doc: emphasise that BDR2 support is for BDR2 only

Barman will usually use one replication slot, but that's generally
preferable to multiple slots.

CONTRIBUTING.md

@@ -2,7 +2,7 @@ License and Contributions
 =========================
 
 `repmgr` is licensed under the GPL v3.  All of its code and documentation is
-Copyright 2010-2019, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+Copyright 2010-2018, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
 details.
 
 The development of repmgr has primarily been sponsored by 2ndQuadrant customers.
@@ -24,7 +24,7 @@ Code style
 Code in repmgr should be formatted to the same standards as the main PostgreSQL
 project. For more details see:
 
-    https://www.postgresql.org/docs/current/source-format.html
+    https://www.postgresql.org/docs/current/static/source-format.html
 
 Contributors should reformat their code similarly before submitting code to
 the project, in order to minimize merge conflicts with other work.

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2019, 2ndQuadrant Limited
+Copyright (c) 2010-2018, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

HISTORY

@@ -1,28 +1,3 @@
-4.3     2019-??
-        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)
-        repmgr: cluster show - differentiate between unreachable nodes
-          and nodes which are running but rejecting connections (Ian)
-        repmgr: add --dry-run option to "standby promote"; GitHub #522 (Ian)
-        repmgr: add "node check --data-directory-config"; GitHub #523 (Ian)
-        repmgr: prevent potential race condition in "standby switchover"
-          when checking received WAL location; GitHub #518 (Ian)
-        repmgr: ensure "standby switchover" verifies repmgr can read the
-          data directory on the demotion candidate; GitHub #523 (Ian)
-        repmgr: ensure "standby switchover" verifies replication connection
-          exists; GitHub #519 (Ian)
-        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)
-        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)
-        repmgrd: don't consider nodes where repmgrd is not running as promotion
-          candidates (Ian)
-        repmgrd: add option "connection_check_type" (Ian)
-        repmgrd: improve witness monitoring when primary node not available (Ian)
-
 4.2     2018-10-24
         repmgr: add parameter "shutdown_check_timeout" for use by "standby switchover";
           GitHub #504 (Ian)

Makefile.in

@@ -15,9 +15,7 @@ DATA = \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \
   repmgr--4.1--4.2.sql \
-  repmgr--4.2.sql \
-  repmgr--4.2--4.3.sql \
-  repmgr--4.3.sql
+  repmgr--4.2.sql
 
 REGRESS = repmgr_extension
 
@@ -50,8 +48,8 @@ $(info Building against PostgreSQL $(MAJORVERSION))
 REPMGR_CLIENT_OBJS = repmgr-client.o \
 	repmgr-action-primary.o repmgr-action-standby.o repmgr-action-witness.o \
 	repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.o repmgr-action-daemon.o \
-	configfile.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
-REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.o
+	configfile.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o
+REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o log.o dbutils.o strutil.o controldata.o compat.o
 DATE=$(shell date "+%Y-%m-%d")
 
 repmgr_version.h: repmgr_version.h.in
@@ -86,15 +84,29 @@ clean: additional-clean
 maintainer-clean: additional-maintainer-clean
 
 additional-clean:
-	rm -f *.o
+	rm -f repmgr-client.o
+	rm -f repmgr-action-primary.o
+	rm -f repmgr-action-standby.o
+	rm -f repmgr-action-witness.o
+	rm -f repmgr-action-bdr.o
+	rm -f repmgr-action-node.o
+	rm -f repmgr-action-cluster.o
+	rm -f repmgr-action-daemon.o
+	rm -f repmgrd.o
+	rm -f repmgrd-physical.o
+	rm -f repmgrd-bdr.o
+	rm -f compat.o
+	rm -f configfile.o
+	rm -f controldata.o
+	rm -f dbutils.o
+	rm -f dirutil.o
+	rm -f log.o
+	rm -f strutil.o
 
-additional-maintainer-clean: clean
-	$(MAKE) -C doc maintainer-clean
+maintainer-additional-clean: clean
+	rm -f configure
 	rm -f config.status config.log
-	rm -f config.h
-	rm -f repmgr_version.h
 	rm -f Makefile
-	rm -f Makefile.global
 	@rm -rf autom4te.cache/
 
 ifeq ($(MAJORVERSION),$(filter $(MAJORVERSION),9.3 9.4))

compat.c

@@ -6,7 +6,7 @@
  *    supported PostgreSQL versions. They're unlikely to change but
  *    it would be worth keeping an eye on them for any fixes/improvements.
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -98,42 +98,9 @@ appendShellString(PQExpBuffer buf, const char *str)
 
 		if (*p == '\'')
 			appendPQExpBufferStr(buf, "'\"'\"'");
-		else if (*p == '&')
-			appendPQExpBufferStr(buf, "\\&");
 		else
 			appendPQExpBufferChar(buf, *p);
 	}
 
 	appendPQExpBufferChar(buf, '\'');
 }
-
-/*
- * Adapted from: src/fe_utils/string_utils.c
- */
-void
-appendRemoteShellString(PQExpBuffer buf, const char *str)
-{
-	const char *p;
-
-	appendPQExpBufferStr(buf, "\\'");
-
-	for (p = str; *p; p++)
-	{
-		if (*p == '\n' || *p == '\r')
-		{
-			fprintf(stderr,
-					_("shell command argument contains a newline or carriage return: \"%s\"\n"),
-					str);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		if (*p == '\'')
-			appendPQExpBufferStr(buf, "'\"'\"'");
-		else if (*p == '&')
-			appendPQExpBufferStr(buf, "\\&");
-		else
-			appendPQExpBufferChar(buf, *p);
-	}
-
-	appendPQExpBufferStr(buf, "\\'");
-}

compat.h

@@ -1,6 +1,6 @@
 /*
  * compat.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -27,6 +27,4 @@ extern void appendConnStrVal(PQExpBuffer buf, const char *str);
 
 extern void appendShellString(PQExpBuffer buf, const char *str);
 
-extern void appendRemoteShellString(PQExpBuffer buf, const char *str);
-
 #endif

configfile.c

@@ -1,7 +1,7 @@
 /*
  * config.c - parse repmgr.conf and other configuration-related functionality
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -123,9 +123,9 @@ load_config(const char *config_file, bool verbose, bool terse, t_configuration_o
 
 		if (stat(config_file_path, &stat_config) != 0)
 		{
-			log_error(_("provided configuration file \"%s\" not found"),
-					  config_file);
-			log_detail("%s", strerror(errno));
+			log_error(_("provided configuration file \"%s\" not found: %s"),
+					  config_file,
+					  strerror(errno));
 			exit(ERR_BAD_CONFIG);
 		}
 
@@ -335,7 +335,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	 */
 	options->shutdown_check_timeout = DEFAULT_SHUTDOWN_CHECK_TIMEOUT;
 	options->standby_reconnect_timeout = DEFAULT_STANDBY_RECONNECT_TIMEOUT;
-	options->wal_receive_check_timeout = DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT;
 
 	/*-----------------
 	 * repmgrd settings
@@ -358,12 +357,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->primary_notification_timeout = DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT;
 	options->repmgrd_standby_startup_timeout = -1; /* defaults to "standby_reconnect_timeout" if not set */
 	memset(options->repmgrd_pid_file, 0, sizeof(options->repmgrd_pid_file));
-	options->standby_disconnect_on_failover = false;
-	options->sibling_nodes_disconnect_timeout = DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT;
-	options->connection_check_type = CHECK_PING;
-	options->primary_visibility_consensus = false;
-	memset(options->failover_validation_command, 0, sizeof(options->failover_validation_command));
-	options->election_rerun_interval = DEFAULT_ELECTION_RERUN_INTERVAL;
 
 	/*-------------
 	 * witness settings
@@ -378,24 +371,17 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->bdr_local_monitoring_only = false;
 	options->bdr_recovery_timeout = DEFAULT_BDR_RECOVERY_TIMEOUT;
 
-	/*-------------------------
-	 * service command settings
-	 *-------------------------
+	/*-----------------
+	 * service settings
+	 *-----------------
 	 */
 	memset(options->pg_ctl_options, 0, sizeof(options->pg_ctl_options));
-	memset(options->service_start_command, 0, sizeof(options->service_start_command));
 	memset(options->service_stop_command, 0, sizeof(options->service_stop_command));
+	memset(options->service_start_command, 0, sizeof(options->service_start_command));
 	memset(options->service_restart_command, 0, sizeof(options->service_restart_command));
 	memset(options->service_reload_command, 0, sizeof(options->service_reload_command));
 	memset(options->service_promote_command, 0, sizeof(options->service_promote_command));
 
-	/*---------------------------------
-	 * repmgrd service command settings
-	 *---------------------------------
-	 */
-	memset(options->repmgrd_service_start_command, 0, sizeof(options->repmgrd_service_start_command));
-	memset(options->repmgrd_service_stop_command, 0, sizeof(options->repmgrd_service_stop_command));
-
 	/*----------------------------
 	 * event notification settings
 	 *----------------------------
@@ -480,7 +466,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		/* Copy into correct entry in parameters struct */
 		if (strcmp(name, "node_id") == 0)
 		{
-			options->node_id = repmgr_atoi(value, name, error_list, MIN_NODE_ID);
+			options->node_id = repmgr_atoi(value, name, error_list, 1);
 			node_id_found = true;
 		}
 		else if (strcmp(name, "node_name") == 0)
@@ -564,8 +550,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			options->shutdown_check_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "standby_reconnect_timeout") == 0)
 			options->standby_reconnect_timeout = repmgr_atoi(value, name, error_list, 0);
-		else if (strcmp(name, "wal_receive_check_timeout") == 0)
-			options->wal_receive_check_timeout = repmgr_atoi(value, name, error_list, 0);
 
 		/* node rejoin settings */
 		else if (strcmp(name, "node_rejoin_timeout") == 0)
@@ -601,11 +585,11 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		else if (strcmp(name, "priority") == 0)
 			options->priority = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "location") == 0)
-			strncpy(options->location, value, sizeof(options->location));
+			strncpy(options->location, value, MAXLEN);
 		else if (strcmp(name, "promote_command") == 0)
-			strncpy(options->promote_command, value, sizeof(options->promote_command));
+			strncpy(options->promote_command, value, MAXLEN);
 		else if (strcmp(name, "follow_command") == 0)
-			strncpy(options->follow_command, value, sizeof(options->follow_command));
+			strncpy(options->follow_command, value, MAXLEN);
 		else if (strcmp(name, "reconnect_attempts") == 0)
 			options->reconnect_attempts = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "reconnect_interval") == 0)
@@ -624,36 +608,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			options->repmgrd_standby_startup_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "repmgrd_pid_file") == 0)
 			strncpy(options->repmgrd_pid_file, value, MAXPGPATH);
-		else if (strcmp(name, "standby_disconnect_on_failover") == 0)
-			options->standby_disconnect_on_failover = parse_bool(value, name, error_list);
-		else if (strcmp(name, "sibling_nodes_disconnect_timeout") == 0)
-			options->sibling_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
-		else if (strcmp(name, "connection_check_type") == 0)
-		{
-			if (strcasecmp(value, "ping") == 0)
-			{
-				options->connection_check_type = CHECK_PING;
-			}
-			else if (strcasecmp(value, "connection") == 0)
-			{
-				options->connection_check_type = CHECK_CONNECTION;
-			}
-			else if (strcasecmp(value, "query") == 0)
-			{
-				options->connection_check_type = CHECK_QUERY;
-			}
-			else
-			{
-				item_list_append(error_list,
-								 _("value for \"connection_check_type\" must be \"ping\" or \"connection\"\n"));
-			}
-		}
-		else if (strcmp(name, "primary_visibility_consensus") == 0)
-			options->primary_visibility_consensus = parse_bool(value, name, error_list);
-		else if (strcmp(name, "failover_validation_command") == 0)
-			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);
 
 		/* witness settings */
 		else if (strcmp(name, "witness_sync_interval") == 0)
@@ -667,48 +621,41 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 
 		/* service settings */
 		else if (strcmp(name, "pg_ctl_options") == 0)
-			strncpy(options->pg_ctl_options, value, sizeof(options->pg_ctl_options));
-		else if (strcmp(name, "service_start_command") == 0)
-			strncpy(options->service_start_command, value, sizeof(options->service_start_command));
+			strncpy(options->pg_ctl_options, value, MAXLEN);
 		else if (strcmp(name, "service_stop_command") == 0)
-			strncpy(options->service_stop_command, value, sizeof(options->service_stop_command));
+			strncpy(options->service_stop_command, value, MAXLEN);
+		else if (strcmp(name, "service_start_command") == 0)
+			strncpy(options->service_start_command, value, MAXLEN);
 		else if (strcmp(name, "service_restart_command") == 0)
-			strncpy(options->service_restart_command, value, sizeof(options->service_restart_command));
+			strncpy(options->service_restart_command, value, MAXLEN);
 		else if (strcmp(name, "service_reload_command") == 0)
-			strncpy(options->service_reload_command, value, sizeof(options->service_reload_command));
+			strncpy(options->service_reload_command, value, MAXLEN);
 		else if (strcmp(name, "service_promote_command") == 0)
-			strncpy(options->service_promote_command, value, sizeof(options->service_promote_command));
-
-		/* repmgrd service settings */
-		else if (strcmp(name, "repmgrd_service_start_command") == 0)
-			strncpy(options->repmgrd_service_start_command, value, sizeof(options->repmgrd_service_start_command));
-		else if (strcmp(name, "repmgrd_service_stop_command") == 0)
-			strncpy(options->repmgrd_service_stop_command, value, sizeof(options->repmgrd_service_stop_command));
-
+			strncpy(options->service_promote_command, value, MAXLEN);
 
 		/* event notification settings */
 		else if (strcmp(name, "event_notification_command") == 0)
-			strncpy(options->event_notification_command, value, sizeof(options->event_notification_command));
+			strncpy(options->event_notification_command, value, MAXLEN);
 		else if (strcmp(name, "event_notifications") == 0)
 		{
 			/* store unparsed value for comparison when reloading config */
-			strncpy(options->event_notifications_orig, value, sizeof(options->event_notifications_orig));
+			strncpy(options->event_notifications_orig, value, MAXLEN);
 			parse_event_notifications_list(options, value);
 		}
 
 		/* barman settings */
 		else if (strcmp(name, "barman_host") == 0)
-			strncpy(options->barman_host, value, sizeof(options->barman_host));
+			strncpy(options->barman_host, value, MAXLEN);
 		else if (strcmp(name, "barman_server") == 0)
-			strncpy(options->barman_server, value, sizeof(options->barman_server));
+			strncpy(options->barman_server, value, MAXLEN);
 		else if (strcmp(name, "barman_config") == 0)
-			strncpy(options->barman_config, value, sizeof(options->barman_config));
+			strncpy(options->barman_config, value, MAXLEN);
 
 		/* rsync/ssh settings */
 		else if (strcmp(name, "rsync_options") == 0)
-			strncpy(options->rsync_options, value, sizeof(options->rsync_options));
+			strncpy(options->rsync_options, value, MAXLEN);
 		else if (strcmp(name, "ssh_options") == 0)
-			strncpy(options->ssh_options, value, sizeof(options->ssh_options));
+			strncpy(options->ssh_options, value, MAXLEN);
 
 		/* undocumented settings for testing */
 		else if (strcmp(name, "promote_delay") == 0)
@@ -1085,19 +1032,15 @@ 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
- * with these):
- *
+ * changeable options:
  * - async_query_timeout
  * - bdr_local_monitoring_only
  * - bdr_recovery_timeout
- * - connection_check_type
  * - conninfo
  * - degraded_monitoring_timeout
  * - event_notification_command
  * - event_notifications
  * - failover
- * - failover_validation_command
  * - follow_command
  * - log_facility
  * - log_file
@@ -1105,19 +1048,12 @@ parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemL
  * - log_status_interval
  * - monitor_interval_secs
  * - monitoring_history
- * - primary_notification_timeout
- * - primary_visibility_consensus
  * - promote_command
+ * - promote_delay
  * - reconnect_attempts
  * - reconnect_interval
  * - repmgrd_standby_startup_timeout
  * - retry_promote_interval_secs
- * - sibling_nodes_disconnect_timeout
- * - standby_disconnect_on_failover
- *
- *
- * Not publicly documented:
- * - promote_delay
  *
  * non-changeable options (repmgrd references these from the "repmgr.nodes"
  * table, not the configuration file)
@@ -1202,6 +1138,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		return false;
 	}
 
+
 	/*
 	 * No configuration problems detected - copy any changed values
 	 *
@@ -1251,8 +1188,8 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		{
 			strncpy(orig_options->conninfo, new_options.conninfo, MAXLEN);
 			log_info(_("\"conninfo\" is now \"%s\""), new_options.conninfo);
-		}
 
+		}
 		PQfinish(conn);
 	}
 
@@ -1330,6 +1267,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
+
 	/* promote_command */
 	if (strncmp(orig_options->promote_command, new_options.promote_command, MAXLEN) != 0)
 	{
@@ -1375,51 +1313,6 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
-	/* standby_disconnect_on_failover */
-	if (orig_options->standby_disconnect_on_failover != new_options.standby_disconnect_on_failover)
-	{
-		orig_options->standby_disconnect_on_failover = new_options.standby_disconnect_on_failover;
-		log_info(_("\"standby_disconnect_on_failover\" is now \"%s\""),
-				 new_options.standby_disconnect_on_failover == true ? "TRUE" : "FALSE");
-		config_changed = true;
-	}
-
-	/* sibling_nodes_disconnect_timeout */
-	if (orig_options->sibling_nodes_disconnect_timeout != new_options.sibling_nodes_disconnect_timeout)
-	{
-		orig_options->sibling_nodes_disconnect_timeout = new_options.sibling_nodes_disconnect_timeout;
-		log_info(_("\"sibling_nodes_disconnect_timeout\" is now \"%i\""),
-				 new_options.sibling_nodes_disconnect_timeout);
-		config_changed = true;
-	}
-
-	/* connection_check_type */
-	if (orig_options->connection_check_type != new_options.connection_check_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");
-		config_changed = true;
-	}
-
-	/* primary_visibility_consensus */
-	if (orig_options->primary_visibility_consensus != new_options.primary_visibility_consensus)
-	{
-		orig_options->primary_visibility_consensus = new_options.primary_visibility_consensus;
-		log_info(_("\"primary_visibility_consensus\" is now \"%s\""),
-				 new_options.primary_visibility_consensus == true ? "TRUE" : "FALSE");
-		config_changed = true;
-	}
-
-	/* failover_validation_command */
-	if (strncmp(orig_options->failover_validation_command, new_options.failover_validation_command, MAXPGPATH) != 0)
-	{
-		strncpy(orig_options->failover_validation_command, new_options.failover_validation_command, MAXPGPATH);
-		log_info(_("\"failover_validation_command\" is now \"%s\""), new_options.failover_validation_command);
-
-		config_changed = true;
-	}
-
 	/*
 	 * Handle changes to logging configuration
 	 */
@@ -1631,7 +1524,7 @@ repmgr_atoi(const char *value, const char *config_item, ItemList *error_list, in
  *
  * TODO: accept "any unambiguous prefix of one of these" as per postgresql.conf:
  *
- *   https://www.postgresql.org/docs/current/config-setting.html
+ *   https://www.postgresql.org/docs/current/static/config-setting.html
  */
 bool
 parse_bool(const char *s, const char *config_item, ItemList *error_list)

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -37,13 +37,6 @@ typedef enum
 	FAILOVER_AUTOMATIC
 } failover_mode_opt;
 
-typedef enum
-{
-	CHECK_PING,
-	CHECK_QUERY,
-	CHECK_CONNECTION
-} ConnectionCheckType;
-
 typedef struct EventNotificationListCell
 {
 	struct EventNotificationListCell *next;
@@ -113,7 +106,6 @@ typedef struct
 	/* standby switchover settings */
 	int			shutdown_check_timeout;
 	int			standby_reconnect_timeout;
-	int			wal_receive_check_timeout;
 
 	/* node rejoin settings */
 	int			node_rejoin_timeout;
@@ -142,12 +134,6 @@ typedef struct
 	int			primary_notification_timeout;
 	int			repmgrd_standby_startup_timeout;
 	char		repmgrd_pid_file[MAXPGPATH];
-	bool		standby_disconnect_on_failover;
-	int			sibling_nodes_disconnect_timeout;
-	ConnectionCheckType connection_check_type;
-	bool		primary_visibility_consensus;
-	char		failover_validation_command[MAXPGPATH];
-	int			election_rerun_interval;
 
 	/* BDR settings */
 	bool		bdr_local_monitoring_only;
@@ -155,18 +141,14 @@ typedef struct
 
 	/* service settings */
 	char		pg_ctl_options[MAXLEN];
-	char		service_start_command[MAXPGPATH];
-	char		service_stop_command[MAXPGPATH];
-	char		service_restart_command[MAXPGPATH];
-	char		service_reload_command[MAXPGPATH];
-	char		service_promote_command[MAXPGPATH];
-
-	/* repmgrd service settings */
-	char		repmgrd_service_start_command[MAXPGPATH];
-	char		repmgrd_service_stop_command[MAXPGPATH];
+	char		service_stop_command[MAXLEN];
+	char		service_start_command[MAXLEN];
+	char		service_restart_command[MAXLEN];
+	char		service_reload_command[MAXLEN];
+	char		service_promote_command[MAXLEN];
 
 	/* event notification settings */
-	char		event_notification_command[MAXPGPATH];
+	char		event_notification_command[MAXLEN];
 	char		event_notifications_orig[MAXLEN];
 	EventNotificationList event_notifications;
 
@@ -192,7 +174,7 @@ typedef struct
 		/* node information */ \
 		UNKNOWN_NODE_ID, "", "", "", "", "", "", "", REPLICATION_TYPE_PHYSICAL,	\
 		/* log settings */ \
-		"", "", "", DEFAULT_LOG_STATUS_INTERVAL, \
+		"", "", "", DEFAULT_LOG_STATUS_INTERVAL,	\
 		/* standby clone settings */ \
 		false, "", "", { NULL, NULL }, "", false, "", false, "", \
 		/* standby promote settings */ \
@@ -203,7 +185,6 @@ typedef struct
 		/* standby switchover settings */ \
 		DEFAULT_SHUTDOWN_CHECK_TIMEOUT, \
 		DEFAULT_STANDBY_RECONNECT_TIMEOUT, \
-		DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT, \
 		/* node rejoin settings */ \
 		DEFAULT_NODE_REJOIN_TIMEOUT, \
 		/* node check settings */ \
@@ -218,15 +199,12 @@ typedef struct
         DEFAULT_RECONNECTION_INTERVAL, \
         false, -1, \
 		DEFAULT_ASYNC_QUERY_TIMEOUT, \
-		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT, \
-		-1, "", false, DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT, \
-		CHECK_PING, true, "", DEFAULT_ELECTION_RERUN_INTERVAL, \
+		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT,	\
+		-1, "", \
 		/* BDR settings */ \
 		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
 		"", "", "", "", "", "", \
-		/* repmgrd service settings */ \
-		"", "",  \
 		/* event notification settings */ \
 		"", "", { NULL, NULL }, \
 		/* barman settings */ \

configure

@@ -1,8 +1,8 @@
 #! /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 4.2.
 #
-# Report bugs to <repmgr@googlegroups.com>.
+# Report bugs to <pgsql-bugs@postgresql.org>.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -11,7 +11,7 @@
 # This configure script is free software; the Free Software Foundation
 # gives unlimited permission to copy, distribute and modify it.
 #
-# Copyright (c) 2010-2019, 2ndQuadrant Ltd.
+# Copyright (c) 2010-2018, 2ndQuadrant Ltd.
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -269,7 +269,7 @@ fi
     $as_echo "$0: be upgraded to zsh 4.3.4 or later."
   else
     $as_echo "$0: Please tell bug-autoconf@gnu.org and
-$0: repmgr@googlegroups.com about your system, including
+$0: pgsql-bugs@postgresql.org about your system, including
 $0: any error possibly output before this message. Then
 $0: install a modern shell, or manually run the script
 $0: under such a shell if you do have one."
@@ -582,10 +582,10 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.3'
-PACKAGE_STRING='repmgr 4.3'
-PACKAGE_BUGREPORT='repmgr@googlegroups.com'
-PACKAGE_URL='https://repmgr.org/'
+PACKAGE_VERSION='4.2'
+PACKAGE_STRING='repmgr 4.2'
+PACKAGE_BUGREPORT='pgsql-bugs@postgresql.org'
+PACKAGE_URL='https://2ndquadrant.com/en/resources/repmgr/'
 
 ac_subst_vars='LTLIBOBJS
 LIBOBJS
@@ -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 4.2 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 4.2:";;
    esac
   cat <<\_ACEOF
 
@@ -1249,8 +1249,8 @@ Some influential environment variables:
 Use these variables to override the choices made by `configure' or to help
 it to find libraries and programs with nonstandard names/locations.
 
-Report bugs to <repmgr@googlegroups.com>.
-repmgr home page: <https://repmgr.org/>.
+Report bugs to <pgsql-bugs@postgresql.org>.
+repmgr home page: <https://2ndquadrant.com/en/resources/repmgr/>.
 _ACEOF
 ac_status=$?
 fi
@@ -1313,14 +1313,14 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.3
+repmgr configure 4.2
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
 This configure script is free software; the Free Software Foundation
 gives unlimited permission to copy, distribute and modify it.
 
-Copyright (c) 2010-2019, 2ndQuadrant Ltd.
+Copyright (c) 2010-2018, 2ndQuadrant Ltd.
 _ACEOF
   exit
 fi
@@ -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 4.2, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2359,7 +2359,7 @@ cat >>$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 4.2, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2415,14 +2415,14 @@ $config_files
 Configuration headers:
 $config_headers
 
-Report bugs to <repmgr@googlegroups.com>.
-repmgr home page: <https://repmgr.org/>."
+Report bugs to <pgsql-bugs@postgresql.org>.
+repmgr home page: <https://2ndquadrant.com/en/resources/repmgr/>."
 
 _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 4.2
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [4.3], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [4.2], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2018, 2ndQuadrant Ltd.])
 
 AC_CONFIG_HEADER(config.h)
 

controldata.c

@@ -1,12 +1,6 @@
 /*
- * controldata.c - functions for reading the pg_control file
- *
- * The functions provided here enable repmgr to read a pg_control file
- * in a version-indepent way, even if the PostgreSQL instance is not
- * running. For that reason we can't use on the pg_control_*() functions
- * provided in PostgreSQL 9.6 and later.
- *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * controldata.c
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -36,53 +30,6 @@
 
 static ControlFileInfo *get_controlfile(const char *DataDir);
 
-int
-get_pg_version(const char *data_directory, char *version_string)
-{
-	char		PgVersionPath[MAXPGPATH] = "";
-	FILE	   *fp = NULL;
-	char	   *endptr = NULL;
-	char		file_version_string[MAX_VERSION_STRING] = "";
-	long		file_major, file_minor;
-	int			ret;
-
-	snprintf(PgVersionPath, MAXPGPATH, "%s/PG_VERSION", data_directory);
-
-	fp = fopen(PgVersionPath, "r");
-
-	if (fp == NULL)
-	{
-		log_warning(_("could not open file \"%s\" for reading"),
-					PgVersionPath);
-		log_detail("%s", strerror(errno));
-		return UNKNOWN_SERVER_VERSION_NUM;
-	}
-
-	file_version_string[0] = '\0';
-
-	ret = fscanf(fp, "%23s", file_version_string);
-	fclose(fp);
-
-	if (ret != 1 || endptr == file_version_string)
-	{
-		log_warning(_("unable to determine major version number from PG_VERSION"));
-
-		return UNKNOWN_SERVER_VERSION_NUM;
-	}
-
-	file_major = strtol(file_version_string, &endptr, 10);
-	file_minor = 0;
-
-	if (*endptr == '.')
-		file_minor = strtol(endptr + 1, NULL, 10);
-
-	if (version_string != NULL)
-		strncpy(version_string, file_version_string, MAX_VERSION_STRING);
-
-	return ((int) file_major * 10000) + ((int) file_minor * 100);
-}
-
-
 uint64
 get_system_identifier(const char *data_directory)
 {
@@ -97,7 +44,6 @@ get_system_identifier(const char *data_directory)
 	return system_identifier;
 }
 
-
 DBState
 get_db_state(const char *data_directory)
 {
@@ -114,7 +60,7 @@ get_db_state(const char *data_directory)
 }
 
 
-XLogRecPtr
+extern XLogRecPtr
 get_latest_checkpoint_location(const char *data_directory)
 {
 	ControlFileInfo *control_file_info = NULL;
@@ -166,59 +112,10 @@ describe_db_state(DBState state)
 		case DB_IN_PRODUCTION:
 			return _("in production");
 	}
-
 	return _("unrecognized status code");
 }
 
 
-TimeLineID
-get_timeline(const char *data_directory)
-{
-	ControlFileInfo *control_file_info = NULL;
-	TimeLineID		 timeline = -1;
-
-	control_file_info = get_controlfile(data_directory);
-
-	timeline = (int) control_file_info->timeline;
-
-	pfree(control_file_info);
-
-	return timeline;
-}
-
-
-TimeLineID
-get_min_recovery_end_timeline(const char *data_directory)
-{
-	ControlFileInfo *control_file_info = NULL;
-	TimeLineID		 timeline = -1;
-
-	control_file_info = get_controlfile(data_directory);
-
-	timeline = (int) control_file_info->minRecoveryPointTLI;
-
-	pfree(control_file_info);
-
-	return timeline;
-}
-
-
-XLogRecPtr
-get_min_recovery_location(const char *data_directory)
-{
-	ControlFileInfo *control_file_info = NULL;
-	XLogRecPtr	minRecoveryPoint  = InvalidXLogRecPtr;
-
-	control_file_info = get_controlfile(data_directory);
-
-	minRecoveryPoint = control_file_info->minRecoveryPoint;
-
-	pfree(control_file_info);
-
-	return minRecoveryPoint;
-}
-
-
 /*
  * We maintain our own version of get_controlfile() as we need cross-version
  * compatibility, and also don't care if the file isn't readable.
@@ -226,10 +123,14 @@ get_min_recovery_location(const char *data_directory)
 static ControlFileInfo *
 get_controlfile(const char *DataDir)
 {
-	char		file_version_string[MAX_VERSION_STRING] = "";
 	ControlFileInfo *control_file_info;
-	int			fd, version_num;
+	FILE	   *fp = NULL;
+	int			fd, ret, version_num;
+	char		PgVersionPath[MAXPGPATH] = "";
 	char		ControlFilePath[MAXPGPATH] = "";
+	char		file_version_string[64] = "";
+	long		file_major, file_minor;
+	char	   *endptr = NULL;
 	void	   *ControlFileDataPtr = NULL;
 	int			expected_size = 0;
 
@@ -241,32 +142,50 @@ get_controlfile(const char *DataDir)
 	control_file_info->state = DB_SHUTDOWNED;
 	control_file_info->checkPoint = InvalidXLogRecPtr;
 	control_file_info->data_checksum_version = -1;
-	control_file_info->timeline = -1;
-	control_file_info->minRecoveryPointTLI = -1;
-	control_file_info->minRecoveryPoint = InvalidXLogRecPtr;
 
 	/*
 	 * Read PG_VERSION, as we'll need to determine which struct to read
 	 * the control file contents into
 	 */
+	snprintf(PgVersionPath, MAXPGPATH, "%s/PG_VERSION", DataDir);
 
-	version_num = get_pg_version(DataDir, file_version_string);
+	fp = fopen(PgVersionPath, "r");
 
-	if (version_num == UNKNOWN_SERVER_VERSION_NUM)
+	if (fp == NULL)
 	{
-		log_warning(_("unable to determine server version number from PG_VERSION"));
+		log_warning(_("could not open file \"%s\" for reading"),
+					PgVersionPath);
+		log_detail("%s", strerror(errno));
 		return control_file_info;
 	}
 
-	if (version_num < MIN_SUPPORTED_VERSION_NUM)
+	file_version_string[0] = '\0';
+
+	ret = fscanf(fp, "%63s", file_version_string);
+	fclose(fp);
+
+	if (ret != 1 || endptr == file_version_string)
 	{
-		log_warning(_("data directory appears to be initialised for %s"),
-					file_version_string);
-		log_detail(_("minimum supported PostgreSQL version is %s"),
-				   MIN_SUPPORTED_VERSION);
+		log_warning(_("unable to determine major version number from PG_VERSION"));
+
 		return control_file_info;
 	}
 
+	file_major = strtol(file_version_string, &endptr, 10);
+	file_minor = 0;
+
+	if (*endptr == '.')
+		file_minor = strtol(endptr + 1, NULL, 10);
+
+	version_num = ((int) file_major * 10000) + ((int) file_minor * 100);
+
+	if (version_num < 90300)
+	{
+		log_warning(_("Data directory appears to be initialised for %s"), file_version_string);
+		return control_file_info;
+	}
+
+
 	snprintf(ControlFilePath, MAXPGPATH, "%s/global/pg_control", DataDir);
 
 	if ((fd = open(ControlFilePath, O_RDONLY | PG_BINARY, 0)) == -1)
@@ -315,9 +234,6 @@ get_controlfile(const char *DataDir)
 		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 >= 90500)
 	{
@@ -326,9 +242,6 @@ get_controlfile(const char *DataDir)
 		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 >= 90400)
 	{
@@ -337,9 +250,6 @@ get_controlfile(const char *DataDir)
 		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 >= 90300)
 	{
@@ -348,9 +258,6 @@ get_controlfile(const char *DataDir)
 		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;
 	}
 
 	pfree(ControlFileDataPtr);
@@ -358,7 +265,9 @@ get_controlfile(const char *DataDir)
 	/*
 	 * We don't check the CRC here as we're potentially checking a pg_control
 	 * file from a different PostgreSQL version to the one repmgr was compiled
-	 * against.
+	 * against. However we're only interested in the first few fields, which
+	 * should be constant across supported versions
+	 *
 	 */
 
 	return control_file_info;

controldata.h

@@ -1,6 +1,6 @@
 /*
  * controldata.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -12,7 +12,6 @@
 #include "postgres_fe.h"
 #include "catalog/pg_control.h"
 
-#define MAX_VERSION_STRING 24
 /*
  * A simplified representation of pg_control containing only those fields
  * required by repmgr.
@@ -24,9 +23,6 @@ typedef struct
 	DBState		state;
 	XLogRecPtr	checkPoint;
 	uint32		data_checksum_version;
-	TimeLineID	timeline;
-	TimeLineID	minRecoveryPointTLI;
-	XLogRecPtr	minRecoveryPoint;
 } ControlFileInfo;
 
 
@@ -138,11 +134,13 @@ typedef struct ControlFileData93
 
 
 /*
- * Following field added since 9.3:
+ * Following fields added since 9.3:
  *
  * 	int			max_worker_processes;
+ *  int			max_prepared_xacts;
+ *  int			max_locks_per_xact;
+ *
  */
-
 typedef struct ControlFileData94
 {
 	uint64		system_identifier;
@@ -333,14 +331,11 @@ typedef struct ControlFileData11
 } ControlFileData11;
 
 
-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);
 extern int	get_data_checksum_version(const char *data_directory);
 extern uint64 get_system_identifier(const char *data_directory);
 extern XLogRecPtr get_latest_checkpoint_location(const char *data_directory);
-extern TimeLineID get_timeline(const char *data_directory);
-extern TimeLineID get_min_recovery_end_timeline(const char *data_directory);
-extern XLogRecPtr get_min_recovery_location(const char *data_directory);
 
 #endif							/* _CONTROLDATA_H_ */

dbutils.h

@@ -1,7 +1,7 @@
 /*
  * dbutils.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -20,7 +20,6 @@
 #ifndef _REPMGR_DBUTILS_H_
 #define _REPMGR_DBUTILS_H_
 
-#include "access/timeline.h"
 #include "access/xlogdefs.h"
 #include "pqexpbuffer.h"
 #include "portability/instr_time.h"
@@ -80,8 +79,7 @@ typedef enum
 	NODE_STATUS_UP,
 	NODE_STATUS_SHUTTING_DOWN,
 	NODE_STATUS_DOWN,
-	NODE_STATUS_UNCLEAN_SHUTDOWN,
-	NODE_STATUS_REJECTED
+	NODE_STATUS_UNCLEAN_SHUTDOWN
 } NodeStatus;
 
 typedef enum
@@ -113,16 +111,12 @@ typedef enum
 
 typedef struct s_extension_versions {
 	char		default_version[8];
-	int			default_version_num;
 	char		installed_version[8];
-	int			installed_version_num;
 } t_extension_versions;
 
 #define T_EXTENSION_VERSIONS_INITIALIZER { \
 	"", \
-	UNKNOWN_SERVER_VERSION_NUM, \
 	"", \
-	UNKNOWN_SERVER_VERSION_NUM \
 }
 
 /*
@@ -184,7 +178,7 @@ typedef struct s_node_info
 	MS_NORMAL, \
 	NULL, \
 	/* for ad-hoc use e.g. when working with a list of nodes */ \
-	"", true, true,	\
+	"", true, true \
 	/* various statistics */ \
 	-1, -1, -1, -1, -1, -1					\
 }
@@ -302,15 +296,22 @@ typedef struct BdrNodeInfoList
 typedef struct
 {
 	char		current_timestamp[MAXLEN];
-	XLogRecPtr	last_wal_receive_lsn;
-	XLogRecPtr	last_wal_replay_lsn;
+	uint64		last_wal_receive_lsn;
+	uint64		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;
 
+#define T_REPLINFO_INTIALIZER { \
+	"", \
+	InvalidXLogRecPtr, \
+	InvalidXLogRecPtr, \
+	"", \
+	0 \
+}
+
+
 typedef struct
 {
 	char		filepath[MAXPGPATH];
@@ -350,16 +351,16 @@ typedef struct RepmgrdInfo {
 	char pid_file[MAXLEN];
 	bool pg_running;
 	char pg_running_text[MAXLEN];
-	RecoveryType recovery_type;
 	bool running;
 	char repmgrd_running[MAXLEN];
 	bool paused;
-	bool wal_paused_pending_wal;
-	int  upstream_last_seen;
-	char upstream_last_seen_text[MAXLEN];
 } RepmgrdInfo;
 
 
+/* global variables */
+
+extern int	server_version_num;
+
 /* macros */
 
 #define is_streaming_replication(x) (x == PRIMARY || x == STANDBY)
@@ -400,7 +401,6 @@ void		param_set_ine(t_conninfo_param_list *param_list, const char *param, const
 char	   *param_get(t_conninfo_param_list *param_list, const char *param);
 bool		parse_conninfo_string(const char *conninfo_str, t_conninfo_param_list *param_list, char **errmsg, bool ignore_local_params);
 char	   *param_list_to_string(t_conninfo_param_list *param_list);
-char	   *normalize_conninfo_string(const char *conninfo_str);
 bool		has_passfile(void);
 
 
@@ -415,30 +415,22 @@ 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		alter_system_int(PGconn *conn, const char *name, int value);
-bool		pg_reload_conf(PGconn *conn);
 
 /* server information functions */
 bool		get_cluster_size(PGconn *conn, char *size);
-int			get_server_version(PGconn *conn, char *server_version_buf);
-
+int			get_server_version(PGconn *conn, char *server_version);
 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);
-TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
-
-/* repmgrd shared memory functions */
 bool		repmgrd_set_local_node_id(PGconn *conn, int local_node_id);
 int			repmgrd_get_local_node_id(PGconn *conn);
-bool		repmgrd_check_local_node_id(PGconn *conn);
 BackupState	server_in_exclusive_backup_mode(PGconn *conn);
 void		repmgrd_set_pid(PGconn *conn, pid_t repmgrd_pid, const char *pidfile);
 pid_t		repmgrd_get_pid(PGconn *conn);
 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);
 
 /* extension functions */
 ExtensionStatus get_repmgr_extension_status(PGconn *conn, t_extension_versions *extversions);
@@ -446,16 +438,13 @@ ExtensionStatus get_repmgr_extension_status(PGconn *conn, t_extension_versions *
 /* node management functions */
 void		checkpoint(PGconn *conn);
 bool		vacuum_table(PGconn *conn, const char *table);
-bool		promote_standby(PGconn *conn, bool wait, int wait_seconds);
-bool		resume_wal_replay(PGconn *conn);
+
 
 /* node record functions */
 t_server_type parse_node_type(const char *type);
 const char *get_node_type_string(t_server_type type);
 
 RecordStatus get_node_record(PGconn *conn, int node_id, t_node_info *node_info);
-RecordStatus refresh_node_record(PGconn *conn, int node_id, t_node_info *node_info);
-
 RecordStatus get_node_record_with_upstream(PGconn *conn, int node_id, t_node_info *node_info);
 
 RecordStatus get_node_record_by_name(PGconn *conn, const char *node_name, t_node_info *node_info);
@@ -502,7 +491,7 @@ PGresult   *get_event_records(PGconn *conn, int node_id, const char *node_name,
 
 /* replication slot functions */
 void		create_slot_name(char *slot_name, int node_id);
-bool		create_replication_slot(PGconn *conn, char *slot_name, PQExpBufferData *error_msg);
+bool		create_replication_slot(PGconn *conn, char *slot_name, int server_version_num, PQExpBufferData *error_msg);
 bool		drop_replication_slot(PGconn *conn, char *slot_name);
 RecordStatus get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record);
 int			get_free_replication_slot_count(PGconn *conn);
@@ -513,13 +502,12 @@ bool		get_tablespace_name_by_location(PGconn *conn, const char *location, char *
 
 /* asynchronous query functions */
 bool		cancel_query(PGconn *conn, int timeout);
-int			wait_connection_availability(PGconn *conn, int timeout);
+int			wait_connection_availability(PGconn *conn, long long timeout);
 
 /* node availability functions */
 bool		is_server_available(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);
 
 /* monitoring functions  */
 void
@@ -550,17 +538,12 @@ bool		get_new_primary(PGconn *conn, int *primary_node_id);
 void		reset_voting_status(PGconn *conn);
 
 /* replication status functions */
-XLogRecPtr	get_primary_current_lsn(PGconn *conn);
-XLogRecPtr	get_node_current_lsn(PGconn *conn);
+XLogRecPtr	get_current_wal_lsn(PGconn *conn);
 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);
+bool		get_replication_info(PGconn *conn, ReplInfo *replication_info);
 int			get_replication_lag_seconds(PGconn *conn);
-void		get_node_replication_stats(PGconn *conn, t_node_info *node_info);
+void		get_node_replication_stats(PGconn *conn, int server_version_num, t_node_info *node_info);
 bool		is_downstream_node_attached(PGconn *conn, char *node_name);
-void		set_upstream_last_seen(PGconn *conn);
-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 */
 int			get_bdr_version_num(void);

dirutil.c

@@ -3,7 +3,7 @@
  * dirmod.c
  *	  directory handling functions
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -50,7 +50,7 @@ typedef long pgpid_t;
  * and tablespace directories.
  */
 DataDirState
-check_dir(const char *path)
+check_dir(char *path)
 {
 	DIR		   *chkdir = NULL;
 	struct dirent *file = NULL;
@@ -91,17 +91,12 @@ check_dir(const char *path)
  * Create directory with error log message when failing
  */
 bool
-create_dir(const char *path)
+create_dir(char *path)
 {
-	char create_dir_path[MAXPGPATH];
-
-	/* mkdir_p() may modify the supplied path */
-	strncpy(create_dir_path, path, MAXPGPATH);
-
-	if (mkdir_p(create_dir_path, 0700) == 0)
+	if (mkdir_p(path, 0700) == 0)
 		return true;
 
-	log_error(_("unable to create directory \"%s\""), create_dir_path);
+	log_error(_("unable to create directory \"%s\""), path);
 	log_detail("%s", strerror(errno));
 
 	return false;
@@ -109,12 +104,13 @@ create_dir(const char *path)
 
 
 bool
-set_dir_permissions(const char *path)
+set_dir_permissions(char *path)
 {
 	return (chmod(path, 0700) != 0) ? false : true;
 }
 
 
+
 /* function from initdb.c */
 /* source adapted from FreeBSD /src/bin/mkdir/mkdir.c */
 
@@ -202,9 +198,9 @@ mkdir_p(char *path, mode_t omode)
 
 
 bool
-is_pg_dir(const char *path)
+is_pg_dir(char *path)
 {
-	char		dirpath[MAXPGPATH] = "";
+	char		dirpath[MAXPGPATH];
 	struct stat sb;
 
 	/* test pgdata */
@@ -227,7 +223,7 @@ is_pg_dir(const char *path)
  * any further useful progress can be made.
  */
 PgDirState
-is_pg_running(const char *path)
+is_pg_running(char *path)
 {
 	long		pid;
 	FILE	   *pidf;
@@ -295,7 +291,7 @@ is_pg_running(const char *path)
 
 
 bool
-create_pg_dir(const char *path, bool force)
+create_pg_dir(char *path, bool force)
 {
 	/* Check this directory can be used as a PGDATA dir */
 	switch (check_dir(path))
@@ -351,9 +347,8 @@ create_pg_dir(const char *path, bool force)
 			}
 			break;
 		case DIR_ERROR:
-			log_error(_("could not access directory \"%s\"")
-					  , path);
-			log_detail("%s", strerror(errno));
+			log_error(_("could not access directory \"%s\": %s"),
+					  path, strerror(errno));
 			return false;
 	}
 
@@ -363,7 +358,7 @@ create_pg_dir(const char *path, bool force)
 
 
 int
-rmdir_recursive(const char *path)
+rmdir_recursive(char *path)
 {
 	return nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
 }

dirutil.h

@@ -1,6 +1,6 @@
 /*
  * dirutil.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,13 +35,13 @@ typedef enum
 } PgDirState;
 
 extern int	mkdir_p(char *path, mode_t omode);
-extern bool set_dir_permissions(const char *path);
+extern bool set_dir_permissions(char *path);
 
-extern DataDirState	check_dir(const char *path);
-extern bool create_dir(const char *path);
-extern bool is_pg_dir(const char *path);
-extern PgDirState is_pg_running(const char *path);
-extern bool create_pg_dir(const char *path, bool force);
-extern int rmdir_recursive(const char *path);
+extern DataDirState	check_dir(char *path);
+extern bool create_dir(char *path);
+extern bool is_pg_dir(char *path);
+extern PgDirState is_pg_running(char *path);
+extern bool create_pg_dir(char *path, bool force);
+extern int rmdir_recursive(char *path);
 
 #endif

doc/Makefile.in

@@ -61,7 +61,7 @@ clean:
 
 maintainer-clean:
 	rm -rf html
-	rm -f Makefile
+	rm -rf Makefile
 
 zip: html
 	cp -r html repmgr-docs-$(REPMGR_VERSION)

doc/appendix-faq.sgml

@@ -76,7 +76,7 @@
    <para>
     Before PostgreSQL 10, hash indexes were not WAL logged and are therefore not suitable
     for use in streaming replication in PostgreSQL 9.6 and earlier. See the
-    <ulink url="https://www.postgresql.org/docs/9.6/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
+    <ulink url="https://www.postgresql.org/docs/9.6/static/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
     for details.
    </para>
    <para>
@@ -96,11 +96,12 @@
    <para>
      For <emphasis>major</emphasis> version upgrades (e.g. from PostgreSQL 9.6 to PostgreSQL 10),
      the traditional approach is to "reseed" a cluster by upgrading a single
-     node with <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade</ulink>
+     node with <ulink url="https://www.postgresql.org/docs/current/static/pgupgrade.html">pg_upgrade</ulink>
      and recloning standbys from this.
    </para>
    <para>
-     To minimize downtime during major upgrades from PostgreSQL 9.4 and later,
+     To minimize downtime during major upgrades, for more recent PostgreSQL
+     versions (PostgreSQL 9.4 and later),
      <ulink url="https://www.2ndquadrant.com/en/resources/pglogical/">pglogical</ulink>
      can be used to set up a parallel cluster using the newer PostgreSQL version,
      which can be kept in sync with the existing production cluster until the

doc/appendix-packages.sgml

@@ -293,7 +293,7 @@
             </row>
             <row>
               <entry>Repository documentation:</entry>
-              <entry><ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink></entry>
+              <entry><ulink url="https://wiki.postgresql.org/wiki/Apt)">https://wiki.postgresql.org/wiki/Apt)</ulink></entry>
             </row>
           </tbody>
         </tgroup>
@@ -456,21 +456,14 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
 
   <sect1 id="packages-old-versions" xreflabel="Installing old package versions">
     <title>Installing old package versions</title>
-
     <indexterm>
       <primary>old packages</primary>
     </indexterm>
-
     <indexterm>
       <primary>packages</primary>
       <secondary>old versions</secondary>
     </indexterm>
 
-    <indexterm>
-      <primary>installation</primary>
-      <secondary>old package versions</secondary>
-    </indexterm>
-
     <sect2 id="packages-old-versions-debian" xreflabel="old Debian package versions">
       <title>Debian/Ubuntu</title>
       <para>

doc/appendix-release-notes.sgml

@@ -15,263 +15,6 @@
     See also: <xref linkend="upgrading-repmgr">
   </para>
 
-  <sect1 id="release-4.3">
-    <title>Release 4.3</title>
-    <para><emphasis>Mar ???, 2019</emphasis></para>
-    <para>
-      &repmgr; 4.3 is a major release.
-    </para>
-
-	<important>
-	  <para>
-	    On Debian-based systems, including Ubuntu, if using <application>repmgrd</application>
-	    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>
-# additional options
-REPMGRD_OPTS="--daemonize=false"</programlisting>
-	  </para>
-	  <para>
-	    For further details, see <link linkend="repmgrd-configuration-debian-ubuntu">repmgrd configuration on Debian/Ubuntu</link>.
-	  </para>
-	</important>
-
-    <sect2>
-      <title>repmgr enhancements</title>
-      <para>
-        <itemizedlist>
-
-          <listitem>
-            <para>
-              <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>:
-              option <option>--upstream-node-id</option> can now be used to specify another standby
-              to follow.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>:
-              verify that it is actually possible to follow another node.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>:
-              verify that it is actually possible to attach the node to the current primary.
-            </para>
-          </listitem>
-
-          <listitem>
-            <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>.
-              GitHub #528.
-            </para>
-            <note>
-              <para>
-                These commands require the configuration file settings
-                <varname>repmgrd_service_start_command</varname> and <varname>repmgrd_service_stop_command</varname>
-                in <filename>repmgr.conf</filename> to be set.
-              </para>
-            </note>
-          </listitem>
-
-          <listitem>
-            <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.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              Add <option>--compact</option> option to <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command> (GitHub #521).
-            </para>
-            <para>
-              This makes it easier to copy the output into emails, chats etc. as a compact table.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>:
-	      differentiate between unreachable nodes and nodes which are running but rejecting connections.
-            </para>
-            <para>
-	      This makes it possible to see whether a node is unreachable at network level,
-	      or if it is running but rejecting connections for some reason.
-            </para>
-          </listitem>
-
-
-          <listitem>
-            <para>
-              Add <option>--dry-run</option> to <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command> (GitHub #522).
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <command>repmgr --version-number</command> outputs the &quot;raw&quot;
-              repmgr version number (e.g. <literal>40300</literal>). This is intended
-              for use by scripts etc. requiring an easily parseable representation
-              of the &repmgr; version.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <link linkend="repmgr-node-check"><command>repmgr node check --data-directory-config</command></link>
-              option added; this is to confirm &repmgr; is correctly configured. GitHub #523.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              Add check to <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>
-              to ensure the data directory on the demotion candidate is configured correctly in <filename>repmgr.conf</filename>.
-              This is to ensure that &repmgr;, when remotely executed on the demotion candidate, can correctly verify
-              that PostgreSQL on the demotion candidate was shut down cleanly. GitHub #523.
-            </para>
-          </listitem>
-
-
-       </itemizedlist>
-      </para>
-    </sect2>
-
-    <sect2>
-      <title>repmgrd enhancements</title>
-      <para>
-        <itemizedlist>
-
-          <listitem>
-            <para>
-              <application>repmgrd</application> will no longer consider nodes where <application>repmgrd</application>
-	      is not running as promotion candidates.
-            </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.
-            </para>
-            <para>
-              Possible values are <literal>ping</literal> (default; uses <command>PQping()</command> to
-              determine server availability), <literal>connection</literal> (attempst to make a new connection to
-              the upstream node), and <literal>query</literal> (determines server availability
-              by executing an SQL statement on the node via the existing connection).
-            </para>
-          </listitem>
-
-          <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>.
-            </para>
-          </listitem>
-
-         <listitem>
-            <para>
-              New configuration option <link linkend="repmgrd-standby-disconnection-on-failover"><option>standby_disconnect_on_failover</option></link>
-              to force standbys to disconnect their WAL receivers before making a failover decision.
-            </para>
-          </listitem>
-
-		</itemizedlist>
-	  </para>
-	</sect2>
-
-    <sect2>
-      <title>Bug fixes</title>
-      <para>
-        <itemizedlist>
-
-          <listitem>
-            <para>
-              &repmgr;: when executing <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
-              prevent escaping issues with connection URIs when executing <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
-              on the demotion candidate. GitHub #525.
-            </para>
-          </listitem>
-
-          <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.
-            </para>
-          </listitem>
-
-         <listitem>
-            <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.
-            </para>
-          </listitem>
-
-          <listitem>
-            <para>
-              <application>repmgrd</application>: on a cascaded standby, don't fail over if
-              <literal>failover=manual</literal>. GitHub #531.
-            </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>
-
-        </itemizedlist>
-      </para>
-    </sect2>
-
-  </sect1>
-
   <sect1 id="release-4.2">
     <title>Release 4.2</title>
     <para><emphasis>Wed October 24, 2018</emphasis></para>
@@ -288,20 +31,6 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       <link linkend="upgrading-major-version">Upgrading a major version release</link>.
     </para>
 
-	<important>
-	  <para>
-	    On Debian-based systems, including Ubuntu, if using <application>repmgrd</application>
-	    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>
-# additional options
-REPMGRD_OPTS="--daemonize=false"</programlisting>
-	  </para>
-	  <para>
-	    For further details, see <link linkend="repmgrd-configuration-debian-ubuntu">repmgrd daemon configuration on Debian/Ubuntu</link>.
-	  </para>
-	</important>
-
     <sect2>
       <title>Configuration file changes</title>
       <para>
@@ -414,6 +143,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             </para>
           </listitem>
 
+
           <listitem>
             <para>
               <application>repmgrd</application>: fix parsing of <option>-d/--daemonize</option> option.
@@ -1542,7 +1272,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             <emphasis>easier upgrades</emphasis>: &repmgr; is now implemented as a native
             PostgreSQL extension, which means future upgrades can be carried out by
             installing the upgraded package and issuing
-            <ulink url="https://www.postgresql.org/docs/current/sql-alterextension.html">ALTER EXTENSION repmgr UPDATE</ulink>.
+            <ulink url="https://www.postgresql.org/docs/current/static/sql-alterextension.html">ALTER EXTENSION repmgr UPDATE</ulink>.
           </para>
         </listitem>
 

doc/appendix-support.sgml

@@ -1,96 +0,0 @@
-<appendix id="appendix-support" xreflabel="repmgr support">
-  <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
-    products, including configuration assistance, installation
-    verification and training for running a robust replication cluster.
-  </para>
-  <para>
-    For further details see: <ulink url="https://2ndquadrant.com/en/support/">https://2ndquadrant.com/en/support/</ulink>
-  </para>
-
-  <para>
-    A mailing list/forum is provided via Google groups to discuss contributions or issues: <ulink url="https://groups.google.com/group/repmgr">https://groups.google.com/group/repmgr</ulink>.
-  </para>
-  <para>
-    Please report bugs and other issues to: <ulink url="https://github.com/2ndQuadrant/repmgr">https://github.com/2ndQuadrant/repmgr</ulink>.
-  </para>
-
-  <important>
-    <para>
-      Please read the <link linkend="appendix-support-reporting-issues">following section</link> before submitting questions or issue reports.
-    </para>
-  </important>
-
-  <sect1 id="appendix-support-reporting-issues" xreflabel="Reportins Issues">
-    <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:
-
-    <itemizedlist spacing="compact" mark="bullet">
-
-     <listitem>
-      <simpara>
-        &repmgr; version
-      </simpara>
-     </listitem>
-
-     <listitem>
-      <simpara>
-        How was &repmgr installed? From source? From packages? If
-        so from which repository?
-      </simpara>
-     </listitem>
-
-     <listitem>
-      <simpara>
-        <filename>repmpgr.conf</filename> files (suitably anonymized if necessary)
-      </simpara>
-     </listitem>
-
-     <listitem>
-      <simpara>
-        Contents of the <literal>repmgr.nodes</literal> table (suitably anonymized if necessary)
-      </simpara>
-     </listitem>
-
-     <listitem>
-      <simpara>
-        PostgreSQL version
-      </simpara>
-     </listitem>
-
-    </itemizedlist>
-    </para>
-    <para>
-      If issues are encountered with a &repmgr; client command, please provide
-      the output of that command executed with the options
-      <option>-LDEBUG --verbose</option>, which will ensure &repmgr; emits
-      the maximum level of logging output.
-    </para>
-    <para>
-      If issues are encountered with <application>repmgrd</application>,
-      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.
-    </para>
-    <para>
-      In all cases it is <emphasis>extremely</emphasis> useful to receive
-      information on how to reliably reproduce an issue with as much detail as
-      possible.
-    </para>
-
-  </sect1>
-
-</appendix>

doc/cloning-standbys.sgml

@@ -262,7 +262,7 @@
     meaning replication changes "cascade" down through a hierarchy of servers. This
     can be used to reduce load on the primary and minimize bandwith usage between
     sites. For more details, see the
-    <ulink url="https://www.postgresql.org/docs/current/warm-standby.html#CASCADING-REPLICATION">
+    <ulink url="https://www.postgresql.org/docs/current/static/warm-standby.html#CASCADING-REPLICATION">
     PostgreSQL cascading replication documentation</ulink>.
    </para>
    <para>
@@ -391,7 +391,7 @@
       a symlink will automatically be created from the main data directory.
     </para>
     <para>
-     See the <ulink url="https://www.postgresql.org/docs/current/app-pgbasebackup.html">PostgreSQL pg_basebackup documentation</ulink>
+     See the <ulink url="https://www.postgresql.org/docs/current/static/app-pgbasebackup.html">PostgreSQL pg_basebackup documentation</ulink>
      for more details of available options.
     </para>
    </sect2>
@@ -413,7 +413,7 @@
      user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
      environment variable <varname>PGPASSWORD</varname>, however this is not recommended for
      security reasons. For more details see the
-     <ulink url="https://www.postgresql.org/docs/current/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
+     <ulink url="https://www.postgresql.org/docs/current/static/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
     </para>
 
     <note>

doc/configuration-file-required-settings.sgml

@@ -56,7 +56,7 @@
      </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/static/libpq-connect.html#LIBPQ-CONNSTRING">Connection Strings</>
         in the PosgreSQL documentation.
      </para>
      <para>
@@ -64,7 +64,7 @@
         <varname>connect_timeout</varname> in the <varname>conninfo</varname>
         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">
+        url="https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT">
         the PostgreSQL documentation</>.
      </para>
     </listitem>

doc/configuration-file.sgml

@@ -36,9 +36,9 @@
     </para>
     <para>
       Whitespace is insignificant (except within a quoted parameter value) and blank lines are ignored.
-      Hash marks (<literal>#</literal>) designate the remainder of the line as a comment.
-      Parameter values that are not simple identifiers or numbers should be single-quoted.
-      Note that single quote cannot be embedded in a parameter value.
+      Hash marks (#) designate the remainder of the line as a comment. Parameter values that are not simple
+      identifiers or numbers should be single-quoted. Note that single quote can not be embedded
+      in a parameter value.
     </para>
     <important>
       <para>

doc/configuring-witness-server.sgml

@@ -1,6 +1,7 @@
 <chapter id="using-witness-server">
  <indexterm>
   <primary>witness server</primary>
+  <seealso>Using a witness server with repmgrd</seealso>
  </indexterm>
 
 
@@ -8,9 +9,8 @@
  <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.
+   failover situation occurs, to provide proof that the primary server
+   itself is unavailable.
  </para>
 
  <para>
@@ -20,7 +20,7 @@
    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,
+   and it should not promote itself. If it can seen 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).
@@ -53,7 +53,7 @@
    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,
+   This instance should *not* 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>

doc/event-notifications.sgml

@@ -88,7 +88,7 @@
 
  <para>
   The values provided for <literal>%t</literal> and <literal>%d</literal>
-  may contain spaces, so should be quoted in the provided command
+  will probably 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"'

doc/filelist.sgml

@@ -50,10 +50,15 @@
 <!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-demonstration SYSTEM "repmgrd-demonstration.sgml">
+<!ENTITY repmgrd-monitoring SYSTEM "repmgrd-monitoring.sgml">
+<!ENTITY repmgrd-degraded-monitoring SYSTEM "repmgrd-degraded-monitoring.sgml">
+<!ENTITY repmgrd-cascading-replication SYSTEM "repmgrd-cascading-replication.sgml">
+<!ENTITY repmgrd-network-split SYSTEM "repmgrd-network-split.sgml">
+<!ENTITY repmgrd-witness-server SYSTEM "repmgrd-witness-server.sgml">
+<!ENTITY repmgrd-pausing SYSTEM "repmgrd-pausing.sgml">
 <!ENTITY repmgrd-bdr SYSTEM "repmgrd-bdr.sgml">
 
 <!ENTITY repmgr-primary-register SYSTEM "repmgr-primary-register.sgml">
@@ -76,8 +81,6 @@
 <!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">
 
@@ -85,7 +88,6 @@
 <!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/follow-new-primary.sgml

@@ -15,7 +15,7 @@
   end of the preceding section (<xref linkend="promoting-standby">),
   execute this:
   <programlisting>
-    $ repmgr -f /etc/repmgr.conf standby follow
+    $ repmgr -f /etc/repmgr.conf repmgr standby follow
     INFO: changing node 3's primary to node 2
     NOTICE: restarting server using "pg_ctl -l /var/log/postgresql/startup.log -w -D '/var/lib/postgresql/data' restart"
     waiting for server to shut down......... done

doc/install-packages.sgml

@@ -1,11 +1,5 @@
 <sect1 id="installation-packages" xreflabel="Installing from packages">
  <title>Installing &repmgr; from packages</title>
-
-  <indexterm>
-   <primary>installation</primary>
-   <secondary>from packages</secondary>
-  </indexterm>
-
  <para>
   We recommend installing &repmgr; using the available packages for your
   system.
@@ -166,17 +160,7 @@ yum search repmgr</programlisting>
       <programlisting>
         [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
     </para>
-
-    <para>
-      <emphasis>Installing old packages</emphasis>
-    </para>
-    <para>
-      See appendix <link linkend="packages-old-versions-rhel-centos">Installing old package versions</link>
-      for details on how to retrieve older package versions.
-    </para>
-
   </sect3>
-
  </sect2>
 
  <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
@@ -240,6 +224,7 @@ curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlist
           </note>
         </listitem>
 
+
 	<listitem>
 	  <para>
             Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
@@ -259,15 +244,6 @@ sudo apt-get install postgresql-10-repmgr</programlisting>
 
     </para>
 
-    <para>
-      <emphasis>Installing old packages</emphasis>
-    </para>
-    <para>
-      See appendix <link linkend="packages-old-versions-debian">Installing old package versions</link>
-      for details on how to retrieve older package versions.
-    </para>
-
-
   </sect3>
  </sect2>
 

doc/install-source.sgml

@@ -12,8 +12,8 @@
    To install &repmgr; the prerequisites for compiling
    &postgres; must be installed. These are described in &postgres;'s
    documentation
-   on <ulink url="https://www.postgresql.org/docs/current/install-requirements.html">build requirements</ulink>
-   and <ulink url="https://www.postgresql.org/docs/current/docguide-toolsets.html">build requirements for documentation</ulink>.
+   on <ulink url="https://www.postgresql.org/docs/current/static/install-requirements.html">build requirements</ulink>
+   and <ulink url="https://www.postgresql.org/docs/current/static/docguide-toolsets.html">build requirements for documentation</ulink>.
   </para>
 
   <para>
@@ -232,7 +232,7 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
     The &repmgr; documentation is (like the main PostgreSQL project)
     written in DocBook 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">
+    <ulink url="https://www.postgresql.org/docs/9.6/static/docguide-toolsets.html">
       PostgreSQL documentation</ulink> then execute:
    <programlisting>
     ./configure && make install-doc</programlisting>

doc/legal.sgml

@@ -3,7 +3,7 @@
 <date>2017</date>
 
 <copyright>
- <year>2010-2019</year>
+ <year>2010-2018</year>
  <holder>2ndQuadrant, Ltd.</holder>
 </copyright>
 
@@ -11,7 +11,7 @@
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2019
+  <productname>repmgr</productname> is Copyright &copy; 2010-2018
   by 2ndQuadrant, Ltd. All rights reserved.
  </para>
 

doc/quickstart.sgml

@@ -97,7 +97,7 @@
     #  PostgreSQL 9.6 and later: one of 'replica' or 'logical'
     #    ('hot_standby' will still be accepted as an alias for 'replica')
     #
-    # See: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-WAL-LEVEL
+    # See: https://www.postgresql.org/docs/current/static/runtime-config-wal.html#GUC-WAL-LEVEL
 
     wal_level = 'hot_standby'
 
@@ -224,7 +224,7 @@
   <note>
    <para>
     &repmgr; stores connection information as <ulink
-    url="https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING">libpq
+    url="https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING">libpq
     connection strings</ulink> throughout. This documentation refers to them as <literal>conninfo</literal>
     strings; an alternative name is <literal>DSN</literal> (<literal>data source name</literal>).
     We'll use these in place of the <command>-h hostname -d databasename -U username</command> syntax.
@@ -446,7 +446,7 @@
   </para>
   <para>
     From PostgreSQL 9.6 you can also use the view
-    <ulink url="https://www.postgresql.org/docs/current/monitoring-stats.html#PG-STAT-WAL-RECEIVER-VIEW">
+    <ulink url="https://www.postgresql.org/docs/current/static/monitoring-stats.html#PG-STAT-WAL-RECEIVER-VIEW">
     <literal>pg_stat_wal_receiver</literal></ulink> to check the replication status from the standby.
 
    <programlisting>

doc/repmgr-cluster-crosscheck.sgml

@@ -42,7 +42,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr cluster crosscheck</command>:
+      Following exit codes can be emitted by <command>repmgr cluster crosscheck</command>:
     </para>
     <variablelist>
 

doc/repmgr-cluster-matrix.sgml

@@ -102,7 +102,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr cluster matrix</command>:
+      Following exit codes can be emitted by <command>repmgr cluster matrix</command>:
     </para>
     <variablelist>
 

doc/repmgr-cluster-show.sgml

@@ -22,14 +22,6 @@
       directly and can be run on any node in the cluster; this is also useful when analyzing
       connectivity from a particular node.
     </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
-      better overviews of connections between nodes.
-    </para>
-
   </refsect1>
 
   <refsect1>
@@ -52,59 +44,39 @@
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
 
-     ID | Name  | Role    | Status    | Upstream | Location | Priority | 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>
+     ID | Name  | Role    | Status    | Upstream | Location | Connection string
+    ----+-------+---------+-----------+----------+----------+-----------------------------------------
+     1  | node1 | primary | * running |          | default  | host=db_node1 dbname=repmgr user=repmgr
+     2  | node2 | standby |   running | node1    | default  | host=db_node2 dbname=repmgr user=repmgr
+     3  | node3 | standby |   running | node1    | default  | host=db_node3 dbname=repmgr user=repmgr</programlisting>
   </para>
   </refsect1>
   <refsect1>
     <title>Notes</title>
     <para>
       The column <literal>Role</literal> shows the expected server role according to the
-      &repmgr; metadata.
-	</para>
-	<para>
-	  <literal>Status</literal> shows whether the server is running or unreachable.
+      &repmgr; metadata. <literal>Status</literal> shows whether the server is running or unreachable.
       If the node has an unexpected role not reflected in the &repmgr; metadata, e.g. a node was manually
-      promoted to primary, this will be highlighted with an exclamation mark.
-	  If a connection to the node cannot be made, this will be highlighted with a question mark.
-	  Note that the node will only be shown as <literal>? unreachable</literal>
-	  if a connection is not possible at network level; if the PostgreSQL instance on the
-	  node is pingable but not accepting connections, it will be shown as <literal>? running</literal>.
-	</para>
-	<para>
-	  In the following example, executed on <literal>node3</literal>, <literal>node1</literal> is not reachable
-	  at network level and assumed to be down; <literal>node2</literal> has been promoted to primary
-	  (but <literal>node3</literal> is not attached to it, and its metadata has not yet been updated);
-	  <literal>node4</literal> is running but rejecting connections (from <literal>node3</literal> at least).
+      promoted to primary, this will be highlighted with an exclamation mark, e.g.:
       <programlisting>
-	 ID | Name  | Role    | Status               | Upstream | Location | Priority | Connection string
-	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
-	 1  | node1 | primary | ? unreachable        |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
-	 2  | node2 | standby | ! running as primary | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
-	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
-	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
+    $ repmgr -f /etc/repmgr.conf cluster show
 
-	WARNING: following issues were detected
-	  - unable to connect to node "node1" (ID: 1)
-	  - node "node1" (ID: 1) is registered as an active primary but is unreachable
-	  - node "node2" (ID: 2) is registered as standby but running as primary
-	  - unable to connect to node "node4" (ID: 4)
-    HINT: execute with --verbose option to see connection error messages</programlisting>
+     ID | Name  | Role    | Status               | Upstream | Location | Connection string
+    ----+-------+---------+----------------------+----------+----------+-----------------------------------------
+     1  | node1 | primary | ? unreachable        |          | default  | host=db_node1 dbname=repmgr user=repmgr
+     2  | node2 | standby | ! running as primary | node1    | default  | host=db_node2 dbname=repmgr user=repmgr
+     3  | node3 | standby |   running            | node1    | default  | host=db_node3 dbname=repmgr user=repmgr
+
+    WARNING: following issues were detected
+      node "node1" (ID: 1) is registered as an active primary but is unreachable
+      node "node2" (ID: 2) is registered as standby but running as primary</programlisting>
+    </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
+          a better overviews of connections between nodes.
     </para>
-	<para>
-	  To diagnose connection issues, execute <command>repmgr cluster show</command>
-	  with the <option>--verbose</option> option; this will display the error message
-	  for each failed connection attempt.
-	</para>
-	<tip>
-	  <para>
-		Use <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck">
-		to diagnose connection issues across the whole replication cluster.
-	  </para>
-	</tip>
   </refsect1>
 
   <refsect1>
@@ -115,56 +87,38 @@
       <varlistentry>
         <term><option>--csv</option></term>
         <listitem>
-	  <para>
-	    <command>repmgr cluster show</command> accepts an optional parameter <literal>--csv</literal>, which
-	    outputs the replication cluster's status in a simple CSV format, suitable for
-	    parsing by scripts, e.g.:
-	    <programlisting>
+		  <para>
+			<command>repmgr cluster show</command> accepts an optional parameter <literal>--csv</literal>, which
+			outputs the replication cluster's status in a simple CSV format, suitable for
+			parsing by scripts, e.g.:
+			<programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show --csv
     1,-1,-1
     2,0,0
     3,0,1</programlisting>
-	  </para>
-	  <para>
-	    The columns have following meanings:
-	    <itemizedlist spacing="compact" mark="bullet">
-	      <listitem>
-		<simpara>
-		  node ID
-		</simpara>
-	      </listitem>
-	      <listitem>
-		<simpara>
+		  </para>
+		  <para>
+			The columns have following meanings:
+			<itemizedlist spacing="compact" mark="bullet">
+			  <listitem>
+				<simpara>
+				  node ID
+				</simpara>
+			  </listitem>
+			  <listitem>
+				<simpara>
             availability (0 = available, -1 = unavailable)
-		</simpara>
-	      </listitem>
-	      <listitem>
-		<simpara>
-            recovery state (0 = not in recovery, 1 = in recovery, -1 = unknown)
-		</simpara>
-	      </listitem>
-	    </itemizedlist>
-	  </para>
-	</listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>--compact</option></term>
-        <listitem>
-          <para>
-			Suppress display of the <literal>conninfo</literal> column.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>--terse</option></term>
-        <listitem>
-          <para>
-			Suppress warnings about connection issues.
-          </para>
-        </listitem>
-      </varlistentry>
+				</simpara>
+			  </listitem>
+			  <listitem>
+				<simpara>
+				  recovery state (0 = not in recovery, 1 = in recovery, -1 = unknown)
+				</simpara>
+			  </listitem>
+			</itemizedlist>
+		  </para>
+		</listitem>
+	  </varlistentry>
 
       <varlistentry>
         <term><option>--verbose</option></term>
@@ -183,7 +137,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr cluster show</command>:
+      Following exit codes can be emitted by <command>repmgr cluster show</command>:
     </para>
     <variablelist>
 

doc/repmgr-daemon-pause.sgml

@@ -3,11 +3,6 @@
     <primary>repmgr daemon pause</primary>
   </indexterm>
 
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>pausing</secondary>
-  </indexterm>
-
   <refmeta>
     <refentrytitle>repmgr daemon pause</refentrytitle>
   </refmeta>
@@ -79,7 +74,7 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
+      Following exit codes can be emitted by <command>repmgr daemon unpause</command>:
     </para>
     <variablelist>
 

doc/repmgr-daemon-start.sgml

@@ -1,203 +0,0 @@
-<refentry id="repmgr-daemon-start">
-  <indexterm>
-    <primary>repmgr daemon start</primary>
-  </indexterm>
-
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>starting</secondary>
-  </indexterm>
-
-  <refmeta>
-    <refentrytitle>repmgr daemon start</refentrytitle>
-  </refmeta>
-
-  <refnamediv>
-    <refname>repmgr daemon start</refname>
-    <refpurpose>Start the <application>repmgrd</application> daemon</refpurpose>
-  </refnamediv>
-
-  <refsect1>
-    <title>Description</title>
-    <para>
-      This command starts the <application>repmgrd</application> daemon on the
-      local node.
-    </para>
-    <para>
-      By default, &repmgr; will wait for up to 15 seconds to confirm that <application>repmgrd</application>
-      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>
-
-    <important>
-      <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.
-      </para>
-    </important>
-  </refsect1>
-
-
-
-  <refsect1>
-
-    <title>Options</title>
-
-    <variablelist>
-
-      <varlistentry>
-        <term><option>--dry-run</option></term>
-        <listitem>
-          <para>
-            Check prerequisites but don't actually attempt to start <application>repmgrd</application>.
-          </para>
-          <para>
-            This action will output the command which would be executed.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>-w</option></term>
-        <term><option>--wait</option></term>
-        <listitem>
-          <para>
-            Wait for the specified number of seconds to confirm that <application>repmgrd</application>
-            started successfully.
-          </para>
-          <para>
-            Note that providing <option>--wait=0</option> is the equivalent of <option>--no-wait</option>.
-          </para>
-
-         </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>--no-wait</option></term>
-        <listitem>
-          <para>
-            Don't wait to confirm that <application>repmgrd</application>
-            started successfully.
-          </para>
-          <para>
-            This is equivalent to providing <option>--wait=0</option>.
-          </para>
-         </listitem>
-      </varlistentry>
-
-    </variablelist>
-  </refsect1>
-
-  <refsect1 id="repmgr-daemon-start-configuration" xreflabel="repmgr daemon start configuration">
-    <title>Configuration file settings</title>
-    <para>
-     The following parameter in <filename>repmgr.conf</filename> is relevant
-     to <command>repmgr daemon start</command>:
-    </para>
-
-    <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>
-          <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>;
-            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>
-          <important>
-            <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>
-              service; this is particularly the case with <literal>systemd</literal>.
-            </para>
-          </important>
-        </listitem>
-      </varlistentry>
-    </variablelist>
-
-  </refsect1>
-
-
-  <refsect1>
-    <title>Exit codes</title>
-    <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon start</command>:
-    </para>
-    <variablelist>
-
-      <varlistentry>
-        <term><option>SUCCESS (0)</option></term>
-        <listitem>
-          <para>
-            The <application>repmgrd</application> 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.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_BAD_CONFIG (1)</option></term>
-        <listitem>
-          <para>
-            <varname>repmgrd_service_start_command</varname> is not defined in
-            <filename>repmgr.conf</filename>.
-          </para>
-        </listitem>
-      </varlistentry>
-
-
-      <varlistentry>
-        <term><option>ERR_DB_CONN (6)</option></term>
-        <listitem>
-          <para>
-            &repmgr; was unable to connect to the local PostgreSQL node.
-          </para>
-          <para>
-            PostgreSQL must be running before <application>repmgrd</application>
-            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>.
-          </para>
-        </listitem>
-      </varlistentry>
-
-
-      <varlistentry>
-        <term><option>ERR_REPMGRD_SERVICE (27)</option></term>
-        <listitem>
-          <para>
-            The <application>repmgrd</application> 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>
-            successfully started (unless the <option>--no-wait</option> option was provided).
-          </para>
-        </listitem>
-      </varlistentry>
-
-    </variablelist>
-  </refsect1>
-
-  <refsect1>
-    <title>See also</title>
-    <para>
-      <xref linkend="repmgr-daemon-stop">, <xref linkend="repmgr-daemon-status">, <xref linkend="repmgrd-daemon">
-    </para>
-  </refsect1>
-
-</refentry>

doc/repmgr-daemon-status.sgml

@@ -3,11 +3,6 @@
     <primary>repmgr daemon status</primary>
   </indexterm>
 
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>displaying daemon status</secondary>
-  </indexterm>
-
   <refmeta>
     <refentrytitle>repmgr daemon status</refentrytitle>
   </refmeta>
@@ -33,10 +28,7 @@
       <command>repmgr daemon status</command> can be executed on any active node in the
       replication cluster. A valid <filename>repmgr.conf</filename> file is required.
     </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.
-    </para>
+
     <note>
       <para>
         After restarting PostgreSQL on any node, the <application>repmgrd</application> instance
@@ -52,34 +44,33 @@
     <para>
       <application>repmgrd</application> 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  | repmgrd | PID  | Paused?
+----+-------+---------+---------+---------+------+---------
+ 1  | node1 | primary | running | running | 7851 | no
+ 2  | node2 | standby | running | running | 7889 | no
+ 3  | node3 | standby | running | running | 7918 | no</programlisting>
     </para>
 
     <para>
       <application>repmgrd</application> 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  | repmgrd | PID  | Paused?
+----+-------+---------+---------+---------+------+---------
+ 1  | node1 | primary | running | running | 7851 | yes
+ 2  | node2 | standby | running | running | 7889 | yes
+ 3  | node3 | standby | running | running | 7918 | yes</programlisting>
     </para>
 
     <para>
       <application>repmgrd</application> 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  | repmgrd     | PID  | Paused?
+----+-------+---------+---------+-------------+------+---------
+ 1  | node1 | primary | running | running     | 7851 | yes
+ 2  | node2 | standby | running | not running | n/a  | n/a
+ 3  | node3 | standby | running | running     | 7918 | yes</programlisting>
     </para>
+
   </refsect1>
 
   <refsect1>
@@ -90,88 +81,76 @@
       <varlistentry>
         <term><option>--csv</option></term>
         <listitem>
-          <para>
-            <command>repmgr daemon status</command> accepts an optional parameter <literal>--csv</literal>, which
-            outputs the replication cluster's status in a simple CSV format, suitable for
-            parsing by scripts, e.g.:
-            <programlisting>
+		  <para>
+			<command>repmgr daemon status</command> accepts an optional parameter <literal>--csv</literal>, which
+			outputs the replication cluster's status in a simple CSV format, suitable for
+			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>
-          </para>
-          <para>
-            The columns have following meanings:
-            <itemizedlist spacing="compact" mark="bullet">
-              <listitem>
-                <simpara>
-                  node ID
-                </simpara>
-              </listitem>
+    1,node1,primary,1,1,10204,1
+    2,node2,standby,1,0,-1,1
+    3,node3,standby,1,1,10225,1</programlisting>
+		  </para>
+		  <para>
+			The columns have following meanings:
+			<itemizedlist spacing="compact" mark="bullet">
+			  <listitem>
+				<simpara>
+				  node ID
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
+			  <listitem>
+				<simpara>
                   node name
-                </simpara>
-              </listitem>
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
+			  <listitem>
+				<simpara>
                   node type (primary or standby)
-                </simpara>
-              </listitem>
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
-                  PostgreSQL server running (1 = running, 0 = not running)
-                </simpara>
-              </listitem>
+			  <listitem>
+				<simpara>
+                  PostgreSQL server running
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
-                  <application>repmgrd</application> running (1 = running, 0 = not running, -1 = unknown)
-                </simpara>
-              </listitem>
+			  <listitem>
+				<simpara>
+                  <application>repmgrd</application> running (1 = running, 0 = not running)
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
-                  <application>repmgrd</application> PID (-1 if not running or status unknown)
-                </simpara>
-              </listitem>
+			  <listitem>
+				<simpara>
+                  <application>repmgrd</application> PID (-1 if not running)
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
-                  <application>repmgrd</application> paused (1 = paused, 0 = not paused, -1 = unknown)
-                </simpara>
-              </listitem>
+			  <listitem>
+				<simpara>
+                  <application>repmgrd</application> paused (1 = paused, 0 = not paused)
+				</simpara>
+			  </listitem>
 
-              <listitem>
-                <simpara>
-                  <application>repmgrd</application> node priority
-                </simpara>
-              </listitem>
-
-              <listitem>
-                <simpara>
-                  interval in seconds since the node's upstream was last seen (this will be -1 if the value could not be retrieved, or the node is primary)
-                </simpara>
-              </listitem>
-
-            </itemizedlist>
-          </para>
-        </listitem>
-      </varlistentry>
+			</itemizedlist>
+		  </para>
+		</listitem>
+	  </varlistentry>
 
       <varlistentry>
         <term><option>--verbose</option></term>
         <listitem>
           <para>
-            Display the full text of any database connection error messages
+			Display the full text of any database connection error messages
           </para>
         </listitem>
       </varlistentry>
 
-    </variablelist>
+	</variablelist>
 
   </refsect1>
 

doc/repmgr-daemon-stop.sgml

@@ -1,200 +0,0 @@
-<refentry id="repmgr-daemon-stop">
-  <indexterm>
-    <primary>repmgr daemon stop</primary>
-  </indexterm>
-
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>stopping</secondary>
-  </indexterm>
-
-  <refmeta>
-    <refentrytitle>repmgr daemon stop</refentrytitle>
-  </refmeta>
-
-  <refnamediv>
-    <refname>repmgr daemon stop</refname>
-    <refpurpose>Stop the <application>repmgrd</application> daemon</refpurpose>
-  </refnamediv>
-
-  <refsect1>
-    <title>Description</title>
-    <para>
-      This command stops the <application>repmgrd</application> daemon on the
-      local node.
-    </para>
-
-    <para>
-      By default, &repmgr; will wait for up to 15 seconds to confirm that <application>repmgrd</application>
-      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.
-      </para>
-    </note>
-
-   <important>
-      <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.
-      </para>
-    </important>
-  </refsect1>
-
-  <refsect1>
-    <title>Configuration</title>
-    <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>;
-      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>
-
-    <important>
-      <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>
-        service; this is particularly the case with <literal>systemd</literal>.
-      </para>
-    </important>
-
-  </refsect1>
-
-  <refsect1>
-
-    <title>Options</title>
-
-    <variablelist>
-
-      <varlistentry>
-        <term><option>--dry-run</option></term>
-        <listitem>
-          <para>
-            Check prerequisites but don't actually attempt to stop <application>repmgrd</application>.
-          </para>
-          <para>
-            This action will output the command which would be executed.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>-w</option></term>
-        <term><option>--wait</option></term>
-        <listitem>
-          <para>
-            Wait for the specified number of seconds to confirm that <application>repmgrd</application>
-            stopped successfully.
-          </para>
-          <para>
-            Note that providing <option>--wait=0</option> is the equivalent of <option>--no-wait</option>.
-          </para>
-
-         </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>--no-wait</option></term>
-        <listitem>
-          <para>
-            Don't wait to confirm that <application>repmgrd</application>
-            stopped successfully.
-          </para>
-          <para>
-            This is equivalent to providing <option>--wait=0</option>.
-          </para>
-         </listitem>
-      </varlistentry>
-    </variablelist>
-  </refsect1>
-
-  <refsect1 id="repmgr-daemon-stop-configuration" xreflabel="repmgr daemon stop configuration">
-    <title>Configuration file settings</title>
-    <para>
-     The following parameter in <filename>repmgr.conf</filename> is relevant
-     to <command>repmgr daemon stop</command>:
-    </para>
-
-    <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>
-          <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>;
-            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>
-          <important>
-            <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>
-              service; this is particularly the case with <literal>systemd</literal>.
-            </para>
-          </important>
-        </listitem>
-      </varlistentry>
-    </variablelist>
-
-  </refsect1>
-
-  <refsect1>
-    <title>Exit codes</title>
-    <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon stop</command>:
-    </para>
-    <variablelist>
-
-      <varlistentry>
-        <term><option>SUCCESS (0)</option></term>
-        <listitem>
-          <para>
-            <application>repmgrd</application> could be stopped.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_BAD_CONFIG (1)</option></term>
-        <listitem>
-          <para>
-            <varname>repmgrd_service_stop_command</varname> is not defined in
-            <filename>repmgr.conf</filename>.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_REPMGRD_SERVICE (27)</option></term>
-        <listitem>
-          <para>
-            <application>repmgrd</application> could not be stopped.
-          </para>
-        </listitem>
-      </varlistentry>
-
-    </variablelist>
-  </refsect1>
-
-  <refsect1>
-    <title>See also</title>
-    <para>
-      <xref linkend="repmgr-daemon-start">, <xref linkend="repmgr-daemon-status">, <xref linkend="repmgrd-daemon">
-    </para>
-  </refsect1>
-
-</refentry>

doc/repmgr-daemon-unpause.sgml

@@ -3,12 +3,6 @@
     <primary>repmgr daemon unpause</primary>
   </indexterm>
 
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>unpausing</secondary>
-  </indexterm>
-
-
   <refmeta>
     <refentrytitle>repmgr daemon unpause</refentrytitle>
   </refmeta>
@@ -74,7 +68,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
+      Following exit codes can be emitted by <command>repmgr daemon unpause</command>:
     </para>
     <variablelist>
 

doc/repmgr-node-check.sgml

@@ -18,14 +18,6 @@
       Performs some health checks on a node from a replication perspective.
       This command must be run on the local node.
     </para>
-	<note>
-	  <para>
-		Currently &repmgr; performs health checks on physical replication
-		slots only, with the aim of warning about streaming replication standbys which
-		have become detached and the associated risk of uncontrolled WAL file
-		growth.
-	  </para>
-	</note>
   </refsect1>
 
   <refsect1>
@@ -38,8 +30,8 @@
             Replication lag: OK (N/A - node is primary)
             WAL archiving: OK (0 pending files)
             Downstream servers: OK (2 of 2 downstream nodes attached)
-            Replication slots: OK (node has no physical replication slots)
-            Missing replication slots: OK (node has no missing physical replication slots)</programlisting>
+            Replication slots: OK (node has no replication slots)
+            Missing replication slots: OK (node has no missing replication slots)</programlisting>
     </para>
   </refsect1>
   <refsect1>
@@ -52,7 +44,7 @@
         OK (node is primary)</programlisting>
     </para>
     <para>
-	  Parameters for individual checks are as follows:
+   Parameters for individual checks are as follows:
     <itemizedlist spacing="compact" mark="bullet">
 
      <listitem>
@@ -84,26 +76,16 @@
 
      <listitem>
       <simpara>
-        <literal>--slots</literal>: checks there are no inactive physical replication slots
+        <literal>--slots</literal>: checks there are no inactive replication slots
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--missing-slots</literal>: checks there are no missing physical replication slots
+        <literal>--missing-slots</literal>: checks there are no missing replication slots
       </simpara>
      </listitem>
 
-     <listitem>
-      <simpara>
-        <literal>--data-directory-config</literal>: checks the data directory configured in
-        <filename>repmgr.conf</filename> matches the actual data directory.
-        This check is not directly related to replication, but is useful to verify &repmgr;
-        is correctly configured.
-      </simpara>
-     </listitem>
-
-
     </itemizedlist>
   </para>
   </refsect1>
@@ -123,7 +105,6 @@
         <listitem>
           <simpara>
             <literal>--nagios</literal>: generate output in a Nagios-compatible format
-            (for individual checks only)
           </simpara>
         </listitem>
       </itemizedlist>
@@ -170,10 +151,9 @@
 
 
     <para>
-      One of the following exit codes will be emitted by <command>repmgr status check</command>
+      Following exit codes can be emitted by <command>repmgr status check</command>
       if no individual check was specified.
     </para>
-
     <variablelist>
 
       <varlistentry>
@@ -195,7 +175,6 @@
       </varlistentry>
 
    </variablelist>
-
   </refsect1>
 
 

doc/repmgr-node-rejoin.sgml

@@ -119,7 +119,6 @@
 
     </variablelist>
   </refsect1>
-
   <refsect1>
     <title>Configuration file settings</title>
 
@@ -133,11 +132,6 @@
 		   the value set in <literal>standby_reconnect_timeout</literal>,
 		   60 seconds).
 		 </simpara>
-         <simpara>
-           Note that <literal>standby_reconnect_timeout</literal> must be
-           set to a value equal to or greater than
-           <literal>node_rejoin_timeout</literal>.
-         </simpara>
 	   </listitem>
 	  </itemizedlist>
 	</para>
@@ -150,55 +144,6 @@
       A <literal>node_rejoin</literal> <link linkend="event-notifications">event notification</link> will be generated.
     </para>
   </refsect1>
-  <refsect1>
-    <title>Exit codes</title>
-    <para>
-      One of the following exit codes will be emitted by <command>repmgr node rejoin</command>:
-    </para>
-
-    <variablelist>
-
-      <varlistentry>
-        <term><option>SUCCESS (0)</option></term>
-        <listitem>
-          <para>
-            The node rejoin succeeded; or if <option>--dry-run</option> was provided,
-            no issues were detected which would prevent the node rejoin.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_BAD_CONFIG (1)</option></term>
-        <listitem>
-          <para>
-            A configuration issue was detected which prevented &repmgr; from
-            continuing with the node rejoin.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_NO_RESTART (4)</option></term>
-        <listitem>
-          <para>
-            The node could not be restarted.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_REJOIN_FAIL (24)</option></term>
-        <listitem>
-          <para>
-            The node rejoin operation failed.
-          </para>
-        </listitem>
-      </varlistentry>
-
-    </variablelist>
-
-  </refsect1>
 
   <refsect1>
     <title>Notes</title>
@@ -222,10 +167,6 @@
           postgres --single -D /var/lib/pgsql/data/ &lt; /dev/null</programlisting>
       </para>
     </tip>
-    <para>
-      &repmgr; will attempt to verify whether the node can rejoin as-is, or whether
-      <command>pg_rewind</command> must be used (see following section).
-    </para>
   </refsect1>
 
   <refsect1 id="repmgr-node-rejoin-pg-rewind" xreflabel="Using pg_rewind">
@@ -247,137 +188,73 @@
         <command>pg_rewind</command> <emphasis>requires</emphasis> that either
         <varname>wal_log_hints</varname> is enabled, or that
         data checksums were enabled when the cluster was initialized. See the
-        <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
+        <ulink url="https://www.postgresql.org/docs/current/static/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
       </para>
     </note>
 
-    <para>
-      We strongly recommend familiarizing yourself with <command>pg_rewind</command> before attempting
-      to use it with &repmgr;, as while it is an extremely useful tool, it is <emphasis>not</emphasis>
-      a &quot;magic bullet&quot; which can resolve all problematic replication situations.
-    </para>
-
-    <para>
-      A typical use-case for <command>pg_rewind</command> is when a scenario like the following
-      is encountered:
-      <programlisting>
-    $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
-        --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose --dry-run
-    INFO: replication connection to the rejoin target node was successful
-    INFO: local and rejoin target system identifiers match
-    DETAIL: system identifier is 6652184002263212600
-    ERROR: this node cannot attach to rejoin target node 3
-    DETAIL: rejoin target server's timeline 2 forked off current database system timeline 1 before current recovery point 0/610D710
-    HINT: use --force-rewind to execute pg_rewind</programlisting>
-
-      Here, <literal>node3</literal> was promoted to a primary while the local node was
-      still attached to the previous primary; this can potentially happen during e.g. a
-      network split. <command>pg_rewind</command> can re-sync the local node with <literal>node3</literal>,
-      removing the need for a full reclone.
-    </para>
-
     <para>
       To have <command>repmgr node rejoin</command> use <command>pg_rewind</command>,
       pass the command line option <literal>--force-rewind</literal>, which will tell &repmgr;
       to execute <command>pg_rewind</command> to ensure the node can be rejoined successfully.
     </para>
 
-    <important>
-      <para>
-        Be aware that if <command>pg_rewind</command> is executed and actually performs a
-        rewind operation, any configuration files in the PostgreSQL data directory will be
-        overwritten with those from the source server.
-      </para>
-      <para>
-        To prevent this happening, provide a comma-separated list of files to retain
-        using the <literal>--config-file</literal> command line option; the specified files
-        will be archived in a temporary directory (whose parent directory can be specified with
-        <literal>--config-archive-dir</literal>) and restored once the rewind operation is
-        complete.
-      </para>
-    </important>
+    <para>
+      Be aware that if <command>pg_rewind</command> is executed and actually performs a
+      rewind operation, any configuration files in the PostgreSQL data directory will be
+      overwritten with those from the source server.
+    </para>
+    <para>
+      To prevent this happening, provide a comma-separated list of files to retain
+      using the <literal>--config-file</literal> command line option; the specified files
+      will be archived in a temporary directory (whose parent directory can be specified with
+      <literal>--config-archive-dir</literal>) and restored once the rewind operation is
+      complete.
+    </para>
 
     <para>
       Example, first using <literal>--dry-run</literal>, then actually executing the
       <literal>node rejoin command</literal>.
     <programlisting>
-    $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
-        --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind --dry-run
-    INFO: replication connection to the rejoin target node was successful
-    INFO: local and rejoin target system identifiers match
-    DETAIL: system identifier is 6652460429293670710
-    NOTICE: pg_rewind execution required for this node to attach to rejoin target node 3
-    DETAIL: rejoin target server's timeline 2 forked off current database system timeline 1 before current recovery point 0/610D710
+    $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node1 dbname=repmgr user=repmgr' \
+         --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose --dry-run
+    NOTICE: using provided configuration file "/etc/repmgr.conf"
     INFO: prerequisites for using pg_rewind are met
-    INFO: file "postgresql.local.conf" would be copied to "/tmp/repmgr-config-archive-node2/postgresql.local.conf"
-    INFO: file "postgresql.replication-setup.conf" would be copied to "/tmp/repmgr-config-archive-node2/postgresql.replication-setup.conf"
+    INFO: file "postgresql.local.conf" would be copied to "/tmp/repmgr-config-archive-node1/postgresql.local.conf"
+    INFO: file "postgresql.conf" would be copied to "/tmp/repmgr-config-archive-node1/postgresql.local.conf"
+    INFO: 2 files would have been copied to "/tmp/repmgr-config-archive-node1"
+    INFO: directory "/tmp/repmgr-config-archive-node1" deleted
     INFO: pg_rewind would now be executed
     DETAIL: pg_rewind command is:
-      pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node3 dbname=repmgr user=repmgr'
-    INFO: prerequisites for executing NODE REJOIN are met</programlisting>
+      pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node1 dbname=repmgr user=repmgr'</programlisting>
 
     <note>
       <para>
         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.
+        this checks the prerequisites for using <application>pg_rewind</application>, but cannot
+        predict the outcome of actually executing <application>pg_rewind</application>.
       </para>
-
     </note>
 
     <programlisting>
-    $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
-        --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind
-    NOTICE: pg_rewind execution required for this node to attach to rejoin target node 3
-    DETAIL: rejoin target server's timeline 2 forked off current database system timeline 1 before current recovery point 0/610D710
+    $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node1 dbname=repmgr user=repmgr' \
+         --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose
+    NOTICE: using provided configuration file "/etc/repmgr.conf"
+    INFO: prerequisites for using pg_rewind are met
+    INFO: 2 files copied to "/tmp/repmgr-config-archive-node1"
     NOTICE: executing pg_rewind
-    DETAIL: pg_rewind command is "pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node3 dbname=repmgr user=repmgr'"
-    NOTICE: 2 files copied to /var/lib/postgresql/data
-    NOTICE: setting node 2's upstream to node 3
-    NOTICE: starting server using "pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' start"
+    NOTICE: 2 files copied to /var/lib/pgsql/data
+    INFO: directory "/tmp/repmgr-config-archive-node1" deleted
+    INFO: deleting "recovery.done"
+    INFO: setting node 1's primary to node 2
+    NOTICE: starting server using "pg_ctl-l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' start"
+    waiting for server to start.... done
+    server started
     NOTICE: NODE REJOIN successful
-    DETAIL: node 2 is now attached to node 3</programlisting>
+    DETAIL: node 1 is now attached to node 2</programlisting>
     </para>
 
   </refsect1>
 
-  <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>
-   <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
-     (rejoin target). This is particularly important if planning to use <application>pg_rewind</application>,
-     which currently (as of PostgreSQL 11) may appear to succeed (or indicate there is no action
-     needed) but potentially allow an impossible action, such as trying to rejoin a standby to a
-     primary which is behind the standby. &repmgr; will prevent this situation from occurring.
-   </para>
-   <para>
-     Currently it is <emphasis>not</emphasis> possible to detect a situation where the rejoin target
-     is a standby which has been &quot;promoted&quot; by removing <filename>recovery.conf</filename>
-     (PostgreSQL 12 and later: <filename>standby.signal</filename>) and restarting it.
-     In this case there will be no information about the point the rejoin target diverged
-     from the current standby; the rejoin operation will fail and
-     the current standby's PostgreSQL log will contain entries with the text
-     &quot;<literal>record with incorrect prev-link</literal>&quot;.
-   </para>
-   <para>
-     We strongly recommend running <command>repmgr node rejoin</command> with the
-     <option>--dry-run</option> option first. Additionally it might be a good idea
-     to execute the <application>pg_rewind</application> command displayed by
-     &repmgr; with the <application>pg_rewind</application> <option>--dry-run</option>
-     option. Note that <application>pg_rewind</application> does not indicate that it
-     is running in <option>--dry-run</option> mode.
-   </para>
-
-  </refsect1>
-
   <refsect1>
     <title>See also</title>
     <para>

doc/repmgr-node-service.sgml

@@ -84,7 +84,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr node service</command>:
+      Following exit codes can be emitted by <command>repmgr node service</command>:
     </para>
     <variablelist>
 

doc/repmgr-node-status.sgml

@@ -55,7 +55,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr node status</command>:
+      Following exit codes can be emitted by <command>repmgr node status</command>:
     </para>
     <variablelist>
 

doc/repmgr-primary-register.sgml

@@ -21,15 +21,6 @@
       installing the &repmgr; extension. This command needs to be executed before any
       standby nodes are registered.
     </para>
-
-    <note>
-      <para>
-        It's possibly to install the &repmgr; extension manually before executing
-        <command>repmgr primary register</command>; in this case &repmgr; will
-        detect the presence of the extension and skip that step.
-      </para>
-    </note>
-
   </refsect1>
 
   <refsect1>
@@ -44,16 +35,16 @@
     </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
-          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>
+    <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
+        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>
   </refsect1>
 

doc/repmgr-standby-clone.sgml

@@ -87,7 +87,7 @@
   <refsect1 id="repmgr-standby-clone-recovery-conf">
    <indexterm>
      <primary>recovery.conf</primary>
-     <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
+     <secondary>customising with "repmgr standby clone"</secondary>
    </indexterm>
 
    <title>Customising recovery.conf</title>
@@ -170,7 +170,7 @@
       pg_basebackup_options='--xlog-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">
+    See the <ulink url="https://www.postgresql.org/docs/current/static/app-pgbasebackup.html">
     pg_basebackup</ulink> documentation for details.
    </para>
 
@@ -194,11 +194,10 @@
    <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).
+     <command><ulink url="http://docs.pgbarman.org/release/2.4/#recover">barman recover</ulink></command> command).
    </para>
    <para>
-     To integrate the standby as a &repmgr; node, once the standby has been cloned,
-     ensure the <filename>repmgr.conf</filename>
+     To integrate the standby as a &repmgr; node, ensure the <filename>repmgr.conf</filename>
      file is created for the node, and that it has been registered using
      <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>.
      Then execute the command <command>repmgr standby clone --recovery-conf-only</command>.

doc/repmgr-standby-follow.sgml

@@ -9,35 +9,23 @@
 
   <refnamediv>
     <refname>repmgr standby follow</refname>
-    <refpurpose>attach a running standby to a new upstream node</refpurpose>
+    <refpurpose>attach a standby to a new primary</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
 
     <para>
-      Attaches the standby (&quot;follow candidate&quot;) to a new upstream node
-      (&quot;follow target&quot;). Typically this will be the primary, but this
-      command can also be used to attach the standby to another standby.
-    </para>
-    <para>
-      This command requires a valid
+      Attaches the standby to a new primary. 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
       default location; no additional arguments are required.
     </para>
-
-	<para>
-	  By default &repmgr; will attempt to attach the standby to the current primary.
-	  If <option>--upstream-node-id</option> is provided, &repmgr; will attempt
-	  to attach the standby to the specified node, which can be another standby.
-	</para>
-
     <para>
       This command will force a restart of the standby server, which must be
-      running.
+      running. It can only be used to attach an active standby to the current primary node
+   (and not to another standby).
     </para>
-
 	<tip>
       <para>
 		To re-add an inactive node to the replication cluster, use
@@ -48,22 +36,9 @@
 	<para>
 	  <command>repmgr standby follow</command> will wait up to
 	  <varname>standby_follow_timeout</varname> seconds (default: <literal>30</literal>)
-	  to verify the standby has actually connected to the new upstream node.
+	  to verify the standby has actually connected to the new primary.
 	</para>
 
-	<note>
-	  <para>
-	    If <option>recovery_min_apply_delay</option> is set for the standby, it
-	    will not attach to the new upstream node until it has replayed available
-	    WAL.
-	  </para>
-	  <para>
-	    Conversely, if the standby is attached to an upstream standby
-	    which has <option>recovery_min_apply_delay</option> set, the upstream
-            standby's replay state may actually be behind that of its new downstream node.
-	  </para>
-	</note>
-
   </refsect1>
 
   <refsect1>
@@ -90,46 +65,19 @@
         <term><option>--dry-run</option></term>
         <listitem>
           <para>
-            Check prerequisites but don't actually follow a new upstream node.
-          </para>
-          <para>
-            This will also verify whether the standby is capable of following the new upstream node.
+            Check prerequisites but don't actually follow a new standby.
           </para>
           <important>
             <para>
-              If a standby was turned into a primary by removing <filename>recovery.conf</filename>
-              (<application>PostgreSQL 12</application> and later: <filename>standby.signal</filename>),
-              &repmgr; will <emphasis>not</emphasis> be able to determine whether that primary's timeline
-              has diverged from the timeline of the standby (&quot;follow candidate&quot;).
-            </para>
-            <para>
-              We recommend always to use <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>
-              to promote a standby to primary, as this will ensure that the new primary
-              will perform a timeline switch (making it practical to check for timeline divergence)
-              and also that &repmgr; metadata is updated correctly.
+              This does not guarantee the standby can follow the primary; in
+              particular, whether the primary and standby timelines have diverged,
+              can currently only be determined by actually attempting to
+              attach the standby to the primary.
             </para>
           </important>
         </listitem>
       </varlistentry>
 
-      <varlistentry>
-        <term><option>--upstream-node-id</option></term>
-        <listitem>
-          <para>
-            Node ID of the new upstream node (&quot;follow target&quot;).
-          </para>
-          <para>
-            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>
-            should always be configured;
-			see <link linkend="repmgrd-automatic-failover-configuration">Automatic failover configuration</link>
-            for details.
-          </para>
-        </listitem>
-      </varlistentry>
-
       <varlistentry>
         <term><option>-w</option></term>
         <term><option>--wait</option></term>
@@ -146,104 +94,13 @@
     </variablelist>
   </refsect1>
 
-  <refsect1>
-    <title>Execution</title>
-
-    <para>
-      Execute with the <literal>--dry-run</literal> option to test the follow operation as
-      far as possible, without actually changing the status of the node.
-    </para>
-
-    <para>
-      Note that &repmgr; will first attempt to determine whether the standby
-      (&quot;follow candidate&quot;) is capable of following the
-      new upstream node (&quot;follow target&quot;).
-    </para>
-    <para>
-      If, for example, the new upstream node has diverged from this node's timeline,
-      for example if the new upstream node was promoted to primary while this node
-      was still attached to the original primary, it will <emphasis>not</emphasis>
-      be possible to follow the new upstream node, and &repmgr; will emit an error
-      message like this:
-      <programlisting>
-ERROR: this node cannot attach to follow target node 3
-DETAIL: follow target server's timeline 2 forked off current database system timeline 1 before current recovery point 0/6108880</programlisting>
-    </para>
-    <para>
-      In this case, it may be possible to have this node follow the new upstream
-      using <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
-      with the <option>--force-rewind</option> to execute <command>pg_rewind</command>.
-      This does mean that transactions which exist on this node, but not the new upstream,
-      will be lost.
-    </para>
-
-  </refsect1>
-
-  <refsect1>
-    <title>Exit codes</title>
-    <para>
-      One of the following exit codes will be emitted by <command>repmgr standby follow</command>:
-    </para>
-    <variablelist>
-
-      <varlistentry>
-        <term><option>SUCCESS (0)</option></term>
-        <listitem>
-          <para>
-            The follow operation succeeded; or if <option>--dry-run</option> was provided,
-            no issues were detected which would prevent the follow operation.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_BAD_CONFIG (1)</option></term>
-        <listitem>
-          <para>
-            A configuration issue was detected which prevented &repmgr; from
-            continuing with the follow operation.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_NO_RESTART (4)</option></term>
-        <listitem>
-          <para>
-            The node could not be restarted.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_DB_CONN (6)</option></term>
-        <listitem>
-          <para>
-            &repmgr; was unable to establish a database connection to one of the nodes.
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>ERR_FOLLOW_FAIL (23)</option></term>
-        <listitem>
-          <para>
-            &repmgr; was unable to complete the follow command.
-          </para>
-        </listitem>
-      </varlistentry>
-
-    </variablelist>
-
-  </refsect1>
-
   <refsect1 id="repmgr-standby-follow-events">
     <title>Event notifications</title>
     <para>
       A <literal>standby_follow</literal> <link linkend="event-notifications">event notification</link> will be generated.
     </para>
     <para>
-      If provided, &repmgr; will substitute the placeholders <literal>%p</literal> with the node ID of the node
+      If provided, &repmgr; will substitute the placeholders <literal>%p</literal> with the node ID of the primary
       being followed, <literal>%c</literal> with its <literal>conninfo</literal> string, and
       <literal>%a</literal> with its node name.
     </para>
@@ -256,3 +113,4 @@ DETAIL: follow target server's timeline 2 forked off current database system tim
     </para>
   </refsect1>
 </refentry>
+

doc/repmgr-standby-promote.sgml

@@ -33,26 +33,8 @@
       Both values can be defined in <filename>repmgr.conf</filename>.
     </para>
 
-    <note>
-      <para>
-        If WAL replay is paused on the standby, and not all WAL files on the standby have been
-        replayed, &repmgr; will not attempt to promote it.
-      </para>
-      <para>
-        This is because if WAL replay is paused, PostgreSQL itself will not react to a promote command
-        until WAL replay is resumed and all pending WAL has been replayed. This means
-        attempting to promote PostgreSQL in this state will leave PostgreSQL in a condition where the
-        promotion may occur at a unpredictable point in the future.
-      </para>
-      <para>
-        Note that if the standby is in archive recovery, &repmgr; will not be able to determine
-        if more WAL is pending replay, and will abort the promotion attempt if WAL replay is paused.
-      </para>
-    </note>
-
   </refsect1>
 
-
   <refsect1>
     <title>Example</title>
     <para>
@@ -68,127 +50,6 @@
   </refsect1>
 
 
-  <refsect1>
-    <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
-          </para>
-        </listitem>
-      </varlistentry>
-    </variablelist>
-  </refsect1>
-
-  <refsect1>
-    <title>Configuration file settings</title>
-   <para>
-     The following parameters in <filename>repmgr.conf</filename> are relevant to the
-     promote operation:
-    </para>
-
-    <para>
-      <itemizedlist spacing="compact" mark="bullet">
-
-       <listitem>
-        <indexterm>
-          <primary>promote_check_interval</primary>
-          <secondary>with &quot;repmgr standby promote &quot;</secondary>
-        </indexterm>
-         <simpara>
-           <literal>promote_check_interval</literal>:
-           interval (in seconds, default: 1 second) to wait between each check
-           to determine whether the standby has been promoted.
-		 </simpara>
-	   </listitem>
-
-       <listitem>
-        <indexterm>
-          <primary>promote_check_timeout</primary>
-          <secondary>with &quot;repmgr standby promote &quot;</secondary>
-        </indexterm>
-         <simpara>
-           <literal>promote_check_timeout</literal>:
-           time (in seconds, default: 60 seconds) to wait to verify that the standby has been promoted
-           before exiting with <literal>ERR_PROMOTION_FAIL</literal>.
-		 </simpara>
-	   </listitem>
-
-	  </itemizedlist>
-	</para>
-
-  </refsect1>
-
-  <refsect1>
-    <title>Exit codes</title>
-    <para>
-      Following exit codes can be emitted by <command>repmgr standby promote</command>:
-    </para>
-    <variablelist>
-      <varlistentry>
-        <term><option>SUCCESS (0)</option></term>
-        <listitem>
-          <para>
-            The standby was successfully promoted to primary.
-          </para>
-        </listitem>
-      </varlistentry>
-
-     <varlistentry>
-        <term><option>ERR_DB_CONN (6)</option></term>
-        <listitem>
-          <para>
-            &repmgr; was unable to connect to the local PostgreSQL node.
-          </para>
-          <para>
-            PostgreSQL must be running before the node can be promoted.
-          </para>
-        </listitem>
-      </varlistentry>
-
-     <varlistentry>
-       <term><option>ERR_PROMOTION_FAIL (8)</option></term>
-        <listitem>
-          <para>
-            The node could not be promoted to primary for one of the following
-            reasons:
-            <itemizedlist spacing="compact" mark="bullet">
-
-              <listitem>
-                <simpara>
-                  there is an existing primary node in the replication cluster
-                </simpara>
-              </listitem>
-
-              <listitem>
-                <simpara>
-                  the node is not a standby
-                </simpara>
-              </listitem>
-
-              <listitem>
-                <simpara>
-                  WAL replay is paused on the node
-                </simpara>
-              </listitem>
-
-              <listitem>
-                <simpara>
-                  execution of the PostgreSQL promote command failed
-                </simpara>
-              </listitem>
-
-            </itemizedlist>
-          </para>
-        </listitem>
-     </varlistentry>
-
-    </variablelist>
-  </refsect1>
-
-
   <refsect1 id="repmgr-standby-promote-events">
     <title>Event notifications</title>
     <para>

doc/repmgr-standby-switchover.sgml

@@ -37,7 +37,7 @@
       </para>
       <para>
         &repmgr; will refuse to perform the switchover if an exclusive backup is running on
-        the current primary, or if WAL replay is paused on the standby.
+        the current primary.
       </para>
     </note>
     <para>
@@ -146,7 +146,6 @@
 
 
      <varlistentry>
-
         <term><option>--siblings-follow</option></term>
         <listitem>
           <para>
@@ -162,45 +161,29 @@
     <title>Configuration file settings</title>
 
     <para>
-     The following parameters in <filename>repmgr.conf</filename> are relevant to the
+     Note that following parameters in <filename>repmgr.conf</filename> are relevant to the
      switchover operation:
-    </para>
+     <itemizedlist spacing="compact" mark="bullet">
 
-    <variablelist>
+       <listitem>
+         <simpara>
+           <literal>replication_lag_critical</literal>:
+           if replication lag (in seconds) on the standby exceeds this value, the
+           switchover will be aborted (unless the <literal>-F/--force</literal> option
+           is provided)
+         </simpara>
+       </listitem>
 
-      <varlistentry>
-        <indexterm>
-          <primary>replication_lag_critical</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
-
-        <term><option>replication_lag_critical</option></term>
-        <listitem>
-          <para>
-            If replication lag (in seconds) on the standby exceeds this value, the
-            switchover will be aborted (unless the <literal>-F/--force</literal> option
-            is provided)
-          </para>
-        </listitem>
-      </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>
-          <para>
-            The maximum number of seconds to wait for the
-            demotion candidate (current primary) to shut down, before aborting the switchover.
-          </para>
-          <para>
-            Note that this parameter is set on the node where <command>repmgr standby switchover</command>
-            is executed (promotion candidate); setting it on the demotion candidate (former primary) will
-            have no effect.
-          </para>
+       <listitem>
+         <simpara>
+           <literal>shutdown_check_timeout</literal>: maximum number of seconds to wait for the
+           demotion candidate (current primary) to shut down, before aborting the switchover.
+         </simpara>
+         <simpara>
+           Note that this parameter is set on the node where <command>repmgr standby switchover</command>
+           is executed (promotion candidate); setting it on the demotion candidate (former primary) will
+           have no effect.
+         </simpara>
          <note>
            <para>
              In versions prior to <link linkend="release-4.2">&repmgr; 4.2</link>, <command>repmgr standby switchover</command> would
@@ -208,73 +191,18 @@
              to determine the timeout for demotion candidate shutdown.
            </para>
          </note>
-        </listitem>
-      </varlistentry>
+       </listitem>
 
+       <listitem>
+         <simpara>
+           <literal>standby_reconnect_timeout</literal>:
+           maximum number of seconds to attempt to wait for the demotion candidate (former primary)
+           to reconnect to the promoted primary (default: 60 seconds)
+         </simpara>
+       </listitem>
 
-      <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>
-          <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
-            with the primary's shut down location.
-         </para>
-        </listitem>
-      </varlistentry>
-
-
-      <varlistentry>
-        <indexterm>
-          <primary>standby_reconnect_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
-
-        <term><option>standby_reconnect_timeout</option></term>
-        <listitem>
-          <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)
-          </para>
-          <para>
-            Note that this parameter is set on the node where <command>repmgr standby switchover</command>
-            is executed (promotion candidate); setting it on the demotion candidate (former primary) will
-            have no effect.
-          </para>
-        </listitem>
-      </varlistentry>
-
-     <varlistentry>
-        <indexterm>
-          <primary>node_rejoin_timeout</primary>
-          <secondary>with &quot;repmgr standby switchover&quot;</secondary>
-        </indexterm>
-
-        <term><option>node_rejoin_timeout</option></term>
-        <listitem>
-          <para>
-            maximum number of seconds to attempt to wait for the demotion candidate (former primary)
-            to reconnect to the promoted primary (default: 60 seconds)
-          </para>
-          <para>
-            Note that this parameter is set on the the demotion candidate (former primary);
-            setting it on the node where <command>repmgr standby switchover</command> is
-            executed will have no effect.
-          </para>
-          <para>
-            However, this value <emphasis>must</emphasis> be less than <option>standby_reconnect_timeout</option> on the
-            promotion candidate (the node where <command>repmgr standby switchover</command> is executed).
-          </para>
-        </listitem>
-      </varlistentry>
-
-    </variablelist>
-
+     </itemizedlist>
+    </para>
   </refsect1>
 
 
@@ -310,7 +238,7 @@
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr standby switchover</command>:
+      Following exit codes can be emitted by <command>repmgr standby switchover</command>:
     </para>
     <variablelist>
 
@@ -318,8 +246,7 @@
         <term><option>SUCCESS (0)</option></term>
         <listitem>
           <para>
-            The switchover completed successfully; or if <option>--dry-run</option> was provided,
-            no issues were detected which would prevent the switchover operation.
+            The switchover completed successfully.
           </para>
         </listitem>
       </varlistentry>
@@ -350,10 +277,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <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 see the section <xref linkend="performing-switchover">.
     </para>
   </refsect1>
 

doc/repmgr-witness-register.sgml

@@ -34,14 +34,6 @@
       witness node's <filename>repmgr.conf</filename>, unless these are explicitly
       provided as command line options.
     </para>
-
-    <note>
-      <para>
-        The primary server must be registered with <command><link linkend="repmgr-primary-register">repmgr primary register</link></command> before the witness
-        server can be registered.
-      </para>
-    </note>
-
     <para>
       Execute with the <option>--dry-run</option> option to check what would happen
       without actually registering the witness server.

doc/repmgr.sgml

@@ -25,25 +25,31 @@
    <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 documentation</ulink>.
    </para>
 
    <para>
-    &repmgr; is developed by
+    &repmgr; was developed by
     <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
     along with contributions from other individuals and companies.
     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>.
+    in touch via <ulink url="https://github.com/2ndQuadrant/repmgr">github</>
+    or <ulink url="https://groups.google.com/group/repmgr">the mailing list/forum</>.
     Multiple 2ndQuadrant customers contribute funding
     to make repmgr development possible.
    </para>
 
    <para>
-     &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.
+    2ndQuadrant, a Platinum sponsor of the PostgreSQL project,
+    continues to develop repmgr to meet internal needs and those of customers.
+     Other companies as well as individual developers
+    are welcome to participate in the efforts.
    </para>
   </abstract>
 
@@ -80,10 +86,15 @@
 
  <part id="using-repmgrd">
   <title>Using repmgrd</title>
-  &repmgrd-overview;
   &repmgrd-automatic-failover;
   &repmgrd-configuration;
-  &repmgrd-operation;
+  &repmgrd-demonstration;
+  &repmgrd-cascading-replication;
+  &repmgrd-network-split;
+  &repmgrd-witness-server;
+  &repmgrd-pausing;
+  &repmgrd-degraded-monitoring;
+  &repmgrd-monitoring;
   &repmgrd-bdr;
  </part>
 
@@ -110,8 +121,6 @@
   &repmgr-cluster-event;
   &repmgr-cluster-cleanup;
   &repmgr-daemon-status;
-  &repmgr-daemon-start;
-  &repmgr-daemon-stop;
   &repmgr-daemon-pause;
   &repmgr-daemon-unpause;
  </part>
@@ -120,7 +129,6 @@
  &appendix-signatures;
  &appendix-faq;
  &appendix-packages;
- &appendix-support;
 
  <![%include-index;[&bookindex;]]>
  <![%include-xslt-index;[<index id="bookindex"></index>]]>

doc/repmgrd-automatic-failover.sgml

@@ -13,230 +13,5 @@
   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>
-
-</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-bdr.sgml

@@ -10,7 +10,7 @@
 
   <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>
@@ -31,8 +31,21 @@
     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

doc/repmgrd-cascading-replication.sgml

@@ -0,0 +1,22 @@
+<chapter id="repmgrd-cascading-replication">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>cascading replication</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 "cascaded standby" will attempt to reconnect to that node's parent.
+ </para>
+</chapter>

doc/repmgrd-configuration.sgml

@@ -5,7 +5,7 @@
     <secondary>configuration</secondary>
   </indexterm>
 
-  <title>repmgrd setup and configuration</title>
+  <title>repmgrd configuration</title>
 
   <para>
     <application>repmgrd</application> is a daemon which runs on each PostgreSQL node,
@@ -20,7 +20,7 @@
   </para>
 
   <sect1 id="repmgrd-basic-configuration">
-    <title>repmgrd configuration</title>
+    <title>repmgrd basic configuration</title>
 
     <para>
       To use <application>repmgrd</application>, its associated function library <emphasis>must</emphasis> be
@@ -31,417 +31,79 @@
     </para>
     <para>
       Changing this setting requires a restart of PostgreSQL; for more details see
-      the <ulink url="https://www.postgresql.org/docs/current/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
+      the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
     </para>
 
-    <para>
-      The following configuraton options apply to <application>repmgrd</application> in all circumstances:
-    </para>
-    <variablelist>
-
-        <varlistentry>
-
-         <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>
-
-        <varlistentry>
-
-          <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>
-                  <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>
-
-              </itemizedlist>
-            </para>
-          </listitem>
-        </varlistentry>
-
-        <varlistentry>
-         <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>
-            <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>
-              The number of reconnection attempts is defined by the parameter <option>reconnect_attempts</option>.
-            </para>
-          </listitem>
-        </varlistentry>
-
-
-
-        <varlistentry>
-          <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>
-
-    </variablelist>
-
-      <para>
-        See also <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file.
-      </para>
 
     <sect2 id="repmgrd-automatic-failover-configuration">
-      <title>Required configuration for automatic failover</title>
-
+      <title>automatic failover configuration</title>
       <para>
-        The following <application>repmgrd</application> options <emphasis>must</emphasis> be set in
-        <filename>repmgr.conf</filename>:
-
-        <itemizedlist spacing="compact" mark="bullet">
-          <listitem>
-            <simpara><option>failover</option></simpara>
-          </listitem>
-          <listitem>
-            <simpara><option>promote_command</option></simpara>
-          </listitem>
-          <listitem>
-            <simpara><option>follow_command</option></simpara>
-          </listitem>
-        </itemizedlist>
-      </para>
-
-
-      <para>
-        Example:
+        If using automatic failover, the following <application>repmgrd</application> options *must* be set in
+        <filename>repmgr.conf</filename> :
         <programlisting>
           failover=automatic
           promote_command='/usr/bin/repmgr standby promote -f /etc/repmgr.conf --log-to-file'
           follow_command='/usr/bin/repmgr standby follow -f /etc/repmgr.conf --log-to-file --upstream-node-id=%n'</programlisting>
       </para>
       <para>
-        Details of each option are as follows:
+        Adjust file paths as appropriate; alway specify the full path to the &repmgr; binary.
       </para>
-      <variablelist>
-        <varlistentry>
 
-          <indexterm>
-            <primary>failover</primary>
-          </indexterm>
-          <term><option>failover</option></term>
-          <listitem>
-            <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>
-                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>
-            </note>
-
-          </listitem>
-        </varlistentry>
-
-        <varlistentry>
-          <indexterm>
-            <primary>promote_command</primary>
-          </indexterm>
-          <term><option>promote_command</option></term>
-          <listitem>
-            <para>
-              The program or script defined in <option>promote_command</option> will be executed
-              in a failover situation when <application>repmgrd</application> determines that
-              the current node is to become the new primary node.
-            </para>
-            <para>
-              Normally <option>promote_command</option> is set as &repmgr;'s
-              <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
-              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
-              &repmgr; will no longer function reliably.
-            </para>
-            <para>
-              Example:
-              <programlisting>
-                promote_command='/usr/bin/repmgr standby promote -f /etc/repmgr.conf --log-to-file'</programlisting>
-            </para>
-
-            <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>.
-            </para>
-            <note>
-              <para>
-                &repmgr; will not apply <option>pg_bindir</option> when executing <option>promote_command</option>
-                or <option>follow_command</option>; these can be user-defined scripts so must always be
-                specified with the full path.
-              </para>
-            </note>
-          </listitem>
-        </varlistentry>
-
-        <varlistentry>
-          <indexterm>
-            <primary>follow_command</primary>
-          </indexterm>
-          <term><option>follow_command</option></term>
-          <listitem>
-            <para>
-              The program or script defined in <option>follow_command</option> will be executed
-              in a failover situation when <application>repmgrd</application> 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.
-            </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,
-              <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
-              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
-              &repmgr; will no longer function reliably.
-            </para>
-            <para>
-              Example:
-              <programlisting>
-          follow_command='/usr/bin/repmgr standby follow -f /etc/repmgr.conf --log-to-file --upstream-node-id=%n'</programlisting>
-            </para>
-
-            <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>.
-            </para>
-            <note>
-              <para>
-                &repmgr; will not apply <option>pg_bindir</option> when executing <option>promote_command</option>
-                or <option>follow_command</option>; these can be user-defined scripts so must always be
-                specified with the full path.
-              </para>
-            </note>
-          </listitem>
-
-        </varlistentry>
-
-      </variablelist>
-
-
-    </sect2>
-
-    <sect2 id="repmgrd-automatic-failover-configuration-optional">
-      <title>Optional configuration for automatic failover</title>
+      <note>
+        <para>
+          &repmgr; will not apply <option>pg_bindir</option> when executing <option>promote_command</option>
+          or <option>follow_command</option>; these can be user-defined scripts so must always be
+          specified with the full path.
+        </para>
+      </note>
 
       <para>
-        The following configuraton options can be use to fine-tune automatic failover:
+        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>.
+        See <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename>
+        for further <application>repmgrd</application>-specific settings.
       </para>
-      <variablelist>
-
-        <varlistentry>
-          <indexterm>
-            <primary>priority</primary>
-          </indexterm>
-          <term><option>priority</option></term>
-          <listitem>
-            <para>
-              Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes;
-			  a value of zero prevents the node being promoted to primary.
-            </para>
-            <para>
-              Note that the priority setting is only applied if two or more nodes are
-              determined as promotion candidates; in that case the node with the
-              higher priority is selected.
-            </para>
-          </listitem>
-        </varlistentry>
-
-        <varlistentry>
-          <indexterm>
-            <primary>failover_validation_command</primary>
-          </indexterm>
-          <term><option>failover_validation_command</option></term>
-          <listitem>
-            <para>
-              User-defined script to execute for an external mechanism to validate the failover
-	      decision made by <application>repmgrd</application>.
-            </para>
-            <note>
-              <para>
-                This option <emphasis>must</emphasis> be identically configured
-                on all nodes.
-              </para>
-            </note>
-            <para>
-              One or both of the following parameter placeholders
-			  should be provided, which will be replaced by repmgrd with the appropriate
-	          value:
-              <itemizedlist spacing="compact" mark="bullet">
-                <listitem>
-                  <simpara><literal>%n</literal>: node ID</simpara>
-                </listitem>
-                <listitem>
-                  <simpara><literal>%a</literal>: node name</simpara>
-                </listitem>
-              </itemizedlist>
-            </para>
-            <para>
-              See also: <link linkend="repmgrd-failover-validation">Failover validation</link>.
-            </para>
-          </listitem>
-        </varlistentry>
-
-        <varlistentry>
-
-         <indexterm>
-            <primary>standby_disconnect_on_failover</primary>
-          </indexterm>
-          <term><option>standby_disconnect_on_failover</option></term>
-          <listitem>
-            <para>
-              In a failover situation, disconnect the local node's WAL receiver.
-            </para>
-            <para>
-              This option is available from PostgreSQL 9.5 and later.
-            </para>
-            <note>
-              <para>
-                This option <emphasis>must</emphasis> be identically configured
-                on all nodes.
-              </para>
-              <para>
-                Additionally the &repmgr; user <emphasis>must</emphasis> be a superuser
-                for this option.
-              </para>
-              <para>
-                <application>repmgrd</application> will refuse to start if this option is set
-                but either of these prerequisites is not met.
-              </para>
-            </note>
-
-            <para>
-              See also: <link linkend="repmgrd-standby-disconnection-on-failover">Standby disconnection on failover</link>.
-            </para>
-          </listitem>
-        </varlistentry>
-
-      </variablelist>
+      <para>
+        When <varname>failover</varname> is set to <literal>automatic</literal>, upon detecting failure
+        of the current  primary, <application>repmgrd</application> will execute one of:
+      </para>
+      <itemizedlist spacing="compact" mark="bullet">
+        <listitem>
+          <simpara>
+            <varname>promote_command</varname> (if the current server is to become the new primary)
+          </simpara>
+        </listitem>
+        <listitem>
+          <simpara>
+            <varname>follow_command</varname> (if the current server needs to follow another server which has
+            become the new primary)
+          </simpara>
+        </listitem>
+      </itemizedlist>
+      <note>
+        <para>
+          These commands can be any valid shell script which results in one of these
+          two actions happening, but if &repmgr;'s <command>standby follow</command> or
+          <command>standby promote</command>
+          commands are not executed (either directly as shown here, or from a script which
+          performs other actions), the &repmgr; metadata will not be updated and
+          &repmgr; will no longer function reliably.
+        </para>
+      </note>
 
       <para>
-        The following options can be used to further fine-tune failover behaviour.
-        In practice it's unlikely these will need to be changed from their default
-        values, but are available as configuration options should the need arise.
+        The <varname>follow_command</varname> 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, &repmgr;
+        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>
-      <variablelist>
-
-        <varlistentry>
-          <indexterm>
-            <primary>election_rerun_interval</primary>
-          </indexterm>
-          <term><option>election_rerun_interval</option></term>
-          <listitem>
-			<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.
-			</para>
-		  </listitem>
-		</varlistentry>
-
-
-        <varlistentry>
-          <indexterm>
-            <primary>sibling_nodes_disconnect_timeout</primary>
-          </indexterm>
-          <term><option>sibling_nodes_disconnect_timeout</option></term>
-          <listitem>
-			<para>
-              If <option>standby_disconnect_on_failover</option> is <literal>true</literal>, the
-              maximum length of time (in seconds, default: <literal>30</literal>)
-			  to wait for other standbys to confirm they have disconnected their
-		      WAL receivers.
-			</para>
-		  </listitem>
-		</varlistentry>
-      </variablelist>
-
-
-
     </sect2>
 
-    <sect2 id="postgresql-service-configuration">
+    <sect2 id="repmgrd-service-configuration">
       <indexterm>
         <primary>repmgrd</primary>
         <secondary>PostgreSQL service configuration</secondary>
@@ -464,42 +126,6 @@
       </para>
     </sect2>
 
-    <sect2 id="repmgrd-service-configuration">
-      <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
-        parameters <emphasis>must</emphasis> be set in <filename>repmgr.conf</filename>:
-        <itemizedlist spacing="compact" mark="bullet">
-
-          <listitem>
-            <simpara><varname>repmgrd_service_start_command</varname></simpara>
-          </listitem>
-
-          <listitem>
-            <simpara><varname>repmgrd_service_stop_command</varname></simpara>
-          </listitem>
-
-        </itemizedlist>
-
-      </para>
-      <para>
-        Example (for &repmgr; with PostgreSQL 11 on CentOS 7):
-        <programlisting>
-repmgrd_service_start_command='sudo systemctl repmgr11 start'
-repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
-</programlisting>
-      </para>
-      <para>
-        For more details see the reference page for each command.
-      </para>
-    </sect2>
-
-
     <sect2 id="repmgrd-monitoring-configuration" xreflabel="repmgrd monitoring configuration">
       <indexterm>
         <primary>repmgrd</primary>
@@ -513,8 +139,10 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         in <filename>repmgr.conf</filename>.
       </para>
       <para>
-        Monitoring data is written at the interval defined by
-        the option <option>monitor_interval_secs</option> (see above).
+        The default monitoring interval is 2 seconds; this value can be explicitly set using:
+        <programlisting>
+          monitor_interval_secs=&lt;seconds&gt;</programlisting>
+        in <filename>repmgr.conf</filename>.
       </para>
       <para>
         For more details on monitoring, see <xref linkend="repmgrd-monitoring">.
@@ -564,13 +192,6 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
           </simpara>
         </listitem>
 
-
-        <listitem>
-          <simpara>
-            <varname>connection_check_type</varname>
-          </simpara>
-        </listitem>
-
         <listitem>
           <simpara>
             <varname>conninfo</varname>
@@ -595,12 +216,6 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
           </simpara>
         </listitem>
 
-        <listitem>
-          <simpara>
-            <varname>failover_validation_command</varname>
-          </simpara>
-        </listitem>
-
         <listitem>
           <simpara>
             <varname>failover</varname>
@@ -673,30 +288,12 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
           </simpara>
         </listitem>
 
-        <listitem>
-          <simpara>
-            <varname>retry_promote_interval_secs</varname>
-          </simpara>
-        </listitem>
-
         <listitem>
           <simpara>
             <varname>repmgrd_standby_startup_timeout</varname>
           </simpara>
         </listitem>
 
-        <listitem>
-          <simpara>
-            <varname>sibling_nodes_disconnect_timeout</varname>
-          </simpara>
-        </listitem>
-
-        <listitem>
-          <simpara>
-            <varname>standby_disconnect_on_failover</varname>
-          </simpara>
-        </listitem>
-
       </itemizedlist>
 
       <para>
@@ -751,7 +348,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
 
   </sect1>
 
-  <sect1 id="repmgrd-daemon" xreflabel="repmgrd daemon">
+  <sect1 id="repmgrd-daemon">
     <indexterm>
       <primary>repmgrd</primary>
       <secondary>starting and stopping</secondary>
@@ -766,20 +363,6 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
       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>.
-    </para>
-    <important>
-      <para>
-        <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link> and
-        <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> require
-        that the appropriate start/stop commands are configured as
-        <varname>repmgrd_service_start_command</varname> and <varname>repmgrd_service_stop_command</varname>
-        in <filename>repmgr.conf</filename>.
-      </para>
-    </important>
     <para>
       <application>repmgrd</application> can be started manually like this:
       <programlisting>
@@ -804,7 +387,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         <simpara>
           This is a behaviour change from previous versions (earlier than 4.1), where
           the PID file had to be explicitly specified with the command line
-          parameter <option>--pid-file</option>.
+          parameter <option> --pid-file</option>.
         </simpara>
       </note>
       <para>
@@ -824,7 +407,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
       </para>
       <para>
         If none of the above apply, <application>repmgrd</application> will create a PID file
-        in the operating system's temporary directory (as setermined by the environment variable
+        in the operating system's temporary directory (das etermined by the environment variable
         <varname>TMPDIR</varname>, or if that is not set, will use <filename>/tmp</filename>).
       </para>
       <para>
@@ -926,7 +509,7 @@ REPMGRD_OPTS="--daemonize=false"
  <para>
   For further details on <varname>conninfo</varname> network connection
   parameters, see the
-  <ulink url="https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-PARAMKEYWORDS">PostgreSQL documentation</ulink>.
+  <ulink url="https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-PARAMKEYWORDS">PostgreSQL documentation</ulink>.
  </para>
  </sect1>
 

doc/repmgrd-degraded-monitoring.sgml

@@ -0,0 +1,83 @@
+<chapter id="repmgrd-degraded-monitoring" xreflabel="repmgrd degraded monitoring">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>degraded monitoring</secondary>
+ </indexterm>
+
+ <title>"degraded monitoring" mode</title>
+ <para>
+  In certain circumstances, <application>repmgrd</application> 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
+  to be resolved.
+ </para>
+ <para>
+  Situations where this happens are:
+  <itemizedlist spacing="compact" mark="bullet">
+
+   <listitem>
+    <simpara>a failover situation has occurred, no nodes in the primary node's location are visible</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>a failover situation has occurred, but no promotion candidate is available</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>a failover situation has occurred, but the promotion candidate could not be promoted</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>a failover situation has occurred, but the node was unable to follow the new primary</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>a failover situation has occurred, but no primary has become available</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>a failover situation has occurred, but automatic failover is not enabled for the node</simpara>
+   </listitem>
+
+   <listitem>
+    <simpara>repmgrd is monitoring the primary node, but it is not available (and no other node has been promoted as primary)</simpara>
+   </listitem>
+  </itemizedlist>
+ </para>
+
+ <para>
+  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 10:59:33] [INFO] checking state of node 1, 1 of 5 attempts
+    [2017-08-29 10:59:33] [INFO] sleeping 1 seconds until next reconnection attempt
+    (...)
+    [2017-08-29 10:59:37] [INFO] checking state of node 1, 5 of 5 attempts
+    [2017-08-29 10:59:37] [WARNING] unable to reconnect to node 1 after 5 attempts
+    [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 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>
+
+ </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.
+ </para>
+
+ <note>
+   <para>
+     If <application>repmgrd</application> 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.
+   </para>
+ </note>
+
+</chapter>

doc/repmgrd-demonstration.sgml

@@ -1,23 +1,6 @@
-<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>
+<chapter 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:
@@ -29,13 +12,6 @@
      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:
@@ -117,6 +93,4 @@
      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-monitoring.sgml

@@ -0,0 +1,80 @@
+<chapter id="repmgrd-monitoring" xreflabel="Monitoring with repmgrd">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>monitoring</secondary>
+ </indexterm>
+ <indexterm>
+   <primary>monitoring</primary>
+   <secondary>with repmgrd</secondary>
+ </indexterm>
+
+ <title>Monitoring with repmgrd</title>
+ <para>
+   When <application>repmgrd</application> 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
+  in the cluster.
+ </para>
+ <para>
+   The view <literal>replication_status</literal> shows the most recent state
+   for each node, e.g.:
+  <programlisting>
+    repmgr=# select * from repmgr.replication_status;
+    -[ RECORD 1 ]-------------+------------------------------
+    primary_node_id           | 1
+    standby_node_id           | 2
+    standby_name              | node2
+    node_type                 | standby
+    active                    | t
+    last_monitor_time         | 2017-08-24 16:28:41.260478+09
+    last_wal_primary_location | 0/6D57A00
+    last_wal_standby_location | 0/5000000
+    replication_lag           | 29 MB
+    replication_time_lag      | 00:00:11.736163
+    apply_lag                 | 15 MB
+    communication_time_lag    | 00:00:01.365643</programlisting>
+ </para>
+ <para>
+  The interval in which monitoring history is written is controlled by the
+  configuration parameter <varname>monitor_interval_secs</varname>;
+  default is 2.
+ </para>
+ <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">
+  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
+  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,
+  no failover action will be taken and the node will require manual intervention to
+  be reattached to replication. If this occurs, an
+  <link linkend="event-notifications">event notification</link>
+  <varname>standby_disconnect_manual</varname> will be created.
+ </para>
+ <para>
+  Note that when a standby node is not streaming directly from its upstream
+  node, e.g. recovering WAL from an archive, <varname>apply_lag</varname> will always appear as
+  <literal>0 bytes</literal>.
+ </para>
+ <tip>
+  <para>
+   If monitoring history is enabled, the contents of the <literal>repmgr.monitoring_history</literal>
+   table will be replicated to attached standbys. This means there will be a small but
+   constant stream of replication activity which may not be desirable. To prevent
+   this, convert the table to an <literal>UNLOGGED</literal> one with:
+   <programlisting>
+     ALTER TABLE repmgr.monitoring_history SET UNLOGGED;</programlisting>
+  </para>
+  <para>
+   This will however mean that monitoring history will not be available on
+   another node following a failover, and the view <literal>repmgr.replication_status</literal>
+   will not work on standbys.
+  </para>
+ </tip>
+</chapter>

doc/repmgrd-network-split.sgml

@@ -0,0 +1,48 @@
+<chapter id="repmgrd-network-split" xreflabel="Handling network splits with repmgrd">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>network splits</secondary>
+ </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>
+
+</chapter>
+

doc/repmgrd-operation.sgml

@@ -1,386 +0,0 @@
-<chapter id="repmgrd-operation" xreflabel="repmgrd operation">
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>operation</secondary>
-  </indexterm>
-
-  <title>repmgrd operation</title>
-
-
-  <sect1 id="repmgrd-pausing">
-
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>pausing</secondary>
-  </indexterm>
-
-  <indexterm>
-    <primary>pausing repmgrd</primary>
-  </indexterm>
-
-  <title>Pausing repmgrd</title>
-
-  <para>
-    In normal operation, <application>repmgrd</application> 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
-    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
-    <link linkend="repmgrd-automatic-failover">configured for automatic failover</link>)
-    to prevent <application>repmgrd</application> from making unintentional changes to the
-    replication cluster.
-  </para>
-
-  <para>
-    From <link linkend="release-4.2">&repmgr; 4.2</link>, <application>repmgrd</application>
-    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.
-  </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
-      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>
-    <para>
-      In order to be able to pause/unpause <application>repmgrd</application>, following
-      prerequisites must be met:
-      <itemizedlist spacing="compact" mark="bullet">
-
-        <listitem>
-          <simpara><link linkend="release-4.2">&repmgr; 4.2</link> or later must be installed on all nodes.</simpara>
-        </listitem>
-
-        <listitem>
-          <simpara>The same major &repmgr; version (e.g. 4.2) must be installed on all nodes (and preferably the same minor version).</simpara>
-        </listitem>
-
-        <listitem>
-          <simpara>
-            PostgreSQL on all nodes must be accessible from the node where the
-            <literal>pause</literal>/<literal>unpause</literal> operation is executed, using the
-            <varname>conninfo</varname> string shown by <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>.
-          </simpara>
-        </listitem>
-      </itemizedlist>
-    </para>
-    <note>
-      <para>
-        These conditions are required for normal &repmgr; operation in any case.
-      </para>
-    </note>
-
-  </sect2>
-
-  <sect2 id="repmgrd-pausing-execution">
-    <title>Pausing/unpausing <application>repmgrd</application></title>
-    <para>
-      To pause <application>repmgrd</application>, 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
-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
-      <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?
-----+-------+---------+---------+---------+------+---------
- 1  | node1 | primary | running | running | 7851 | yes
- 2  | node2 | standby | running | running | 7889 | yes
- 3  | node3 | standby | running | running | 7918 | yes</programlisting>
-    </para>
-
-    <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.
-      </para>
-    </note>
-
-    <para>
-      If the primary (in this example, <literal>node1</literal>) is stopped, <application>repmgrd</application>
-      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] [INFO] checking state of node 1, 1 of 5 attempts
-[2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
-...
-[2018-09-20 12:22:24] [INFO] sleeping 1 seconds until next reconnection attempt
-[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] [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>
-      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.:
-   <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon unpause
-NOTICE: node 1 (node1) unpaused
-NOTICE: node 2 (node2) unpaused
-NOTICE: node 3 (node3) unpaused</programlisting>
-    </para>
-
-    <note>
-      <para>
-        If the previous primary is no longer accessible when <application>repmgrd</application>
-        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
-		<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
-      </para>
-      <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
-        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>
-
-    <para>
-      The pause state of each node will be stored over a PostgreSQL restart.
-    </para>
-
-	<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.
-	</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>.
-      </para>
-    </note>
-  </sect2>
-  </sect1>
-
-  <sect1 id="repmgrd-wal-replay-pause">
-    <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
-      automatically resume WAL replay.
-    </para>
-    <para>
-      This is because if WAL replay is paused, but WAL is pending replay,
-      PostgreSQL cannot be promoted until WAL replay is resumed.
-    </para>
-    <note>
-      <para>
-        <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command>
-        will refuse to promote a node in this state, as the PostgreSQL
-        <command>promote</command> command will not be acted on until
-        WAL replay is resumed, leaving the cluster in a potentially
-        unstable state. In this case it is up to the user to
-        decide whether to resume WAL replay.
-      </para>
-    </note>
-  </sect1>
-
-<sect1 id="repmgrd-degraded-monitoring" xreflabel="repmgrd degraded monitoring">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>degraded monitoring</secondary>
- </indexterm>
-
- <indexterm>
-   <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
-  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
-  to be resolved.
- </para>
- <para>
-  Situations where this happens are:
-  <itemizedlist spacing="compact" mark="bullet">
-
-   <listitem>
-    <simpara>a failover situation has occurred, no nodes in the primary node's location are visible</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>a failover situation has occurred, but no promotion candidate is available</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>a failover situation has occurred, but the promotion candidate could not be promoted</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>a failover situation has occurred, but the node was unable to follow the new primary</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>a failover situation has occurred, but no primary has become available</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>a failover situation has occurred, but automatic failover is not enabled for the node</simpara>
-   </listitem>
-
-   <listitem>
-    <simpara>repmgrd is monitoring the primary node, but it is not available (and no other node has been promoted as primary)</simpara>
-   </listitem>
-  </itemizedlist>
- </para>
-
- <para>
-  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 10:59:33] [INFO] checking state of node 1, 1 of 5 attempts
-    [2017-08-29 10:59:33] [INFO] sleeping 1 seconds until next reconnection attempt
-    (...)
-    [2017-08-29 10:59:37] [INFO] checking state of node 1, 5 of 5 attempts
-    [2017-08-29 10:59:37] [WARNING] unable to reconnect to node 1 after 5 attempts
-    [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 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>
-
- </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.
- </para>
-
- <note>
-   <para>
-     If <application>repmgrd</application> 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.
-   </para>
- </note>
-</sect1>
-
-
-<sect1 id="repmgrd-monitoring" xreflabel="Storing monitoring data">
- <indexterm>
-   <primary>repmgrd</primary>
-   <secondary>monitoring</secondary>
- </indexterm>
- <indexterm>
-   <primary>monitoring</primary>
-   <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>,
-  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
-  in the cluster.
- </para>
- <para>
-   The view <literal>replication_status</literal> shows the most recent state
-   for each node, e.g.:
-  <programlisting>
-    repmgr=# select * from repmgr.replication_status;
-    -[ RECORD 1 ]-------------+------------------------------
-    primary_node_id           | 1
-    standby_node_id           | 2
-    standby_name              | node2
-    node_type                 | standby
-    active                    | t
-    last_monitor_time         | 2017-08-24 16:28:41.260478+09
-    last_wal_primary_location | 0/6D57A00
-    last_wal_standby_location | 0/5000000
-    replication_lag           | 29 MB
-    replication_time_lag      | 00:00:11.736163
-    apply_lag                 | 15 MB
-    communication_time_lag    | 00:00:01.365643</programlisting>
- </para>
- <para>
-  The interval in which monitoring history is written is controlled by the
-  configuration parameter <varname>monitor_interval_secs</varname>;
-  default is 2.
- </para>
- <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">
-  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
-  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,
-  no failover action will be taken and the node will require manual intervention to
-  be reattached to replication. If this occurs, an
-  <link linkend="event-notifications">event notification</link>
-  <varname>standby_disconnect_manual</varname> will be created.
- </para>
- <para>
-  Note that when a standby node is not streaming directly from its upstream
-  node, e.g. recovering WAL from an archive, <varname>apply_lag</varname> will always appear as
-  <literal>0 bytes</literal>.
- </para>
- <tip>
-  <para>
-   If monitoring history is enabled, the contents of the <literal>repmgr.monitoring_history</literal>
-   table will be replicated to attached standbys. This means there will be a small but
-   constant stream of replication activity which may not be desirable. To prevent
-   this, convert the table to an <literal>UNLOGGED</literal> one with:
-   <programlisting>
-     ALTER TABLE repmgr.monitoring_history SET UNLOGGED;</programlisting>
-  </para>
-  <para>
-   This will however mean that monitoring history will not be available on
-   another node following a failover, and the view <literal>repmgr.replication_status</literal>
-   will not work on standbys.
-  </para>
- </tip>
-</sect1>
-
-
-</chapter>

doc/repmgrd-pausing.sgml

@@ -0,0 +1,178 @@
+<chapter id="repmgrd-pausing" xreflabel="Pausing repmgrd">
+
+  <indexterm>
+    <primary>repmgrd</primary>
+    <secondary>pausing</secondary>
+  </indexterm>
+
+  <indexterm>
+    <primary>pausing repmgrd</primary>
+  </indexterm>
+
+  <title>Pausing repmgrd</title>
+
+  <para>
+    In normal operation, <application>repmgrd</application> 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
+    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
+    <link linkend="repmgrd-automatic-failover">configured for automatic failover</link>)
+    to prevent <application>repmgrd</application> from making unintentional changes to the
+    replication cluster.
+  </para>
+
+  <para>
+    From <link linkend="release-4.2">&repmgr; 4.2</link>, <application>repmgrd</application>
+    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.
+  </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
+      once the &repmgr; packages for the new PostgreSQL major version have been installed.
+    </para>
+  </note>
+
+  <sect1 id="repmgrd-pausing-prerequisites">
+    <title>Prerequisites for pausing <application>repmgrd</application></title>
+    <para>
+      In order to be able to pause/unpause <application>repmgrd</application>, following
+      prerequisites must be met:
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara><link linkend="release-4.2">&repmgr; 4.2</link> or later must be installed on all nodes.</simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>The same major &repmgr; version (e.g. 4.2) must be installed on all nodes (and preferably the same minor version).</simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            PostgreSQL on all nodes must be accessible from the node where the
+            <literal>pause</literal>/<literal>unpause</literal> operation is executed, using the
+            <varname>conninfo</varname> string shown by <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>.
+          </simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+    <note>
+      <para>
+        These conditions are required for normal &repmgr; operation in any case.
+      </para>
+    </note>
+
+  </sect1>
+
+  <sect1 id="repmgrd-pausing-execution">
+    <title>Pausing/unpausing <application>repmgrd</application></title>
+    <para>
+      To pause <application>repmgrd</application>, 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
+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
+      <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?
+----+-------+---------+---------+---------+------+---------
+ 1  | node1 | primary | running | running | 7851 | yes
+ 2  | node2 | standby | running | running | 7889 | yes
+ 3  | node3 | standby | running | running | 7918 | yes</programlisting>
+    </para>
+
+    <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.
+      </para>
+    </note>
+
+    <para>
+      If the primary (in this example, <literal>node1</literal>) is stopped, <application>repmgrd</application>
+      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] [INFO] checking state of node 1, 1 of 5 attempts
+[2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
+...
+[2018-09-20 12:22:24] [INFO] sleeping 1 seconds until next reconnection attempt
+[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] [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>
+      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.:
+   <programlisting>
+$ repmgr -f /etc/repmgr.conf daemon unpause
+NOTICE: node 1 (node1) unpaused
+NOTICE: node 2 (node2) unpaused
+NOTICE: node 3 (node3) unpaused</programlisting>
+    </para>
+
+    <note>
+      <para>
+        If the previous primary is no longer accessible when <application>repmgrd</application>
+        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
+		<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
+      </para>
+      <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
+        candidate to the one intended by the administrator.
+      </para>
+    </note>
+
+  <sect2 id="repmgrd-pausing-details">
+    <title>Details on the <application>repmgrd</application> pausing mechanism</title>
+
+    <para>
+      The pause state of each node will be stored over a PostgreSQL restart.
+    </para>
+
+	<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.
+	</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>.
+      </para>
+    </note>
+  </sect2>
+  </sect1>
+</chapter>
+

doc/repmgrd-witness-server.sgml

@@ -0,0 +1,31 @@
+<chapter id="repmgrd-witness-server" xreflabel="Using a witness server with repmgrd">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>witness server</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 "split-brain" 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 "voting majority", 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 "casting vote" when
+   deciding which network segment has a majority. A witness server can
+   be set up using <xref linkend="repmgr-witness-register">. Note that 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>
+</chapter>

doc/switchover.sgml

@@ -137,8 +137,8 @@
 
    <note>
      <para>
-       If an exclusive backup is running on the current primary, or if WAL replay is paused on the standby,
-       &repmgr; will <emphasis>not</emphasis> perform the switchover.
+       If an exclusive backup is running on the current primary, &repmgr; will not perform the
+       switchover.
      </para>
    </note>
 
@@ -236,7 +236,7 @@
     </note>
     <para>
       For more details on <application>pg_rewind</application>, see:
-      <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html">https://www.postgresql.org/docs/current/app-pgrewind.html</ulink>.
+      <ulink url="https://www.postgresql.org/docs/current/static/app-pgrewind.html">https://www.postgresql.org/docs/current/static/app-pgrewind.html</ulink>.
     </para>
     <para>
       <application>pg_rewind</application> has been part of the core PostgreSQL distribution since
@@ -347,7 +347,7 @@
      <simpara>
       <command>pg_rewind</command> *requires* that either <varname>wal_log_hints</varname> is enabled, or that
       data checksums were enabled when the cluster was initialized. See the
-      <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html">pg_rewind documentation</ulink>
+      <ulink url="https://www.postgresql.org/docs/current/static/app-pgrewind.html">pg_rewind documentation</ulink>
       for details.
      </simpara>
     </listitem>
@@ -418,7 +418,7 @@ HINT: stop backup before attempting the switchover</programlisting>
        To proceed, either wait until the backup has finished, or cancel it with the command
        <command>SELECT pg_stop_backup()</command>. For more details see the PostgreSQL
        documentation section
-       <ulink url="https://www.postgresql.org/docs/current/continuous-archiving.html#BACKUP-LOWLEVEL-BASE-BACKUP-EXCLUSIVE">Making an exclusive low level backup</ulink>.
+       <ulink url="https://www.postgresql.org/docs/current/static/continuous-archiving.html#BACKUP-LOWLEVEL-BASE-BACKUP-EXCLUSIVE">Making an exclusive low level backup</ulink>.
      </para>
    </sect2>
  </sect1>

doc/upgrading-repmgr.sgml

@@ -247,7 +247,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     </simpara>
   </note>
   <para>
-    For further details please see the <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade documentation</ulink>.
+    For further details please see the <ulink url="https://www.postgresql.org/docs/current/static/pgupgrade.html">pg_upgrade documentation</ulink>.
   </para>
   <para>
     If replication slots are in use, bear in mind these will <emphasis>not</emphasis>

doc/version.sgml

@@ -0,0 +1 @@
+<!ENTITY repmgrversion "4.2">

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -48,6 +48,5 @@
 #define ERR_REJOIN_FAIL 24
 #define ERR_NODE_STATUS 25
 #define ERR_REPMGRD_PAUSE 26
-#define ERR_REPMGRD_SERVICE 27
 
 #endif							/* _ERRCODE_H_ */

expected/repmgr_extension.out

@@ -47,7 +47,7 @@ SELECT repmgr.am_bdr_failover_handler(NULL);
 SELECT repmgr.get_new_primary();
  get_new_primary 
 -----------------
-              -1
+                
 (1 row)
 
 SELECT repmgr.notify_follow_primary(-1);

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr--4.2--4.3.sql

@@ -1,17 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
-
-CREATE FUNCTION set_upstream_last_seen()
-  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_wal_receiver_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_wal_receiver_pid'
-  LANGUAGE C STRICT;

repmgr--4.3.sql

@@ -1,217 +0,0 @@
--- 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;
-
-
-/* XXX update upgrade scripts! */
-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()
-  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;
-
-
-/* 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

@@ -3,7 +3,7 @@
  *
  * Implements BDR-related actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-bdr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-bdr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-cluster.c

@@ -3,7 +3,7 @@
  *
  * Implements cluster information actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -24,7 +24,7 @@
 #include "repmgr-client-global.h"
 #include "repmgr-action-cluster.h"
 
-#define SHOW_HEADER_COUNT 8
+#define SHOW_HEADER_COUNT 7
 
 typedef enum
 {
@@ -34,7 +34,6 @@ typedef enum
 	SHOW_STATUS,
 	SHOW_UPSTREAM_NAME,
 	SHOW_LOCATION,
-	SHOW_PRIORITY,
 	SHOW_CONNINFO
 }			ShowHeader;
 
@@ -103,19 +102,12 @@ do_cluster_show(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* Initialize column headers  */
 	strncpy(headers_show[SHOW_ID].title, _("ID"), MAXLEN);
 	strncpy(headers_show[SHOW_NAME].title, _("Name"), MAXLEN);
 	strncpy(headers_show[SHOW_ROLE].title, _("Role"), MAXLEN);
 	strncpy(headers_show[SHOW_STATUS].title, _("Status"), MAXLEN);
 	strncpy(headers_show[SHOW_UPSTREAM_NAME].title, _("Upstream"), MAXLEN);
 	strncpy(headers_show[SHOW_LOCATION].title, _("Location"), MAXLEN);
-
-	if (runtime_options.compact == true)
-		strncpy(headers_show[SHOW_PRIORITY].title, _("Prio."), MAXLEN);
-	else
-		strncpy(headers_show[SHOW_PRIORITY].title, _("Priority"), MAXLEN);
-
 	strncpy(headers_show[SHOW_CONNINFO].title, _("Connection string"), MAXLEN);
 
 	/*
@@ -125,26 +117,12 @@ do_cluster_show(void)
 
 	for (i = 0; i < SHOW_HEADER_COUNT; i++)
 	{
-		headers_show[i].display = true;
-
-		if (runtime_options.compact == true)
-		{
-			if (i == SHOW_CONNINFO)
-			{
-				headers_show[i].display = false;
-			}
-		}
-
-		if (headers_show[i].display == true)
-		{
-			headers_show[i].max_length = strlen(headers_show[i].title);
-		}
+		headers_show[i].max_length = strlen(headers_show[i].title);
 	}
 
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
 		PQExpBufferData details;
-		PQExpBufferData buf;
 
 		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
 
@@ -155,12 +133,7 @@ do_cluster_show(void)
 		}
 		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->node_status = NODE_STATUS_DOWN;
 			cell->node_info->recovery_type = RECTYPE_UNKNOWN;
 
 			connection_error_found = true;
@@ -235,19 +208,6 @@ do_cluster_show(void)
 							}
 						}
 					}
-					/* 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
 					{
@@ -312,27 +272,6 @@ do_cluster_show(void)
 														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
@@ -347,12 +286,11 @@ do_cluster_show(void)
 						}
 						else
 						{
-								appendPQExpBufferStr(&details, "- failed");
-								error_found = true;
+							appendPQExpBufferStr(&details, "- failed");
+							error_found = true;
 						}
 					}
 				}
-
 				break;
 			case WITNESS:
 			case BDR:
@@ -370,20 +308,6 @@ do_cluster_show(void)
 							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
 					{
@@ -414,35 +338,15 @@ do_cluster_show(void)
 		PQfinish(cell->node_info->conn);
 		cell->node_info->conn = NULL;
 
-		initPQExpBuffer(&buf);
-		appendPQExpBuffer(&buf, "%i", cell->node_info->node_id);
-		headers_show[SHOW_ID].cur_length = strlen(buf.data);
-		termPQExpBuffer(&buf);
-
 		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);
-		appendPQExpBuffer(&buf, "%i", cell->node_info->priority);
-		headers_show[SHOW_PRIORITY].cur_length = strlen(buf.data);
-		termPQExpBuffer(&buf);
-
 		headers_show[SHOW_LOCATION].cur_length = strlen(cell->node_info->location);
-
-
-
 		headers_show[SHOW_CONNINFO].cur_length = strlen(cell->node_info->conninfo);
 
 		for (i = 0; i < SHOW_HEADER_COUNT; i++)
 		{
-			if (runtime_options.compact == true)
-			{
-				if (headers_show[i].display == false)
-					continue;
-			}
-
 			if (headers_show[i].cur_length > headers_show[i].max_length)
 			{
 				headers_show[i].max_length = headers_show[i].cur_length;
@@ -494,14 +398,7 @@ do_cluster_show(void)
 			printf("| %-*s ", headers_show[SHOW_STATUS].max_length, cell->node_info->details);
 			printf("| %-*s ", headers_show[SHOW_UPSTREAM_NAME].max_length, cell->node_info->upstream_node_name);
 			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_CONNINFO].display == true)
-			{
-				printf("| %-*s", headers_show[SHOW_CONNINFO].max_length, cell->node_info->conninfo);
-			}
-
-			puts("");
+			printf("| %-*s\n", headers_show[SHOW_CONNINFO].max_length, cell->node_info->conninfo);
 		}
 	}
 
@@ -1161,7 +1058,6 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 		(void) remote_command(host,
 							  runtime_options.remote_user,
 							  command.data,
-							  config_file_options.ssh_options,
 							  &command_output);
 
 		p = command_output.data;
@@ -1374,7 +1270,6 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 			(void) remote_command(host,
 								  runtime_options.remote_user,
 								  quoted_command.data,
-								  config_file_options.ssh_options,
 								  &command_output);
 
 			free_conninfo_params(&remote_conninfo);
@@ -1597,7 +1492,6 @@ do_cluster_help(void)
 	printf(_("  Configuration file or database connection required.\n"));
 	puts("");
 	printf(_("    --csv                     emit output as CSV (with a subset of fields)\n"));
-	printf(_("    --compact                 display only a subset of fields\n"));
 	puts("");
 
 	printf(_("CLUSTER MATRIX\n"));

repmgr-action-cluster.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-cluster.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-daemon.c

@@ -2,7 +2,7 @@
  * repmgr-action-daemon.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -18,17 +18,12 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <signal.h>
-#include <sys/stat.h>			/* for stat() */
-
 #include "repmgr.h"
 
 #include "repmgr-client-global.h"
 #include "repmgr-action-daemon.h"
 
-#define REPMGR_DAEMON_STOP_START_WAIT 15
-#define REPMGR_DAEMON_STATUS_START_HINT _("use \"repmgr daemon status\" to confirm that repmgrd was successfully started")
-#define REPMGR_DAEMON_STATUS_STOP_HINT _("use \"repmgr daemon status\" to confirm that repmgrd was successfully stopped")
+
 
 /*
  * Possibly also show:
@@ -43,15 +38,13 @@ typedef enum
 	STATUS_ID = 0,
 	STATUS_NAME,
 	STATUS_ROLE,
-	STATUS_PRIORITY,
 	STATUS_PG,
 	STATUS_RUNNING,
 	STATUS_PID,
-	STATUS_PAUSED,
-	STATUS_UPSTREAM_LAST_SEEN
+	STATUS_PAUSED
 } StatusHeader;
 
-#define STATUS_HEADER_COUNT 9
+#define STATUS_HEADER_COUNT 7
 
 struct ColHeader headers_status[STATUS_HEADER_COUNT];
 
@@ -68,7 +61,6 @@ do_daemon_status(void)
 	int i;
 	RepmgrdInfo **repmgrd_info;
 	ItemList	warnings = {NULL, NULL};
-	bool		connection_error_found = false;
 
 	/* Connect to local database to obtain cluster connection data */
 	log_verbose(LOG_INFO, _("connecting to database"));
@@ -91,27 +83,14 @@ 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);
-
-	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_PID].title, _("PID"), MAXLEN);
 	strncpy(headers_status[STATUS_PAUSED].title, _("Paused?"), MAXLEN);
 
-	if (runtime_options.compact == true)
-		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstr. last"), MAXLEN);
-	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;
 	}
 
 	i = 0;
@@ -119,24 +98,18 @@ do_daemon_status(void)
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
 		int j;
-		PQExpBufferData buf;
 
 		repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
 		repmgrd_info[i]->node_id = cell->node_info->node_id;
 		repmgrd_info[i]->pid = UNKNOWN_PID;
-		repmgrd_info[i]->recovery_type = RECTYPE_UNKNOWN;
 		repmgrd_info[i]->paused = false;
 		repmgrd_info[i]->running = false;
 		repmgrd_info[i]->pg_running = true;
-		repmgrd_info[i]->wal_paused_pending_wal = false;
-		repmgrd_info[i]->upstream_last_seen = -1;
 
 		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
 
 		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 		{
-			connection_error_found = true;
-
 			if (runtime_options.verbose)
 			{
 				char		error[MAXLEN];
@@ -187,55 +160,16 @@ do_daemon_status(void)
 
 			repmgrd_info[i]->paused = repmgrd_is_paused(cell->node_info->conn);
 
-			repmgrd_info[i]->recovery_type = get_recovery_type(cell->node_info->conn);
-
-			if (repmgrd_info[i]->recovery_type == RECTYPE_STANDBY)
-			{
-				repmgrd_info[i]->wal_paused_pending_wal = is_wal_replay_paused(cell->node_info->conn, true);
-
-				if (repmgrd_info[i]->wal_paused_pending_wal == 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);
-				}
-			}
-
-			repmgrd_info[i]->upstream_last_seen = get_upstream_last_seen(cell->node_info->conn, cell->node_info->type);
-			if (repmgrd_info[i]->upstream_last_seen < 0)
-			{
-				maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, "%s", _("n/a"));
-			}
-			else
-			{
-				if (runtime_options.compact == true)
-				{
-					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i sec(s) ago"), repmgrd_info[i]->upstream_last_seen);
-				}
-				else
-				{
-					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i second(s) ago"), repmgrd_info[i]->upstream_last_seen);
-				}
-			}
-
 			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));
-
-		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_UPSTREAM_LAST_SEEN].cur_length = strlen(repmgrd_info[i]->upstream_last_seen_text);
-
 		for (j = 0; j < STATUS_HEADER_COUNT; j++)
 		{
 			if (headers_status[j].cur_length > headers_status[j].max_length)
@@ -259,61 +193,38 @@ do_daemon_status(void)
 	{
 		if (runtime_options.output_mode == OM_CSV)
 		{
-			int running = repmgrd_info[i]->running ? 1 : 0;
-			int paused = repmgrd_info[i]->paused ? 1 : 0;
-
-			/* If PostgreSQL is not running, repmgrd status is unknown */
-			if (repmgrd_info[i]->pg_running == false)
-			{
-				running = -1;
-				paused = -1;
-			}
-
-			printf("%i,%s,%s,%i,%i,%i,%i,%i,%i\n",
+			printf("%i,%s,%s,%i,%i,%i,%i\n",
 				   cell->node_info->node_id,
 				   cell->node_info->node_name,
 				   get_node_type_string(cell->node_info->type),
 				   repmgrd_info[i]->pg_running ? 1 : 0,
-				   running,
+				   repmgrd_info[i]->running ? 1 : 0,
 				   repmgrd_info[i]->pid,
-				   paused,
-				   cell->node_info->priority,
-				   repmgrd_info[i]->pid == UNKNOWN_PID
-				     ? -1
-				     : repmgrd_info[i]->upstream_last_seen);
+				   repmgrd_info[i]->paused ? 1 : 0);
 		}
 		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_PID].max_length, repmgrd_info[i]->pid_text);
 
 			if (repmgrd_info[i]->pid == UNKNOWN_PID)
-			{
-				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, _("n/a"));
-				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, _("n/a"));
-
-			}
+				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, "n/a");
 			else
-			{
-				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, repmgrd_info[i]->paused ? _("yes") : _("no"));
-
-				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, repmgrd_info[i]->upstream_last_seen_text);
-			}
+				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, repmgrd_info[i]->paused ? "yes" : "no");
 
 			printf("\n");
 		}
 
-		pfree(repmgrd_info[i]);
+		free(repmgrd_info[i]);
 		i++;
 	}
 
-	pfree(repmgrd_info);
+	free(repmgrd_info);
 
 	/* emit any warnings */
 
@@ -327,7 +238,7 @@ do_daemon_status(void)
 			printf(_("  - %s\n"), cell->string);
 		}
 
-		if (runtime_options.verbose == false && connection_error_found == true)
+		if (runtime_options.verbose == false)
 		{
 			log_hint(_("execute with --verbose option to see connection error messages"));
 		}
@@ -353,9 +264,18 @@ _do_repmgr_pause(bool pause)
 	PGconn	   *conn = NULL;
 	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
 	NodeInfoListCell *cell = NULL;
+	RepmgrdInfo **repmgrd_info;
 	int i;
 	int error_nodes = 0;
 
+	repmgrd_info = (RepmgrdInfo **) pg_malloc0(sizeof(RepmgrdInfo *) * nodes.node_count);
+
+	if (repmgrd_info == NULL)
+	{
+		log_error(_("unable to allocate memory"));
+		exit(ERR_OUT_OF_MEMORY);
+	}
+
 	/* Connect to local database to obtain cluster connection data */
 	log_verbose(LOG_INFO, _("connecting to database"));
 
@@ -370,6 +290,9 @@ _do_repmgr_pause(bool pause)
 
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
+		repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
+		repmgrd_info[i]->node_id = cell->node_info->node_id;
+
 		log_verbose(LOG_DEBUG, "pausing node %i (%s)",
 					cell->node_info->node_id,
 					cell->node_info->node_name);
@@ -460,285 +383,6 @@ fetch_node_records(PGconn *conn, NodeInfoList *node_list)
 }
 
 
-void
-do_daemon_start(void)
-{
-	PGconn	   *conn = NULL;
-	PQExpBufferData repmgrd_command;
-	PQExpBufferData output_buf;
-	bool		success;
-
-	if (config_file_options.repmgrd_service_start_command[0] == '\0')
-	{
-		log_error(_("\"repmgrd_service_start_command\" is not set"));
-		log_hint(_("set \"repmgrd_service_start_command\" in \"repmgr.conf\""));
-		exit(ERR_BAD_CONFIG);
-	}
-
-	log_verbose(LOG_INFO, _("connecting to local node"));
-
-	conn = establish_db_connection(config_file_options.conninfo, false);
-
-	if (PQstatus(conn) != CONNECTION_OK)
-	{
-		/* TODO: if PostgreSQL is not available, have repmgrd loop and retry connection */
-		log_error(_("unable to connect to local node"));
-		log_detail(_("PostgreSQL must be running before \"repmgrd\" can be started"));
-		exit(ERR_DB_CONN);
-	}
-
-	/*
-	 * if local connection available, check if repmgr.so is installed, and
-	 * whether repmgrd is running
-	 */
-	check_shared_library(conn);
-
-	if (is_repmgrd_running(conn) == true)
-	{
-		pid_t		pid = UNKNOWN_PID;
-
-		log_error(_("repmgrd appears to be running already"));
-
-		pid = repmgrd_get_pid(conn);
-
-		if (pid != UNKNOWN_PID)
-			log_detail(_("repmgrd PID is %i"), pid);
-		else
-			log_warning(_("unable to determine repmgrd PID"));
-
-		PQfinish(conn);
-		exit(ERR_REPMGRD_SERVICE);
-	}
-
-	PQfinish(conn);
-
-
-	initPQExpBuffer(&repmgrd_command);
-	appendPQExpBufferStr(&repmgrd_command,
-						 config_file_options.repmgrd_service_start_command);
-
-	if (runtime_options.dry_run == true)
-	{
-		log_info(_("prerequisites for starting repmgrd met"));
-		log_detail("following command would be executed:\n  %s", repmgrd_command.data);
-		exit(SUCCESS);
-	}
-
-	log_notice(_("executing: \"%s\""), repmgrd_command.data);
-
-	initPQExpBuffer(&output_buf);
-
-	success = local_command(repmgrd_command.data, &output_buf);
-	termPQExpBuffer(&repmgrd_command);
-
-	if (success == false)
-	{
-		log_error(_("unable to start repmgrd"));
-		if (output_buf.data[0] != '\0')
-			log_detail("%s", output_buf.data);
-		termPQExpBuffer(&output_buf);
-		exit(ERR_REPMGRD_SERVICE);
-	}
-
-	termPQExpBuffer(&output_buf);
-
-	if (runtime_options.no_wait == true || runtime_options.wait == 0)
-	{
-		log_hint(REPMGR_DAEMON_STATUS_START_HINT);
-	}
-	else
-	{
-		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
-
-		if (runtime_options.wait_provided)
-			timeout = runtime_options.wait;
-
-		conn = establish_db_connection(config_file_options.conninfo, false);
-
-		if (PQstatus(conn) != CONNECTION_OK)
-		{
-			log_notice(_("unable to connect to local node"));
-			log_hint(REPMGR_DAEMON_STATUS_START_HINT);
-			exit(ERR_DB_CONN);
-		}
-
-		for (;;)
-		{
-			if (is_repmgrd_running(conn) == true)
-			{
-				log_notice(_("repmgrd was successfully started"));
-				PQfinish(conn);
-				break;
-			}
-
-			if (i == timeout)
-			{
-				PQfinish(conn);
-				log_error(_("repmgrd does not appear to have started after %i seconds"),
-						  timeout);
-				log_hint(REPMGR_DAEMON_STATUS_START_HINT);
-				exit(ERR_REPMGRD_SERVICE);
-			}
-
-			log_debug("sleeping 1 second; %i of %i attempts to determine if repmgrd is running",
-					  i, runtime_options.wait);
-			sleep(1);
-			i++;
-		}
-	}
-}
-
-
-void do_daemon_stop(void)
-{
-	PGconn	   *conn = NULL;
-	PQExpBufferData repmgrd_command;
-	PQExpBufferData output_buf;
-	bool		success;
-	bool		have_db_connection = true;
-	pid_t		pid = UNKNOWN_PID;
-
-	if (config_file_options.repmgrd_service_stop_command[0] == '\0')
-	{
-		log_error(_("\"repmgrd_service_stop_command\" is not set"));
-		log_hint(_("set \"repmgrd_service_stop_command\" in \"repmgr.conf\""));
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/*
-	 * if local connection available, check if repmgr.so is installed, and
-	 * whether repmgrd is running
-	 */
-	log_verbose(LOG_INFO, _("connecting to local node"));
-
-	conn = establish_db_connection(config_file_options.conninfo, false);
-
-	if (PQstatus(conn) != CONNECTION_OK)
-	{
-		/*
-		 * a PostgreSQL connection is not required to stop repmgrd,
-		 */
-		log_warning(_("unable to connect to local node"));
-		have_db_connection = false;
-	}
-	else
-	{
-		check_shared_library(conn);
-
-		if (is_repmgrd_running(conn) == false)
- 		{
-			log_error(_("repmgrd appears to be stopped already"));
-			PQfinish(conn);
-			exit(ERR_REPMGRD_SERVICE);
-		}
-
-		/* Attempt to fetch the PID, in case we need it later */
-		pid = repmgrd_get_pid(conn);
-		log_debug("retrieved pid is %i", pid);
-	}
-
-	PQfinish(conn);
-
-	initPQExpBuffer(&repmgrd_command);
-
-	appendPQExpBufferStr(&repmgrd_command,
-						 config_file_options.repmgrd_service_stop_command);
-
-	if (runtime_options.dry_run == true)
-	{
-		log_info(_("prerequisites for stopping repmgrd met"));
-		log_detail("following command would be executed:\n  %s", repmgrd_command.data);
-		exit(SUCCESS);
-	}
-
-	log_notice(_("executing: \"%s\""), repmgrd_command.data);
-
-	initPQExpBuffer(&output_buf);
-
-	success = local_command(repmgrd_command.data, &output_buf);
-	termPQExpBuffer(&repmgrd_command);
-
-	if (success == false)
-	{
-		log_error(_("unable to stop repmgrd"));
-		if (output_buf.data[0] != '\0')
-			log_detail("%s", output_buf.data);
-		termPQExpBuffer(&output_buf);
-		exit(ERR_REPMGRD_SERVICE);
-	}
-
-	termPQExpBuffer(&output_buf);
-
-	if (runtime_options.no_wait == true || runtime_options.wait == 0)
-	{
-		if (have_db_connection == true)
-			log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
-	}
-	else
-	{
-		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
-		/*
-		 *
-		 */
-		if (pid == UNKNOWN_PID)
-		{
-			/*
-			 * XXX attempt to get pidfile from config
-			 *   and get contents
-			 *   ( see check_and_create_pid_file() )
-			 * if PID still unknown, exit here
-			 */
-			log_warning(_("unable to determine repmgrd PID"));
-
-			if (have_db_connection == true)
-				log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
-
-			exit(ERR_REPMGRD_SERVICE);
-		}
-
-		if (runtime_options.wait_provided)
-			timeout = runtime_options.wait;
-
-		for (;;)
-		{
-			if (kill(pid, 0) == -1)
-			{
-				if (errno == ESRCH)
-				{
-					log_notice(_("repmgrd was successfully stopped"));
-					exit(SUCCESS);
-				}
-				else
-				{
-					log_error(_("unable to determine status of process with PID %i"), pid);
-					log_detail("%s", strerror(errno));
-					exit(ERR_REPMGRD_SERVICE);
-				}
-			}
-
-
-			if (i == timeout)
-			{
-				log_error(_("repmgrd does not appear to have stopped after %i seconds"),
-						  timeout);
-
-				if (have_db_connection == true)
-					log_hint(REPMGR_DAEMON_STATUS_START_HINT);
-
-				exit(ERR_REPMGRD_SERVICE);
-			}
-
-			log_debug("sleeping 1 second; %i of %i attempts to determine if repmgrd with PID %i is running",
-					  i, timeout, pid);
-			sleep(1);
-			i++;
-		}
-	}
-}
-
-
 void do_daemon_help(void)
 {
 	print_help_header();
@@ -747,8 +391,6 @@ void do_daemon_help(void)
 	printf(_("    %s [OPTIONS] daemon status\n"),  progname());
 	printf(_("    %s [OPTIONS] daemon pause\n"),   progname());
 	printf(_("    %s [OPTIONS] daemon unpause\n"), progname());
-	printf(_("    %s [OPTIONS] daemon start\n"),   progname());
-	printf(_("    %s [OPTIONS] daemon stop\n"),    progname());
 	puts("");
 
 	printf(_("DAEMON STATUS\n"));
@@ -759,24 +401,6 @@ void do_daemon_help(void)
 	printf(_("    --verbose                 show text of database connection error messages\n"));
 	puts("");
 
-	printf(_("DAEMON START\n"));
-	puts("");
-	printf(_("  \"daemon start\" attempts to start repmgrd\n"));
-	puts("");
-	printf(_("    --dry-run               check prerequisites but don't start repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
-	printf(_("    --no-wait               don't wait for repmgrd to start\n"));
-	puts("");
-
-	printf(_("DAEMON STOP\n"));
-	puts("");
-	printf(_("  \"daemon stop\" attempts to stop repmgrd\n"));
-	puts("");
-	printf(_("    --dry-run               check prerequisites but don't stop repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
-	printf(_("    --no-wait               don't wait for repmgrd to stop\n"));
-	puts("");
-
 	printf(_("DAEMON PAUSE\n"));
 	puts("");
 	printf(_("  \"daemon pause\" instructs repmgrd on each node to pause failover detection\n"));
@@ -784,12 +408,13 @@ void do_daemon_help(void)
 	printf(_("    --dry-run               check if nodes are reachable but don't pause repmgrd\n"));
 	puts("");
 
-	printf(_("DAEMON UNPAUSE\n"));
+	printf(_("DAEMON PAUSE\n"));
 	puts("");
 	printf(_("  \"daemon unpause\"  instructs repmgrd on each node to resume failover detection\n"));
 	puts("");
 	printf(_("    --dry-run               check if nodes are reachable but don't unpause repmgrd\n"));
 	puts("");
 
+
 	puts("");
 }

repmgr-action-daemon.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-daemon.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -23,8 +23,6 @@
 extern void do_daemon_status(void);
 extern void do_daemon_pause(void);
 extern void do_daemon_unpause(void);
-extern void do_daemon_start(void);
-extern void do_daemon_stop(void);
 
 extern void do_daemon_help(void);
 #endif

repmgr-action-node.c

@@ -3,7 +3,7 @@
  *
  * Implements actions available for any kind of node
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -48,7 +48,6 @@ static CheckStatus do_node_check_replication_lag(PGconn *conn, OutputMode mode,
 static CheckStatus do_node_check_role(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
-static CheckStatus do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 
 /*
  * NODE STATUS
@@ -67,6 +66,7 @@ do_node_status(void)
 	PGconn	   *conn = NULL;
 
 	t_node_info node_info = T_NODE_INFO_INITIALIZER;
+	char		server_version[MAXLEN];
 	char		cluster_size[MAXLEN];
 	PQExpBufferData output;
 
@@ -76,29 +76,21 @@ do_node_status(void)
 
 	ItemList	warnings = {NULL, NULL};
 	RecoveryType recovery_type = RECTYPE_UNKNOWN;
-	ReplInfo	replication_info;
+	ReplInfo	replication_info = T_REPLINFO_INTIALIZER;
 	t_recovery_conf recovery_conf = T_RECOVERY_CONF_INITIALIZER;
 
 	char		data_dir[MAXPGPATH] = "";
-	int			server_version_num = UNKNOWN_SERVER_VERSION_NUM;
-	char		server_version_str[MAXVERSIONSTR] = "";
 
-	/*
-	 * A database connection is *not* required for this check
-	 */
 	if (runtime_options.is_shutdown_cleanly == true)
 	{
 		return _do_node_status_is_shutdown_cleanly();
 	}
 
-	init_replication_info(&replication_info);
-
-
 	/* config file required, so we should have "conninfo" and "data_directory" */
 	conn = establish_db_connection(config_file_options.conninfo, true);
 	strncpy(data_dir, config_file_options.data_directory, MAXPGPATH);
 
-	server_version_num = get_server_version(conn, server_version_str);
+	server_version_num = get_server_version(conn, NULL);
 
 	/* check node exists  */
 
@@ -109,16 +101,18 @@ do_node_status(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	(void) get_server_version(conn, server_version);
+
 	if (get_cluster_size(conn, cluster_size) == false)
 		strncpy(cluster_size, _("unknown"), MAXLEN);
 
 	recovery_type = get_recovery_type(conn);
 
-	get_node_replication_stats(conn, &node_info);
+	get_node_replication_stats(conn, server_version_num, &node_info);
 
 	key_value_list_set(&node_status,
 					   "PostgreSQL version",
-					   server_version_str);
+					   server_version);
 
 	key_value_list_set(&node_status,
 					   "Total data size",
@@ -225,27 +219,19 @@ do_node_status(void)
 
 		ready_files = get_ready_archive_files(conn, data_dir);
 
-		if (ready_files == ARCHIVE_STATUS_DIR_ERROR)
+		if (runtime_options.output_mode == OM_CSV)
 		{
-			item_list_append_format(&warnings,
-									"- unable to check archive_status directory\n");
+			key_value_list_set_format(&node_status,
+									  "WALs pending archiving",
+									  "%i",
+									  ready_files);
 		}
 		else
 		{
-			if (runtime_options.output_mode == OM_CSV)
-			{
-				key_value_list_set_format(&node_status,
-										  "WALs pending archiving",
-										  "%i",
-										  ready_files);
-			}
-			else
-			{
-				key_value_list_set_format(&node_status,
-										  "WALs pending archiving",
-										  "%i pending files",
-										  ready_files);
-			}
+			key_value_list_set_format(&node_status,
+									  "WALs pending archiving",
+									  "%i pending files",
+									  ready_files);
 		}
 
 		if (guc_set(conn, "archive_mode", "=", "off"))
@@ -368,7 +354,7 @@ do_node_status(void)
 		initPQExpBuffer(&slotinfo);
 
 		appendPQExpBuffer(&slotinfo,
-						  "%i physical (of maximal %i; %i missing)",
+						  "%i (of maximal %i; %i missing)",
 						  node_info.active_replication_slots + node_info.inactive_replication_slots,
 						  node_info.max_replication_slots,
 						  missing_slots.node_count);
@@ -385,13 +371,13 @@ do_node_status(void)
 							  node_info.inactive_replication_slots);
 
 			item_list_append_format(&warnings,
-									_("- node has %i inactive physical replication slots"),
+									_("- node has %i inactive replication slots"),
 									node_info.inactive_replication_slots);
 
 			for (cell = inactive_replication_slots.head; cell; cell = cell->next)
 			{
 				item_list_append_format(&warnings,
-										"  - %s", cell->key);
+										"  - %s (%s)", cell->key, cell->value);
 			}
 
 			key_value_list_free(&inactive_replication_slots);
@@ -413,7 +399,7 @@ do_node_status(void)
 								  node_info.upstream_node_name,
 								  node_info.upstream_node_id);
 
-		get_replication_info(conn, node_info.type, &replication_info);
+		get_replication_info(conn, &replication_info);
 
 		key_value_list_set_format(&node_status,
 								  "Replication lag",
@@ -668,17 +654,27 @@ _do_node_status_is_shutdown_cleanly(void)
 		node_status = NODE_STATUS_DOWN;
 	}
 
-	log_verbose(LOG_DEBUG, "node status determined as: %s",
-				print_node_status(node_status));
+	log_verbose(LOG_DEBUG, "node status determined as: %s", print_node_status(node_status));
 
-	appendPQExpBuffer(&output,
-					  "%s", print_node_status(node_status));
-
-	if (node_status == NODE_STATUS_DOWN)
+	switch (node_status)
 	{
-		appendPQExpBuffer(&output,
-						  " --last-checkpoint-lsn=%X/%X",
-						  format_lsn(checkPoint));
+		case NODE_STATUS_UP:
+			appendPQExpBufferStr(&output, "RUNNING");
+			break;
+		case NODE_STATUS_SHUTTING_DOWN:
+			appendPQExpBufferStr(&output, "SHUTTING_DOWN");
+			break;
+		case NODE_STATUS_DOWN:
+			appendPQExpBuffer(&output,
+							  "SHUTDOWN --last-checkpoint-lsn=%X/%X",
+							  format_lsn(checkPoint));
+			break;
+		case NODE_STATUS_UNCLEAN_SHUTDOWN:
+			appendPQExpBufferStr(&output, "UNCLEAN_SHUTDOWN");
+			break;
+		case NODE_STATUS_UNKNOWN:
+			appendPQExpBufferStr(&output, "UNKNOWN");
+			break;
 	}
 
 	printf("%s\n", output.data);
@@ -729,8 +725,10 @@ do_node_check(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	server_version_num = get_server_version(conn, NULL);
+
 	/* add replication statistics to node record */
-	get_node_replication_stats(conn, &node_info);
+	get_node_replication_stats(conn, server_version_num, &node_info);
 
 	/*
 	 * handle specific checks ======================
@@ -794,16 +792,6 @@ do_node_check(void)
 		exit(return_code);
 	}
 
-	if (runtime_options.data_directory_config == true)
-	{
-		return_code = do_node_check_data_directory(conn,
-												   runtime_options.output_mode,
-												   &node_info,
-												   NULL);
-		PQfinish(conn);
-		exit(return_code);
-	}
-
 
 	if (runtime_options.output_mode == OM_NAGIOS)
 	{
@@ -836,9 +824,6 @@ do_node_check(void)
 	if (do_node_check_missing_slots(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
 		issue_detected = true;
 
-	if (do_node_check_data_directory(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
-		issue_detected = true;
-
 	if (runtime_options.output_mode == OM_CSV)
 	{
 		appendPQExpBuffer(&output,
@@ -1460,9 +1445,11 @@ do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_i
 	switch (mode)
 	{
 		case OM_OPTFORMAT:
-			printf("--status=%s %s\n",
-				   output_check_status(status),
-				   details.data);
+			{
+				printf("--status=%s %s\n",
+					   output_check_status(status),
+					   details.data);
+			}
 			break;
 		case OM_NAGIOS:
 			printf("REPMGR_REPLICATION_LAG %s: %s\n",
@@ -1631,7 +1618,7 @@ do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, Check
 
 	initPQExpBuffer(&details);
 
-	if (PQserverVersion(conn) < 90400)
+	if (server_version_num < 90400)
 	{
 		appendPQExpBufferStr(&details,
 							 _("replication slots not available for this PostgreSQL version"));
@@ -1639,12 +1626,12 @@ do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, Check
 	else if (node_info->total_replication_slots == 0)
 	{
 		appendPQExpBufferStr(&details,
-							 _("node has no physical replication slots"));
+							 _("node has no replication slots"));
 	}
 	else if (node_info->inactive_replication_slots == 0)
 	{
 		appendPQExpBuffer(&details,
-						  _("%i of %i physical replication slots are active"),
+						  _("%i of %i replication slots are active"),
 						  node_info->total_replication_slots,
 						  node_info->total_replication_slots);
 	}
@@ -1653,7 +1640,7 @@ do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, Check
 		status = CHECK_STATUS_CRITICAL;
 
 		appendPQExpBuffer(&details,
-						  _("%i of %i physical replication slots are inactive"),
+						  _("%i of %i replication slots are inactive"),
 						  node_info->inactive_replication_slots,
 						  node_info->total_replication_slots);
 	}
@@ -1707,7 +1694,7 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 
 	initPQExpBuffer(&details);
 
-	if (PQserverVersion(conn) < 90400)
+	if (server_version_num < 90400)
 	{
 		appendPQExpBufferStr(&details,
 							 _("replication slots not available for this PostgreSQL version"));
@@ -1721,7 +1708,7 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 		if (missing_slots.node_count == 0)
 		{
 			appendPQExpBufferStr(&details,
-								 _("node has no missing physical replication slots"));
+								 _("node has no missing replication slots"));
 		}
 		else
 		{
@@ -1731,7 +1718,7 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 			status = CHECK_STATUS_CRITICAL;
 
 			appendPQExpBuffer(&details,
-							  _("%i physical replication slots are missing"),
+							  _("%i replication slots are missing"),
 							  missing_slots.node_count);
 
 			if (missing_slots.node_count)
@@ -1792,7 +1779,7 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 			if (list_output != NULL)
 			{
 				check_status_list_set(list_output,
-									  "Missing physical replication slots",
+									  "Missing replication slots",
 									  status,
 									  details.data);
 			}
@@ -1813,135 +1800,6 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 }
 
 
-CheckStatus
-do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
-{
-	CheckStatus status = CHECK_STATUS_OK;
-	char actual_data_directory[MAXPGPATH] = "";
-	PQExpBufferData details;
-
-	if (mode == OM_CSV && list_output == NULL)
-	{
-		log_error(_("--csv output not provided with --data-directory-config option"));
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	initPQExpBuffer(&details);
-	/*
-	 * Check actual data directory matches that in repmgr.conf; note this requires
-	 * a superuser connection
-	 */
-
-	if (is_superuser_connection(conn, NULL) == true)
-	{
-		/* we expect to have a database connection */
-		if (get_pg_setting(conn, "data_directory", actual_data_directory) == false)
-		{
-			appendPQExpBuffer(&details,
-							  _("unable to determine current \"data_directory\""));
-			status = CHECK_STATUS_UNKNOWN;
-		}
-
-		if (strncmp(actual_data_directory, config_file_options.data_directory, MAXPGPATH) != 0)
-		{
-			if (mode != OM_NAGIOS)
-			{
-				appendPQExpBuffer(&details,
-								  _("configured \"data_directory\" is \"%s\"; "),
-								  config_file_options.data_directory);
-			}
-
-			appendPQExpBuffer(&details,
-							  "actual data directory is \"%s\"",
-							  actual_data_directory);
-
-			status = CHECK_STATUS_CRITICAL;
-		}
-		else
-		{
-			appendPQExpBuffer(&details,
-							  _("configured \"data_directory\" is \"%s\""),
-							  config_file_options.data_directory);
-		}
-	}
-	/*
-	 * If no superuser connection available, sanity-check that the configuration directory looks
-	 * like a PostgreSQL directory and hope it's the right one.
-	 */
-	else
-	{
-		if (mode == OM_TEXT)
-		{
-			log_info(_("connection is not a superuser connection, falling back to simple check"));
-
-			/* XXX add -S/--superuser option */
-			if (PQserverVersion(conn) >= 100000)
-			{
-				log_hint(_("add the \"%s\" user to group \"pg_read_all_settings\""),
-						   PQuser(conn));
-			}
-		}
-
-		if (is_pg_dir(config_file_options.data_directory) == false)
-		{
-			if (mode == OM_NAGIOS)
-			{
-				appendPQExpBufferStr(&details,
-								  _("configured \"data_directory\" is not a PostgreSQL data directory"));
-			}
-			else
-			{
-				appendPQExpBuffer(&details,
-								  _("configured \"data_directory\" \"%s\" is not a PostgreSQL data directory"),
-								  actual_data_directory);
-			}
-
-			status = CHECK_STATUS_CRITICAL;
-		}
-	}
-
-	switch (mode)
-	{
-		case OM_OPTFORMAT:
-			printf("--configured-data-directory=%s\n",
-				   output_check_status(status));
-			break;
-		case OM_NAGIOS:
-			printf("REPMGR_DATA_DIRECTORY %s: %s",
-				   output_check_status(status),
-				   config_file_options.data_directory);
-
-			if (status == CHECK_STATUS_CRITICAL)
-			{
-				printf(" | %s", details.data);
-			}
-			puts("");
-			break;
-		case OM_CSV:
-		case OM_TEXT:
-			if (list_output != NULL)
-			{
-				check_status_list_set(list_output,
-									  "Configured data directory",
-									  status,
-									  details.data);
-			}
-			else
-			{
-				printf("%s (%s)\n",
-					   output_check_status(status),
-					   details.data);
-			}
-		default:
-			break;
-	}
-
-	termPQExpBuffer(&details);
-
-	return status;
-}
-
 
 void
 do_node_service(void)
@@ -2135,9 +1993,7 @@ void
 do_node_rejoin(void)
 {
 	PGconn	   *upstream_conn = NULL;
-	RecoveryType primary_recovery_type = RECTYPE_UNKNOWN;
-	PGconn	   *primary_conn = NULL;
-
+	RecoveryType upstream_recovery_type = RECTYPE_UNKNOWN;
 	DBState		db_state;
 	PGPing		status;
 	bool		is_shutdown = true;
@@ -2149,9 +2005,11 @@ do_node_rejoin(void)
 	t_node_info primary_node_record = T_NODE_INFO_INITIALIZER;
 
 	bool		success = true;
+	int			server_version_num = UNKNOWN_SERVER_VERSION_NUM;
 	int			follow_error_code = SUCCESS;
 
 	/* check node is not actually running */
+
 	status = PQping(config_file_options.conninfo);
 
 	switch (status)
@@ -2177,7 +2035,7 @@ do_node_rejoin(void)
 		log_error(_("database is still running in state \"%s\""),
 				  describe_db_state(db_state));
 		log_hint(_("\"repmgr node rejoin\" cannot be executed on a running node"));
-		exit(ERR_REJOIN_FAIL);
+		exit(ERR_BAD_CONFIG);
 	}
 
 	/* check if cleanly shut down */
@@ -2196,15 +2054,18 @@ do_node_rejoin(void)
 				log_detail(_("pg_rewind will not be able to run"));
 			}
 			log_hint(_("database should be restarted then shut down cleanly after crash recovery completes"));
-			exit(ERR_REJOIN_FAIL);
+			exit(ERR_BAD_CONFIG);
 		}
 	}
 
+
 	/* check provided upstream connection */
 	upstream_conn = establish_db_connection_by_params(&source_conninfo, true);
 
 	/* sanity checks for 9.3 */
-	if (PQserverVersion(upstream_conn) < 90400)
+	server_version_num = get_server_version(upstream_conn, NULL);
+
+	if (server_version_num < 90400)
 		check_93_config();
 
 	if (get_primary_node_record(upstream_conn, &primary_node_record) == false)
@@ -2215,85 +2076,40 @@ do_node_rejoin(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	PQfinish(upstream_conn);
+
 	/* connect to registered primary and check it's not in recovery */
-	primary_conn = establish_db_connection(primary_node_record.conninfo, false);
+	upstream_conn = establish_db_connection(primary_node_record.conninfo, false);
 
-	if (PQstatus(primary_conn) != CONNECTION_OK)
+	if (PQstatus(upstream_conn) != CONNECTION_OK)
 	{
-		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 primary \"%s\" (node ID: %i)"),
 				  primary_node_record.node_name,
 				  primary_node_record.node_id);
-		log_detail(_("registered primary node conninfo is: \"%s\""),
+		log_detail(_("primay node conninfo is: \"%s\""),
 				   primary_node_record.conninfo);
-		/*
-		 * Catch case where provided upstream is not in recovery, but is also
-		 * not registered as primary
-		 */
-
-		if (upstream_recovery_type == RECTYPE_PRIMARY)
-		{
-			log_warning(_("provided upstream connection string is for a server which is not in recovery, but not registered as primary"));
-			log_hint(_("fix repmgr metadata configuration before continuing"));
-		}
-
-		PQfinish(upstream_conn);
 		exit(ERR_BAD_CONFIG);
 	}
 
-	PQfinish(upstream_conn);
+	upstream_recovery_type = get_recovery_type(upstream_conn);
 
-	primary_recovery_type = get_recovery_type(primary_conn);
-
-	if (primary_recovery_type != RECTYPE_PRIMARY)
+	if (upstream_recovery_type != RECTYPE_PRIMARY)
 	{
-		log_error(_("primary server is registered as node \"%s\" (ID: %i), but server is not a primary"),
+		log_error(_("primary server is registered node \"%s\" (ID: %i), but server is not a primary"),
 				  primary_node_record.node_name,
 				  primary_node_record.node_id);
 		/* TODO: hint about checking cluster */
-		PQfinish(primary_conn);
+		PQfinish(upstream_conn);
 
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/*
-	 * sanity-check that it will actually be possible to stream from the new upstream
-	 */
-	{
-		bool can_follow;
-		TimeLineID tli = get_min_recovery_end_timeline(config_file_options.data_directory);
-		XLogRecPtr min_recovery_location = get_min_recovery_location(config_file_options.data_directory);
-
-		/*
-		 * It's possible this was a former primary, so the minRecoveryPoint*
-		 * fields may be empty.
-		 */
-
-		if (min_recovery_location == InvalidXLogRecPtr)
-			min_recovery_location = get_latest_checkpoint_location(config_file_options.data_directory);
-		if (tli == 0)
-			tli = get_timeline(config_file_options.data_directory);
-
-		can_follow = check_node_can_attach(tli,
-										   min_recovery_location,
-										   primary_conn,
-										   &primary_node_record,
-										   true);
-
-		if (can_follow == false)
-		{
-			PQfinish(primary_conn);
-			exit(ERR_REJOIN_FAIL);
-		}
-	}
-
-
 	/*
 	 * --force-rewind specified - check prerequisites, and attempt to execute
   	 * (if --dry-run provided, just output the command which would be executed)
 	 */
 
+
 	if (runtime_options.force_rewind_used == true)
 	{
 		PQExpBufferData msg;
@@ -2306,12 +2122,12 @@ do_node_rejoin(void)
 
 		initPQExpBuffer(&msg);
 
-		if (can_use_pg_rewind(primary_conn, config_file_options.data_directory, &msg) == false)
+		if (can_use_pg_rewind(upstream_conn, config_file_options.data_directory, &msg) == false)
 		{
 			log_error(_("--force-rewind specified but pg_rewind cannot be used"));
 			log_detail("%s", msg.data);
 			termPQExpBuffer(&msg);
-			PQfinish(primary_conn);
+			PQfinish(upstream_conn);
 
 			exit(ERR_BAD_CONFIG);
 		}
@@ -2370,8 +2186,8 @@ do_node_rejoin(void)
 		else
 		{
 			log_notice(_("executing pg_rewind"));
-			log_detail(_("pg_rewind command is \"%s\""),
-					   command.data);
+			log_debug("pg_rewind command is:\n  %s",
+					  command.data);
 
 			initPQExpBuffer(&command_output);
 
@@ -2387,7 +2203,7 @@ do_node_rejoin(void)
 
 				termPQExpBuffer(&command_output);
 
-				exit(ERR_REJOIN_FAIL);
+				exit(ERR_BAD_CONFIG);
 			}
 
 			termPQExpBuffer(&command_output);
@@ -2490,34 +2306,26 @@ do_node_rejoin(void)
 
 	initPQExpBuffer(&follow_output);
 
-	/*
-	 * do_standby_follow_internal() can handle situations where the follow
-	 * target is not the primary, so requires database handles to both
-	 * (even if they point to the same node). For the time being,
-	 * "node rejoin" will only attach a standby to the primary.
-	 */
-	success = do_standby_follow_internal(primary_conn,
-										 primary_conn,
+	success = do_standby_follow_internal(upstream_conn,
 										 &primary_node_record,
 										 &follow_output,
-										 ERR_REJOIN_FAIL,
 										 &follow_error_code);
 
 	if (success == false)
 	{
-		log_error(_("NODE REJOIN failed"));
+		log_notice(_("NODE REJOIN failed"));
 
 		if (strlen(follow_output.data))
 			log_detail("%s", follow_output.data);
 
-		create_event_notification(primary_conn,
+		create_event_notification(upstream_conn,
 								  &config_file_options,
 								  config_file_options.node_id,
 								  "node_rejoin",
 								  success,
 								  follow_output.data);
 
-		PQfinish(primary_conn);
+		PQfinish(upstream_conn);
 
 		termPQExpBuffer(&follow_output);
 		exit(follow_error_code);
@@ -2560,7 +2368,7 @@ 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);
+			success = is_downstream_node_attached(upstream_conn, config_file_options.node_name);
 
 			if (success == true)
 			{
@@ -2571,13 +2379,9 @@ do_node_rejoin(void)
 
 			if (i % 5 == 0)
 			{
-				log_info(_("waiting for node \"%s\" (ID: %i) to connect to new primary; %i of max %i attempts"),
-						 config_file_options.node_name,
+				log_info(_("waiting for node %i to connect to new primary; %i of max %i attempts"),
 						 config_file_options.node_id,
 						 i + 1, config_file_options.node_rejoin_timeout);
-				log_detail(_("checking for record in node \"%s\"'s \"pg_stat_replication\" table where \"application_name\" is \"%s\""),
-						   primary_node_record.node_name,
-						   config_file_options.node_name);
 			}
 			else
 			{
@@ -2589,7 +2393,7 @@ do_node_rejoin(void)
 			sleep(1);
 		}
 
-		create_event_notification(primary_conn,
+		create_event_notification(upstream_conn,
 								  &config_file_options,
 								  config_file_options.node_id,
 								  "node_rejoin",
@@ -2599,18 +2403,13 @@ do_node_rejoin(void)
 		if (success == false)
 		{
 			termPQExpBuffer(&follow_output);
-			log_error(_("NODE REJOIN failed"));
-			log_detail(_("no record for local node \"%s\" found in node \"%s\"'s \"pg_stat_replication\" table"),
-					   config_file_options.node_name,
-					   primary_node_record.node_name);
-			log_hint(_("check the PostgreSQL log on the local node"));
+			log_notice(_("NODE REJOIN failed"));
 			exit(ERR_REJOIN_FAIL);
 		}
 	}
 	else
 	{
-		/* -W/--no-wait provided - check once */
-		success = is_downstream_node_attached(primary_conn, config_file_options.node_name);
+		success = is_downstream_node_attached(upstream_conn, config_file_options.node_name);
 	}
 
 	/*
@@ -2681,48 +2480,6 @@ do_node_rejoin(void)
 }
 
 
-/*
- * Currently for testing purposes only, not documented;
- * use at own risk!
- */
-
-void
-do_node_control(void)
-{
-	PGconn	   *conn = NULL;
-	pid_t	    wal_receiver_pid = UNKNOWN_PID;
-	conn = establish_db_connection(config_file_options.conninfo, true);
-
-	if (runtime_options.disable_wal_receiver == true)
-	{
-		wal_receiver_pid = disable_wal_receiver(conn);
-
-		PQfinish(conn);
-
-		if (wal_receiver_pid == UNKNOWN_PID)
-			exit(ERR_BAD_CONFIG);
-
-		exit(SUCCESS);
-	}
-
-	if (runtime_options.enable_wal_receiver == true)
-	{
-		wal_receiver_pid = enable_wal_receiver(conn, true);
-
-		PQfinish(conn);
-
-		if (wal_receiver_pid == UNKNOWN_PID)
-			exit(ERR_BAD_CONFIG);
-
-		exit(SUCCESS);
-	}
-
-	log_error(_("no option provided"));
-
-	PQfinish(conn);
-}
-
-
 /*
  * For "internal" use by `node rejoin` on the local node when
  * called by "standby switchover" from the remote node.
@@ -3165,8 +2922,8 @@ do_node_help(void)
 	puts("");
 	printf(_("  Configuration file required, runs on local node only.\n"));
 	puts("");
-	printf(_("    --csv                   emit output as CSV (not available for individual check output)\n"));
-	printf(_("    --nagios                emit output in Nagios format (individual check output only)\n"));
+	printf(_("    --csv                   emit output as CSV\n"));
+	printf(_("    --nagios                emit output in Nagios format (individual status output only)\n"));
 	puts("");
 	printf(_("  Following options check an individual status:\n"));
 	printf(_("    --archive-ready         number of WAL files ready for archiving\n"));
@@ -3175,7 +2932,6 @@ do_node_help(void)
 	printf(_("    --role                  check node has expected role\n"));
 	printf(_("    --slots                 check for inactive replication slots\n"));
 	printf(_("    --missing-slots         check for missing replication slots\n"));
-	printf(_("    --data-directory-config check repmgr's data directory configuration\n"));
 
 	puts("");
 

repmgr-action-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -24,7 +24,6 @@ extern void do_node_check(void);
 
 extern void do_node_rejoin(void);
 extern void do_node_service(void);
-extern void do_node_control(void);
 
 extern void do_node_help(void);
 

repmgr-action-primary.c

@@ -3,7 +3,7 @@
  *
  * Implements primary actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -251,7 +251,6 @@ do_primary_unregister(void)
 	PGconn	   *primary_conn = NULL;
 	PGconn	   *local_conn = NULL;
 	t_node_info local_node_info = T_NODE_INFO_INITIALIZER;
-	t_node_info primary_node_info = T_NODE_INFO_INITIALIZER;
 
 	t_node_info *target_node_info_ptr = NULL;
 	PGconn	   *target_node_conn = NULL;
@@ -272,6 +271,8 @@ do_primary_unregister(void)
 
 	if (PQstatus(primary_conn) != CONNECTION_OK)
 	{
+		t_node_info primary_node_info = T_NODE_INFO_INITIALIZER;
+
 		log_error(_("unable to connect to primary server"));
 
 		if (get_primary_node_record(local_conn, &primary_node_info) == true)
@@ -290,19 +291,10 @@ do_primary_unregister(void)
 	/* Local connection no longer required */
 	PQfinish(local_conn);
 
-	if (get_primary_node_record(primary_conn, &primary_node_info) == false)
-	{
-		log_error(_("unable to retrieve record for primary node"));
-		PQfinish(primary_conn);
-		exit(ERR_BAD_CONFIG);
-	}
 
 	/* Target node is local node? */
-	if (target_node_info.node_id == UNKNOWN_NODE_ID)
-	{
-		target_node_info_ptr = &primary_node_info;
-	}
-	else if (target_node_info.node_id == config_file_options.node_id)
+	if (target_node_info.node_id == UNKNOWN_NODE_ID
+		|| target_node_info.node_id == config_file_options.node_id)
 	{
 		target_node_info_ptr = &local_node_info;
 	}
@@ -312,24 +304,6 @@ do_primary_unregister(void)
 		target_node_info_ptr = &target_node_info;
 	}
 
-	/*
-	 * Sanity-check the target node is not a witness
-	 */
-
-	if (target_node_info_ptr->type == WITNESS)
-	{
-		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)
-		{
-			log_hint(_("the node can be unregistered with \"repmgr witness unregister\""));
-		}
-
-		PQfinish(primary_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
 	/*
 	 * Check for downstream nodes - if any still defined, we won't be able to
 	 * delete the node record due to foreign key constraints.

repmgr-action-primary.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-primary.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-standby.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-standby.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -28,7 +28,7 @@ extern void do_standby_switchover(void);
 
 extern void do_standby_help(void);
 
-extern bool do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_node_info *follow_target_node_record, PQExpBufferData *output, int general_error_code, int *error_code);
+extern bool do_standby_follow_internal(PGconn *primary_conn, t_node_info *primary_node_record, PQExpBufferData *output, int *error_code);
 
 
 

repmgr-action-witness.c

@@ -3,7 +3,7 @@
  *
  * Implements witness actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -36,12 +36,10 @@ do_witness_register(void)
 {
 	PGconn	   *witness_conn = NULL;
 	PGconn	   *primary_conn = NULL;
-	int			primary_node_id = UNKNOWN_NODE_ID;
 	RecoveryType recovery_type = RECTYPE_UNKNOWN;
 	ExtensionStatus extension_status = REPMGR_UNKNOWN;
 	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
 	t_node_info node_record = T_NODE_INFO_INITIALIZER;
-	t_node_info primary_node_record = T_NODE_INFO_INITIALIZER;
 	RecordStatus record_status = RECORD_NOT_FOUND;
 	bool		record_created = false;
 
@@ -127,59 +125,6 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-
-	/* check we can determine the primary node */
-	primary_node_id = get_primary_node_id(primary_conn);
-
-	if (primary_node_id == UNKNOWN_NODE_ID)
-	{
-		log_error(_("unable to determine the cluster's primary node"));
-		log_hint(_("ensure the primary node connection details are correct and that it is registered"));
-		PQfinish(witness_conn);
-		PQfinish(primary_conn);
-
-		exit(ERR_BAD_CONFIG);
-	}
-
-	record_status = get_node_record(primary_conn, primary_node_id, &primary_node_record);
-	PQfinish(primary_conn);
-
-	if (record_status != RECORD_FOUND)
-	{
-		log_error(_("unable to retrieve record for primary node %i"),
-				  primary_node_id);
-
-		PQfinish(witness_conn);
-
-
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/*
-	 * Reconnect to the primary node's conninfo - this will
-	 * protect against the situation where the witness connection
-	 * details were provided, and we're actually connected to the
-	 * witness server.
-	 */
-
-	primary_conn = establish_db_connection_quiet(primary_node_record.conninfo);
-
-	if (PQstatus(primary_conn) != CONNECTION_OK)
-	{
-		log_error(_("unable to reconnect to the primary node (node %i)"), primary_node_id);
-		log_detail(_("primary node's conninfo is \"%s\""), primary_node_record.conninfo);
-
-		PQfinish(witness_conn);
-
-		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
-	 */
-
 	/* check that primary node is not a BDR node */
 	if (is_bdr_db_quiet(primary_conn) == true)
 	{
@@ -192,6 +137,11 @@ 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
+	 */
 
 	/* create repmgr extension, if does not exist */
 	if (runtime_options.dry_run == false &&  !create_repmgr_extension(witness_conn))
@@ -325,7 +275,7 @@ do_witness_register(void)
 	/* these values are mandatory, setting them to anything else has no point */
 	node_record.type = WITNESS;
 	node_record.priority = 0;
-	node_record.upstream_node_id = primary_node_id;
+	node_record.upstream_node_id = get_primary_node_id(primary_conn);
 
 	if (record_status == RECORD_FOUND)
 	{

repmgr-action-witness.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-witness.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-client-global.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client-global.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,16 +35,14 @@ typedef struct
 	bool		connection_param_provided;
 	bool		host_param_provided;
 	bool		limit_provided;
-	bool		wait_provided;
 
 	/* general configuration options */
 	char		config_file[MAXPGPATH];
 	bool		dry_run;
 	bool		force;
 	char		pg_bindir[MAXLEN];	/* overrides setting in repmgr.conf */
-	int			wait;
+	bool		wait;
 	bool		no_wait;
-	bool		compact;
 
 	/* logging options */
 	char		log_level[MAXLEN];	/* overrides setting in repmgr.conf */
@@ -113,9 +111,8 @@ typedef struct
 	bool		missing_slots;
 	bool		has_passfile;
 	bool		replication_connection;
-	bool		data_directory_config;
 
-	/* "node rejoin" options */
+	/* "node join" options */
 	char		config_files[MAXLEN];
 
 	/* "node service" options */
@@ -135,15 +132,13 @@ typedef struct
 	/* following options for internal use */
 	char		config_archive_dir[MAXPGPATH];
 	OutputMode	output_mode;
-	bool		disable_wal_receiver;
-	bool		enable_wal_receiver;
 } t_runtime_options;
 
 #define T_RUNTIME_OPTIONS_INITIALIZER { \
 		/* configuration metadata */ \
-		false, false, false, false, false,	\
+		false, false, false, false,	\
 		/* general configuration options */	\
-		"", false, false, "", -1, false, false, \
+		"", false, false, "", false, false,	\
 		/* logging options */ \
 		"", false, false, false, false,	\
 		/* output options */ \
@@ -166,8 +161,8 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, false, false, false,	false, \
-		/* "node rejoin" options */ \
+		false, false, false, false, false, false, false, false,	\
+		/* "node join" options */ \
 		"", \
 		/* "node service" options */ \
 		"", false, false, false,  \
@@ -176,7 +171,7 @@ typedef struct
 		/* "cluster cleanup" options */ \
 		0, \
 		/* following options for internal use */ \
-		"/tmp", OM_TEXT, false, false \
+		"/tmp", OM_TEXT	\
 }
 
 
@@ -204,7 +199,6 @@ typedef struct ColHeader
 	char		title[MAXLEN];
 	int			max_length;
 	int			cur_length;
-	bool		display;
 } ColHeader;
 
 
@@ -226,6 +220,8 @@ extern int	check_server_version(PGconn *conn, char *server_type, bool exit_on_er
 extern void check_93_config(void);
 extern bool create_repmgr_extension(PGconn *conn);
 extern int	test_ssh_connection(char *host, char *remote_user);
+extern bool local_command(const char *command, PQExpBufferData *outputbuf);
+extern bool local_command_simple(const char *command, PQExpBufferData *outputbuf);
 
 extern standy_clone_mode get_standby_clone_mode(void);
 
@@ -238,9 +234,9 @@ extern char *make_pg_path(const char *file);
 
 extern void get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privileged_conn);
 
-extern void make_remote_repmgr_path(PQExpBufferData *outputbuf, t_node_info *remote_node_record);
-extern void make_repmgrd_path(PQExpBufferData *output_buf);
+extern bool remote_command(const char *host, const char *user, const char *command, PQExpBufferData *outputbuf);
 
+extern void make_remote_repmgr_path(PQExpBufferData *outputbuf, t_node_info *remote_node_record);
 
 /* display functions */
 extern void print_help_header(void);
@@ -255,8 +251,4 @@ extern void init_node_record(t_node_info *node_record);
 extern bool can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *reason);
 extern void drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);
 
-extern 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);
-extern void check_shared_library(PGconn *conn);
-extern bool is_repmgrd_running(PGconn *conn);
-
 #endif							/* _REPMGR_CLIENT_GLOBAL_H_ */

repmgr-client.c

@@ -1,7 +1,7 @@
 /*
  * repmgr-client.c - Command interpreter for the repmgr package
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This module is a command-line utility to easily setup a cluster of
  * hot standby servers for an HA environment
@@ -31,13 +31,11 @@
  * NODE CHECK
  * NODE REJOIN
  * NODE SERVICE
- * NODE CONTROL
  *
  * DAEMON STATUS
  * DAEMON PAUSE
  * DAEMON UNPAUSE
- * DAEMON START
- * DAEMON STOP
+ *
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -55,7 +53,6 @@
 
 #include <unistd.h>
 #include <sys/stat.h>
-#include <signal.h>
 
 #include "repmgr.h"
 #include "compat.h"
@@ -98,6 +95,8 @@ t_node_info target_node_info = T_NODE_INFO_INITIALIZER;
 static ItemList cli_errors = {NULL, NULL};
 static ItemList cli_warnings = {NULL, NULL};
 
+static bool _local_command(const char *command, PQExpBufferData *outputbuf, bool simple);
+
 int
 main(int argc, char **argv)
 {
@@ -206,7 +205,6 @@ main(int argc, char **argv)
 				help_option = true;
 				break;
 
-				/* -V/--version */
 			case 'V':
 
 				/*
@@ -217,11 +215,6 @@ main(int argc, char **argv)
 				printf("%s %s\n", progname(), REPMGR_VERSION);
 				exit(SUCCESS);
 
-				/* --version-number */
-			case OPT_VERSION_NUMBER:
-				printf("%i\n", REPMGR_VERSION_NUM);
-				exit(SUCCESS);
-
 				/*------------------------------
 				 * general configuration options
 				 *------------------------------
@@ -254,11 +247,7 @@ main(int argc, char **argv)
 
 				/* -w/--wait */
 			case 'w':
-				runtime_options.wait_provided = true;
-				if (optarg != NULL)
-				{
-					runtime_options.wait = repmgr_atoi(optarg, "--wait", &cli_errors, 0);
-				}
+				runtime_options.wait = true;
 				break;
 
 				/* -W/--no-wait */
@@ -266,12 +255,6 @@ main(int argc, char **argv)
 				runtime_options.no_wait = true;
 				break;
 
-				/* --compact */
-			case OPT_COMPACT:
-				runtime_options.compact = true;
-				break;
-
-
 				/*----------------------------
 				 * database connection options
 				 *----------------------------
@@ -304,12 +287,7 @@ main(int argc, char **argv)
 				break;
 
 			case 'p':
-				/*
-				 * minimum TCP port number is 1; in practice PostgreSQL
-				 * won't be running on a privileged port, but we don't want
-				 * to be concerned with that level of checking
-				 */
-				(void) repmgr_atoi(optarg, "-p/--port", &cli_errors, 1);
+				(void) repmgr_atoi(optarg, "-p/--port", &cli_errors, false);
 				param_set(&source_conninfo, "port", optarg);
 				strncpy(runtime_options.port,
 						optarg,
@@ -351,7 +329,7 @@ main(int argc, char **argv)
 
 				/* --node-id */
 			case OPT_NODE_ID:
-				runtime_options.node_id = repmgr_atoi(optarg, "--node-id", &cli_errors, MIN_NODE_ID);
+				runtime_options.node_id = repmgr_atoi(optarg, "--node-id", &cli_errors, false);
 				break;
 
 				/* --node-name */
@@ -361,7 +339,7 @@ main(int argc, char **argv)
 
 				/* --remote-node-id */
 			case OPT_REMOTE_NODE_ID:
-				runtime_options.remote_node_id = repmgr_atoi(optarg, "--remote-node-id", &cli_errors, MIN_NODE_ID);
+				runtime_options.remote_node_id = repmgr_atoi(optarg, "--remote-node-id", &cli_errors, false);
 				break;
 
 				/*
@@ -370,7 +348,7 @@ main(int argc, char **argv)
 
 				/* --upstream-node-id */
 			case OPT_UPSTREAM_NODE_ID:
-				runtime_options.upstream_node_id = repmgr_atoi(optarg, "--upstream-node-id", &cli_errors, MIN_NODE_ID);
+				runtime_options.upstream_node_id = repmgr_atoi(optarg, "--upstream-node-id", &cli_errors, false);
 				break;
 
 				/*------------------------
@@ -430,14 +408,14 @@ main(int argc, char **argv)
 				 */
 
 			case OPT_WAIT_START:
-				runtime_options.wait_start = repmgr_atoi(optarg, "--wait-start", &cli_errors, 0);
+				runtime_options.wait_start = repmgr_atoi(optarg, "--wait-start", &cli_errors, false);
 				break;
 
 			case OPT_WAIT_SYNC:
 				runtime_options.wait_register_sync = true;
 				if (optarg != NULL)
 				{
-					runtime_options.wait_register_sync_seconds = repmgr_atoi(optarg, "--wait-sync", &cli_errors, 0);
+					runtime_options.wait_register_sync_seconds = repmgr_atoi(optarg, "--wait-sync", &cli_errors, false);
 				}
 				break;
 
@@ -513,10 +491,6 @@ main(int argc, char **argv)
 				runtime_options.replication_connection = true;
 				break;
 
-			case OPT_DATA_DIRECTORY_CONFIG:
-				runtime_options.data_directory_config = true;
-				break;
-
 				/*--------------------
 				 * "node rejoin" options
 				 *--------------------
@@ -558,7 +532,7 @@ main(int argc, char **argv)
 				break;
 
 			case OPT_LIMIT:
-				runtime_options.limit = repmgr_atoi(optarg, "--limit", &cli_errors, 1);
+				runtime_options.limit = repmgr_atoi(optarg, "--limit", &cli_errors, false);
 				runtime_options.limit_provided = true;
 				break;
 
@@ -573,7 +547,7 @@ main(int argc, char **argv)
 
 				/* -k/--keep-history */
 			case 'k':
-				runtime_options.keep_history = repmgr_atoi(optarg, "-k/--keep-history", &cli_errors, 0);
+				runtime_options.keep_history = repmgr_atoi(optarg, "-k/--keep-history", &cli_errors, false);
 				break;
 
 				/*----------------
@@ -625,7 +599,7 @@ main(int argc, char **argv)
 				break;
 
 
-				/*---------------
+				/*--------------
 				 * output options
 				 *---------------
 				 */
@@ -641,19 +615,6 @@ main(int argc, char **argv)
 				runtime_options.optformat = true;
 				break;
 
-				/*---------------------------------
-				 * undocumented options for testing
-				 *----------------------------------
-				 */
-
-			case OPT_DISABLE_WAL_RECEIVER:
-				runtime_options.disable_wal_receiver = true;
-				break;
-
-			case OPT_ENABLE_WAL_RECEIVER:
-				runtime_options.enable_wal_receiver = true;
-				break;
-
 				/*-----------------------------
 				 * options deprecated since 3.3
 				 *-----------------------------
@@ -813,7 +774,7 @@ main(int argc, char **argv)
 	 *   BDR { REGISTER | UNREGISTER } |
 	 *   NODE { STATUS | CHECK | REJOIN | SERVICE } |
 	 *   CLUSTER { CROSSCHECK | MATRIX | SHOW | EVENT | CLEANUP }
-	 *   DAEMON { STATUS | PAUSE | UNPAUSE | START | STOP }
+	 *   DAEMON { STATUS | PAUSE | UNPAUSE }
 	 *
 	 * [node] is an optional hostname, provided instead of the -h/--host
 	 * option
@@ -926,8 +887,6 @@ main(int argc, char **argv)
 				action = NODE_REJOIN;
 			else if (strcasecmp(repmgr_action, "SERVICE") == 0)
 				action = NODE_SERVICE;
-			else if (strcasecmp(repmgr_action, "CONTROL") == 0)
-				action = NODE_CONTROL;
 		}
 
 		else if (strcasecmp(repmgr_command, "CLUSTER") == 0)
@@ -966,10 +925,6 @@ main(int argc, char **argv)
 				action = DAEMON_PAUSE;
 			else if (strcasecmp(repmgr_action, "UNPAUSE") == 0)
 				action = DAEMON_UNPAUSE;
-			else if (strcasecmp(repmgr_action, "START") == 0)
-				action = DAEMON_START;
-			else if (strcasecmp(repmgr_action, "STOP") == 0)
-				action = DAEMON_STOP;
 		}
 		else
 		{
@@ -1351,9 +1306,6 @@ main(int argc, char **argv)
 		case NODE_SERVICE:
 			do_node_service();
 			break;
-		case NODE_CONTROL:
-			do_node_control();
-			break;
 
 			/* CLUSTER */
 		case CLUSTER_SHOW:
@@ -1382,12 +1334,6 @@ main(int argc, char **argv)
 		case DAEMON_UNPAUSE:
 			do_daemon_unpause();
 			break;
-		case DAEMON_START:
-			do_daemon_start();
-			break;
-		case DAEMON_STOP:
-			do_daemon_stop();
-			break;
 
 		default:
 			/* An action will have been determined by this point  */
@@ -1712,6 +1658,12 @@ check_cli_parameters(const int action)
 		switch (action)
 		{
 			case CLUSTER_EVENT:
+				if (runtime_options.limit < 1)
+				{
+					item_list_append_format(&cli_errors,
+											_("value for --limit must be 1 or greater (provided: %i)"),
+											runtime_options.limit);
+				}
 				break;
 			default:
 				item_list_append_format(&cli_warnings,
@@ -1741,19 +1693,17 @@ check_cli_parameters(const int action)
 
 	/* --wait/--no-wait */
 
-	if (runtime_options.wait_provided == true && runtime_options.no_wait == true)
+	if (runtime_options.wait == true && runtime_options.no_wait == true)
 	{
 		item_list_append_format(&cli_errors,
 								_("both --wait and --no-wait options provided"));
 	}
 	else
 	{
-		if (runtime_options.wait_provided)
+		if (runtime_options.wait)
 		{
 			switch (action)
 			{
-				case DAEMON_START:
-				case DAEMON_STOP:
 				case STANDBY_FOLLOW:
 					break;
 				default:
@@ -1762,12 +1712,10 @@ check_cli_parameters(const int action)
 											action_name(action));
 			}
 		}
-		else if (runtime_options.no_wait)
+		else if (runtime_options.wait)
 		{
 			switch (action)
 			{
-				case DAEMON_START:
-				case DAEMON_STOP:
 				case NODE_REJOIN:
 					break;
 				default:
@@ -1869,15 +1817,12 @@ check_cli_parameters(const int action)
 			case STANDBY_REGISTER:
 			case STANDBY_FOLLOW:
 			case STANDBY_SWITCHOVER:
-			case STANDBY_PROMOTE:
 			case WITNESS_REGISTER:
 			case WITNESS_UNREGISTER:
 			case NODE_REJOIN:
 			case NODE_SERVICE:
 			case DAEMON_PAUSE:
 			case DAEMON_UNPAUSE:
-			case DAEMON_START:
-			case DAEMON_STOP:
 				break;
 			default:
 				item_list_append_format(&cli_warnings,
@@ -1906,44 +1851,6 @@ check_cli_parameters(const int action)
 							 "only one of --csv, --nagios and --optformat can be used");
 		}
 	}
-
-	/* --compact */
-
-	if (runtime_options.compact == true)
-	{
-		switch (action)
-		{
-			case CLUSTER_SHOW:
-			case DAEMON_STATUS:
-				break;
-			default:
-				item_list_append_format(&cli_warnings,
-										_("--compact 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)
-	{
-		switch (action)
-		{
-			case NODE_CONTROL:
-			{
-				if (runtime_options.disable_wal_receiver == true && runtime_options.enable_wal_receiver == true)
-				{
-						item_list_append(&cli_errors,
-										 _("provide either --disable-wal-receiver or --enable-wal-receiver"));
-				}
-			}
-				break;
-			default:
-					item_list_append_format(&cli_warnings,
-											_("--disable-wal-receiver / --enable-wal-receiver not effective when executing %s"),
-											action_name(action));
-		}
-	}
-
 }
 
 
@@ -2002,10 +1909,7 @@ action_name(const int action)
 			return "DAEMON PAUSE";
 		case DAEMON_UNPAUSE:
 			return "DAEMON UNPAUSE";
-		case DAEMON_START:
-			return "DAEMON START";
-		case DAEMON_STOP:
-			return "DAEMON STOP";
+
 	}
 
 	return "UNKNOWN ACTION";
@@ -2037,20 +1941,9 @@ void
 print_status_header(int cols, ColHeader *headers)
 {
 	int i;
-	int max_cols = 0;
-
-	/* count how many columns we actually need to display */
-	for (i = 0; i < cols; i++)
-	{
-		if (headers[i].display == true)
-			max_cols ++;
-	}
 
 	for (i = 0; i < cols; i++)
 	{
-		if (headers[i].display == false)
-			continue;
-
 		if (i == 0)
 			printf(" ");
 		else
@@ -2060,22 +1953,17 @@ print_status_header(int cols, ColHeader *headers)
 			   headers[i].max_length,
 			   headers[i].title);
 	}
-
-
 	printf("\n");
 	printf("-");
 
-	for (i = 0; i < max_cols; i++)
+	for (i = 0; i < cols; i++)
 	{
 		int			j;
 
-		if (headers[i].display == false)
-			continue;
-
 		for (j = 0; j < headers[i].max_length; j++)
 			printf("-");
 
-		if (i < (max_cols - 1))
+		if (i < (cols - 1))
 			printf("-+-");
 		else
 			printf("-");
@@ -2113,7 +2001,7 @@ do_help(void)
 	printf(_("    %s [OPTIONS] node    {status|check|rejoin|service}\n"), progname());
 	printf(_("    %s [OPTIONS] cluster {show|event|matrix|crosscheck|cleanup}\n"), progname());
 	printf(_("    %s [OPTIONS] witness {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] daemon  {status|pause|unpause|start|stop}\n"), progname());
+	printf(_("    %s [OPTIONS] daemon  {status|pause|unpause}\n"), progname());
 
 	puts("");
 
@@ -2124,7 +2012,6 @@ do_help(void)
 	printf(_("General options:\n"));
 	printf(_("  -?, --help                          show this help, then exit\n"));
 	printf(_("  -V, --version                       output version information, then exit\n"));
-	printf(_("  --version-number                    output version number, then exit\n"));
 	puts("");
 
 	printf(_("General configuration options:\n"));
@@ -2350,15 +2237,17 @@ create_repmgr_extension(PGconn *conn)
 int
 check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *server_version_string)
 {
-	int			conn_server_version_num = get_server_version(conn, server_version_string);
+	int			conn_server_version_num = UNKNOWN_SERVER_VERSION_NUM;
 
+	conn_server_version_num = get_server_version(conn, server_version_string);
 	if (conn_server_version_num < MIN_SUPPORTED_VERSION_NUM)
 	{
 		if (conn_server_version_num > 0)
 			log_error(_("%s requires %s to be PostgreSQL %s or later"),
 					  progname(),
 					  server_type,
-					  MIN_SUPPORTED_VERSION);
+					  MIN_SUPPORTED_VERSION
+				);
 
 		if (exit_on_error == true)
 		{
@@ -2366,7 +2255,7 @@ check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *
 			exit(ERR_BAD_CONFIG);
 		}
 
-		return UNKNOWN_SERVER_VERSION_NUM;
+		return -1;
 	}
 
 	return conn_server_version_num;
@@ -2438,6 +2327,75 @@ test_ssh_connection(char *host, char *remote_user)
 
 
 
+/*
+ * Execute a command locally. "outputbuf" should either be an
+ * initialised PQexpbuffer, or NULL
+ */
+bool
+local_command(const char *command, PQExpBufferData *outputbuf)
+{
+	return _local_command(command, outputbuf, false);
+}
+
+
+bool
+local_command_simple(const char *command, PQExpBufferData *outputbuf)
+{
+	return _local_command(command, outputbuf, true);
+}
+
+
+static bool
+_local_command(const char *command, PQExpBufferData *outputbuf, bool simple)
+{
+	FILE	   *fp = NULL;
+	char		output[MAXLEN];
+	int			retval = 0;
+	bool		success;
+
+	log_verbose(LOG_DEBUG, "executing:\n  %s", command);
+
+	if (outputbuf == NULL)
+	{
+		retval = system(command);
+		return (retval == 0) ? true : false;
+	}
+
+	fp = popen(command, "r");
+
+	if (fp == NULL)
+	{
+		log_error(_("unable to execute local command:\n%s"), command);
+		return false;
+	}
+
+
+	while (fgets(output, MAXLEN, fp) != NULL)
+	{
+		appendPQExpBuffer(outputbuf, "%s", output);
+
+		if (!feof(fp) && simple == false)
+		{
+			break;
+		}
+	}
+
+	retval = pclose(fp);
+
+	/*  */
+	success = (WEXITSTATUS(retval) == 0 || WEXITSTATUS(retval) == 141) ? true : false;
+
+	log_verbose(LOG_DEBUG, "result of command was %i (%i)", WEXITSTATUS(retval), retval);
+
+	if (outputbuf->data != NULL)
+		log_verbose(LOG_DEBUG, "local_command(): output returned was:\n%s", outputbuf->data);
+	else
+		log_verbose(LOG_DEBUG, "local_command(): no output returned");
+
+	return success;
+}
+
+
 /*
  * get_superuser_connection()
  *
@@ -2644,6 +2602,78 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 }
 
 
+/*
+ * Execute a command via ssh on the remote host.
+ *
+ * TODO: implement SSH calls using libssh2.
+ */
+bool
+remote_command(const char *host, const char *user, const char *command, PQExpBufferData *outputbuf)
+{
+	FILE	   *fp;
+	char		ssh_command[MAXLEN] = "";
+	PQExpBufferData ssh_host;
+
+	char		output[MAXLEN] = "";
+
+	initPQExpBuffer(&ssh_host);
+
+	if (*user != '\0')
+	{
+		appendPQExpBuffer(&ssh_host, "%s@", user);
+	}
+
+	appendPQExpBuffer(&ssh_host, "%s", host);
+
+	maxlen_snprintf(ssh_command,
+					"ssh -o Batchmode=yes %s %s %s",
+					config_file_options.ssh_options,
+					ssh_host.data,
+					command);
+
+	termPQExpBuffer(&ssh_host);
+
+	log_debug("remote_command():\n  %s", ssh_command);
+
+	fp = popen(ssh_command, "r");
+
+	if (fp == NULL)
+	{
+		log_error(_("unable to execute remote command:\n  %s"), ssh_command);
+		return false;
+	}
+
+	if (outputbuf != NULL)
+	{
+		/* TODO: better error handling */
+		while (fgets(output, MAXLEN, fp) != NULL)
+		{
+			appendPQExpBuffer(outputbuf, "%s", output);
+		}
+	}
+	else
+	{
+		while (fgets(output, MAXLEN, fp) != NULL)
+		{
+			if (!feof(fp))
+			{
+				break;
+			}
+		}
+	}
+
+	pclose(fp);
+
+	if (outputbuf != NULL)
+	{
+		if (strlen(outputbuf->data))
+			log_verbose(LOG_DEBUG, "remote_command(): output returned was:\n%s", outputbuf->data);
+		else
+			log_verbose(LOG_DEBUG, "remote_command(): no output returned");
+	}
+
+	return true;
+}
 
 
 void
@@ -2675,34 +2705,6 @@ make_remote_repmgr_path(PQExpBufferData *output_buf, t_node_info *remote_node_re
 }
 
 
-void
-make_repmgrd_path(PQExpBufferData *output_buf)
-{
-	if (config_file_options.repmgr_bindir[0] != '\0')
-	{
-		int			len = strlen(config_file_options.repmgr_bindir);
-
-		appendPQExpBufferStr(output_buf,
-							 config_file_options.repmgr_bindir);
-
-		/* Add trailing slash */
-		if (config_file_options.repmgr_bindir[len - 1] != '/')
-		{
-			appendPQExpBufferChar(output_buf, '/');
-		}
-	}
-	else if (pg_bindir[0] != '\0')
-	{
-		appendPQExpBufferStr(output_buf,
-							 pg_bindir);
-	}
-
-	appendPQExpBuffer(output_buf,
-					  "repmgrd -f %s ",
-					  config_file_path);
-}
-
-
 /* ======================== */
 /* server control functions */
 /* ======================== */
@@ -3029,9 +3031,10 @@ bool
 can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *reason)
 {
 	bool		can_use = true;
+	int			server_version_num = get_server_version(conn, NULL);
 
 	/* wal_log_hints not available in 9.3, so just determine if data checksums enabled */
-	if (PQserverVersion(conn) < 90400)
+	if (server_version_num < 90400)
 	{
 		int			data_checksum_version = get_data_checksum_version(data_directory);
 
@@ -3138,251 +3141,3 @@ 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.
- */
-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)
-{
-	uint64		local_system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
-	t_conninfo_param_list follow_target_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
-	PGconn	   *follow_target_repl_conn = NULL;
-	t_system_identification follow_target_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
-	TimeLineHistoryEntry *follow_target_history = NULL;
-	bool success = true;
-
-	const char *action = is_rejoin == true ? "rejoin" : "follow";
-
-	/* check replication connection */
-	initialize_conninfo_params(&follow_target_repl_conninfo, false);
-
-	conn_to_param_list(follow_target_conn, &follow_target_repl_conninfo);
-
-	if (strcmp(param_get(&follow_target_repl_conninfo, "user"), follow_target_node_record->repluser) != 0)
-	{
-		param_set(&follow_target_repl_conninfo, "user", follow_target_node_record->repluser);
-		param_set(&follow_target_repl_conninfo, "dbname", "replication");
-	}
-
-	param_set(&follow_target_repl_conninfo, "replication", "1");
-
-	follow_target_repl_conn = establish_db_connection_by_params(&follow_target_repl_conninfo, false);
-
-	free_conninfo_params(&follow_target_repl_conninfo);
-
-	if (PQstatus(follow_target_repl_conn) != CONNECTION_OK)
-	{
-		log_error(_("unable to establish a replication connection to the %s target node"), action);
-		return false;
-	}
-	else if (runtime_options.dry_run == true)
-	{
-		log_info(_("replication connection to the %s target node was successful"), action);
-	}
-
-	/* check system_identifiers match */
-	if (identify_system(follow_target_repl_conn, &follow_target_identification) == false)
-	{
-		log_error(_("unable to query the %s target node's system identification"), action);
-
-		PQfinish(follow_target_repl_conn);
-		return false;
-	}
-
-	local_system_identifier = get_system_identifier(config_file_options.data_directory);
-
-	/*
-	 * Check for thing that should never happen, but expect the unexpected anyway.
-	 */
-	if (follow_target_identification.system_identifier != local_system_identifier)
-	{
-		log_error(_("this node is not part of the %s target node's replication cluster"), action);
-		log_detail(_("this node's system identifier is %lu, %s target node's system identifier is %lu"),
-				   local_system_identifier,
-				   action,
-				   follow_target_identification.system_identifier);
-		PQfinish(follow_target_repl_conn);
-		return false;
-	}
-
-	if (runtime_options.dry_run == true)
-	{
-		log_info(_("local and %s target system identifiers match"), action);
-		log_detail(_("system identifier is %lu"), local_system_identifier);
-	}
-
-	/* check timelines */
-
-	log_verbose(LOG_DEBUG, "local timeline: %i; %s target timeline: %i",
-				local_tli,
-				action,
-				follow_target_identification.timeline);
-
-	/* upstream's timeline is lower than ours - impossible case */
-	if (follow_target_identification.timeline < local_tli)
-	{
-		log_error(_("this node's timeline is ahead of the %s target node's timeline"), action);
-		log_detail(_("this node's timeline is %i, %s target node's timeline is %i"),
-				   local_tli,
-				   action,
-				   follow_target_identification.timeline);
-		PQfinish(follow_target_repl_conn);
-		return false;
-	}
-
-	if (follow_target_identification.timeline == local_tli)
-	{
-		XLogRecPtr follow_target_xlogpos = get_node_current_lsn(follow_target_conn);
-
-		if (local_xlogpos == InvalidXLogRecPtr || follow_target_xlogpos == InvalidXLogRecPtr)
-		{
-			log_error(_("unable to compare LSN positions"));
-			PQfinish(follow_target_repl_conn);
-			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"));
-			log_detail(_("local node lsn is %X/%X, %s target lsn is %X/%X"),
-					   format_lsn(local_xlogpos),
-					   action,
-					   format_lsn(follow_target_xlogpos));
-		}
-		else
-		{
-			log_error(_("this node is ahead of the %s target"), action);
-			log_detail(_("local node lsn is %X/%X, %s target lsn is %X/%X"),
-					   format_lsn(local_xlogpos),
-					   action,
-					   format_lsn(follow_target_xlogpos));
-
-			success = false;
-		}
-	}
-	else
-	{
-		/*
-		 * upstream has higher timeline - check where it forked off from this node's timeline
-		 */
-		follow_target_history = get_timeline_history(follow_target_repl_conn, local_tli + 1);
-
-		if (follow_target_history == NULL)
-		{
-			/* get_timeline_history() will emit relevant error messages */
-			PQfinish(follow_target_repl_conn);
-			return false;
-		}
-
-		log_debug("local tli: %i; local_xlogpos: %X/%X; follow_target_history->tli: %i; follow_target_history->end: %X/%X",
-				  local_tli,
-				  format_lsn(local_xlogpos),
-				  follow_target_history->tli,
-				  format_lsn(follow_target_history->end));
-
-		/*
-		 * Local node has proceeded beyond the follow target's fork, so we
-		 * definitely can't attach.
-		 *
-		 * This could be the case if the follow target was promoted, but does
-		 * not contain all changes which are being replayed to this standby.
-		 */
-		if (local_xlogpos > follow_target_history->end)
-		{
-			if (is_rejoin == true && runtime_options.force_rewind_used == true)
-			{
-				log_notice(_("pg_rewind execution required for this node to attach to rejoin target node %i"),
-						   follow_target_node_record->node_id);
-			}
-			else
-			{
-				log_error(_("this node cannot attach to %s target node %i"),
-						  action,
-						  follow_target_node_record->node_id);
-				success = false;
-			}
-
-			log_detail(_("%s target server's timeline %i forked off current database system timeline %i before current recovery point %X/%X"),
-					   action,
-					   local_tli + 1,
-					   local_tli,
-					   format_lsn(local_xlogpos));
-
-			if (is_rejoin == true && runtime_options.force_rewind_used == false)
-			{
-				log_hint(_("use --force-rewind to execute pg_rewind"));
-			}
-		}
-
-		if (success == true)
-		{
-			if (is_rejoin == false || (is_rejoin == true && runtime_options.force_rewind_used == false))
-			{
-				log_info(_("local node %i can attach to %s target node %i"),
-						 config_file_options.node_id,
-						 action,
-						 follow_target_node_record->node_id);
-
-				log_detail(_("local node's recovery point: %X/%X; %s target node's fork point: %X/%X"),
-						   format_lsn(local_xlogpos),
-						   action,
-						   format_lsn(follow_target_history->end));
-			}
-		}
-	}
-
-	PQfinish(follow_target_repl_conn);
-
-	if (follow_target_history)
-		pfree(follow_target_history);
-
-	return success;
-}
-
-
-/*
- * Simple check to see if "shared_preload_libraries" includes "repmgr".
- * Parsing "shared_preload_libraries" is non-trivial, as it's potentially
- * a comma-separated list, and worse may not be readable by the repmgr
- * user.
- *
- * Instead, we check if a function which should return a value returns
- * NULL; this indicates the shared library is not installed.
- */
-void
-check_shared_library(PGconn *conn)
-{
-	bool ok = repmgrd_check_local_node_id(conn);
-
-	if (ok == true)
-		return;
-
-	log_error(_("repmgrd not configured for this node"));
-	log_hint(_("ensure \"shared_preload_libraries\" includes \"repmgr\" and restart PostgreSQL"));
-	PQfinish(conn);
-	exit(ERR_BAD_CONFIG);
-}
-
-
-bool
-is_repmgrd_running(PGconn *conn)
-{
-	pid_t		pid;
-	bool		is_running = false;
-
-	pid = repmgrd_get_pid(conn);
-
-	if (pid != UNKNOWN_PID)
-	{
-		if (kill(pid, 0) != -1)
-		{
-			is_running = true;
-		}
-	}
-
-	return is_running;
-}

repmgr-client.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -40,17 +40,14 @@
 #define NODE_CHECK			   14
 #define NODE_SERVICE		   15
 #define NODE_REJOIN            16
-#define NODE_CONTROL           17
-#define CLUSTER_SHOW		   18
-#define CLUSTER_CLEANUP		   19
-#define CLUSTER_MATRIX		   20
-#define CLUSTER_CROSSCHECK	   21
-#define CLUSTER_EVENT		   22
-#define DAEMON_STATUS		   23
-#define DAEMON_PAUSE		   24
-#define DAEMON_UNPAUSE		   25
-#define DAEMON_START 		   26
-#define DAEMON_STOP 		   27
+#define CLUSTER_SHOW		   17
+#define CLUSTER_CLEANUP		   18
+#define CLUSTER_MATRIX		   19
+#define CLUSTER_CROSSCHECK	   20
+#define CLUSTER_EVENT		   21
+#define DAEMON_STATUS		   22
+#define DAEMON_PAUSE		   23
+#define DAEMON_UNPAUSE		   24
 
 /* command line options without short versions */
 #define OPT_HELP						   1001
@@ -95,11 +92,6 @@
 #define OPT_NO_WAIT                        1040
 #define OPT_MISSING_SLOTS                  1041
 #define OPT_REPMGRD_NO_PAUSE               1042
-#define OPT_VERSION_NUMBER				   1043
-#define OPT_DATA_DIRECTORY_CONFIG		   1044
-#define OPT_COMPACT		                   1045
-#define OPT_DISABLE_WAL_RECEIVER           1046
-#define OPT_ENABLE_WAL_RECEIVER            1047
 
 /* deprecated since 3.3 */
 #define OPT_DATA_DIR						999
@@ -110,18 +102,16 @@
 static struct option long_options[] =
 {
 /* general options */
-	{"help", no_argument, NULL, OPT_HELP},
 	{"version", no_argument, NULL, 'V'},
-	{"version-number", no_argument, NULL, OPT_VERSION_NUMBER},
+	{"help", no_argument, NULL, OPT_HELP},
 
 /* general configuration options */
 	{"config-file", required_argument, NULL, 'f'},
 	{"dry-run", no_argument, NULL, OPT_DRY_RUN},
 	{"force", no_argument, NULL, 'F'},
 	{"pg_bindir", required_argument, NULL, 'b'},
-	{"wait", optional_argument, NULL, 'w'},
+	{"wait", no_argument, NULL, 'w'},
 	{"no-wait", no_argument, NULL, 'W'},
-	{"compact", no_argument, NULL, OPT_COMPACT},
 
 /* connection options */
 	{"dbname", required_argument, NULL, 'd'},
@@ -166,7 +156,7 @@ static struct option long_options[] =
 
 /* "standby switchover" options
  *
- * Note: --force-rewind accepted to pass to "node rejoin"
+ * Note: --force-rewind accepted to pass to "node join"
  */
 	{"always-promote", no_argument, NULL, OPT_ALWAYS_PROMOTE},
 	{"siblings-follow", no_argument, NULL, OPT_SIBLINGS_FOLLOW},
@@ -184,7 +174,6 @@ static struct option long_options[] =
 	{"missing-slots", no_argument, NULL, OPT_MISSING_SLOTS},
 	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
 	{"replication-connection", no_argument, NULL, OPT_REPL_CONN},
-	{"data-directory-config", no_argument, NULL, OPT_DATA_DIRECTORY_CONFIG},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},
@@ -204,10 +193,6 @@ static struct option long_options[] =
 /* "cluster cleanup" options */
 	{"keep-history", required_argument, NULL, 'k'},
 
-/* undocumented options for testing */
-	{"disable-wal-receiver", no_argument, NULL, OPT_DISABLE_WAL_RECEIVER},
-	{"enable-wal-receiver", no_argument, NULL, OPT_ENABLE_WAL_RECEIVER},
-
 /* deprecated */
 	{"check-upstream-config", no_argument, NULL, OPT_CHECK_UPSTREAM_CONFIG},
 	{"no-conninfo-password", no_argument, NULL, OPT_NO_CONNINFO_PASSWORD},

repmgr.c

@@ -1,7 +1,7 @@
 /*
  * repmgr.c - repmgr extension
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This is the actual extension code; see repmgr-client.c for the code which
  * generates the repmgr binary
@@ -40,6 +40,7 @@
 
 #include "utils/timestamp.h"
 
+#include "executor/spi.h"
 #include "lib/stringinfo.h"
 #include "access/xact.h"
 #include "utils/snapmgr.h"
@@ -53,7 +54,6 @@
 #include "voting.h"
 
 #define UNKNOWN_NODE_ID		-1
-#define ELECTION_RERUN_NOTIFICATION -2
 #define UNKNOWN_PID			-1
 
 #define TRANCHE_NAME "repmgrd"
@@ -78,7 +78,6 @@ typedef struct repmgrdSharedState
 	char		repmgrd_pidfile[MAXPGPATH];
 	bool		repmgrd_paused;
 	/* streaming failover */
-	TimestampTz upstream_last_seen;
 	NodeVotingStatus voting_status;
 	int			current_electoral_term;
 	int			candidate_node_id;
@@ -109,12 +108,6 @@ PG_FUNCTION_INFO_V1(standby_set_last_updated);
 Datum		standby_get_last_updated(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(standby_get_last_updated);
 
-Datum		set_upstream_last_seen(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(set_upstream_last_seen);
-
-Datum		get_upstream_last_seen(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_upstream_last_seen);
-
 Datum		notify_follow_primary(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(notify_follow_primary);
 
@@ -148,8 +141,6 @@ PG_FUNCTION_INFO_V1(repmgrd_pause);
 Datum		repmgrd_is_paused(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(repmgrd_is_paused);
 
-Datum		get_wal_receiver_pid(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_wal_receiver_pid);
 
 
 /*
@@ -228,8 +219,6 @@ repmgr_shmem_startup(void)
 		memset(shared_state->repmgrd_pidfile, 0, MAXPGPATH);
 		shared_state->repmgrd_paused = false;
 		shared_state->current_electoral_term = 0;
-		/* arbitrary "magic" date to indicate this field hasn't been updated */
-		shared_state->upstream_last_seen = POSTGRES_EPOCH_JDATE;
 		shared_state->voting_status = VS_NO_VOTE;
 		shared_state->candidate_node_id = UNKNOWN_NODE_ID;
 		shared_state->follow_new_primary = false;
@@ -365,54 +354,6 @@ standby_get_last_updated(PG_FUNCTION_ARGS)
 }
 
 
-Datum
-set_upstream_last_seen(PG_FUNCTION_ARGS)
-{
-	if (!shared_state)
-		PG_RETURN_VOID();
-
-	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
-
-	shared_state->upstream_last_seen = GetCurrentTimestamp();
-
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_VOID();
-}
-
-
-Datum
-get_upstream_last_seen(PG_FUNCTION_ARGS)
-{
-	long		secs;
-	int			microsecs;
-	TimestampTz last_seen;
-
-	if (!shared_state)
-		PG_RETURN_INT32(-1);
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	last_seen = shared_state->upstream_last_seen;
-
-	LWLockRelease(shared_state->lock);
-
-	/*
-	 * "last_seen" is initialised with the PostgreSQL epoch as a
-	 * "magic" value to indicate the field hasn't ever been updated
-	 * by repmgrd. We return -1 instead, rather than imply that the
-	 * primary was last seen at the turn of the century.
-	 */
-	if (last_seen == POSTGRES_EPOCH_JDATE)
-		PG_RETURN_INT32(-1);
-
-
-	TimestampDifference(last_seen, GetCurrentTimestamp(),
-						&secs, &microsecs);
-
-	/* let's hope repmgrd never runs for more than a century or so without seeing a primary */
-	PG_RETURN_INT32((uint32)secs);
-}
 
 
 /* ===================*/
@@ -426,10 +367,10 @@ notify_follow_primary(PG_FUNCTION_ARGS)
 	int			primary_node_id = UNKNOWN_NODE_ID;
 
 	if (!shared_state)
-		PG_RETURN_VOID();
+		PG_RETURN_NULL();
 
 	if (PG_ARGISNULL(0))
-		PG_RETURN_VOID();
+		PG_RETURN_NULL();
 
 	primary_node_id = PG_GETARG_INT32(0);
 
@@ -438,17 +379,9 @@ notify_follow_primary(PG_FUNCTION_ARGS)
 	/* only do something if local_node_id is initialised */
 	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
 	{
-		if (primary_node_id == ELECTION_RERUN_NOTIFICATION)
-		{
-			elog(INFO, "node %i received notification to rerun promotion candidate election",
-				 shared_state->local_node_id);
-		}
-		else
-		{
-			elog(INFO, "node %i received notification to follow node %i",
-				 shared_state->local_node_id,
-				 primary_node_id);
-		}
+		elog(INFO, "node %i received notification to follow node %i",
+			 shared_state->local_node_id,
+			 primary_node_id);
 
 		LWLockRelease(shared_state->lock);
 		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
@@ -469,7 +402,7 @@ get_new_primary(PG_FUNCTION_ARGS)
 	int			new_primary_node_id = UNKNOWN_NODE_ID;
 
 	if (!shared_state)
-		PG_RETURN_INT32(UNKNOWN_NODE_ID);
+		PG_RETURN_NULL();
 
 	LWLockAcquire(shared_state->lock, LW_SHARED);
 
@@ -479,7 +412,7 @@ get_new_primary(PG_FUNCTION_ARGS)
 	LWLockRelease(shared_state->lock);
 
 	if (new_primary_node_id == UNKNOWN_NODE_ID)
-		PG_RETURN_INT32(UNKNOWN_NODE_ID);
+		PG_RETURN_NULL();
 
 	PG_RETURN_INT32(new_primary_node_id);
 }
@@ -747,17 +680,3 @@ repmgrd_is_paused(PG_FUNCTION_ARGS)
 
 	PG_RETURN_BOOL(is_paused);
 }
-
-
-Datum
-get_wal_receiver_pid(PG_FUNCTION_ARGS)
-{
-	int wal_receiver_pid;
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	wal_receiver_pid = WalRcv->pid;
-
-	PG_RETURN_INT32(wal_receiver_pid);
-}

repmgr.conf.sample

@@ -33,13 +33,13 @@
 				 # the local node using this string.
 				 #
 				 # For details on conninfo strings, see:
-				 #  https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING
+				 #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING
 				 #
 				 # If repmgrd is in use, consider explicitly setting
 				 # "connect_timeout" in the conninfo string to determine
 				 # the length of time which elapses before a network
 				 # connection attempt is abandoned; for details see:
-				 #  https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT
+				 #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT
 
 #data_directory=''		 # The node's data directory. This is needed by repmgr
 				 # when performing operations when the PostgreSQL instance
@@ -247,9 +247,6 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for the demoted standby to reconnect to the promoted
 					# primary (note: this value should be equal to or greater
 					# than that set for "node_rejoin_timeout")
-#wal_receive_check_timeout=30		# The max length of time (in seconds) to wait for the walreceiver
-					# on the standby to flush WAL to disk before comparing location
-					# with the shut-down primary
 
 #------------------------------------------------------------------------------
 # "node rejoin" settings
@@ -278,6 +275,11 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # These settings are only applied when repmgrd is running. Values shown
 # are defaults.
 
+#repmgrd_pid_file=			# Path of PID file to use for repmgrd; if not set, a PID file will
+					# be generated in a temporary directory specified by the environment
+					# variable $TMPDIR, or if not set, in "/tmp". This value can be overridden
+					# by the command line option "-p/--pid-file"; the command line option
+					# "--no-pid-file" will force PID file creation to be skipped.
 #failover=manual			# one of 'automatic', 'manual'.
 					# determines what action to take in the event of upstream failure
 					#
@@ -287,13 +289,10 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					#    manual attention to reattach it to replication
 					# (does not apply to BDR mode)
 
-#priority=100				# indicates a preferred priority for promoting nodes;
+#priority=100				# indicate a preferred priority for promoting nodes;
 					# a value of zero prevents the node being promoted to primary
 					# (default: 100)
 
-#connection_check_type=ping		# How to check availability of the upstream node; valid options:
-                                        #  'ping': use PQping() to check if the node is accepting connections
-                                        #  'connection': execute a throwaway query on the current connection
 #reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
 #reconnect_interval=10			# Interval between attempts to reconnect to an unreachable
@@ -317,29 +316,10 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #monitoring_history=no                  # Whether to write monitoring data to the "montoring_history" table
 #monitor_interval_secs=2                # Interval (in seconds) at which to write monitoring data
 #degraded_monitoring_timeout=-1		# Interval (in seconds) after which repmgrd will terminate if the
-					# server(s) being monitored are no longer available. -1 (default)
+					# server being monitored is no longer available. -1 (default)
 					# disables the timeout completely.
 #async_query_timeout=60			# Interval (in seconds) which repmgrd will wait before
 					# cancelling an asynchronous query.
-#repmgrd_pid_file=			# Path of PID file to use for repmgrd; if not set, a PID file will
-					# be generated in a temporary directory specified by the environment
-					# variable $TMPDIR, or if not set, in "/tmp". This value can be overridden
-					# by the command line option "-p/--pid-file"; the command line option
-					# "--no-pid-file" will force PID file creation to be skipped.
-					# Note: there is normally no need to set this, particularly if
-					# repmgr was installed from packages.
-#standby_disconnect_on_failover=false	# If "true", in a failover situation wait for all standbys to
-					# disconnect their WAL receivers before electing a new primary
-					# (PostgreSQL 9.5 and later only; repmgr user must be a superuser for this)
-#sibling_nodes_disconnect_timeout=30	# If "standby_disconnect_on_failover" is true, the maximum length of time
-					#  (in seconds) to wait for other standbys to confirm they have disconnected their
-					# WAL receivers
-#failover_validation_command=		# Script to execute for an external mechanism to validate the failover
-					# decision made by repmgrd. One or both of the following parameter placeholders
-					# should be provided, which will be replaced by repmgrd with the appropriate
-					# value: %n (node_id), %a (node_name). *Must* be the same on all nodes.
-#election_rerun_interval=15		# if "failover_validation_command" is set, and the command returns
-					# an error, pause the specified amount of seconds before rerunning the election.
 
 #------------------------------------------------------------------------------
 # service control commands
@@ -348,12 +328,6 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # repmgr provides options to override the default pg_ctl commands
 # used to stop, start, restart, reload and promote the PostgreSQL cluster
 #
-# These options are useful when PostgreSQL has been installed from a package
-# which provides OS-level service commands. In environments using an init system
-# such as systemd, which keeps track of the state of various services, it is
-# essential that the service commands are correctly configured and pg_ctl is
-# not executed directly.
-#
 # NOTE: These commands must be runnable on remote nodes as well for switchover
 # to function correctly.
 #
@@ -375,7 +349,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #
 # Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
 #
-# For more details, see: https://repmgr.org/docs/current/configuration-service-commands.html
+# For more details, see: https://repmgr.org/docs/4.1/configuration-service-commands.html
 
 #service_start_command = ''
 #service_stop_command = ''
@@ -387,11 +361,6 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for "promote_command"; do not use "repmgr standby promote"
 					# (or a script which executes "repmgr standby promote") here.
 
-# Used by "repmgr daemon (start|stop)" to control repmgrd
-#
-#repmgrd_service_start_command = ''
-#repmgrd_service_stop_command = ''
-
 #------------------------------------------------------------------------------
 # Status check thresholds
 #------------------------------------------------------------------------------

repmgr.control

@@ -1,6 +1,6 @@
 # repmgr extension
 comment = 'Replication manager for PostgreSQL'
-default_version = '4.3'
+default_version = '4.2'
 module_pathname = '$libdir/repmgr'
 relocatable = false
 schema = repmgr

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -41,7 +41,6 @@
 #include "configfile.h"
 #include "dbutils.h"
 #include "log.h"
-#include "sysutils.h"
 
 #define MIN_SUPPORTED_VERSION		"9.3"
 #define MIN_SUPPORTED_VERSION_NUM	90300
@@ -59,11 +58,8 @@
 #define NODE_NOT_FOUND		-1
 #define NO_UPSTREAM_NODE	-1
 #define UNKNOWN_NODE_ID		-1
-#define MIN_NODE_ID          1
-#define ELECTION_RERUN_NOTIFICATION -2
+
 #define VOTING_TERM_NOT_SET -1
-#define ARCHIVE_STATUS_DIR_ERROR -1
-#define NO_DEGRADED_MONITORING_ELAPSED -1
 
 #define BDR2_REPLICATION_SET_NAME "repmgr"
 
@@ -92,11 +88,6 @@
 #define DEFAULT_SHUTDOWN_CHECK_TIMEOUT       60  /* seconds */
 #define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */
 #define DEFAULT_NODE_REJOIN_TIMEOUT          60  /* seconds */
-#define DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT    30  /* seconds */
-#define DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT 30 /* seconds */
-#define DEFAULT_ELECTION_RERUN_INTERVAL      15  /* seconds */
-
-#define WALRECEIVER_DISABLE_TIMEOUT_VALUE    86400000 /* milliseconds */
 
 #ifndef RECOVERY_COMMAND_FILE
 #define RECOVERY_COMMAND_FILE "recovery.conf"

repmgr_version.h.in

@@ -1,3 +1,2 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.3rc1"
-#define REPMGR_VERSION_NUM 40300
+#define REPMGR_VERSION "4.2"

repmgrd-bdr.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd-bdr.c - BDR functionality for repmgrd
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -43,12 +43,10 @@ handle_sigint_bdr(SIGNAL_ARGS)
 	initPQExpBuffer(&event_details);
 
 	appendPQExpBuffer(&event_details,
-					  _("%s signal received"),
+					  "%s signal received",
 					  postgres_signal_arg == SIGTERM
 					  ? "TERM" : "INT");
 
-	log_notice("%s", event_details.data);
-
 	create_event_notification(local_conn,
 							  &config_file_options,
 							  config_file_options.node_id,

repmgrd-bdr.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-bdr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgrd-physical.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-physical.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgrd.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd.c - Replication manager daemon
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -372,6 +372,12 @@ main(int argc, char **argv)
 	/* abort if local node not available at startup */
 	local_conn = establish_db_connection(config_file_options.conninfo, true);
 
+	/*
+	 * store the server version number - we'll need this to generate
+	 * version-dependent queries etc.
+	 */
+	server_version_num = get_server_version(local_conn, NULL);
+
 	/*
 	 * sanity checks
 	 *
@@ -383,51 +389,10 @@ main(int argc, char **argv)
 	 * repmgr has not been properly configured.
 	 */
 
-
-	/* warn about any settings which might not be relevant for the current PostgreSQL version  */
-	if (config_file_options.standby_disconnect_on_failover == true && PQserverVersion(local_conn) < 90500)
-	{
-		log_warning(_("\"standby_disconnect_on_failover\" specified, but not available for this PostgreSQL version"));
-		/* TODO: format server version */
-		log_detail(_("available from PostgreSQL 9.5, this PostgreSQL version is %i"), PQserverVersion(local_conn));
-	}
-
 	/* Check "repmgr" the extension is installed */
 	extension_status = get_repmgr_extension_status(local_conn, &extversions);
 
-	if (extension_status == REPMGR_INSTALLED)
-	{
-		/*
-		 * extension is the latest available according to "pg_available_extensions" -
-		 * - does our (major) version match that?
-		 */
-		log_verbose(LOG_DEBUG, "binary version: %i; extension version: %i",
-					REPMGR_VERSION_NUM, extversions.installed_version_num);
-		if ((REPMGR_VERSION_NUM/100) < (extversions.installed_version_num / 100))
-		{
-			log_error(_("this \"repmgr\" version is older than the installed \"repmgr\" extension version"));
-			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
-					   REPMGR_VERSION,
-					   extversions.installed_version);
-
-			log_hint(_("verify the repmgr installation on this server is updated properly before continuing"));
-			close_connection(&local_conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		if ((REPMGR_VERSION_NUM/100) > (extversions.installed_version_num / 100))
-		{
-			log_error(_("this \"repmgr\" version is newer than the installed \"repmgr\" extension version"));
-			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
-					   REPMGR_VERSION,
-					   extversions.installed_version);
-
-			log_hint(_("verify the repmgr extension is updated properly before continuing"));
-			close_connection(&local_conn);
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-	else
+	if (extension_status != REPMGR_INSTALLED)
 	{
 		/* this is unlikely to happen */
 		if (extension_status == REPMGR_UNKNOWN)
@@ -441,10 +406,11 @@ main(int argc, char **argv)
 		if (extension_status == REPMGR_OLD_VERSION_INSTALLED)
 		{
 			log_error(_("an older version of the \"repmgr\" extension is installed"));
-			log_detail(_("extension version %s is installed but newer version %s is available"),
+			log_detail(_("version %s is installed but newer version %s is available"),
 					   extversions.installed_version,
 					   extversions.default_version);
 			log_hint(_("verify the repmgr installation is updated properly before continuing"));
+
 		}
 		else
 		{
@@ -627,8 +593,7 @@ daemonize_process(void)
 	switch (pid)
 	{
 		case -1:
-			log_error(_("error in fork()"));
-			log_detail("%s", strerror(errno));
+			log_error(_("error in fork():\n  %s"), strerror(errno));
 			exit(ERR_SYS_FAILURE);
 			break;
 
@@ -637,8 +602,7 @@ daemonize_process(void)
 			pid = setsid();
 			if (pid == (pid_t) -1)
 			{
-				log_error(_("error executing setsid()"));
-				log_detail("%s", strerror(errno));
+				log_error(_("error in setsid():\n  %s"), strerror(errno));
 				exit(ERR_SYS_FAILURE);
 			}
 
@@ -648,8 +612,7 @@ daemonize_process(void)
 			/* error case */
 			if (pid == -1)
 			{
-				log_error(_("error executing fork()"));
-				log_detail("%s", strerror(errno));
+				log_error(_("error in fork():\n  %s"), strerror(errno));
 				exit(ERR_SYS_FAILURE);
 			}
 
@@ -827,81 +790,6 @@ show_help(void)
 }
 
 
-bool
-check_upstream_connection(PGconn **conn, const char *conninfo)
-{
-	/* Check the connection status twice in case it changes after reset */
-	bool		twice = false;
-
-	if (config_file_options.connection_check_type == CHECK_PING)
-		return is_server_available(conninfo);
-
-	if (config_file_options.connection_check_type == CHECK_CONNECTION)
-	{
-		bool success = true;
-		PGconn *test_conn = PQconnectdb(conninfo);
-
-		log_debug("check_upstream_connection(): attempting to connect to \"%s\"", conninfo);
-
-		if (PQstatus(test_conn) != CONNECTION_OK)
-		{
-			log_warning(_("unable to connect to \"%s\""), conninfo);
-			success = false;
-		}
-		PQfinish(test_conn);
-
-		return success;
-	}
-
-	for (;;)
-	{
-		if (PQstatus(*conn) != CONNECTION_OK)
-		{
-			log_debug("check_upstream_connection(): connection not OK");
-			if (twice)
-				return false;
-			/* reconnect */
-			PQfinish(*conn);
-			*conn = PQconnectdb(conninfo);
-			twice = true;
-		}
-		else
-		{
-			if (!cancel_query(*conn, config_file_options.async_query_timeout))
-				goto failed;
-
-			if (wait_connection_availability(*conn, config_file_options.async_query_timeout) != 1)
-				goto failed;
-
-			/* execute a simple query to verify connection availability */
-			if (PQsendQuery(*conn, "SELECT 1") == 0)
-			{
-				log_warning(_("unable to send query to upstream"));
-				log_detail("%s", PQerrorMessage(*conn));
-				goto failed;
-			}
-
-			if (wait_connection_availability(*conn, config_file_options.async_query_timeout) != 1)
-				goto failed;
-
-			break;
-
-	failed:
-			/* retry once */
-			if (twice)
-				return false;
-
-			/* reconnect */
-			PQfinish(*conn);
-			*conn = PQconnectdb(conninfo);
-			twice = true;
-		}
-	}
-
-	return true;
-}
-
-
 void
 try_reconnect(PGconn **conn, t_node_info *node_info)
 {
@@ -927,7 +815,8 @@ try_reconnect(PGconn **conn, t_node_info *node_info)
 				 node_info->node_id, i + 1, max_attempts);
 		if (is_server_available_params(&conninfo_params) == true)
 		{
-			log_notice(_("node %i has recovered, reconnecting"), node_info->node_id);
+
+			log_notice(_("node has recovered, reconnecting"));
 
 			/*
 			 * XXX we should also handle the case where node is pingable but
@@ -957,7 +846,7 @@ try_reconnect(PGconn **conn, t_node_info *node_info)
 
 					if (ping_result != PGRES_TUPLES_OK)
 					{
-						log_info("original connection no longer available, using new connection");
+						log_info("original connnection no longer available, using new connection");
 						close_connection(conn);
 						*conn = our_conn;
 					}

repmgrd.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  */
 
 
@@ -23,7 +23,6 @@ extern PGconn *local_conn;
 extern bool startup_event_logged;
 extern char pid_file[MAXPGPATH];
 
-bool		check_upstream_connection(PGconn **conn, const char *conninfo);
 void		try_reconnect(PGconn **conn, t_node_info *node_info);
 
 int			calculate_elapsed(instr_time start_time);
@@ -32,4 +31,5 @@ const char *print_monitoring_state(MonitoringState monitoring_state);
 void		update_registration(PGconn *conn);
 void		terminate(int retval);
 
+
 #endif							/* _REPMGRD_H_ */

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by