </sect1>

doc/configuration-file-service-commands.xml

@@ -1,4 +1,6 @@
 <sect1 id="configuration-file-service-commands" xreflabel="service command settings">
+  <title>Service command settings</title>
+
   <indexterm>
     <primary>repmgr.conf</primary>
     <secondary>service command settings</secondary>
@@ -7,10 +9,9 @@
     <primary>service command settings</primary>
     <secondary>configuration in repmgr.conf</secondary>
   </indexterm>
-  <title>Service command settings</title>
 
   <para>
-    In some circumstances, &repmgr; (and <application>repmgrd</application>) need to
+    In some circumstances, &repmgr; (and &repmgrd;) need to
     be able to stop, start or restart PostgreSQL. &repmgr; commands which need to do this
     include <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>,
     <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link> and
@@ -68,7 +69,7 @@
     </para>
     <para>
       Do not confuse this with <varname>promote_command</varname>, which is used
-      by <application>repmgrd</application> to execute <xref linkend="repmgr-standby-promote">.
+      by &repmgrd; to execute <xref linkend="repmgr-standby-promote"/>.
     </para>
   </note>
 

doc/configuration-file.xml

@@ -1,4 +1,7 @@
 <sect1 id="configuration-file" xreflabel="configuration file">
+
+  <title>Configuration file</title>
+
   <indexterm>
     <primary>repmgr.conf</primary>
   </indexterm>
@@ -8,28 +11,26 @@
     <secondary>repmgr.conf</secondary>
   </indexterm>
 
-  <title>Configuration file</title>
-
   <para>
-    <application>repmgr</application> and <application>repmgrd</application>
+    <application>repmgr</application> and &repmgrd;
     use a common configuration file, by default called
     <filename>repmgr.conf</filename> (although any name can be used if explicitly specified).
     <filename>repmgr.conf</filename> must contain a number of required parameters, including
     the database connection string for the local node and the location
     of its data directory; other values will be inferred from defaults if
-    not explicitly supplied. See section <xref linkend="configuration-file-settings">
+    not explicitly supplied. See section <xref linkend="configuration-file-settings"/>
     for more details.
   </para>
 
   <sect2 id="configuration-file-format" xreflabel="configuration file format">
 
+    <title>Configuration file format</title>
+
     <indexterm>
       <primary>repmgr.conf</primary>
       <secondary>format</secondary>
     </indexterm>
 
-    <title>Configuration file format</title>
-
     <para>
       <filename>repmgr.conf</filename> is a plain text file with one parameter/value
       combination per line.
@@ -61,14 +62,79 @@ data_directory = /var/lib/pgsql/11/data</programlisting>
   </sect2>
 
 
+  <sect2 id="configuration-file-items" xreflabel="configuration file items">
+
+    <title>Configuration file items</title>
+    <para>
+      The following sections document some sections of the configuration file:
+       <itemizedlist>
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-settings"/>
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-optional-settings"/>
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-log-settings"/>
+            </simpara>
+          </listitem>
+
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-service-commands"/>
+            </simpara>
+          </listitem>
+
+       </itemizedlist>
+
+    </para>
+    <para>
+      For a full list of annotated configuration items, see the file
+      <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
+    </para>
+    <para>
+      For &repmgrd;-specific settings, see <xref linkend="repmgrd-configuration"/>.
+    </para>
+
+    <note>
+      <para>
+        The following parameters in the configuration file can be overridden with
+        command line options:
+        <itemizedlist>
+          <listitem>
+            <simpara>
+              <literal>-L/--log-level</literal> overrides <literal>log_level</literal> in
+              <filename>repmgr.conf</filename>
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              <literal>-b/--pg_bindir</literal> overrides <literal>pg_bindir</literal> in
+              <filename>repmgr.conf</filename>
+            </simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </note>
+
+  </sect2>
 
   <sect2 id="configuration-file-location" xreflabel="configuration file location">
+  <title>Configuration file location</title>
+
   <indexterm>
     <primary>repmgr.conf</primary>
     <secondary>location</secondary>
   </indexterm>
 
-  <title>Configuration file location</title>
 
   <para>
    The configuration file will be searched for in the following locations:
@@ -105,10 +171,10 @@ data_directory = /var/lib/pgsql/11/data</programlisting>
   <note>
     <para>
       If providing the configuration file location with <literal>-f/--config-file</literal>,
-      avoid using a relative path, particularly when executing <xref linkend="repmgr-primary-register">
-      and <xref linkend="repmgr-standby-register">, as &repmgr; stores the configuration file location
+      avoid using a relative path, particularly when executing <xref linkend="repmgr-primary-register"/>
+      and <xref linkend="repmgr-standby-register"/>, as &repmgr; stores the configuration file location
       in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
-      <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
+      <xref linkend="repmgr-standby-switchover"/>). &repmgr; will attempt to convert the
       a relative path into an absolute one, but this may not be the same as the path you
       would explicitly provide (e.g. <filename>./repmgr.conf</filename> might be converted
       to <filename>/path/to/./repmgr.conf</filename>, whereas you'd normally write

doc/configuration.xml

@@ -2,6 +2,8 @@
   <title>repmgr configuration</title>
 
   <sect1 id="configuration-prerequisites" xreflabel="Prerequisites for configuration">
+    <title>Prerequisites for configuration</title>
+
     <indexterm>
       <primary>configuration</primary>
       <secondary>prerequisites</secondary>
@@ -12,7 +14,6 @@
       <secondary>ssh</secondary>
     </indexterm>
 
-    <title>Prerequisites for configuration</title>
     <para>
      Following software must be installed on both servers:
      <itemizedlist spacing="compact" mark="bullet">
@@ -62,6 +63,8 @@
     </tip>
 
   <sect2 id="configuration-postgresql" xreflabel="PostgreSQL configuration">
+      <title>PostgreSQL configuration for &repmgr;</title>
+
     <indexterm>
       <primary>configuration</primary>
       <secondary>PostgreSQL</secondary>
@@ -71,7 +74,6 @@
       <primary>PostgreSQL configuration</primary>
     </indexterm>
 
-    <title>PostgreSQL configuration for &repmgr;</title>
     <para>
       The following PostgreSQL configuration parameters may need to be changed in order
       for &repmgr; (and replication itself) to function correctly.
@@ -81,13 +83,14 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>hot_standby</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>hot_standby</option></term>
         <listitem>
+
+          <indexterm>
+            <primary>hot_standby</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             <option>hot_standby</option> must always be set to <literal>on</literal>, as &repmgr; needs
             to be able to connect to each server it manages.
@@ -104,13 +107,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>wal_level</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>wal_level</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>wal_level</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             <option>wal_level</option> must be one of <option>replica</option> or <option>logical</option>
             (PostgreSQL 9.5 and earlier: one of <option>hot_standby</option> or <option>logical</option>).
@@ -123,13 +128,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>max_wal_senders</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>max_wal_senders</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>max_wal_senders</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             <option>max_wal_senders</option> must be set to a value of <literal>2</literal> or greater.
             In general you will need one WAL sender for each standby which will attach to the PostgreSQL
@@ -149,13 +156,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>max_replication_slots</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>max_replication_slots</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>max_replication_slots</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             If you are intending to use replication slots, <option>max_replication_slots</option>
             must be set to a non-zero value.
@@ -174,19 +183,20 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>wal_log_hints</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>wal_log_hints</option></term>
         <listitem>
+          <indexterm>
+            <primary>wal_log_hints</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
+
           <para>If you are intending to use <application>pg_rewind</application>,
             and the cluster was not initialised using data checksums, you may want to consider enabling
             <option>wal_log_hints</option>.
           </para>
           <para>
-            For more details see <xref linkend="repmgr-node-rejoin-pg-rewind">.
+            For more details see <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
           </para>
           <para>
             PostgreSQL documentation: <ulink url="https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-WAL-LOG-HINTS">wal_log_hints</ulink>.
@@ -196,13 +206,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>archive_mode</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>archive_mode</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>archive_mode</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             We suggest setting <option>archive_mode</option> to <literal>on</literal> (and
             <option>archive_command</option> to <literal>/bin/true</literal>; see below)
@@ -225,13 +237,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>archive_command</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>archive_command</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>archive_command</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             If you have set  <option>archive_mode</option> to <literal>on</literal> but are not currently planning
             to use WAL file archiving, set <option>archive_command</option> to a command which does nothing but returns
@@ -246,13 +260,15 @@
 
       <varlistentry>
 
-        <indexterm>
-          <primary>wal_keep_segments</primary>
-          <secondary>PostgreSQL configuration</secondary>
-        </indexterm>
-
         <term><option>wal_keep_segments</option></term>
+
         <listitem>
+
+          <indexterm>
+            <primary>wal_keep_segments</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
             Normally there is no need to set <option>wal_keep_segments</option> (default: <literal>0</literal>), as it
             is <emphasis>not</emphasis> a reliable way of ensuring that all required WAL segments are available to standbys.
@@ -289,16 +305,18 @@
 
   &configuration-file;
   &configuration-file-required-settings;
+  &configuration-file-optional-settings;
   &configuration-file-log-settings;
   &configuration-file-service-commands;
 
   <sect1 id="configuration-permissions" xreflabel="Database user permissions">
+    <title>repmgr database user permissions</title>
+
     <indexterm>
       <primary>configuration</primary>
       <secondary>database user permissions</secondary>
     </indexterm>
 
-    <title>repmgr database user permissions</title>
     <para>
       &repmgr; will create an extension database containing objects
       for administering &repmgr; metadata. The user defined in the <varname>conninfo</varname>

doc/configuring-witness-server.sgml

@@ -1,93 +0,0 @@
-<chapter id="using-witness-server">
- <indexterm>
-  <primary>witness server</primary>
- </indexterm>
-
-
- <title>Using a witness server</title>
- <para>
-   A <xref linkend="witness-server"> is a normal PostgreSQL instance which
-   is not part of the streaming replication cluster; its purpose is, if a
-   failover situation occurs, to provide proof that it is the primary server
-   itself which is unavailable, rather than e.g. a network split between
-   different physical locations.
- </para>
-
- <para>
-   A typical use case for a witness server is a two-node streaming replication
-   setup, where the primary and standby are in different locations (data centres).
-   By creating a witness server in the same location (data centre) as the primary,
-   if the primary becomes unavailable it's possible for the standby to decide whether
-   it can promote itself without risking a "split brain" scenario: if it can't see either the
-   witness or the primary server, it's likely there's a network-level interruption
-   and it should not promote itself. If it can see the witness but not the primary,
-   this proves there is no network interruption and the primary itself is unavailable,
-   and it can therefore promote itself (and ideally take action to fence the
-   former primary).
- </para>
- <note>
-   <para>
-     <emphasis>Never</emphasis> install a witness server on the same physical host
-     as another node in the replication cluster managed by &repmgr; - it's essential
-     the witness is not affected in any way by failure of another node.
-   </para>
- </note>
- <para>
-   For more complex replication scenarios,e.g. with multiple datacentres, it may
-   be preferable to use location-based failover, which ensures that only nodes
-   in the same location as the primary will ever be promotion candidates;
-   see <xref linkend="repmgrd-network-split"> for more details.
- </para>
-
- <note>
-   <simpara>
-     A witness server will only be useful if <application>repmgrd</application>
-     is in use.
-   </simpara>
- </note>
-
- <sect1 id="creating-witness-server">
-   <title>Creating a witness server</title>
- <para>
-   To create a witness server, set up a normal PostgreSQL instance on a server
-   in the same physical location as the cluster's primary server.
- </para>
- <para>
-   This instance should <emphasis>not</emphasis> be on the same physical host as the primary server,
-   as otherwise if the primary server fails due to hardware issues, the witness
-   server will be lost too.
- </para>
- <note>
-   <simpara>
-     &repmgr; 3.3 and earlier provided a <command>repmgr create witness</command>
-     command, which would automatically create a PostgreSQL instance. However
-     this often resulted in an unsatisfactory, hard-to-customise instance.
-   </simpara>
- </note>
- <para>
-   The witness server should be configured in the same way as a normal
-   &repmgr; node; see section <xref linkend="configuration">.
- </para>
- <para>
-   Register the witness server with <xref linkend="repmgr-witness-register">.
-   This will create the &repmgr; extension on the witness server, and make
-   a copy of the &repmgr; metadata.
- </para>
- <note>
-   <simpara>
-    As the witness server is not part of the replication cluster, further
-    changes to the &repmgr; metadata will be synchronised by
-    <application>repmgrd</application>.
-   </simpara>
- </note>
- <para>
-   Once the witness server has been configured, <application>repmgrd</application>
-   should be started; for more details see <xref linkend="repmgrd-witness-server">.
- </para>
-
- <para>
-  To unregister a witness server, use <xref linkend="repmgr-witness-unregister">.
- </para>
-
- </sect1>
-</chapter>

doc/event-notifications.xml

@@ -1,12 +1,12 @@
 <chapter id="event-notifications" xreflabel="event notifications">
+ <title>Event Notifications</title>
 
  <indexterm>
    <primary>event notifications</primary>
  </indexterm>
 
- <title>Event Notifications</title>
  <para>
-  Each time &repmgr; or <application>repmgrd</application> perform a significant event, a record
+  Each time &repmgr; or &repmgrd; perform a significant event, a record
   of that event is written into the <literal>repmgr.events</literal> table together with
   a timestamp, an indication of failure or success, and further details
   if appropriate. This is useful for gaining an overview of events
@@ -27,7 +27,7 @@
     (3 rows)</programlisting>
  </para>
  <para>
-  Alternatively, use <xref linkend="repmgr-cluster-event"> to output a
+  Alternatively, use <xref linkend="repmgr-cluster-event"/> to output a
   formatted list of events.
  </para>
  <para>
@@ -91,8 +91,7 @@
   may contain spaces, so should be quoted in the provided command
   configuration, e.g.:
   <programlisting>
-    event_notification_command='/path/to/some/script %n %e %s "%t" "%d"'
-  </programlisting>
+    event_notification_command='/path/to/some/script %n %e %s "%t" "%d"'</programlisting>
  </para>
 
  <para>
@@ -104,10 +103,10 @@
    <term><option>%p</option></term>
    <listitem>
     <para>
-     node ID of the current primary (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+     node ID of the current primary (<xref linkend="repmgr-standby-register"/> and <xref linkend="repmgr-standby-follow"/>)
     </para>
     <para>
-     node ID of the demoted primary (<xref linkend="repmgr-standby-switchover"> only)
+     node ID of the demoted primary (<xref linkend="repmgr-standby-switchover"/> only)
     </para>
    </listitem>
   </varlistentry>
@@ -116,7 +115,7 @@
    <listitem>
     <para>
      <literal>conninfo</literal> string of the primary node
-     (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+     (<xref linkend="repmgr-standby-register"/> and <xref linkend="repmgr-standby-follow"/>)
     </para>
     <para>
       <literal>conninfo</literal> string of the next available node
@@ -129,7 +128,7 @@
    <term><option>%a</option></term>
    <listitem>
     <para>
-     name of the current primary node (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+     name of the current primary node (<xref linkend="repmgr-standby-register"/> and <xref linkend="repmgr-standby-follow"/>)
     </para>
     <para>
      name of the next available node (<varname>bdr_failover</varname> and  <varname>bdr_recovery</varname>)
@@ -147,7 +146,10 @@
  <para>
   By default, all notification types will be passed to the designated script;
   the notification types can be filtered to explicitly named ones using the
-  <varname>event_notifications</varname> parameter.
+  <varname>event_notifications</varname> parameter, e.g.:
+    <programlisting>
+    event_notifications=primary_register,standby_register,witness_register</programlisting>
+
  </para>
 
  <para>
@@ -205,7 +207,7 @@
  </para>
 
  <para>
-   Events generated by <application>repmgrd</application> (streaming replication mode):
+   Events generated by &repmgrd; (streaming replication mode):
 
    <itemizedlist spacing="compact" mark="bullet">
    <listitem>
@@ -255,11 +257,24 @@
     <simpara><literal>standby_recovery</literal></simpara>
    </listitem>
 
+   <listitem>
+     <simpara><literal><link linkend="repmgrd-primary-child-disconnection-events">child_node_disconnect</link></literal></simpara>
+   </listitem>
+   <listitem>
+     <simpara><literal><link linkend="repmgrd-primary-child-disconnection-events">child_node_reconnect</link></literal></simpara>
+   </listitem>
+   <listitem>
+     <simpara><literal><link linkend="repmgrd-primary-child-disconnection-events">child_node_new_connect</link></literal></simpara>
+   </listitem>
+   <listitem>
+     <simpara><literal><link linkend="repmgrd-primary-child-disconnection-events">child_nodes_disconnect_command</link></literal></simpara>
+   </listitem>
+
    </itemizedlist>
  </para>
 
   <para>
-   Events generated by <application>repmgrd</application> (BDR mode):
+   Events generated by &repmgrd; (BDR mode):
    <itemizedlist spacing="compact" mark="bullet">
    <listitem>
     <simpara><literal>bdr_failover</literal></simpara>

doc/filelist.sgml

@@ -1,91 +0,0 @@
-<!-- doc/filelist.sgml -->
-
-<!ENTITY legal      SYSTEM "legal.sgml">
-
-<!ENTITY bookindex  SYSTEM "bookindex.sgml">
-
-<!--
- Some parts of the documentation are also source for some plain-text
- files used during installation.  To selectively ignore or include
- some parts (e.g., external xref's) when generating these files we use
- these parameter entities.  See also standalone-install.sgml.
- -->
-<!ENTITY % standalone-ignore  "INCLUDE">
-<!ENTITY % standalone-include "IGNORE">
-
-<!-- doc/filelist.sgml -->
-
-<!--
- By default, no index is included.  Use -i include-index on the command line
- to include it.
- -->
-<!ENTITY % include-index "IGNORE">
-
-<!--
- Create empty index element for processing by XSLT stylesheet.
- -->
-<!ENTITY % include-xslt-index "IGNORE">
-
-<!--
- Include external documentation sections
- -->
-
-<!ENTITY overview      SYSTEM "overview.sgml">
-<!ENTITY install SYSTEM "install.sgml">
-<!ENTITY install-requirements      SYSTEM "install-requirements.sgml">
-<!ENTITY install-packages      SYSTEM "install-packages.sgml">
-<!ENTITY install-source      SYSTEM "install-source.sgml">
-<!ENTITY quickstart      SYSTEM "quickstart.sgml">
-<!ENTITY configuration      SYSTEM "configuration.sgml">
-<!ENTITY configuration-file      SYSTEM "configuration-file.sgml">
-<!ENTITY configuration-file-required-settings      SYSTEM "configuration-file-required-settings.sgml">
-<!ENTITY configuration-file-log-settings      SYSTEM "configuration-file-log-settings.sgml">
-<!ENTITY configuration-file-service-commands   SYSTEM "configuration-file-service-commands.sgml">
-<!ENTITY cloning-standbys  SYSTEM "cloning-standbys.sgml">
-<!ENTITY promoting-standby  SYSTEM "promoting-standby.sgml">
-<!ENTITY follow-new-primary  SYSTEM "follow-new-primary.sgml">
-<!ENTITY switchover  SYSTEM "switchover.sgml">
-<!ENTITY configuring-witness-server SYSTEM "configuring-witness-server.sgml">
-
-<!ENTITY event-notifications  SYSTEM "event-notifications.sgml">
-<!ENTITY upgrading-repmgr  SYSTEM "upgrading-repmgr.sgml">
-
-<!ENTITY repmgrd-overview SYSTEM "repmgrd-overview.sgml">
-<!ENTITY repmgrd-automatic-failover SYSTEM "repmgrd-automatic-failover.sgml">
-<!ENTITY repmgrd-configuration SYSTEM "repmgrd-configuration.sgml">
-<!ENTITY repmgrd-operation SYSTEM "repmgrd-operation.sgml">
-<!ENTITY repmgrd-bdr SYSTEM "repmgrd-bdr.sgml">
-
-<!ENTITY repmgr-primary-register SYSTEM "repmgr-primary-register.sgml">
-<!ENTITY repmgr-primary-unregister SYSTEM "repmgr-primary-unregister.sgml">
-<!ENTITY repmgr-standby-clone SYSTEM "repmgr-standby-clone.sgml">
-<!ENTITY repmgr-standby-register SYSTEM "repmgr-standby-register.sgml">
-<!ENTITY repmgr-standby-unregister SYSTEM "repmgr-standby-unregister.sgml">
-<!ENTITY repmgr-standby-promote SYSTEM "repmgr-standby-promote.sgml">
-<!ENTITY repmgr-standby-follow SYSTEM "repmgr-standby-follow.sgml">
-<!ENTITY repmgr-standby-switchover SYSTEM "repmgr-standby-switchover.sgml">
-<!ENTITY repmgr-witness-register SYSTEM "repmgr-witness-register.sgml">
-<!ENTITY repmgr-witness-unregister SYSTEM "repmgr-witness-unregister.sgml">
-<!ENTITY repmgr-node-status SYSTEM "repmgr-node-status.sgml">
-<!ENTITY repmgr-node-check SYSTEM "repmgr-node-check.sgml">
-<!ENTITY repmgr-node-rejoin SYSTEM "repmgr-node-rejoin.sgml">
-<!ENTITY repmgr-node-service SYSTEM "repmgr-node-service.sgml">
-<!ENTITY repmgr-cluster-show SYSTEM "repmgr-cluster-show.sgml">
-<!ENTITY repmgr-cluster-matrix SYSTEM "repmgr-cluster-matrix.sgml">
-<!ENTITY repmgr-cluster-crosscheck SYSTEM "repmgr-cluster-crosscheck.sgml">
-<!ENTITY repmgr-cluster-event SYSTEM "repmgr-cluster-event.sgml">
-<!ENTITY repmgr-cluster-cleanup SYSTEM "repmgr-cluster-cleanup.sgml">
-<!ENTITY repmgr-daemon-status SYSTEM "repmgr-daemon-status.sgml">
-<!ENTITY repmgr-daemon-start SYSTEM "repmgr-daemon-start.sgml">
-<!ENTITY repmgr-daemon-stop SYSTEM "repmgr-daemon-stop.sgml">
-<!ENTITY repmgr-daemon-pause SYSTEM "repmgr-daemon-pause.sgml">
-<!ENTITY repmgr-daemon-unpause SYSTEM "repmgr-daemon-unpause.sgml">
-
-<!ENTITY appendix-release-notes  SYSTEM "appendix-release-notes.sgml">
-<!ENTITY appendix-faq      SYSTEM "appendix-faq.sgml">
-<!ENTITY appendix-signatures      SYSTEM "appendix-signatures.sgml">
-<!ENTITY appendix-packages      SYSTEM "appendix-packages.sgml">
-<!ENTITY appendix-support SYSTEM "appendix-support.sgml">
-
-<!ENTITY bookindex  SYSTEM "bookindex.sgml">
-

doc/filelist.xml

@@ -0,0 +1,70 @@
+<!-- doc/filelist.xml -->
+
+<!ENTITY legal      SYSTEM "legal.xml">
+
+<!ENTITY bookindex  SYSTEM "bookindex.xml">
+
+
+<!--
+ Include external documentation sections
+ -->
+
+<!ENTITY overview      SYSTEM "overview.xml">
+<!ENTITY install SYSTEM "install.xml">
+<!ENTITY install-requirements      SYSTEM "install-requirements.xml">
+<!ENTITY install-packages      SYSTEM "install-packages.xml">
+<!ENTITY install-source      SYSTEM "install-source.xml">
+<!ENTITY quickstart      SYSTEM "quickstart.xml">
+<!ENTITY configuration      SYSTEM "configuration.xml">
+<!ENTITY configuration-file      SYSTEM "configuration-file.xml">
+<!ENTITY configuration-file-required-settings      SYSTEM "configuration-file-required-settings.xml">
+<!ENTITY configuration-file-optional-settings      SYSTEM "configuration-file-optional-settings.xml">
+<!ENTITY configuration-file-log-settings      SYSTEM "configuration-file-log-settings.xml">
+<!ENTITY configuration-file-service-commands   SYSTEM "configuration-file-service-commands.xml">
+<!ENTITY cloning-standbys  SYSTEM "cloning-standbys.xml">
+<!ENTITY promoting-standby  SYSTEM "promoting-standby.xml">
+<!ENTITY follow-new-primary  SYSTEM "follow-new-primary.xml">
+<!ENTITY switchover  SYSTEM "switchover.xml">
+
+<!ENTITY event-notifications  SYSTEM "event-notifications.xml">
+<!ENTITY upgrading-repmgr  SYSTEM "upgrading-repmgr.xml">
+
+<!ENTITY repmgrd-overview SYSTEM "repmgrd-overview.xml">
+<!ENTITY repmgrd-automatic-failover SYSTEM "repmgrd-automatic-failover.xml">
+<!ENTITY repmgrd-configuration SYSTEM "repmgrd-configuration.xml">
+<!ENTITY repmgrd-operation SYSTEM "repmgrd-operation.xml">
+<!ENTITY repmgrd-bdr SYSTEM "repmgrd-bdr.xml">
+
+<!ENTITY repmgr-primary-register SYSTEM "repmgr-primary-register.xml">
+<!ENTITY repmgr-primary-unregister SYSTEM "repmgr-primary-unregister.xml">
+<!ENTITY repmgr-standby-clone SYSTEM "repmgr-standby-clone.xml">
+<!ENTITY repmgr-standby-register SYSTEM "repmgr-standby-register.xml">
+<!ENTITY repmgr-standby-unregister SYSTEM "repmgr-standby-unregister.xml">
+<!ENTITY repmgr-standby-promote SYSTEM "repmgr-standby-promote.xml">
+<!ENTITY repmgr-standby-follow SYSTEM "repmgr-standby-follow.xml">
+<!ENTITY repmgr-standby-switchover SYSTEM "repmgr-standby-switchover.xml">
+<!ENTITY repmgr-witness-register SYSTEM "repmgr-witness-register.xml">
+<!ENTITY repmgr-witness-unregister SYSTEM "repmgr-witness-unregister.xml">
+<!ENTITY repmgr-node-status SYSTEM "repmgr-node-status.xml">
+<!ENTITY repmgr-node-check SYSTEM "repmgr-node-check.xml">
+<!ENTITY repmgr-node-rejoin SYSTEM "repmgr-node-rejoin.xml">
+<!ENTITY repmgr-node-service SYSTEM "repmgr-node-service.xml">
+<!ENTITY repmgr-cluster-show SYSTEM "repmgr-cluster-show.xml">
+<!ENTITY repmgr-cluster-matrix SYSTEM "repmgr-cluster-matrix.xml">
+<!ENTITY repmgr-cluster-crosscheck SYSTEM "repmgr-cluster-crosscheck.xml">
+<!ENTITY repmgr-cluster-event SYSTEM "repmgr-cluster-event.xml">
+<!ENTITY repmgr-cluster-cleanup SYSTEM "repmgr-cluster-cleanup.xml">
+<!ENTITY repmgr-daemon-status SYSTEM "repmgr-daemon-status.xml">
+<!ENTITY repmgr-daemon-start SYSTEM "repmgr-daemon-start.xml">
+<!ENTITY repmgr-daemon-stop SYSTEM "repmgr-daemon-stop.xml">
+<!ENTITY repmgr-daemon-pause SYSTEM "repmgr-daemon-pause.xml">
+<!ENTITY repmgr-daemon-unpause SYSTEM "repmgr-daemon-unpause.xml">
+
+<!ENTITY appendix-release-notes  SYSTEM "appendix-release-notes.xml">
+<!ENTITY appendix-faq      SYSTEM "appendix-faq.xml">
+<!ENTITY appendix-signatures      SYSTEM "appendix-signatures.xml">
+<!ENTITY appendix-packages      SYSTEM "appendix-packages.xml">
+<!ENTITY appendix-support SYSTEM "appendix-support.xml">
+
+<!ENTITY bookindex  SYSTEM "bookindex.xml">
+

doc/follow-new-primary.xml

@@ -1,18 +1,19 @@
 <chapter id="follow-new-primary">
+ <title>Following a new primary</title>
+
  <indexterm>
   <primary>Following a new primary</primary>
   <seealso>repmgr standby follow</seealso>
  </indexterm>
 
- <title>Following a new primary</title>
  <para>
    Following the failure or removal of the replication cluster's existing primary
-   server, <xref linkend="repmgr-standby-follow"> can be used to make 'orphaned' standbys
+   server, <xref linkend="repmgr-standby-follow"/> can be used to make &quot;orphaned&quot; standbys
    follow the new primary and catch up to its current state.
  </para>
  <para>
   To demonstrate this, assuming a replication cluster in the same state as the
-  end of the preceding section (<xref linkend="promoting-standby">),
+  end of the preceding section (<xref linkend="promoting-standby"/>),
   execute this:
   <programlisting>
     $ repmgr -f /etc/repmgr.conf standby follow

doc/install-packages.xml

@@ -13,12 +13,13 @@
 
  <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, CentOS and Fedora">
 
+  <title>RedHat/CentOS/Fedora</title>
+
   <indexterm>
    <primary>installation</primary>
    <secondary>on Red Hat/CentOS/Fedora etc.</secondary>
   </indexterm>
 
-  <title>RedHat/CentOS/Fedora</title>
   <para>
 	&repmgr; RPM packages for RedHat/CentOS variants and Fedora are available from the
 	<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
@@ -46,7 +47,7 @@
   <para>
     For more information on the package contents, including details of installation
     paths and relevant <link linkend="configuration-file-service-commands">service commands</link>,
-    see the appendix section <xref linkend="packages-centos">.
+    see the appendix section <xref linkend="packages-centos"/>.
   </para>
 
 
@@ -105,7 +106,7 @@ sudo yum repolist</programlisting>
 
         <listitem>
           <para>
-            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
 sudo yum install repmgr10</programlisting>
           </para>
@@ -181,12 +182,13 @@ yum search repmgr</programlisting>
 
  <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
 
+  <title>Debian/Ubuntu</title>
+
   <indexterm>
    <primary>installation</primary>
    <secondary>on Debian/Ubuntu etc.</secondary>
   </indexterm>
 
-  <title>Debian/Ubuntu</title>
   <para>.deb packages for &repmgr; are available from the
   PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
   Instructions can be found in the APT section of the PostgreSQL Wiki
@@ -195,7 +197,7 @@ yum search repmgr</programlisting>
   <para>
     For more information on the package contents, including details of installation
     paths and relevant <link linkend="configuration-file-service-commands">service commands</link>,
-    see the appendix section <xref linkend="packages-debian-ubuntu">.
+    see the appendix section <xref linkend="packages-debian-ubuntu"/>.
   </para>
 
   <sect3 id="installation-packages-debian-ubuntu-2ndq">
@@ -242,7 +244,7 @@ curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlist
 
 	<listitem>
 	  <para>
-            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
 sudo apt-get install postgresql-10-repmgr</programlisting>
 	  </para>

doc/install-requirements.xml

@@ -1,11 +1,12 @@
 <sect1 id="install-requirements" xreflabel="installation requirements">
 
+  <title>Requirements for installing repmgr</title>
+
   <indexterm>
    <primary>installation</primary>
    <secondary>requirements</secondary>
   </indexterm>
 
-  <title>Requirements for installing repmgr</title>
   <para>
     repmgr is developed and tested on Linux and OS X, but should work on any
     UNIX-like system supported by PostgreSQL itself. There is no support for
@@ -20,7 +21,7 @@
 
   <note>
    <simpara>
-    If upgrading from &repmgr; 3.x, please see the section <xref linkend="upgrading-from-repmgr-3">.
+    If upgrading from &repmgr; 3.x, please see the section <xref linkend="upgrading-from-repmgr-3"/>.
    </simpara>
   </note>
 
@@ -45,14 +46,14 @@
    </simpara>
    <simpara>
      If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x)
-     are installed on different nodes, in the best case &repmgr; (in particular <application>repmgrd</application>)
+     are installed on different nodes, in the best case &repmgr; (in particular &repmgrd;)
      will not run. In the worst case, you will end up with a broken cluster.
    </simpara>
   </note>
 
   <para>
    A dedicated system user for &repmgr; is <emphasis>not</emphasis> required; as many &repmgr; and
-   <application>repmgrd</application> actions require direct access to the PostgreSQL data directory,
+   &repmgrd; actions require direct access to the PostgreSQL data directory,
    these commands should be executed by the <literal>postgres</literal> user.
   </para>
 
@@ -72,6 +73,8 @@
 
   <sect2 id="install-compatibility-matrix">
 
+    <title>&repmgr; compatibility matrix</title>
+
     <indexterm>
       <primary>repmgr</primary>
       <secondary>compatibility matrix</secondary>
@@ -81,7 +84,6 @@
       <primary>compatibility matrix</primary>
     </indexterm>
 
-    <title>&repmgr; compatibility matrix</title>
     <para>
       The following table provides an overview of which &repmgr; version supports
       which PostgreSQL version.
@@ -91,7 +93,7 @@
     <table id="repmgr-compatibility-matrix">
       <title>&repmgr; compatibility matrix</title>
 
-      <tgroup cols="2">
+      <tgroup cols="3">
         <thead>
           <row>
             <entry>

doc/install-source.xml

@@ -1,11 +1,12 @@
 <sect1 id="installation-source" xreflabel="Installing from source code">
-  <indexterm>
-   <primary>installation</primary>
-   <secondary>from source</secondary>
-  </indexterm>
 
  <title>Installing &repmgr; from source</title>
 
+ <indexterm>
+  <primary>installation</primary>
+  <secondary>from source</secondary>
+ </indexterm>
+
  <sect2 id="installation-source-prereqs">
   <title>Prerequisites for installing from source</title>
   <para>
@@ -61,28 +62,28 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
          <itemizedlist spacing="compact" mark="bullet">
 
            <listitem>
-             <simpara><literal>llibedit-dev</literal></simpara>
+             <simpara><literal>libedit-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibkrb5-dev</literal></simpara>
+             <simpara><literal>libkrb5-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibpam0g-dev</literal></simpara>
+             <simpara><literal>libpam0g-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibreadline-dev</literal></simpara>
+             <simpara><literal>libreadline-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibselinux1-dev</literal></simpara>
+             <simpara><literal>libselinux1-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibssl-dev</literal></simpara>
+             <simpara><literal>libssl-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibxml2-dev</literal></simpara>
+             <simpara><literal>libxml2-dev</literal></simpara>
            </listitem>
            <listitem>
-             <simpara><literal>llibxslt1-dev</literal></simpara>
+             <simpara><literal>libxslt1-dev</literal></simpara>
            </listitem>
          </itemizedlist>
        </para>
@@ -136,6 +137,16 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
          </itemizedlist>
        </para>
      </note>
+
+     <tip>
+       <para>
+         If building against PostgreSQL 11 or later configured with the <option>--with-llvm</option> option
+         (this is the case with the PGDG-provided packages) you'll also need to install the
+         <literal>llvm-toolset-7-clang</literal> package. This is available via the
+         <ulink url="https://wiki.centos.org/AdditionalResources/Repositories/SCL">Software Collections (SCL) Repository</ulink>.
+       </para>
+     </tip>
+
     </listitem>
    </itemizedlist>
   </para>
@@ -190,7 +201,7 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
     &repmgr; website along with a tarball checksum and a matching GnuPG
     signature. See
     <ulink url="http://repmgr.org/">http://repmgr.org/</ulink>
-    for the download information. See <xref linkend="appendix-signatures">
+    for the download information. See <xref linkend="appendix-signatures"/>
     for information on verifying digital signatures.
    </para>
 
@@ -198,11 +209,11 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
     You will need to download the repmgr source, e.g. <filename>repmgr-4.0.tar.gz</filename>.
     You may optionally verify the package checksums from the
     <literal>.md5</literal> files and/or verify the GnuPG signatures
-    per <xref linkend="appendix-signatures">.
+    per <xref linkend="appendix-signatures"/>.
    </para>
 
    <para>
-    After you unpack the source code archives using <literal>tar xf</literal>
+    After you unpack the source code archives using <command>tar xf</command>
     the installation process is the same as if you were installing from a git
     clone.
    </para>
@@ -217,7 +228,7 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
    To installing &repmgr; from source, simply execute:
 
    <programlisting>
-    ./configure && make install</programlisting>
+    ./configure &amp;&amp; make install</programlisting>
 
    Ensure <command>pg_config</command> for the target PostgreSQL version is in
    <varname>$PATH</varname>.
@@ -226,16 +237,30 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
 
 
- <sect2 id="installation-build-repmgr-docs">
+ <sect2 id="installation-build-repmgr-docs" xreflabel="Building repmgr documentation">
    <title>Building &repmgr; documentation</title>
    <para>
     The &repmgr; documentation is (like the main PostgreSQL project)
-    written in DocBook format. To build it locally as HTML, you'll need to
+    written in DocBook XML format. To build it locally as HTML, you'll need to
     install the required packages as described in the
-    <ulink url="https://www.postgresql.org/docs/9.6/docguide-toolsets.html">
-      PostgreSQL documentation</ulink> then execute:
+    <ulink url="https://www.postgresql.org/docs/current/docguide-toolsets.html">PostgreSQL documentation</ulink>.
+   </para>
+   <para>
+	 The minimum PostgreSQL version for building the &repmgr; documentation is
+	 PostgreSQL 9.5.
+   </para>
+
+   <note>
+     <simpara>
+       In &repmgr; 4.3 and earlier, the documentation can only be built against
+       PostgreSQL 9.6 or earlier.
+     </simpara>
+   </note>
+
+   <para>
+     To build the documentation as HTML, execute:
    <programlisting>
-    ./configure && make install-doc</programlisting>
+    ./configure &amp;&amp; make doc</programlisting>
    </para>
    <para>
      The generated HTML files will be placed in the <filename>doc/html</filename>
@@ -243,19 +268,20 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
    </para>
 
    <para>
-     To build the documentation as a single HTML file, execute:
+     To build the documentation as a single HTML file, after configuring and building
+     the main &repmgr; source as described above, execute:
    <programlisting>
-    cd doc/ && make repmgr.html</programlisting>
+     ./configure &amp;&amp; make doc-repmgr.html</programlisting>
    </para>
 
-   <note>
-     <simpara>
-       Due to changes in PostgreSQL's documentation build system from PostgreSQL 10,
-       the documentation can currently only be built against PostgreSQL 9.6 or earlier.
-       This limitation will be fixed when time and resources permit.
-     </simpara>
-   </note>
+   <para>
+     To build the documentation as a PDF file, after configuring and building
+     the main &repmgr; source as described above, execute:
+   <programlisting>
+     ./configure &amp;&amp; make doc-repmgr-A4.pdf</programlisting>
+   </para>
+
+
  </sect2>
 
-
 </sect1>

doc/install.xml

@@ -1,10 +1,11 @@
 <chapter id="installation" xreflabel="Installation">
+
+ <title>Installation</title>
+
  <indexterm>
   <primary>installation</primary>
  </indexterm>
 
- <title>Installation</title>
-
  <para>
   &repmgr; can be installed from binary packages provided by your operating
   system's packaging system, or from source.
@@ -18,7 +19,7 @@
   only option if there are no packages for your operating system yet.
  </para>
  <para>
-  Before installing &repmgr; make sure you satisfy the <xref linkend="install-requirements">.
+  Before installing &repmgr; make sure you satisfy the <xref linkend="install-requirements"/>.
  </para>
 
  &install-requirements;

doc/legal.xml

@@ -1,4 +1,4 @@
-<!-- doc/legal.sgml -->
+<!-- doc/legal.xml -->
 
 <date>2017</date>
 

doc/overview.xml

@@ -7,18 +7,18 @@
  </para>
  <sect1 id="repmgr-concepts" xreflabel="Concepts">
 
+  <title>Concepts</title>
+
   <indexterm>
     <primary>concepts</primary>
   </indexterm>
 
-  <title>Concepts</title>
-
   <para>
    This guide assumes that you are familiar with PostgreSQL administration and
    streaming replication concepts. For further details on streaming
    replication, see the PostgreSQL documentation section on <ulink
-   url="https://www.postgresql.org/docs/current/interactive/warm-standby.html#STREAMING-REPLICATION">
-   streaming replication</>.
+   url="https://www.postgresql.org/docs/current/warm-standby.html#STREAMING-REPLICATION">
+   streaming replication</ulink>.
   </para>
   <para>
    The following terms are used throughout the &repmgr; documentation.
@@ -58,7 +58,7 @@
      <listitem>
       <simpara>
        This is the action which occurs if a primary server fails and a suitable standby
-       is  promoted as the new primary. The <application>repmgrd</application> daemon supports automatic failover
+       is  promoted as the new primary. The &repmgrd; daemon supports automatic failover
        to minimise downtime.
       </simpara>
      </listitem>
@@ -107,7 +107,7 @@
         promotes a (local) standby.
       </para>
       <para>
-        A witness server only needs to be created if <application>repmgrd</application>
+        A witness server only needs to be created if &repmgrd;
         is in use.
       </para>
      </listitem>
@@ -198,7 +198,7 @@
         </listitem>
         <listitem>
           <simpara><literal>repmgr.monitoring_history</literal>: historical standby monitoring information
-            written by <application>repmgrd</application></simpara>
+            written by &repmgrd;</simpara>
         </listitem>
        </itemizedlist>
       </para>
@@ -214,7 +214,7 @@
            name of the server's upstream node</simpara>
         </listitem>
         <listitem>
-          <simpara>repmgr.replication_status: when <application>repmgrd</application>'s monitoring is enabled, shows
+          <simpara>repmgr.replication_status: when &repmgrd;'s monitoring is enabled, shows
             current monitoring status for each standby.</simpara>
         </listitem>
        </itemizedlist>

doc/promoting-standby.xml

@@ -1,13 +1,13 @@
 <chapter id="promoting-standby" xreflabel="Promoting a standby">
+ <title>Promoting a standby server with repmgr</title>
  <indexterm>
    <primary>promoting a standby</primary>
    <seealso>repmgr standby promote</seealso>
  </indexterm>
- <title>Promoting a standby server with repmgr</title>
  <para>
    If a primary server fails or needs to be removed from the replication cluster,
    a new primary server must be designated, to ensure the cluster continues
-   to function correctly. This can be done with <xref linkend="repmgr-standby-promote">,
+   to function correctly. This can be done with <xref linkend="repmgr-standby-promote"/>,
    which promotes the standby on the current server to primary.
  </para>
 
@@ -31,7 +31,7 @@
   At this point the replication cluster will be in a partially disabled state, with
   both standbys accepting read-only connections while attempting to connect to the
   stopped primary. Note that the &repmgr; metadata table will not yet have been updated;
-  executing <xref linkend="repmgr-cluster-show"> will note the discrepancy:
+  executing <xref linkend="repmgr-cluster-show"/> will note the discrepancy:
   <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
      ID | Name  | Role    | Status        | Upstream | Location | Connection string
@@ -60,7 +60,7 @@
     DETAIL: node 2 was successfully promoted to primary</programlisting>
  </para>
  <para>
-  Executing <xref linkend="repmgr-cluster-show"> will show the current state; as there is now an
+  Executing <xref linkend="repmgr-cluster-show"/> will show the current state; as there is now an
   active primary, the previous warning will not be displayed:
   <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
@@ -72,8 +72,8 @@
  </para>
  <para>
   However the sole remaining standby (<literal>node3</literal>) is still trying to replicate from the failed
-  primary; <xref linkend="repmgr-standby-follow"> must now be executed to rectify this situation
-  (see <xref linkend="follow-new-primary"> for example).
+  primary; <xref linkend="repmgr-standby-follow"/> must now be executed to rectify this situation
+  (see <xref linkend="follow-new-primary"/> for example).
  </para>
 </chapter>
 

doc/quickstart.xml

@@ -17,7 +17,7 @@
  <note>
    <simpara>
      To upgrade an existing &repmgr; 3.x installation, see section
-     <xref linkend="upgrading-from-repmgr-3">.
+     <xref linkend="upgrading-from-repmgr-3"/>.
    </simpara>
  </note>
 
@@ -76,19 +76,25 @@
    </para>
    <programlisting>
 
-    # Enable replication connections; set this figure to at least one more
+    # Enable replication connections; set this value to at least one more
     # than the number of standbys which will connect to this server
-    # (note that repmgr will execute `pg_basebackup` in WAL streaming mode,
-    # which requires two free WAL senders)
+    # (note that repmgr will execute "pg_basebackup" in WAL streaming mode,
+    # which requires two free WAL senders).
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-WAL-SENDERS
 
     max_wal_senders = 10
 
-    # Enable replication slots; set this figure to at least one more
+    # If using replication slots, set this value to at least one more
     # than the number of standbys which will connect to this server.
     # Note that repmgr will only make use of replication slots if
-    # "use_replication_slots" is set to "true" in repmgr.conf
+    # "use_replication_slots" is set to "true" in "repmgr.conf".
+    # (If you are not intending to use replication slots, this value
+    # can be set to "0").
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-REPLICATION-SLOTS
 
-    max_replication_slots = 0
+    max_replication_slots = 10
 
     # Ensure WAL files contain enough information to enable read-only queries
     # on the standby.
@@ -103,33 +109,41 @@
 
     # Enable read-only queries on a standby
     # (Note: this will be ignored on a primary but we recommend including
-    # it anyway)
+    # it anyway, in case the primary later becomes a standby)
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-HOT-STANDBY
 
     hot_standby = on
 
     # Enable WAL file archiving
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-ARCHIVE-MODE
+
     archive_mode = on
 
-    # Set archive command to a script or application that will safely store
-    # you WALs in a secure place. /bin/true is an example of a command that
-    # ignores archiving. Use something more sensible.
+    # Set archive command to a dummy command; this can later be changed without
+    # needing to restart the PostgreSQL instance.
+    #
+    # See: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-ARCHIVE-COMMAND
+
     archive_command = '/bin/true'
    </programlisting>
    <tip>
     <simpara>
       Rather than editing these settings in the default <filename>postgresql.conf</filename>
-     file, create a separate file such as <filename>postgresql.replication.conf</filename> and
+      file, create a separate file such as <filename>postgresql.replication.conf</filename> and
       include it from the end of the main configuration file with:
-     <command>include 'postgresql.replication.conf</command>.
+     <command>include 'postgresql.replication.conf'</command>.
     </simpara>
    </tip>
    <para>
      Additionally, if you are intending to use <application>pg_rewind</application>,
      and the cluster was not initialised using data checksums, you may want to consider enabling
-     <varname>wal_log_hints</varname>; for more details see <xref linkend="repmgr-node-rejoin-pg-rewind">.
+     <varname>wal_log_hints</varname>; for more details see <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
    </para>
     <para>
-      See also the <link linkend="configuration-postgresql">PostgreSQL configuration</link> section in the <link linkend="configuration">repmgr configuaration guide</link>.
+      See also the <link linkend="configuration-postgresql">PostgreSQL configuration</link> section in the
+      <link linkend="configuration">repmgr configuration guide</link>.
     </para>
  </sect1>
 
@@ -248,7 +262,7 @@
   <para>
    <filename>repmgr.conf</filename> should not be stored inside the PostgreSQL data directory,
    as it could be overwritten when setting up or reinitialising the PostgreSQL
-   server. See sections <xref linkend="configuration"> and <xref linkend="configuration-file">
+   server. See sections <xref linkend="configuration"/> and <xref linkend="configuration-file"/>
    for further details about <filename>repmgr.conf</filename>.
   </para>
 
@@ -289,7 +303,7 @@
 
   <para>
    See the file
-   <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</>
+   <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>
     for details of all available configuration parameters.
   </para>
 
@@ -338,7 +352,7 @@
     slot_name        |
     config_file      | /etc/repmgr.conf</programlisting>
   <para>
-    Each server in the replication cluster will have its own record. If <application>repmgrd</application>
+    Each server in the replication cluster will have its own record. If &repmgrd;
     is in use, the fields <literal>upstream_node_id</literal>, <literal>active</literal> and
     <literal>type</literal> will be updated when the node's status or role changes.
   </para>

doc/repmgr-cluster-cleanup.xml

@@ -38,7 +38,7 @@
     <title>Notes</title>
 
     <para>
-      Monitoring history will only be written if <application>repmgrd</application> is active, and
+      Monitoring history will only be written if &repmgrd; is active, and
       <varname>monitoring_history</varname> is set to <literal>true</literal> in
       <filename>repmgr.conf</filename>.
     </para>
@@ -69,8 +69,8 @@
   <refsect1>
     <title>See also</title>
     <para>
-      For more details see the sections <xref linkend="repmgrd-monitoring"> and
-      <xref linkend="repmgrd-monitoring-configuration">.
+      For more details see the sections <xref linkend="repmgrd-monitoring"/> and
+      <xref linkend="repmgrd-monitoring-configuration"/>.
     </para>
   </refsect1>
 

doc/repmgr-cluster-crosscheck.xml

@@ -16,9 +16,9 @@
   <refsect1>
     <title>Description</title>
     <para>
-      <command>repmgr cluster crosscheck</command> is similar to <xref linkend="repmgr-cluster-matrix">,
+      <command>repmgr cluster crosscheck</command> is similar to <xref linkend="repmgr-cluster-matrix"/>,
         but cross-checks connections between each combination of nodes. In "Example 3" in
-        <xref linkend="repmgr-cluster-matrix"> we have no information about the state of <literal>node3</literal>.
+        <xref linkend="repmgr-cluster-matrix"/> we have no information about the state of <literal>node3</literal>.
         However by running <command>repmgr cluster crosscheck</command> it's possible to get a better
         overview of the cluster situation:
           <programlisting>

doc/repmgr-cluster-event.xml

@@ -40,12 +40,12 @@
           <simpara><literal>--node-name</literal>: restrict entries to node with this name</simpara>
         </listitem>
         <listitem>
-          <simpara><literal>--event</literal>: filter specific event (see <xref linkend="event-notifications"> for a full list)</simpara>
+          <simpara><literal>--event</literal>: filter specific event (see <xref linkend="event-notifications"/> for a full list)</simpara>
         </listitem>
       </itemizedlist>
     </para>
     <para>
-      The "Details" column can be omitted by providing <literal>--terse</literal>.
+      The &quot;Details&quot; column can be omitted by providing <literal>--compact</literal>.
     </para>
   </refsect1>
 
@@ -71,9 +71,9 @@
       <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster event --event=standby_register
      Node ID | Name  | Event            | OK | Timestamp           | Details
-    ---------+-------+------------------+----+---------------------+--------------------------------
-     3       | node3 | standby_register | t  | 2017-08-17 10:28:55 | standby registration succeeded
-     2       | node2 | standby_register | t  | 2017-08-17 10:28:53 | standby registration succeeded</programlisting>
+    ---------+-------+------------------+----+---------------------+-------------------------------------------------------
+     3       | node3 | standby_register | t  | 2019-04-16 10:59:59 | standby registration succeeded; upstream node ID is 1
+     2       | node2 | standby_register | t  | 2019-04-16 10:59:57 | standby registration succeeded; upstream node ID is 1</programlisting>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-cluster-matrix.xml

@@ -93,7 +93,7 @@
    connection from <literal>node3</literal>.
   </para>
   <para>
-    In this case, the <xref linkend="repmgr-cluster-crosscheck"> command will produce a more
+    In this case, the <xref linkend="repmgr-cluster-crosscheck"/> command will produce a more
     useful result.
   </para>
   </refsect1>

doc/repmgr-cluster-show.xml

@@ -22,11 +22,13 @@
       directly and can be run on any node in the cluster; this is also useful when analyzing
       connectivity from a particular node.
     </para>
-
+	<para>
+	  For PostgreSQL 9.6 and later, the output will also contain the node's current timeline ID.
+	</para>
     <para>
       Node availability is tested by connecting from the node where
       <command>repmgr cluster show</command> is executed, and does not necessarily imply the node
-      is down. See <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck"> to get
+      is down. See <xref linkend="repmgr-cluster-matrix"/> and <xref linkend="repmgr-cluster-crosscheck"/> to get
       better overviews of connections between nodes.
     </para>
 
@@ -52,11 +54,11 @@
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
 
-     ID | Name  | Role    | Status    | Upstream | Location | Priority | Connection string
+     ID | Name  | Role    | Status    | Upstream | Location | Priority | Timeline | Connection string
     ----+-------+---------+-----------+----------+----------+----------+-----------------------------------------
-     1  | node1 | primary | * running |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
-     2  | node2 | standby |   running | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr</programlisting>
+     1  | node1 | primary | * running |          | default  | 100      | 1        | host=db_node1 dbname=repmgr user=repmgr
+     2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=db_node2 dbname=repmgr user=repmgr
+     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr</programlisting>
   </para>
   </refsect1>
   <refsect1>
@@ -101,7 +103,7 @@
 	</para>
 	<tip>
 	  <para>
-		Use <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck">
+		Use <xref linkend="repmgr-cluster-matrix"/> and <xref linkend="repmgr-cluster-crosscheck"/>
 		to diagnose connection issues across the whole replication cluster.
 	  </para>
 	</tip>
@@ -196,11 +198,31 @@
         </listitem>
       </varlistentry>
 
+      <varlistentry>
+        <term><option>ERR_BAD_CONFIG (1)</option></term>
+        <listitem>
+          <para>
+            An issue was encountered while attempting to retrieve
+            &repmgr; metadata.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_DB_CONN (6)</option></term>
+        <listitem>
+          <para>
+            &repmgr; was unable to connect to the local PostgreSQL instance.
+          </para>
+        </listitem>
+      </varlistentry>
+
       <varlistentry>
         <term><option>ERR_NODE_STATUS (25)</option></term>
         <listitem>
           <para>
-            One or more issues were detected.
+            One or more issues were detected with the replication configuration,
+            e.g. a node was not in its expected state.
           </para>
         </listitem>
       </varlistentry>
@@ -211,7 +233,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-status">, <xref linkend="repmgr-node-check">, <xref linkend="repmgr-daemon-status">
+     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-pause.xml

@@ -14,30 +14,30 @@
 
   <refnamediv>
     <refname>repmgr daemon pause</refname>
-    <refpurpose>Instruct all <application>repmgrd</application> instances in the replication cluster to pause failover operations</refpurpose>
+    <refpurpose>Instruct all &repmgrd; instances in the replication cluster to pause failover operations</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
       This command can be run on any active node in the replication cluster to instruct all
-      running <application>repmgrd</application> instances to &quot;pause&quot; themselves, i.e. take no
+      running &repmgrd; instances to &quot;pause&quot; themselves, i.e. take no
       action (such as promoting themselves or following a new primary) if a failover event is detected.
     </para>
     <para>
       This functionality is useful for performing maintenance operations, such as switchovers
-      or upgrades, which might otherwise trigger a failover if <application>repmgrd</application>
+      or upgrades, which might otherwise trigger a failover if &repmgrd;
       is running normally.
     </para>
     <note>
       <para>
         It's important to wait a few seconds after restarting PostgreSQL on any node before running
-        <command>repmgr daemon pause</command>, as the <application>repmgrd</application> instance
+        <command>repmgr daemon pause</command>, as the &repmgrd; instance
         on the restarted node will take a second or two before it has updated its status.
       </para>
     </note>
     <para>
-      <xref linkend="repmgr-daemon-unpause"> will instruct all previously paused <application>repmgrd</application>
+      <xref linkend="repmgr-daemon-unpause"/> will instruct all previously paused &repmgrd;
       instances to resume normal failover operation.
     </para>
   </refsect1>
@@ -69,7 +69,7 @@ NOTICE: node 3 (node3) paused</programlisting>
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check if nodes are reachable but don't pause <application>repmgrd</application>.
+            Check if nodes are reachable but don't pause &repmgrd;.
           </para>
         </listitem>
       </varlistentry>
@@ -87,7 +87,7 @@ NOTICE: node 3 (node3) paused</programlisting>
         <term><option>SUCCESS (0)</option></term>
         <listitem>
           <para>
-            <application>repmgrd</application> could be paused on all nodes.
+            &repmgrd; could be paused on all nodes.
           </para>
         </listitem>
       </varlistentry>
@@ -96,7 +96,7 @@ NOTICE: node 3 (node3) paused</programlisting>
         <term><option>ERR_REPMGRD_PAUSE (26)</option></term>
         <listitem>
           <para>
-           <application>repmgrd</application> could not be paused on one or mode nodes.
+           &repmgrd; could not be paused on one or mode nodes.
           </para>
         </listitem>
       </varlistentry>
@@ -107,7 +107,7 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-unpause">, <xref linkend="repmgr-daemon-status">
+      <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-daemon-start.xml

@@ -14,17 +14,17 @@
 
   <refnamediv>
     <refname>repmgr daemon start</refname>
-    <refpurpose>Start the <application>repmgrd</application> daemon</refpurpose>
+    <refpurpose>Start the &repmgrd; daemon</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
-      This command starts the <application>repmgrd</application> daemon on the
+      This command starts the &repmgrd; daemon on the
       local node.
     </para>
     <para>
-      By default, &repmgr; will wait for up to 15 seconds to confirm that <application>repmgrd</application>
+      By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
       started. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
@@ -33,7 +33,7 @@
       <para>
         The <filename>repmgr.conf</filename> parameter <varname>repmgrd_service_start_command</varname>
         must be set for <command>repmgr daemon start</command> to work; see section
-        <xref linkend="repmgr-daemon-start-configuration"> for details.
+        <xref linkend="repmgr-daemon-start-configuration"/> for details.
       </para>
     </important>
   </refsect1>
@@ -50,7 +50,7 @@
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check prerequisites but don't actually attempt to start <application>repmgrd</application>.
+            Check prerequisites but don't actually attempt to start &repmgrd;.
           </para>
           <para>
             This action will output the command which would be executed.
@@ -63,7 +63,7 @@
         <term><option>--wait</option></term>
         <listitem>
           <para>
-            Wait for the specified number of seconds to confirm that <application>repmgrd</application>
+            Wait for the specified number of seconds to confirm that &repmgrd;
             started successfully.
           </para>
           <para>
@@ -77,7 +77,7 @@
         <term><option>--no-wait</option></term>
         <listitem>
           <para>
-            Don't wait to confirm that <application>repmgrd</application>
+            Don't wait to confirm that &repmgrd;
             started successfully.
           </para>
           <para>
@@ -99,17 +99,18 @@
     <variablelist>
 
       <varlistentry>
-        <indexterm>
-          <primary>repmgrd_service_start_command</primary>
-          <secondary>with &quot;repmgr daemon start&quot;</secondary>
-        </indexterm>
 
         <term><option>repmgrd_service_start_command</option></term>
         <listitem>
+          <indexterm>
+            <primary>repmgrd_service_start_command</primary>
+            <secondary>with &quot;repmgr daemon start&quot;</secondary>
+          </indexterm>
+
           <para>
             <command>repmgr daemon start</command> will execute the command defined by the
             <varname>repmgrd_service_start_command</varname> parameter in <filename>repmgr.conf</filename>.
-            This must be set to a shell command which will start <application>repmgrd</application>;
+            This must be set to a shell command which will start &repmgrd;;
             if &repmgr; was installed from a package, this will be the service command defined by the
             package. For more details see <link linkend="appendix-packages">Appendix: &repmgr; package details</link>.
           </para>
@@ -117,7 +118,7 @@
             <para>
               If &repmgr; was installed from a system package, and you do not configure
               <varname>repmgrd_service_start_command</varname> to an appropriate service command, this may
-              result in the system becoming confused about the state of the <application>repmgrd</application>
+              result in the system becoming confused about the state of the &repmgrd;
               service; this is particularly the case with <literal>systemd</literal>.
             </para>
           </important>
@@ -139,12 +140,12 @@
         <term><option>SUCCESS (0)</option></term>
         <listitem>
           <para>
-            The <application>repmgrd</application> start command (defined in
+            The &repmgrd; start command (defined in
             <varname>repmgrd_service_start_command</varname>) was successfully executed.
           </para>
           <para>
             If the <option>--wait</option> option was provided, &repmgr; will confirm that
-            <application>repmgrd</application> has actually started up.
+            &repmgrd; has actually started up.
           </para>
         </listitem>
       </varlistentry>
@@ -167,10 +168,10 @@
             &repmgr; was unable to connect to the local PostgreSQL node.
           </para>
           <para>
-            PostgreSQL must be running before <application>repmgrd</application>
+            PostgreSQL must be running before &repmgrd;
             can be started. Additionally, unless the <option>--no-wait</option> option was
             provided, &repmgr; needs to be able to connect to the local PostgreSQL node
-            to determine the state of <application>repmgrd</application>.
+            to determine the state of &repmgrd;.
           </para>
         </listitem>
       </varlistentry>
@@ -180,11 +181,11 @@
         <term><option>ERR_REPMGRD_SERVICE (27)</option></term>
         <listitem>
           <para>
-            The <application>repmgrd</application> start command (defined in
+            The &repmgrd; start command (defined in
             <varname>repmgrd_service_start_command</varname>) was not successfully executed.
           </para>
           <para>
-            This can also mean that &repmgr; was unable to confirm whether <application>repmgrd</application>
+            This can also mean that &repmgr; was unable to confirm whether &repmgrd;
             successfully started (unless the <option>--no-wait</option> option was provided).
           </para>
         </listitem>
@@ -196,7 +197,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-stop">, <xref linkend="repmgr-daemon-status">, <xref linkend="repmgrd-daemon">
+      <xref linkend="repmgr-daemon-stop"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-status.xml

@@ -14,15 +14,15 @@
 
   <refnamediv>
     <refname>repmgr daemon status</refname>
-    <refpurpose>display information about the status of <application>repmgrd</application> on each node in the cluster</refpurpose>
+    <refpurpose>display information about the status of &repmgrd; on each node in the cluster</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
       This command provides an overview over all active nodes in the cluster and the state
-      of each node's <application>repmgrd</application> instance. It can be used to check
-      the result of <xref linkend="repmgr-daemon-pause"> and <xref linkend="repmgr-daemon-unpause">
+      of each node's &repmgrd; instance. It can be used to check
+      the result of <xref linkend="repmgr-daemon-pause"/> and <xref linkend="repmgr-daemon-unpause"/>
       operations.
     </para>
   </refsect1>
@@ -35,13 +35,13 @@
     </para>
     <para>
       If PostgreSQL is not running on a node, &repmgr; will not be able to determine the
-      status of that node's <application>repmgrd</application> instance.
+      status of that node's &repmgrd; instance.
     </para>
     <note>
       <para>
-        After restarting PostgreSQL on any node, the <application>repmgrd</application> instance
+        After restarting PostgreSQL on any node, the &repmgrd; instance
         will take a second or two before it is able to update its status. Until then,
-        <application>repmgrd</application> will be shown as not running.
+        &repmgrd; will be shown as not running.
       </para>
     </note>
 
@@ -50,35 +50,33 @@
   <refsect1>
     <title>Examples</title>
     <para>
-      <application>repmgrd</application> running normally on all nodes:
+      &repmgrd; running normally on all nodes:
     <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
- ID | Name  | Role    | Priority | Status  | repmgrd | PID   | Paused? | Upstream last seen
-----+-------+---------+----------+---------+---------+-------+---------+--------------------
- 1  | node1 | primary | 100      | running | running | 71987 | no      | n/a
- 2  | node2 | standby | 100      | running | running | 71996 | no      | 1 second(s) ago
- 3  | node3 | standby | 100      | running | running | 72042 | no      | 1 second(s) ago
-</programlisting>
+ ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
+----+-------+---------+-----------+----------+---------+-------+---------+--------------------
+ 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
+ 2  | node2 | standby |   running | node1    | running | 96572 | no      | 1 second(s) ago
+ 3  | node3 | standby |   running | node1    | running | 96584 | no      | 0 second(s) ago</programlisting>
     </para>
 
     <para>
-      <application>repmgrd</application> paused on all nodes (using <xref linkend="repmgr-daemon-pause">):
+      &repmgrd; paused on all nodes (using <xref linkend="repmgr-daemon-pause"/>):
     <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
- ID | Name  | Role    | Priority | Status  | repmgrd | PID   | Paused? | Upstream last seen
-----+-------+---------+----------+---------+---------+-------+---------+--------------------
- 1  | node1 | primary | 100      | running | running | 71987 | yes     | n/a
- 2  | node2 | standby | 100      | running | running | 71996 | yes     | 0 second(s) ago
- 3  | node3 | standby | 100      | running | running | 72042 | yes     | 0 second(s) ago
-</programlisting>
+ ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
+----+-------+---------+-----------+----------+---------+-------+---------+--------------------
+ 1  | node1 | primary | * running |          | running | 96563 | yes     | n/a
+ 2  | node2 | standby |   running | node1    | running | 96572 | yes     | 1 second(s) ago
+ 3  | node3 | standby |   running | node1    | running | 96584 | yes     | 0 second(s) ago</programlisting>
     </para>
 
     <para>
-      <application>repmgrd</application> not running on one node:
+      &repmgrd; not running on one node:
     <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
- ID | Name  | Role    | Priority | Status  | repmgrd     | PID   | Paused? | Upstream last seen
-----+-------+---------+----------+---------+-------------+-------+---------+--------------------
- 1  | node1 | primary | 100      | running | running     | 71987 | yes     | n/a
- 2  | node2 | standby | 100      | running | not running | n/a   | n/a     | n/a
- 3  | node3 | standby | 100      | running | running     | 72042 | yes     | 0 second(s) ago</programlisting>
+ ID | Name  | Role    | Status    | Upstream | repmgrd     | PID   | Paused? | Upstream last seen
+----+-------+---------+-----------+----------+-------------+-------+---------+--------------------
+ 1  | node1 | primary | * running |          | running     | 96563 | yes     | n/a
+ 2  | node2 | standby |   running | node1    | not running | n/a   | n/a     | n/a
+ 3  | node3 | standby |   running | node1    | running     | 96584 | yes     | 0 second(s) ago</programlisting>
     </para>
   </refsect1>
 
@@ -96,9 +94,9 @@
             parsing by scripts, e.g.:
             <programlisting>
     $ repmgr -f /etc/repmgr.conf daemon status --csv
-    1,node1,primary,1,1,5722,1,100,-1
-    2,node2,standby,1,0,-1,1,100,1
-    3,node3,standby,1,1,5779,1,100,1</programlisting>
+    1,node1,primary,1,1,5722,1,100,-1,default
+    2,node2,standby,1,0,-1,1,100,1,default
+    3,node3,standby,1,1,5779,1,100,1,default</programlisting>
           </para>
           <para>
             The columns have following meanings:
@@ -129,25 +127,25 @@
 
               <listitem>
                 <simpara>
-                  <application>repmgrd</application> running (1 = running, 0 = not running, -1 = unknown)
+                  &repmgrd; running (1 = running, 0 = not running, -1 = unknown)
                 </simpara>
               </listitem>
 
               <listitem>
                 <simpara>
-                  <application>repmgrd</application> PID (-1 if not running or status unknown)
+                  &repmgrd; PID (-1 if not running or status unknown)
                 </simpara>
               </listitem>
 
               <listitem>
                 <simpara>
-                  <application>repmgrd</application> paused (1 = paused, 0 = not paused, -1 = unknown)
+                  &repmgrd; paused (1 = paused, 0 = not paused, -1 = unknown)
                 </simpara>
               </listitem>
 
               <listitem>
                 <simpara>
-                  <application>repmgrd</application> node priority
+                  &repmgrd; node priority
                 </simpara>
               </listitem>
 
@@ -157,9 +155,25 @@
                 </simpara>
               </listitem>
 
+			  <listitem>
+                <simpara>
+                  node location
+                </simpara>
+              </listitem>
+
             </itemizedlist>
           </para>
         </listitem>
+	  </varlistentry>
+
+	  <varlistentry>
+        <term><option>--detail</option></term>
+        <listitem>
+          <para>
+            Display additional information (<literal>location</literal>, <literal>priority</literal>)
+			about the &repmgr; configuration.
+          </para>
+        </listitem>
       </varlistentry>
 
       <varlistentry>
@@ -175,12 +189,10 @@
 
   </refsect1>
 
-
-
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-pause">, <xref linkend="repmgr-daemon-unpause">, <xref linkend="repmgr-cluster-show">
+      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-cluster-show"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-daemon-stop.xml

@@ -14,25 +14,25 @@
 
   <refnamediv>
     <refname>repmgr daemon stop</refname>
-    <refpurpose>Stop the <application>repmgrd</application> daemon</refpurpose>
+    <refpurpose>Stop the &repmgrd; daemon</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
-      This command stops the <application>repmgrd</application> daemon on the
+      This command stops the &repmgrd; daemon on the
       local node.
     </para>
 
     <para>
-      By default, &repmgr; will wait for up to 15 seconds to confirm that <application>repmgrd</application>
+      By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
       stopped. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
     <note>
       <para>
         If PostgreSQL is not running on the local node, under some circumstances &repmgr; may not
-        be able to confirm if <application>repmgrd</application> has actually stopped.
+        be able to confirm if &repmgrd; has actually stopped.
       </para>
     </note>
 
@@ -40,7 +40,7 @@
       <para>
         The <filename>repmgr.conf</filename> parameter <varname>repmgrd_service_stop_command</varname>
         must be set for <command>repmgr daemon stop</command> to work; see section
-        <xref linkend="repmgr-daemon-stop-configuration"> for details.
+        <xref linkend="repmgr-daemon-stop-configuration"/> for details.
       </para>
     </important>
   </refsect1>
@@ -50,7 +50,7 @@
     <para>
       <command>repmgr daemon stop</command> will execute the command defined by the
       <varname>repmgrd_service_stop_command</varname> parameter in <filename>repmgr.conf</filename>.
-      This must be set to a shell command which will stop <application>repmgrd</application>;
+      This must be set to a shell command which will stop &repmgrd;;
       if &repmgr; was installed from a package, this will be the service command defined by the
       package. For more details see <link linkend="appendix-packages">Appendix: &repmgr; package details</link>.
     </para>
@@ -59,7 +59,7 @@
       <para>
         If &repmgr; was installed from a system package, and you do not configure
         <varname>repmgrd_service_stop_command</varname> to an appropriate service command, this may
-        result in the system becoming confused about the state of the <application>repmgrd</application>
+        result in the system becoming confused about the state of the &repmgrd;
         service; this is particularly the case with <literal>systemd</literal>.
       </para>
     </important>
@@ -76,7 +76,7 @@
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check prerequisites but don't actually attempt to stop <application>repmgrd</application>.
+            Check prerequisites but don't actually attempt to stop &repmgrd;.
           </para>
           <para>
             This action will output the command which would be executed.
@@ -89,7 +89,7 @@
         <term><option>--wait</option></term>
         <listitem>
           <para>
-            Wait for the specified number of seconds to confirm that <application>repmgrd</application>
+            Wait for the specified number of seconds to confirm that &repmgrd;
             stopped successfully.
           </para>
           <para>
@@ -103,7 +103,7 @@
         <term><option>--no-wait</option></term>
         <listitem>
           <para>
-            Don't wait to confirm that <application>repmgrd</application>
+            Don't wait to confirm that &repmgrd;
             stopped successfully.
           </para>
           <para>
@@ -124,17 +124,18 @@
     <variablelist>
 
       <varlistentry>
-        <indexterm>
-          <primary>repmgrd_service_stop_command</primary>
-          <secondary>with &quot;repmgr daemon stop&quot;</secondary>
-        </indexterm>
 
         <term><option>repmgrd_service_stop_command</option></term>
         <listitem>
+          <indexterm>
+            <primary>repmgrd_service_stop_command</primary>
+          <secondary>with &quot;repmgr daemon stop&quot;</secondary>
+          </indexterm>
+
           <para>
             <command>repmgr daemon stop</command> will execute the command defined by the
             <varname>repmgrd_service_stop_command</varname> parameter in <filename>repmgr.conf</filename>.
-            This must be set to a shell command which will stop <application>repmgrd</application>;
+            This must be set to a shell command which will stop &repmgrd;;
             if &repmgr; was installed from a package, this will be the service command defined by the
             package. For more details see <link linkend="appendix-packages">Appendix: &repmgr; package details</link>.
           </para>
@@ -142,7 +143,7 @@
             <para>
               If &repmgr; was installed from a system package, and you do not configure
               <varname>repmgrd_service_stop_command</varname> to an appropriate service command, this may
-              result in the system becoming confused about the state of the <application>repmgrd</application>
+              result in the system becoming confused about the state of the &repmgrd;
               service; this is particularly the case with <literal>systemd</literal>.
             </para>
           </important>
@@ -163,7 +164,7 @@
         <term><option>SUCCESS (0)</option></term>
         <listitem>
           <para>
-            <application>repmgrd</application> could be stopped.
+            &repmgrd; could be stopped.
           </para>
         </listitem>
       </varlistentry>
@@ -182,7 +183,7 @@
         <term><option>ERR_REPMGRD_SERVICE (27)</option></term>
         <listitem>
           <para>
-            <application>repmgrd</application> could not be stopped.
+            &repmgrd; could not be stopped.
           </para>
         </listitem>
       </varlistentry>
@@ -193,7 +194,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-start">, <xref linkend="repmgr-daemon-status">, <xref linkend="repmgrd-daemon">
+      <xref linkend="repmgr-daemon-start"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-unpause.xml

@@ -15,22 +15,22 @@
 
   <refnamediv>
     <refname>repmgr daemon unpause</refname>
-    <refpurpose>Instruct all <application>repmgrd</application> instances in the replication cluster to resume failover operations</refpurpose>
+    <refpurpose>Instruct all &repmgrd; instances in the replication cluster to resume failover operations</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
       This command can be run on any active node in the replication cluster to instruct all
-      running <application>repmgrd</application> instances to &quot;unpause&quot;
-      (following a previous execution of <xref linkend="repmgr-daemon-pause">)
+      running &repmgrd; instances to &quot;unpause&quot;
+      (following a previous execution of <xref linkend="repmgr-daemon-pause"/>)
       and resume normal failover/monitoring operation.
     </para>
 
     <note>
       <para>
         It's important to wait a few seconds after restarting PostgreSQL on any node before running
-        <command>repmgr daemon pause</command>, as the <application>repmgrd</application> instance
+        <command>repmgr daemon pause</command>, as the &repmgrd; instance
         on the restarted node will take a second or two before it has updated its status.
       </para>
     </note>
@@ -64,7 +64,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check if nodes are reachable but don't unpause <application>repmgrd</application>.
+            Check if nodes are reachable but don't unpause &repmgrd;.
           </para>
         </listitem>
       </varlistentry>
@@ -82,7 +82,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
         <term><option>SUCCESS (0)</option></term>
         <listitem>
           <para>
-            <application>repmgrd</application> could be unpaused on all nodes.
+            &repmgrd; could be unpaused on all nodes.
           </para>
         </listitem>
       </varlistentry>
@@ -91,7 +91,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
         <term><option>ERR_REPMGRD_PAUSE (26)</option></term>
         <listitem>
           <para>
-           <application>repmgrd</application> could not be unpaused on one or mode nodes.
+           &repmgrd; could not be unpaused on one or mode nodes.
           </para>
         </listitem>
       </varlistentry>
@@ -102,7 +102,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-pause">, <xref linkend="repmgr-daemon-status">
+      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-node-check.xml

@@ -203,7 +203,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-status">, <xref linkend="repmgr-cluster-show">
+     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-cluster-show"/>
     </para>
   </refsect1>
 

doc/repmgr-node-rejoin.xml

@@ -26,10 +26,10 @@
     <tip>
       <para>
         If the node is running and needs to be attached to the current primary, use
-        <xref linkend="repmgr-standby-follow">.
+        <xref linkend="repmgr-standby-follow"/>.
       </para>
       <para>
-        Note <xref linkend="repmgr-standby-follow"> can only be used for standbys which have not diverged
+        Note <xref linkend="repmgr-standby-follow"/> can only be used for standbys which have not diverged
         from the rest of the cluster.
       </para>
     </tip>
@@ -230,12 +230,13 @@
 
   <refsect1 id="repmgr-node-rejoin-pg-rewind" xreflabel="Using pg_rewind">
 
+   <title>Using <command>pg_rewind</command></title>
+
    <indexterm>
       <primary>pg_rewind</primary>
       <secondary>using with "repmgr node rejoin"</secondary>
     </indexterm>
 
-    <title>Using <command>pg_rewind</command></title>
     <para>
       <command>repmgr node rejoin</command> can optionally use <command>pg_rewind</command> to re-integrate a
       node which has diverged from the rest of the cluster, typically a failed primary.
@@ -321,7 +322,7 @@
         If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
         this checks the prerequisites for using <application>pg_rewind</application>, but is
         not an absolute guarantee that actually executing <application>pg_rewind</application>
-        will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"> below.
+        will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
       </para>
 
     </note>
@@ -344,12 +345,13 @@
 
   <refsect1 id="repmgr-node-rejoin-caveats" xreflabel="Caveats">
 
-   <indexterm>
-      <primary>repmgr node rejoin</primary>
-      <secondary>caveats</secondary>
-    </indexterm>
-
    <title>Caveats when using <command>repmgr node rejoin</command></title>
+
+   <indexterm>
+     <primary>repmgr node rejoin</primary>
+     <secondary>caveats</secondary>
+   </indexterm>
+
    <para>
      <command>repmgr node rejoin</command> attempts to determine whether it will succeed by
      comparing the timelines and relative WAL positions of the local node (rejoin candidate) and primary
@@ -381,7 +383,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-standby-follow">
+     <xref linkend="repmgr-standby-follow"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-node-status.xml

@@ -84,7 +84,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      See <xref linkend="repmgr-node-check"> to diagnose issues and <xref linkend="repmgr-cluster-show">
+      See <xref linkend="repmgr-node-check"/> to diagnose issues and <xref linkend="repmgr-cluster-show"/>
       for an overview of all nodes in the cluster.
     </para>
   </refsect1>

doc/repmgr-primary-register.xml

@@ -38,23 +38,25 @@
       Execute with the <option>--dry-run</option> option to check what would happen without
       actually registering the primary.
     </para>
-    <para>
-      <command>repmgr master register</command> can be used as an alias for
-      <command>repmgr primary register</command>.
-    </para>
 
     <note>
       <para>
         If providing the configuration file location with <option>-f/--config-file</option>,
         avoid using a relative path, as &repmgr; stores the configuration file location
         in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
-        <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
+        <xref linkend="repmgr-standby-switchover"/>). &repmgr; will attempt to convert the
           a relative path into an absolute one, but this may not be the same as the path you
           would explicitly provide (e.g. <filename>./repmgr.conf</filename> might be converted
           to <filename>/path/to/./repmgr.conf</filename>, whereas you'd normally write
           <filename>/path/to/repmgr.conf</filename>).
       </para>
     </note>
+
+	<para>
+      <command>repmgr master register</command> can be used as an alias for
+      <command>repmgr primary register</command>.
+    </para>
+
   </refsect1>
 
   <refsect1>

doc/repmgr-standby-clone.xml

@@ -85,12 +85,13 @@
   </refsect1>
 
   <refsect1 id="repmgr-standby-clone-recovery-conf">
-   <indexterm>
+    <title>Customising recovery.conf</title>
+    <indexterm>
      <primary>recovery.conf</primary>
      <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
-   </indexterm>
+    </indexterm>
+
 
-   <title>Customising recovery.conf</title>
    <para>
      By default, &repmgr; will create a minimal <filename>recovery.conf</filename>
      containing following parameters:
@@ -142,7 +143,7 @@
        We recommend using <ulink url="https://www.pgbarman.org/">Barman</ulink> to manage
        WAL file archiving. For more details on combining &repmgr; and <application>Barman</application>,
        in particular using <varname>restore_command</varname> to configure Barman as a backup source of
-       WAL files, see <xref linkend="cloning-from-barman">.
+       WAL files, see <xref linkend="cloning-from-barman"/>.
      </para>
    </note>
 
@@ -154,7 +155,7 @@
     When initially cloning a standby, you will need to ensure
     that all required WAL files remain available while the cloning is taking
     place. To ensure this happens when using the default <command>pg_basebackup</command> method,
-    &repmgr; will set <command>pg_basebackup</command>'s <literal>--xlog-method</literal>
+    &repmgr; will set <command>pg_basebackup</command>'s <literal>--wal-method</literal>
     parameter to <literal>stream</literal>,
     which will ensure all WAL files generated during the cloning process are
     streamed in parallel with the main backup. Note that this requires two
@@ -164,10 +165,10 @@
    </para>
    <para>
     To override this behaviour, in <filename>repmgr.conf</filename> set
-    <command>pg_basebackup</command>'s <literal>--xlog-method</literal>
+    <command>pg_basebackup</command>'s <literal>--wal-method</literal>
     parameter to <literal>fetch</literal>:
     <programlisting>
-      pg_basebackup_options='--xlog-method=fetch'</programlisting>
+      pg_basebackup_options='--wal-method=fetch'</programlisting>
 
     and ensure that <literal>wal_keep_segments</literal> is set to an appropriately high value.
     See the <ulink url="https://www.postgresql.org/docs/current/app-pgbasebackup.html">
@@ -176,9 +177,8 @@
 
    <note>
     <simpara>
-      From PostgreSQL 10, <command>pg_basebackup</command>'s
-      <literal>--xlog-method</literal> parameter has been renamed to
-      <literal>--wal-method</literal>.
+      If using PostgreSQL 9.6 or earlier, replace <literal>--wal-method</literal>
+      with <literal>--xlog-method</literal>.
     </simpara>
    </note>
   </refsect1>
@@ -186,12 +186,13 @@
 
   <refsect1 id="repmgr-standby-create-recovery-conf">
 
+   <title>Using a standby cloned by another method</title>
+
    <indexterm>
      <primary>recovery.conf</primary>
      <secondary>generating for a standby cloned by another method</secondary>
    </indexterm>
 
-   <title>Using a standby cloned by another method</title>
    <para>
      &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
      <command><ulink url="http://docs.pgbarman.org/release/2.5/#recover">barman recover</ulink></command> command).
@@ -296,7 +297,7 @@
         <term><option> --recovery-conf-only</option></term>
         <listitem>
           <para>
-            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr 4.0.4 and later.
+            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr; 4.0.4 and later.
           </para>
         </listitem>
       </varlistentry>
@@ -325,9 +326,13 @@
         <term><option>--upstream-conninfo</option></term>
         <listitem>
           <para>
-            <literal>primary_conninfo</literal> value to write in recovery.conf
+            <literal>primary_conninfo</literal> value to write in <filename>recovery.conf</filename>
             when the intended upstream server does not yet exist.
           </para>
+          <para>
+            Note that &repmgr; may modify the provided value, in particular to set the
+            correct <literal>application_name</literal>.
+          </para>
         </listitem>
       </varlistentry>
 
@@ -361,7 +366,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      See <xref linkend="cloning-standbys"> for details about various aspects of cloning.
+      See <xref linkend="cloning-standbys"/> for details about various aspects of cloning.
     </para>
   </refsect1>
 </refentry>

doc/repmgr-standby-follow.xml

@@ -41,7 +41,7 @@
 	<tip>
       <para>
 		To re-add an inactive node to the replication cluster, use
-		<xref linkend="repmgr-node-rejoin">.
+		<xref linkend="repmgr-node-rejoin"/>.
       </para>
 	</tip>
 
@@ -122,7 +122,7 @@
             If not provided, &repmgr; will attempt to follow the current primary node.
           </para>
           <para>
-            Note that when using <application>repmgrd</application>, <option>--upstream-node-id</option>
+            Note that when using &repmgrd;, <option>--upstream-node-id</option>
             should always be configured;
 			see <link linkend="repmgrd-automatic-failover-configuration">Automatic failover configuration</link>
             for details.
@@ -252,7 +252,7 @@ DETAIL: follow target server's timeline 2 forked off current database system tim
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-rejoin">
+     <xref linkend="repmgr-node-rejoin"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-standby-promote.xml

@@ -17,18 +17,50 @@
     <para>
       Promotes a standby to a primary if the current primary has failed. This
       command requires a valid <filename>repmgr.conf</filename> file for the standby, either
-      specified explicitly  with <literal>-f/--config-file</literal> or located in a
+      specified explicitly with <literal>-f/--config-file</literal> or located in a
       default location; no additional arguments are required.
     </para>
+    <important>
+      <para>
+        If &repmgrd; is active, you must execute
+        <command><link linkend="repmgr-daemon-pause">repmgr daemon pause</link></command>
+        to temporarily disable &repmgrd; while making any changes
+        to the replication cluster.
+      </para>
+    </important>
+
     <para>
       If the standby promotion succeeds, the server will not need to be
-      restarted. However any other standbys will need to follow the new server,
-      by using <xref linkend="repmgr-standby-follow">; if <application>repmgrd</application>
-        is active, it will handle this automatically.
+      restarted. However any other standbys will need to follow the new primary,
+      and will need to be restarted to do this.
     </para>
     <para>
-      Note that &repmgr; will wait for up to <varname>promote_check_timeout</varname> seconds
-      (default: 60 seconds) to verify that the standby has been promoted, and will
+      Beginning with <link linkend="release-4.4">repmgr 4.4</link>,
+      the option <option>--siblings-follow</option> can be used to have
+      all other standbys (and a witness server, if in use)
+	  follow the new primary.
+    </para>
+
+    <note>
+      <para>
+        If using &repmgrd;, when invoking
+        <command>repmgr standby promote</command> (either directly via
+        the <option>promote_command</option>, or in a script called
+        via <option>promote_command</option>), <option>--siblings-follow</option>
+        <emphasis>must not</emphasis> be included as a
+        command line option for <command>repmgr standby promote</command>.
+      </para>
+    </note>
+
+    <para>
+      In <link linkend="release-4.3">repmgr 4.3</link> and earlier,
+      <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>
+      must be executed on each standby individually.
+    </para>
+
+    <para>
+      &repmgr; will wait for up to <varname>promote_check_timeout</varname> seconds
+      (default: <literal>60</literal>) to verify that the standby has been promoted, and will
       check the promotion every <varname>promote_check_interval</varname> seconds (default: 1 second).
       Both values can be defined in <filename>repmgr.conf</filename>.
     </para>
@@ -72,13 +104,36 @@
     <title>Options</title>
     <variablelist>
       <varlistentry>
+
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check if this node can be promoted, but don't carry out the promotion
+            Check if this node can be promoted, but don't carry out the promotion.
           </para>
         </listitem>
       </varlistentry>
+
+      <varlistentry>
+        <term><option>--siblings-follow</option></term>
+        <listitem>
+          <para>
+            Have all sibling nodes (nodes formerly attached to the same upstream
+            node as the promotion candidate) follow this node after it has been promoted.
+          </para>
+		  <para>
+			Note that a witness server, if in use, is also
+			counted as a &quot;sibling node&quot; as it needs to be instructed to
+			synchronise its metadata with the new primary.
+		  </para>
+          <important>
+            <para>
+              Do <emphasis>not</emphasis> provide this option when configuring
+              &repmgrd;'s <option>promote_command</option>.
+            </para>
+          </important>
+        </listitem>
+      </varlistentry>
+
     </variablelist>
   </refsect1>
 

doc/repmgr-standby-register.xml

@@ -17,7 +17,7 @@
     <para>
       <command>repmgr standby register</command> adds a standby's information to
       the &repmgr; metadata. This command needs to be executed to enable
-      promote/follow operations and to allow <application>repmgrd</application> to work with the node.
+      promote/follow operations and to allow &repmgrd; to work with the node.
       An existing standby can be registered using this command. Execute with the
       <literal>--dry-run</literal> option to check what would happen without actually registering the
       standby.
@@ -28,7 +28,7 @@
         If providing the configuration file location with <literal>-f/--config-file</literal>,
         avoid using a relative path, as &repmgr; stores the configuration file location
         in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
-        <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
+        <xref linkend="repmgr-standby-switchover"/>). &repmgr; will attempt to convert the
           a relative path into an absolute one, but this may not be the same as the path you
           would explicitly provide (e.g. <filename>./repmgr.conf</filename> might be converted
           to <filename>/path/to/./repmgr.conf</filename>, whereas you'd normally write
@@ -59,7 +59,7 @@
    <para>
      Depending on your environment and workload, it may take some time for the standby's node record
      to propagate from the primary to the standby. Some actions (such as starting
-     <application>repmgrd</application>) require that the standby's node record
+     &repmgrd;) require that the standby's node record
      is present and up-to-date to function correctly.
    </para>
    <para>

doc/repmgr-standby-switchover.xml

@@ -22,11 +22,13 @@
       passwordless SSH connection to the current primary.
     </para>
     <para>
-      If other standbys are connected to the demotion candidate, &repmgr; can instruct
+      If other nodes are connected to the demotion candidate, &repmgr; can instruct
       these to follow the new primary if the option <literal>--siblings-follow</literal>
       is specified. This requires a passwordless SSH connection between the promotion
-      candidate (new primary) and the standbys attached to the demotion candidate
-      (existing primary).
+      candidate (new primary) and the nodes attached to the demotion candidate
+      (existing primary). Note that a witness server, if in use, is also
+	  counted as a &quot;sibling node&quot; as it needs to be instructed to
+	  synchronise its metadata with the new primary.
     </para>
     <note>
       <para>
@@ -42,18 +44,18 @@
     </note>
     <para>
       For more details on performing a switchover, including preparation and configuration,
-      see section <xref linkend="performing-switchover">.
+      see section <xref linkend="performing-switchover"/>.
     </para>
 
     <note>
       <para>
         From <link linkend="release-4.2">repmgr 4.2</link>, &repmgr; will instruct any running
-        <application>repmgrd</application> instances to pause operations while the switchover
-        is being carried out, to prevent <application>repmgrd</application> from
-        unintentionally promoting a node. For more details, see <xref linkend="repmgrd-pausing">.
+        &repmgrd; instances to pause operations while the switchover
+        is being carried out, to prevent &repmgrd; from
+        unintentionally promoting a node. For more details, see <xref linkend="repmgrd-pausing"/>.
       </para>
       <para>
-        Users of &repmgr; versions prior to 4.2 should ensure that <application>repmgrd</application>
+        Users of &repmgr; versions prior to 4.2 should ensure that &repmgrd;
         is not running on any nodes while a switchover is being executed.
       </para>
     </note>
@@ -115,7 +117,7 @@
             (and the prerequisites for using <application>pg_rewind</application> are met).
             If using PostgreSQL 9.3 or 9.4, and the <application>pg_rewind</application>
             binary is not installed in the PostgreSQL <filename>bin</filename> directory,
-            provide its full path. For more details see also <xref linkend="switchover-pg-rewind">.
+            provide its full path. For more details see also <xref linkend="switchover-pg-rewind"/>.
           </para>
         </listitem>
       </varlistentry>
@@ -134,12 +136,30 @@
         <term><option>--repmgrd-no-pause</option></term>
         <listitem>
           <para>
-            Don't pause <application>repmgrd</application> while executing a switchover.
+            Don't pause &repmgrd; while executing a switchover.
           </para>
           <para>
             This option should not be used unless you take steps by other means
-            to ensure <application>repmgrd</application> is paused or not
+            to ensure &repmgrd; is paused or not
             running on all nodes.
+          </para>
+		  <para>
+            This option cannot be used together with <option>--repmgrd-force-unpause</option>.
+          </para>
+
+        </listitem>
+      </varlistentry>
+
+	  <varlistentry>
+        <term><option>--repmgrd-force-unpause</option></term>
+        <listitem>
+          <para>
+            Always unpause all &repmgrd; instances after executing a switchover. This will ensure that
+			any &repmgrd; instances which were paused before the switchover will be
+			unpaused.
+          </para>
+          <para>
+            This option cannot be used together with <option>--repmgrd-no-pause</option>.
           </para>
         </listitem>
       </varlistentry>
@@ -150,8 +170,18 @@
         <term><option>--siblings-follow</option></term>
         <listitem>
           <para>
-            Have standbys attached to the old primary follow the new primary.
+            Have nodes attached to the old primary follow the new primary.
           </para>
+          <para>
+            This will also ensure that a witness node, if in use, is updated
+            with the new primary's data.
+          </para>
+          <note>
+            <para>
+              In a future &repmgr; release, <option>--siblings-follow</option> will be applied
+              by default.
+            </para>
+          </note>
         </listitem>
       </varlistentry>
     </variablelist>
@@ -169,13 +199,14 @@
     <variablelist>
 
       <varlistentry>
-        <indexterm>
-          <primary>replication_lag_critical</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
-
         <term><option>replication_lag_critical</option></term>
         <listitem>
+
+          <indexterm>
+            <primary>replication_lag_critical</primary>
+            <secondary>with &quot;repmgr standby switchover&quot;</secondary>
+          </indexterm>
+
           <para>
             If replication lag (in seconds) on the standby exceeds this value, the
             switchover will be aborted (unless the <literal>-F/--force</literal> option
@@ -185,13 +216,14 @@
       </varlistentry>
 
       <varlistentry>
-        <indexterm>
-          <primary>shutdown_check_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
 
         <term><option>shutdown_check_timeout</option></term>
         <listitem>
+          <indexterm>
+            <primary>shutdown_check_timeout</primary>
+            <secondary>with &quot;repmgr standby switchover&quot;</secondary>
+          </indexterm>
+
           <para>
             The maximum number of seconds to wait for the
             demotion candidate (current primary) to shut down, before aborting the switchover.
@@ -213,13 +245,13 @@
 
 
       <varlistentry>
-        <indexterm>
-          <primary>wal_receive_check_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
-
         <term><option>wal_receive_check_timeout</option></term>
         <listitem>
+          <indexterm>
+            <primary>wal_receive_check_timeout</primary>
+          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
+          </indexterm>
+
           <para>
             After the primary has shut down, the maximum number of seconds to wait for the
             walreceiver on the standby to flush WAL to disk before comparing WAL receive location
@@ -230,13 +262,14 @@
 
 
       <varlistentry>
-        <indexterm>
-          <primary>standby_reconnect_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
 
         <term><option>standby_reconnect_timeout</option></term>
         <listitem>
+          <indexterm>
+            <primary>standby_reconnect_timeout</primary>
+            <secondary>with &quot;repmgr standby switchover&quot;</secondary>
+          </indexterm>
+
           <para>
             The maximum number of seconds to attempt to wait for the demotion candidate (former primary)
             to reconnect to the promoted primary (default: 60 seconds)
@@ -249,14 +282,16 @@
         </listitem>
       </varlistentry>
 
-     <varlistentry>
-        <indexterm>
-          <primary>node_rejoin_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
+      <varlistentry>
 
         <term><option>node_rejoin_timeout</option></term>
         <listitem>
+
+          <indexterm>
+            <primary>node_rejoin_timeout</primary>
+            <secondary>with &quot;repmgr standby switchover&quot;</secondary>
+          </indexterm>
+
           <para>
             maximum number of seconds to attempt to wait for the demotion candidate (former primary)
             to reconnect to the promoted primary (default: 60 seconds)
@@ -350,10 +385,10 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-standby-follow">, <xref linkend="repmgr-node-rejoin">
+      <xref linkend="repmgr-standby-follow"/>, <xref linkend="repmgr-node-rejoin"/>
     </para>
     <para>
-      For more details on performing a switchover operation, see the section <xref linkend="performing-switchover">.
+      For more details on performing a switchover operation, see the section <xref linkend="performing-switchover"/>.
     </para>
   </refsect1>
 

doc/repmgr-witness-register.xml

@@ -20,7 +20,7 @@
       record to the &repmgr; metadata, and if necessary initialises the witness
       node by installing the &repmgr; extension and copying the &repmgr; metadata
       to the witness server. This command needs to be executed to enable
-      use of the witness server with <application>repmgrd</application>.
+      use of the witness server with &repmgrd;.
     </para>
     <para>
       When executing <command>repmgr witness register</command>, database connection

doc/repmgr.xml

@@ -1,14 +1,16 @@
-<!-- doc/src/sgml/postgres.sgml -->
+<!-- doc/repmgr.xml -->
 
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook V4.2//EN" [
-
-          <!ENTITY % version SYSTEM "version.sgml">
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
+          "http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd"
+[
+          <!ENTITY % version SYSTEM "version.xml">
           %version;
 
-          <!ENTITY % filelist SYSTEM "filelist.sgml">
+          <!ENTITY % filelist SYSTEM "filelist.xml">
           %filelist;
 
           <!ENTITY repmgr "<productname>repmgr</productname>">
+          <!ENTITY repmgrd "<productname>repmgrd</productname>">
           <!ENTITY postgres "<productname>PostgreSQL</productname>">
 ]>
 
@@ -25,13 +27,19 @@
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
    use with PostgreSQL 9.3 - PostgreSQL 11.
-   It describes the functionality supported by the current version of &repmgr;.
+   </para>
+   <para>
+     &repmgr; is being continually developed and we strongly recommend using the
+     latest version. Please check the
+     <ulink url="https://repmgr.org/">repmgr website</ulink> for details
+     about the current &repmgr; version as well as the
+     <ulink url="https://repmgr.org/docs/current/index.html">current repmgr documentation</ulink>.
    </para>
 
    <para>
     &repmgr; is developed by
     <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
-    along with contributions from other individuals and companies.
+    along with contributions from other individuals and organisations.
     Contributions from the community are appreciated and welcome - get
     in touch via <ulink url="https://github.com/2ndQuadrant/repmgr">github</ulink>
     or <ulink url="https://groups.google.com/group/repmgr">the mailing list/forum</ulink>.
@@ -43,7 +51,7 @@
      &repmgr; is fully supported by 2ndQuadrant's
      <ulink url="https://www.2ndquadrant.com/en/support/support-postgresql/">24/7 Production Support</ulink>.
      2ndQuadrant, a Major Sponsor of the PostgreSQL project, continues to develop and maintain &repmgr;.
-     Other companies as well as individual developers are welcome to participate in the efforts.
+     Other organisations as well as individual developers are welcome to participate in the efforts.
    </para>
   </abstract>
 
@@ -73,7 +81,6 @@
   &promoting-standby;
   &follow-new-primary;
   &switchover;
-  &configuring-witness-server;
   &event-notifications;
   &upgrading-repmgr;
  </part>
@@ -122,7 +129,6 @@
  &appendix-packages;
  &appendix-support;
 
- <![%include-index;[&bookindex;]]>
- <![%include-xslt-index;[<index id="bookindex"></index>]]>
+ <index id="bookindex"></index>
 
 </book>

doc/repmgrd-automatic-failover.sgml

@@ -1,246 +0,0 @@
-<chapter id="repmgrd-automatic-failover" xreflabel="Automatic failover with repmgrd">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>automatic failover</secondary>
- </indexterm>
-
- <title>Automatic failover with repmgrd</title>
-
- <para>
-  <application>repmgrd</application> is a management and monitoring daemon which runs
-  on each node in a replication cluster. It can automate actions such as
-  failover and updating standbys to follow the new primary, as well as
-  providing monitoring information about the state of each standby.
- </para>
-
-<sect1 id="repmgrd-witness-server" xreflabel="Using a witness server with repmgrd">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>witness server</secondary>
- </indexterm>
-
- <indexterm>
-   <primary>witness server</primary>
-   <secondary>repmgrd</secondary>
- </indexterm>
-
- <title>Using a witness server with repmgrd</title>
- <para>
-   In a situation caused e.g. by a network interruption between two
-   data centres, it's important to avoid a &quot;split-brain&quot; situation where
-   both sides of the network assume they are the active segment and the
-   side without an active primary unilaterally promotes one of its standbys.
- </para>
- <para>
-   To prevent this situation happening, it's essential to ensure that one
-   network segment has a &quot;voting majority&quot;, so other segments will know
-   they're in the minority and not attempt to promote a new primary. Where
-   an odd number of servers exists, this is not an issue. However, if each
-   network has an even number of nodes, it's necessary to provide some way
-   of ensuring a majority, which is where the witness server becomes useful.
- </para>
- <para>
-   This is not a fully-fledged standby node and is not integrated into
-   replication, but it effectively represents the &quot;casting vote&quot; when
-   deciding which network segment has a majority. A witness server can
-   be set up using <link linkend="repmgr-witness-register"><command>repmgr witness register</command></link>;
-   see also section <link linkend="using-witness-server">Using a witness server</link>.
- </para>
- <note>
-   <para>
-     It only
-     makes sense to create a witness server in conjunction with running
-     <application>repmgrd</application>; the witness server will require its own
-     <application>repmgrd</application> instance.
-   </para>
- </note>
-
-</sect1>
-
-
-<sect1 id="repmgrd-network-split" xreflabel="Handling network splits with repmgrd">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>network splits</secondary>
- </indexterm>
-
- <indexterm>
-   <primary>network splits</primary>
- </indexterm>
-
- <title>Handling network splits with repmgrd</title>
- <para>
-  A common pattern for replication cluster setups is to spread servers over
-  more than one datacentre. This can provide benefits such as geographically-
-  distributed read replicas and DR (disaster recovery capability). However
-  this also means there is a risk of disconnection at network level between
-  datacentre locations, which would result in a split-brain scenario if
-  servers in a secondary data centre were no longer able to see the primary
-  in the main data centre and promoted a standby among themselves.
- </para>
- <para>
-  &repmgr; enables provision of &quot;<xref linkend="witness-server">&quot; to
-  artificially create a quorum of servers in a particular location, ensuring
-  that nodes in another location will not elect a new primary if they
-  are unable to see the majority of nodes. However this approach does not
-  scale well, particularly with more complex replication setups, e.g.
-  where the majority of nodes are located outside of the primary datacentre.
-  It also means the <literal>witness</literal> node needs to be managed as an
-  extra PostgreSQL instance outside of the main replication cluster, which
-  adds administrative and programming complexity.
- </para>
- <para>
-  <literal>repmgr4</literal> introduces the concept of <literal>location</literal>:
-  each node is associated with an arbitrary location string (default is
-  <literal>default</literal>); this is set in <filename>repmgr.conf</filename>, e.g.:
-  <programlisting>
-    node_id=1
-    node_name=node1
-    conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'
-    data_directory='/var/lib/postgresql/data'
-    location='dc1'</programlisting>
- </para>
- <para>
-  In a failover situation, <application>repmgrd</application> will check if any servers in the
-  same location as the current primary node are visible.  If not, <application>repmgrd</application>
-  will assume a network interruption and not promote any node in any
-  other location (it will however enter <link linkend="repmgrd-degraded-monitoring">degraded monitoring</link>
-  mode until a primary becomes visible).
- </para>
-
-</sect1>
-
-<sect1 id="repmgrd-standby-disconnection-on-failover" xreflabel="Standby disconnection on failover">
-  <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>standby disconnection on failover</secondary>
- </indexterm>
-
-  <indexterm>
-    <primary>standby disconnection on failover</primary>
-  </indexterm>
-
-  <title>Standby disconnection on failover</title>
-  <para>
-    If <option>standby_disconnect_on_failover</option> is set to <literal>true</literal> in
-    <filename>repmgr.conf</filename>, in a failover situation <application>repmgrd</application> will forcibly disconnect
-    the local node's WAL receiver before making a failover decision.
-  </para>
-  <note>
-    <para>
-      <option>standby_disconnect_on_failover</option> is available from PostgreSQL 9.5 and later.
-      Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
-    </para>
-  </note>
-  <para>
-    By doing this, it's possible to ensure that, at the point the failover decision is made, no nodes
-    are receiving data from the primary and their LSN location will be static.
-  </para>
-  <important>
-    <para>
-      <option>standby_disconnect_on_failover</option> <emphasis>must</emphasis> be set to the same value on
-      all nodes.
-    </para>
-  </important>
-  <para>
-    Note that when using <option>standby_disconnect_on_failover</option> there will be a delay of 5 seconds
-    plus however many seconds it takes to confirm the WAL receiver is disconnected before
-    <application>repmgrd</application> proceeds with the failover decision.
-  </para>
-  <para>
-    Following the failover operation, no matter what the outcome, each node will reconnect its WAL receiver.
-  </para>
-  <para>
-    If using <option>standby_disconnect_on_failover</option>, we recommend that the
-    <option>primary_visibility_consensus</option> option is also used.
-  </para>
-
-</sect1>
-
-<sect1 id="repmgrd-failover-validation" xreflabel="Failover validation">
-  <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>failover validation</secondary>
- </indexterm>
-
-  <indexterm>
-    <primary>failover validation</primary>
-  </indexterm>
-
-  <title>Failover validation</title>
-  <para>
-    From <link linkend="release-4.3">repmgr 4.3</link>, &repmgr; makes it possible to provide a script
-    to <application>repmgrd</application> which, in a failover situation,
-    will be executed by the promotion candidate (the node which has been selected
-    to be the new primary) to confirm whether the node should actually be promoted.
-  </para>
-  <para>
-    To use this, <option>failover_validation_command</option> in <filename>repmgr.conf</filename>
-    to a script executable by the <literal>postgres</literal> system user, e.g.:
-    <programlisting>
-      failover_validation_command=/path/to/script.sh %n %a</programlisting>
-  </para>
-  <para>
-    The <literal>%n</literal> parameter will be replaced with the node ID, and the
-    <literal>%a</literal> parameter will be replaced by the node name when the script is executed.
-  </para>
-  <para>
-    This script must return an exit code of <literal>0</literal> to indicate the node should promote itself.
-    Any other value will result in the promotion being aborted and the election rerun.
-    There is a pause of <option>election_rerun_interval</option> seconds before the election is rerun.
-  </para>
-  <para>
-    Sample <application>repmgrd</application> log file output during which the failover validation
-    script rejects the proposed promotion candidate:
-    <programlisting>
-[2019-03-13 21:01:30] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
-[2019-03-13 21:01:30] [NOTICE] promotion candidate is "node2" (ID: 2)
-[2019-03-13 21:01:30] [NOTICE] executing "failover_validation_command"
-[2019-03-13 21:01:30] [DETAIL] /usr/local/bin/failover-validation.sh 2
-[2019-03-13 21:01:30] [INFO] output returned by failover validation command:
-Node ID: 2
-
-[2019-03-13 21:01:30] [NOTICE] failover validation command returned a non-zero value: "1"
-[2019-03-13 21:01:30] [NOTICE] promotion candidate election will be rerun
-[2019-03-13 21:01:30] [INFO] 1 followers to notify
-[2019-03-13 21:01:30] [NOTICE] notifying node "node3" (node ID: 3) to rerun promotion candidate selection
-INFO:  node 3 received notification to rerun promotion candidate election
-[2019-03-13 21:01:30] [NOTICE] rerunning election after 15 seconds ("election_rerun_interval")</programlisting>
-  </para>
-
-
-</sect1>
-
-  <sect1 id="cascading-replication" xreflabel="Cascading replication">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>cascading replication</secondary>
- </indexterm>
-
- <indexterm>
-   <primary>cascading replication</primary>
-   <secondary>repmgrd</secondary>
- </indexterm>
-
- <title>repmgrd and cascading replication</title>
- <para>
-  Cascading replication - where a standby can connect to an upstream node and not
-  the primary server itself - was introduced in PostgreSQL 9.2. &repmgr; and
-  <application>repmgrd</application> support cascading replication by keeping track of the relationship
-  between standby servers - each node record is stored with the node id of its
-  upstream ("parent") server (except of course the primary server).
- </para>
- <para>
-  In a failover situation where the primary node fails and a top-level standby
-  is promoted, a standby connected to another standby will not be affected
-  and continue working as normal (even if the upstream standby it's connected
-  to becomes the primary node). If however the node's direct upstream fails,
-  the &quot;cascaded standby&quot; will attempt to reconnect to that node's parent
-  (unless <varname>failover</varname> is set to <literal>manual</literal> in
-  <filename>repmgr.conf</filename>).
- </para>
-
-  </sect1>
-
-
-</chapter>

doc/repmgrd-automatic-failover.xml

@@ -0,0 +1,925 @@
+<chapter id="repmgrd-automatic-failover" xreflabel="Automatic failover with repmgrd">
+
+ <title>Automatic failover with repmgrd</title>
+
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>automatic failover</secondary>
+ </indexterm>
+
+ <para>
+  &repmgrd; is a management and monitoring daemon which runs
+  on each node in a replication cluster. It can automate actions such as
+  failover and updating standbys to follow the new primary, as well as
+  providing monitoring information about the state of each standby.
+ </para>
+
+ <sect1 id="repmgrd-witness-server" xreflabel="Using a witness server with repmgrd">
+   <title>Using a witness server</title>
+
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>witness server</secondary>
+ </indexterm>
+
+ <indexterm>
+   <primary>witness server</primary>
+   <secondary>repmgrd</secondary>
+ </indexterm>
+
+ <para>
+   A <xref linkend="witness-server"/> is a normal PostgreSQL instance which
+   is not part of the streaming replication cluster; its purpose is, if a
+   failover situation occurs, to provide proof that it is the primary server
+   itself which is unavailable, rather than e.g. a network split between
+   different physical locations.
+ </para>
+
+ <para>
+   A typical use case for a witness server is a two-node streaming replication
+   setup, where the primary and standby are in different locations (data centres).
+   By creating a witness server in the same location (data centre) as the primary,
+   if the primary becomes unavailable it's possible for the standby to decide whether
+   it can promote itself without risking a "split brain" scenario: if it can't see either the
+   witness or the primary server, it's likely there's a network-level interruption
+   and it should not promote itself. If it can see the witness but not the primary,
+   this proves there is no network interruption and the primary itself is unavailable,
+   and it can therefore promote itself (and ideally take action to fence the
+   former primary).
+ </para>
+ <note>
+   <para>
+     <emphasis>Never</emphasis> install a witness server on the same physical host
+     as another node in the replication cluster managed by &repmgr; - it's essential
+     the witness is not affected in any way by failure of another node.
+   </para>
+ </note>
+ <para>
+   For more complex replication scenarios, e.g. with multiple datacentres, it may
+   be preferable to use location-based failover, which ensures that only nodes
+   in the same location as the primary will ever be promotion candidates;
+   see <xref linkend="repmgrd-network-split"/> for more details.
+ </para>
+
+ <note>
+   <simpara>
+     A witness server will only be useful if &repmgrd;
+     is in use.
+   </simpara>
+ </note>
+
+ <sect2 id="creating-witness-server">
+   <title>Creating a witness server</title>
+ <para>
+   To create a witness server, set up a normal PostgreSQL instance on a server
+   in the same physical location as the cluster's primary server.
+ </para>
+ <para>
+   This instance should <emphasis>not</emphasis> be on the same physical host as the primary server,
+   as otherwise if the primary server fails due to hardware issues, the witness
+   server will be lost too.
+ </para>
+ <note>
+   <simpara>
+     &repmgr; 3.3 and earlier provided a <command>repmgr create witness</command>
+     command, which would automatically create a PostgreSQL instance. However
+     this often resulted in an unsatisfactory, hard-to-customise instance.
+   </simpara>
+ </note>
+ <para>
+   The witness server should be configured in the same way as a normal
+   &repmgr; node; see section <xref linkend="configuration"/>.
+ </para>
+ <para>
+   Register the witness server with <xref linkend="repmgr-witness-register"/>.
+   This will create the &repmgr; extension on the witness server, and make
+   a copy of the &repmgr; metadata.
+ </para>
+ <note>
+   <simpara>
+    As the witness server is not part of the replication cluster, further
+    changes to the &repmgr; metadata will be synchronised by
+    &repmgrd;.
+   </simpara>
+ </note>
+ <para>
+   Once the witness server has been configured, &repmgrd;
+   should be started.
+ </para>
+
+ <para>
+  To unregister a witness server, use <xref linkend="repmgr-witness-unregister"/>.
+ </para>
+
+ </sect2>
+
+</sect1>
+
+
+<sect1 id="repmgrd-network-split" xreflabel="Handling network splits with repmgrd">
+ <title>Handling network splits with repmgrd</title>
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>network splits</secondary>
+ </indexterm>
+
+ <indexterm>
+   <primary>network splits</primary>
+ </indexterm>
+
+ <para>
+  A common pattern for replication cluster setups is to spread servers over
+  more than one datacentre. This can provide benefits such as geographically-
+  distributed read replicas and DR (disaster recovery capability). However
+  this also means there is a risk of disconnection at network level between
+  datacentre locations, which would result in a split-brain scenario if
+  servers in a secondary data centre were no longer able to see the primary
+  in the main data centre and promoted a standby among themselves.
+ </para>
+ <para>
+  &repmgr; enables provision of &quot;<xref linkend="witness-server"/>&quot; to
+  artificially create a quorum of servers in a particular location, ensuring
+  that nodes in another location will not elect a new primary if they
+  are unable to see the majority of nodes. However this approach does not
+  scale well, particularly with more complex replication setups, e.g.
+  where the majority of nodes are located outside of the primary datacentre.
+  It also means the <literal>witness</literal> node needs to be managed as an
+  extra PostgreSQL instance outside of the main replication cluster, which
+  adds administrative and programming complexity.
+ </para>
+ <para>
+  <literal>repmgr4</literal> introduces the concept of <literal>location</literal>:
+  each node is associated with an arbitrary location string (default is
+  <literal>default</literal>); this is set in <filename>repmgr.conf</filename>, e.g.:
+  <programlisting>
+    node_id=1
+    node_name=node1
+    conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'
+    data_directory='/var/lib/postgresql/data'
+    location='dc1'</programlisting>
+ </para>
+ <para>
+  In a failover situation, &repmgrd; will check if any servers in the
+  same location as the current primary node are visible.  If not, &repmgrd;
+  will assume a network interruption and not promote any node in any
+  other location (it will however enter <link linkend="repmgrd-degraded-monitoring">degraded monitoring</link>
+  mode until a primary becomes visible).
+ </para>
+
+</sect1>
+
+
+<sect1 id="repmgrd-primary-visibility-consensus" xreflabel="Primary visibility consensus">
+  <title>Primary visibility consensus</title>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>primary visibility consensus</secondary>
+  </indexterm>
+
+  <indexterm>
+   <primary>primary_visibility_consensus</primary>
+  </indexterm>
+
+  <para>
+    In more complex replication setups, particularly where replication occurs between
+    multiple datacentres, it's possible that some but not all standbys get cut off from the
+    primary (but not from the other standbys).
+  </para>
+  <para>
+    In this situation, normally it's not desirable for any of the standbys which have been
+    cut off to initiate a failover, as the primary is still functioning and standbys are
+    connected. Beginning with <link linkend="release-4.4">&repmgr; 4.4</link>
+    it is now possible for the affected standbys to build a consensus about whether
+    the primary is still available to some standbys (&quot;primary visibility consensus&quot;).
+    This is done by polling each standby for the time it last saw the primary;
+    if any have seen the primary very recently, it's reasonable
+    to infer that the primary is still available and a failover should not be started.
+  </para>
+
+  <para>
+    The time the primary was last seen by each node can be checked by executing
+    <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>,
+    which includes this in its output, e.g.:
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+ ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
+----+-------+---------+-----------+----------+---------+-------+---------+--------------------
+ 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
+ 2  | node2 | standby |   running | node1    | running | 96572 | no      | 1 second(s) ago
+ 3  | node3 | standby |   running | node1    | running | 96584 | no      | 0 second(s) ago</programlisting>
+
+  </para>
+
+  <para>
+    To enable this functionality, in <filename>repmgr.conf</filename> set:
+    <programlisting>
+      primary_visibility_consensus=true</programlisting>
+  </para>
+  <note>
+    <para>
+      <option>primary_visibility_consensus</option> <emphasis>must</emphasis> be set to
+      <literal>true</literal> on all nodes for it to be effective.
+    </para>
+  </note>
+
+  <para>
+    The following sample &repmgrd; log output demonstrates the behaviour in a situation
+    where one of three standbys is no longer able to connect to the primary, but <emphasis>can</emphasis>
+    connect to the two other standbys (&quot;sibling nodes&quot;):
+    <programlisting>
+    [2019-05-17 05:36:12] [WARNING] unable to reconnect to node 1 after 3 attempts
+    [2019-05-17 05:36:12] [INFO] 2 active sibling nodes registered
+    [2019-05-17 05:36:12] [INFO] local node's last receive lsn: 0/7006E58
+    [2019-05-17 05:36:12] [INFO] checking state of sibling node "node3" (ID: 3)
+    [2019-05-17 05:36:12] [INFO] node "node3" (ID: 3) reports its upstream is node 1, last seen 1 second(s) ago
+    [2019-05-17 05:36:12] [NOTICE] node 3 last saw primary node 1 second(s) ago, considering primary still visible
+    [2019-05-17 05:36:12] [INFO] last receive LSN for sibling node "node3" (ID: 3) is: 0/7006E58
+    [2019-05-17 05:36:12] [INFO] node "node3" (ID: 3) has same LSN as current candidate "node2" (ID: 2)
+    [2019-05-17 05:36:12] [INFO] checking state of sibling node "node4" (ID: 4)
+    [2019-05-17 05:36:12] [INFO] node "node4" (ID: 4) reports its upstream is node 1, last seen 0 second(s) ago
+    [2019-05-17 05:36:12] [NOTICE] node 4 last saw primary node 0 second(s) ago, considering primary still visible
+    [2019-05-17 05:36:12] [INFO] last receive LSN for sibling node "node4" (ID: 4) is: 0/7006E58
+    [2019-05-17 05:36:12] [INFO] node "node4" (ID: 4) has same LSN as current candidate "node2" (ID: 2)
+    [2019-05-17 05:36:12] [INFO] 2 nodes can see the primary
+    [2019-05-17 05:36:12] [DETAIL] following nodes can see the primary:
+     - node "node3" (ID: 3): 1 second(s) ago
+     - node "node4" (ID: 4): 0 second(s) ago
+    [2019-05-17 05:36:12] [NOTICE] cancelling failover as some nodes can still see the primary
+    [2019-05-17 05:36:12] [NOTICE] election cancelled
+    [2019-05-17 05:36:14] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state</programlisting>
+    In this situation it will cancel the failover and enter degraded monitoring node,
+    waiting for the primary to reappear.
+  </para>
+</sect1>
+
+<sect1 id="repmgrd-standby-disconnection-on-failover" xreflabel="Standby disconnection on failover">
+  <title>Standby disconnection on failover</title>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>standby disconnection on failover</secondary>
+ </indexterm>
+
+  <indexterm>
+    <primary>standby disconnection on failover</primary>
+  </indexterm>
+
+  <para>
+    If <option>standby_disconnect_on_failover</option> is set to <literal>true</literal> in
+    <filename>repmgr.conf</filename>, in a failover situation &repmgrd; will forcibly disconnect
+    the local node's WAL receiver before making a failover decision.
+  </para>
+  <note>
+    <para>
+      <option>standby_disconnect_on_failover</option> is available from PostgreSQL 9.5 and later.
+      Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
+    </para>
+  </note>
+  <para>
+    By doing this, it's possible to ensure that, at the point the failover decision is made, no nodes
+    are receiving data from the primary and their LSN location will be static.
+  </para>
+  <important>
+    <para>
+      <option>standby_disconnect_on_failover</option> <emphasis>must</emphasis> be set to the same value on
+      all nodes.
+    </para>
+  </important>
+  <para>
+    Note that when using <option>standby_disconnect_on_failover</option> there will be a delay of 5 seconds
+    plus however many seconds it takes to confirm the WAL receiver is disconnected before
+    &repmgrd; proceeds with the failover decision.
+  </para>
+  <para>
+    Following the failover operation, no matter what the outcome, each node will reconnect its WAL receiver.
+  </para>
+  <para>
+    If using <option>standby_disconnect_on_failover</option>, we recommend that the
+    <option>primary_visibility_consensus</option> option is also used.
+  </para>
+
+</sect1>
+
+<sect1 id="repmgrd-failover-validation" xreflabel="Failover validation">
+  <title>Failover validation</title>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>failover validation</secondary>
+ </indexterm>
+
+  <indexterm>
+    <primary>failover validation</primary>
+  </indexterm>
+
+  <para>
+    From <link linkend="release-4.3">repmgr 4.3</link>, &repmgr; makes it possible to provide a script
+    to &repmgrd; which, in a failover situation,
+    will be executed by the promotion candidate (the node which has been selected
+    to be the new primary) to confirm whether the node should actually be promoted.
+  </para>
+  <para>
+    To use this, <option>failover_validation_command</option> in <filename>repmgr.conf</filename>
+    to a script executable by the <literal>postgres</literal> system user, e.g.:
+    <programlisting>
+      failover_validation_command=/path/to/script.sh %n %a</programlisting>
+  </para>
+  <para>
+    The <literal>%n</literal> parameter will be replaced with the node ID, and the
+    <literal>%a</literal> parameter will be replaced by the node name when the script is executed.
+  </para>
+  <para>
+    This script must return an exit code of <literal>0</literal> to indicate the node should promote itself.
+    Any other value will result in the promotion being aborted and the election rerun.
+    There is a pause of <option>election_rerun_interval</option> seconds before the election is rerun.
+  </para>
+  <para>
+    Sample &repmgrd; log file output during which the failover validation
+    script rejects the proposed promotion candidate:
+    <programlisting>
+[2019-03-13 21:01:30] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
+[2019-03-13 21:01:30] [NOTICE] promotion candidate is "node2" (ID: 2)
+[2019-03-13 21:01:30] [NOTICE] executing "failover_validation_command"
+[2019-03-13 21:01:30] [DETAIL] /usr/local/bin/failover-validation.sh 2
+[2019-03-13 21:01:30] [INFO] output returned by failover validation command:
+Node ID: 2
+
+[2019-03-13 21:01:30] [NOTICE] failover validation command returned a non-zero value: "1"
+[2019-03-13 21:01:30] [NOTICE] promotion candidate election will be rerun
+[2019-03-13 21:01:30] [INFO] 1 followers to notify
+[2019-03-13 21:01:30] [NOTICE] notifying node "node3" (ID: 3) to rerun promotion candidate selection
+INFO:  node 3 received notification to rerun promotion candidate election
+[2019-03-13 21:01:30] [NOTICE] rerunning election after 15 seconds ("election_rerun_interval")</programlisting>
+  </para>
+
+
+</sect1>
+
+ <sect1 id="cascading-replication" xreflabel="Cascading replication">
+  <title>repmgrd and cascading replication</title>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>cascading replication</secondary>
+  </indexterm>
+
+ <indexterm>
+   <primary>cascading replication</primary>
+   <secondary>repmgrd</secondary>
+ </indexterm>
+
+ <para>
+  Cascading replication - where a standby can connect to an upstream node and not
+  the primary server itself - was introduced in PostgreSQL 9.2. &repmgr; and
+  &repmgrd; support cascading replication by keeping track of the relationship
+  between standby servers - each node record is stored with the node id of its
+  upstream ("parent") server (except of course the primary server).
+ </para>
+ <para>
+  In a failover situation where the primary node fails and a top-level standby
+  is promoted, a standby connected to another standby will not be affected
+  and continue working as normal (even if the upstream standby it's connected
+  to becomes the primary node). If however the node's direct upstream fails,
+  the &quot;cascaded standby&quot; will attempt to reconnect to that node's parent
+  (unless <varname>failover</varname> is set to <literal>manual</literal> in
+  <filename>repmgr.conf</filename>).
+ </para>
+
+  </sect1>
+
+<sect1 id="repmgrd-primary-child-disconnection" xreflabel="Monitoring standby disconnections on the primary">
+  <title>Monitoring standby disconnections on the primary node</title>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>standby disconnection</secondary>
+  </indexterm>
+
+  <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>child node disconnection</secondary>
+  </indexterm>
+
+  <note>
+    <para>
+      This functionality is available in <link linkend="release-4.4">&repmgr; 4.4</link> and later.
+    </para>
+  </note>
+  <para>
+    When running on the primary node, &repmgrd; can
+    monitor connections and in particular disconnections by its attached
+    child nodes (standbys, and if in use, the witness server), and optionally
+    execute a custom command if certain criteria are met (such as the number of
+    attached nodes falling to zero following a failover to a new primary); this
+    command can be used for example to &quot;fence&quot; the node and ensure it
+    is isolated from any applications attempting to access the replication cluster.
+  </para>
+
+  <note>
+	<para>
+	  Currently &repmgrd; can only detect disconnections
+	  of streaming replication standbys and cannot determine whether a standby
+	  has disconnected and fallen back to archive recovery.
+	</para>
+	<para>
+	  See section <link linkend="repmgrd-primary-child-disconnection-caveats">caveats</link> below.
+	</para>
+  </note>
+
+  <sect2 id="repmgrd-primary-child-disconnection-monitoring-process">
+	<title>Standby disconnections monitoring process and criteria</title>
+	<para>
+	  &repmgrd; monitors attached child nodes and decides
+	  whether to invoke the user-defined command based on the following process
+	  and criteria:
+    <itemizedlist>
+
+      <listitem>
+        <para>
+          Every few seconds (defined by the configuration parameter <varname>child_nodes_check_interval</varname>;
+          default: <literal>5</literal> seconds, a value of <literal>0</literal> disables this altogether), &repmgrd; queries
+          the <literal>pg_stat_replication</literal> system view and compares
+          the nodes present there against the list of nodes registered with &repmgr; which
+          should be attached to the primary.
+        </para>
+        <para>
+          If a witness server is in use, &repmgrd; connects to it and checks which upstream node
+          it is following.
+        </para>
+      </listitem>
+
+      <listitem>
+        <para>
+          If a child node (standby) is no longer present in <literal>pg_stat_replication</literal>,
+          &repmgrd; notes the time it detected the node's absence, and additionally generates a
+          <literal>child_node_disconnect</literal> event.
+        </para>
+        <para>
+          If a witness server is in use, and it is no longer following the primary, or not
+          reachable at all, &repmgrd; notes the time it detected the node's absence, and additionally generates a
+          <literal>child_node_disconnect</literal> event.
+        </para>
+      </listitem>
+
+      <listitem>
+        <para>
+          If a child node (standby) which was absent from <literal>pg_stat_replication</literal> reappears,
+          &repmgrd; clears the time it detected the node's absence, and additionally generates a
+          <literal>child_node_reconnect</literal> event.
+        </para>
+        <para>
+          If a witness server is in use, which was previously not reachable or not following the
+          primary node, has become reachable and is following the primary node,  &repmgrd; clears the
+          time it detected the node's absence, and additionally generates a
+          <literal>child_node_reconnect</literal> event.
+        </para>
+      </listitem>
+
+      <listitem>
+        <para>
+          If an entirely new child node (standby or witness) is detected, &repmgrd; adds it to its internal list
+          and additionally generates a <literal>child_node_new_connect</literal> event.
+        </para>
+      </listitem>
+
+      <listitem>
+        <para>
+          If the <varname>child_nodes_disconnect_command</varname> parameter is set in
+          <filename>repmgr.conf</filename>, &repmgrd; will then loop through all child nodes.
+          If it determines that insufficient child nodes are connected, and a
+          minimum of <varname>child_nodes_disconnect_timeout</varname> seconds (default: <literal>30</literal>)
+          has elapsed since  the last node became disconnected, &repmgrd; will then execute the
+          <varname>child_nodes_disconnect_command</varname> script.
+        </para>
+        <para>
+          By default, the <varname>child_nodes_disconnect_command</varname> will only be executed
+          if all child nodes are disconnected. If <varname>child_nodes_connected_min_count</varname>
+          is set, the <varname>child_nodes_disconnect_command</varname> script will be triggered
+          if the number of connected child nodes falls below the specified value (e.g.
+          if set to <literal>2</literal>, the script will be triggered if only one child node
+          is connected). Alternatively, if <varname>child_nodes_disconnect_min_count</varname>
+          and more than that number of child nodes disconnects, the script will be triggered.
+        </para>
+        <note>
+          <para>
+            By default, a witness node, if in use, will <emphasis>not</emphasis> be counted as a
+            child node for the purposes of determining whether to execute
+            <varname>child_nodes_disconnect_command</varname>.
+          </para>
+          <para>
+            To enable the witness node to be counted as a child node, set
+            <varname>child_nodes_connected_include_witness</varname> in <filename>repmgr.conf</filename>
+            to <literal>true</literal>
+            (and <link linkend="repmgrd-reloading-configuration">reload the configuration</link> if &repmgrd;
+            is running).
+          </para>
+        </note>
+      </listitem>
+
+      <listitem>
+        <para>
+          Note that child nodes which are not attached when &repmgrd;
+          starts will <emphasis>not</emphasis> be considered as missing, as &repmgrd;
+          cannot know why they are not attached.
+        </para>
+      </listitem>
+
+    </itemizedlist>
+	</para>
+  </sect2>
+
+  <sect2 id="repmgrd-primary-child-disconnection-example">
+	<title>Standby disconnections monitoring process example</title>
+	<para>
+	  This example shows typical &repmgrd; log output from a three-node cluster
+	  (primary and two child nodes), with <varname>child_nodes_connected_min_count</varname>
+	  set to <literal>2</literal>.
+	</para>
+	<para>
+	  &repmgrd; on the primary has started up, while two child
+	  nodes are being provisioned:
+	  <programlisting>
+[2019-04-24 15:25:33] [INFO] monitoring primary node "node1" (ID: 1) in normal state
+[2019-04-24 15:25:35] [NOTICE] new node "node2" (ID: 2) has connected
+[2019-04-24 15:25:35] [NOTICE] 1 (of 1) child nodes are connected, but at least 2 child nodes required
+[2019-04-24 15:25:35] [INFO] no child nodes have detached since repmgrd startup
+(...)
+[2019-04-24 15:25:44] [NOTICE] new node "node3" (ID: 3) has connected
+[2019-04-24 15:25:46] [INFO] monitoring primary node "node1" (ID: 1) in normal state
+(...)</programlisting>
+	</para>
+	<para>
+	  One of the child nodes has disconnected; &repmgrd;
+	  is now waiting <varname>child_nodes_disconnect_timeout</varname> seconds
+	  before executing <varname>child_nodes_disconnect_command</varname>:
+	  <programlisting>
+[2019-04-24 15:28:11] [INFO] monitoring primary node "node1" (ID: 1) in normal state
+[2019-04-24 15:28:17] [INFO] monitoring primary node "node1" (ID: 1) in normal state
+[2019-04-24 15:28:19] [NOTICE] node "node3" (ID: 3) has disconnected
+[2019-04-24 15:28:19] [NOTICE] 1 (of 2) child nodes are connected, but at least 2 child nodes required
+[2019-04-24 15:28:19] [INFO] most recently detached child node was 3 (ca. 0 seconds ago), not triggering "child_nodes_disconnect_command"
+[2019-04-24 15:28:19] [DETAIL] "child_nodes_disconnect_timeout" set To 30 seconds
+(...)</programlisting>
+	</para>
+	<para>
+	  <varname>child_nodes_disconnect_command</varname> is executed once:
+	  <programlisting>
+[2019-04-24 15:28:49] [INFO] most recently detached child node was 3 (ca. 30 seconds ago), triggering "child_nodes_disconnect_command"
+[2019-04-24 15:28:49] [INFO] "child_nodes_disconnect_command" is:
+	"/usr/bin/fence-all-the-things.sh"
+[2019-04-24 15:28:51] [NOTICE] 1 (of 2) child nodes are connected, but at least 2 child nodes required
+[2019-04-24 15:28:51] [INFO] "child_nodes_disconnect_command" was previously executed, taking no action</programlisting>
+	</para>
+
+  </sect2>
+
+  <sect2 id="repmgrd-primary-child-disconnection-caveats">
+	<title>Standby disconnections monitoring caveats</title>
+	<para>
+	  The follwing caveats should be considered if you are intending to use this functionality.
+	</para>
+	<para>
+	  <itemizedlist mark="bullet">
+		<listitem>
+          <para>
+			If a child node is configured to use archive recovery, it's possible that
+			the child node will disconnect from the primary node and fall back to
+			archive recovery. In this case &repmgrd;
+			will nevertheless register a node disconnection.
+		  </para>
+		</listitem>
+
+        <listitem>
+          <para>
+			&repmgr; relies on <varname>application_name</varname> in the child node's
+			<varname>primary_conninfo</varname> string to be the same as the node name
+			defined in the node's <filename>repmgr.conf</filename> file. Furthermore,
+			this <varname>application_name</varname> must be unique across the replication
+			cluster.
+          </para>
+		  <para>
+			If a custom <varname>application_name</varname> is used, or the
+			<varname>application_name</varname> is not unique across the replication
+			cluster, &repmgr; will not be able to reliably monitor child node connections.
+		  </para>
+        </listitem>
+
+	  </itemizedlist>
+	</para>
+  </sect2>
+
+
+  <sect2 id="repmgrd-primary-child-disconnection-configuration">
+	<title>Standby disconnections monitoring process configuration</title>
+	<para>
+	  The following parameters, set in <filename>repmgr.conf</filename>,
+	  control how child node disconnection monitoring operates.
+	</para>
+	<variablelist>
+
+      <varlistentry>
+        <term><varname>child_nodes_check_interval</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_check_interval</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+			Interval (in seconds) after which &repmgrd; queries the
+			<literal>pg_stat_replication</literal> system view and compares the nodes present
+			there against the list of nodes registered with repmgr which should be attached to the primary.
+		  </para>
+		  <para>
+			Default is <literal>5</literal> seconds, a value of <literal>0</literal> disables this check
+			altogether.
+		  </para>
+		</listitem>
+	  </varlistentry>
+
+	  <varlistentry>
+        <term><varname>child_nodes_disconnect_command</varname></term>
+
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_disconnect_command</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+			User-definable script to be executed when &repmgrd;
+			determines that an insufficient number of child nodes are connected. By default
+			the script is executed when no child nodes are executed, but the execution
+			threshold can be modified by setting one of <varname>child_nodes_connected_min_count</varname>
+			or<varname>child_nodes_disconnect_min_count</varname> (see below).
+		  </para>
+		  <para>
+			The <varname>child_nodes_disconnect_command</varname> script can be
+			any user-defined script or program. It <emphasis>must</emphasis> be able
+			to be executed by the system user under which the PostgreSQL server itself
+			runs (usually <literal>postgres</literal>).
+		  </para>
+		  <note>
+			<para>
+			  If <varname>child_nodes_disconnect_command</varname> is not set, no action
+			  will be taken.
+			</para>
+		  </note>
+		  <para>
+			If specified, the following format placeholder will be substituted when
+			executing <varname>child_nodes_disconnect_command</varname>:
+		  </para>
+
+		   <variablelist>
+			 <varlistentry>
+			   <term><option>%p</option></term>
+			   <listitem>
+				 <para>
+				   ID of the node executing the <varname>child_nodes_disconnect_command</varname> script.
+				 </para>
+			   </listitem>
+			 </varlistentry>
+		   </variablelist>
+
+		  <para>
+			The <varname>child_nodes_disconnect_command</varname> script will only be executed once
+			while the criteria for its execution are met. If the criteria for its execution are no longer
+			met (i.e. some child nodes have reconnected), it will be executed again if
+			the criteria for its execution are met again.
+          </para>
+          <para>
+			The <varname>child_nodes_disconnect_command</varname> script will not be executed if
+			&repmgrd; is <link linkend="repmgrd-pausing">paused</link>.
+          </para>
+
+		</listitem>
+	  </varlistentry>
+
+	  <varlistentry>
+        <term><varname>child_nodes_disconnect_timeout</varname></term>
+
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_disconnect_timeout</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+			If &repmgrd; determines that an insufficient number of
+			child nodes are connected, it will wait for the specified number of seconds
+			to execute the <varname>child_nodes_disconnect_command</varname>.
+		  </para>
+		  <para>
+			Default: <literal>30</literal> seconds.
+		  </para>
+		</listitem>
+	  </varlistentry>
+
+      <varlistentry>
+        <term><varname>child_nodes_connected_min_count</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_connected_min_count</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+			If the number of child nodes connected falls below the number specified in
+			this parameter, the <varname>child_nodes_disconnect_command</varname> script
+			will be executed.
+		  </para>
+		  <para>
+			For example, if <varname>child_nodes_connected_min_count</varname> is set
+			to <literal>2</literal>, the <varname>child_nodes_disconnect_command</varname>
+			script will be executed if one or no child nodes are connected.
+		  </para>
+		  <para>
+			Note that <varname>child_nodes_connected_min_count</varname> overrides any value
+			set in <varname>child_nodes_disconnect_min_count</varname>.
+		  </para>
+		  <para>
+			If neither of <varname>child_nodes_connected_min_count</varname> or
+			<varname>child_nodes_disconnect_min_count</varname> are set,
+			the <varname>child_nodes_disconnect_command</varname> script
+			will be executed when no child nodes are connected.
+		  </para>
+          <para>
+            A witness node, if in use, will not be counted as a child node unless
+            <varname>child_nodes_connected_include_witness</varname> is set to <literal>true</literal>.
+          </para>
+		</listitem>
+	  </varlistentry>
+
+
+	  <varlistentry>
+        <term><varname>child_nodes_disconnect_min_count</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_disconnect_min_count</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+			If the number of disconnected child nodes exceeds the number specified in
+			this parameter, the <varname>child_nodes_disconnect_command</varname> script
+			will be executed.
+		  </para>
+
+		  <para>
+			For example, if <varname>child_nodes_disconnect_min_count</varname> is set
+			to <literal>2</literal>, the <varname>child_nodes_disconnect_command</varname>
+			script will be executed if more than two child nodes are disconnected.
+		  </para>
+
+		  <para>
+			Note that any value set in <varname>child_nodes_disconnect_min_count</varname>
+			will be overriden by <varname>child_nodes_connected_min_count</varname>.
+		  </para>
+		  <para>
+			If neither of <varname>child_nodes_connected_min_count</varname> or
+			<varname>child_nodes_disconnect_min_count</varname> are set,
+			the <varname>child_nodes_disconnect_command</varname> script
+			will be executed when no child nodes are connected.
+		  </para>
+
+          <para>
+            A witness node, if in use, will not be counted as a child node unless
+            <varname>child_nodes_connected_include_witness</varname> is set to <literal>true</literal>.
+          </para>
+
+		</listitem>
+	  </varlistentry>
+
+
+	  <varlistentry>
+        <term><varname>child_nodes_connected_include_witness</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_connected_include_witness</primary>
+		    <secondary>child node disconnection monitoring</secondary>
+		  </indexterm>
+
+		  <para>
+            Whether to count the witness node (if in use) as a child node when
+            determining whether to execute <varname>child_nodes_disconnect_command</varname>.
+          </para>
+          <para>
+            Default to <literal>false</literal>.
+          </para>
+        </listitem>
+      </varlistentry>
+
+	</variablelist>
+
+  </sect2>
+
+  <sect2 id="repmgrd-primary-child-disconnection-events">
+	<title>Standby disconnections monitoring process event notifications</title>
+	<para>
+	  The following <link linkend="event-notifications">event notifications</link> may be generated:
+	</para>
+	<variablelist>
+
+      <varlistentry>
+        <term><varname>child_node_disconnect</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_node_disconnect</primary>
+		    <secondary>event notification</secondary>
+		  </indexterm>
+
+          <para>
+			This event is generated after &repmgrd;
+			detects that a child node is no longer streaming from the primary node.
+          </para>
+		  <para>
+			Example:
+			<programlisting>
+$ repmgr cluster event --event=child_node_disconnect
+ Node ID | Name  | Event                 | OK | Timestamp           | Details
+---------+-------+-----------------------+----+---------------------+--------------------------------------------
+ 1       | node1 | child_node_disconnect | t  | 2019-04-24 12:41:36 | node "node3" (ID: 3) has disconnected</programlisting>
+		  </para>
+        </listitem>
+      </varlistentry>
+
+	  <varlistentry>
+        <term><varname>child_node_reconnect</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_node_reconnect</primary>
+		    <secondary>event notification</secondary>
+		  </indexterm>
+
+          <para>
+			This event is generated after &repmgrd;
+			detects that a child node has resumed streaming from the primary node.
+          </para>
+		  <para>
+			Example:
+			<programlisting>
+$ repmgr cluster event --event=child_node_reconnect
+ Node ID | Name  | Event                | OK | Timestamp           | Details
+---------+-------+----------------------+----+---------------------+------------------------------------------------------------
+ 1       | node1 | child_node_reconnect | t  | 2019-04-24 12:42:19 | node "node3" (ID: 3) has reconnected after 42 seconds</programlisting>
+		  </para>
+        </listitem>
+      </varlistentry>
+
+	  <varlistentry>
+        <term><varname>child_node_new_connect</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_node_new_connect</primary>
+		    <secondary>event notification</secondary>
+		  </indexterm>
+
+          <para>
+			This event is generated after &repmgrd;
+			detects that a new child node has been registered with &repmgr; and has
+			connected to the primary.
+          </para>
+		  <para>
+			Example:
+			<programlisting>
+$ repmgr cluster event --event=child_node_new_connect
+ Node ID | Name  | Event                  | OK | Timestamp           | Details
+---------+-------+------------------------+----+---------------------+---------------------------------------------
+ 1       | node1 | child_node_new_connect | t  | 2019-04-24 12:41:30 | new node "node3" (ID: 3) has connected</programlisting>
+		  </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><varname>child_nodes_disconnect_command</varname></term>
+        <listitem>
+          <indexterm>
+		    <primary>child_nodes_disconnect_command</primary>
+		    <secondary>event notification</secondary>
+		  </indexterm>
+
+          <para>
+			This event is generated after &repmgrd; detects
+			that sufficient child nodes have been disconnected for a sufficient amount
+			of time to trigger execution of the <varname>child_nodes_disconnect_command</varname>.
+          </para>
+		  <para>
+			Example:
+			<programlisting>
+$ repmgr cluster event --event=child_nodes_disconnect_command
+ Node ID | Name  | Event                          | OK | Timestamp           | Details
+---------+-------+--------------------------------+----+---------------------+--------------------------------------------------------
+ 1       | node1 | child_nodes_disconnect_command | t  | 2019-04-24 13:08:17 | "child_nodes_disconnect_command" successfully executed</programlisting>
+		  </para>
+        </listitem>
+      </varlistentry>
+
+	</variablelist>
+
+  </sect2>
+
+
+</sect1>
+
+
+</chapter>

doc/repmgrd-bdr.xml

@@ -1,4 +1,6 @@
 <chapter id="repmgrd-bdr">
+  <title>BDR failover with repmgrd</title>
+
   <indexterm>
     <primary>repmgrd</primary>
     <secondary>BDR</secondary>
@@ -8,9 +10,8 @@
     <primary>BDR</primary>
   </indexterm>
 
-  <title>BDR failover with repmgrd</title>
   <para>
-    &repmgr; 4.x provides support for monitoring BDR nodes and taking action in
+    &repmgr; 4.x provides support for monitoring a pair of BDR 2.x nodes and taking action in
     case one of the nodes fails.
   </para>
   <note>
@@ -24,15 +25,28 @@
   <para>
     In contrast to streaming replication, there's no concept of "promoting" a new
     primary node with BDR. Instead, "failover" involves monitoring both nodes
-    with <application>repmgrd</application> and redirecting queries from the failed node to the remaining
+    with &repmgrd; and redirecting queries from the failed node to the remaining
     active node. This can be done by using an
     <link linkend="event-notifications">event notification</link> script
-    which is called by <application>repmgrd</application> to dynamically
+    which is called by &repmgrd; to dynamically
     reconfigure a proxy server/connection pooler such as <application>PgBouncer</application>.
   </para>
 
+  <note>
+    <simpara>
+      This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
+      It is <emphasis>not</emphasis> required for later BDR versions.
+    </simpara>
+  </note>
+
   <sect1 id="bdr-prerequisites" xreflabel="BDR prequisites">
     <title>Prerequisites</title>
+    <important>
+      <para>
+        This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
+        It is <emphasis>not</emphasis> required for later BDR versions.
+      </para>
+    </important>
     <para>
       &repmgr; 4 requires PostgreSQL 9.4 or 9.6 with the BDR 2 extension
       enabled and configured for a two-node BDR network. &repmgr; 4 packages
@@ -47,7 +61,7 @@
     <para>
       Application database connections *must* be passed through a proxy server/
       connection pooler such as <application>PgBouncer</application>, and it must be possible to dynamically
-      reconfigure that from <application>repmgrd</application>. The example demonstrated in this document
+      reconfigure that from &repmgrd;. The example demonstrated in this document
       will use <application>PgBouncer</application>
     </para>
     <para>
@@ -81,7 +95,7 @@
 
         # Event notification configuration
         event_notifications=bdr_failover
-        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&1'
+        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&amp;1'
 
         # repmgrd options
         monitor_interval_secs=5
@@ -107,7 +121,7 @@
       <simpara>
         <varname>event_notification_command</varname> is the script which does the actual "heavy lifting"
         of reconfiguring the proxy server/ connection pooler. It is fully
-        user-definable; see section <xref linkend="bdr-event-notification-command"> for a reference
+        user-definable; see section <xref linkend="bdr-event-notification-command"/> for a reference
         implementation.
       </simpara>
     </note>
@@ -145,7 +159,7 @@
     </important>
     <para>
       At this point the meta data for both nodes has been created; executing
-      <xref linkend="repmgr-cluster-show"> (on either node) should produce output like this:
+      <xref linkend="repmgr-cluster-show"/> (on either node) should produce output like this:
       <programlisting>
         $ repmgr -f /etc/repmgr.conf cluster show
         ID | Name  | Role | Status    | Upstream | Location | Connection string
@@ -155,7 +169,7 @@
     </para>
     <para>
       Additionally it's possible to display log of significant events;  executing
-      <xref linkend="repmgr-cluster-event"> (on either node) should produce output like this:
+      <xref linkend="repmgr-cluster-event"/> (on either node) should produce output like this:
       <programlisting>
         $ repmgr -f /etc/repmgr.conf cluster event
         Node ID | Event        | OK | Timestamp           | Details
@@ -283,7 +297,7 @@
         </listitem>
         <listitem>
           <simpara>recreates the <application>PgBouncer</application> configuration file on each
-            node using the information provided by <application>repmgrd</application>
+            node using the information provided by &repmgrd;
             (primarily the <varname>conninfo</varname> string) to configure
             <application>PgBouncer</application></simpara>
         </listitem>
@@ -305,21 +319,21 @@
     <title>Node monitoring and failover</title>
     <para>
       At the intervals specified by <varname>monitor_interval_secs</varname>
-      in <filename>repmgr.conf</filename>, <application>repmgrd</application>
+      in <filename>repmgr.conf</filename>, &repmgrd;
       will ping each node to check if it's available. If a node isn't available,
-      <application>repmgrd</application> will enter failover mode and check <varname>reconnect_attempts</varname>
+      &repmgrd; will enter failover mode and check <varname>reconnect_attempts</varname>
       times at intervals of <varname>reconnect_interval</varname> to confirm the node is definitely unreachable.
       This buffer period is necessary to avoid false positives caused by transient
       network outages.
     </para>
     <para>
-      If the node is still unavailable, <application>repmgrd</application> will enter failover mode and execute
+      If the node is still unavailable, &repmgrd; will enter failover mode and execute
       the script defined in <varname>event_notification_command</varname>; an entry will be logged
-      in the <literal>repmgr.events</literal> table and <application>repmgrd</application> will
+      in the <literal>repmgr.events</literal> table and &repmgrd; will
       (unless otherwise configured) resume monitoring of the node in "degraded" mode until it reappears.
     </para>
     <para>
-      <application>repmgrd</application> logfile output during a failover event will look something like this
+      &repmgrd; logfile output during a failover event will look something like this
       on one node (usually the node which has failed, here <literal>node2</literal>):
       <programlisting>
             ...
@@ -375,8 +389,8 @@
     </para>
     <para>
       This assumes only the PostgreSQL instance on <literal>node2</literal> has failed. In this case the
-      <application>repmgrd</application> instance running on <literal>node2</literal> has performed the failover. However if
-      the entire server becomes unavailable, <application>repmgrd</application> on <literal>node1</literal> will perform
+      &repmgrd; instance running on <literal>node2</literal> has performed the failover. However if
+      the entire server becomes unavailable, &repmgrd; on <literal>node1</literal> will perform
       the failover.
     </para>
   </sect1>
@@ -391,7 +405,7 @@
     </para>
     <para>
       If the failed node comes back up and connects correctly, output similar to this
-      will be visible in the <application>repmgrd</application> log:
+      will be visible in the &repmgrd; log:
       <programlisting>
         [2017-07-27 21:25:30] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
         [2017-07-27 21:25:46] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
@@ -404,10 +418,10 @@
   <sect1 id="bdr-complete-shutdown" xreflabel="Shutdown of both nodes">
     <title>Shutdown of both nodes</title>
     <para>
-      If both PostgreSQL instances are shut down, <application>repmgrd</application> will try and handle the
+      If both PostgreSQL instances are shut down, &repmgrd; will try and handle the
       situation as gracefully as possible, though with no failover candidates available
       there's not much it can do. Should this case ever occur, we recommend shutting
-      down <application>repmgrd</application> on both nodes and restarting it once the PostgreSQL instances
+      down &repmgrd; on both nodes and restarting it once the PostgreSQL instances
       are running properly.
     </para>
   </sect1>

doc/repmgrd-configuration.xml

@@ -1,20 +1,20 @@
 <chapter id="repmgrd-configuration">
 
+  <title>repmgrd setup and configuration</title>
+
   <indexterm>
     <primary>repmgrd</primary>
     <secondary>configuration</secondary>
   </indexterm>
 
-  <title>repmgrd setup and configuration</title>
-
   <para>
-    <application>repmgrd</application> is a daemon which runs on each PostgreSQL node,
+    &repmgrd; is a daemon which runs on each PostgreSQL node,
     monitoring the local node, and (unless it's the primary node) the upstream server
     (the primary server or with cascading replication, another standby) which it's
     connected to.
   </para>
   <para>
-    <application>repmgrd</application> can be configured to provide failover
+    &repmgrd; can be configured to provide failover
     capability in case the primary upstream node becomes unreachable, and/or
     provide monitoring data to the &repmgr; metadatabase.
   </para>
@@ -23,7 +23,7 @@
     <title>repmgrd configuration</title>
 
     <para>
-      To use <application>repmgrd</application>, its associated function library <emphasis>must</emphasis> be
+      To use &repmgrd;, its associated function library <emphasis>must</emphasis> be
       included via <filename>postgresql.conf</filename> with:
 
       <programlisting>
@@ -35,112 +35,115 @@
     </para>
 
     <para>
-      The following configuraton options apply to <application>repmgrd</application> in all circumstances:
+      The following configuraton options apply to &repmgrd; in all circumstances:
     </para>
     <variablelist>
 
-        <varlistentry>
-
-         <indexterm>
+      <varlistentry>
+        <term><option>monitor_interval_secs</option></term>
+        <listitem>
+          <indexterm>
             <primary>monitor_interval_secs</primary>
           </indexterm>
-          <term><option>monitor_interval_secs</option></term>
-          <listitem>
-            <para>
-              The interval (in seconds, default: <literal>2</literal>) to check the availability of the upstream node.
-            </para>
-          </listitem>
 
-        </varlistentry>
+          <para>
+            The interval (in seconds, default: <literal>2</literal>) to check the availability of the upstream node.
+          </para>
+        </listitem>
 
-        <varlistentry>
+      </varlistentry>
 
+      <varlistentry id="connection-check-type">
+
+        <term><option>connection_check_type</option></term>
+        <listitem>
           <indexterm>
             <primary>connection_check_type</primary>
           </indexterm>
-          <term><option>connection_check_type</option></term>
-          <listitem>
-            <para>
-              The option <option>connection_check_type</option> is used to select the method
-              <application>repmgrd</application> uses to determine whether the upstream node is available.
-            </para>
-            <para>
-              Possible values are:
-              <itemizedlist spacing="compact" mark="bullet">
-                <listitem>
+
+          <para>
+            The option <option>connection_check_type</option> is used to select the method
+            &repmgrd; uses to determine whether the upstream node is available.
+          </para>
+          <para>
+            Possible values are:
+            <itemizedlist spacing="compact" mark="bullet">
+              <listitem>
                   <simpara>
                     <literal>ping</literal> (default) - uses <command>PQping()</command> to
                     determine server availability
                   </simpara>
-                </listitem>
-                <listitem>
-                  <simpara>
-                    <literal>connection</literal> - determines server availability
-                    by attempt ingto make a new connection to the upstream node
-                  </simpara>
-                </listitem>
-                <listitem>
-                  <simpara>
-                    <literal>query</literal> - determines server availability
-                    by executing an SQL statement on the node via the existing connection
-                  </simpara>
-                </listitem>
+              </listitem>
+              <listitem>
+                <simpara>
+                  <literal>connection</literal> - determines server availability
+                  by attempt ingto make a new connection to the upstream node
+                </simpara>
+              </listitem>
+              <listitem>
+                <simpara>
+                  <literal>query</literal> - determines server availability
+                  by executing an SQL statement on the node via the existing connection
+                </simpara>
+              </listitem>
 
-              </itemizedlist>
-            </para>
-          </listitem>
-        </varlistentry>
+            </itemizedlist>
+          </para>
+        </listitem>
+      </varlistentry>
 
-        <varlistentry>
-         <indexterm>
+      <varlistentry>
+        <term><option>reconnect_attempts</option></term>
+        <listitem>
+          <indexterm>
             <primary>reconnect_attempts</primary>
           </indexterm>
-          <term><option>reconnect_attempts</option></term>
-          <listitem>
-            <para>
-              The number of attempts (default: <literal>6</literal>) will be made to reconnect to an unreachable
-	      upstream node before initiating a failover.
-            </para>
-            <para>
-              There will be an interval of <option>reconnect_interval</option> seconds between each reconnection
-              attempt.
-            </para>
-          </listitem>
-        </varlistentry>
-        <varlistentry>
-         <indexterm>
+          <para>
+            The number of attempts (default: <literal>6</literal>) will be made to reconnect to an unreachable
+	        upstream node before initiating a failover.
+          </para>
+          <para>
+            There will be an interval of <option>reconnect_interval</option> seconds between each reconnection
+            attempt.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>reconnect_interval</option></term>
+
+        <listitem>
+          <indexterm>
             <primary>reconnect_interval</primary>
           </indexterm>
-          <term><option>reconnect_interval</option></term>
-          <listitem>
-            <para>
-              Interval (in seconds, default: <literal>10</literal>) between attempts to reconnect to an unreachable
-              upstream node.
-            </para>
-            <para>
+
+          <para>
+            Interval (in seconds, default: <literal>10</literal>) between attempts to reconnect to an unreachable
+            upstream node.
+          </para>
+          <para>
               The number of reconnection attempts is defined by the parameter <option>reconnect_attempts</option>.
-            </para>
-          </listitem>
-        </varlistentry>
+          </para>
+        </listitem>
+      </varlistentry>
 
-
-
-        <varlistentry>
+      <varlistentry>
+        <term><option>degraded_monitoring_timeout</option></term>
+        <listitem>
           <indexterm>
             <primary>degraded_monitoring_timeout</primary>
           </indexterm>
-          <term><option>degraded_monitoring_timeout</option></term>
-          <listitem>
-	    <para>
-              Interval (in seconds) after which <application>repmgrd</application> will terminate if
-              either of the servers (local node and or upstream node) being monitored is no longer available
-              (<link linkend="repmgrd-degraded-monitoring">degraded monitoring mode</link>).
-            </para>
-            <para>
-              <literal>-1</literal> (default) disables this timeout completely.
-            </para>
-	  </listitem>
-	</varlistentry>
+
+	      <para>
+            Interval (in seconds) after which &repmgrd; will terminate if
+            either of the servers (local node and or upstream node) being monitored is no longer available
+            (<link linkend="repmgrd-degraded-monitoring">degraded monitoring mode</link>).
+          </para>
+          <para>
+            <literal>-1</literal> (default) disables this timeout completely.
+          </para>
+	    </listitem>
+	  </varlistentry>
 
     </variablelist>
 
@@ -152,7 +155,7 @@
       <title>Required configuration for automatic failover</title>
 
       <para>
-        The following <application>repmgrd</application> options <emphasis>must</emphasis> be set in
+        The following &repmgrd; options <emphasis>must</emphasis> be set in
         <filename>repmgr.conf</filename>:
 
         <itemizedlist spacing="compact" mark="bullet">
@@ -182,17 +185,18 @@
       <variablelist>
         <varlistentry>
 
-          <indexterm>
-            <primary>failover</primary>
-          </indexterm>
           <term><option>failover</option></term>
           <listitem>
+            <indexterm>
+              <primary>failover</primary>
+            </indexterm>
+
             <para>
               <option>failover</option> can be one of <literal>automatic</literal> or <literal>manual</literal>.
             </para>
             <note>
               <para>
-                If <option>failover</option> is set to <literal>manual</literal>, <application>repmgrd</application>
+                If <option>failover</option> is set to <literal>manual</literal>, &repmgrd;
                 will not take any action if a failover situation is detected, and the node may need to
                 be modified manually (e.g. by executing <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>).
               </para>
@@ -202,14 +206,16 @@
         </varlistentry>
 
         <varlistentry>
-          <indexterm>
-            <primary>promote_command</primary>
-          </indexterm>
           <term><option>promote_command</option></term>
+
           <listitem>
+            <indexterm>
+              <primary>promote_command</primary>
+            </indexterm>
+
             <para>
               The program or script defined in <option>promote_command</option> will be executed
-              in a failover situation when <application>repmgrd</application> determines that
+              in a failover situation when &repmgrd; determines that
               the current node is to become the new primary node.
             </para>
             <para>
@@ -217,7 +223,7 @@
               <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command> command.
             </para>
             <para>
-              It is also possible to provide e.g. a shell script to e.g. perform user-defined tasks
+              It is also possible to provide a shell script to e.g. perform user-defined tasks
               before promoting the current node. In this case the script <emphasis>must</emphasis>
               at some point execute <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command>
               to promote the node; if this is not done, &repmgr; metadata will not be updated and
@@ -231,8 +237,8 @@
 
             <para>
               Note that the <literal>--log-to-file</literal> option will cause
-              output generated by the &repmgr; command, when executed by <application>repmgrd</application>,
-              to be logged to the same destination configured to receive log output for <application>repmgrd</application>.
+              output generated by the &repmgr; command, when executed by &repmgrd;,
+              to be logged to the same destination configured to receive log output for &repmgrd;.
             </para>
             <note>
               <para>
@@ -245,32 +251,33 @@
         </varlistentry>
 
         <varlistentry>
-          <indexterm>
-            <primary>follow_command</primary>
-          </indexterm>
           <term><option>follow_command</option></term>
           <listitem>
+            <indexterm>
+              <primary>follow_command</primary>
+            </indexterm>
+
             <para>
               The program or script defined in <option>follow_command</option> will be executed
-              in a failover situation when <application>repmgrd</application> determines that
+              in a failover situation when &repmgrd; determines that
               the current node is to follow the new primary node.
             </para>
             <para>
               Normally <option>follow_command</option> is set as &repmgr;'s
-              <command><link linkend="repmgr-standby-follow">repmgr standby promote</link></command> command.
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command> command.
             </para>
             <para>
               The <option>follow_command</option> parameter
               should provide the <literal>--upstream-node-id=%n</literal>
               option to <command>repmgr standby follow</command>; the <literal>%n</literal> will be replaced by
-              <application>repmgrd</application> with the ID of the new primary node. If this is not provided,
+              &repmgrd; with the ID of the new primary node. If this is not provided,
               <command>repmgr standby follow</command> will attempt to determine the new primary by itself, but if the
               original primary comes back online after the new primary is promoted, there is a risk that
               <command>repmgr standby follow</command> will result in the node continuing to follow
               the original primary.
             </para>
             <para>
-              It is also possible to provide e.g. a shell script to e.g. perform user-defined tasks
+              It is also possible to provide a shell script to e.g. perform user-defined tasks
               before promoting the current node. In this case the script <emphasis>must</emphasis>
               at some point execute <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>
               to promote the node; if this is not done, &repmgr; metadata will not be updated and
@@ -284,8 +291,8 @@
 
             <para>
               Note that the <literal>--log-to-file</literal> option will cause
-              output generated by the &repmgr; command, when executed by <application>repmgrd</application>,
-              to be logged to the same destination configured to receive log output for <application>repmgrd</application>.
+              output generated by the &repmgr; command, when executed by &repmgrd;,
+              to be logged to the same destination configured to receive log output for &repmgrd;.
             </para>
             <note>
               <para>
@@ -312,11 +319,12 @@
       <variablelist>
 
         <varlistentry>
-          <indexterm>
-            <primary>priority</primary>
-          </indexterm>
           <term><option>priority</option></term>
           <listitem>
+            <indexterm>
+              <primary>priority</primary>
+            </indexterm>
+
             <para>
               Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes;
 			  a value of zero prevents the node being promoted to primary.
@@ -330,14 +338,15 @@
         </varlistentry>
 
         <varlistentry>
-          <indexterm>
-            <primary>failover_validation_command</primary>
-          </indexterm>
           <term><option>failover_validation_command</option></term>
           <listitem>
+            <indexterm>
+              <primary>failover_validation_command</primary>
+            </indexterm>
+
             <para>
               User-defined script to execute for an external mechanism to validate the failover
-	      decision made by <application>repmgrd</application>.
+	      decision made by &repmgrd;.
             </para>
             <note>
               <para>
@@ -366,12 +375,13 @@
 
 
         <varlistentry>
-
-         <indexterm>
-            <primary>primary_visibility_consensus</primary>
-          </indexterm>
           <term><option>primary_visibility_consensus</option></term>
+
           <listitem>
+            <indexterm>
+              <primary>primary_visibility_consensus</primary>
+            </indexterm>
+
             <para>
               If <literal>true</literal>, only continue with failover if no standbys have seen
 			  the primary node recently.
@@ -387,11 +397,12 @@
 
         <varlistentry>
 
-         <indexterm>
-            <primary>standby_disconnect_on_failover</primary>
-          </indexterm>
           <term><option>standby_disconnect_on_failover</option></term>
           <listitem>
+            <indexterm>
+              <primary>standby_disconnect_on_failover</primary>
+            </indexterm>
+
             <para>
               In a failover situation, disconnect the local node's WAL receiver.
             </para>
@@ -408,7 +419,7 @@
                 for this option.
               </para>
               <para>
-                <application>repmgrd</application> will refuse to start if this option is set
+                &repmgrd; will refuse to start if this option is set
                 but either of these prerequisites is not met.
               </para>
             </note>
@@ -429,11 +440,12 @@
       <variablelist>
 
         <varlistentry>
-          <indexterm>
-            <primary>election_rerun_interval</primary>
-          </indexterm>
           <term><option>election_rerun_interval</option></term>
           <listitem>
+            <indexterm>
+              <primary>election_rerun_interval</primary>
+            </indexterm>
+
 			<para>
 			  If <option>failover_validation_command</option> is set, and the command returns
 			  an error, pause the specified amount of seconds (default: 15) before rerunning the election.
@@ -443,11 +455,12 @@
 
 
         <varlistentry>
-          <indexterm>
-            <primary>sibling_nodes_disconnect_timeout</primary>
-          </indexterm>
           <term><option>sibling_nodes_disconnect_timeout</option></term>
           <listitem>
+            <indexterm>
+              <primary>sibling_nodes_disconnect_timeout</primary>
+            </indexterm>
+
 			<para>
               If <option>standby_disconnect_on_failover</option> is <literal>true</literal>, the
               maximum length of time (in seconds, default: <literal>30</literal>)
@@ -463,34 +476,36 @@
     </sect2>
 
     <sect2 id="postgresql-service-configuration">
+      <title>PostgreSQL service configuration</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>PostgreSQL service configuration</secondary>
       </indexterm>
-      <title>PostgreSQL service configuration</title>
       <para>
-        If using automatic failover, currently <application>repmgrd</application> will need to execute
+        If using automatic failover, currently &repmgrd; will need to execute
         <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>
         to restart PostgreSQL on standbys to have them follow a new primary.
       </para>
       <para>
         To ensure this happens smoothly, it's essential to provide the appropriate system/service restart
         command appropriate to your operating system via <varname>service_restart_command</varname>
-        in <filename>repmgr.conf</filename>. If you don't do this, <application>repmgrd</application>
+        in <filename>repmgr.conf</filename>. If you don't do this, &repmgrd;
         will default to using <command>pg_ctl</command>, which can result in unexpected problems,
         particularly on <application>systemd</application>-based systems.
       </para>
       <para>
-        For more details, see <xref linkend="configuration-file-service-commands">.
+        For more details, see <xref linkend="configuration-file-service-commands"/>.
       </para>
     </sect2>
 
     <sect2 id="repmgrd-service-configuration">
+      <title>repmgrd service configuration</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>repmgrd service configuration</secondary>
       </indexterm>
-      <title>repmgrd service configuration</title>
       <para>
         If you are intending to use the <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link>
         and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> commands, the following
@@ -522,11 +537,12 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
 
 
     <sect2 id="repmgrd-monitoring-configuration" xreflabel="repmgrd monitoring configuration">
+      <title>Monitoring configuration</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>monitoring configuration</secondary>
       </indexterm>
-      <title>Monitoring configuration</title>
       <para>
         To enable monitoring, set:
         <programlisting>
@@ -538,32 +554,33 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         the option <option>monitor_interval_secs</option> (see above).
       </para>
       <para>
-        For more details on monitoring, see <xref linkend="repmgrd-monitoring">.
+        For more details on monitoring, see <xref linkend="repmgrd-monitoring"/>.
       </para>
     </sect2>
 
-    <sect2 id="repmgrd-reloading-configuration"xreflabel="reloading repmgrd configuration">
+    <sect2 id="repmgrd-reloading-configuration" xreflabel="reloading repmgrd configuration">
+      <title>Applying configuration changes to repmgrd</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>applying configuration changes</secondary>
       </indexterm>
-      <title>Applying configuration changes to repmgrd</title>
       <para>
-        To apply configuration file changes to a running <application>repmgrd</application>
-        daemon, execute the operating system's <application>repmgrd</application> service reload command
-        (see <xref linkend="appendix-packages"> for examples),
+        To apply configuration file changes to a running &repmgrd;
+        daemon, execute the operating system's &repmgrd; service reload command
+        (see <xref linkend="appendix-packages"/> for examples),
           or for instances  which were manually started, execute <command>kill -HUP</command>, e.g.
           <command>kill -HUP `cat /tmp/repmgrd.pid`</command>.
       </para>
       <tip>
         <para>
-          Check the <application>repmgrd</application> log to see what changes were
+          Check the &repmgrd; log to see what changes were
           applied, or if any issues were encountered when reloading the configuration.
         </para>
       </tip>
       <para>
         Note that only the following subset of configuration file parameters can be changed on a
-        running <application>repmgrd</application> daemon:
+        running &repmgrd; daemon:
       </para>
       <itemizedlist spacing="compact" mark="bullet">
 
@@ -585,6 +602,41 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
           </simpara>
         </listitem>
 
+         <listitem>
+          <simpara>
+            <varname>child_nodes_check_interval</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>child_nodes_connected_include_witness</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>child_nodes_connected_min_count</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>child_nodes_disconnect_command</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>child_nodes_disconnect_min_count</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>child_nodes_disconnect_timeout</varname>
+          </simpara>
+        </listitem>
 
         <listitem>
           <simpara>
@@ -770,7 +822,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
       <note>
         <para>
           After executing <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>,
-          <application>repmgrd</application> <emphasis>must</emphasis> be restarted for the changes to take effect.
+          &repmgrd; <emphasis>must</emphasis> be restarted for the changes to take effect.
         </para>
       </note>
 
@@ -779,24 +831,25 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
   </sect1>
 
   <sect1 id="repmgrd-daemon" xreflabel="repmgrd daemon">
+    <title>repmgrd daemon</title>
+
     <indexterm>
       <primary>repmgrd</primary>
       <secondary>starting and stopping</secondary>
     </indexterm>
-    <title>repmgrd daemon</title>
     <para>
-      If installed from a package, the <application>repmgrd</application> can be started
+      If installed from a package, the &repmgrd; can be started
       via the operating system's service command, e.g. in <application>systemd</application>
       using <command>systemctl</command>.
     </para>
     <para>
-      See appendix <xref linkend="appendix-packages"> for details of service commands
+      See appendix <xref linkend="appendix-packages"/> for details of service commands
       for different distributions.
     </para>
     <para>
       The commands <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link> and
       <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> can be used
-      as convenience wrappers to start and stop <application>repmgrd</application>.
+      as convenience wrappers to start and stop &repmgrd;.
     </para>
     <important>
       <para>
@@ -808,13 +861,15 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
       </para>
     </important>
     <para>
-      <application>repmgrd</application> can be started manually like this:
+      &repmgrd; can be started manually like this:
       <programlisting>
         repmgrd -f /etc/repmgr.conf --pid-file /tmp/repmgrd.pid</programlisting>
       and stopped with <command>kill `cat /tmp/repmgrd.pid`</command>. Adjust paths as appropriate.
     </para>
 
     <sect2 id="repmgrd-pid-file" xreflabel="repmgrd's PID file">
+      <title>repmgrd's PID file</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>PID file</secondary>
@@ -823,9 +878,8 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         <primary>PID file</primary>
         <secondary>repmgrd</secondary>
       </indexterm>
-      <title>repmgrd's PID file</title>
       <para>
-        <application>repmgrd</application> will generate a PID file by default.
+        &repmgrd; will generate a PID file by default.
       </para>
       <note>
         <simpara>
@@ -845,12 +899,12 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         <option>--pid-file</option> may be deprecated in future releases.
       </para>
       <para>
-        If a PID file location was specified by the package maintainer, <application>repmgrd</application>
+        If a PID file location was specified by the package maintainer, &repmgrd;
         will use that. This only applies if &repmgr; was installed from a package and the package
         maintainer has specified the PID file location.
       </para>
       <para>
-        If none of the above apply, <application>repmgrd</application> will create a PID file
+        If none of the above apply, &repmgrd; will create a PID file
         in the operating system's temporary directory (as setermined by the environment variable
         <varname>TMPDIR</varname>, or if that is not set, will use <filename>/tmp</filename>).
       </para>
@@ -859,15 +913,17 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         <option>--no-pid-file</option>.
       </para>
       <para>
-        To see which PID file <application>repmgrd</application> would use, execute <application>repmgrd</application>
-        with the option <option>--show-pid-file</option>. <application>repmgrd</application>
+        To see which PID file &repmgrd; would use, execute &repmgrd;
+        with the option <option>--show-pid-file</option>. &repmgrd;
         will not start if this option is provided. Note that the value shown is the
-        file  <application>repmgrd</application> would use next time it starts, and is
+        file  &repmgrd; would use next time it starts, and is
         not necessarily the PID file currently in use.
       </para>
     </sect2>
 
     <sect2 id="repmgrd-configuration-debian-ubuntu">
+      <title>repmgrd daemon configuration on Debian/Ubuntu</title>
+
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>Debian/Ubuntu and daemon configuration</secondary>
@@ -877,11 +933,9 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         <secondary>repmgrd daemon configuration</secondary>
       </indexterm>
 
-      <title>repmgrd daemon configuration on Debian/Ubuntu</title>
-
       <para>
         If &repmgr; was installed from Debian/Ubuntu packages, additional configuration
-        is required before <application>repmgrd</application> is started as a daemon.
+        is required before &repmgrd; is started as a daemon.
       </para>
       <para>
         This is done via the file <filename>/etc/default/repmgrd</filename>, which by default
@@ -915,17 +969,17 @@ REPMGRD_OPTS="--daemonize=false"
       </para>
       <tip>
         <para>
-          See <xref linkend="packages-debian-ubuntu"> for details of the Debian/Ubuntu packages and
+          See <xref linkend="packages-debian-ubuntu"/> for details of the Debian/Ubuntu packages and
           typical file locations (including <filename>repmgr.conf</filename>).
         </para>
       </tip>
       <para>
-        From <application>repmgrd</application> 4.1, ensure <varname>REPMGRD_OPTS</varname> includes
+        From &repmgrd; 4.1, ensure <varname>REPMGRD_OPTS</varname> includes
         <option>--daemonize=false</option>, as daemonization is handled by the service command.
       </para>
       <para>
         If using <application>systemd</application>, you may need to execute <command>systemctl daemon-reload</command>.
-        Also, if you attempted to start <application>repmgrd</application> using <command>systemctl start repmgrd</command>,
+        Also, if you attempted to start &repmgrd; using <command>systemctl start repmgrd</command>,
         you'll need to execute <command>systemctl stop repmgrd</command>. Because that's how <application>systemd</application>
         rolls.
       </para>
@@ -959,7 +1013,9 @@ REPMGRD_OPTS="--daemonize=false"
 
 
 
- <sect1 id="repmgrd-log-rotation">
+  <sect1 id="repmgrd-log-rotation">
+     <title>repmgrd log rotation</title>
+
    <indexterm>
      <primary>log rotation</primary>
      <secondary>repmgrd</secondary>
@@ -970,9 +1026,8 @@ REPMGRD_OPTS="--daemonize=false"
      <secondary>log rotation</secondary>
    </indexterm>
 
-  <title>repmgrd log rotation</title>
   <para>
-   To ensure the current <application>repmgrd</application> logfile
+   To ensure the current &repmgrd; logfile
    (specified in <filename>repmgr.conf</filename> with the parameter
    <option>log_file</option>) does not grow indefinitely, configure your
    system's <command>logrotate</command> to regularly rotate it.

doc/repmgrd-operation.xml

@@ -1,14 +1,15 @@
 <chapter id="repmgrd-operation" xreflabel="repmgrd operation">
+  <title>repmgrd operation</title>
+
   <indexterm>
     <primary>repmgrd</primary>
     <secondary>operation</secondary>
   </indexterm>
 
-  <title>repmgrd operation</title>
-
-
   <sect1 id="repmgrd-pausing">
 
+    <title>Pausing repmgrd</title>
+
   <indexterm>
     <primary>repmgrd</primary>
     <secondary>pausing</secondary>
@@ -18,45 +19,44 @@
     <primary>pausing repmgrd</primary>
   </indexterm>
 
-  <title>Pausing repmgrd</title>
 
   <para>
-    In normal operation, <application>repmgrd</application> monitors the state of the
+    In normal operation, &repmgrd; monitors the state of the
     PostgreSQL node it is running on, and will take appropriate action if problems
     are detected, e.g. (if so configured) promote the node to primary, if the existing
     primary has been determined as failed.
   </para>
 
   <para>
-    However, <application>repmgrd</application> is unable to distinguish between
+    However, &repmgrd; is unable to distinguish between
     planned outages (such as performing a <link linkend="performing-switchover">switchover</link>
     or installing PostgreSQL maintenance released), and an actual server outage. In versions prior to
-    &repmgr; 4.2 it was necessary to stop <application>repmgrd</application> on all nodes (or at least
-    on all nodes where <application>repmgrd</application> is
+    &repmgr; 4.2 it was necessary to stop &repmgrd; on all nodes (or at least
+    on all nodes where &repmgrd; is
     <link linkend="repmgrd-automatic-failover">configured for automatic failover</link>)
-    to prevent <application>repmgrd</application> from making unintentional changes to the
+    to prevent &repmgrd; from making unintentional changes to the
     replication cluster.
   </para>
 
   <para>
-    From <link linkend="release-4.2">&repmgr; 4.2</link>, <application>repmgrd</application>
+    From <link linkend="release-4.2">&repmgr; 4.2</link>, &repmgrd;
     can now be &quot;paused&quot;, i.e. instructed not to take any action such as performing a failover.
     This can be done from any node in the cluster, removing the need to stop/restart
-    each <application>repmgrd</application> individually.
+    each &repmgrd; individually.
   </para>
 
   <note>
     <para>
       For major PostgreSQL upgrades, e.g. from PostgreSQL 10 to PostgreSQL 11,
-      <application>repmgrd</application> should be shut down completely and only started up
+      &repmgrd; should be shut down completely and only started up
       once the &repmgr; packages for the new PostgreSQL major version have been installed.
     </para>
   </note>
 
   <sect2 id="repmgrd-pausing-prerequisites">
-    <title>Prerequisites for pausing <application>repmgrd</application></title>
+    <title>Prerequisites for pausing &repmgrd;</title>
     <para>
-      In order to be able to pause/unpause <application>repmgrd</application>, following
+      In order to be able to pause/unpause &repmgrd;, following
       prerequisites must be met:
       <itemizedlist spacing="compact" mark="bullet">
 
@@ -86,9 +86,9 @@
   </sect2>
 
   <sect2 id="repmgrd-pausing-execution">
-    <title>Pausing/unpausing <application>repmgrd</application></title>
+    <title>Pausing/unpausing &repmgrd;</title>
     <para>
-      To pause <application>repmgrd</application>, execute <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link>, e.g.:
+      To pause &repmgrd;, execute <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link>, e.g.:
    <programlisting>
 $ repmgr -f /etc/repmgr.conf daemon pause
 NOTICE: node 1 (node1) paused
@@ -96,7 +96,7 @@ NOTICE: node 2 (node2) paused
 NOTICE: node 3 (node3) paused</programlisting>
     </para>
     <para>
-      The state of <application>repmgrd</application> on each node can be checked with
+      The state of &repmgrd; on each node can be checked with
       <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>, e.g.:
     <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status  | repmgrd | PID  | Paused?
@@ -109,15 +109,15 @@ NOTICE: node 3 (node3) paused</programlisting>
     <note>
       <para>
         If executing a switchover with  <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-		&repmgr; will automatically pause/unpause <application>repmgrd</application> as part of the switchover process.
+		&repmgr; will automatically pause/unpause &repmgrd; as part of the switchover process.
       </para>
     </note>
 
     <para>
-      If the primary (in this example, <literal>node1</literal>) is stopped, <application>repmgrd</application>
+      If the primary (in this example, <literal>node1</literal>) is stopped, &repmgrd;
       running on one of the standbys (here: <literal>node2</literal>) will react like this:
       <programlisting>
-[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (node ID: 1)
+[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (ID: 1)
 [2018-09-20 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts
 [2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
 ...
@@ -125,19 +125,19 @@ NOTICE: node 3 (node3) paused</programlisting>
 [2018-09-20 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts
 [2018-09-20 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
 [2018-09-20 12:22:25] [NOTICE] node is paused
-[2018-09-20 12:22:33] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state
+[2018-09-20 12:22:33] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state
 [2018-09-20 12:22:33] [DETAIL] repmgrd paused by administrator
 [2018-09-20 12:22:33] [HINT] execute "repmgr daemon unpause" to resume normal failover mode</programlisting>
     </para>
     <para>
-      If the primary becomes available again (e.g. following a software upgrade), <application>repmgrd</application>
+      If the primary becomes available again (e.g. following a software upgrade), &repmgrd;
       will automatically reconnect, e.g.:
       <programlisting>
 [2018-09-20 13:12:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
     </para>
 
     <para>
-      To unpause <application>repmgrd</application>, execute <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>, e.g.:
+      To unpause &repmgrd;, execute <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>, e.g.:
    <programlisting>
 $ repmgr -f /etc/repmgr.conf daemon unpause
 NOTICE: node 1 (node1) unpaused
@@ -147,7 +147,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
 
     <note>
       <para>
-        If the previous primary is no longer accessible when <application>repmgrd</application>
+        If the previous primary is no longer accessible when &repmgrd;
         is unpaused, no failover action will be taken. Instead, a new primary must be manually promoted using
         <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>,
 		and any standbys attached to the new primary with
@@ -156,13 +156,13 @@ NOTICE: node 3 (node3) unpaused</programlisting>
       <para>
         This is to prevent <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
         resulting in the automatic promotion of a new primary, which may be a problem particularly
-        in larger clusters, where <application>repmgrd</application> could select a different promotion
+        in larger clusters, where &repmgrd; could select a different promotion
         candidate to the one intended by the administrator.
       </para>
     </note>
   </sect2>
   <sect2 id="repmgrd-pausing-details">
-    <title>Details on the <application>repmgrd</application> pausing mechanism</title>
+    <title>Details on the &repmgrd; pausing mechanism</title>
 
     <para>
       The pause state of each node will be stored over a PostgreSQL restart.
@@ -171,30 +171,31 @@ NOTICE: node 3 (node3) unpaused</programlisting>
 	<para>
 	  <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
 	  <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link> can be
-	  executed even if <application>repmgrd</application> is not running; in this case,
-	  <application>repmgrd</application> will start up in whichever pause state has been set.
+	  executed even if &repmgrd; is not running; in this case,
+	  &repmgrd; will start up in whichever pause state has been set.
 	</para>
     <note>
       <para>
 		<link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
 		<link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
-		<emphasis>do not</emphasis> stop/start <application>repmgrd</application>.
+		<emphasis>do not</emphasis> stop/start &repmgrd;.
       </para>
     </note>
   </sect2>
   </sect1>
 
   <sect1 id="repmgrd-wal-replay-pause">
+    <title>repmgrd and paused WAL replay</title>
+
     <indexterm>
       <primary>repmgrd</primary>
       <secondary>paused WAL replay</secondary>
     </indexterm>
 
-    <title>repmgrd and paused WAL replay</title>
     <para>
       If WAL replay has been paused (using <command>pg_wal_replay_pause()</command>,
       on PostgreSQL 9.6 and earlier <command>pg_xlog_replay_pause()</command>),
-      in a failover situation <application>repmgrd</application> will
+      in a failover situation &repmgrd; will
       automatically resume WAL replay.
     </para>
     <para>
@@ -214,6 +215,8 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   </sect1>
 
 <sect1 id="repmgrd-degraded-monitoring" xreflabel="repmgrd degraded monitoring">
+ <title>"degraded monitoring" mode</title>
+
  <indexterm>
    <primary>repmgrd</primary>
    <secondary>degraded monitoring</secondary>
@@ -223,11 +226,10 @@ NOTICE: node 3 (node3) unpaused</programlisting>
    <primary>degraded monitoring</primary>
  </indexterm>
 
- <title>"degraded monitoring" mode</title>
  <para>
-  In certain circumstances, <application>repmgrd</application> is not able to fulfill its primary mission
+  In certain circumstances, &repmgrd; is not able to fulfill its primary mission
   of monitoring the node's upstream server. In these cases it enters &quot;degraded monitoring&quot;
-  mode, where <application>repmgrd</application> remains active but is waiting for the situation
+  mode, where &repmgrd; remains active but is waiting for the situation
   to be resolved.
  </para>
  <para>
@@ -268,8 +270,8 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   Example output in a situation where there is only one standby with <literal>failover=manual</literal>,
   and the primary node is unavailable (but is later restarted):
   <programlisting>
-    [2017-08-29 10:59:19] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in normal state (automatic failover disabled)
-    [2017-08-29 10:59:33] [WARNING] unable to connect to upstream node "node1" (node ID: 1)
+    [2017-08-29 10:59:19] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in normal state (automatic failover disabled)
+    [2017-08-29 10:59:33] [WARNING] unable to connect to upstream node "node1" (ID: 1)
     [2017-08-29 10:59:33] [INFO] checking state of node 1, 1 of 5 attempts
     [2017-08-29 10:59:33] [INFO] sleeping 1 seconds until next reconnection attempt
     (...)
@@ -278,21 +280,21 @@ NOTICE: node 3 (node3) unpaused</programlisting>
     [2017-08-29 10:59:37] [NOTICE] this node is not configured for automatic failover so will not be considered as promotion candidate
     [2017-08-29 10:59:37] [NOTICE] no other nodes are available as promotion candidate
     [2017-08-29 10:59:37] [HINT] use "repmgr standby promote" to manually promote this node
-    [2017-08-29 10:59:37] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state (automatic failover disabled)
-    [2017-08-29 10:59:53] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state (automatic failover disabled)
+    [2017-08-29 10:59:37] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
+    [2017-08-29 10:59:53] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
     [2017-08-29 11:00:45] [NOTICE] reconnected to upstream node 1 after 68 seconds, resuming monitoring
-    [2017-08-29 11:00:57] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in normal state (automatic failover disabled)</programlisting>
+    [2017-08-29 11:00:57] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in normal state (automatic failover disabled)</programlisting>
 
  </para>
  <para>
   By default, <literal>repmgrd</literal> will continue in degraded monitoring mode indefinitely.
   However a timeout (in seconds) can be set with <varname>degraded_monitoring_timeout</varname>,
-  after which <application>repmgrd</application> will terminate.
+  after which &repmgrd; will terminate.
  </para>
 
  <note>
    <para>
-     If <application>repmgrd</application> is monitoring a primary mode which has been stopped
+     If &repmgrd; is monitoring a primary mode which has been stopped
      and manually restarted as a standby attached to a new primary, it will automatically detect
      the status change and update the node record to reflect the node's new status
      as an active standby. It will then resume monitoring the node as a standby.
@@ -302,6 +304,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
 
 
 <sect1 id="repmgrd-monitoring" xreflabel="Storing monitoring data">
+ <title>Storing monitoring data</title>
  <indexterm>
    <primary>repmgrd</primary>
    <secondary>monitoring</secondary>
@@ -311,9 +314,8 @@ NOTICE: node 3 (node3) unpaused</programlisting>
    <secondary>with repmgrd</secondary>
  </indexterm>
 
- <title>Storing monitoring data</title>
  <para>
-   When <application>repmgrd</application> is running with the option <literal>monitoring_history=true</literal>,
+   When &repmgrd; is running with the option <literal>monitoring_history=true</literal>,
   it will constantly write standby node status information to the
   <varname>monitoring_history</varname> table, providing a near-real time
   overview of replication status on all nodes
@@ -346,12 +348,12 @@ NOTICE: node 3 (node3) unpaused</programlisting>
  <para>
   As this can generate a large amount of monitoring data in the table
   <literal>repmgr.monitoring_history</literal>. it's advisable to regularly
-  purge historical data using the <xref linkend="repmgr-cluster-cleanup">
+  purge historical data using the <xref linkend="repmgr-cluster-cleanup"/>
   command; use the <literal>-k/--keep-history</literal> option to
   specify how many day's worth of data should be retained.
  </para>
  <para>
-  It's possible to use <application>repmgrd</application> to run in monitoring
+  It's possible to use &repmgrd; to run in monitoring
   mode only (without automatic failover capability) for some or all
   nodes by setting <literal>failover=manual</literal> in the node's
   <filename>repmgr.conf</filename> file. In the event of the node's upstream failing,

doc/repmgrd-overview.sgml

@@ -1,122 +0,0 @@
-<chapter id="repmgrd-overview" xreflabel="repmgrd overview">
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>overview</secondary>
-  </indexterm>
-
-  <title>repmgrd overview</title>
-
-  <para>
-    <application>repmgrd</application> (&quot;<literal>replication manager daemon</literal>&quot;)
-    is a management and monitoring daemon which runs
-    on each node in a replication cluster. It can automate actions such as
-    failover and updating standbys to follow the new primary, as well as
-    providing monitoring information about the state of each standby.
-  </para>
-
-  <sect1 id="repmgrd-demonstration">
-
-    <title>repmgrd demonstration</title>
-    <para>
-  To demonstrate automatic failover, set up a 3-node replication cluster (one primary
-  and two standbys streaming directly from the primary) so that the cluster looks
-  something like this:
-  <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster show
-     ID | Name  | Role    | Status    | Upstream | Location | Connection string
-    ----+-------+---------+-----------+----------+----------+--------------------------------------
-     1  | node1 | primary | * running |          | default  | host=node1 dbname=repmgr user=repmgr
-     2  | node2 | standby |   running | node1    | default  | host=node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node1    | default  | host=node3 dbname=repmgr user=repmgr</programlisting>
- </para>
-
- <tip>
-   <para>
-     See section <link linkend="repmgrd-automatic-failover-configuration">Required configuration for automatic failover</link>
-     for an example of minimal <filename>repmgr.conf</filename> file settings suitable for use with <application>repmgrd</application>.
-   </para>
- </tip>
- <para>
-  Start <application>repmgrd</application> on each standby and verify that it's running by examining the
-  log output, which at log level <literal>INFO</literal> will look like this:
-  <programlisting>
-    [2017-08-24 17:31:00] [NOTICE] using configuration file "/etc/repmgr.conf"
-    [2017-08-24 17:31:00] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr"
-    [2017-08-24 17:31:00] [NOTICE] starting monitoring of node <literal>node2</literal> (ID: 2)
-    [2017-08-24 17:31:00] [INFO] monitoring connection to upstream node "node1" (node ID: 1)</programlisting>
- </para>
- <para>
-  Each <application>repmgrd</application> should also have recorded its successful startup as an event:
-  <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
-     Node ID | Name  | Event         | OK | Timestamp           | Details
-    ---------+-------+---------------+----+---------------------+-------------------------------------------------------------
-     3       | node3 | repmgrd_start | t  | 2017-08-24 17:35:54 | monitoring connection to upstream node "node1" (node ID: 1)
-     2       | node2 | repmgrd_start | t  | 2017-08-24 17:35:50 | monitoring connection to upstream node "node1" (node ID: 1)
-     1       | node1 | repmgrd_start | t  | 2017-08-24 17:35:46 | monitoring cluster primary "node1" (node ID: 1)  </programlisting>
- </para>
- <para>
-  Now stop the current primary server with e.g.:
-  <programlisting>
-    pg_ctl -D /var/lib/postgresql/data -m immediate stop</programlisting>
- </para>
- <para>
-  This will force the primary to shut down straight away, aborting all processes
-  and transactions.  This will cause a flurry of activity in the <application>repmgrd</application> log
-  files as each <application>repmgrd</application> detects the failure of the primary and a failover
-  decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
-  which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
-  <programlisting>
-    [2017-08-24 23:32:01] [INFO] node "node2" (node ID: 2) monitoring upstream node "node1" (node ID: 1) in normal state
-    [2017-08-24 23:32:08] [WARNING] unable to connect to upstream node "node1" (node ID: 1)
-    [2017-08-24 23:32:08] [INFO] checking state of node 1, 1 of 5 attempts
-    [2017-08-24 23:32:08] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-08-24 23:32:09] [INFO] checking state of node 1, 2 of 5 attempts
-    [2017-08-24 23:32:09] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-08-24 23:32:10] [INFO] checking state of node 1, 3 of 5 attempts
-    [2017-08-24 23:32:10] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-08-24 23:32:11] [INFO] checking state of node 1, 4 of 5 attempts
-    [2017-08-24 23:32:11] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-08-24 23:32:12] [INFO] checking state of node 1, 5 of 5 attempts
-    [2017-08-24 23:32:12] [WARNING] unable to reconnect to node 1 after 5 attempts
-    INFO:  setting voting term to 1
-    INFO:  node 2 is candidate
-    INFO:  node 3 has received request from node 2 for electoral term 1 (our term: 0)
-    [2017-08-24 23:32:12] [NOTICE] this node is the winner, will now promote self and inform other nodes
-    INFO: connecting to standby database
-    NOTICE: promoting standby
-    DETAIL: promoting server using 'pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' promote'
-    INFO: reconnecting to promoted server
-    NOTICE: STANDBY PROMOTE successful
-    DETAIL: node 2 was successfully promoted to primary
-    INFO:  node 3 received notification to follow node 2
-    [2017-08-24 23:32:13] [INFO] switching to primary monitoring mode</programlisting>
- </para>
- <para>
-  The cluster status will now look like this, with the original primary (<literal>node1</literal>)
-  marked as inactive, and standby <literal>node3</literal> now following the new primary
-  (<literal>node2</literal>):
-  <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster show
-     ID | Name  | Role    | Status    | Upstream | Location | Connection string
-    ----+-------+---------+-----------+----------+----------+----------------------------------------------------
-     1  | node1 | primary | - failed  |          | default  | host=node1 dbname=repmgr user=repmgr
-     2  | node2 | primary | * running |          | default  | host=node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node2    | default  | host=node3 dbname=repmgr user=repmgr</programlisting>
-
- </para>
- <para>
-  <command>repmgr cluster event</command> will display a summary of what happened to each server
-  during the failover:
-  <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster event
-     Node ID | Name  | Event                    | OK | Timestamp           | Details
-    ---------+-------+--------------------------+----+---------------------+-----------------------------------------------------------------------------------
-     3       | node3 | repmgrd_failover_follow  | t  | 2017-08-24 23:32:16 | node 3 now following new upstream node 2
-     3       | node3 | standby_follow           | t  | 2017-08-24 23:32:16 | node 3 is now attached to node 2
-     2       | node2 | repmgrd_failover_promote | t  | 2017-08-24 23:32:13 | node 2 promoted to primary; old primary 1 marked as failed
-     2       | node2 | standby_promote          | t  | 2017-08-24 23:32:13 | node 2 was successfully promoted to primary</programlisting>
- </para>
-
-  </sect1>
-</chapter>

doc/repmgrd-overview.xml

@@ -0,0 +1,187 @@
+<chapter id="repmgrd-overview" xreflabel="repmgrd overview">
+  <title>repmgrd overview</title>
+
+  <indexterm>
+    <primary>repmgrd</primary>
+    <secondary>overview</secondary>
+  </indexterm>
+
+  <para>
+    &repmgrd; (&quot;<literal>replication manager daemon</literal>&quot;)
+    is a management and monitoring daemon which runs
+    on each node in a replication cluster. It can automate actions such as
+    failover and updating standbys to follow the new primary, as well as
+    providing monitoring information about the state of each standby.
+  </para>
+  <para>
+    &repmgrd; is designed to be straightforward to set up
+    and does not require additional external infrastructure.
+  </para>
+  <para>
+    Functionality provided by &repmgrd; includes:
+    <itemizedlist spacing="compact" mark="bullet">
+
+       <listitem>
+         <simpara>
+           wide range of <link linkend="repmgrd-basic-configuration">configuration options</link>
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           option to execute custom scripts (&quot;<link linkend="event-notifications">event notifications</link>
+           at different points in the failover sequence
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           ability to <link linkend="repmgrd-pausing">pause repmgrd</link>
+           operation on all nodes with a
+           <link linkend="repmgr-daemon-pause"><command>single command</command></link>
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           optional <link linkend="repmgrd-witness-server">witness server</link>
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           &quot;location&quot; configuration option to restrict
+           potential promotion candidates to a single location
+           (e.g. when nodes are spread over multiple data centres)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           <link linkend="connection-check-type">choice of method</link> to determine node availability
+           (PostgreSQL ping, query execution or new connection)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           retention of monitoring statistics (optional)
+         </simpara>
+       </listitem>
+
+
+    </itemizedlist>
+
+  </para>
+
+  <sect1 id="repmgrd-demonstration">
+
+    <title>repmgrd demonstration</title>
+    <para>
+  To demonstrate automatic failover, set up a 3-node replication cluster (one primary
+  and two standbys streaming directly from the primary) so that the cluster looks
+  something like this:
+  <programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster show --compact
+     ID | Name  | Role    | Status    | Upstream | Location | Prio.
+    ----+-------+---------+-----------+----------+----------+-------
+     1  | node1 | primary | * running |          | default  | 100
+     2  | node2 | standby |   running | node1    | default  | 100
+     3  | node3 | standby |   running | node1    | default  | 100</programlisting>
+ </para>
+
+ <tip>
+   <para>
+     See section <link linkend="repmgrd-automatic-failover-configuration">Required configuration for automatic failover</link>
+     for an example of minimal <filename>repmgr.conf</filename> file settings suitable for use with &repmgrd;.
+   </para>
+ </tip>
+ <para>
+  Start &repmgrd; on each standby and verify that it's running by examining the
+  log output, which at log level <literal>INFO</literal> will look like this:
+  <programlisting>
+    [2019-03-15 06:32:05] [NOTICE] repmgrd (repmgrd 4.3) starting up
+    [2019-03-15 06:32:05] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr connect_timeout=2"
+    INFO:  set_repmgrd_pid(): provided pidfile is /var/run/repmgr/repmgrd-11.pid
+    [2019-03-15 06:32:05] [NOTICE] starting monitoring of node "node2" (ID: 2)
+    [2019-03-15 06:32:05] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
+ </para>
+ <para>
+  Each &repmgrd; should also have recorded its successful startup as an event:
+  <programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
+     Node ID | Name  | Event         | OK | Timestamp           | Details
+    ---------+-------+---------------+----+---------------------+--------------------------------------------------------
+     3       | node3 | repmgrd_start | t  | 2019-03-14 04:17:30 | monitoring connection to upstream node "node1" (ID: 1)
+     2       | node2 | repmgrd_start | t  | 2019-03-14 04:11:47 | monitoring connection to upstream node "node1" (ID: 1)
+     1       | node1 | repmgrd_start | t  | 2019-03-14 04:04:31 | monitoring cluster primary "node1" (ID: 1)</programlisting>
+ </para>
+ <para>
+  Now stop the current primary server with e.g.:
+  <programlisting>
+    pg_ctl -D /var/lib/postgresql/data -m immediate stop</programlisting>
+ </para>
+ <para>
+  This will force the primary to shut down straight away, aborting all processes
+  and transactions.  This will cause a flurry of activity in the &repmgrd; log
+  files as each &repmgrd; detects the failure of the primary and a failover
+  decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
+  which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
+  <programlisting>
+    [2019-03-15 06:37:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
+    [2019-03-15 06:37:50] [INFO] checking state of node 1, 1 of 3 attempts
+    [2019-03-15 06:37:50] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-03-15 06:37:55] [INFO] checking state of node 1, 2 of 3 attempts
+    [2019-03-15 06:37:55] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-03-15 06:38:00] [INFO] checking state of node 1, 3 of 3 attempts
+    [2019-03-15 06:38:00] [WARNING] unable to reconnect to node 1 after 3 attempts
+    [2019-03-15 06:38:00] [INFO] primary and this node have the same location ("default")
+    [2019-03-15 06:38:00] [INFO] local node's last receive lsn: 0/900CBF8
+    [2019-03-15 06:38:00] [INFO] node 3 last saw primary node 12 second(s) ago
+    [2019-03-15 06:38:00] [INFO] last receive LSN for sibling node "node3" (ID: 3) is: 0/900CBF8
+    [2019-03-15 06:38:00] [INFO] node "node3" (ID: 3) has same LSN as current candidate "node2" (ID: 2)
+    [2019-03-15 06:38:00] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
+    [2019-03-15 06:38:00] [NOTICE] promotion candidate is "node2" (ID: 2)
+    [2019-03-15 06:38:00] [NOTICE] this node is the winner, will now promote itself and inform other nodes
+    [2019-03-15 06:38:00] [INFO] promote_command is:
+      "/usr/pgsql-11/bin/repmgr -f /etc/repmgr/11/repmgr.conf standby promote"
+    NOTICE: promoting standby to primary
+    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote"
+    NOTICE: waiting up to 60 seconds (parameter "promote_check_timeout") for promotion to complete
+    NOTICE: STANDBY PROMOTE successful
+    DETAIL: server "node2" (ID: 2) was successfully promoted to primary
+    [2019-03-15 06:38:01] [INFO] 3 followers to notify
+    [2019-03-15 06:38:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
+    INFO:  node 3 received notification to follow node 2
+    [2019-03-15 06:38:01] [INFO] switching to primary monitoring mode
+    [2019-03-15 06:38:01] [NOTICE] monitoring cluster primary "node2" (ID: 2)</programlisting>
+ </para>
+ <para>
+  The cluster status will now look like this, with the original primary (<literal>node1</literal>)
+  marked as inactive, and standby <literal>node3</literal> now following the new primary
+  (<literal>node2</literal>):
+  <programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster show --compact
+     ID | Name  | Role    | Status    | Upstream | Location | Prio.
+    ----+-------+---------+-----------+----------+----------+-------
+     1  | node1 | primary | - failed  |          | default  | 100
+     2  | node2 | primary | * running |          | default  | 100
+     3  | node3 | standby |   running | node2    | default  | 100</programlisting>
+
+ </para>
+ <para>
+   <link linkend="repmgr-cluster-event"><command>repmgr cluster event</command></link> will display a summary of
+   what happened to each server during the failover:
+  <programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster event
+     Node ID | Name  | Event                      | OK | Timestamp           | Details
+    ---------+-------+----------------------------+----+---------------------+-------------------------------------------------------------
+     3       | node3 | repmgrd_failover_follow    | t  | 2019-03-15 06:38:03 | node 3 now following new upstream node 2
+     3       | node3 | standby_follow             | t  | 2019-03-15 06:38:02 | standby attached to upstream node "node2" (ID: 2)
+     2       | node2 | repmgrd_reload             | t  | 2019-03-15 06:38:01 | monitoring cluster primary "node2" (ID: 2)
+     2       | node2 | repmgrd_failover_promote   | t  | 2019-03-15 06:38:01 | node 2 promoted to primary; old primary 1 marked as failed
+     2       | node2 | standby_promote            | t  | 2019-03-15 06:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
+ </para>
+
+  </sect1>
+</chapter>

doc/stylesheet-common.xsl

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="utf-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version="1.0">
+
+<!--
+  This file contains XSLT stylesheet customizations that are common to
+  all output formats (HTML, HTML Help, XSL-FO, etc.).
+  -->
+
+<xsl:include href="stylesheet-speedup-common.xsl" />
+
+<!-- Parameters -->
+
+<!--
+<xsl:param name="draft.mode">
+  <xsl:choose>
+    <xsl:when test="contains($repmgr.version, 'devel')">yes</xsl:when>
+    <xsl:otherwise>no</xsl:otherwise>
+  </xsl:choose>
+</xsl:param>
+-->
+
+<xsl:param name="show.comments">
+  <xsl:choose>
+    <xsl:when test="contains($repmgr.version, 'devel')">1</xsl:when>
+    <xsl:otherwise>0</xsl:otherwise>
+  </xsl:choose>
+</xsl:param>
+
+<xsl:param name="callout.graphics" select="'0'"></xsl:param>
+<xsl:param name="toc.section.depth">2</xsl:param>
+<xsl:param name="linenumbering.extension" select="'0'"></xsl:param>
+<xsl:param name="section.autolabel" select="1"></xsl:param>
+<xsl:param name="section.label.includes.component.label" select="1"></xsl:param>
+<xsl:param name="refentry.generate.name" select="0"></xsl:param>
+<xsl:param name="refentry.generate.title" select="1"></xsl:param>
+<xsl:param name="refentry.xref.manvolnum" select="0"/>
+<xsl:param name="formal.procedures" select="0"></xsl:param>
+<xsl:param name="generate.consistent.ids" select="1"/>
+<xsl:param name="punct.honorific" select="''"></xsl:param>
+<xsl:param name="variablelist.term.break.after">1</xsl:param>
+<xsl:param name="variablelist.term.separator"></xsl:param>
+<xsl:param name="xref.with.number.and.title" select="0"></xsl:param>
+
+
+<!-- Change display of some elements -->
+
+<xsl:template match="productname">
+  <xsl:call-template name="inline.charseq"/>
+</xsl:template>
+
+<xsl:template match="structfield">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="structname">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="symbol">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="systemitem">
+  <xsl:call-template name="inline.charseq"/>
+</xsl:template>
+
+<xsl:template match="token">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="type">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="programlisting/emphasis">
+  <xsl:call-template name="inline.boldseq"/>
+</xsl:template>
+
+
+<!-- Special support for Tcl synopses -->
+
+<xsl:template match="optional[@role='tcl']">
+  <xsl:text>?</xsl:text>
+  <xsl:call-template name="inline.charseq"/>
+  <xsl:text>?</xsl:text>
+</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet-fo.xsl

@@ -0,0 +1,97 @@
+<?xml version="1.0" encoding="utf-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version="1.0"
+                xmlns:fo="http://www.w3.org/1999/XSL/Format">
+
+<xsl:import href="http://docbook.sourceforge.net/release/xsl/current/fo/docbook.xsl"/>
+<xsl:include href="stylesheet-common.xsl" />
+
+<xsl:param name="fop1.extensions" select="1"></xsl:param>
+<xsl:param name="tablecolumns.extension" select="0"></xsl:param>
+<xsl:param name="toc.max.depth">3</xsl:param>
+<xsl:param name="ulink.footnotes" select="1"></xsl:param>
+<xsl:param name="use.extensions" select="1"></xsl:param>
+<xsl:param name="variablelist.as.blocks" select="1"></xsl:param>
+
+<xsl:attribute-set name="monospace.verbatim.properties"
+                   use-attribute-sets="verbatim.properties monospace.properties">
+  <xsl:attribute name="wrap-option">wrap</xsl:attribute>
+</xsl:attribute-set>
+
+<xsl:attribute-set name="nongraphical.admonition.properties">
+  <xsl:attribute name="border-style">solid</xsl:attribute>
+  <xsl:attribute name="border-width">1pt</xsl:attribute>
+  <xsl:attribute name="border-color">black</xsl:attribute>
+  <xsl:attribute name="padding-start">12pt</xsl:attribute>
+  <xsl:attribute name="padding-end">12pt</xsl:attribute>
+  <xsl:attribute name="padding-top">6pt</xsl:attribute>
+  <xsl:attribute name="padding-bottom">6pt</xsl:attribute>
+</xsl:attribute-set>
+
+<xsl:attribute-set name="admonition.title.properties">
+  <xsl:attribute name="text-align">center</xsl:attribute>
+</xsl:attribute-set>
+
+<!-- fix missing space after vertical simplelist
+     https://github.com/docbook/xslt10-stylesheets/issues/31 -->
+<xsl:attribute-set name="normal.para.spacing">
+  <xsl:attribute name="space-after.optimum">1em</xsl:attribute>
+  <xsl:attribute name="space-after.minimum">0.8em</xsl:attribute>
+  <xsl:attribute name="space-after.maximum">1.2em</xsl:attribute>
+</xsl:attribute-set>
+
+<!-- Change display of some elements -->
+
+<xsl:template match="command">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="confgroup" mode="bibliography.mode">
+  <fo:inline>
+    <xsl:apply-templates select="conftitle/text()" mode="bibliography.mode"/>
+    <xsl:text>, </xsl:text>
+    <xsl:apply-templates select="confdates/text()" mode="bibliography.mode"/>
+    <xsl:value-of select="$biblioentry.item.separator"/>
+  </fo:inline>
+</xsl:template>
+
+<xsl:template match="isbn" mode="bibliography.mode">
+  <fo:inline>
+    <xsl:text>ISBN </xsl:text>
+    <xsl:apply-templates mode="bibliography.mode"/>
+    <xsl:value-of select="$biblioentry.item.separator"/>
+  </fo:inline>
+</xsl:template>
+
+<!-- bug fix from <https://sourceforge.net/p/docbook/bugs/1360/#831b> -->
+
+<xsl:template match="varlistentry/term" mode="xref-to">
+  <xsl:param name="verbose" select="1"/>
+  <xsl:apply-templates mode="no.anchor.mode"/>
+</xsl:template>
+
+<!-- include refsects in PDF bookmarks
+     (https://github.com/docbook/xslt10-stylesheets/issues/46) -->
+
+<xsl:template match="refsect1|refsect2|refsect3"
+              mode="bookmark">
+
+  <xsl:variable name="id">
+    <xsl:call-template name="object.id"/>
+  </xsl:variable>
+  <xsl:variable name="bookmark-label">
+    <xsl:apply-templates select="." mode="object.title.markup"/>
+  </xsl:variable>
+
+  <fo:bookmark internal-destination="{$id}">
+    <xsl:attribute name="starting-state">
+      <xsl:value-of select="$bookmarks.state"/>
+    </xsl:attribute>
+    <fo:bookmark-title>
+      <xsl:value-of select="normalize-space($bookmark-label)"/>
+    </fo:bookmark-title>
+    <xsl:apply-templates select="*" mode="bookmark"/>
+  </fo:bookmark>
+</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet-html-common.xsl

@@ -0,0 +1,292 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE xsl:stylesheet [
+<!ENTITY % common.entities SYSTEM "http://docbook.sourceforge.net/release/xsl/current/common/entities.ent">
+%common.entities;
+]>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version="1.0">
+
+<!--
+  This file contains XSLT stylesheet customizations that are common to
+  all HTML output variants (chunked and single-page).
+  -->
+
+<!-- Parameters -->
+<xsl:param name="make.valid.html" select="1"></xsl:param>
+<xsl:param name="generate.id.attributes" select="1"></xsl:param>
+<xsl:param name="make.graphic.viewport" select="0"/>
+<xsl:param name="link.mailto.url">pgsql-docs@lists.postgresql.org</xsl:param>
+<xsl:param name="toc.max.depth">2</xsl:param>
+
+
+<!-- Change display of some elements -->
+
+<xsl:template match="command">
+  <xsl:call-template name="inline.monoseq"/>
+</xsl:template>
+
+<xsl:template match="confgroup" mode="bibliography.mode">
+  <span>
+    <xsl:call-template name="common.html.attributes"/>
+    <xsl:call-template name="id.attribute"/>
+    <xsl:apply-templates select="conftitle/text()" mode="bibliography.mode"/>
+    <xsl:text>, </xsl:text>
+    <xsl:apply-templates select="confdates/text()" mode="bibliography.mode"/>
+    <xsl:copy-of select="$biblioentry.item.separator"/>
+  </span>
+</xsl:template>
+
+<xsl:template match="isbn" mode="bibliography.mode">
+  <span>
+    <xsl:call-template name="common.html.attributes"/>
+    <xsl:call-template name="id.attribute"/>
+    <xsl:text>ISBN </xsl:text>
+    <xsl:apply-templates mode="bibliography.mode"/>
+    <xsl:copy-of select="$biblioentry.item.separator"/>
+  </span>
+</xsl:template>
+
+
+<!-- table of contents configuration -->
+
+<xsl:param name="generate.toc">
+appendix  toc,title
+article/appendix  nop
+article   toc,title
+book      toc,title
+chapter   toc,title
+part      toc,title
+preface   toc,title
+qandadiv  toc
+qandaset  toc
+reference toc,title
+sect1     toc
+sect2     toc
+sect3     toc
+sect4     toc
+sect5     toc
+section   toc
+set       toc,title
+</xsl:param>
+
+<xsl:param name="generate.section.toc.level" select="1"></xsl:param>
+
+<!-- include refentry under sect1 in tocs -->
+<xsl:template match="sect1" mode="toc">
+  <xsl:param name="toc-context" select="."/>
+  <xsl:call-template name="subtoc">
+    <xsl:with-param name="toc-context" select="$toc-context"/>
+    <xsl:with-param name="nodes" select="sect2|refentry
+                                         |bridgehead[$bridgehead.in.toc != 0]"/>
+  </xsl:call-template>
+</xsl:template>
+
+
+<!-- Put index "quicklinks" (A | B | C | ...) at the top of the bookindex page. -->
+
+<!-- from html/autoidx.xsl -->
+
+<xsl:template name="generate-basic-index">
+  <xsl:param name="scope" select="NOTANODE"/>
+
+  <xsl:variable name="role">
+    <xsl:if test="$index.on.role != 0">
+      <xsl:value-of select="@role"/>
+    </xsl:if>
+  </xsl:variable>
+
+  <xsl:variable name="type">
+    <xsl:if test="$index.on.type != 0">
+      <xsl:value-of select="@type"/>
+    </xsl:if>
+  </xsl:variable>
+
+  <xsl:variable name="terms"
+                select="//indexterm
+                        [count(.|key('letter',
+                          translate(substring(&primary;, 1, 1),
+                             &lowercase;,
+                             &uppercase;))
+                          [&scope;][1]) = 1
+                          and not(@class = 'endofrange')]"/>
+
+  <xsl:variable name="alphabetical"
+                select="$terms[contains(concat(&lowercase;, &uppercase;),
+                                        substring(&primary;, 1, 1))]"/>
+
+  <xsl:variable name="others" select="$terms[not(contains(concat(&lowercase;,
+                                                 &uppercase;),
+                                             substring(&primary;, 1, 1)))]"/>
+
+  <div class="index">
+    <!-- pgsql-docs: begin added stuff -->
+    <p class="indexdiv-quicklinks">
+      <a href="#indexdiv-Symbols">
+        <xsl:call-template name="gentext">
+          <xsl:with-param name="key" select="'index symbols'"/>
+        </xsl:call-template>
+      </a>
+      <xsl:apply-templates select="$alphabetical[count(.|key('letter',
+                                   translate(substring(&primary;, 1, 1),
+                                   &lowercase;,&uppercase;))[&scope;][1]) = 1]"
+                           mode="index-div-quicklinks">
+        <xsl:with-param name="position" select="position()"/>
+        <xsl:with-param name="scope" select="$scope"/>
+        <xsl:with-param name="role" select="$role"/>
+        <xsl:with-param name="type" select="$type"/>
+        <xsl:sort select="translate(&primary;, &lowercase;, &uppercase;)"/>
+      </xsl:apply-templates>
+    </p>
+    <!-- pgsql-docs: end added stuff -->
+
+    <xsl:if test="$others">
+      <xsl:choose>
+        <xsl:when test="normalize-space($type) != '' and
+                        $others[@type = $type][count(.|key('primary', &primary;)[&scope;][1]) = 1]">
+          <!-- pgsql-docs: added id attribute here for linking to it -->
+          <div class="indexdiv" id="indexdiv-Symbols">
+            <h3>
+              <xsl:call-template name="gentext">
+                <xsl:with-param name="key" select="'index symbols'"/>
+              </xsl:call-template>
+            </h3>
+            <dl>
+              <xsl:apply-templates select="$others[count(.|key('primary', &primary;)[&scope;][1]) = 1]"
+                                   mode="index-symbol-div">
+                <xsl:with-param name="position" select="position()"/>
+                <xsl:with-param name="scope" select="$scope"/>
+                <xsl:with-param name="role" select="$role"/>
+                <xsl:with-param name="type" select="$type"/>
+                <xsl:sort select="translate(&primary;, &lowercase;, &uppercase;)"/>
+              </xsl:apply-templates>
+            </dl>
+          </div>
+        </xsl:when>
+        <xsl:when test="normalize-space($type) != ''">
+          <!-- Output nothing, as there isn't a match for $other using this $type -->
+        </xsl:when>
+        <xsl:otherwise>
+          <!-- pgsql-docs: added id attribute here for linking to it -->
+          <div class="indexdiv" id="indexdiv-Symbols">
+            <h3>
+              <xsl:call-template name="gentext">
+                <xsl:with-param name="key" select="'index symbols'"/>
+              </xsl:call-template>
+            </h3>
+            <dl>
+              <xsl:apply-templates select="$others[count(.|key('primary',
+                                          &primary;)[&scope;][1]) = 1]"
+                                  mode="index-symbol-div">
+                <xsl:with-param name="position" select="position()"/>
+                <xsl:with-param name="scope" select="$scope"/>
+                <xsl:with-param name="role" select="$role"/>
+                <xsl:with-param name="type" select="$type"/>
+                <xsl:sort select="translate(&primary;, &lowercase;, &uppercase;)"/>
+              </xsl:apply-templates>
+            </dl>
+          </div>
+        </xsl:otherwise>
+      </xsl:choose>
+    </xsl:if>
+
+    <xsl:apply-templates select="$alphabetical[count(.|key('letter',
+                                 translate(substring(&primary;, 1, 1),
+                                           &lowercase;,&uppercase;))[&scope;][1]) = 1]"
+                         mode="index-div-basic">
+      <xsl:with-param name="position" select="position()"/>
+      <xsl:with-param name="scope" select="$scope"/>
+      <xsl:with-param name="role" select="$role"/>
+      <xsl:with-param name="type" select="$type"/>
+      <xsl:sort select="translate(&primary;, &lowercase;, &uppercase;)"/>
+    </xsl:apply-templates>
+  </div>
+</xsl:template>
+
+<xsl:template match="indexterm" mode="index-div-basic">
+  <xsl:param name="scope" select="."/>
+  <xsl:param name="role" select="''"/>
+  <xsl:param name="type" select="''"/>
+
+  <xsl:variable name="key"
+                select="translate(substring(&primary;, 1, 1),
+                         &lowercase;,&uppercase;)"/>
+
+  <xsl:if test="key('letter', $key)[&scope;]
+                [count(.|key('primary', &primary;)[&scope;][1]) = 1]">
+    <div class="indexdiv">
+      <!-- pgsql-docs: added id attribute here for linking to it -->
+      <xsl:attribute name="id">
+        <xsl:value-of select="concat('indexdiv-', $key)"/>
+      </xsl:attribute>
+
+      <xsl:if test="contains(concat(&lowercase;, &uppercase;), $key)">
+        <h3>
+          <xsl:value-of select="translate($key, &lowercase;, &uppercase;)"/>
+        </h3>
+      </xsl:if>
+      <dl>
+        <xsl:apply-templates select="key('letter', $key)[&scope;]
+                                     [count(.|key('primary', &primary;)
+                                     [&scope;][1])=1]"
+                             mode="index-primary">
+          <xsl:with-param name="position" select="position()"/>
+          <xsl:with-param name="scope" select="$scope"/>
+          <xsl:with-param name="role" select="$role"/>
+          <xsl:with-param name="type" select="$type"/>
+          <xsl:sort select="translate(&primary;, &lowercase;, &uppercase;)"/>
+        </xsl:apply-templates>
+      </dl>
+    </div>
+  </xsl:if>
+</xsl:template>
+
+<!-- pgsql-docs -->
+<xsl:template match="indexterm" mode="index-div-quicklinks">
+  <xsl:param name="scope" select="."/>
+  <xsl:param name="role" select="''"/>
+  <xsl:param name="type" select="''"/>
+
+  <xsl:variable name="key"
+                select="translate(substring(&primary;, 1, 1),
+                        &lowercase;,&uppercase;)"/>
+
+  <xsl:if test="key('letter', $key)[&scope;]
+                [count(.|key('primary', &primary;)[&scope;][1]) = 1]">
+    <xsl:if test="contains(concat(&lowercase;, &uppercase;), $key)">
+      |
+      <a>
+        <xsl:attribute name="href">
+          <xsl:value-of select="concat('#indexdiv-', $key)"/>
+        </xsl:attribute>
+        <xsl:value-of select="translate($key, &lowercase;, &uppercase;)"/>
+      </a>
+    </xsl:if>
+  </xsl:if>
+</xsl:template>
+
+
+<!-- upper case HTML anchors for backward compatibility -->
+
+<xsl:template name="object.id">
+  <xsl:param name="object" select="."/>
+  <xsl:choose>
+    <xsl:when test="$object/@id">
+      <xsl:value-of select="translate($object/@id, &lowercase;, &uppercase;)"/>
+    </xsl:when>
+    <xsl:when test="$object/@xml:id">
+      <xsl:value-of select="$object/@xml:id"/>
+    </xsl:when>
+    <xsl:when test="$generate.consistent.ids != 0">
+      <!-- Make $object the current node -->
+      <xsl:for-each select="$object">
+        <xsl:text>id-</xsl:text>
+        <xsl:number level="multiple" count="*"/>
+      </xsl:for-each>
+    </xsl:when>
+    <xsl:otherwise>
+      <xsl:value-of select="generate-id($object)"/>
+    </xsl:otherwise>
+  </xsl:choose>
+</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet-html-nochunk.xsl

@@ -0,0 +1,23 @@
+<?xml version='1.0'?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version='1.0'
+                xmlns="http://www.w3.org/TR/xhtml1/transitional"
+                exclude-result-prefixes="#default">
+
+<xsl:import href="http://docbook.sourceforge.net/release/xsl/current/xhtml/docbook.xsl"/>
+<xsl:include href="stylesheet-common.xsl" />
+<xsl:include href="stylesheet-html-common.xsl" />
+<xsl:include href="stylesheet-speedup-xhtml.xsl" />
+
+<!-- embed SVG images into output file -->
+<xsl:template match="imagedata[@format='SVG']">
+  <xsl:variable name="filename">
+    <xsl:call-template name="mediaobject.filename">
+      <xsl:with-param name="object" select=".."/>
+    </xsl:call-template>
+  </xsl:variable>
+
+  <xsl:copy-of select="document($filename)"/>
+</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet-speedup-common.xsl

@@ -0,0 +1,100 @@
+<?xml version="1.0" encoding="utf-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version='1.0'>
+
+<!-- Performance-optimized versions of some upstream templates from common/
+     directory -->
+
+<!-- from common/labels.xsl -->
+
+<xsl:template match="chapter" mode="label.markup">
+  <xsl:choose>
+    <xsl:when test="@label">
+      <xsl:value-of select="@label"/>
+    </xsl:when>
+    <xsl:when test="string($chapter.autolabel) != 0">
+      <xsl:if test="$component.label.includes.part.label != 0 and
+                      ancestor::part">
+        <xsl:variable name="part.label">
+          <xsl:apply-templates select="ancestor::part"
+                               mode="label.markup"/>
+        </xsl:variable>
+        <xsl:if test="$part.label != ''">
+          <xsl:value-of select="$part.label"/>
+          <xsl:apply-templates select="ancestor::part"
+                               mode="intralabel.punctuation">
+            <xsl:with-param name="object" select="."/>
+          </xsl:apply-templates>
+        </xsl:if>
+      </xsl:if>
+      <xsl:variable name="format">
+        <xsl:call-template name="autolabel.format">
+          <xsl:with-param name="format" select="$chapter.autolabel"/>
+        </xsl:call-template>
+      </xsl:variable>
+      <xsl:choose>
+        <xsl:when test="$label.from.part != 0 and ancestor::part">
+          <xsl:number from="part" count="chapter" format="{$format}" level="any"/>
+        </xsl:when>
+        <xsl:otherwise>
+          <!-- Optimization for pgsql-docs: When counting to get label for
+               this chapter, preceding chapters can only be our siblings or
+               children of a preceding part, so only count those instead of
+               scanning the entire node tree. -->
+          <!-- <xsl:number from="book" count="chapter" format="{$format}" level="any"/> -->
+          <xsl:number value="count(../preceding-sibling::part/chapter) + count(preceding-sibling::chapter) + 1" format="{$format}"/>
+        </xsl:otherwise>
+      </xsl:choose>
+    </xsl:when>
+  </xsl:choose>
+</xsl:template>
+
+<xsl:template match="appendix" mode="label.markup">
+  <xsl:choose>
+    <xsl:when test="@label">
+      <xsl:value-of select="@label"/>
+    </xsl:when>
+    <xsl:when test="string($appendix.autolabel) != 0">
+      <xsl:if test="$component.label.includes.part.label != 0 and
+                      ancestor::part">
+        <xsl:variable name="part.label">
+          <xsl:apply-templates select="ancestor::part"
+                               mode="label.markup"/>
+        </xsl:variable>
+        <xsl:if test="$part.label != ''">
+          <xsl:value-of select="$part.label"/>
+          <xsl:apply-templates select="ancestor::part"
+                               mode="intralabel.punctuation">
+            <xsl:with-param name="object" select="."/>
+          </xsl:apply-templates>
+        </xsl:if>
+      </xsl:if>
+      <xsl:variable name="format">
+        <xsl:call-template name="autolabel.format">
+          <xsl:with-param name="format" select="$appendix.autolabel"/>
+        </xsl:call-template>
+      </xsl:variable>
+      <xsl:choose>
+        <xsl:when test="$label.from.part != 0 and ancestor::part">
+          <xsl:number from="part" count="appendix" format="{$format}" level="any"/>
+        </xsl:when>
+        <xsl:otherwise>
+          <!-- Optimization for pgsql-docs: When counting to get label for
+               this appendix, preceding appendixes can only be our siblings or
+               children of a preceding part, so only count those instead of
+               scanning the entire node tree. -->
+          <!-- <xsl:number from="book|article" count="appendix" format="{$format}" level="any"/> -->
+          <xsl:number value="count(../preceding-sibling::part/appendix) + count(preceding-sibling::appendix) + 1" format="{$format}"/>
+        </xsl:otherwise>
+      </xsl:choose>
+    </xsl:when>
+  </xsl:choose>
+</xsl:template>
+
+<!-- from common/l10n.xsl -->
+
+<!-- Just hardcode the language for the whole document, to make it faster. -->
+
+<xsl:template name="l10n.language">en</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet-speedup-xhtml.xsl

@@ -0,0 +1,345 @@
+<?xml version="1.0" encoding="utf-8"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                xmlns="http://www.w3.org/1999/xhtml"
+                version='1.0'>
+
+<!-- Performance-optimized versions of some upstream templates from xhtml/
+     directory -->
+
+<!-- from xhtml/autoidx.xsl -->
+
+<xsl:template match="indexterm" mode="reference">
+  <xsl:param name="scope" select="."/>
+  <xsl:param name="role" select="''"/>
+  <xsl:param name="type" select="''"/>
+  <xsl:param name="position"/>
+  <xsl:param name="separator" select="''"/>
+
+  <xsl:variable name="term.separator">
+    <xsl:call-template name="index.separator">
+      <xsl:with-param name="key" select="'index.term.separator'"/>
+    </xsl:call-template>
+  </xsl:variable>
+
+  <xsl:variable name="number.separator">
+    <xsl:call-template name="index.separator">
+      <xsl:with-param name="key" select="'index.number.separator'"/>
+    </xsl:call-template>
+  </xsl:variable>
+
+  <xsl:variable name="range.separator">
+    <xsl:call-template name="index.separator">
+      <xsl:with-param name="key" select="'index.range.separator'"/>
+    </xsl:call-template>
+  </xsl:variable>
+
+  <xsl:choose>
+    <xsl:when test="$separator != ''">
+      <xsl:value-of select="$separator"/>
+    </xsl:when>
+    <xsl:when test="$position = 1">
+      <xsl:value-of select="$term.separator"/>
+    </xsl:when>
+    <xsl:otherwise>
+      <xsl:value-of select="$number.separator"/>
+    </xsl:otherwise>
+  </xsl:choose>
+
+  <xsl:choose>
+    <xsl:when test="@zone and string(@zone)">
+      <xsl:call-template name="reference">
+        <xsl:with-param name="zones" select="normalize-space(@zone)"/>
+        <xsl:with-param name="position" select="position()"/>
+        <xsl:with-param name="scope" select="$scope"/>
+        <xsl:with-param name="role" select="$role"/>
+        <xsl:with-param name="type" select="$type"/>
+      </xsl:call-template>
+    </xsl:when>
+    <xsl:otherwise>
+      <a>
+        <xsl:apply-templates select="." mode="class.attribute"/>
+        <xsl:variable name="title">
+          <xsl:choose>
+            <xsl:when test="$index.prefer.titleabbrev != 0">
+              <xsl:apply-templates select="(ancestor-or-self::set|ancestor-or-self::book|ancestor-or-self::part|ancestor-or-self::reference|ancestor-or-self::partintro|ancestor-or-self::chapter|ancestor-or-self::appendix|ancestor-or-self::preface|ancestor-or-self::article|ancestor-or-self::section|ancestor-or-self::sect1|ancestor-or-self::sect2|ancestor-or-self::sect3|ancestor-or-self::sect4|ancestor-or-self::sect5|ancestor-or-self::refentry|ancestor-or-self::refsect1|ancestor-or-self::refsect2|ancestor-or-self::refsect3|ancestor-or-self::simplesect|ancestor-or-self::bibliography|ancestor-or-self::glossary|ancestor-or-self::index|ancestor-or-self::webpage|ancestor-or-self::topic)[last()]" mode="titleabbrev.markup"/>
+            </xsl:when>
+            <xsl:otherwise>
+              <xsl:apply-templates select="(ancestor-or-self::set|ancestor-or-self::book|ancestor-or-self::part|ancestor-or-self::reference|ancestor-or-self::partintro|ancestor-or-self::chapter|ancestor-or-self::appendix|ancestor-or-self::preface|ancestor-or-self::article|ancestor-or-self::section|ancestor-or-self::sect1|ancestor-or-self::sect2|ancestor-or-self::sect3|ancestor-or-self::sect4|ancestor-or-self::sect5|ancestor-or-self::refentry|ancestor-or-self::refsect1|ancestor-or-self::refsect2|ancestor-or-self::refsect3|ancestor-or-self::simplesect|ancestor-or-self::bibliography|ancestor-or-self::glossary|ancestor-or-self::index|ancestor-or-self::webpage|ancestor-or-self::topic)[last()]" mode="title.markup"/>
+            </xsl:otherwise>
+          </xsl:choose>
+        </xsl:variable>
+
+        <xsl:attribute name="href">
+          <xsl:choose>
+            <xsl:when test="$index.links.to.section = 1">
+              <xsl:call-template name="href.target">
+                <xsl:with-param name="object" select="(ancestor-or-self::set|ancestor-or-self::book|ancestor-or-self::part|ancestor-or-self::reference|ancestor-or-self::partintro|ancestor-or-self::chapter|ancestor-or-self::appendix|ancestor-or-self::preface|ancestor-or-self::article|ancestor-or-self::section|ancestor-or-self::sect1|ancestor-or-self::sect2|ancestor-or-self::sect3|ancestor-or-self::sect4|ancestor-or-self::sect5|ancestor-or-self::refentry|ancestor-or-self::refsect1|ancestor-or-self::refsect2|ancestor-or-self::refsect3|ancestor-or-self::simplesect|ancestor-or-self::bibliography|ancestor-or-self::glossary|ancestor-or-self::index|ancestor-or-self::webpage|ancestor-or-self::topic)[last()]"/>
+                <!-- Optimization for pgsql-docs: We only have an index as a
+                     child of book, so look that up directly instead of
+                     scanning the entire node tree.  Also, don't look for
+                     setindex. -->
+                <!-- <xsl:with-param name="context" select="(//index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))] | //setindex[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))])[1]"/> -->
+                <xsl:with-param name="context" select="(/book/index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))])[1]"/>
+              </xsl:call-template>
+            </xsl:when>
+            <xsl:otherwise>
+              <xsl:call-template name="href.target">
+                <xsl:with-param name="object" select="."/>
+                <xsl:with-param name="context" select="(//index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))] | //setindex[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))])[1]"/>
+              </xsl:call-template>
+            </xsl:otherwise>
+          </xsl:choose>
+
+        </xsl:attribute>
+
+        <xsl:value-of select="$title"/> <!-- text only -->
+      </a>
+
+      <xsl:variable name="id" select="(@id|@xml:id)[1]"/>
+      <xsl:if test="key('endofrange', $id)[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))]">
+        <xsl:apply-templates select="key('endofrange', $id)[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))][last()]" mode="reference">
+          <xsl:with-param name="position" select="position()"/>
+          <xsl:with-param name="scope" select="$scope"/>
+          <xsl:with-param name="role" select="$role"/>
+          <xsl:with-param name="type" select="$type"/>
+          <xsl:with-param name="separator" select="$range.separator"/>
+        </xsl:apply-templates>
+      </xsl:if>
+    </xsl:otherwise>
+  </xsl:choose>
+</xsl:template>
+
+<xsl:template name="reference">
+  <xsl:param name="scope" select="."/>
+  <xsl:param name="role" select="''"/>
+  <xsl:param name="type" select="''"/>
+  <xsl:param name="zones"/>
+
+  <xsl:choose>
+    <xsl:when test="contains($zones, ' ')">
+      <xsl:variable name="zone" select="substring-before($zones, ' ')"/>
+      <xsl:variable name="target" select="key('sections', $zone)"/>
+
+      <a>
+        <xsl:apply-templates select="." mode="class.attribute"/>
+<!--    Optimization for pgsql-docs: this call adds nothing but fails with docbook-xsl 1.76 -->
+<!--    <xsl:call-template name="id.attribute"/> -->
+        <xsl:attribute name="href">
+          <xsl:call-template name="href.target">
+            <xsl:with-param name="object" select="$target[1]"/>
+            <xsl:with-param name="context" select="//index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))][1]"/>
+          </xsl:call-template>
+        </xsl:attribute>
+        <xsl:apply-templates select="$target[1]" mode="index-title-content"/>
+      </a>
+      <xsl:text>, </xsl:text>
+      <xsl:call-template name="reference">
+        <xsl:with-param name="zones" select="substring-after($zones, ' ')"/>
+        <xsl:with-param name="position" select="position()"/>
+        <xsl:with-param name="scope" select="$scope"/>
+        <xsl:with-param name="role" select="$role"/>
+        <xsl:with-param name="type" select="$type"/>
+      </xsl:call-template>
+    </xsl:when>
+    <xsl:otherwise>
+      <xsl:variable name="zone" select="$zones"/>
+      <xsl:variable name="target" select="key('sections', $zone)"/>
+
+      <a>
+        <xsl:apply-templates select="." mode="class.attribute"/>
+<!--    Optimization for pgsql-docs: this call adds nothing but fails with docbook-xsl 1.76 -->
+<!--    <xsl:call-template name="id.attribute"/> -->
+        <xsl:attribute name="href">
+          <xsl:call-template name="href.target">
+            <xsl:with-param name="object" select="$target[1]"/>
+            <!-- Optimization for pgsql-docs: Only look for index under book
+                 instead of searching the whole node tree. -->
+            <!-- <xsl:with-param name="context" select="//index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))][1]"/> -->
+            <xsl:with-param name="context" select="/book/index[count(ancestor::node()|$scope) = count(ancestor::node()) and ($role = @role or $type = @type or (string-length($role) = 0 and string-length($type) = 0))][1]"/>
+          </xsl:call-template>
+        </xsl:attribute>
+        <xsl:apply-templates select="$target[1]" mode="index-title-content"/>
+      </a>
+    </xsl:otherwise>
+  </xsl:choose>
+</xsl:template>
+
+
+<!-- from xhtml/chunk-common.xsl -->
+
+<xsl:template name="chunk-all-sections">
+  <xsl:param name="content">
+    <xsl:apply-imports/>
+  </xsl:param>
+
+  <!-- Optimization for pgsql-docs: Since we set a fixed $chunk.section.depth,
+       we can do away with a bunch of complicated XPath searches for the
+       previous and next sections at various levels. -->
+
+  <xsl:if test="$chunk.section.depth != 1">
+    <xsl:message terminate="yes">
+      <xsl:text>Error: If you change $chunk.section.depth, then you must update the performance-optimized chunk-all-sections-template.</xsl:text>
+    </xsl:message>
+  </xsl:if>
+
+  <xsl:variable name="prev"
+    select="(preceding::book[1]
+             |preceding::preface[1]
+             |preceding::chapter[1]
+             |preceding::appendix[1]
+             |preceding::part[1]
+             |preceding::reference[1]
+             |preceding::refentry[1]
+             |preceding::colophon[1]
+             |preceding::article[1]
+             |preceding::topic[1]
+             |preceding::bibliography[parent::article or parent::book or parent::part][1]
+             |preceding::glossary[parent::article or parent::book or parent::part][1]
+             |preceding::index[$generate.index != 0]
+                               [parent::article or parent::book or parent::part][1]
+             |preceding::setindex[$generate.index != 0][1]
+             |ancestor::set
+             |ancestor::book[1]
+             |ancestor::preface[1]
+             |ancestor::chapter[1]
+             |ancestor::appendix[1]
+             |ancestor::part[1]
+             |ancestor::reference[1]
+             |ancestor::article[1]
+             |ancestor::topic[1]
+             |preceding::sect1[1]
+             |ancestor::sect1[1])[last()]"/>
+
+  <xsl:variable name="next"
+    select="(following::book[1]
+             |following::preface[1]
+             |following::chapter[1]
+             |following::appendix[1]
+             |following::part[1]
+             |following::reference[1]
+             |following::refentry[1]
+             |following::colophon[1]
+             |following::bibliography[parent::article or parent::book or parent::part][1]
+             |following::glossary[parent::article or parent::book or parent::part][1]
+             |following::index[$generate.index != 0]
+                               [parent::article or parent::book][1]
+             |following::article[1]
+             |following::topic[1]
+             |following::setindex[$generate.index != 0][1]
+             |descendant::book[1]
+             |descendant::preface[1]
+             |descendant::chapter[1]
+             |descendant::appendix[1]
+             |descendant::article[1]
+             |descendant::topic[1]
+             |descendant::bibliography[parent::article or parent::book][1]
+             |descendant::glossary[parent::article or parent::book or parent::part][1]
+             |descendant::index[$generate.index != 0]
+                                [parent::article or parent::book][1]
+             |descendant::colophon[1]
+             |descendant::setindex[$generate.index != 0][1]
+             |descendant::part[1]
+             |descendant::reference[1]
+             |descendant::refentry[1]
+             |following::sect1[1]
+             |descendant::sect1[1])[1]"/>
+
+  <xsl:call-template name="process-chunk">
+    <xsl:with-param name="prev" select="$prev"/>
+    <xsl:with-param name="next" select="$next"/>
+    <xsl:with-param name="content" select="$content"/>
+  </xsl:call-template>
+</xsl:template>
+
+<xsl:template name="href.target">
+  <xsl:param name="context" select="."/>
+  <xsl:param name="object" select="."/>
+  <xsl:param name="toc-context" select="."/>
+  <!-- Optimization for pgsql-docs: Remove support for dbhtml processing
+       instruction here -->
+  <xsl:variable name="href.to.uri">
+    <xsl:call-template name="href.target.uri">
+      <xsl:with-param name="object" select="$object"/>
+    </xsl:call-template>
+  </xsl:variable>
+  <xsl:variable name="href.from.uri">
+    <xsl:choose>
+      <xsl:when test="not($toc-context = .)">
+        <xsl:call-template name="href.target.uri">
+          <xsl:with-param name="object" select="$toc-context"/>
+        </xsl:call-template>
+      </xsl:when>
+      <xsl:otherwise>
+        <xsl:call-template name="href.target.uri">
+          <xsl:with-param name="object" select="$context"/>
+        </xsl:call-template>
+      </xsl:otherwise>
+    </xsl:choose>
+  </xsl:variable>
+  <xsl:variable name="href.to">
+    <xsl:value-of select="$href.to.uri"/>
+  </xsl:variable>
+  <xsl:variable name="href.from">
+    <xsl:call-template name="trim.common.uri.paths">
+      <xsl:with-param name="uriA" select="$href.to.uri"/>
+      <xsl:with-param name="uriB" select="$href.from.uri"/>
+      <xsl:with-param name="return" select="'B'"/>
+    </xsl:call-template>
+  </xsl:variable>
+  <xsl:variable name="depth">
+    <xsl:call-template name="count.uri.path.depth">
+      <xsl:with-param name="filename" select="$href.from"/>
+    </xsl:call-template>
+  </xsl:variable>
+  <xsl:variable name="href">
+    <xsl:call-template name="copy-string">
+      <xsl:with-param name="string" select="'../'"/>
+      <xsl:with-param name="count" select="$depth"/>
+    </xsl:call-template>
+    <xsl:value-of select="$href.to"/>
+  </xsl:variable>
+  <xsl:value-of select="$href"/>
+</xsl:template>
+
+<xsl:template name="html.head">
+  <xsl:param name="prev" select="/foo"/>
+  <xsl:param name="next" select="/foo"/>
+
+  <!-- Optimization for pgsql-docs: Cut out a bunch of things we don't need
+       here, including an expensive //legalnotice search. -->
+
+  <head>
+    <xsl:call-template name="system.head.content"/>
+    <xsl:call-template name="head.content"/>
+
+    <xsl:if test="$prev">
+      <link rel="prev">
+        <xsl:attribute name="href">
+          <xsl:call-template name="href.target">
+            <xsl:with-param name="object" select="$prev"/>
+          </xsl:call-template>
+        </xsl:attribute>
+        <xsl:attribute name="title">
+          <xsl:apply-templates select="$prev" mode="object.title.markup.textonly"/>
+        </xsl:attribute>
+      </link>
+    </xsl:if>
+
+    <xsl:if test="$next">
+      <link rel="next">
+        <xsl:attribute name="href">
+          <xsl:call-template name="href.target">
+            <xsl:with-param name="object" select="$next"/>
+          </xsl:call-template>
+        </xsl:attribute>
+        <xsl:attribute name="title">
+          <xsl:apply-templates select="$next" mode="object.title.markup.textonly"/>
+        </xsl:attribute>
+      </link>
+    </xsl:if>
+
+    <xsl:call-template name="user.head.content"/>
+  </head>
+</xsl:template>
+
+</xsl:stylesheet>

doc/stylesheet.css

@@ -1,96 +1,471 @@
-/* doc/src/sgml/stylesheet.css */
+/* PostgreSQL.org Documentation Style */
 
-/* color scheme similar to www.postgresql.org */
+@import 'website-docs.css';
 
-BODY {
-	color: #000000;
-	background: #FFFFFF;
-	font-family: verdana, sans-serif;
+/* requires global.css, table.css and text.css to be loaded before this file! */
+body {
+  font-family: verdana, sans-serif;
+  font-size: 76%;
+  background: url("/resources/background.png") repeat-x scroll left top transparent;
+  padding: 15px 4%;
+  margin: 0;
 }
 
-A:link		{ color:#0066A2; }
-A:visited	{ color:#004E66; }
-A:active	{ color:#0066A2; }
-A:hover		{ color:#000000; }
-
-H1 {
-	font-size: 1.4em;
-	font-weight: bold;
-	margin-top: 0em;
-	margin-bottom: 0em;
-	color: #EC5800;
+/* monospace font size fix */
+pre, code, kbd, samp, tt {
+  font-family: monospace,monospace;
+  font-size: 1em;
 }
 
-H2 {
-	font-size: 1.2em;
-	margin: 1.2em 0em 1.2em 0em;
-	font-weight: bold;
-	color: #666;
+div.NAVHEADER table {
+  margin-left: 0;
 }
 
-H3 {
-	font-size: 1.1em;
-	margin: 1.2em 0em 1.2em 0em;
-	font-weight: bold;
-	color: #666;
+/* Container Definitions */
+
+#docContainerWrap {
+  text-align: center; /* Win IE5 */
 }
 
-H4 {
-	font-size: 0.95em;
-	margin: 1.2em 0em 1.2em 0em;
-	font-weight: normal;
-	color: #666;
+#docContainer {
+  margin: 0 auto;
+  width: 90%;
+  padding-bottom: 2em;
+  display: block;
+  text-align: left; /* Win IE5 */
 }
 
-H5 {
-	font-size: 0.9em;
-	margin: 1.2em 0em 1.2em 0em;
-	font-weight: normal;
+#docHeader {
+  background-image: url("/media/img/docs/bg_hdr.png");
+  height: 83px;
+  margin: 0px;
+  padding: 0px;
+  display: block;
 }
 
-H6 {
-	font-size: 0.85em;
-	margin: 1.2em 0em 1.2em 0em;
-	font-weight: normal;
+#docHeaderLogo {
+  position: relative;
+  width: 206px;
+  height: 83px;
+  border: 0px;
+  padding: 0px;
+  margin: 0 0 0 20px;
 }
 
-/* center some titles */
-
-.BOOK .TITLE, .BOOK .CORPAUTHOR, .BOOK .COPYRIGHT {
-	text-align: center;
+#docHeaderLogo img {
+  border: 0px;
 }
 
-/* decoration for formal examples */
-
-DIV.EXAMPLE {
-	padding-left: 15px;
-	border-style: solid;
-	border-width: 0px;
-	border-left-width: 2px;
-	border-color: black;
-	margin: 0.5ex;
+#docNavSearchContainer {
+  padding-bottom: 2px;
 }
 
-/* less dense spacing of TOC */
-
-.BOOK .TOC DL DT {
-	padding-top: 1.5ex;
-	padding-bottom: 1.5ex;
+#docNav, #docVersions {
+  position: relative;
+  text-align: left;
+  margin-left: 10px;
+  margin-top: 5px;
+  color: #666;
+  font-size: 0.95em;
 }
 
-.BOOK .TOC DL DL DT {
-	padding-top: 0ex;
-	padding-bottom: 0ex;
+#docSearch {
+  position: relative;
+  text-align: right;
+  padding: 0;
+  margin: 0;
+  color: #666;
 }
 
-/* miscellaneous */
-
-PRE.LITERALLAYOUT, .SCREEN, .SYNOPSIS, .PROGRAMLISTING {
-	margin-left: 4ex;
+#docTextSize {
+  text-align: right;
+  white-space: nowrap;
+  margin-top: 7px;
+  font-size: 0.95em;
 }
 
-.COMMENT	{ color: red; }
+#docSearch form {
+  position: relative;
+  top: 5px;
+  right: 0;
+  margin: 0; /* need for IE 5.5 OSX */
+  text-align: right; /* need for IE 5.5 OSX */
+  white-space: nowrap; /* for Opera */
+}
 
-VAR		{ font-family: monospace; font-style: italic; }
-/* Konqueror's standard style for ACRONYM is italic. */
-ACRONYM		{ font-style: inherit; }
+#docSearch form label {
+  color: #666;
+  font-size: 0.95em;
+}
+
+#docSearch form input {
+  font-size: 0.95em;
+}
+  
+#docSearch form #submit {
+  font-size: 0.95em;
+  background: #7A7A7A;
+  color: #fff;
+  border: 1px solid #7A7A7A;
+  padding: 1px 4px;
+}
+  
+#docSearch form #q {
+  width: 170px;
+  font-size: 0.95em;
+  border:  1px solid #7A7A7A;
+  background: #E1E1E1;
+  color: #000000;
+  padding: 2px;
+}
+
+.frmDocSearch {
+  padding: 0;
+  margin: 0;
+  display: inline;
+}
+
+.inpDocSearch {
+  padding: 0;
+  margin: 0;
+  color: #000;
+}
+
+#docContent {
+  position: relative;
+  margin-left: 10px;
+  margin-right: 10px;
+  margin-top: 40px;
+}
+
+#docFooter {
+  position: relative;
+  font-size: 0.9em; 
+  color: #666; 
+  line-height: 1.3em; 
+  margin-left: 10px;
+  margin-right: 10px;
+}
+
+#docComments {
+  margin-top: 10px;
+}
+
+#docClear {
+  clear: both;
+  margin: 0;
+  padding: 0;
+}
+
+/* Heading Definitions */
+
+h1, h2, h3 {
+  font-weight: bold;
+  margin-top: 2ex;
+  color: #444;
+}
+
+h1 {
+  font-size: 1.4em;
+}
+
+h2 {
+  font-size: 1.2em !important;
+}
+
+h3 {
+  font-size: 1.1em;
+}
+
+h1 a:hover,
+h2 a:hover,
+h3 a:hover,
+h4 a:hover {
+  color: #444;
+  text-decoration: none;
+}
+
+/* Text Styles */
+
+div.SECT2 {
+  margin-top: 4ex;
+}
+
+div.SECT3 {
+  margin-top: 3ex;
+  margin-left: 3ex;
+}
+
+.txtCurrentLocation {
+  font-weight: bold;
+}
+
+p, ol, ul, li {
+  line-height: 1.5em;
+}
+
+.txtCommentsWrap {
+  border: 2px solid #F5F5F5; 
+  width: 100%;
+}
+
+.txtCommentsContent {
+  background: #F5F5F5;
+  padding: 3px;
+}
+
+.txtCommentsPoster {
+  float: left;
+}
+
+.txtCommentsDate {
+  float: right;
+}
+
+.txtCommentsComment {
+  padding: 3px;
+}
+
+#docContainer pre code,
+#docContainer pre tt,
+#docContainer pre pre,
+#docContainer tt tt,
+#docContainer tt code,
+#docContainer tt pre {
+  font-size: 1em;
+}
+
+pre.LITERALLAYOUT,
+.SCREEN,
+.SYNOPSIS,
+.PROGRAMLISTING,
+.REFSYNOPSISDIV p,
+table.CAUTION,
+table.WARNING,
+blockquote.NOTE,
+blockquote.TIP,
+table.CALSTABLE {
+  -moz-box-shadow: 3px 3px 5px #DFDFDF;
+  -webkit-box-shadow: 3px 3px 5px #DFDFDF;
+  -khtml-box-shadow: 3px 3px 5px #DFDFDF;
+  -o-box-shadow: 3px 3px 5px #DFDFDF;
+  box-shadow: 3px 3px 5px #DFDFDF;
+}
+
+pre.LITERALLAYOUT,
+.SCREEN,
+.SYNOPSIS,
+.PROGRAMLISTING,
+.REFSYNOPSISDIV p,
+table.CAUTION,
+table.WARNING,
+blockquote.NOTE,
+blockquote.TIP {
+  color: black;
+  border-width: 1px;
+  border-style: solid;
+  padding: 2ex;
+  margin: 2ex 0 2ex 2ex;
+  overflow: auto;
+  -moz-border-radius: 8px;
+  -webkit-border-radius: 8px;
+  -khtml-border-radius: 8px;
+  border-radius: 8px;
+}
+
+pre.LITERALLAYOUT,
+pre.SYNOPSIS,
+pre.PROGRAMLISTING,
+.REFSYNOPSISDIV p,
+.SCREEN {
+  border-color: #CFCFCF;
+  background-color: #F7F7F7;
+}
+
+blockquote.NOTE,
+blockquote.TIP {
+  border-color: #DBDBCC;
+  background-color: #EEEEDD;
+  padding: 14px;
+  width: 572px;
+}
+
+blockquote.NOTE,
+blockquote.TIP,
+table.CAUTION,
+table.WARNING {
+  margin: 4ex auto;
+}
+
+blockquote.NOTE p,
+blockquote.TIP p {
+  margin: 0;
+}
+
+blockquote.NOTE pre,
+blockquote.NOTE code,
+blockquote.TIP pre,
+blockquote.TIP code {
+  margin-left: 0;
+  margin-right: 0;
+  -moz-box-shadow: none;
+  -webkit-box-shadow: none;
+  -khtml-box-shadow: none;
+  -o-box-shadow: none;
+  box-shadow: none;
+}
+
+.emphasis,
+.c2 {
+  font-weight: bold;
+}
+
+.REPLACEABLE {
+  font-style: italic;
+}
+
+/* Table Styles */
+
+table {
+  margin-left: 2ex;
+}
+
+table.CALSTABLE td,
+table.CALSTABLE th,
+table.CAUTION td,
+table.CAUTION th,
+table.WARNING td,
+table.WARNING th {
+  border-style: solid;
+}
+
+table.CALSTABLE,
+table.CAUTION,
+table.WARNING {
+  border-spacing: 0;
+  border-collapse: collapse;
+}
+
+table.CALSTABLE
+{
+  margin: 2ex 0 2ex 2ex;
+  background-color: #E0ECEF;
+  border: 2px solid #A7C6DF;
+}
+
+table.CALSTABLE tr:hover td
+{
+  background-color: #EFEFEF;
+}
+
+table.CALSTABLE td {
+  background-color: #FFF;
+}
+
+table.CALSTABLE td,
+table.CALSTABLE th {
+  border: 1px solid #A7C6DF;
+  padding: 0.5ex 0.5ex;
+}
+
+table.CAUTION,
+table.WARNING {
+  border-collapse: separate;
+  display: block;
+  padding: 0;
+  max-width: 600px;
+}
+
+table.CAUTION {
+  background-color: #F5F5DC;
+  border-color: #DEDFA7;
+}
+
+table.WARNING {
+  background-color: #FFD7D7;
+  border-color: #DF421E;
+}
+
+table.CAUTION td,
+table.CAUTION th,
+table.WARNING td,
+table.WARNING th {
+  border-width: 0;
+  padding-left: 2ex;
+  padding-right: 2ex;
+}
+
+table.CAUTION td,
+table.CAUTION th {
+  border-color: #F3E4D5
+}
+
+table.WARNING td,
+table.WARNING th {
+  border-color: #FFD7D7;
+}
+
+td.c1,
+td.c2,
+td.c3,
+td.c4,
+td.c5,
+td.c6 {
+  font-size: 1.1em;
+  font-weight: bold;
+  border-bottom: 0px solid #FFEFEF;
+  padding: 1ex 2ex 0;
+}
+
+/* Link Styles */
+
+#docNav a {
+  font-weight: bold;
+}
+
+a:link,
+a:visited,
+a:active,
+a:hover {
+  text-decoration: underline;
+}
+
+a:link,
+a:active {
+  color:#0066A2;
+}
+
+a:visited {
+  color:#004E66;
+}
+
+a:hover {
+  color:#000000;
+}
+
+#docFooter a:link,
+#docFooter a:visited,
+#docFooter a:active {
+  color:#666;
+}
+
+#docContainer code.FUNCTION tt {
+  font-size: 1em;
+}
+
+div.header {
+    color: #444;
+    margin-top: 5px;
+}
+
+div.footer {
+    text-align: center;
+    background-image: url("/resources/footerl.png"), url("/resources/footerr.png"), url("/resources/footerc.png");
+    background-position: left top, right top, center top;
+    background-repeat: no-repeat, no-repeat, repeat-x;
+    padding-top: 45px;
+}
+
+img {
+    border-style: none;
+}

doc/stylesheet.xsl

@@ -0,0 +1,174 @@
+<?xml version='1.0'?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                version='1.0'
+                xmlns="http://www.w3.org/TR/xhtml1/transitional"
+                exclude-result-prefixes="#default">
+
+<xsl:import href="http://docbook.sourceforge.net/release/xsl/current/xhtml/chunk.xsl"/>
+<xsl:include href="stylesheet-common.xsl" />
+<xsl:include href="stylesheet-html-common.xsl" />
+<xsl:include href="stylesheet-speedup-xhtml.xsl" />
+
+
+<!-- Parameters -->
+<xsl:param name="base.dir" select="'html/'"></xsl:param>
+<xsl:param name="use.id.as.filename" select="'1'"></xsl:param>
+<xsl:param name="generate.legalnotice.link" select="1"></xsl:param>
+<xsl:param name="chunk.first.sections" select="1"/>
+<xsl:param name="chunk.quietly" select="1"></xsl:param>
+<xsl:param name="admon.style"></xsl:param>  <!-- handled by CSS stylesheet -->
+
+<xsl:param name="website.stylesheet" select="0"/>
+
+<xsl:param name="html.stylesheet">
+  <xsl:choose>
+    <xsl:when test="$website.stylesheet = 0">stylesheet.css</xsl:when>
+    <xsl:otherwise>https://www.postgresql.org/media/css/docs.css</xsl:otherwise>
+  </xsl:choose>
+</xsl:param>
+
+
+<!-- strip directory name from image filerefs -->
+<xsl:template match="imagedata/@fileref">
+ <xsl:value-of select="substring-after(., '/')"/>
+</xsl:template>
+
+
+<!--
+Customization of header
+- add Up and Home links
+- add tool tips to links
+
+(overrides html/chunk-common.xsl)
+-->
+<xsl:template name="header.navigation">
+  <xsl:param name="prev" select="/foo"/>
+  <xsl:param name="next" select="/foo"/>
+  <xsl:param name="nav.context"/>
+
+  <xsl:variable name="home" select="/*[1]"/>
+  <xsl:variable name="up" select="parent::*"/>
+
+  <xsl:variable name="row1" select="$navig.showtitles != 0"/>
+  <xsl:variable name="row2" select="count($prev) &gt; 0
+                                    or (count($up) &gt; 0
+                                        and generate-id($up) != generate-id($home)
+                                        and $navig.showtitles != 0)
+                                    or count($next) &gt; 0"/>
+
+  <xsl:if test="$suppress.navigation = '0' and $suppress.header.navigation = '0'">
+    <div class="navheader">
+      <xsl:if test="$row1 or $row2">
+        <table width="100%" summary="Navigation header">
+          <xsl:if test="$row1">
+            <tr>
+              <th colspan="5" align="center">
+                <xsl:apply-templates select="." mode="object.title.markup"/>
+              </th>
+            </tr>
+          </xsl:if>
+
+          <xsl:if test="$row2">
+            <tr>
+              <td width="10%" align="{$direction.align.start}">
+                <xsl:if test="count($prev)>0">
+                  <a accesskey="p">
+                    <xsl:attribute name="href">
+                      <xsl:call-template name="href.target">
+                        <xsl:with-param name="object" select="$prev"/>
+                      </xsl:call-template>
+                    </xsl:attribute>
+                    <xsl:attribute name="title">
+                      <xsl:apply-templates select="$prev" mode="object.title.markup"/>
+                    </xsl:attribute>
+                    <xsl:call-template name="navig.content">
+                      <xsl:with-param name="direction" select="'prev'"/>
+                    </xsl:call-template>
+                  </a>
+                </xsl:if>
+                <xsl:text>&#160;</xsl:text>
+              </td>
+              <td width="10%" align="{$direction.align.start}">
+                <xsl:choose>
+                  <xsl:when test="count($up)&gt;0
+                                  and generate-id($up) != generate-id($home)">
+                    <a accesskey="u">
+                      <xsl:attribute name="href">
+                        <xsl:call-template name="href.target">
+                          <xsl:with-param name="object" select="$up"/>
+                        </xsl:call-template>
+                      </xsl:attribute>
+                      <xsl:attribute name="title">
+                        <xsl:apply-templates select="$up" mode="object.title.markup"/>
+                      </xsl:attribute>
+                      <xsl:call-template name="navig.content">
+                        <xsl:with-param name="direction" select="'up'"/>
+                      </xsl:call-template>
+                    </a>
+                  </xsl:when>
+                  <xsl:otherwise>&#160;</xsl:otherwise>
+                </xsl:choose>
+              </td>
+              <th width="60%" align="center">
+                <xsl:choose>
+                  <xsl:when test="count($up) > 0
+                                  and generate-id($up) != generate-id($home)
+                                  and $navig.showtitles != 0">
+                    <xsl:apply-templates select="$up" mode="object.title.markup"/>
+                  </xsl:when>
+                  <xsl:otherwise>&#160;</xsl:otherwise>
+                </xsl:choose>
+              </th>
+              <td width="10%" align="{$direction.align.end}">
+                <xsl:choose>
+                  <xsl:when test="$home != . or $nav.context = 'toc'">
+                    <a accesskey="h">
+                      <xsl:attribute name="href">
+                        <xsl:call-template name="href.target">
+                          <xsl:with-param name="object" select="$home"/>
+                        </xsl:call-template>
+                      </xsl:attribute>
+                    <xsl:attribute name="title">
+                      <xsl:apply-templates select="$home" mode="object.title.markup"/>
+                    </xsl:attribute>
+                      <xsl:call-template name="navig.content">
+                        <xsl:with-param name="direction" select="'home'"/>
+                      </xsl:call-template>
+                    </a>
+                    <xsl:if test="$chunk.tocs.and.lots != 0 and $nav.context != 'toc'">
+                      <xsl:text>&#160;|&#160;</xsl:text>
+                    </xsl:if>
+                  </xsl:when>
+                  <xsl:otherwise>&#160;</xsl:otherwise>
+                </xsl:choose>
+              </td>
+              <td width="10%" align="{$direction.align.end}">
+                <xsl:text>&#160;</xsl:text>
+                <xsl:if test="count($next)>0">
+                  <a accesskey="n">
+                    <xsl:attribute name="href">
+                      <xsl:call-template name="href.target">
+                        <xsl:with-param name="object" select="$next"/>
+                      </xsl:call-template>
+                    </xsl:attribute>
+                    <xsl:attribute name="title">
+                      <xsl:apply-templates select="$next" mode="object.title.markup"/>
+                    </xsl:attribute>
+                    <xsl:call-template name="navig.content">
+                      <xsl:with-param name="direction" select="'next'"/>
+                    </xsl:call-template>
+                  </a>
+                </xsl:if>
+              </td>
+            </tr>
+          </xsl:if>
+        </table>
+      </xsl:if>
+      <xsl:if test="$header.rule != 0">
+        <hr/>
+      </xsl:if>
+    </div>
+  </xsl:if>
+</xsl:template>
+
+</xsl:stylesheet>

doc/switchover.xml

@@ -1,10 +1,10 @@
 <chapter id="performing-switchover" xreflabel="Performing a switchover with repmgr">
+ <title>Performing a switchover with repmgr</title>
 
  <indexterm>
   <primary>switchover</primary>
  </indexterm>
 
- <title>Performing a switchover with repmgr</title>
  <para>
   A typical use-case for replication is a combination of primary and standby
   server, with the standby serving as a backup which can easily be activated
@@ -15,7 +15,7 @@
  <para>
   In some cases however it's desirable to promote the standby in a planned
   way, e.g. so maintenance can be performed on the primary; this kind of switchover
-  is supported by the <xref linkend="repmgr-standby-switchover"> command.
+  is supported by the <xref linkend="repmgr-standby-switchover"/> command.
  </para>
  <para>
   <command>repmgr standby switchover</command> differs from other &repmgr;
@@ -44,17 +44,18 @@
     and capturing all output to assist troubleshooting any problems.
   </simpara>
   <simpara>
-   Please also read carefully the sections <xref linkend="preparing-for-switchover"> and
-   <xref linkend="switchover-caveats"> below.
+   Please also read carefully the sections <xref linkend="preparing-for-switchover"/> and
+   <xref linkend="switchover-caveats"/> below.
   </simpara>
  </note>
 
  <sect1 id="preparing-for-switchover" xreflabel="Preparing for switchover">
+   <title>Preparing for switchover</title>
+
    <indexterm>
      <primary>switchover</primary>
      <secondary>preparation</secondary>
    </indexterm>
-   <title>Preparing for switchover</title>
 
    <para>
     As mentioned in the previous section, success of the switchover operation depends on
@@ -72,7 +73,8 @@
      Ensure that a passwordless SSH connection is possible from the promotion candidate
      (standby) to the demotion candidate (current primary). If <literal>--siblings-follow</literal>
      will be used, ensure that passwordless SSH connections are possible from the
-     promotion candidate to all standbys attached to the demotion candidate.
+     promotion candidate to all nodes attached to the demotion candidate
+     (including the witness server, if in use).
    </para>
 
    <note>
@@ -113,7 +115,7 @@
        server.
      </para>
      <para>
-       For more details, see <xref linkend="configuration-file-service-commands">.
+       For more details, see <xref linkend="configuration-file-service-commands"/>.
      </para>
    </important>
 
@@ -158,12 +160,12 @@
     <note>
       <para>
         From <link linkend="release-4.2">repmgr 4.2</link>, &repmgr; will instruct any running
-        <application>repmgrd</application> instances to pause operations while the switchover
-        is being carried out, to prevent <application>repmgrd</application> from
-        unintentionally promoting a node. For more details, see <xref linkend="repmgrd-pausing">.
+        &repmgrd; instances to pause operations while the switchover
+        is being carried out, to prevent &repmgrd; from
+        unintentionally promoting a node. For more details, see <xref linkend="repmgrd-pausing"/>.
       </para>
       <para>
-        Users of &repmgr; versions prior to 4.2 should ensure that <application>repmgrd</application>
+        Users of &repmgr; versions prior to 4.2 should ensure that &repmgrd;
         is not running on any nodes while a switchover is being executed.
       </para>
     </note>
@@ -203,18 +205,19 @@
 
    <note>
      <simpara>
-       See <xref linkend="repmgr-standby-switchover"> for a full list of available
+       See <xref linkend="repmgr-standby-switchover"/> for a full list of available
        command line options and <filename>repmgr.conf</filename> settings relevant
        to performing a switchover.
      </simpara>
    </note>
 
-  <sect2 id="switchover-pg-rewind" xreflabel="Switchover and pg_rewind">
+   <sect2 id="switchover-pg-rewind" xreflabel="Switchover and pg_rewind">
+    <title>Switchover and pg_rewind</title>
+
     <indexterm>
       <primary>pg_rewind</primary>
       <secondary>using with "repmgr standby switchover"</secondary>
     </indexterm>
-    <title>Switchover and pg_rewind</title>
     <para>
       If the demotion candidate does not shut down smoothly or cleanly, there's a risk it
       will have a slightly divergent timeline and will not be able to attach to the new
@@ -257,11 +260,12 @@
  </sect1>
 
  <sect1 id="switchover-execution" xreflabel="Executing the switchover command">
+  <title>Executing the switchover command</title>
+
   <indexterm>
    <primary>switchover</primary>
     <secondary>execution</secondary>
   </indexterm>
-  <title>Executing the switchover command</title>
   <para>
    To demonstrate switchover, we will assume a replication cluster with a
    primary (<literal>node1</literal>) and one standby (<literal>node2</literal>);
@@ -312,13 +316,13 @@
    </programlisting>
   </para>
   <para>
-    If <application>repmgrd</application> is in use, it's worth double-checking that
+    If &repmgrd; is in use, it's worth double-checking that
     all nodes are unpaused by executing <command><link linkend="repmgr-daemon-status">repmgr-daemon-status</link></command>.
   </para>
 
    <note>
      <para>
-       Users of &repmgr; versions prior to 4.2 will need to manually restart <application>repmgrd</application>
+       Users of &repmgr; versions prior to 4.2 will need to manually restart &repmgrd;
        on all nodes after the switchover is completed.
      </para>
     </note>
@@ -327,11 +331,11 @@
 
 
  <sect1 id="switchover-caveats" xreflabel="Caveats">
+  <title>Caveats</title>
   <indexterm>
    <primary>switchover</primary>
     <secondary>caveats</secondary>
   </indexterm>
-  <title>Caveats</title>
   <para>
    <itemizedlist spacing="compact" mark="bullet">
     <listitem>
@@ -356,11 +360,12 @@
  </sect1>
 
  <sect1 id="switchover-troubleshooting" xreflabel="Troubleshooting">
+   <title>Troubleshooting switchover issues</title>
+
    <indexterm>
      <primary>switchover</primary>
      <secondary>troubleshooting</secondary>
    </indexterm>
-   <title>Troubleshooting switchover issues</title>
 
    <para>
      As <link linkend="performing-switchover">emphasised previously</link>, performing a switchover

doc/upgrading-repmgr.xml

@@ -1,10 +1,10 @@
 <chapter id="upgrading-repmgr" xreflabel="Upgrading repmgr">
+ <title>Upgrading repmgr</title>
 
  <indexterm>
   <primary>upgrading</primary>
  </indexterm>
 
- <title>Upgrading repmgr</title>
 
  <para>
   &repmgr; is updated regularly with minor releases (e.g. 4.0.1 to 4.0.2)
@@ -13,18 +13,19 @@
  </para>
 
  <sect1 id="upgrading-repmgr-extension" xreflabel="Upgrading repmgr 4.x and later">
+  <title>Upgrading repmgr 4.x and later</title>
+
   <indexterm>
    <primary>upgrading</primary>
    <secondary>repmgr 4.x and later</secondary>
   </indexterm>
-  <title>Upgrading repmgr 4.x and later</title>
   <para>
     From version 4, &repmgr; consists of three elements:
      <itemizedlist spacing="compact" mark="bullet">
 
        <listitem>
          <simpara>
-           the <application>repmgr</application> and <application>repmgrd</application> executables
+           the <application>repmgr</application> and &repmgrd; executables
          </simpara>
        </listitem>
 
@@ -37,7 +38,7 @@
 
        <listitem>
          <simpara>
-           the shared library module used by <application>repmgrd</application> which
+           the shared library module used by &repmgrd; which
            is resident in the PostgreSQL backend
          </simpara>
        </listitem>
@@ -45,8 +46,8 @@
   </para>
   <para>
     With <emphasis>minor releases</emphasis>, usually changes are only made to the <application>repmgr</application>
-    and <application>repmgrd</application> executables. In this case, the upgrade is quite straightforward,
-    and is simply a case of installing the new version, and restarting <application>repmgrd</application>
+    and &repmgrd; executables. In this case, the upgrade is quite straightforward,
+    and is simply a case of installing the new version, and restarting &repmgrd;
     (if running).
   </para>
 
@@ -63,11 +64,12 @@
   </important>
 
   <sect2 id="upgrading-minor-version" xreflabel="Upgrading a minor version release">
+	<title>Upgrading a minor version release</title>
+
 	<indexterm>
 	  <primary>upgrading</primary>
 	  <secondary>minor release</secondary>
 	</indexterm>
-	<title>Upgrading a minor version release</title>
 
     <para>
       The process for installing minor version upgrades is quite straightforward:
@@ -82,7 +84,7 @@
 
         <listitem>
           <simpara>
-            restart <application>repmgrd</application> on all nodes where it is running
+            restart &repmgrd; on all nodes where it is running
           </simpara>
         </listitem>
 
@@ -93,7 +95,7 @@
     <note>
 	  <para>
         Some packaging systems (e.g. <link linkend="packages-debian-ubuntu">Debian/Ubuntu</link>
-        may restart <application>repmgrd</application> as part of the package upgrade process.
+        may restart &repmgrd; as part of the package upgrade process.
       </para>
     </note>
 
@@ -118,15 +120,17 @@
   </sect2>
 
   <sect2 id="upgrading-major-version" xreflabel="Upgrading a major version release">
+	<title>Upgrading a major version release</title>
+
 	<indexterm>
 	  <primary>upgrading</primary>
 	  <secondary>major release</secondary>
 	</indexterm>
-	<title>Upgrading a major version release</title>
+
 	<para>
 	  &quot;major version&quot; upgrades need to be planned more carefully, as they may include
 	  changes to the &repmgr; metadata (which need to be propagated from the primary to all
-	  standbys) and/or changes to the shared object file used by <application>repmgrd</application>
+	  standbys) and/or changes to the shared object file used by &repmgrd;
 	  (which require a PostgreSQL restart).
 	</para>
 	<para>
@@ -138,14 +142,14 @@
 
 		<listitem>
           <simpara>
-			Stop <application>repmgrd</application> (if in use) on all nodes where it is running.
+			Stop &repmgrd; (if in use) on all nodes where it is running.
           </simpara>
 		</listitem>
 
 		<listitem>
           <simpara>
-			Disable the <application>repmgrd</application> service on all nodes where it is in use;
-            this is to prevent packages from prematurely restarting <application>repmgrd</application>.
+			Disable the &repmgrd; service on all nodes where it is in use;
+            this is to prevent packages from prematurely restarting &repmgrd;.
           </simpara>
 		</listitem>
 
@@ -167,12 +171,12 @@ systemctl daemon-reload</programlisting>
 		<listitem>
           <simpara>
 			If the &repmgr; shared library module has been updated (check the <link linkend="appendix-release-notes">release notes</link>!),
-            restart PostgreSQL, then <application>repmgrd</application> (if in use)	on each node,
+            restart PostgreSQL, then &repmgrd; (if in use)	on each node,
             The order in which this is applied to individual nodes is not critical,
-			and it's also fine to restart PostgreSQL on all nodes first before starting <application>repmgrd</application>.
+			and it's also fine to restart PostgreSQL on all nodes first before starting &repmgrd;.
 		  </simpara>
 		  <simpara>
-			Note that if the upgrade requires a PostgreSQL restart, <application>repmgrd</application>
+			Note that if the upgrade requires a PostgreSQL restart, &repmgrd;
 			will only function correctly once all nodes have been restarted.
           </simpara>
 		</listitem>
@@ -188,7 +192,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 
 		<listitem>
           <simpara>
-			Reenable the <application>repmgrd</application> service on all nodes where it is in use, and
+			Reenable the &repmgrd; service on all nodes where it is in use, and
             ensure it is running.
           </simpara>
 		</listitem>
@@ -205,19 +209,22 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   </sect2>
 
   <sect2 id="upgrading-check-repmgrd" xreflabel="Checking repmgrd status after an upgrade">
+	<title>Checking repmgrd status after an upgrade</title>
+
 	<indexterm>
 	  <primary>upgrading</primary>
 	  <secondary>checking repmgrd status</secondary>
 	</indexterm>
-	<title>Checking repmgrd status after an upgrade</title>
 	<para>
       From <link linkend="release-4.2">repmgr 4.2</link>, once the upgrade is complete, execute the <command><link linkend="repmgr-daemon-status">repmgr daemon status</link></command>
-      command (on any node) to show an overview of the status of <application>repmgrd</application> on all nodes.
+      command (on any node) to show an overview of the status of &repmgrd; on all nodes.
     </para>
   </sect2>
  </sect1>
 
  <sect1 id="upgrading-and-pg-upgrade" xreflabel="pg_upgrade and repmgr">
+  <title>pg_upgrade and repmgr</title>
+
   <indexterm>
    <primary>upgrading</primary>
    <secondary>pg_upgrade</secondary>
@@ -225,7 +232,6 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   <indexterm>
     <primary>pg_upgrade</primary>
   </indexterm>
-  <title>pg_upgrade and repmgr</title>
 
   <para>
     <application>pg_upgrade</application> requires that if any functions are
@@ -265,12 +271,13 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 
 
  <sect1 id="upgrading-from-repmgr-3" xreflabel="Upgrading from repmgr 3.x">
+  <title>Upgrading from repmgr 3.x</title>
+
   <indexterm>
    <primary>upgrading</primary>
    <secondary>from repmgr 3.x</secondary>
   </indexterm>
 
-  <title>Upgrading from repmgr 3.x</title>
   <para>
    The upgrade process consists of two steps:
    <orderedlist>
@@ -332,7 +339,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
       </listitem>
       <listitem>
         <simpara><varname>monitoring_history</varname>: this replaces the
-          <application>repmgrd</application> command line option
+          &repmgrd; command line option
           <literal>--monitoring-history</literal></simpara>
       </listitem>
      </itemizedlist>
@@ -383,7 +390,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
         to the server configured in Barman (in &repmgr; 3, the deprecated
         <literal>cluster</literal> parameter was used for this);
         the physical Barman hostname is configured with
-        <literal>barman_host</literal> (see <xref linkend="cloning-from-barman-prerequisites">
+        <literal>barman_host</literal> (see <xref linkend="cloning-from-barman-prerequisites"/>
           for details).
       </para>
     </note>
@@ -433,7 +440,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   <sect2>
    <title>Upgrading the repmgr schema</title>
    <para>
-    Ensure <application>repmgrd</application> is not running, or any cron jobs which execute the
+    Ensure &repmgrd; is not running, or any cron jobs which execute the
     <command>repmgr</command> binary.
    </para>
    <para>
@@ -499,7 +506,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     </para>
     <para>
      Check the data is updated as expected by examining the <structname>repmgr.nodes</structname>
-     table; restart <application>repmgrd</application> if required.
+     table; restart &repmgrd; if required.
     </para>
     <para>
      The original <literal>repmgr_$cluster</literal> schema can be dropped at any time.

doc/website-docs.css

@@ -1,21 +1,20 @@
 /* PostgreSQL.org Documentation Style */
 
+/*
+ * Documentation generated by XSL stylesheets has lower-case class
+ * names, older documentation generated by DSSSL stylesheets has
+ * upper-case class names, so we need to support both for a while.  In
+ * some cases, the elements and classes differ further between the two
+ * stylesheets.
+ */
+
 /* requires global.css, table.css and text.css to be loaded before this file! */
 body {
-  font-family: verdana, sans-serif;
   font-size: 76%;
-  background: url("/resources/background.png") repeat-x scroll left top transparent;
-  padding: 15px 4%;
-  margin: 0;
 }
 
-/* monospace font size fix */
-pre, code, kbd, samp, tt {
-  font-family: monospace,monospace;
-  font-size: 1em;
-}
-
-div.NAVHEADER table {
+.navheader table,
+.NAVHEADER table {
   margin-left: 0;
 }
 
@@ -99,7 +98,7 @@ div.NAVHEADER table {
 #docSearch form input {
   font-size: 0.95em;
 }
-  
+
 #docSearch form #submit {
   font-size: 0.95em;
   background: #7A7A7A;
@@ -107,7 +106,7 @@ div.NAVHEADER table {
   border: 1px solid #7A7A7A;
   padding: 1px 4px;
 }
-  
+
 #docSearch form #q {
   width: 170px;
   font-size: 0.95em;
@@ -138,9 +137,9 @@ div.NAVHEADER table {
 
 #docFooter {
   position: relative;
-  font-size: 0.9em; 
-  color: #666; 
-  line-height: 1.3em; 
+  font-size: 0.9em;
+  color: #666;
+  line-height: 1.3em;
   margin-left: 10px;
   margin-right: 10px;
 }
@@ -160,7 +159,6 @@ div.NAVHEADER table {
 h1, h2, h3 {
   font-weight: bold;
   margin-top: 2ex;
-  color: #444;
 }
 
 h1 {
@@ -175,20 +173,35 @@ h3 {
   font-size: 1.1em;
 }
 
-h1 a:hover,
+h1 a:hover {
+  color: #EC5800;
+  text-decoration: none;
+}
+
 h2 a:hover,
 h3 a:hover,
 h4 a:hover {
-  color: #444;
+  color: #666666;
   text-decoration: none;
 }
 
+/*
+ * Change color of h2 chunk titles in XSL build.  (In DSSSL build,
+ * these will be h1, which is already handled elsewhere.)
+ */
+.titlepage h2.title,
+.refnamediv h2 {
+  color: #EC5800;
+}
+
 /* Text Styles */
 
+div.sect2,
 div.SECT2 {
   margin-top: 4ex;
 }
 
+div.sect3,
 div.SECT3 {
   margin-top: 3ex;
   margin-left: 3ex;
@@ -203,7 +216,7 @@ p, ol, ul, li {
 }
 
 .txtCommentsWrap {
-  border: 2px solid #F5F5F5; 
+  border: 2px solid #F5F5F5;
   width: 100%;
 }
 
@@ -233,6 +246,17 @@ p, ol, ul, li {
   font-size: 1em;
 }
 
+pre.literallayout,
+.screen,
+.synopsis,
+.programlisting,
+.refsynopsisdiv p,
+.caution,
+.warning,
+.note,
+.tip,
+.table table,
+.informaltable table,
 pre.LITERALLAYOUT,
 .SCREEN,
 .SYNOPSIS,
@@ -250,6 +274,15 @@ table.CALSTABLE {
   box-shadow: 3px 3px 5px #DFDFDF;
 }
 
+pre.literallayout,
+.screen,
+.synopsis,
+.programlisting,
+.refsynopsisdiv p,
+.caution,
+.warning,
+.note,
+.tip,
 pre.LITERALLAYOUT,
 .SCREEN,
 .SYNOPSIS,
@@ -271,6 +304,11 @@ blockquote.TIP {
   border-radius: 8px;
 }
 
+pre.literallayout,
+pre.synopsis,
+pre.programlisting,
+.refsynopsisdiv p,
+.screen,
 pre.LITERALLAYOUT,
 pre.SYNOPSIS,
 pre.PROGRAMLISTING,
@@ -280,6 +318,8 @@ pre.PROGRAMLISTING,
   background-color: #F7F7F7;
 }
 
+.note,
+.tip,
 blockquote.NOTE,
 blockquote.TIP {
   border-color: #DBDBCC;
@@ -288,6 +328,10 @@ blockquote.TIP {
   width: 572px;
 }
 
+.note,
+.tip,
+.caution,
+.warning,
 blockquote.NOTE,
 blockquote.TIP,
 table.CAUTION,
@@ -295,11 +339,17 @@ table.WARNING {
   margin: 4ex auto;
 }
 
+.note p,
+.tip p,
 blockquote.NOTE p,
 blockquote.TIP p {
   margin: 0;
 }
 
+.note pre,
+.note code,
+.tip pre,
+.tip code,
 blockquote.NOTE pre,
 blockquote.NOTE code,
 blockquote.TIP pre,
@@ -313,11 +363,24 @@ blockquote.TIP code {
   box-shadow: none;
 }
 
+.caution,
+.warning {
+  max-width: 600px;
+}
+
+.tip h3,
+.note h3,
+.caution h3,
+.warning h3 {
+  text-align: center;
+}
+
 .emphasis,
 .c2 {
   font-weight: bold;
 }
 
+.replaceable,
 .REPLACEABLE {
   font-style: italic;
 }
@@ -328,6 +391,10 @@ table {
   margin-left: 2ex;
 }
 
+.table table td,
+.table table th,
+.informaltable table td,
+.informaltable table th,
 table.CALSTABLE td,
 table.CALSTABLE th,
 table.CAUTION td,
@@ -337,6 +404,8 @@ table.WARNING th {
   border-style: solid;
 }
 
+.table table,
+.informaltable table,
 table.CALSTABLE,
 table.CAUTION,
 table.WARNING {
@@ -344,6 +413,8 @@ table.WARNING {
   border-collapse: collapse;
 }
 
+.table table,
+.informaltable table,
 table.CALSTABLE
 {
   margin: 2ex 0 2ex 2ex;
@@ -351,15 +422,23 @@ table.CALSTABLE
   border: 2px solid #A7C6DF;
 }
 
+.table table tr:hover td,
+.informaltable table tr:hover td,
 table.CALSTABLE tr:hover td
 {
   background-color: #EFEFEF;
 }
 
+.table table td,
+.informaltable table td,
 table.CALSTABLE td {
   background-color: #FFF;
 }
 
+.table table td,
+.table table th,
+.informaltable table td,
+.informaltable table th,
 table.CALSTABLE td,
 table.CALSTABLE th {
   border: 1px solid #A7C6DF;
@@ -374,11 +453,13 @@ table.WARNING {
   max-width: 600px;
 }
 
+.caution,
 table.CAUTION {
   background-color: #F5F5DC;
   border-color: #DEDFA7;
 }
 
+.warning,
 table.WARNING {
   background-color: #FFD7D7;
   border-color: #DF421E;
@@ -447,23 +528,7 @@ a:hover {
   color:#666;
 }
 
+#docContainer code.function tt,
 #docContainer code.FUNCTION tt {
   font-size: 1em;
 }
-
-div.header {
-    color: #444;
-    margin-top: 5px;
-}
-
-div.footer {
-    text-align: center;
-    background-image: url("/resources/footerl.png"), url("/resources/footerr.png"), url("/resources/footerc.png");
-    background-position: left top, right top, center top;
-    background-repeat: no-repeat, no-repeat, repeat-x;
-    padding-top: 45px;
-}
-
-img {
-    border-style: none;
-}

log.c

@@ -85,7 +85,7 @@ _stderr_log_with_level(const char *level_name, int level, const char *fmt, va_li
 
 			time(&t);
 			tm = localtime(&t);
-			strftime(buf, 100, "[%Y-%m-%d %H:%M:%S]", tm);
+			strftime(buf, sizeof(buf), "[%Y-%m-%d %H:%M:%S]", tm);
 			fprintf(stderr, "%s [%s] ", buf, level_name);
 		}
 		else

repmgr--4.0.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.1.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.2.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.3--4.4.sql

@@ -0,0 +1,19 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+DROP FUNCTION set_upstream_last_seen();
+
+CREATE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
+  LANGUAGE C STRICT;

repmgr--4.3.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.4.sql

@@ -0,0 +1,224 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+CREATE TABLE repmgr.nodes (
+  node_id          INTEGER     PRIMARY KEY,
+  upstream_node_id INTEGER     NULL REFERENCES nodes (node_id) DEFERRABLE,
+  active           BOOLEAN     NOT NULL DEFAULT TRUE,
+  node_name        TEXT        NOT NULL,
+  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
+  location         TEXT        NOT NULL DEFAULT 'default',
+  priority         INT         NOT NULL DEFAULT 100,
+  conninfo         TEXT        NOT NULL,
+  repluser         VARCHAR(63) NOT NULL,
+  slot_name        TEXT        NULL,
+  config_file      TEXT        NOT NULL
+);
+
+CREATE TABLE repmgr.events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
+DO $repmgr$
+DECLARE
+  DECLARE server_version_num INT;
+BEGIN
+  SELECT setting
+    FROM pg_catalog.pg_settings
+   WHERE name = 'server_version_num'
+    INTO server_version_num;
+  IF server_version_num >= 90400 THEN
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+  ELSE
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      TEXT NOT NULL,
+  last_wal_standby_location      TEXT,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+  END IF;
+END$repmgr$;
+
+
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+
+/* ================= */
+/* repmgrd functions */
+/* ================= */
+
+/* monitoring functions */
+
+CREATE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_last_seen()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
+  LANGUAGE C STRICT;
+
+/* failover functions */
+
+CREATE FUNCTION notify_follow_primary(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'notify_follow_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_new_primary()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_new_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION reset_voting_status()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'reset_voting_status'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION am_bdr_failover_handler(INT)
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'am_bdr_failover_handler'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION unset_bdr_failover_handler()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'unset_bdr_failover_handler'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pidfile()
+  RETURNS TEXT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_is_running()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_running'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_pause(BOOL)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgrd_pause'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_is_paused()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_wal_receiver_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_wal_receiver_pid'
+  LANGUAGE C STRICT;
+
+
+
+
+/* views */
+
+CREATE VIEW repmgr.replication_status AS
+  SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
+ 	     n.type AS node_type, n.active, last_monitor_time,
+         CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
+         m.last_wal_standby_location,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
+         CASE WHEN n.type='standby' THEN
+           CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
+           ELSE NULL
+         END AS replication_time_lag,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
+         AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
+    FROM repmgr.monitoring_history m
+    JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
+   WHERE (m.standby_node_id, m.last_monitor_time) IN (
+	          SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
+			    FROM repmgr.monitoring_history m1 GROUP BY 1
+         );
+

repmgr-action-bdr.c

@@ -93,6 +93,15 @@ do_bdr_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	if (get_bdr_version_num() > 2)
+	{
+		log_error(_("\"repmgr bdr register\" is for BDR 2.x only"));
+		PQfinish(conn);
+		pfree(dbname);
+		exit(ERR_BAD_CONFIG);
+	}
+
+
 	/* check for a matching BDR node */
 	{
 		PQExpBufferData bdr_local_node_name;
@@ -216,7 +225,7 @@ do_bdr_register(void)
 				ExtensionStatus other_node_extension_status = REPMGR_UNKNOWN;
 
 				/* skip the local node */
-				if (strncmp(node_info.node_name, bdr_cell->node_info->node_name, MAXLEN) == 0)
+				if (strncmp(node_info.node_name, bdr_cell->node_info->node_name, sizeof(node_info.node_name)) == 0)
 				{
 					continue;
 				}
@@ -304,9 +313,9 @@ do_bdr_register(void)
 	node_info.active = true;
 	node_info.priority = config_file_options.priority;
 
-	strncpy(node_info.node_name, config_file_options.node_name, MAXLEN);
-	strncpy(node_info.location, config_file_options.location, MAXLEN);
-	strncpy(node_info.conninfo, config_file_options.conninfo, MAXLEN);
+	strncpy(node_info.node_name, config_file_options.node_name, sizeof(node_info.node_name));
+	strncpy(node_info.location, config_file_options.location, sizeof(node_info.location));
+	strncpy(node_info.conninfo, config_file_options.conninfo, sizeof(node_info.conninfo));
 
 	if (record_status == RECORD_FOUND)
 	{
@@ -330,7 +339,7 @@ do_bdr_register(void)
 		 * name set when the node was registered.
 		 */
 
-		if (strncmp(node_info.node_name, config_file_options.node_name, MAXLEN) != 0)
+		if (strncmp(node_info.node_name, config_file_options.node_name, sizeof(node_info.node_name)) != 0)
 		{
 			log_error(_("a record for node %i is already registered with node_name \"%s\""),
 					  config_file_options.node_id, node_info.node_name);

repmgr-action-cluster.c

@@ -24,7 +24,7 @@
 #include "repmgr-client-global.h"
 #include "repmgr-action-cluster.h"
 
-#define SHOW_HEADER_COUNT 8
+#define SHOW_HEADER_COUNT 9
 
 typedef enum
 {
@@ -35,6 +35,7 @@ typedef enum
 	SHOW_UPSTREAM_NAME,
 	SHOW_LOCATION,
 	SHOW_PRIORITY,
+	SHOW_TIMELINE_ID,
 	SHOW_CONNINFO
 }			ShowHeader;
 
@@ -64,6 +65,7 @@ static void cube_set_node_status(t_node_status_cube **cube, int n, int node_id,
  * CLUSTER SHOW
  *
  * Parameters:
+ *   --compact
  *   --csv
  */
 void
@@ -112,9 +114,15 @@ do_cluster_show(void)
 	strncpy(headers_show[SHOW_LOCATION].title, _("Location"), MAXLEN);
 
 	if (runtime_options.compact == true)
+	{
 		strncpy(headers_show[SHOW_PRIORITY].title, _("Prio."), MAXLEN);
+		strncpy(headers_show[SHOW_TIMELINE_ID].title, _("TLI"), MAXLEN);
+	}
 	else
+	{
 		strncpy(headers_show[SHOW_PRIORITY].title, _("Priority"), MAXLEN);
+		strncpy(headers_show[SHOW_TIMELINE_ID].title, _("Timeline"), MAXLEN);
+	}
 
 	strncpy(headers_show[SHOW_CONNINFO].title, _("Connection string"), MAXLEN);
 
@@ -127,6 +135,16 @@ do_cluster_show(void)
 	{
 		headers_show[i].display = true;
 
+		/* Don't display timeline on pre-9.6 clusters  */
+		if (i == SHOW_TIMELINE_ID)
+		{
+			if (PQserverVersion(conn) < 90600)
+			{
+				headers_show[i].display = false;
+			}
+		}
+
+		/* if --compact provided, don't display conninfo */
 		if (runtime_options.compact == true)
 		{
 			if (i == SHOW_CONNINFO)
@@ -135,34 +153,38 @@ do_cluster_show(void)
 			}
 		}
 
+
 		if (headers_show[i].display == true)
 		{
 			headers_show[i].max_length = strlen(headers_show[i].title);
 		}
 	}
 
+	/*
+	 * TODO: count nodes marked as "? unreachable" and add a hint about
+	 * the other cluster commands for better determining whether
+	 * unreachable.
+	 */
+
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
-		PQExpBufferData details;
+		PQExpBufferData node_status;
+		PQExpBufferData upstream;
 		PQExpBufferData buf;
 
+		cell->node_info->replication_info = palloc0(sizeof(ReplInfo));
+		if (cell->node_info->replication_info == NULL)
+		{
+			log_error(_("unable to allocate memory"));
+			exit(ERR_INTERNAL);
+		}
+
+		init_replication_info(cell->node_info->replication_info);
+
 		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
 
-		if (PQstatus(cell->node_info->conn) == CONNECTION_OK)
+		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 		{
-			cell->node_info->node_status = NODE_STATUS_UP;
-			cell->node_info->recovery_type = get_recovery_type(cell->node_info->conn);
-		}
-		else
-		{
-			/* check if node is reachable, but just not letting us in */
-			if (is_server_available(cell->node_info->conninfo))
-				cell->node_info->node_status = NODE_STATUS_REJECTED;
-			else
-				cell->node_info->node_status = NODE_STATUS_DOWN;
-
-			cell->node_info->recovery_type = RECTYPE_UNKNOWN;
-
 			connection_error_found = true;
 
 			if (runtime_options.verbose)
@@ -181,235 +203,25 @@ do_cluster_show(void)
 										cell->node_info->node_name, cell->node_info->node_id);
 			}
 		}
-
-		initPQExpBuffer(&details);
-
-		/*
-		 * TODO: count nodes marked as "? unreachable" and add a hint about
-		 * the other cluster commands for better determining whether
-		 * unreachable.
-		 */
-		switch (cell->node_info->type)
+		else
 		{
-			case PRIMARY:
-				{
-					/* node is reachable */
-					if (cell->node_info->node_status == NODE_STATUS_UP)
-					{
-						if (cell->node_info->active == true)
-						{
-							switch (cell->node_info->recovery_type)
-							{
-								case RECTYPE_PRIMARY:
-									appendPQExpBufferStr(&details, "* running");
-									break;
-								case RECTYPE_STANDBY:
-									appendPQExpBufferStr(&details, "! running as standby");
-									item_list_append_format(&warnings,
-															"node \"%s\" (ID: %i) is registered as primary but running as standby",
-															cell->node_info->node_name, cell->node_info->node_id);
-									break;
-								case RECTYPE_UNKNOWN:
-									appendPQExpBufferStr(&details, "! unknown");
-									item_list_append_format(&warnings,
-															"node \"%s\" (ID: %i) has unknown replication status",
-															cell->node_info->node_name, cell->node_info->node_id);
-									break;
-							}
-						}
-						else
-						{
-							if (cell->node_info->recovery_type == RECTYPE_PRIMARY)
-							{
-								appendPQExpBufferStr(&details, "! running");
-								item_list_append_format(&warnings,
-														"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
-														cell->node_info->node_name, cell->node_info->node_id);
-							}
-							else
-							{
-								appendPQExpBufferStr(&details, "! running as standby");
-								item_list_append_format(&warnings,
-														"node \"%s\" (ID: %i) is registered as an inactive primary but running as standby",
-														cell->node_info->node_name, cell->node_info->node_id);
-							}
-						}
-					}
-					/* node is up but cannot connect */
-					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
-					{
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? running");
-						}
-						else
-						{
-							appendPQExpBufferStr(&details, "! running");
-								error_found = true;
-						}
-					}
-					/* node is unreachable */
-					else
-					{
-						/* node is unreachable but marked active */
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? unreachable");
-							item_list_append_format(&warnings,
-													"node \"%s\" (ID: %i) is registered as an active primary but is unreachable",
-													cell->node_info->node_name, cell->node_info->node_id);
-						}
-						/* node is unreachable and marked as inactive */
-						else
-						{
-							appendPQExpBufferStr(&details, "- failed");
-							error_found = true;
-						}
-					}
-				}
-				break;
-			case STANDBY:
-				{
-					/* node is reachable */
-					if (cell->node_info->node_status == NODE_STATUS_UP)
-					{
-						if (cell->node_info->active == true)
-						{
-							switch (cell->node_info->recovery_type)
-							{
-								case RECTYPE_STANDBY:
-									appendPQExpBufferStr(&details, "  running");
-									break;
-								case RECTYPE_PRIMARY:
-									appendPQExpBufferStr(&details, "! running as primary");
-									item_list_append_format(&warnings,
-															"node \"%s\" (ID: %i) is registered as standby but running as primary",
-															cell->node_info->node_name, cell->node_info->node_id);
-									break;
-								case RECTYPE_UNKNOWN:
-									appendPQExpBufferStr(&details, "! unknown");
-									item_list_append_format(
-															&warnings,
-															"node \"%s\" (ID: %i) has unknown replication status",
-															cell->node_info->node_name, cell->node_info->node_id);
-									break;
-							}
-						}
-						else
-						{
-							if (cell->node_info->recovery_type == RECTYPE_STANDBY)
-							{
-								appendPQExpBufferStr(&details, "! running");
-								item_list_append_format(&warnings,
-														"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
-														cell->node_info->node_name, cell->node_info->node_id);
-							}
-							else
-							{
-								appendPQExpBufferStr(&details, "! running as primary");
-								item_list_append_format(&warnings,
-														"node \"%s\" (ID: %i) is running as primary but the repmgr node record is inactive",
-														cell->node_info->node_name, cell->node_info->node_id);
-							}
-						}
-
-						/* warn about issue with paused WAL replay */
-						if (is_wal_replay_paused(cell->node_info->conn, true))
-						{
-							item_list_append_format(&warnings,
-													_("WAL replay is paused on node \"%s\" (ID: %i) with WAL replay pending; this node cannot be manually promoted until WAL replay is resumed"),
-													cell->node_info->node_name, cell->node_info->node_id);
-						}
-					}
-					/* node is up but cannot connect */
-					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
-					{
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? running");
-						}
-						else
-						{
-							appendPQExpBufferStr(&details, "! running");
-								error_found = true;
-						}
-					}
-					/* node is unreachable */
-					else
-					{
-						/* node is unreachable but marked active */
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? unreachable");
-							item_list_append_format(&warnings,
-													"node \"%s\" (ID: %i) is registered as an active standby but is unreachable",
-													cell->node_info->node_name, cell->node_info->node_id);
-						}
-						else
-						{
-								appendPQExpBufferStr(&details, "- failed");
-								error_found = true;
-						}
-					}
-				}
-
-				break;
-			case WITNESS:
-			case BDR:
-				{
-					/* node is reachable */
-					if (cell->node_info->node_status == NODE_STATUS_UP)
-					{
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "* running");
-						}
-						else
-						{
-							appendPQExpBufferStr(&details, "! running");
-							error_found = true;
-						}
-					}
-					/* node is up but cannot connect */
-					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
-					{
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? rejected");
-						}
-						else
-						{
-							appendPQExpBufferStr(&details, "! failed");
-							error_found = true;
-						}
-
-					}
-					/* node is unreachable */
-					else
-					{
-						if (cell->node_info->active == true)
-						{
-							appendPQExpBufferStr(&details, "? unreachable");
-						}
-						else
-						{
-							appendPQExpBufferStr(&details, "- failed");
-							error_found = true;
-						}
-					}
-				}
-				break;
-			case UNKNOWN:
-				{
-					/* this should never happen */
-					appendPQExpBufferStr(&details, "? unknown node type");
-						error_found = true;
-				}
-				break;
+			/* NOP on pre-9.6 servers */
+			cell->node_info->replication_info->timeline_id = get_node_timeline(cell->node_info->conn);
 		}
 
-		strncpy(cell->node_info->details, details.data, MAXLEN);
-		termPQExpBuffer(&details);
+		initPQExpBuffer(&node_status);
+		initPQExpBuffer(&upstream);
+
+		if (format_node_status(cell->node_info, &node_status, &upstream, &warnings) == true)
+			error_found = true;
+
+		snprintf(cell->node_info->details, sizeof(cell->node_info->details),
+				 "%s", node_status.data);
+		snprintf(cell->node_info->upstream_node_name, sizeof(cell->node_info->upstream_node_name),
+				 "%s", upstream.data);
+
+		termPQExpBuffer(&node_status);
+		termPQExpBuffer(&upstream);
 
 		PQfinish(cell->node_info->conn);
 		cell->node_info->conn = NULL;
@@ -422,6 +234,7 @@ do_cluster_show(void)
 		headers_show[SHOW_ROLE].cur_length = strlen(get_node_type_string(cell->node_info->type));
 		headers_show[SHOW_NAME].cur_length = strlen(cell->node_info->node_name);
 		headers_show[SHOW_STATUS].cur_length = strlen(cell->node_info->details);
+
 		headers_show[SHOW_UPSTREAM_NAME].cur_length = strlen(cell->node_info->upstream_node_name);
 
 		initPQExpBuffer(&buf);
@@ -431,7 +244,18 @@ do_cluster_show(void)
 
 		headers_show[SHOW_LOCATION].cur_length = strlen(cell->node_info->location);
 
-
+		if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
+		{
+			/* display "?" */
+			headers_show[SHOW_PRIORITY].cur_length = 1;
+		}
+		else
+		{
+			initPQExpBuffer(&buf);
+			appendPQExpBuffer(&buf, "%i", cell->node_info->replication_info->timeline_id);
+			headers_show[SHOW_PRIORITY].cur_length = strlen(buf.data);
+			termPQExpBuffer(&buf);
+		}
 
 		headers_show[SHOW_CONNINFO].cur_length = strlen(cell->node_info->conninfo);
 
@@ -496,6 +320,14 @@ do_cluster_show(void)
 			printf("| %-*s ", headers_show[SHOW_LOCATION].max_length, cell->node_info->location);
 			printf("| %-*i ", headers_show[SHOW_PRIORITY].max_length, cell->node_info->priority);
 
+			if (headers_show[SHOW_TIMELINE_ID].display == true)
+			{
+				if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
+					printf("| %-*c ", headers_show[SHOW_TIMELINE_ID].max_length, '?');
+				else
+					printf("| %-*i ", headers_show[SHOW_TIMELINE_ID].max_length, (int)cell->node_info->replication_info->timeline_id);
+			}
+
 			if (headers_show[SHOW_CONNINFO].display == true)
 			{
 				printf("| %-*s", headers_show[SHOW_CONNINFO].max_length, cell->node_info->conninfo);
@@ -550,6 +382,7 @@ do_cluster_show(void)
  *   --node-[id|name]
  *   --event
  *   --csv
+ *   --compact
  */
 
 void
@@ -595,11 +428,11 @@ do_cluster_event(void)
 	strncpy(headers_event[EV_DETAILS].title, _("Details"), MAXLEN);
 
 	/*
-	 * If --terse or --csv provided, simply omit the "Details" column.
+	 * If --compact or --csv provided, simply omit the "Details" column.
 	 * In --csv mode we'd need to quote/escape the contents "Details" column,
 	 * which is doable but which will remain a TODO for now.
 	 */
-	if (runtime_options.terse == true || runtime_options.output_mode == OM_CSV)
+	if (runtime_options.compact == true || runtime_options.output_mode == OM_CSV)
 		column_count --;
 
 	for (i = 0; i < column_count; i++)
@@ -1063,7 +896,9 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 		matrix_rec_list[i] = (t_node_matrix_rec *) pg_malloc0(sizeof(t_node_matrix_rec));
 
 		matrix_rec_list[i]->node_id = cell->node_info->node_id;
-		strncpy(matrix_rec_list[i]->node_name, cell->node_info->node_name, MAXLEN);
+		strncpy(matrix_rec_list[i]->node_name,
+				cell->node_info->node_name,
+				sizeof(matrix_rec_list[i]->node_name));
 
 		/*
 		 * Find the maximum length of a node name
@@ -1278,7 +1113,7 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 
 		cube[h] = (t_node_status_cube *) pg_malloc(sizeof(t_node_status_cube));
 		cube[h]->node_id = cell->node_info->node_id;
-		strncpy(cube[h]->node_name, cell->node_info->node_name, MAXLEN);
+		strncpy(cube[h]->node_name, cell->node_info->node_name, sizeof(cube[h]->node_name));
 
 		/*
 		 * Find the maximum length of a node name
@@ -1300,7 +1135,7 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 			/* we don't need the name here */
 			cube[h]->matrix_list_rec[i]->node_name[0] = '\0';
 
-			cube[h]->matrix_list_rec[i]->node_status_list = (t_node_status_rec **) pg_malloc0(sizeof(t_node_status_rec) * nodes.node_count);
+			cube[h]->matrix_list_rec[i]->node_status_list = (t_node_status_rec **) pg_malloc0(sizeof(t_node_status_rec *) * nodes.node_count);
 
 			j = 0;
 
@@ -1628,6 +1463,7 @@ do_cluster_help(void)
 	printf(_("    --event                   filter specific event\n"));
 	printf(_("    --node-id                 restrict entries to node with this ID\n"));
 	printf(_("    --node-name               restrict entries to node with this name\n"));
+	printf(_("    --compact                 omit \"Details\" column"));
 	printf(_("    --csv                     emit output as CSV\n"));
 	puts("");
 

repmgr-action-cluster.h

@@ -30,14 +30,14 @@ typedef struct
 typedef struct
 {
 	int			node_id;
-	char		node_name[MAXLEN];
+	char		node_name[NAMEDATALEN];
 	t_node_status_rec **node_status_list;
 } t_node_matrix_rec;
 
 typedef struct
 {
 	int			node_id;
-	char		node_name[MAXLEN];
+	char		node_name[NAMEDATALEN];
 	t_node_matrix_rec **matrix_list_rec;
 } t_node_status_cube;
 

repmgr-action-daemon.c

@@ -43,15 +43,17 @@ typedef enum
 	STATUS_ID = 0,
 	STATUS_NAME,
 	STATUS_ROLE,
-	STATUS_PRIORITY,
 	STATUS_PG,
-	STATUS_RUNNING,
+	STATUS_UPSTREAM_NAME,
+	STATUS_LOCATION,
+	STATUS_PRIORITY,
+	STATUS_REPMGRD,
 	STATUS_PID,
 	STATUS_PAUSED,
 	STATUS_UPSTREAM_LAST_SEEN
 } StatusHeader;
 
-#define STATUS_HEADER_COUNT 9
+#define STATUS_HEADER_COUNT 11
 
 struct ColHeader headers_status[STATUS_HEADER_COUNT];
 
@@ -91,14 +93,17 @@ do_daemon_status(void)
 	strncpy(headers_status[STATUS_ID].title, _("ID"), MAXLEN);
 	strncpy(headers_status[STATUS_NAME].title, _("Name"), MAXLEN);
 	strncpy(headers_status[STATUS_ROLE].title, _("Role"), MAXLEN);
+	strncpy(headers_status[STATUS_PG].title, _("Status"), MAXLEN);
+	strncpy(headers_status[STATUS_UPSTREAM_NAME].title, _("Upstream"), MAXLEN);
 
+	/* following only displayed with the --detail option */
+	strncpy(headers_status[STATUS_LOCATION].title, _("Location"), MAXLEN);
 	if (runtime_options.compact == true)
 		strncpy(headers_status[STATUS_PRIORITY].title, _("Prio."), MAXLEN);
 	else
 		strncpy(headers_status[STATUS_PRIORITY].title, _("Priority"), MAXLEN);
 
-	strncpy(headers_status[STATUS_PG].title, _("Status"), MAXLEN);
-	strncpy(headers_status[STATUS_RUNNING].title, _("repmgrd"), MAXLEN);
+	strncpy(headers_status[STATUS_REPMGRD].title, _("repmgrd"), MAXLEN);
 	strncpy(headers_status[STATUS_PID].title, _("PID"), MAXLEN);
 	strncpy(headers_status[STATUS_PAUSED].title, _("Paused?"), MAXLEN);
 
@@ -107,19 +112,25 @@ do_daemon_status(void)
 	else
 		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstream last seen"), MAXLEN);
 
-
 	for (i = 0; i < STATUS_HEADER_COUNT; i++)
 	{
 		headers_status[i].max_length = strlen(headers_status[i].title);
 		headers_status[i].display = true;
 	}
 
+	if (runtime_options.detail == false)
+	{
+		headers_status[STATUS_LOCATION].display = false;
+		headers_status[STATUS_PRIORITY].display = false;
+	}
+
 	i = 0;
 
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
 		int j;
-		PQExpBufferData buf;
+		PQExpBufferData node_status;
+		PQExpBufferData upstream;
 
 		repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
 		repmgrd_info[i]->node_id = cell->node_info->node_id;
@@ -135,6 +146,7 @@ do_daemon_status(void)
 
 		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 		{
+
 			connection_error_found = true;
 
 			if (runtime_options.verbose)
@@ -155,13 +167,13 @@ do_daemon_status(void)
 			}
 
 			repmgrd_info[i]->pg_running = false;
-			maxlen_snprintf(repmgrd_info[i]->pg_running_text, "%s", _("not running"));
 			maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("n/a"));
 			maxlen_snprintf(repmgrd_info[i]->pid_text, "%s", _("n/a"));
 		}
 		else
 		{
-			maxlen_snprintf(repmgrd_info[i]->pg_running_text, "%s", _("running"));
+			cell->node_info->node_status = NODE_STATUS_UP;
+			cell->node_info->recovery_type = get_recovery_type(cell->node_info->conn);
 
 			repmgrd_info[i]->pid = repmgrd_get_pid(cell->node_info->conn);
 
@@ -217,22 +229,42 @@ do_daemon_status(void)
 					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i second(s) ago"), repmgrd_info[i]->upstream_last_seen);
 				}
 			}
-
-			PQfinish(cell->node_info->conn);
 		}
 
+		initPQExpBuffer(&node_status);
+		initPQExpBuffer(&upstream);
+
+		(void)format_node_status(cell->node_info, &node_status, &upstream, &warnings);
+		snprintf(repmgrd_info[i]->pg_running_text, sizeof(cell->node_info->details),
+				 "%s", node_status.data);
+
+		snprintf(cell->node_info->upstream_node_name, sizeof(cell->node_info->upstream_node_name),
+				 "%s", upstream.data);
+
+		termPQExpBuffer(&node_status);
+		termPQExpBuffer(&upstream);
+
+		PQfinish(cell->node_info->conn);
 
 		headers_status[STATUS_NAME].cur_length = strlen(cell->node_info->node_name);
 		headers_status[STATUS_ROLE].cur_length = strlen(get_node_type_string(cell->node_info->type));
+		headers_status[STATUS_PG].cur_length = strlen(repmgrd_info[i]->pg_running_text);
+		headers_status[STATUS_UPSTREAM_NAME].cur_length = strlen(cell->node_info->upstream_node_name);
 
-		initPQExpBuffer(&buf);
-		appendPQExpBuffer(&buf, "%i", cell->node_info->priority);
-		headers_status[STATUS_PRIORITY].cur_length = strlen(buf.data);
-		termPQExpBuffer(&buf);
+		if (runtime_options.detail == true)
+		{
+			PQExpBufferData buf;
+
+			headers_status[STATUS_LOCATION].cur_length = strlen(cell->node_info->location);
+
+			initPQExpBuffer(&buf);
+			appendPQExpBuffer(&buf, "%i", cell->node_info->priority);
+			headers_status[STATUS_PRIORITY].cur_length = strlen(buf.data);
+			termPQExpBuffer(&buf);
+		}
 
 		headers_status[STATUS_PID].cur_length = strlen(repmgrd_info[i]->pid_text);
-		headers_status[STATUS_RUNNING].cur_length = strlen(repmgrd_info[i]->repmgrd_running);
-		headers_status[STATUS_PG].cur_length = strlen(repmgrd_info[i]->pg_running_text);
+		headers_status[STATUS_REPMGRD].cur_length = strlen(repmgrd_info[i]->repmgrd_running);
 
 		headers_status[STATUS_UPSTREAM_LAST_SEEN].cur_length = strlen(repmgrd_info[i]->upstream_last_seen_text);
 
@@ -269,7 +301,7 @@ do_daemon_status(void)
 				paused = -1;
 			}
 
-			printf("%i,%s,%s,%i,%i,%i,%i,%i,%i\n",
+			printf("%i,%s,%s,%i,%i,%i,%i,%i,%i,%s\n",
 				   cell->node_info->node_id,
 				   cell->node_info->node_name,
 				   get_node_type_string(cell->node_info->type),
@@ -280,17 +312,24 @@ do_daemon_status(void)
 				   cell->node_info->priority,
 				   repmgrd_info[i]->pid == UNKNOWN_PID
 				     ? -1
-				     : repmgrd_info[i]->upstream_last_seen);
+ 				     : repmgrd_info[i]->upstream_last_seen,
+				   cell->node_info->location);
 		}
 		else
 		{
 			printf(" %-*i ",  headers_status[STATUS_ID].max_length, cell->node_info->node_id);
 			printf("| %-*s ", headers_status[STATUS_NAME].max_length, cell->node_info->node_name);
 			printf("| %-*s ", headers_status[STATUS_ROLE].max_length, get_node_type_string(cell->node_info->type));
-			printf("| %-*i ", headers_status[STATUS_PRIORITY].max_length, cell->node_info->priority);
-
 			printf("| %-*s ", headers_status[STATUS_PG].max_length, repmgrd_info[i]->pg_running_text);
-			printf("| %-*s ", headers_status[STATUS_RUNNING].max_length, repmgrd_info[i]->repmgrd_running);
+			printf("| %-*s ", headers_status[STATUS_UPSTREAM_NAME].max_length, cell->node_info->upstream_node_name);
+
+			if (runtime_options.detail == true)
+			{
+				printf("| %-*s ", headers_status[STATUS_LOCATION].max_length, cell->node_info->location);
+				printf("| %-*i ", headers_status[STATUS_PRIORITY].max_length, cell->node_info->priority);
+			}
+
+			printf("| %-*s ", headers_status[STATUS_REPMGRD].max_length, repmgrd_info[i]->repmgrd_running);
 			printf("| %-*s ", headers_status[STATUS_PID].max_length, repmgrd_info[i]->pid_text);
 
 			if (repmgrd_info[i]->pid == UNKNOWN_PID)
@@ -441,7 +480,7 @@ _do_repmgr_pause(bool pause)
 void
 fetch_node_records(PGconn *conn, NodeInfoList *node_list)
 {
-	bool success = get_all_node_records(conn, node_list);
+	bool success = get_all_node_records_with_upstream(conn, node_list);
 
 	if (success == false)
 	{
@@ -756,6 +795,7 @@ void do_daemon_help(void)
 	printf(_("  \"daemon status\" shows the status of repmgrd on each node in the cluster\n"));
 	puts("");
 	printf(_("    --csv                     emit output as CSV\n"));
+	printf(_("    --detail                  show additional detail\n"));
 	printf(_("    --verbose                 show text of database connection error messages\n"));
 	puts("");
 

repmgr-action-node.c

@@ -294,7 +294,7 @@ do_node_status(void)
 				continue;
 			}
 
-			if (is_downstream_node_attached(conn, node_cell->node_info->node_name) == false)
+			if (is_downstream_node_attached(conn, node_cell->node_info->node_name) != NODE_ATTACHED)
 			{
 				missing_nodes_count++;
 				item_list_append_format(&missing_nodes,
@@ -1166,7 +1166,7 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, CheckStatusList *list_ou
 			continue;
 		}
 
-		if (is_downstream_node_attached(conn, cell->node_info->node_name) == false)
+		if (is_downstream_node_attached(conn, cell->node_info->node_name) != NODE_ATTACHED)
 		{
 			missing_nodes_count++;
 			item_list_append_format(&missing_nodes,
@@ -1408,7 +1408,7 @@ do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_i
 					break;
 			}
 		}
-		else if (lag_seconds < 0)
+		else if (lag_seconds == UNKNOWN_REPLICATION_LAG)
 		{
 			status = CHECK_STATUS_UNKNOWN;
 
@@ -2222,7 +2222,7 @@ do_node_rejoin(void)
 	{
 		RecoveryType upstream_recovery_type = get_recovery_type(upstream_conn);
 
-		log_error(_("unable to connect to current registered primary \"%s\" (node ID: %i)"),
+		log_error(_("unable to connect to current registered primary \"%s\" (ID: %i)"),
 				  primary_node_record.node_name,
 				  primary_node_record.node_id);
 		log_detail(_("registered primary node conninfo is: \"%s\""),
@@ -2476,6 +2476,8 @@ do_node_rejoin(void)
 
 						termPQExpBuffer(&slotdir_ent_path);
 					}
+
+					closedir(slotdir);
 				}
 				termPQExpBuffer(&slotdir_path);
 			}
@@ -2560,9 +2562,10 @@ do_node_rejoin(void)
 
 		for (;  i < config_file_options.node_rejoin_timeout; i++)
 		{
-			success = is_downstream_node_attached(primary_conn, config_file_options.node_name);
+			NodeAttached node_attached = is_downstream_node_attached(primary_conn,
+														config_file_options.node_name);
 
-			if (success == true)
+			if (node_attached == NODE_ATTACHED)
 			{
 				log_verbose(LOG_INFO, _("node %i has attached to its upstream node"),
 							config_file_options.node_id);
@@ -2610,7 +2613,9 @@ do_node_rejoin(void)
 	else
 	{
 		/* -W/--no-wait provided - check once */
-		success = is_downstream_node_attached(primary_conn, config_file_options.node_name);
+		NodeAttached node_attached = is_downstream_node_attached(primary_conn, config_file_options.node_name);
+		if (node_attached == NODE_ATTACHED)
+			success = true;
 	}
 
 	/*
@@ -2784,6 +2789,7 @@ _do_node_archive_config(void)
 
 	arcdir = opendir(archive_dir.data);
 
+	/* always attempt to open the directory */
 	if (arcdir == NULL)
 	{
 		log_error(_("unable to open archive directory \"%s\""),
@@ -2829,10 +2835,11 @@ _do_node_archive_config(void)
 
 			termPQExpBuffer(&arcdir_ent_path);
 		}
-
-		closedir(arcdir);
 	}
 
+	closedir(arcdir);
+
+
 	/*
 	 * extract list of config files from --config-files
 	 */
@@ -2850,7 +2857,7 @@ _do_node_archive_config(void)
 			{
 				int			filename_len = j - i;
 
-				if (filename_len > MAXPGPATH)
+				if (filename_len >= MAXPGPATH)
 					filename_len = MAXPGPATH - 1;
 
 				strncpy(filenamebuf, runtime_options.config_files + i, filename_len);
@@ -3104,11 +3111,12 @@ copy_file(const char *src_file, const char *dest_file)
 	int			a = 0;
 
 	ptr_old = fopen(src_file, "r");
-	ptr_new = fopen(dest_file, "w");
 
 	if (ptr_old == NULL)
 		return false;
 
+	ptr_new = fopen(dest_file, "w");
+
 	if (ptr_new == NULL)
 	{
 		fclose(ptr_old);

repmgr-action-primary.c

@@ -96,28 +96,6 @@ do_primary_register(void)
 
 	initialize_voting_term(conn);
 
-	/* Ensure there isn't another registered node which is primary */
-	primary_conn = get_primary_connection(conn, &current_primary_id, NULL);
-
-	if (primary_conn != NULL)
-	{
-		if (current_primary_id != config_file_options.node_id)
-		{
-			/*
-			 * it's impossible to add a second primary to a streaming
-			 * replication cluster
-			 */
-			log_error(_("there is already an active registered primary (node ID: %i) in this cluster"), current_primary_id);
-			PQfinish(primary_conn);
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		/* we've probably connected to ourselves */
-		PQfinish(primary_conn);
-	}
-
-
 	begin_transaction(conn);
 
 	/*
@@ -128,12 +106,32 @@ do_primary_register(void)
 	current_primary_id = get_primary_node_id(conn);
 	if (current_primary_id != NODE_NOT_FOUND && current_primary_id != config_file_options.node_id)
 	{
-		log_error(_("another node with id %i is already registered as primary"), current_primary_id);
-		log_detail(_("a streaming replication cluster can have only one primary node"));
+		log_debug("XXX %i", current_primary_id);
+		primary_conn = establish_primary_db_connection(conn, false);
 
-		rollback_transaction(conn);
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
+		if (PQstatus(primary_conn) == CONNECTION_OK)
+		{
+			if (get_recovery_type(primary_conn) == RECTYPE_PRIMARY)
+			{
+				log_error(_("there is already an active registered primary (ID: %i) in this cluster"),
+						  current_primary_id);
+				log_detail(_("a streaming replication cluster can have only one primary node"));
+
+				log_hint(_("ensure this node is shut down before registering a new primary"));
+				PQfinish(primary_conn);
+				rollback_transaction(conn);
+				PQfinish(conn);
+				exit(ERR_BAD_CONFIG);
+			}
+
+			log_warning(_("node %is is registered as primary but running as a standby"),
+						  current_primary_id);
+			PQfinish(primary_conn);
+		}
+
+		log_notice(_("setting node %i's node record to inactive"),
+						  current_primary_id);
+		update_node_record_set_active(conn, current_primary_id, false);
 	}
 
 	/*
@@ -225,12 +223,12 @@ do_primary_register(void)
 
 	if (record_status == RECORD_FOUND)
 	{
-		log_notice(_("primary node record (id: %i) updated"),
+		log_notice(_("primary node record (ID: %i) updated"),
 				   config_file_options.node_id);
 	}
 	else
 	{
-		log_notice(_("primary node record (id: %i) registered"),
+		log_notice(_("primary node record (ID: %i) registered"),
 				   config_file_options.node_id);
 	}
 
@@ -276,7 +274,7 @@ do_primary_unregister(void)
 
 		if (get_primary_node_record(local_conn, &primary_node_info) == true)
 		{
-			log_detail(_("current primary registered as node %s (id: %i, conninfo: \"%s\")"),
+			log_detail(_("current primary registered as node \"%s\" (ID: %i, conninfo: \"%s\")"),
 					   primary_node_info.node_name,
 					   primary_node_info.node_id,
 					   primary_node_info.conninfo);
@@ -318,7 +316,7 @@ do_primary_unregister(void)
 
 	if (target_node_info_ptr->type == WITNESS)
 	{
-		log_error(_("node %s (id: %i) is a witness server, unable to unregister"),
+		log_error(_("node \"%s\" (ID: %i) is a witness server, unable to unregister"),
 					  target_node_info_ptr->node_name,
 					  target_node_info_ptr->node_id);
 		if (target_node_info_ptr->type == STANDBY)
@@ -359,7 +357,7 @@ do_primary_unregister(void)
 		for (cell = downstream_nodes.head; cell; cell = cell->next)
 		{
 			appendPQExpBuffer(&detail,
-							  "  %s (id: %i)\n",
+							  "  %s (ID: %i)\n",
 							  cell->node_info->node_name,
 							  cell->node_info->node_id);
 		}
@@ -379,7 +377,7 @@ do_primary_unregister(void)
 	{
 		if (target_node_info_ptr->type != PRIMARY)
 		{
-			log_error(_("node %s (id: %i) is not a primary, unable to unregister"),
+			log_error(_("node \"%s\" (ID: %i) is not a primary, unable to unregister"),
 					  target_node_info_ptr->node_name,
 					  target_node_info_ptr->node_id);
 			if (target_node_info_ptr->type == STANDBY)
@@ -406,7 +404,7 @@ do_primary_unregister(void)
 			 */
 			if (target_node_info_ptr->type != PRIMARY)
 			{
-				log_error(_("node %s (ID: %i) is a %s, unable to unregister"),
+				log_error(_("node \"%s\" (ID: %i) is a %s, unable to unregister"),
 						  target_node_info_ptr->node_name,
 						  target_node_info_ptr->node_id,
 						  get_node_type_string(target_node_info_ptr->type));
@@ -420,7 +418,7 @@ do_primary_unregister(void)
 			 */
 			else if (!runtime_options.force)
 			{
-				log_error(_("node %s (ID: %i) is running as a standby, unable to unregister"),
+				log_error(_("node \"%s\" (ID: %i) is running as a standby, unable to unregister"),
 						  target_node_info_ptr->node_name,
 						  target_node_info_ptr->node_id);
 				log_hint(_("the node can be registered as a standby with \"repmgr standby register --force\""));
@@ -445,7 +443,7 @@ do_primary_unregister(void)
 
 			if (primary_record_found == false)
 			{
-				log_error(_("node %s (ID: %i) is a primary node, but no primary node record found"),
+				log_error(_("node \"%s\" (ID: %i) is a primary node, but no primary node record found"),
 						  target_node_info_ptr->node_name,
 						  target_node_info_ptr->node_id);
 				log_hint(_("register this node as primary with \"repmgr primary register --force\""));
@@ -460,7 +458,7 @@ do_primary_unregister(void)
 			 */
 			if (primary_node_info.node_id == target_node_info_ptr->node_id)
 			{
-				log_error(_("node %s (ID: %i) is the current primary node, unable to unregister"),
+				log_error(_("node \"%s\" (ID: %i) is the current primary node, unable to unregister"),
 						  target_node_info_ptr->node_name,
 						  target_node_info_ptr->node_id);
 
@@ -482,7 +480,7 @@ do_primary_unregister(void)
 	{
 		if (!runtime_options.force)
 		{
-			log_error(_("node %s (ID: %i) is marked as active, unable to unregister"),
+			log_error(_("node \"%s\" (ID: %i) is marked as active, unable to unregister"),
 					  target_node_info_ptr->node_name,
 					  target_node_info_ptr->node_id);
 			log_hint(_("run \"repmgr primary unregister --force\" to unregister this node"));
@@ -493,7 +491,7 @@ do_primary_unregister(void)
 
 	if (runtime_options.dry_run == true)
 	{
-		log_notice(_("node %s (ID: %i) would now be unregistered"),
+		log_notice(_("node \"%s\" (ID: %i) would now be unregistered"),
 				   target_node_info_ptr->node_name,
 				   target_node_info_ptr->node_id);
 		log_hint(_("run the same command without the --dry-run option to unregister this node"));
@@ -506,7 +504,7 @@ do_primary_unregister(void)
 
 		if (delete_success == false)
 		{
-			log_error(_("unable to unregister node %s (ID: %i)"),
+			log_error(_("unable to unregister node \"%s\" (ID: %i)"),
 					  target_node_info_ptr->node_name,
 					  target_node_info_ptr->node_id);
 			PQfinish(primary_conn);
@@ -515,14 +513,14 @@ do_primary_unregister(void)
 
 		initPQExpBuffer(&event_details);
 		appendPQExpBuffer(&event_details,
-						  _("node %s (ID: %i) unregistered"),
+						  _("node \"%s\" (ID: %i) unregistered"),
 						  target_node_info_ptr->node_name,
 						  target_node_info_ptr->node_id);
 
 		if (target_node_info_ptr->node_id != config_file_options.node_id)
 		{
 			appendPQExpBuffer(&event_details,
-							  _(" from node %s (ID: %i)"),
+							  _(" from node \"%s\" (ID: %i)"),
 							  config_file_options.node_name,
 							  config_file_options.node_id);
 		}
@@ -535,7 +533,7 @@ do_primary_unregister(void)
 								  event_details.data);
 		termPQExpBuffer(&event_details);
 
-		log_info(_("node %s (ID: %i) was successfully unregistered"),
+		log_info(_("node \"%s\" (ID: %i) was successfully unregistered"),
 				 target_node_info_ptr->node_name,
 				 target_node_info_ptr->node_id);
 	}

repmgr-action-witness.c

@@ -56,8 +56,7 @@ do_witness_register(void)
 		log_error(_("unable to connect to witness node \"%s\" (ID: %i)"),
 				  config_file_options.node_name,
 				  config_file_options.node_id);
-		log_detail("%s",
-				   PQerrorMessage(witness_conn));
+		log_detail("\n%s", PQerrorMessage(witness_conn));
 		log_hint(_("the witness node must be running before it can be registered"));
 		exit(ERR_BAD_CONFIG);
 	}
@@ -174,11 +173,26 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/*
-	 * TODO: sanity check witness node is not part of main cluster; we could
-	 * add a random application_name to the respective connections,
-	 * and do a simple check of pg_stat_activity
-	 */
+	/* Sanity check witness node is not part of main cluster. */
+	if (PQserverVersion(primary_conn) >= 90600 &&
+		PQserverVersion(witness_conn) >= 90600)
+	{
+		uint64		primary_system_identifier = system_identifier(primary_conn);
+		uint64		witness_system_identifier = system_identifier(witness_conn);
+
+		if (primary_system_identifier == witness_system_identifier &&
+			primary_system_identifier != UNKNOWN_SYSTEM_IDENTIFIER)
+		{
+			log_error(_("witness node cannot be in the same cluster as the primary node"));
+			log_detail(_("database system identifiers on primary node and provided witness node match (%lu)"),
+					   primary_system_identifier);
+			log_hint(_("the witness node must be created on a separate read/write node"));
+			PQfinish(witness_conn);
+			PQfinish(primary_conn);
+
+			exit(ERR_BAD_CONFIG);
+		}
+	}
 
 	/* check that primary node is not a BDR node */
 	if (is_bdr_db_quiet(primary_conn) == true)
@@ -357,13 +371,24 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* create event */
-	create_event_record(primary_conn,
-						&config_file_options,
-						config_file_options.node_id,
-						"witness_register",
-						true,
-						NULL);
+	{
+		PQExpBufferData event_details;
+		initPQExpBuffer(&event_details);
+
+		appendPQExpBuffer(&event_details,
+						  _("witness registration succeeded; upstream node ID is %i"),
+						  node_record.upstream_node_id);
+
+		/* create event */
+		create_event_notification(primary_conn,
+								  &config_file_options,
+								  config_file_options.node_id,
+								  "witness_register",
+								  true,
+								  event_details.data);
+
+		termPQExpBuffer(&event_details);
+	}
 
 	PQfinish(primary_conn);
 	PQfinish(witness_conn);
@@ -411,7 +436,7 @@ do_witness_unregister(void)
 			log_error(_("unable to connect to node \"%s\" (ID: %i)"),
 					  config_file_options.node_name,
 					  config_file_options.node_id);
-			log_detail("%s", PQerrorMessage(local_conn));
+			log_detail("\n%s", PQerrorMessage(local_conn));
 			exit(ERR_BAD_CONFIG);
 		}
 
@@ -437,7 +462,7 @@ do_witness_unregister(void)
 	if (PQstatus(primary_conn) != CONNECTION_OK)
 	{
 		log_error(_("unable to connect to primary"));
-		log_detail("%s", PQerrorMessage(primary_conn));
+		log_detail("\n%s", PQerrorMessage(primary_conn));
 
 		if (local_node_available == true)
 		{
@@ -506,13 +531,24 @@ do_witness_unregister(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* Log the event */
-	create_event_record(primary_conn,
-						&config_file_options,
-						witness_node_id,
-						"witness_unregister",
-						true,
-						NULL);
+
+	{
+		PQExpBufferData event_details;
+		initPQExpBuffer(&event_details);
+
+		appendPQExpBufferStr(&event_details,
+							 _("witness unregistration succeeded"));
+
+		/* create event */
+		create_event_notification(primary_conn,
+								  &config_file_options,
+								  witness_node_id,
+								  "witness_unregister",
+								  true,
+								  event_details.data);
+
+		termPQExpBuffer(&event_details);
+	}
 
 	PQfinish(primary_conn);
 

repmgr-client-global.h

@@ -45,6 +45,7 @@ typedef struct
 	int			wait;
 	bool		no_wait;
 	bool		compact;
+	bool		detail;
 
 	/* logging options */
 	char		log_level[MAXLEN];	/* overrides setting in repmgr.conf */
@@ -70,7 +71,7 @@ typedef struct
 
 	/* general node options */
 	int			node_id;
-	char		node_name[MAXLEN];
+	char		node_name[NAMEDATALEN];
 	char		data_dir[MAXPGPATH];
 	int			remote_node_id;
 
@@ -100,6 +101,7 @@ typedef struct
 	char		force_rewind_path[MAXPGPATH];
 	bool		siblings_follow;
 	bool		repmgrd_no_pause;
+	bool		repmgrd_force_unpause;
 
 	/* "node status" options */
 	bool		is_shutdown_cleanly;
@@ -143,7 +145,7 @@ typedef struct
 		/* configuration metadata */ \
 		false, false, false, false, false,	\
 		/* general configuration options */	\
-		"", false, false, "", -1, false, false, \
+		"", false, false, "", -1, false, false, false, \
 		/* logging options */ \
 		"", false, false, false, false,	\
 		/* output options */ \
@@ -162,7 +164,7 @@ typedef struct
 		/* "standby register" options */ \
 		false, -1, DEFAULT_WAIT_START,   \
 		/* "standby switchover" options */ \
-		false, false, "", false, false,	\
+		false, false, "", false, false, false,	\
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
@@ -241,8 +243,8 @@ extern void get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGc
 extern void make_remote_repmgr_path(PQExpBufferData *outputbuf, t_node_info *remote_node_record);
 extern void make_repmgrd_path(PQExpBufferData *output_buf);
 
-
 /* display functions */
+extern bool format_node_status(t_node_info *node_info, PQExpBufferData *node_status, PQExpBufferData *upstream, ItemList *warnings);
 extern void print_help_header(void);
 extern void print_status_header(int cols, ColHeader *headers);
 

repmgr-client.c

@@ -271,6 +271,10 @@ main(int argc, char **argv)
 				runtime_options.compact = true;
 				break;
 
+				/* --detail */
+			case OPT_DETAIL:
+				runtime_options.detail = true;
+				break;
 
 				/*----------------------------
 				 * database connection options
@@ -356,9 +360,15 @@ main(int argc, char **argv)
 
 				/* --node-name */
 			case OPT_NODE_NAME:
-				strncpy(runtime_options.node_name, optarg, MAXLEN);
+			{
+				if (strlen(optarg) < sizeof(runtime_options.node_name))
+					strncpy(runtime_options.node_name, optarg, sizeof(runtime_options.node_name));
+				else
+					item_list_append_format(&cli_errors,
+											_("value for \"--node-name\" must contain fewer than %lu characters"),
+											sizeof(runtime_options.node_name));
 				break;
-
+			}
 				/* --remote-node-id */
 			case OPT_REMOTE_NODE_ID:
 				runtime_options.remote_node_id = repmgr_atoi(optarg, "--remote-node-id", &cli_errors, MIN_NODE_ID);
@@ -468,6 +478,10 @@ main(int argc, char **argv)
 				runtime_options.repmgrd_no_pause = true;
 				break;
 
+			case OPT_REPMGRD_FORCE_UNPAUSE:
+				runtime_options.repmgrd_force_unpause = true;
+				break;
+
 				/*----------------------
 				 * "node status" options
 				 *----------------------
@@ -1280,7 +1294,7 @@ main(int argc, char **argv)
 			pfree(escaped);
 			if (record_status != RECORD_FOUND)
 			{
-				log_error(_("node %s (specified with --node-name) not found"),
+				log_error(_("node \"%s\" (specified with --node-name) not found"),
 						  runtime_options.node_name);
 				PQfinish(conn);
 				free_conninfo_params(&source_conninfo);
@@ -1674,6 +1688,8 @@ check_cli_parameters(const int action)
 				item_list_append_format(&cli_warnings,
 										_("--replication-user ignored when executing %s"),
 										action_name(action));
+				break;
+
 			default:
 				item_list_append_format(&cli_warnings,
 										_("--replication-user not required when executing %s"),
@@ -1846,6 +1862,22 @@ check_cli_parameters(const int action)
 		}
 	}
 
+	if (runtime_options.repmgrd_force_unpause == true)
+	{
+		switch (action)
+		{
+			case STANDBY_SWITCHOVER:
+				if (runtime_options.repmgrd_no_pause == true)
+					item_list_append(&cli_errors,
+									 _("--repmgrd-force-unpause and --repmgrd-no-pause cannot be used together"));
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--repmgrd-force-unpause will be ignored when executing %s"),
+										action_name(action));
+		}
+	}
+
 	if (runtime_options.config_files[0] != '\0')
 	{
 		switch (action)
@@ -1908,12 +1940,12 @@ check_cli_parameters(const int action)
 	}
 
 	/* --compact */
-
 	if (runtime_options.compact == true)
 	{
 		switch (action)
 		{
 			case CLUSTER_SHOW:
+			case CLUSTER_EVENT:
 			case DAEMON_STATUS:
 				break;
 			default:
@@ -1923,6 +1955,35 @@ check_cli_parameters(const int action)
 		}
 	}
 
+	/* --detail */
+	if (runtime_options.detail == true)
+	{
+		switch (action)
+		{
+			case DAEMON_STATUS:
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--detail is not effective when executing %s"),
+										action_name(action));
+		}
+	}
+
+	/* --siblings-follow */
+	if (runtime_options.siblings_follow == true)
+	{
+		switch (action)
+		{
+			case STANDBY_PROMOTE:
+			case STANDBY_SWITCHOVER:
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("----siblings-follow is not effective when executing %s"),
+										action_name(action));
+		}
+	}
+
 	/* --disable-wal-receiver / --enable-wal-receiver */
 	if (runtime_options.disable_wal_receiver == true || runtime_options.enable_wal_receiver == true)
 	{
@@ -1947,6 +2008,425 @@ check_cli_parameters(const int action)
 }
 
 
+/*
+ * Generate formatted node status output for display by "cluster show" and
+ * "daemon status".
+ */
+bool
+format_node_status(t_node_info *node_info, PQExpBufferData *node_status, PQExpBufferData *upstream, ItemList *warnings)
+{
+	bool error_found = false;
+	t_node_info remote_node_rec = T_NODE_INFO_INITIALIZER;
+	RecordStatus remote_node_rec_found = RECORD_NOT_FOUND;
+
+	if (PQstatus(node_info->conn) == CONNECTION_OK)
+	{
+		node_info->node_status = NODE_STATUS_UP;
+		node_info->recovery_type = get_recovery_type(node_info->conn);
+		/* get node's copy of its record so we can see what it thinks its status is */
+		remote_node_rec_found = get_node_record_with_upstream(node_info->conn, node_info->node_id, &remote_node_rec);
+	}
+	else
+	{
+		/* check if node is reachable, but just not letting us in */
+		if (is_server_available_quiet(node_info->conninfo))
+			node_info->node_status = NODE_STATUS_REJECTED;
+		else
+			node_info->node_status = NODE_STATUS_DOWN;
+
+		node_info->recovery_type = RECTYPE_UNKNOWN;
+	}
+
+	/* format node status info */
+	switch (node_info->type)
+	{
+		case PRIMARY:
+		{
+			/* node is reachable */
+			if (node_info->node_status == NODE_STATUS_UP)
+			{
+				if (node_info->active == true)
+				{
+					switch (node_info->recovery_type)
+					{
+						case RECTYPE_PRIMARY:
+							appendPQExpBufferStr(node_status, "* running");
+							break;
+						case RECTYPE_STANDBY:
+							appendPQExpBufferStr(node_status, "! running as standby");
+							item_list_append_format(warnings,
+													"node \"%s\" (ID: %i) is registered as primary but running as standby",
+													node_info->node_name, node_info->node_id);
+							break;
+						case RECTYPE_UNKNOWN:
+							appendPQExpBufferStr(node_status, "! unknown");
+							item_list_append_format(warnings,
+													"node \"%s\" (ID: %i) has unknown replication status",
+													node_info->node_name, node_info->node_id);
+							break;
+					}
+				}
+				else
+				{
+					if (node_info->recovery_type == RECTYPE_PRIMARY)
+					{
+						appendPQExpBufferStr(node_status, "! running");
+						item_list_append_format(warnings,
+												"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
+												node_info->node_name, node_info->node_id);
+					}
+					else
+					{
+						appendPQExpBufferStr(node_status, "! running as standby");
+						item_list_append_format(warnings,
+												"node \"%s\" (ID: %i) is registered as an inactive primary but running as standby",
+												node_info->node_name, node_info->node_id);
+					}
+				}
+			}
+			/* node is up but cannot connect */
+			else if (node_info->node_status == NODE_STATUS_REJECTED)
+			{
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? running");
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "! running");
+					error_found = true;
+				}
+			}
+			/* node is unreachable */
+			else
+			{
+				/* node is unreachable but marked active */
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? unreachable");
+					item_list_append_format(warnings,
+											"node \"%s\" (ID: %i) is registered as an active primary but is unreachable",
+											node_info->node_name, node_info->node_id);
+				}
+				/* node is unreachable and marked as inactive */
+				else
+				{
+					appendPQExpBufferStr(node_status, "- failed");
+					error_found = true;
+				}
+			}
+		}
+		break;
+		case STANDBY:
+		{
+			/* node is reachable */
+			if (node_info->node_status == NODE_STATUS_UP)
+			{
+				if (node_info->active == true)
+				{
+					switch (node_info->recovery_type)
+					{
+						case RECTYPE_STANDBY:
+							appendPQExpBufferStr(node_status, "  running");
+							break;
+						case RECTYPE_PRIMARY:
+							appendPQExpBufferStr(node_status, "! running as primary");
+							item_list_append_format(warnings,
+													"node \"%s\" (ID: %i) is registered as standby but running as primary",
+													node_info->node_name, node_info->node_id);
+							break;
+						case RECTYPE_UNKNOWN:
+							appendPQExpBufferStr(node_status, "! unknown");
+							item_list_append_format(
+								warnings,
+								"node \"%s\" (ID: %i) has unknown replication status",
+								node_info->node_name, node_info->node_id);
+							break;
+					}
+				}
+				else
+				{
+					if (node_info->recovery_type == RECTYPE_STANDBY)
+					{
+						appendPQExpBufferStr(node_status, "! running");
+						item_list_append_format(warnings,
+												"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
+												node_info->node_name, node_info->node_id);
+					}
+					else
+					{
+						appendPQExpBufferStr(node_status, "! running as primary");
+						item_list_append_format(warnings,
+												"node \"%s\" (ID: %i) is running as primary but the repmgr node record is inactive",
+												node_info->node_name, node_info->node_id);
+					}
+				}
+
+				/* warn about issue with paused WAL replay */
+				if (is_wal_replay_paused(node_info->conn, true))
+				{
+					item_list_append_format(warnings,
+											_("WAL replay is paused on node \"%s\" (ID: %i) with WAL replay pending; this node cannot be manually promoted until WAL replay is resumed"),
+											node_info->node_name, node_info->node_id);
+				}
+			}
+			/* node is up but cannot connect */
+			else if (node_info->node_status == NODE_STATUS_REJECTED)
+			{
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? running");
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "! running");
+					error_found = true;
+				}
+			}
+			/* node is unreachable */
+			else
+			{
+				/* node is unreachable but marked active */
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? unreachable");
+					item_list_append_format(warnings,
+											"node \"%s\" (ID: %i) is registered as an active standby but is unreachable",
+											node_info->node_name, node_info->node_id);
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "- failed");
+					error_found = true;
+				}
+			}
+		}
+
+		break;
+		case WITNESS:
+		case BDR:
+		{
+			/* node is reachable */
+			if (node_info->node_status == NODE_STATUS_UP)
+			{
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "* running");
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "! running");
+					error_found = true;
+				}
+			}
+			/* node is up but cannot connect */
+			else if (node_info->node_status == NODE_STATUS_REJECTED)
+			{
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? rejected");
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "! failed");
+					error_found = true;
+				}
+			}
+			/* node is unreachable */
+			else
+			{
+				if (node_info->active == true)
+				{
+					appendPQExpBufferStr(node_status, "? unreachable");
+				}
+				else
+				{
+					appendPQExpBufferStr(node_status, "- failed");
+					error_found = true;
+				}
+			}
+		}
+		break;
+		case UNKNOWN:
+		{
+			/* this should never happen */
+			appendPQExpBufferStr(node_status, "? unknown node type");
+			error_found = true;
+		}
+		break;
+	}
+
+	/* format node upstream info */
+
+	if (remote_node_rec_found == RECORD_NOT_FOUND)
+	{
+		/*
+		 * Unable to retrieve the node's copy of its own record - copy the
+		 * name from our own copy of the record
+		 */
+		appendPQExpBufferStr(upstream,
+							 node_info->upstream_node_name);
+	}
+	else if (remote_node_rec.type == WITNESS)
+	{
+		/* no upstream - unlikely to happen */
+		if (remote_node_rec.upstream_node_id == NO_UPSTREAM_NODE)
+		{
+			appendPQExpBufferStr(upstream, "! ");
+			item_list_append_format(warnings,
+									"node \"%s\" (ID: %i) is a witness but reports it has no upstream node",
+									node_info->node_name,
+									node_info->node_id);
+		}
+		/* mismatch between reported upstream and upstream in local node's metadata */
+		else if(node_info->upstream_node_id != remote_node_rec.upstream_node_id)
+		{
+			appendPQExpBufferStr(upstream, "! ");
+
+			if (node_info->upstream_node_id != remote_node_rec.upstream_node_id)
+			{
+				item_list_append_format(warnings,
+										"node \"%s\" (ID: %i) reports a different upstream (reported: \"%s\", expected \"%s\")",
+										node_info->node_name,
+										node_info->node_id,
+										remote_node_rec.upstream_node_name,
+										node_info->upstream_node_name);
+			}
+		}
+		else
+		{
+			t_node_info upstream_node_rec = T_NODE_INFO_INITIALIZER;
+			RecordStatus upstream_node_rec_found = get_node_record(node_info->conn,
+																   node_info->upstream_node_id,
+																   &upstream_node_rec);
+
+			if (upstream_node_rec_found != RECORD_FOUND)
+			{
+				appendPQExpBufferStr(upstream, "? ");
+				item_list_append_format(warnings,
+										"unable to find record for upstream node ID %i",
+										node_info->upstream_node_id);
+
+			}
+			else
+			{
+				PGconn *upstream_conn = establish_db_connection_quiet(upstream_node_rec.conninfo);
+
+				if (PQstatus(upstream_conn) != CONNECTION_OK)
+				{
+					appendPQExpBufferStr(upstream, "? ");
+					item_list_append_format(warnings,
+											"unable to connect to node \"%s\" (ID: %i)'s upstream node \"%s\" (ID: %i)",
+											node_info->node_name,
+											node_info->node_id,
+											upstream_node_rec.node_name,
+											upstream_node_rec.node_id);
+				}
+
+				PQfinish(upstream_conn);
+			}
+		}
+
+		appendPQExpBufferStr(upstream,
+							 remote_node_rec.upstream_node_name);
+
+	}
+	else if (remote_node_rec.type == STANDBY)
+	{
+		if (node_info->upstream_node_id != NO_UPSTREAM_NODE && node_info->upstream_node_id == remote_node_rec.upstream_node_id)
+		{
+			/*
+			 * expected and reported upstreams match - check if node is actually
+			 * connected to the upstream
+			 */
+			NodeAttached attached_to_upstream = NODE_ATTACHED_UNKNOWN;
+			t_node_info upstream_node_rec = T_NODE_INFO_INITIALIZER;
+			RecordStatus upstream_node_rec_found = get_node_record(node_info->conn,
+																   node_info->upstream_node_id,
+																   &upstream_node_rec);
+
+			if (upstream_node_rec_found != RECORD_FOUND)
+			{
+				item_list_append_format(warnings,
+										"unable to find record for upstream node ID %i",
+										node_info->upstream_node_id);
+
+			}
+			else
+			{
+				PGconn *upstream_conn = establish_db_connection_quiet(upstream_node_rec.conninfo);
+
+				if (PQstatus(upstream_conn) != CONNECTION_OK)
+				{
+					item_list_append_format(warnings,
+											"unable to connect to node \"%s\" (ID: %i)'s upstream node \"%s\" (ID: %i)",
+											node_info->node_name,
+											node_info->node_id,
+											upstream_node_rec.node_name,
+											upstream_node_rec.node_id);
+				}
+				else
+				{
+					attached_to_upstream = is_downstream_node_attached(upstream_conn, node_info->node_name);
+				}
+
+				PQfinish(upstream_conn);
+			}
+
+			if (attached_to_upstream == NODE_ATTACHED_UNKNOWN)
+			{
+				appendPQExpBufferStr(upstream, "? ");
+				item_list_append_format(warnings,
+										"unable to determine if node \"%s\" (ID: %i) is attached to its upstream node \"%s\" (ID: %i)",
+										node_info->node_name,
+										node_info->node_id,
+										upstream_node_rec.node_name,
+										upstream_node_rec.node_id);
+			}
+			else if (attached_to_upstream == NODE_DETACHED)
+			{
+				appendPQExpBufferStr(upstream, "! ");
+				item_list_append_format(warnings,
+										"node \"%s\" (ID: %i) is not attached to its upstream node \"%s\" (ID: %i)",
+										node_info->node_name,
+										node_info->node_id,
+										upstream_node_rec.node_name,
+										upstream_node_rec.node_id);
+			}
+			appendPQExpBufferStr(upstream,
+								 node_info->upstream_node_name);
+
+		}
+		else
+		{
+			if (node_info->upstream_node_id != NO_UPSTREAM_NODE && remote_node_rec.upstream_node_id == NO_UPSTREAM_NODE)
+			{
+				appendPQExpBufferChar(upstream, '!');
+				item_list_append_format(warnings,
+										"node \"%s\" (ID: %i) reports it has no upstream (expected: \"%s\")",
+										node_info->node_name,
+										node_info->node_id,
+										node_info->upstream_node_name);
+			}
+			else if (node_info->upstream_node_id != NO_UPSTREAM_NODE && remote_node_rec.upstream_node_id != NO_UPSTREAM_NODE)
+
+			{
+				appendPQExpBuffer(upstream,
+								  "! %s", remote_node_rec.upstream_node_name);
+				item_list_append_format(warnings,
+										"node \"%s\" (ID: %i) reports a different upstream (reported: \"%s\", expected \"%s\")",
+										node_info->node_name,
+										node_info->node_id,
+										remote_node_rec.upstream_node_name,
+										node_info->upstream_node_name);
+			}
+		}
+	}
+
+	return error_found;
+}
+
+
 static const char *
 action_name(const int action)
 {
@@ -2036,9 +2516,10 @@ print_error_list(ItemList *error_list, int log_level)
 void
 print_status_header(int cols, ColHeader *headers)
 {
-	int i;
+	int i, di;
 	int max_cols = 0;
 
+
 	/* count how many columns we actually need to display */
 	for (i = 0; i < cols; i++)
 	{
@@ -2065,7 +2546,8 @@ print_status_header(int cols, ColHeader *headers)
 	printf("\n");
 	printf("-");
 
-	for (i = 0; i < max_cols; i++)
+	di = 0;
+	for (i = 0; i < cols; i++)
 	{
 		int			j;
 
@@ -2075,10 +2557,11 @@ print_status_header(int cols, ColHeader *headers)
 		for (j = 0; j < headers[i].max_length; j++)
 			printf("-");
 
-		if (i < (max_cols - 1))
+		if (di < (max_cols - 1))
 			printf("-+-");
 		else
 			printf("-");
+		di++;
 	}
 
 	printf("\n");
@@ -2211,7 +2694,7 @@ create_repmgr_extension(PGconn *conn)
 			log_detail(_("version %s is installed but newer version %s is available"),
 					   extversions.installed_version,
 					   extversions.default_version);
-			log_hint(_("execute \"ALTER EXTENSION repmgr UPGRADE\""));
+			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\""));
 			return false;
 
 		case REPMGR_INSTALLED:
@@ -2457,6 +2940,7 @@ get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privil
 	if (PQstatus(*conn) != CONNECTION_OK)
 	{
 		log_error(_("no database connection available"));
+		log_detail("\n%s", PQerrorMessage(*conn));
 		exit(ERR_INTERNAL);
 	}
 
@@ -3000,7 +3484,7 @@ init_node_record(t_node_info *node_record)
 		strncpy(node_record->location, "default", MAXLEN);
 
 
-	strncpy(node_record->node_name, config_file_options.node_name, MAXLEN);
+	strncpy(node_record->node_name, config_file_options.node_name, sizeof(node_record->node_name));
 	strncpy(node_record->conninfo, config_file_options.conninfo, MAXLEN);
 	strncpy(node_record->config_file, config_file_path, MAXPGPATH);
 
@@ -3054,9 +3538,6 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 	/* "full_page_writes" must be on in any case */
 	if (guc_set(conn, "full_page_writes", "=", "off"))
 	{
-		if (can_use == false)
-			appendPQExpBuffer(reason, "; ");
-
 		appendPQExpBuffer(reason,
 						  _("\"full_page_writes\" must be set to \"on\""));
 
@@ -3143,6 +3624,8 @@ drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name)
 /*
  * Here we'll perform some timeline sanity checks to ensure the follow target
  * can actually be followed.
+ *
+ * See also comment for check_node_can_follow() in repmgrd-physical.c .
  */
 bool
 check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_record, bool is_rejoin)
@@ -3233,6 +3716,7 @@ check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *fo
 		return false;
 	}
 
+	/* timelines are the same - check relative positions */
 	if (follow_target_identification.timeline == local_tli)
 	{
 		XLogRecPtr follow_target_xlogpos = get_node_current_lsn(follow_target_conn);
@@ -3244,7 +3728,6 @@ check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *fo
 			return false;
 		}
 
-		/* timeline is the same - check relative positions */
 		if (local_xlogpos <= follow_target_xlogpos)
 		{
 			log_info(_("timelines are same, this server is not ahead"));