doc: add a link to the current documentation from the contents page

Per user report on mailing list.

.gitignore

@@ -39,6 +39,8 @@ lib*.pc
 
 # test output
 /results/
+/regression.diffs
+/regression.out
 
 /doc/Makefile
 

CONTRIBUTING.md

@@ -2,7 +2,7 @@ License and Contributions
 =========================
 
 `repmgr` is licensed under the GPL v3.  All of its code and documentation is
-Copyright 2010-2017, 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.

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2017, 2ndQuadrant Limited
+Copyright (c) 2010-2018, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify
@@ -12,5 +12,5 @@ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License
-along with this program.  If not, see http://www.gnu.org/licenses/
+along with this program.  If not, see https://www.gnu.org/licenses/
 to obtain one.

FAQ.md

@@ -0,0 +1,8 @@
+FAQ - Frequently Asked Questions about repmgr
+=============================================
+
+The repmgr 4 FAQ is located here: [repmgr FAQ (Frequently Asked Questions)](https://repmgr.org/docs/4.0/appendix-faq.html "repmgr FAQ")
+
+The repmgr 3.x FAQ can be found here:
+
+    https://github.com/2ndQuadrant/repmgr/blob/REL3_3_STABLE/FAQ.md

HISTORY

@@ -1,6 +1,116 @@
-4.0     2017-10-04
-        Complete rewrite with many changes; see file "doc/upgrading-from-repmgr3.md"
-        for details.
+4.0.6   2018-06-14
+        repmgr: (witness register) prevent registration of a witness server with the
+ 		  same name as an existing node (Ian)
+		repmgr: (standby follow) check node has actually connected to new primary
+		  before reporting success; GitHub #444 (Ian)
+		repmgr: (standby clone) improve handling of external configuration file copying,
+		  including consideration in --dry-run check; GitHub #443 (Ian)
+		repmgr: (standby clone) don't require presence of "user" parameter in
+		  conninfo string; GitHub #437 (Ian)
+		repmgr: (standby clone) improve documentation of --recovery-conf-only
+		  mode; GitHub #438 (Ian)
+		repmgr: (node rejoin) fix bug when parsing --config-files parameter;
+		  GitHub #442 (Ian)
+		repmgr: when using --dry-run, force log level to INFO to ensure output
+		  will always be displayed; GitHub #441 (Ian)
+        repmgr: (cluster matrix/crosscheck) return non-zero exit code if node
+           connection issues detected; GitHub #447 (Ian)
+		repmgrd: ensure local node is counted as quorum member; GitHub #439 (Ian)
+
+4.0.5   2018-05-02
+        repmgr: poll demoted primary after restart as a standby during a
+          switchover operation; GitHub #408 (Ian)
+        repmgr: add configuration parameter "config_directory"; GitHub #424 (Ian)
+        repmgr: add "dbname=replication" to all replication connection strings;
+          GitHub #421 (Ian)
+        repmgr: add sanity check if --upstream-node-id not supplied when executing
+          "standby register"; GitHub #395 (Ian)
+        repmgr: enable provision of "archive_cleanup_command" in recovery.conf;
+          GitHub #416 (Ian)
+        repmgr: actively check for node to rejoin cluster; GitHub #415 (Ian)
+        repmgr: enable pg_rewind to be used with PostgreSQL 9.3/9.4; GitHub #413 (Ian)
+        repmgr: fix minimum accepted value for "degraded_monitoring_timeout";
+          GitHub #411 (Ian)
+        repmgr: fix superuser password handling; GitHub #400 (Ian)
+        repmgr: fix parsing of "archive_ready_critical" configuration file
+          parameter; GitHub #426 (Ian)
+        repmgr: fix display of conninfo parsing error messages (Ian)
+        repmgr: fix "repmgr cluster crosscheck" output; GitHub #389 (Ian)
+        repmgrd: prevent standby connection handle from going stale (Ian)
+        repmgrd: fix memory leaks in witness code; GitHub #402 (AndrzejNowicki, Martín)
+        repmgrd: handle "pg_ctl promote" timeout; GitHub #425 (Ian)
+        repmgrd: handle failover situation with only two nodes in the primary
+          location, and at least one node in another location; GitHub #407 (Ian)
+        repmgrd: set "connect_timeout=2" when pinging a server (Ian)
+
+4.0.4   2018-03-09
+        repmgr: add "standby clone --recovery-conf-only" option; GitHub #382 (Ian)
+        repmgr: make "standby promote" timeout values configurable; GitHub #387 (Ian)
+        repmgr: improve replication slot warnings generated by "node status";
+          GitHub #385 (Ian)
+        repmgr: remove restriction on replication slots when cloning from
+          a Barman server; GitHub #379 (Ian)
+        repmgr: ensure "node rejoin" honours "--dry-run" option; GitHub #383 (Ian)
+        repmgr: fix --superuser handling when cloning a standby; GitHub #380 (Ian)
+        repmgr: update various help options; GitHub #391, #392 (hasegeli)
+        repmgrd: add event "repmgrd_shutdown"; GitHub #393 (Ian)
+        repmgrd: improve detection of status change from primary to standby (Ian)
+        repmgrd: improve log output in various situations (Ian)
+        repmgrd: improve reconnection to the local node after a failover (Ian)
+        repmgrd: ensure witness server connects to new primary after a failover (Ian)
+
+4.0.3   2018-02-15
+        repmgr: improve switchover handling when "pg_ctl" used to control the
+          server and logging output is not explicitly redirected (Ian)
+        repmgr: improve switchover log messages and exit code when old primary could
+          not be shut down cleanly (Ian)
+        repmgr: check demotion candidate can make a replication connection to the
+          promotion candidate before executing a switchover; GitHub #370 (Ian)
+        repmgr: add check for sufficient walsenders/replication slots before executing
+          a switchover; GitHub #371 (Ian)
+        repmgr: add --dry-run mode to "repmgr standby follow"; GitHub #368 (Ian)
+        repmgr: provide information about the primary node for "standby_register" and
+          "standby_follow" event notifications; GitHub #375 (Ian)
+        repmgr: add "standby_register_sync" event notification; GitHub #374 (Ian)
+        repmgr: output any connection error messages in "cluster show"'s list of
+          warnings; GitHub #369 (Ian)
+        repmgr: ensure an inactive data directory can be deleted; GitHub #366 (Ian)
+        repmgr: fix upstream node display in "repmgr node status"; GitHub #363 (fanf2)
+        repmgr: improve/clarify documentation and update --help output for
+          "primary unregister"; GitHub #373 (Ian)
+        repmgr: allow replication slots when Barman is configured; GitHub #379 (Ian)
+        repmgr: fix parsing of "pg_basebackup_options"; GitHub #376 (Ian)
+        repmgr: ensure "pg_subtrans" directory is created when cloning a standby in
+          Barman mode (Ian)
+        repmgr: fix primary node check in "witness register"; GitHub #377 (Ian)
+
+4.0.2   2018-01-18
+        repmgr: add missing -W option to getopt_long() invocation; GitHub #350 (Ian)
+        repmgr: automatically create slot name if missing; GitHub #343 (Ian)
+        repmgr: fixes to parsing output of remote repmgr invocations; GitHub #349 (Ian)
+        repmgr: BDR support - create missing connection replication set
+          if required; GitHub #347 (Ian)
+        repmgr: handle missing node record in "repmgr node rejoin"; GitHub #358 (Ian)
+        repmgr: enable documentation to be build as single HTML file; GitHub #353 (fanf2)
+        repmgr: recognize "--terse" option for "repmgr cluster event"; GitHub #360 (Ian)
+        repmgr: add "--wait-start" option for "repmgr standby register"; GitHub #356 (Ian)
+        repmgr: add "%p" event notification parameter for "repmgr standby switchover"
+          containing the node ID of the demoted primary (Ian)
+        docs: various fixes and updates (Ian, Daymel, Martín, ams)
+
+4.0.1   2017-12-13
+        repmgr: ensure "repmgr node check --action=" returns appropriate return
+          code; GitHub #340 (Ian)
+        repmgr: add missing schema qualification in get_all_node_records_with_upstream()
+          query GitHub #341 (Martín)
+        repmgr: initialise "voting_term" table in application, not extension SQL;
+          GitHub #344 (Ian)
+        repmgr: delete any replication slots copied by pg_rewind; GitHub #334 (Ian)
+        repmgr: fix configuration file sanity check; GitHub #342 (Ian)
+
+4.0.0   2017-11-21
+        Complete rewrite with many changes; for details see the repmgr 4.0.0 release
+        notes at: https://repmgr.org/docs/4.0/release-4.0.0.html
 
 3.3.2   2017-06-01
         Add support for PostgreSQL 10 (Ian)
@@ -223,7 +333,7 @@
         Add a ssh_options parameter (Jay Taylor)
 
 2.0beta1 2012-07-27
-        Make CLONE command try to make an exact copy including $PGDATA location (Cedric) 
+        Make CLONE command try to make an exact copy including $PGDATA location (Cedric)
         Add detection of master failure (Jaime)
         Add the notion of a witness server (Jaime)
         Add autofailover capabilities (Jaime)

Makefile.in

@@ -37,9 +37,10 @@ include Makefile.global
 $(info Building against PostgreSQL $(MAJORVERSION))
 
 REPMGR_CLIENT_OBJS = repmgr-client.o \
-	repmgr-action-primary.o repmgr-action-standby.o repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.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 \
 	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
+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
@@ -77,6 +78,7 @@ additional-clean:
 	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

TODO.md

@@ -0,0 +1,20 @@
+TODO
+====
+
+This file contains a list of improvements which are desireable and/or have
+been requested, and which we aim to address/implement when time and resources
+permit.
+
+It is *not* a roadmap and there's no guarantee of any item being implemented
+within any given timeframe.
+
+
+Enable suspension of repmgrd failover
+-------------------------------------
+
+When performing maintenance, e.g. a switchover, it's necessary to stop all
+repmgrd nodes to prevent unintended failover; this is obviously inconvenient.
+We'll need to implement some way of notifying each repmgrd to suspend automatic
+failover until further notice.
+
+Requested in GitHub #410 ( https://github.com/2ndQuadrant/repmgr/issues/410 )

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, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

compat.h

@@ -1,6 +1,6 @@
 /*
  * compat.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

config.h.in

@@ -1,4 +1,2 @@
 /* config.h.in.  Generated from configure.in by autoheader.  */
 
-/* Only build repmgr for BDR */
-#undef BDR_ONLY

configfile.c

@@ -1,7 +1,7 @@
 /*
  * config.c - parse repmgr.conf and other configuration-related functionality
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -73,6 +73,59 @@ load_config(const char *config_file, bool verbose, bool terse, t_configuration_o
 		strncpy(config_file_path, config_file, MAXPGPATH);
 		canonicalize_path(config_file_path);
 
+		/* relative path supplied - convert to absolute path */
+		if (config_file_path[0] != '/')
+		{
+			PQExpBufferData fullpath;
+			char *pwd = NULL;
+
+			initPQExpBuffer(&fullpath);
+
+			/*
+			 * we'll attempt to use $PWD to derive the effective path; getcwd()
+			 * will likely resolve symlinks, which may result in a path which
+			 * isn't permanent (e.g. if filesystem mountpoints change).
+			 */
+			pwd = getenv("PWD");
+
+			if (pwd != NULL)
+			{
+				appendPQExpBuffer(&fullpath,
+								  "%s", pwd);
+			}
+			else
+			{
+				/* $PWD not available - fall back to getcwd() */
+				char cwd[MAXPGPATH] = "";
+
+				if (getcwd(cwd, MAXPGPATH) == NULL)
+				{
+					log_error(_("unable to execute getcwd()"));
+					log_detail("%s", strerror(errno));
+
+					termPQExpBuffer(&fullpath);
+					exit(ERR_BAD_CONFIG);
+				}
+
+				appendPQExpBuffer(&fullpath,
+								  "%s",
+								  cwd);
+			}
+
+			appendPQExpBuffer(&fullpath,
+							  "/%s", config_file_path);
+
+			log_debug("relative configuration file converted to:\n  \"%s\"",
+					  fullpath.data);
+
+			strncpy(config_file_path, fullpath.data, MAXPGPATH);
+
+			termPQExpBuffer(&fullpath);
+
+			canonicalize_path(config_file_path);
+		}
+
+
 		if (stat(config_file_path, &stat_config) != 0)
 		{
 			log_error(_("provided configuration file \"%s\" not found: %s"),
@@ -81,6 +134,7 @@ load_config(const char *config_file, bool verbose, bool terse, t_configuration_o
 			exit(ERR_BAD_CONFIG);
 		}
 
+
 		if (verbose == true)
 		{
 			log_notice(_("using provided configuration file \"%s\""), config_file);
@@ -234,6 +288,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	memset(options->node_name, 0, sizeof(options->node_name));
 	memset(options->conninfo, 0, sizeof(options->conninfo));
 	memset(options->data_directory, 0, sizeof(options->data_directory));
+	memset(options->config_directory, 0, sizeof(options->data_directory));
 	memset(options->pg_bindir, 0, sizeof(options->pg_bindir));
 	options->replication_type = REPLICATION_TYPE_PHYSICAL;
 
@@ -249,7 +304,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->log_status_interval = DEFAULT_LOG_STATUS_INTERVAL;
 
 	/*-----------------------
-	 * standby action settings
+	 * standby clone settings
 	 *------------------------
 	 */
 	options->use_replication_slots = false;
@@ -260,7 +315,23 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->tablespace_mapping.tail = NULL;
 	memset(options->recovery_min_apply_delay, 0, sizeof(options->recovery_min_apply_delay));
 	options->recovery_min_apply_delay_provided = false;
+	memset(options->archive_cleanup_command, 0, sizeof(options->archive_cleanup_command));
 	options->use_primary_conninfo_password = false;
+	memset(options->passfile, 0, sizeof(options->passfile));
+
+	/*-------------------------
+	 * standby promote settings
+	 *-------------------------
+	 */
+	options->promote_check_timeout = DEFAULT_PROMOTE_CHECK_TIMEOUT;
+	options->promote_check_interval = DEFAULT_PROMOTE_CHECK_INTERVAL;
+
+	/*------------------------
+	 * standby follow settings
+	 *------------------------
+	 */
+	options->primary_follow_timeout = DEFAULT_PRIMARY_FOLLOW_TIMEOUT;
+	options->standby_follow_timeout = DEFAULT_STANDBY_FOLLOW_TIMEOUT;
 
 	/*-----------------
 	 * repmgrd settings
@@ -281,7 +352,13 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->degraded_monitoring_timeout = -1;
 	options->async_query_timeout = DEFAULT_ASYNC_QUERY_TIMEOUT;
 	options->primary_notification_timeout = DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT;
-	options->primary_follow_timeout = DEFAULT_PRIMARY_FOLLOW_TIMEOUT;
+	options->standby_reconnect_timeout = DEFAULT_STANDBY_RECONNECT_TIMEOUT;
+
+	/*-------------
+	 * witness settings
+	 *-------------
+	 */
+	options->witness_sync_interval = DEFAULT_WITNESS_SYNC_INTERVAL;
 
 	/*-------------
 	 * BDR settings
@@ -394,6 +471,9 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			strncpy(options->conninfo, value, MAXLEN);
 		else if (strcmp(name, "data_directory") == 0)
 			strncpy(options->data_directory, value, MAXPGPATH);
+		else if (strcmp(name, "config_directory") == 0)
+			strncpy(options->config_directory, value, MAXPGPATH);
+
 		else if (strcmp(name, "replication_user") == 0)
 		{
 			if (strlen(value) < NAMEDATALEN)
@@ -439,13 +519,30 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			parse_time_unit_parameter(name, value, options->recovery_min_apply_delay, error_list);
 			options->recovery_min_apply_delay_provided = true;
 		}
+		else if (strcmp(name, "archive_cleanup_command") == 0)
+			strncpy(options->archive_cleanup_command, value, MAXLEN);
 		else if (strcmp(name, "use_primary_conninfo_password") == 0)
 			options->use_primary_conninfo_password = parse_bool(value, name, error_list);
+		else if (strcmp(name, "passfile") == 0)
+			strncpy(options->passfile, value, sizeof(options->passfile));
+
+		/* standby promote settings */
+		else if (strcmp(name, "promote_check_timeout") == 0)
+			options->promote_check_timeout = repmgr_atoi(value, name, error_list, 1);
+
+		else if (strcmp(name, "promote_check_interval") == 0)
+			options->promote_check_interval = repmgr_atoi(value, name, error_list, 1);
+
+		/* standby follow settings */
+		else if (strcmp(name, "primary_follow_timeout") == 0)
+			options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "standby_follow_timeout") == 0)
+			options->standby_follow_timeout = repmgr_atoi(value, name, error_list, 0);
 
 		/* node check settings */
 		else if (strcmp(name, "archive_ready_warning") == 0)
 			options->archive_ready_warning = repmgr_atoi(value, name, error_list, 1);
-		else if (strcmp(name, "archive_ready_critcial") == 0)
+		else if (strcmp(name, "archive_ready_critical") == 0)
 			options->archive_ready_critical = repmgr_atoi(value, name, error_list, 1);
 		else if (strcmp(name, "replication_lag_warning") == 0)
 			options->replication_lag_warning = repmgr_atoi(value, name, error_list, 1);
@@ -486,13 +583,17 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		else if (strcmp(name, "monitoring_history") == 0)
 			options->monitoring_history = parse_bool(value, name, error_list);
 		else if (strcmp(name, "degraded_monitoring_timeout") == 0)
-			options->degraded_monitoring_timeout = repmgr_atoi(value, name, error_list, 1);
+			options->degraded_monitoring_timeout = repmgr_atoi(value, name, error_list, -1);
 		else if (strcmp(name, "async_query_timeout") == 0)
 			options->async_query_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "primary_notification_timeout") == 0)
 			options->primary_notification_timeout = repmgr_atoi(value, name, error_list, 0);
-		else if (strcmp(name, "primary_follow_timeout") == 0)
-			options->primary_follow_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);
+
+		/* witness settings */
+		else if (strcmp(name, "witness_sync_interval") == 0)
+			options->witness_sync_interval = repmgr_atoi(value, name, error_list, 1);
 
 		/* BDR settings */
 		else if (strcmp(name, "bdr_local_monitoring_only") == 0)
@@ -604,7 +705,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		 * Raise an error if a known parameter is provided with an empty
 		 * value. Currently there's no reason why empty parameters are needed;
 		 * if we want to accept those, we'd need to add stricter default
-		 * checking, as currently e.g. an empty `node` value will be converted
+		 * checking, as currently e.g. an empty `node_id` value will be converted
 		 * to '0'.
 		 */
 		if (known_parameter == true && !strlen(value))
@@ -677,7 +778,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		item_list_append(error_list,
 						 _("use \"barman_host\" for the hostname of the Barman server"));
 		item_list_append(error_list,
-						 _("use \"barman_server\" for the name of the [server] section in the Barman configururation file"));
+						 _("use \"barman_server\" for the name of the [server] section in the Barman configuration file"));
 
 	}
 
@@ -961,7 +1062,7 @@ reload_config(t_configuration_options *orig_options)
 		return false;
 	}
 
-	if (strcmp(new_options.node_name, orig_options->node_name) != 0)
+	if (strncmp(new_options.node_name, orig_options->node_name, MAXLEN) != 0)
 	{
 		log_warning(_("\"node_name\" cannot be changed, keeping current configuration"));
 		return false;
@@ -1005,7 +1106,7 @@ reload_config(t_configuration_options *orig_options)
 	}
 
 	/* conninfo */
-	if (strcmp(orig_options->conninfo, new_options.conninfo) != 0)
+	if (strncmp(orig_options->conninfo, new_options.conninfo, MAXLEN) != 0)
 	{
 		/* Test conninfo string works */
 		conn = establish_db_connection(new_options.conninfo, false);
@@ -1032,7 +1133,7 @@ reload_config(t_configuration_options *orig_options)
 	}
 
 	/* event_notification_command */
-	if (strcmp(orig_options->event_notification_command, new_options.event_notification_command) != 0)
+	if (strncmp(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN);
 		log_info(_("\"event_notification_command\" is now \"%s\""), new_options.event_notification_command);
@@ -1041,7 +1142,7 @@ reload_config(t_configuration_options *orig_options)
 	}
 
 	/* event_notifications */
-	if (strcmp(orig_options->event_notifications_orig, new_options.event_notifications_orig) != 0)
+	if (strncmp(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN) != 0)
 	{
 		strncpy(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN);
 		log_info(_("\"event_notifications\" is now \"%s\""), new_options.event_notifications_orig);
@@ -1061,7 +1162,7 @@ reload_config(t_configuration_options *orig_options)
 	}
 
 	/* follow_command */
-	if (strcmp(orig_options->follow_command, new_options.follow_command) != 0)
+	if (strncmp(orig_options->follow_command, new_options.follow_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->follow_command, new_options.follow_command, MAXLEN);
 		log_info(_("\"follow_command\" is now \"%s\""), new_options.follow_command);
@@ -1098,7 +1199,7 @@ reload_config(t_configuration_options *orig_options)
 
 
 	/* promote_command */
-	if (strcmp(orig_options->promote_command, new_options.promote_command) != 0)
+	if (strncmp(orig_options->promote_command, new_options.promote_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->promote_command, new_options.promote_command, MAXLEN);
 		log_info(_("\"promote_command\" is now \"%s\""), new_options.promote_command);
@@ -1138,18 +1239,18 @@ reload_config(t_configuration_options *orig_options)
 	 */
 
 	/* log_facility */
-	if (strcmp(orig_options->log_facility, new_options.log_facility) != 0)
+	if (strncmp(orig_options->log_facility, new_options.log_facility, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_facility, new_options.log_facility);
+		strncpy(orig_options->log_facility, new_options.log_facility, MAXLEN);
 		log_info(_("\"log_facility\" is now \"%s\""), new_options.log_facility);
 
 		log_config_changed = true;
 	}
 
 	/* log_file */
-	if (strcmp(orig_options->log_file, new_options.log_file) != 0)
+	if (strncmp(orig_options->log_file, new_options.log_file, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_file, new_options.log_file);
+		strncpy(orig_options->log_file, new_options.log_file, MAXLEN);
 		log_info(_("\"log_file\" is now \"%s\""), new_options.log_file);
 
 		log_config_changed = true;
@@ -1157,9 +1258,9 @@ reload_config(t_configuration_options *orig_options)
 
 
 	/* log_level */
-	if (strcmp(orig_options->log_level, new_options.log_level) != 0)
+	if (strncmp(orig_options->log_level, new_options.log_level, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_level, new_options.log_level);
+		strncpy(orig_options->log_level, new_options.log_level, MAXLEN);
 		log_info(_("\"log_level\" is now \"%s\""), new_options.log_level);
 
 		log_config_changed = true;
@@ -1533,31 +1634,109 @@ clear_event_notification_list(t_configuration_options *options)
 }
 
 
-bool
-parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_options *backup_options, int server_version_num, ItemList *error_list)
+int
+parse_output_to_argv(const char *string, char ***argv_array)
 {
 	int			options_len = 0;
 	char	   *options_string = NULL;
 	char	   *options_string_ptr = NULL;
+	int			c = 1,
+	   			argc_item = 1;
+	char	   *argv_item = NULL;
+	char	  **local_argv_array = NULL;
+	ItemListCell *cell;
 
 	/*
 	 * Add parsed options to this list, then copy to an array to pass to
 	 * getopt
 	 */
-	static ItemList option_argv = {NULL, NULL};
+	ItemList option_argv = {NULL, NULL};
 
-	char	   *argv_item = NULL;
-	int			c,
-				argc_item = 1;
+	options_len = strlen(string) + 1;
+	options_string = pg_malloc0(options_len);
+	options_string_ptr = options_string;
+
+	/* Copy the string before operating on it with strtok() */
+	strncpy(options_string, string, options_len);
+
+	/* Extract arguments into a list and keep a count of the total */
+	while ((argv_item = strtok(options_string_ptr, " ")) != NULL)
+	{
+		item_list_append(&option_argv, trim(argv_item));
+
+		argc_item++;
+
+		if (options_string_ptr != NULL)
+			options_string_ptr = NULL;
+	}
+
+	pfree(options_string);
+
+	/*
+	 * Array of argument values to pass to getopt_long - this will need to
+	 * include an empty string as the first value (normally this would be the
+	 * program name)
+	 */
+	local_argv_array = pg_malloc0(sizeof(char *) * (argc_item + 2));
+
+	/* Insert a blank dummy program name at the start of the array */
+	local_argv_array[0] = pg_malloc0(1);
+
+	/*
+	 * Copy the previously extracted arguments from our list to the array
+	 */
+	for (cell = option_argv.head; cell; cell = cell->next)
+	{
+		int			argv_len = strlen(cell->string) + 1;
+
+		local_argv_array[c] = (char *)pg_malloc0(argv_len);
+
+		strncpy(local_argv_array[c], cell->string, argv_len);
+
+		c++;
+	}
+
+	local_argv_array[c] = NULL;
+
+	item_list_free(&option_argv);
+
+	*argv_array = local_argv_array;
+
+	return argc_item;
+}
+
+
+void
+free_parsed_argv(char ***argv_array)
+{
+	char	  **local_argv_array = *argv_array;
+	int			i = 0;
+
+	while (local_argv_array[i] != NULL)
+	{
+		pfree((char *)local_argv_array[i]);
+		i++;
+	}
+
+	pfree((char **)local_argv_array);
+	*argv_array = NULL;
+}
+
+
+bool
+parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_options *backup_options, int server_version_num, ItemList *error_list)
+{
+	bool		backup_options_ok = true;
+
+	int			c = 0,
+				argc_item = 0;
 
 	char	  **argv_array = NULL;
-	ItemListCell *cell = NULL;
 
 	int			optindex = 0;
 
 	struct option *long_options = NULL;
 
-	bool		backup_options_ok = true;
 
 	/* We're only interested in these options */
 	static struct option long_options_9[] =
@@ -1583,56 +1762,12 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 	if (!strlen(pg_basebackup_options))
 		return backup_options_ok;
 
-	options_len = strlen(pg_basebackup_options) + 1;
-	options_string = pg_malloc(options_len);
-	options_string_ptr = options_string;
-
 	if (server_version_num >= 100000)
 		long_options = long_options_10;
 	else
 		long_options = long_options_9;
 
-	/* Copy the string before operating on it with strtok() */
-	strncpy(options_string, pg_basebackup_options, options_len);
-
-	/* Extract arguments into a list and keep a count of the total */
-	while ((argv_item = strtok(options_string_ptr, " ")) != NULL)
-	{
-		item_list_append(&option_argv, argv_item);
-
-		argc_item++;
-
-		if (options_string_ptr != NULL)
-			options_string_ptr = NULL;
-	}
-
-	/*
-	 * Array of argument values to pass to getopt_long - this will need to
-	 * include an empty string as the first value (normally this would be the
-	 * program name)
-	 */
-	argv_array = pg_malloc0(sizeof(char *) * (argc_item + 2));
-
-	/* Insert a blank dummy program name at the start of the array */
-	argv_array[0] = pg_malloc0(1);
-
-	c = 1;
-
-	/*
-	 * Copy the previously extracted arguments from our list to the array
-	 */
-	for (cell = option_argv.head; cell; cell = cell->next)
-	{
-		int			argv_len = strlen(cell->string) + 1;
-
-		argv_array[c] = pg_malloc0(argv_len);
-
-		strncpy(argv_array[c], cell->string, argv_len);
-
-		c++;
-	}
-
-	argv_array[c] = NULL;
+	argc_item = parse_output_to_argv(pg_basebackup_options, &argv_array);
 
 	/* Reset getopt's optind variable */
 	optind = 0;
@@ -1676,15 +1811,7 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 		backup_options_ok = false;
 	}
 
-	pfree(options_string);
-
-	{
-		int			i;
-
-		for (i = 0; i < argc_item + 2; i++)
-			pfree(argv_array[i]);
-	}
-	pfree(argv_array);
+	free_parsed_argv(&argv_array);
 
 	return backup_options_ok;
 }

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -73,6 +73,7 @@ typedef struct
 	char		conninfo[MAXLEN];
 	char		replication_user[NAMEDATALEN];
 	char		data_directory[MAXPGPATH];
+	char		config_directory[MAXPGPATH];
 	char		pg_bindir[MAXPGPATH];
 	int			replication_type;
 
@@ -82,14 +83,24 @@ typedef struct
 	char		log_file[MAXLEN];
 	int			log_status_interval;
 
-	/* standby action settings */
+	/* standby clone settings */
 	bool		use_replication_slots;
 	char		pg_basebackup_options[MAXLEN];
 	char		restore_command[MAXLEN];
 	TablespaceList tablespace_mapping;
 	char		recovery_min_apply_delay[MAXLEN];
 	bool		recovery_min_apply_delay_provided;
+	char		archive_cleanup_command[MAXLEN];
 	bool		use_primary_conninfo_password;
+	char		passfile[MAXPGPATH];
+
+	/* standby promote settings */
+	int			promote_check_timeout;
+	int			promote_check_interval;
+
+	/* standby follow settings */
+	int			primary_follow_timeout;
+	int			standby_follow_timeout;
 
 	/* node check settings */
 	int			archive_ready_warning;
@@ -97,6 +108,9 @@ typedef struct
 	int			replication_lag_warning;
 	int			replication_lag_critical;
 
+	/* witness settings */
+	int			witness_sync_interval;
+
 	/* repmgrd settings */
 	failover_mode_opt failover;
 	char		location[MAXLEN];
@@ -110,7 +124,7 @@ typedef struct
 	int			degraded_monitoring_timeout;
 	int			async_query_timeout;
 	int			primary_notification_timeout;
-	int			primary_follow_timeout;
+	int			standby_reconnect_timeout;
 
 	/* BDR settings */
 	bool		bdr_local_monitoring_only;
@@ -149,14 +163,21 @@ typedef struct
 
 #define T_CONFIGURATION_OPTIONS_INITIALIZER { \
 		/* node information */ \
-		UNKNOWN_NODE_ID, "", "", "", "", "", REPLICATION_TYPE_PHYSICAL,	\
+		UNKNOWN_NODE_ID, "", "", "", "", "", "", REPLICATION_TYPE_PHYSICAL,	\
 		/* log settings */ \
 		"", "", "", DEFAULT_LOG_STATUS_INTERVAL,	\
-		/* standby action settings */ \
-		false, "", "", { NULL, NULL }, "", false, false, \
+		/* standby clone settings */ \
+		false, "", "", { NULL, NULL }, "", false, "", false, "", \
+		/* standby promote settings */ \
+		DEFAULT_PROMOTE_CHECK_TIMEOUT, DEFAULT_PROMOTE_CHECK_INTERVAL, \
+		/* standby follow settings */ \
+		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
+		DEFAULT_STANDBY_FOLLOW_TIMEOUT,	\
 		/* node check settings */ \
 		DEFAULT_ARCHIVE_READY_WARNING, DEFAULT_ARCHIVE_READY_CRITICAL, \
 		DEFAULT_REPLICATION_LAG_WARNING, DEFAULT_REPLICATION_LAG_CRITICAL, \
+		/* witness settings */ \
+		DEFAULT_WITNESS_SYNC_INTERVAL, \
 		/* repmgrd settings */ \
 		FAILOVER_MANUAL, DEFAULT_LOCATION, DEFAULT_PRIORITY, "", "", \
 		DEFAULT_MONITORING_INTERVAL, \
@@ -165,7 +186,7 @@ typedef struct
         false, -1, \
 		DEFAULT_ASYNC_QUERY_TIMEOUT, \
 		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT,	\
-		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
+		DEFAULT_STANDBY_RECONNECT_TIMEOUT,	\
 		/* BDR settings */ \
 		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
@@ -242,7 +263,6 @@ typedef struct
 }
 
 
-
 void		set_progname(const char *argv0);
 const char *progname(void);
 
@@ -257,12 +277,15 @@ int repmgr_atoi(const char *s,
 			ItemList *error_list,
 			int minval);
 
-
 bool parse_pg_basebackup_options(const char *pg_basebackup_options,
 							t_basebackup_options *backup_options,
 							int server_version_num,
 							ItemList *error_list);
 
+int parse_output_to_argv(const char *string, char ***argv_array);
+void free_parsed_argv(char ***argv_array);
+
+
 /* called by repmgr-client and repmgrd */
 void		exit_with_cli_errors(ItemList *error_list);
 void		print_item_list(ItemList *item_list);

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.0.
+# Generated by GNU Autoconf 2.69 for repmgr 4.0.5.
 #
 # Report bugs to <pgsql-bugs@postgresql.org>.
 #
@@ -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) 2010-2017, 2ndQuadrant Ltd.
+# Copyright (c) 2010-2018, 2ndQuadrant Ltd.
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.0'
-PACKAGE_STRING='repmgr 4.0'
+PACKAGE_VERSION='4.0.5'
+PACKAGE_STRING='repmgr 4.0.5'
 PACKAGE_BUGREPORT='pgsql-bugs@postgresql.org'
 PACKAGE_URL='https://2ndquadrant.com/en/resources/repmgr/'
 
@@ -633,7 +633,6 @@ SHELL'
 ac_subst_files=''
 ac_user_opts='
 enable_option_checking
-with_bdr_only
 '
       ac_precious_vars='build_alias
 host_alias
@@ -1179,7 +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 4.0 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.0.5 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1240,15 +1239,10 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.0:";;
+     short | recursive ) echo "Configuration of repmgr 4.0.5:";;
    esac
   cat <<\_ACEOF
 
-Optional Packages:
-  --with-PACKAGE[=ARG]    use PACKAGE [ARG=yes]
-  --without-PACKAGE       do not use PACKAGE (same as --with-PACKAGE=no)
-  --with-bdr-only         BDR-only build
-
 Some influential environment variables:
   PG_CONFIG   Location to find pg_config for target PostgreSQL (default PATH)
 
@@ -1319,14 +1313,14 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.0
+repmgr configure 4.0.5
 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) 2010-2017, 2ndQuadrant Ltd.
+Copyright (c) 2010-2018, 2ndQuadrant Ltd.
 _ACEOF
   exit
 fi
@@ -1338,7 +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 4.0, which was
+It was created by repmgr $as_me 4.0.5, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1694,20 +1688,6 @@ ac_config_headers="$ac_config_headers config.h"
 
 
 
-
-# Check whether --with-bdr_only was given.
-if test "${with_bdr_only+set}" = set; then :
-  withval=$with_bdr_only;
-fi
-
-if test "x$with_bdr_only" != "x"; then :
-
-$as_echo "#define BDR_ONLY \"1\"" >>confdefs.h
-
-
-fi
-
-
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for a sed that does not truncate output" >&5
 $as_echo_n "checking for a sed that does not truncate output... " >&6; }
 if ${ac_cv_path_SED+:} false; then :
@@ -2379,7 +2359,7 @@ cat >>$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 4.0, which was
+This file was extended by repmgr $as_me 4.0.5, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2442,7 +2422,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-repmgr config.status 4.0
+repmgr config.status 4.0.5
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,17 +1,11 @@
-AC_INIT([repmgr], [4.0], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
+AC_INIT([repmgr], [4.0.6], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2017, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2018, 2ndQuadrant Ltd.])
 
 AC_CONFIG_HEADER(config.h)
 
 AC_ARG_VAR([PG_CONFIG], [Location to find pg_config for target PostgreSQL (default PATH)])
 
-AC_ARG_WITH([bdr_only], [AS_HELP_STRING([--with-bdr-only], [BDR-only build])])
-AS_IF([test "x$with_bdr_only" != "x"],
-    [AC_DEFINE([BDR_ONLY], ["1"], [Only build repmgr for BDR])]
-)
-
-
 AC_PROG_SED
 
 if test -z "$PG_CONFIG"; then

controldata.c

@@ -1,6 +1,6 @@
 /*
  * controldata.c
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -37,13 +37,8 @@ get_system_identifier(const char *data_directory)
 	uint64		system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
 
 	control_file_info = get_controlfile(data_directory);
+	system_identifier = control_file_info->system_identifier;
 
-	if (control_file_info->control_file_processed == true)
-		system_identifier = control_file_info->control_file->system_identifier;
-	else
-		system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
-
-	pfree(control_file_info->control_file);
 	pfree(control_file_info);
 
 	return system_identifier;
@@ -57,13 +52,8 @@ get_db_state(const char *data_directory)
 
 	control_file_info = get_controlfile(data_directory);
 
-	if (control_file_info->control_file_processed == true)
-		state = control_file_info->control_file->state;
-	else
-		/* if we were unable to parse the control file, assume DB is shut down */
-		state = DB_SHUTDOWNED;
+	state = control_file_info->state;
 
-	pfree(control_file_info->control_file);
 	pfree(control_file_info);
 
 	return state;
@@ -78,12 +68,8 @@ get_latest_checkpoint_location(const char *data_directory)
 
 	control_file_info = get_controlfile(data_directory);
 
-	if (control_file_info->control_file_processed == false)
-		return InvalidXLogRecPtr;
+	checkPoint = control_file_info->checkPoint;
 
-	checkPoint = control_file_info->control_file->checkPoint;
-
-	pfree(control_file_info->control_file);
 	pfree(control_file_info);
 
 	return checkPoint;
@@ -98,16 +84,8 @@ get_data_checksum_version(const char *data_directory)
 
 	control_file_info = get_controlfile(data_directory);
 
-	if (control_file_info->control_file_processed == false)
-	{
-		data_checksum_version = -1;
-	}
-	else
-	{
-		data_checksum_version = (int) control_file_info->control_file->data_checksum_version;
-	}
+	data_checksum_version = (int) control_file_info->data_checksum_version;
 
-	pfree(control_file_info->control_file);
 	pfree(control_file_info);
 
 	return data_checksum_version;
@@ -139,33 +117,109 @@ describe_db_state(DBState state)
 
 
 /*
- * we maintain our own version of get_controlfile() as we need cross-version
+ * 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.
  */
 static ControlFileInfo *
 get_controlfile(const char *DataDir)
 {
 	ControlFileInfo *control_file_info;
-	int			fd;
+	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;
 
 	control_file_info = palloc0(sizeof(ControlFileInfo));
+
+	/* set default values */
 	control_file_info->control_file_processed = false;
-	control_file_info->control_file = palloc0(sizeof(ControlFileData));
+	control_file_info->system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
+	control_file_info->state = DB_SHUTDOWNED;
+	control_file_info->checkPoint = InvalidXLogRecPtr;
+	control_file_info->data_checksum_version = -1;
+
+	/*
+	 * 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);
+
+	fp = fopen(PgVersionPath, "r");
+
+	if (fp == NULL)
+	{
+		log_warning(_("could not open file \"%s\" for reading"),
+					PgVersionPath);
+		log_detail("%s", strerror(errno));
+		return control_file_info;
+	}
+
+	file_version_string[0] = '\0';
+
+	ret = fscanf(fp, "%63s", file_version_string);
+	fclose(fp);
+
+	if (ret != 1 || endptr == file_version_string)
+	{
+		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)
 	{
-		log_debug("could not open file \"%s\" for reading: %s",
-				  ControlFilePath, strerror(errno));
+		log_warning(_("could not open file \"%s\" for reading"),
+					ControlFilePath);
+		log_detail("%s", strerror(errno));
 		return control_file_info;
 	}
 
-	if (read(fd, control_file_info->control_file, sizeof(ControlFileData)) != sizeof(ControlFileData))
+
+	if (version_num >= 90500)
 	{
-		log_debug("could not read file \"%s\": %s",
-				  ControlFilePath, strerror(errno));
+		expected_size = sizeof(ControlFileData95);
+		ControlFileDataPtr = palloc0(expected_size);
+	}
+	else if (version_num >= 90400)
+	{
+		expected_size = sizeof(ControlFileData94);
+		ControlFileDataPtr = palloc0(expected_size);
+	}
+	else if (version_num >= 90300)
+	{
+		expected_size = sizeof(ControlFileData93);
+		ControlFileDataPtr = palloc0(expected_size);
+	}
+
+
+	if (read(fd, ControlFileDataPtr, expected_size) != expected_size)
+	{
+		log_warning(_("could not read file \"%s\""),
+					ControlFilePath);
+		log_detail("%s", strerror(errno));
+
 		return control_file_info;
 	}
 
@@ -173,6 +227,33 @@ get_controlfile(const char *DataDir)
 
 	control_file_info->control_file_processed = true;
 
+	if (version_num >= 90500)
+	{
+		ControlFileData95 *ptr = (struct ControlFileData95 *)ControlFileDataPtr;
+		control_file_info->system_identifier = ptr->system_identifier;
+		control_file_info->state = ptr->state;
+		control_file_info->checkPoint = ptr->checkPoint;
+		control_file_info->data_checksum_version = ptr->data_checksum_version;
+	}
+	else if (version_num >= 90400)
+	{
+		ControlFileData94 *ptr = (struct ControlFileData94 *)ControlFileDataPtr;
+		control_file_info->system_identifier = ptr->system_identifier;
+		control_file_info->state = ptr->state;
+		control_file_info->checkPoint = ptr->checkPoint;
+		control_file_info->data_checksum_version = ptr->data_checksum_version;
+	}
+	else if (version_num >= 90300)
+	{
+		ControlFileData93 *ptr = (struct ControlFileData93 *)ControlFileDataPtr;
+		control_file_info->system_identifier = ptr->system_identifier;
+		control_file_info->state = ptr->state;
+		control_file_info->checkPoint = ptr->checkPoint;
+		control_file_info->data_checksum_version = ptr->data_checksum_version;
+	}
+
+	pfree(ControlFileDataPtr);
+
 	/*
 	 * 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

controldata.h

@@ -1,6 +1,6 @@
 /*
  * controldata.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -12,12 +12,261 @@
 #include "postgres_fe.h"
 #include "catalog/pg_control.h"
 
+/*
+ * A simplified representation of pg_control containing only those fields
+ * required by repmgr.
+ */
 typedef struct
 {
 	bool		control_file_processed;
-	ControlFileData *control_file;
+	uint64		system_identifier;
+	DBState		state;
+	XLogRecPtr	checkPoint;
+	uint32		data_checksum_version;
 } ControlFileInfo;
 
+
+
+/* Same for 9.3, 9.4 */
+typedef struct CheckPoint93
+{
+	XLogRecPtr	redo;			/* next RecPtr available when we began to
+								 * create CheckPoint (i.e. REDO start point) */
+	TimeLineID	ThisTimeLineID; /* current TLI */
+	TimeLineID	PrevTimeLineID; /* previous TLI, if this record begins a new
+								 * timeline (equals ThisTimeLineID otherwise) */
+	bool		fullPageWrites; /* current full_page_writes */
+	uint32		nextXidEpoch;	/* higher-order bits of nextXid */
+	TransactionId nextXid;		/* next free XID */
+	Oid			nextOid;		/* next free OID */
+	MultiXactId nextMulti;		/* next free MultiXactId */
+	MultiXactOffset nextMultiOffset;	/* next free MultiXact offset */
+	TransactionId oldestXid;	/* cluster-wide minimum datfrozenxid */
+	Oid			oldestXidDB;	/* database with minimum datfrozenxid */
+	MultiXactId oldestMulti;	/* cluster-wide minimum datminmxid */
+	Oid			oldestMultiDB;	/* database with minimum datminmxid */
+	pg_time_t	time;			/* time stamp of checkpoint */
+
+	TransactionId oldestActiveXid;
+} CheckPoint93;
+
+
+/* Same for 9.5, 9.6, 10, HEAD */
+typedef struct CheckPoint95
+{
+	XLogRecPtr	redo;			/* next RecPtr available when we began to
+								 * create CheckPoint (i.e. REDO start point) */
+	TimeLineID	ThisTimeLineID; /* current TLI */
+	TimeLineID	PrevTimeLineID; /* previous TLI, if this record begins a new
+								 * timeline (equals ThisTimeLineID otherwise) */
+	bool		fullPageWrites; /* current full_page_writes */
+	uint32		nextXidEpoch;	/* higher-order bits of nextXid */
+	TransactionId nextXid;		/* next free XID */
+	Oid			nextOid;		/* next free OID */
+	MultiXactId nextMulti;		/* next free MultiXactId */
+	MultiXactOffset nextMultiOffset;	/* next free MultiXact offset */
+	TransactionId oldestXid;	/* cluster-wide minimum datfrozenxid */
+	Oid			oldestXidDB;	/* database with minimum datfrozenxid */
+	MultiXactId oldestMulti;	/* cluster-wide minimum datminmxid */
+	Oid			oldestMultiDB;	/* database with minimum datminmxid */
+	pg_time_t	time;			/* time stamp of checkpoint */
+	TransactionId oldestCommitTsXid;	/* oldest Xid with valid commit
+										 * timestamp */
+	TransactionId newestCommitTsXid;	/* newest Xid with valid commit
+										 * timestamp */
+
+	TransactionId oldestActiveXid;
+} CheckPoint95;
+
+
+typedef struct ControlFileData93
+{
+	uint64		system_identifier;
+
+	uint32		pg_control_version;		/* PG_CONTROL_VERSION */
+	uint32		catalog_version_no;		/* see catversion.h */
+
+	DBState		state;			/* see enum above */
+	pg_time_t	time;			/* time stamp of last pg_control update */
+	XLogRecPtr	checkPoint;		/* last check point record ptr */
+	XLogRecPtr	prevCheckPoint; /* previous check point record ptr */
+
+	CheckPoint93	checkPointCopy; /* copy of last check point record */
+
+	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
+
+	XLogRecPtr	minRecoveryPoint;
+	TimeLineID	minRecoveryPointTLI;
+	XLogRecPtr	backupStartPoint;
+	XLogRecPtr	backupEndPoint;
+	bool		backupEndRequired;
+
+	int			wal_level;
+	int			MaxConnections;
+	int			max_prepared_xacts;
+	int			max_locks_per_xact;
+
+	uint32		maxAlign;		/* alignment requirement for tuples */
+	double		floatFormat;	/* constant 1234567.0 */
+
+	uint32		blcksz;			/* data block size for this DB */
+	uint32		relseg_size;	/* blocks per segment of large relation */
+
+	uint32		xlog_blcksz;	/* block size within WAL files */
+	uint32		xlog_seg_size;	/* size of each WAL segment */
+
+	uint32		nameDataLen;	/* catalog name field width */
+	uint32		indexMaxKeys;	/* max number of columns in an index */
+
+	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
+
+	/* flag indicating internal format of timestamp, interval, time */
+	bool		enableIntTimes; /* int64 storage enabled? */
+
+	/* flags indicating pass-by-value status of various types */
+	bool		float4ByVal;	/* float4 pass-by-value? */
+	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
+
+	/* Are data pages protected by checksums? Zero if no checksum version */
+	uint32		data_checksum_version;
+
+} ControlFileData93;
+
+
+/*
+ * 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;
+
+	uint32		pg_control_version;		/* PG_CONTROL_VERSION */
+	uint32		catalog_version_no;		/* see catversion.h */
+
+	DBState		state;			/* see enum above */
+	pg_time_t	time;			/* time stamp of last pg_control update */
+	XLogRecPtr	checkPoint;		/* last check point record ptr */
+	XLogRecPtr	prevCheckPoint; /* previous check point record ptr */
+
+	CheckPoint93	checkPointCopy; /* copy of last check point record */
+
+	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
+
+	XLogRecPtr	minRecoveryPoint;
+	TimeLineID	minRecoveryPointTLI;
+	XLogRecPtr	backupStartPoint;
+	XLogRecPtr	backupEndPoint;
+	bool		backupEndRequired;
+
+	int			wal_level;
+	bool		wal_log_hints;
+	int			MaxConnections;
+	int			max_worker_processes;
+	int			max_prepared_xacts;
+	int			max_locks_per_xact;
+
+	uint32		maxAlign;		/* alignment requirement for tuples */
+	double		floatFormat;	/* constant 1234567.0 */
+
+	uint32		blcksz;			/* data block size for this DB */
+	uint32		relseg_size;	/* blocks per segment of large relation */
+
+	uint32		xlog_blcksz;	/* block size within WAL files */
+	uint32		xlog_seg_size;	/* size of each WAL segment */
+
+	uint32		nameDataLen;	/* catalog name field width */
+	uint32		indexMaxKeys;	/* max number of columns in an index */
+
+	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
+	uint32		loblksize;		/* chunk size in pg_largeobject */
+
+	bool		enableIntTimes; /* int64 storage enabled? */
+
+	bool		float4ByVal;	/* float4 pass-by-value? */
+	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
+
+	/* Are data pages protected by checksums? Zero if no checksum version */
+	uint32		data_checksum_version;
+
+} ControlFileData94;
+
+
+
+/*
+ * Following field added since 9.4:
+ *
+ *	bool		track_commit_timestamp;
+ *
+ * Unchanged in 9.6
+ *
+ * In 10, following field appended *after* "data_checksum_version":
+ *
+ *	char		mock_authentication_nonce[MOCK_AUTH_NONCE_LEN];
+ *
+ * (but we don't care about that)
+ */
+
+typedef struct ControlFileData95
+{
+	uint64		system_identifier;
+
+	uint32		pg_control_version;		/* PG_CONTROL_VERSION */
+	uint32		catalog_version_no;		/* see catversion.h */
+
+	DBState		state;			/* see enum above */
+	pg_time_t	time;			/* time stamp of last pg_control update */
+	XLogRecPtr	checkPoint;		/* last check point record ptr */
+	XLogRecPtr	prevCheckPoint; /* previous check point record ptr */
+
+	CheckPoint95	checkPointCopy; /* copy of last check point record */
+
+	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
+
+	XLogRecPtr	minRecoveryPoint;
+	TimeLineID	minRecoveryPointTLI;
+	XLogRecPtr	backupStartPoint;
+	XLogRecPtr	backupEndPoint;
+	bool		backupEndRequired;
+
+	int			wal_level;
+	bool		wal_log_hints;
+	int			MaxConnections;
+	int			max_worker_processes;
+	int			max_prepared_xacts;
+	int			max_locks_per_xact;
+	bool		track_commit_timestamp;
+
+	uint32		maxAlign;		/* alignment requirement for tuples */
+	double		floatFormat;	/* constant 1234567.0 */
+
+	uint32		blcksz;			/* data block size for this DB */
+	uint32		relseg_size;	/* blocks per segment of large relation */
+
+	uint32		xlog_blcksz;	/* block size within WAL files */
+	uint32		xlog_seg_size;	/* size of each WAL segment */
+
+	uint32		nameDataLen;	/* catalog name field width */
+	uint32		indexMaxKeys;	/* max number of columns in an index */
+
+	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
+	uint32		loblksize;		/* chunk size in pg_largeobject */
+
+	bool		enableIntTimes; /* int64 storage enabled? */
+
+	bool		float4ByVal;	/* float4 pass-by-value? */
+	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
+
+	uint32		data_checksum_version;
+
+} ControlFileData95;
+
+
+
 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);

dbutils.h

@@ -1,7 +1,7 @@
 /*
  * dbutils.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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 @@
 #include "strutil.h"
 #include "voting.h"
 
-#define REPMGR_NODES_COLUMNS "node_id, type, upstream_node_id, node_name, conninfo, repluser, slot_name, location, priority, active, config_file, '' AS upstream_node_name "
+#define REPMGR_NODES_COLUMNS "n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, n.slot_name, n.location, n.priority, n.active, n.config_file, '' AS upstream_node_name "
 #define BDR_NODES_COLUMNS "node_sysid, node_timeline, node_dboid, node_status, node_name, node_local_dsn, node_init_from_dsn, node_read_only, node_seq_id"
 
 #define ERRBUFF_SIZE 512
@@ -38,6 +38,7 @@ typedef enum
 	UNKNOWN = 0,
 	PRIMARY,
 	STANDBY,
+	WITNESS,
 	BDR
 } t_server_type;
 
@@ -73,17 +74,18 @@ typedef enum
 {
 	NODE_STATUS_UNKNOWN = -1,
 	NODE_STATUS_UP,
+	NODE_STATUS_SHUTTING_DOWN,
 	NODE_STATUS_DOWN,
 	NODE_STATUS_UNCLEAN_SHUTDOWN
 } NodeStatus;
 
 typedef enum
 {
-	VR_VOTE_REFUSED = -1,
-	VR_POSITIVE_VOTE,
-	VR_NEGATIVE_VOTE
-} VoteRequestResult;
-
+	CONN_UNKNOWN = -1,
+	CONN_OK,
+	CONN_BAD,
+	CONN_ERROR
+} ConnectionStatus;
 
 typedef enum
 {
@@ -181,11 +183,13 @@ typedef struct s_event_info
 {
 	char	   *node_name;
 	char	   *conninfo_str;
+	int			node_id;
 } t_event_info;
 
 #define T_EVENT_INFO_INITIALIZER { \
 	NULL, \
- 	NULL \
+	NULL, \
+	UNKNOWN_NODE_ID \
 }
 
 
@@ -339,9 +343,6 @@ bool		atobool(const char *value);
 PGconn *establish_db_connection(const char *conninfo,
 						const bool exit_on_error);
 PGconn	   *establish_db_connection_quiet(const char *conninfo);
-PGconn *establish_db_connection_as_user(const char *conninfo,
-								const char *user,
-								const bool exit_on_error);
 
 PGconn *establish_db_connection_by_params(t_conninfo_param_list *param_list,
 								  const bool exit_on_error);
@@ -352,10 +353,11 @@ PGconn	   *get_primary_connection(PGconn *standby_conn, int *primary_id, char *p
 PGconn	   *get_primary_connection_quiet(PGconn *standby_conn, int *primary_id, char *primary_conninfo_out);
 
 bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
+void		close_connection(PGconn **conn);
 
 /* conninfo manipulation functions */
 bool		get_conninfo_value(const char *conninfo, const char *keyword, char *output);
-
+bool		get_conninfo_default_value(const char *param, char *output, int maxlen);
 void		initialize_conninfo_params(t_conninfo_param_list *param_list, bool set_defaults);
 void		free_conninfo_params(t_conninfo_param_list *param_list);
 void		copy_conninfo_params(t_conninfo_param_list *dest_list, t_conninfo_param_list *source_list);
@@ -363,8 +365,10 @@ void		conn_to_param_list(PGconn *conn, t_conninfo_param_list *param_list);
 void		param_set(t_conninfo_param_list *param_list, const char *param, const char *value);
 void		param_set_ine(t_conninfo_param_list *param_list, const char *param, const char *value);
 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);
+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);
+bool		has_passfile(void);
+
 
 /* transaction functions */
 bool		begin_transaction(PGconn *conn);
@@ -375,10 +379,8 @@ bool		check_cluster_schema(PGconn *conn);
 /* GUC manipulation functions */
 bool		set_config(PGconn *conn, const char *config_param, const char *config_value);
 bool		set_config_bool(PGconn *conn, const char *config_param, bool state);
-int guc_set(PGconn *conn, const char *parameter, const char *op,
-		const char *value);
-int guc_set_typed(PGconn *conn, const char *parameter, const char *op,
-			  const char *value, const char *datatype);
+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);
 
 /* server information functions */
@@ -386,10 +388,10 @@ bool		get_cluster_size(PGconn *conn, char *size);
 int			get_server_version(PGconn *conn, char *server_version);
 RecoveryType get_recovery_type(PGconn *conn);
 int			get_primary_node_id(PGconn *conn);
-bool		can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *reason);
 int			get_ready_archive_files(PGconn *conn, const char *data_directory);
 bool		identify_system(PGconn *repl_conn, t_system_identification *identification);
 bool		repmgrd_set_local_node_id(PGconn *conn, int local_node_id);
+int			repmgrd_get_local_node_id(PGconn *conn);
 
 /* extension functions */
 ExtensionStatus get_repmgr_extension_status(PGconn *conn);
@@ -404,6 +406,8 @@ 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 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);
 t_node_info *get_node_record_pointer(PGconn *conn, int node_id);
 
@@ -414,17 +418,23 @@ void		get_all_node_records(PGconn *conn, NodeInfoList *node_list);
 void		get_downstream_node_records(PGconn *conn, int node_id, NodeInfoList *nodes);
 void		get_active_sibling_node_records(PGconn *conn, int node_id, int upstream_node_id, NodeInfoList *node_list);
 void		get_node_records_by_priority(PGconn *conn, NodeInfoList *node_list);
-void		get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list);
+bool		get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list);
+bool		get_downstream_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *noede_list);
 
 bool		create_node_record(PGconn *conn, char *repmgr_action, t_node_info *node_info);
 bool		update_node_record(PGconn *conn, char *repmgr_action, t_node_info *node_info);
 bool		delete_node_record(PGconn *conn, int node);
+bool		truncate_node_records(PGconn *conn);
 
 bool		update_node_record_set_active(PGconn *conn, int this_node_id, bool active);
 bool		update_node_record_set_primary(PGconn *conn, int this_node_id);
+bool		update_node_record_set_active_standby(PGconn *conn, int this_node_id);
 bool		update_node_record_set_upstream(PGconn *conn, int this_node_id, int new_upstream_node_id);
 bool		update_node_record_status(PGconn *conn, int this_node_id, char *type, int upstream_node_id, bool active);
 bool		update_node_record_conn_priority(PGconn *conn, t_configuration_options *options);
+bool		update_node_record_slot_name(PGconn *primary_conn, int node_id, char *slot_name);
+
+bool		witness_copy_node_records(PGconn *primary_conn, PGconn *witness_conn);
 
 void		clear_node_info_list(NodeInfoList *nodes);
 
@@ -438,11 +448,15 @@ void		config_file_list_add(t_configfile_list *list, const char *file, const char
 bool		create_event_record(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details);
 bool		create_event_notification(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details);
 bool		create_event_notification_extended(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details, t_event_info *event_info);
+PGresult   *get_event_records(PGconn *conn, int node_id, const char *node_name, const char *event, bool all, int limit);
 
 /* replication slot functions */
+void		create_slot_name(char *slot_name, int node_id);
 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);
+int			get_inactive_replication_slots(PGconn *conn, KeyValueList *list);
 
 /* tablespace functions */
 bool		get_tablespace_name_by_location(PGconn *conn, const char *location, char *name);
@@ -453,6 +467,8 @@ 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);
+void		connection_ping(PGconn *conn);
 
 /* monitoring functions  */
 void
@@ -474,9 +490,9 @@ bool		delete_monitoring_records(PGconn *primary_conn, int keep_history);
 
 
 /* node voting functions */
-NodeVotingStatus get_voting_status(PGconn *conn);
-VoteRequestResult request_vote(PGconn *conn, t_node_info *this_node, t_node_info *other_node, int electoral_term);
-int			set_voting_status_initiated(PGconn *conn);
+void		initialize_voting_term(PGconn *conn);
+int			get_current_term(PGconn *conn);
+void		increment_current_term(PGconn *conn);
 bool		announce_candidature(PGconn *conn, t_node_info *this_node, t_node_info *other_node, int electoral_term);
 void		notify_follow_primary(PGconn *conn, int primary_node_id);
 bool		get_new_primary(PGconn *conn, int *primary_node_id);
@@ -487,24 +503,30 @@ XLogRecPtr	get_current_wal_lsn(PGconn *conn);
 XLogRecPtr	get_last_wal_receive_location(PGconn *conn);
 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);
 
 /* BDR functions */
 void		get_all_bdr_node_records(PGconn *conn, BdrNodeInfoList *node_list);
 RecordStatus get_bdr_node_record_by_name(PGconn *conn, const char *node_name, t_bdr_node_info *node_info);
 bool		is_bdr_db(PGconn *conn, PQExpBufferData *output);
+bool		is_bdr_db_quiet(PGconn *conn);
 bool		is_active_bdr_node(PGconn *conn, const char *node_name);
 bool		is_bdr_repmgr(PGconn *conn);
 bool		is_table_in_bdr_replication_set(PGconn *conn, const char *tablename, const char *set);
 bool		add_table_to_bdr_replication_set(PGconn *conn, const char *tablename, const char *set);
 void		add_extension_tables_to_bdr_replication_set(PGconn *conn);
-
-bool		bdr_node_exists(PGconn *conn, const char *node_name);
+bool		bdr_node_name_matches(PGconn *conn, const char *node_name, PQExpBufferData *bdr_local_node_name);
 ReplSlotStatus get_bdr_node_replication_slot_status(PGconn *conn, const char *node_name);
 void		get_bdr_other_node_name(PGconn *conn, int node_id, char *name_buf);
 
 bool		am_bdr_failover_handler(PGconn *conn, int node_id);
 void		unset_bdr_failover_handler(PGconn *conn);
+bool		bdr_node_has_repmgr_set(PGconn *conn, const char *node_name);
+bool		bdr_node_set_repmgr_set(PGconn *conn, const char *node_name);
+
+/* miscellaneous debugging functions */
+const char *print_node_status(NodeStatus node_status);
+const char *print_pqping_status(PGPing ping_status);
 
 #endif							/* _REPMGR_DBUTILS_H_ */

dirutil.c

@@ -3,7 +3,7 @@
  * dirmod.c
  *	  directory handling functions
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -21,6 +21,7 @@
 
 #include <unistd.h>
 #include <dirent.h>
+#include <signal.h>
 #include <sys/stat.h>
 #include <errno.h>
 #include <stdio.h>
@@ -34,34 +35,33 @@
 #include "dirutil.h"
 #include "strutil.h"
 #include "log.h"
+#include "controldata.h"
 
 static int	unlink_dir_callback(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf);
 
+/* PID can be negative if backend is standalone */
+typedef long pgpid_t;
 
 
 /*
- * make sure the directory either doesn't exist or is empty
- * we use this function to check the new data directory and
- * the directories for tablespaces
+ * Check if a directory exists, and if so whether it is empty.
  *
- * This is the same check initdb does on the new PGDATA dir
- *
- * Returns 0 if nonexistent, 1 if exists and empty, 2 if not empty,
- * or -1 if trouble accessing directory
+ * This function is used for checking both the data directory
+ * and tablespace directories.
  */
-int
+DataDirState
 check_dir(char *path)
 {
-	DIR		   *chkdir;
-	struct dirent *file;
-	int			result = 1;
+	DIR		   *chkdir = NULL;
+	struct dirent *file = NULL;
+	int			result = DIR_EMPTY;
 
 	errno = 0;
 
 	chkdir = opendir(path);
 
 	if (!chkdir)
-		return (errno == ENOENT) ? 0 : -1;
+		return (errno == ENOENT) ? DIR_NOENT : DIR_ERROR;
 
 	while ((file = readdir(chkdir)) != NULL)
 	{
@@ -73,25 +73,15 @@ check_dir(char *path)
 		}
 		else
 		{
-			result = 2;			/* not empty */
+			result = DIR_NOT_EMPTY;
 			break;
 		}
 	}
 
-#ifdef WIN32
-
-	/*
-	 * This fix is in mingw cvs (runtime/mingwex/dirent.c rev 1.4), but not in
-	 * released version
-	 */
-	if (GetLastError() == ERROR_NO_MORE_FILES)
-		errno = 0;
-#endif
-
 	closedir(chkdir);
 
 	if (errno != 0)
-		return -1;				/* some kind of I/O error? */
+		return DIR_ERROR;				/* some kind of I/O error? */
 
 	return result;
 }
@@ -106,12 +96,13 @@ create_dir(char *path)
 	if (mkdir_p(path, 0700) == 0)
 		return true;
 
-	log_error(_("unable to create directory \"%s\": %s"),
-			  path, strerror(errno));
+	log_error(_("unable to create directory \"%s\""), path);
+	log_detail("%s", strerror(errno));
 
 	return false;
 }
 
+
 bool
 set_dir_permissions(char *path)
 {
@@ -146,26 +137,6 @@ mkdir_p(char *path, mode_t omode)
 	oumask = 0;
 	retval = 0;
 
-#ifdef WIN32
-	/* skip network and drive specifiers for win32 */
-	if (strlen(p) >= 2)
-	{
-		if (p[0] == '/' && p[1] == '/')
-		{
-			/* network drive */
-			p = strstr(p + 2, "/");
-			if (p == NULL)
-				return 1;
-		}
-		else if (p[1] == ':' &&
-				 ((p[0] >= 'a' && p[0] <= 'z') ||
-				  (p[0] >= 'A' && p[0] <= 'Z')))
-		{
-			/* local drive */
-			p += 2;
-		}
-	}
-#endif
 
 	if (p[0] == '/')			/* Skip leading '/'. */
 		++p;
@@ -242,17 +213,91 @@ is_pg_dir(char *path)
 	return false;
 }
 
+/*
+ * Attempt to determine if a PostgreSQL data directory is in use
+ * by reading the pidfile. This is the same mechanism used by
+ * "pg_ctl".
+ *
+ * This function will abort with appropriate log messages if a file error
+ * is encountered, as the user will need to address the situation before
+ * any further useful progress can be made.
+ */
+PgDirState
+is_pg_running(char *path)
+{
+	long		pid;
+	FILE	   *pidf;
+
+	char pid_file[MAXPGPATH];
+
+	/* it's reasonable to assume the pidfile name will not change */
+	snprintf(pid_file, MAXPGPATH, "%s/postmaster.pid", path);
+
+	pidf = fopen(pid_file, "r");
+	if (pidf == NULL)
+	{
+		/*
+		 * No PID file - PostgreSQL shouldn't be running. From 9.3 (the
+		 * earliesty version we care about) removal of the PID file will
+		 * cause the postmaster to shut down, so it's highly unlikely
+		 * that PostgreSQL will still be running.
+		 */
+		if (errno == ENOENT)
+		{
+			return PG_DIR_NOT_RUNNING;
+		}
+		else
+		{
+			log_error(_("unable to open PostgreSQL PID file \"%s\""), pid_file);
+			log_detail("%s", strerror(errno));
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+
+	/*
+	 * In the unlikely event we're unable to extract a PID from the PID file,
+	 * log a warning but assume we're not dealing with a running instance
+	 * as PostgreSQL should have shut itself down in these cases anyway.
+	 */
+	if (fscanf(pidf, "%ld", &pid) != 1)
+	{
+		/* Is the file empty? */
+		if (ftell(pidf) == 0 && feof(pidf))
+		{
+			log_warning(_("PostgreSQL PID file \"%s\" is empty"), path);
+		}
+		else
+		{
+			log_warning(_("invalid data in PostgreSQL PID file \"%s\""), path);
+		}
+
+		return PG_DIR_NOT_RUNNING;
+	}
+
+	fclose(pidf);
+
+	if (pid == getpid())
+		return PG_DIR_NOT_RUNNING;
+
+	if (pid == getppid())
+		return PG_DIR_NOT_RUNNING;
+
+	if (kill(pid, 0) == 0)
+		return PG_DIR_RUNNING;
+
+	return PG_DIR_NOT_RUNNING;
+}
+
 
 bool
 create_pg_dir(char *path, bool force)
 {
-	bool		pg_dir = false;
-
-	/* Check this directory could be used as a PGDATA dir */
+	/* Check this directory can be used as a PGDATA dir */
 	switch (check_dir(path))
 	{
-		case 0:
-			/* dir not there, must create it */
+		case DIR_NOENT:
+			/* directory does not exist, attempt to create it */
 			log_info(_("creating directory \"%s\"..."), path);
 
 			if (!create_dir(path))
@@ -262,55 +307,62 @@ create_pg_dir(char *path, bool force)
 				return false;
 			}
 			break;
-		case 1:
-			/* Present but empty, fix permissions and use it */
-			log_info(_("checking and correcting permissions on existing directory %s"),
+		case DIR_EMPTY:
+			/* exists but empty, fix permissions and use it */
+			log_info(_("checking and correcting permissions on existing directory \"%s\""),
 					 path);
 
 			if (!set_dir_permissions(path))
 			{
-				log_error(_("unable to change permissions of directory \"%s\":\n  %s"),
-						  path, strerror(errno));
+				log_error(_("unable to change permissions of directory \"%s\""), path);
+				log_detail("%s", strerror(errno));
 				return false;
 			}
 			break;
-		case 2:
-			/* Present and not empty */
+		case DIR_NOT_EMPTY:
+			/* exists but is not empty */
 			log_warning(_("directory \"%s\" exists but is not empty"),
 						path);
 
-			pg_dir = is_pg_dir(path);
-
-			if (pg_dir && force)
+			if (is_pg_dir(path))
 			{
-				/* TODO: check DB state, if not running overwrite */
-
-				if (false)
+				if (force == true)
 				{
-					log_notice(_("deleting existing data directory \"%s\""), path);
+					log_notice(_("-F/--force provided - deleting existing data directory \"%s\""), path);
 					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+					return true;
 				}
-				/* Let it continue */
-				break;
-			}
-			else if (pg_dir && !force)
-			{
-				log_hint(_("This looks like a PostgreSQL directory.\n"
-						   "If you are sure you want to clone here, "
-						   "please check there is no PostgreSQL server "
-						   "running and use the -F/--force option"));
+
 				return false;
 			}
-
-			return false;
-		default:
+			else
+			{
+				if (force == true)
+				{
+					log_notice(_("deleting existing directory \"%s\""), path);
+					nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+					return true;
+				}
+				return false;
+			}
+			break;
+		case DIR_ERROR:
 			log_error(_("could not access directory \"%s\": %s"),
 					  path, strerror(errno));
 			return false;
 	}
+
 	return true;
 }
 
+
+
+int
+rmdir_recursive(char *path)
+{
+	return nftw(path, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+}
+
 static int
 unlink_dir_callback(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf)
 {

dirutil.h

@@ -1,6 +1,6 @@
 /*
  * dirutil.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -19,12 +19,29 @@
 #ifndef _DIRUTIL_H_
 #define _DIRUTIL_H_
 
+typedef enum
+{
+	DIR_ERROR = -1,
+	DIR_NOENT,
+	DIR_EMPTY,
+	DIR_NOT_EMPTY
+} DataDirState;
+
+typedef enum
+{
+	PG_DIR_ERROR = -1,
+	PG_DIR_NOT_RUNNING,
+	PG_DIR_RUNNING
+} PgDirState;
+
 extern int	mkdir_p(char *path, mode_t omode);
 extern bool set_dir_permissions(char *path);
 
-extern int	check_dir(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/.gitignore

@@ -2,4 +2,6 @@ HTML.index
 bookindex.sgml
 html-stamp
 html/
+nochunks.dsl
+repmgr.html
 version.sgml

doc/Makefile.in

@@ -10,7 +10,7 @@ SGMLINCLUDE = -D . -D ${srcdir}
 
 SPFLAGS += -wall -wno-unused-param -wno-empty -wfully-tagged
 
-JADE.html.call = $(JADE) $(JADEFLAGS) $(SPFLAGS) $(SGMLINCLUDE) $(CATALOG) -d stylesheet.dsl -t sgml -i output-html
+JADE.html.call = $(JADE) $(JADEFLAGS) $(SPFLAGS) $(SGMLINCLUDE) $(CATALOG) -t sgml -i output-html
 
 ALLSGML := $(wildcard $(srcdir)/*.sgml)
 # to build bookindex
@@ -26,10 +26,15 @@ html: html-stamp
 
 html-stamp: repmgr.sgml $(ALLSGML) $(GENERATED_SGML) stylesheet.dsl website-docs.css
 	$(MKDIR_P) html
-	$(JADE.html.call) -i include-index $<
+	$(JADE.html.call) -d stylesheet.dsl -i include-index $<
 	cp $(srcdir)/stylesheet.css $(srcdir)/website-docs.css html/
 	touch $@
 
+repmgr.html: repmgr.sgml $(ALLSGML) $(GENERATED_SGML) stylesheet.dsl website-docs.css
+	sed '/html-index-filename/a\
+(define nochunks  #t)' <stylesheet.dsl >nochunks.dsl
+	$(JADE.html.call) -d nochunks.dsl -i include-index $< >repmgr.html
+
 version.sgml: ${repmgr_top_builddir}/repmgr_version.h
 	{ \
 	  echo "<!ENTITY repmgrversion \"$(REPMGR_VERSION)\">"; \
@@ -37,7 +42,7 @@ version.sgml: ${repmgr_top_builddir}/repmgr_version.h
 
 HTML.index: repmgr.sgml $(ALMOSTALLSGML) stylesheet.dsl
 	@$(MKDIR_P) html
-	$(JADE.html.call) -V html-index $<
+	$(JADE.html.call) -d stylesheet.dsl -V html-index $<
 
 website-docs.css:
 	@$(MKDIR_P) html

doc/appendix-faq.sgml

@@ -0,0 +1,307 @@
+<appendix id="appendix-faq" xreflabel="FAQ">
+ <indexterm>
+  <primary>FAQ (Frequently Asked Questions)</primary>
+ </indexterm>
+
+ <title>FAQ (Frequently Asked Questions)</title>
+
+ <sect1 id="faq-general" xreflabel="General">
+  <title>General</title>
+
+  <sect2 id="faq-xrepmgr-version-diff" xreflabel="Version differences">
+    <title>What's the difference between the repmgr versions?</title>
+    <para>
+      &repmgr; 4 is a complete rewrite of the existing &repmgr; code base
+      and implements &repmgr; as a PostgreSQL extension. It
+      supports all PostgreSQL versions from 9.3 (although some &repmgr;
+      features are not available for PostgreSQL 9.3 and 9.4).
+     </para>
+     <para>
+      &repmgr; 3.x builds on the improved replication facilities added
+      in PostgreSQL 9.3, as well as improved automated failover support
+      via <application>repmgrd</application>, and is not compatible with PostgreSQL 9.2
+      and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
+      series will no longer be actively maintained.
+     </para>
+     <para>
+      &repmgr; 2.x supports PostgreSQL 9.0 ~ 9.3. While it is compatible
+      with PostgreSQL 9.3, we recommend using repmgr 4.x. &repmgr; 2.x is
+      no longer maintained.
+     </para>
+  </sect2>
+
+  <sect2 id="faq-replication-slots-advantage" xreflabel="Advantages of replication slots">
+   <title>What's the advantage of using replication slots?</title>
+   <para>
+    Replication slots, introduced in PostgreSQL 9.4, ensure that the
+    primary server will retain WAL files until they have been consumed
+    by all standby servers. This makes WAL file management much easier,
+    and if used &repmgr; will no longer insist on a fixed minimum number
+    (default: 5000) of WAL files being retained.
+   </para>
+   <para>
+    However this does mean that if a standby is no longer connected to the
+    primary, the presence of the replication slot will cause WAL files
+    to be retained indefinitely.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-replication-slots-number" xreflabel="Number of replication slots">
+   <title>How many replication slots should I define in <varname>max_replication_slots</varname>?</title>
+   <para>
+    Normally at least same number as the number of standbys which will connect
+    to the node. Note that changes to <varname>max_replication_slots</varname> require a server
+    restart to take effect, and as there is no particular penalty for unused
+    replication slots, setting a higher figure will make adding new nodes
+    easier.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-hash-index" xreflabel="Hash indexes">
+   <title>Does &repmgr; support hash indexes?</title>
+   <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/static/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
+    for details.
+   </para>
+   <para>
+    From PostgreSQL 10, this restriction has been lifted and hash indexes can be used
+    in a streaming replication cluster.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-upgrades" xreflabel="Upgrading PostgreSQL with repmgr">
+   <title>Can &repmgr; assist with upgrading a PostgreSQL cluster?</title>
+   <para>
+     For <emphasis>minor</emphasis> version upgrades, e.g. from 9.6.7 to 9.6.8, a common
+     approach is to upgrade a standby to the latest version, perform a
+     <link linkend="performing-switchover">switchover</link> promoting it to a primary,
+     then upgrade the former primary.
+   </para>
+   <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/static/pgupgrade.html">pg_upgrade</ulink>
+     and recloning standbys from this.
+   </para>
+   <para>
+     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
+     new cluster is ready to be put into production.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-libdir-repmgr-error">
+   <title>What does this error mean: <literal>ERROR: could not access file "$libdir/repmgr"</literal>?</title>
+   <para>
+     It means the &repmgr; extension code is not installed in the
+     PostgreSQL application directory. This typically happens when using PostgreSQL
+     packages provided by a third-party vendor, which often have different
+     filesystem layouts.
+   </para>
+   <para>
+     Either use PostgreSQL packages provided by the community or 2ndQuadrant; if this
+     is not possible, contact your vendor for assistance.
+   </para>
+  </sect2>
+ </sect1>
+
+ <sect1 id="faq-repmgr" xreflabel="repmgr">
+  <title><command>repmgr</command></title>
+
+  <sect2 id="faq-register-existing-node" xreflabel="registering an existing node">
+   <title>Can I register an existing PostgreSQL server with repmgr?</title>
+   <para>
+    Yes, any existing PostgreSQL server which is part of the same replication
+    cluster can be registered with &repmgr;. There's no requirement for a
+    standby to have been cloned using &repmgr;.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-clone-other-source" >
+   <title>Can I use a standby not cloned by &repmgr; as a &repmgr; node?</title>
+
+   <para>
+     For a standby which has been manually cloned or recovered from an external
+     backup manager such as Barman, the command
+     <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>
+     can be used to create the correct <filename>recovery.conf</filename> file for
+     use with &repmgr; (and will create a replication slot if required). Once this has been done,
+     <link linkend="repmgr-standby-register">register the node</link> as usual.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-recovery-conf" >
+    <title>What does &repmgr; write in <filename>recovery.conf</filename>, and what options can be set there?</title>
+   <para>
+     See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-failed-primary-standby" xreflabel="Reintegrate a failed primary as a standby">
+   <title>How can a failed primary be re-added as a standby?</title>
+   <para>
+    This is a two-stage process. First, the failed primary's data directory
+    must be re-synced with the current primary; secondly the failed primary
+    needs to be re-registered as a standby.
+   </para>
+   <para>
+    It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
+    directory, which will usually be much
+    faster than re-cloning the server. However <command>pg_rewind</command> can only
+    be used if PostgreSQL either has <varname>wal_log_hints</varname> enabled, or
+    data checksums were enabled when the cluster was initialized.
+   </para>
+   <para>
+     Note that <command>pg_rewind</command> is available as part of the core PostgreSQL
+     distribution from PostgreSQL 9.5, and as a third-party utility for PostgreSQL 9.3 and 9.4.
+   </para>
+   <para>
+    &repmgr; provides the command <command>repmgr node rejoin</command> which can
+    optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin">
+    documentation for details, in particular the section <xref linkend="repmgr-node-rejoin-pg-rewind">.
+   </para>
+   <para>
+    If <command>pg_rewind</command> cannot be used, then the data directory will need
+    to be re-cloned from scratch.
+   </para>
+
+  </sect2>
+
+  <sect2 id="faq-repmgr-check-configuration" xreflabel="Check PostgreSQL configuration">
+   <title>Is there an easy way to check my primary server is correctly configured for use with &repmgr;?</title>
+   <para>
+    Execute <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>
+    with the <literal>--dry-run</literal> option; this will report any configuration problems
+    which need to be rectified.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-clone-skip-config-files" xreflabel="">
+   <title>When cloning a standby, how can I get &repmgr; to copy
+     <filename>postgresql.conf</filename> and <filename>pg_hba.conf</filename> from the PostgreSQL configuration
+     directory in <filename>/etc</filename>?</title>
+   <para>
+    Use the command line option <literal>--copy-external-config-files</literal>. For more details
+    see <xref linkend="repmgr-standby-clone-config-file-copying">.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
+    <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
+      in <filename>postgresql.conf</filename> if I'm not using <application>repmgrd</application>?</title>
+   <para>
+    No, the <literal>repmgr</literal> shared library is only needed when running <application>repmgrd</application>.
+    If you later decide to run <application>repmgrd</application>, you just need to add
+    <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-permissions" xreflabel="Replication permission problems">
+   <title>I've provided replication permission for the <literal>repmgr</literal> user in <filename>pg_hba.conf</filename>
+     but <command>repmgr</command>/<application>repmgrd</application> complains it can't connect to the server... Why?</title>
+   <para>
+    <command>repmgr</command> and <application>repmgrd</application> need to be able to connect to the repmgr database
+    with a normal connection to query metadata. The <literal>replication</literal> connection
+    permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-clone-provide-primary-conninfo" xreflabel="Providing primary connection parameters">
+   <title>When cloning a standby, why do I need to provide the connection parameters
+     for the primary server on the command line, not in the configuration file?</title>
+   <para>
+    Cloning a standby is a one-time action; the role of the server being cloned
+    from could change, so fixing it in the configuration file would create
+    confusion. If &repmgr; needs to establish a connection to the primary
+    server, it can retrieve this from the <literal>repmgr.nodes</literal> table on the local
+    node, and if necessary scan the replication cluster until it locates the active primary.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-clone-waldir-xlogdir" xreflabel="Providing a custom WAL directory">
+   <title>When cloning a standby, how do I ensure the WAL files are placed in a custom directory?</title>
+   <para>
+     Provide the option <literal>--waldir</literal>  (<literal>--xlogdir</literal> in PostgreSQL 9.6
+     and earlier) with the absolute path to the WAL directory in <varname>pg_basebackup_options</varname>.
+     For more details see <xref linkend="cloning-advanced-pg-basebackup-options">.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgr-events-no-fkey" xreflabel="No foreign key on node_id in repmgr.events">
+   <title>Why is there no foreign key on the <literal>node_id</literal> column in the <literal>repmgr.events</literal>
+     table?</title>
+   <para>
+     Under some circumstances event notifications can be generated for servers
+     which have not yet been registered; it's also useful to retain a record
+     of events which includes servers removed from the replication cluster
+     which no longer have an entry in the <literal>repmrg.nodes</literal> table.
+   </para>
+  </sect2>
+
+
+
+
+ </sect1>
+
+ <sect1 id="faq-repmgrd" xreflabel="repmgrd">
+  <title><application>repmgrd</application></title>
+
+
+  <sect2 id="faq-repmgrd-prevent-promotion" xreflabel="Prevent standby from being promoted to primary">
+   <title>How can I prevent a node from ever being promoted to primary?</title>
+   <para>
+    In `repmgr.conf`, set its priority to a value of 0 or less; apply the changed setting with
+    <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>.
+   </para>
+   <para>
+    Additionally, if <varname>failover</varname> is set to <literal>manual</literal>, the node will never
+    be considered as a promotion candidate.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgrd-delayed-standby" xreflabel="Delayed standby support">
+   <title>Does <application>repmgrd</application> support delayed standbys?</title>
+   <para>
+    <application>repmgrd</application> can monitor delayed standbys - those set up with
+    <varname>recovery_min_apply_delay</varname> set to a non-zero value
+    in <filename>recovery.conf</filename> - but as it's not currently possible
+    to directly examine the value applied to the standby, <application>repmgrd</application>
+    may not be able to properly evaluate the node as a promotion candidate.
+   </para>
+   <para>
+    We recommend that delayed standbys are explicitly excluded from promotion
+    by setting <varname>priority</varname> to <literal>0</literal> in
+    <filename>repmgr.conf</filename>.
+   </para>
+   <para>
+    Note that after registering a delayed standby, <application>repmgrd</application> will only start
+    once the metadata added in the primary node has been replicated.
+   </para>
+  </sect2>
+
+  <sect2 id="faq-repmgrd-logfile-rotate" xreflabel="repmgrd logfile rotation">
+   <title>How can I get <application>repmgrd</application> to rotate its logfile?</title>
+   <para>
+     Configure your system's <literal>logrotate</literal> service to do this; see <xref linkend="repmgrd-log-rotation">.
+   </para>
+
+  </sect2>
+
+  <sect2 id="faq-repmgrd-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
+   <title>I've recloned a failed primary as a standby, but <application>repmgrd</application> refuses to start?</title>
+   <para>
+    Check you registered the standby after recloning. If unregistered, the standby
+    cannot be considered as a promotion candidate even if <varname>failover</varname> is set to
+    <literal>automatic</literal>, which is probably not what you want. <application>repmgrd</application> will start if
+    <varname>failover</varname> is set to <literal>manual</literal> so the node's replication status can still
+  be monitored, if desired.
+   </para>
+  </sect2>
+
+ </sect1>
+</appendix>

doc/appendix-packages.sgml

@@ -0,0 +1,367 @@
+<appendix id="appendix-packages" xreflabel="Package details">
+  <indexterm>
+    <primary>packages</primary>
+  </indexterm>
+
+  <title>&repmgr; package details</title>
+  <para>
+    This section provides technical details about various &repmgr; binary
+    packages, such as location of the installed binaries and
+    configuration files.
+  </para>
+
+  <sect1 id="packages-centos" xreflabel="CentOS packages">
+    <title>CentOS Packages</title>
+    <indexterm>
+      <primary>packages</primary>
+      <secondary>CentOS packages</secondary>
+    </indexterm>
+    <para>
+      Currently, &repmgr; RPM packages are provided for versions 6.x and 7.x of CentOS. These should also
+      work on matching versions of Red Hat Enterprise Linux, Scientific Linux and Oracle Enterprise Linux;
+      together with CentOS, these are the same RedHat-based distributions for which the main community project
+      (PGDG) provides packages (see the <ulink url="https://yum.postgresql.org/">PostgreSQL RPM Building Project</ulink>
+      page for details).
+    </para>
+
+    <para>
+      Note these &repmgr; RPM packages are not designed to work with SuSE/OpenSuSE.
+    </para>
+
+    <note>
+      <para>
+        &repmgr; packages are designed to be compatible with community-provided PostgreSQL packages.
+        They may not work with vendor-specific packages such as those provided by RedHat for RHEL
+        customers, as the filesystem layout may be different to the community RPMs.
+        Please contact your support vendor for assistance.
+      </para>
+    </note>
+
+    <sect2 id="packages-centos-repositories">
+      <title>CentOS repositories</title>
+
+      <para>
+        &repmgr; packages are available from the public 2ndQuadrant repository, and also the
+        PostgreSQL community repository. The 2ndQuadrant repository is updated immediately
+        after each
+        &repmgr; release.
+      </para>
+
+      <table id="centos-2ndquadrant-repository">
+        <title>2ndQuadrant public repository</title>
+        <tgroup cols="2">
+          <tbody>
+            <row>
+              <entry>Repository URL:</entry>
+              <entry><ulink url="https://rpm.2ndquadrant.com/">https://rpm.2ndquadrant.com/</ulink></entry>
+            </row>
+            <row>
+              <entry>Repository documentation:</entry>
+              <entry><ulink url="https://repmgr.org/docs/4.0/installation-packages.html#INSTALLATION-PACKAGES-REDHAT-2NDQ">https://repmgr.org/docs/4.0/installation-packages.html#INSTALLATION-PACKAGES-REDHAT-2NDQ</ulink></entry>
+            </row>
+          </tbody>
+        </tgroup>
+      </table>
+
+      <table id="centos-pgdg-repository">
+        <title>PostgreSQL community repository (PGDG)</title>
+        <tgroup cols="2">
+          <tbody>
+            <row>
+              <entry>Repository URL:</entry>
+              <entry><ulink url="https://yum.postgresql.org/repopackages.php">https://yum.postgresql.org/repopackages.php</ulink></entry>
+            </row>
+            <row>
+              <entry>Repository documentation:</entry>
+              <entry><ulink url="https://yum.postgresql.org/">https://yum.postgresql.org/</ulink></entry>
+            </row>
+          </tbody>
+        </tgroup>
+      </table>
+
+    </sect2>
+
+    <sect2 id="packages-centos-details">
+      <title>CentOS package details</title>
+
+      <para>
+        The two tables below list relevant information, paths, commands etc. for the &repmgr; packages on
+        CentOS 7 (with systemd) and CentOS 6 (no systemd). Substitute the appropriate PostgreSQL major
+        version number for your installation.
+      </para>
+
+      <note>
+        <para>
+          For PostgreSQL 9.6 and lower, the CentOS packages use a mixture of <literal>9.6</literal>
+          and <literal>96</literal> in various places to designate the major version; e.g. the
+          package name is <literal>repmgr96</literal>, but the binary directory is
+          <filename>/var/lib/pgsql/9.6/data</filename>.
+        </para>
+        <para>
+          From PostgreSQL 10, the first part of the version number (e.g. <literal>10</literal>) is
+          the major version, so there is more consistency in file/path/package naming
+          (package <literal>repmgr10</literal>, binary directory <filename>/var/lib/pgsql/10/data</filename>).
+        </para>
+      </note>
+
+
+  <table id="centos-7-packages">
+   <title>CentOS 7 packages</title>
+
+   <tgroup cols="2">
+    <tbody>
+
+     <row>
+      <entry>Package name example:</entry>
+      <entry><filename>repmgr10-4.0.4-1.rhel7.x86_64</filename></entry>
+     </row>
+
+     <row>
+      <entry>Metapackage:</entry>
+      <entry>(none)</entry>
+     </row>
+
+     <row>
+      <entry>Installation command:</entry>
+      <entry><literal>yum install repmgr10</literal></entry>
+     </row>
+
+     <row>
+      <entry>Binary location:</entry>
+      <entry><filename>/usr/pgsql-10/bin</filename></entry>
+     </row>
+
+     <row>
+      <entry>repmgr in default path:</entry>
+      <entry>NO</entry>
+     </row>
+
+     <row>
+      <entry>Configuration file location:</entry>
+      <entry><filename>/etc/repmgr/10/repmgr.conf</filename></entry>
+     </row>
+
+     <row>
+      <entry>Data directory:</entry>
+      <entry><filename>/var/lib/pgsql/10/data</filename></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd service command:</entry>
+      <entry><command>systemctl [start|stop|restart|reload] repmgr10</command></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd service file location:</entry>
+      <entry><filename>/usr/lib/systemd/system/repmgr10.service</filename></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd log file location:</entry>
+      <entry>(not specified by package; set in <filename>repmgr.conf</filename>)</entry>
+     </row>
+
+    </tbody>
+   </tgroup>
+  </table>
+
+  <table id="centos-6-packages">
+   <title>CentOS 6 packages</title>
+
+   <tgroup cols="2">
+    <tbody>
+
+     <row>
+      <entry>Package name example:</entry>
+      <entry><filename>repmgr96-4.0.4-1.rhel6.x86_64</filename></entry>
+     </row>
+
+     <row>
+      <entry>Metapackage:</entry>
+      <entry>(none)</entry>
+     </row>
+
+     <row>
+      <entry>Installation command:</entry>
+      <entry><literal>yum install repmgr96</literal></entry>
+     </row>
+
+     <row>
+      <entry>Binary location:</entry>
+      <entry><filename>/usr/pgsql-9.6/bin</filename></entry>
+     </row>
+
+     <row>
+      <entry>repmgr in default path:</entry>
+      <entry>NO</entry>
+     </row>
+
+     <row>
+      <entry>Configuration file location:</entry>
+      <entry><filename>/etc/repmgr/9.6/repmgr.conf</filename></entry>
+     </row>
+
+     <row>
+      <entry>Data directory:</entry>
+      <entry><filename>/var/lib/pgsql/9.6/data</filename></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd service command:</entry>
+      <entry><literal>service [start|stop|restart|reload] repmgr-9.6</literal></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd service file location:</entry>
+      <entry><literal>/etc/init.d/repmgr-9.6</literal></entry>
+     </row>
+
+     <row>
+      <entry>repmgrd log file location:</entry>
+      <entry><filename>/var/log/repmgr/repmgrd-9.6.log</filename></entry>
+     </row>
+
+    </tbody>
+   </tgroup>
+  </table>
+
+    </sect2>
+ </sect1>
+
+
+
+
+  <sect1 id="packages-debian-ubuntu" xreflabel="Debian/Ubuntu packages">
+    <title>Debian/Ubuntu Packages</title>
+    <indexterm>
+      <primary>packages</primary>
+      <secondary>Debian/Ubuntu packages</secondary>
+    </indexterm>
+    <para>
+      &repmgr; <literal>.deb</literal> packages are provided via the
+      PostgreSQL Community APT repository, and are available for each community-supported
+      PostgreSQL version, currently supported Debian releases, and currently supported
+      Ubuntu LTS releases.
+    </para>
+
+    <sect2 id="packages-apt-repository">
+      <title>APT repository</title>
+
+      <para>
+        &repmgr; packages are available from the  PostgreSQL Community APT repository,
+        which is updated immediately after each &repmgr; release.
+      </para>
+
+
+      <table id="apt-repository">
+        <title>PostgreSQL Community APT repository (PGDG)</title>
+        <tgroup cols="2">
+          <tbody>
+            <row>
+              <entry>Repository URL:</entry>
+              <entry><ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink></entry>
+            </row>
+            <row>
+              <entry>Repository documentation:</entry>
+              <entry><ulink url="https://wiki.postgresql.org/wiki/Apt)">https://wiki.postgresql.org/wiki/Apt)</ulink></entry>
+            </row>
+          </tbody>
+        </tgroup>
+      </table>
+    </sect2>
+
+   <sect2 id="packages-debian-details">
+      <title>Debian/Ubuntu package details</title>
+
+      <para>
+        The table below lists relevant information, paths, commands etc. for the &repmgr; packages on
+        Debian 9.x ("Stretch"). Substitute the appropriate PostgreSQL major
+        version number for your installation.
+      </para>
+      <para>
+        See also <xref linkend="repmgrd-configuration-debian-ubuntu"> for some specifics related
+        to configuring the <application>repmgrd</application> daemon.
+      </para>
+
+      <table id="debian-9-packages">
+        <title>Debian 9.x packages</title>
+
+        <tgroup cols="2">
+          <tbody>
+
+            <row>
+              <entry>Package name example:</entry>
+              <entry><filename>postgresql-10-repmgr</filename></entry>
+            </row>
+
+            <row>
+              <entry>Metapackage:</entry>
+              <entry><filename>repmgr-common</filename></entry>
+            </row>
+
+            <row>
+              <entry>Installation command:</entry>
+              <entry><literal>apt-get install postgresql-10-repmgr</literal></entry>
+            </row>
+
+            <row>
+              <entry>Binary location:</entry>
+              <entry><filename>/usr/lib/postgresql/10/bin</filename></entry>
+            </row>
+
+            <row>
+              <entry>repmgr in default path:</entry>
+              <entry>Yes (via wrapper script <filename>/usr/bin/repmgr</filename>)</entry>
+            </row>
+
+            <row>
+              <entry>Configuration file location:</entry>
+              <entry>(not set by package)</entry>
+            </row>
+
+            <row>
+              <entry>Data directory:</entry>
+              <entry><filename>/var/lib/postgresql/10/main</filename></entry>
+            </row>
+
+            <row>
+              <entry>PostgreSQL service command:</entry>
+              <entry><command>systemctl [start|stop|restart|reload] postgresql@10-main</command></entry>
+
+            </row>
+
+            <row>
+              <entry>repmgrd service command:</entry>
+              <entry><command>systemctl [start|stop|restart|reload] repmgrd</command></entry>
+            </row>
+
+            <row>
+              <entry>repmgrd service file location:</entry>
+              <entry><filename>/etc/init.d/repmgrd</filename> (defaults in: <filename>/etc/defaults/repmgrd</filename>)</entry>
+            </row>
+
+            <row>
+              <entry>repmgrd log file location:</entry>
+              <entry>(not specified by package; set in <filename>repmgr.conf</filename>)</entry>
+            </row>
+
+          </tbody>
+        </tgroup>
+      </table>
+      <note>
+        <para>
+          Instead of using the <application>systemd</application> service command directly,
+          it's recommended to execute <command>pg_ctlcluster</command> (as <literal>root</literal>,
+          either directly or via <command>sudo</command>), e.g.:
+          <programlisting>
+            <command>pg_ctlcluster 10 main [start|stop|restart|reload]</command></programlisting>
+        </para>
+        <para>
+          For pre-<application>systemd</application> systems, <command>pg_ctlcluster</command>
+          can be executed directly by the <literal>postgres</literal> user.
+        </para>
+      </note>
+   </sect2>
+
+  </sect1>
+</appendix>

doc/appendix-signatures.sgml

@@ -1,5 +1,37 @@
 <appendix id="appendix-signatures" xreflabel="Verifying digital signatures">
  <title>Verifying digital signatures</title>
 
- <para>WIP</para>
+ <sect1 id="repmgr-source-key" xreflabel="repmgr source key">
+   <title>repmgr source code signing key</title>
+   <para>
+     The signing key ID used for <application>repmgr</application> source code bundles is:
+     <ulink url="http://packages.2ndquadrant.com/repmgr/SOURCE-GPG-KEY-repmgr">
+       <literal>0x297F1DCC</literal></ulink>.
+   </para>
+
+   <para>
+     To download the <application>repmgr</application> source key to your computer:
+     <programlisting>
+       curl -s http://packages.2ndquadrant.com/repmgr/SOURCE-GPG-KEY-repmgr | gpg --import
+       gpg --fingerprint 0x297F1DCC
+     </programlisting>
+     then verify that the fingerprint is the expected value:
+     <programlisting>
+       085A BE38 6FD9 72CE 6365  340D 8365 683D 297F 1DCC</programlisting>
+   </para>
+
+   <para>
+     For checking tarballs, first download and import the <application>repmgr</application>
+     source signing key as shown above. Then download both source tarball and the detached
+     key (e.g. <filename>repmgr-4.0beta1.tar.gz</filename> and
+     <filename>repmgr-4.0beta1.tar.gz.asc</filename>) from
+     <ulink url="https://repmgr.org/download/">https://repmgr.org/download/</ulink>
+     and use <application>gpg</application> to verify the key, e.g.:
+     <programlisting>
+       gpg --verify repmgr-4.0beta1.tar.gz.asc</programlisting>
+   </para>
+
+ </sect1>
+
+
 </appendix>

doc/bdr-failover.md

@@ -1,288 +1,8 @@
 BDR failover with repmgrd
 =========================
 
-`repmgr 4` provides support for monitoring BDR nodes and taking action in case
-one of the nodes fails.
+This document has been integrated into the main `repmgr` documentation
+and is now located here:
 
-    *NOTE* Due to the nature of BDR, it's only safe to use this solution for
-    a two-node scenario. Introducing additional nodes will create an inherent
-    risk of node desynchronisation if a node goes down without being cleanly
-    removed from the cluster.
+> [BDR failover with repmgrd](https://repmgr.org/docs/4.0/repmgrd-bdr.html)
 
-In contrast to streaming replication, there's no concept of "promoting" a new
-primary node with BDR. Instead, "failover" involves monitoring both nodes
-with `repmgrd` and redirecting queries from the failed node to the remaining
-active node. This can be done by using the event notification script generated by
-`repmgrd` to dynamically reconfigure a proxy server/connection pooler such
-as PgBouncer.
-
-
-Prerequisites
--------------
-
-`repmgr 4` requires PostgreSQL 9.6 with the BDR 2 extension enabled and
-configured for a two-node BDR network. `repmgr 4` packages
-must be installed on each node before attempting to configure repmgr.
-
-    *NOTE* `repmgr 4` will refuse to install if it detects more than two
-    BDR nodes.
-
-Application database connections *must* be passed through a proxy server/
-connection pooler such as PgBouncer, and it must be possible to dynamically
-reconfigure that from `repmgrd`. The example demonstrated in this document
-will use PgBouncer.
-
-The proxy server / connection poolers must not be installed on the database
-servers.
-
-For this example, it's assumed password-less SSH connections are available
-from the PostgreSQL servers to the servers where PgBouncer runs, and
-that the user on those servers has permission to alter the PgBouncer
-configuration files.
-
-PostgreSQL connections must be possible between each node, and each node
-must be able to connect to each PgBouncer instance.
-
-
-Configuration
--------------
-
-Sample configuration for `repmgr.conf`:
-
-    node_id=1
-    node_name='node1'
-    conninfo='host=node1 dbname=bdrtest user=repmgr connect_timeout=2'
-    replication_type='bdr'
-
-    event_notifications=bdr_failover
-    event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&1'
-
-    # repmgrd options
-    monitor_interval_secs=5
-    reconnect_attempts=6
-    reconnect_interval=5
-
-Adjust settings as appropriate; copy and adjust for the second node (particularly
-the values `node_id`, `node_name` and `conninfo`).
-
-Note that the values provided for the `conninfo` string must be valid for
-connections from *both* nodes in the cluster. The database must be the BDR
-database.
-
-If defined, `event_notifications` will restrict execution of `event_notification_command`
-to the specified events.
-
-`event_notification_command` is the script which does the actual "heavy lifting"
-of reconfiguring the proxy server/ connection pooler. It is fully user-definable;
-a sample implementation is documented below.
-
-
-repmgr user permissions
------------------------
-
-`repmgr` will create an extension in the BDR database containing objects
-for administering `repmgr` metadata. The user defined in the `conninfo`
-setting must be able to access all objects. Additionally, superuser permissions
-are required to install the `repmgr` extension. The easiest way to do this
-is create the `repmgr` user as a superuser, however if this is not
-desirable, the `repmgr` user can be created as a normal user and a
-superuser specified with `--superuser` when registering a BDR node.
-
-repmgr setup
-------------
-
-Register both nodes:
-
-    $ repmgr -f /etc/repmgr.conf bdr register
-    NOTICE: attempting to install extension "repmgr"
-    NOTICE: "repmgr" extension successfully installed
-    NOTICE: node record created for node 'node1' (ID: 1)
-    NOTICE: BDR node 1 registered (conninfo: host=localhost dbname=bdrtest user=repmgr port=5501)
-
-    $ repmgr -f /etc/repmgr.conf bdr register
-    NOTICE: node record created for node 'node2' (ID: 2)
-    NOTICE: BDR node 2 registered (conninfo: host=localhost dbname=bdrtest user=repmgr port=5502)
-
-The `repmgr` extension will be automatically created when the first
-node is registered, and will be propagated to the second node.
-
-    *IMPORTANT* ensure the repmgr package is available on both nodes before
-    attempting to register the first node
-
-
-At this point the meta data for both nodes has been created; executing
-`repmgr cluster show` (on either node) should produce output like this:
-
-    $ repmgr -f /etc/repmgr.conf cluster show
-     ID | Name  | Role | Status    | Upstream | Connection string
-    ----+-------+------+-----------+----------+--------------------------------------------------------
-     1  | node1 | bdr  | * running |          | host=node1 dbname=bdrtest user=repmgr connect_timeout=2
-     2  | node2 | bdr  | * running |          | host=node2 dbname=bdrtest user=repmgr connect_timeout=2
-
-Additionally it's possible to see a log of significant events; so far
-this will only record the two node registrations (in reverse chronological order):
-
-     Node ID | Event        | OK | Timestamp           | Details
-    ---------+--------------+----+---------------------+----------------------------------------------
-     2       | bdr_register | t  | 2017-07-27 17:51:48 | node record created for node 'node2' (ID: 2)
-     1       | bdr_register | t  | 2017-07-27 17:51:00 | node record created for node 'node1' (ID: 1)
-
-
-Defining the "event_notification_command"
------------------------------------------
-
-Key to "failover" execution is the `event_notification_command`, which is a
-user-definable script which should reconfigure the  proxy server/
-connection pooler.
-
-Each time `repmgr` (or `repmgrd`) records an event, it can optionally
-execute the script defined in `event_notification_command` to
-take further action; details of the event will be passed as parameters.
-Following placeholders are available to the script:
-
-    %n - node ID
-    %e - event type
-    %s - success (1 or 0)
-    %t - timestamp
-    %d - details
-    %c - conninfo string of the next available node
-    %a - name of the next available node
-
-Note that `%c` and `%a` will only be provided during `bdr_failover`
-events, which is what is of interest here.
-
-The provided sample script (`scripts/bdr-pgbouncer.sh`) is configured like
-this:
-
-    event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a"'
-
-and parses the configures parameters like this:
-
-    NODE_ID=$1
-    EVENT_TYPE=$2
-    SUCCESS=$3
-    NEXT_CONNINFO=$4
-    NEXT_NODE_NAME=$5
-
-It also contains some hard-coded values about the PgBouncer configuration for
-both nodes; these will need to be adjusted for your local environment of course
-(ideally the scripts would be maintained as templates and generated by some
-kind of provisioning system).
-
-The script performs following steps:
-
- - pauses PgBouncer on all nodes
- - recreates the PgBouncer configuration file on each node using the information
-   provided by `repmgrd` (mainly the `conninfo` string) to configure PgBouncer
-   to point to the remaining node
- - reloads the PgBouncer configuration
- - resumes PgBouncer
-
-From that point, any connections to PgBouncer on the failed BDR node will be redirected
-to the active node.
-
-
-repmgrd
--------
-
-
-
-Node monitoring and failover
-----------------------------
-
-At the intervals specified by `monitor_interval_secs` in `repmgr.conf`, `repmgrd`
-will ping each node to check if it's available. If a node isn't available,
-`repmgrd` will enter failover mode and  check `reconnect_attempts` times
-at intervals of `reconnect_interval` to confirm the node is definitely unreachable.
-This buffer period is necessary to avoid false positives caused by transient
-network outages.
-
-If the node is still unavailable, `repmgrd` will enter failover mode and execute
-the script defined in `event_notification_command`; an entry will be logged
-in the `repmgr.events` table and `repmgrd` will (unless otherwise configured)
-resume monitoring of the node in "degraded" mode until it reappears.
-
-`repmgrd` logfile output during a failover event will look something like this
-one one node (usually the node which has failed, here "node2"):
-
-    ...
-    [2017-07-27 21:08:39] [INFO] starting continuous BDR node monitoring
-    [2017-07-27 21:08:39] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:08:55] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:11] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
-    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
-    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
-    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
-    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
-    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
-    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
-    [2017-07-27 21:09:28] [NOTICE] setting node record for node 2 to inactive
-    [2017-07-27 21:09:28] [INFO] executing notification command for event "bdr_failover"
-    [2017-07-27 21:09:28] [DETAIL] command is:
-      /path/to/bdr-pgbouncer.sh 2 bdr_failover 1 "host=host=node1 dbname=bdrtest user=repmgr connect_timeout=2" "node1"
-    [2017-07-27 21:09:28] [INFO] node 'node2' (ID: 2) detected as failed; next available node is 'node1' (ID: 1)
-    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-    ...
-
-Output on the other node ("node1") during the same event will look like this:
-
-    [2017-07-27 21:08:35] [INFO] starting continuous BDR node monitoring
-    [2017-07-27 21:08:35] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:08:51] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:07] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
-    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
-    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
-    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
-    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
-    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
-    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
-    [2017-07-27 21:09:28] [NOTICE] other node's repmgrd is handling failover
-    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-
-This assumes only the PostgreSQL instance on "node2" has failed. In this case the
-`repmgrd` instance running on "node2" has performed the failover. However if
-the entire server becomes unavailable, `repmgrd` on "node1" will perform
-the failover.
-
-
-Node recovery
--------------
-
-Following failure of a BDR node, if the node subsequently becomes available again,
-a `bdr_recovery` event will be generated. This could potentially be used to
-reconfigure PgBouncer automatically to bring the node back into the available pool,
-however it would be prudent to manually verify the node's status before
-exposing it to the application.
-
-If the failed node comes back up and connects correctly, output similar to this
-will be visible in the `repmgrd` log:
-
-    [2017-07-27 21:25:30] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-    [2017-07-27 21:25:46] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:25:46] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-    [2017-07-27 21:25:55] [INFO] active replication slot for node "node1" found after 1 seconds
-    [2017-07-27 21:25:55] [NOTICE] node "node2" (ID: 2) has recovered after 986 seconds
-
-
-Shutdown of both nodes
-----------------------
-
-If both PostgreSQL instances are shut down, `repmgrd` will try and handle the
-situation as gracefully as possible, though with no failover candidates available
-there's not much it can do. Should this case ever occur, we recommend shutting
-down `repmgrd` on both nodes and restarting it once the PostgreSQL instances
-are running properly.

doc/changes-in-repmgr4.md

@@ -1,106 +1,7 @@
+Changes in repmgr 4
+===================
 
-Standardisation on `primary`
-----------------------------
+This document has been integrated into the main `repmgr` documentation
+and is now located here:
 
-To standardise terminology, `primary` is used to denote the read/write
-node in a streaming replication cluster. `master` is still accepted
-as a synonym (e.g. `repmgr master register`).
-
-
-New command line options
-------------------------
-
-- `--dry-run`: repmgr will attempt to perform the action as far as possible
-   without making any changes to the database
-
-- `--upstream-node-id`: use to specify the upstream node the standby will
-  connect later stream from, when cloning a standby. This replaces the configuration
-  file parameter `upstream_node`, as the upstream node is set when the standby
-  is initially cloned, but can change over the lifetime of an installation (due
-  to failovers, switchovers etc.) so it's pointless/confusing keeping the original
-  value around in the config file.
-
-Changed command line options
-----------------------------
-
-### repmgr
-
-- `--replication-user` has been deprecated; it has been replaced by the
-  configuration file option `replication_user`.  The value (which defaults
-  to the user in the `conninfo` string) will be stored in the repmgr metadata
-  for use by  standby clone/follow..
-
-- `--recovery-min-apply-delay` is now a configuration file parameter
-  `recovery_min_apply_delay, to ensure the setting does not get lost when
-  a standby follows a new upstream.
-
-### repmgrd
-
-- `--monitoring-history` is deprecated and has been replaced by the
-  configuration file option `monitoring_history`. This enables the
-  setting to be changed without having to modify system service files.
-
-Changes to repmgr commands
---------------------------
-
-
-### `repmgr cluster show`
-
-This now displays the role of each node (e.g. `primary`, `standby`)
-and its status in separate columns.
-
-The `--csv` option now emits a third column indicating the recovery
-status of the node.
-
-
-Configuration file changes
---------------------------
-
-### Required settings
-
-The following 4 parameters are mandatory in `repmgr.conf`:
-
-- `node_id`
-- `node_name`
-- `conninfo`
-- `data_directory`
-
-
-### Renamed settings
-
-Some settings have been renamed for clarity and consistency:
-
-- `node`: now `node_id`
-- `name`: now `node_name`
-- `master_reponse_timeout`: now `async_query_timeout` to better indicate its
-   purpose
-
-- The following configuration file parameters have been renamed for consistency
-  with other parameters (and conform to the pattern used by PostgreSQL itself,
-  which uses the prefix `log_` for logging parameters):
-  - `loglevel` has been renamed to `log_level`
-  - `logfile` has been renamed to `log_file`
-  - `logfacility` has been renamed to `log_facility`
-
-### Removed settings
-
-- `cluster`: has been removed
-- `upstream_node`: see note about `--upstream-node-id` above.
-- `retry_promote_interval_secs`: this is now redundant due to changes in the
-   failover/promotion mechanism; the new equivalent is `primary_notification_timeout`
-
-
-### Logging changes
-
-- default value for `log_level` is `INFO` rather than `NOTICE`.
-- new parameter `log_status_interval`, which causes `repmgrd` to emit a status log
-  line at the specified interval
-
-
-repmgrd
--------
-
-The `repmgr` shared library has been renamed from `repmgr_funcs` to `repmgr`,
-meaning `shared_preload_libraries` needs to be updated to the new name:
-
-    shared_preload_libraries = 'repmgr'
+> [Release notes](https://repmgr.org/docs/4.0/release-4.0.html)

doc/cloning-standbys.sgml

@@ -1,13 +1,16 @@
 <chapter id="cloning-standbys" xreflabel="cloning standbys">
  <title>Cloning standbys</title>
- <para>
- </para>
 
  <sect1 id="cloning-from-barman" xreflabel="Cloning from Barman">
    <indexterm>
-     <primary>cloning</primary>
-     <secondary>from Barman</secondary>
+    <primary>cloning</primary>
+    <secondary>from Barman</secondary>
    </indexterm>
+   <indexterm>
+    <primary>Barman</primary>
+    <secondary>cloning a standby</secondary>
+   </indexterm>
+
    <title>Cloning a standby from Barman</title>
    <para>
     <xref linkend="repmgr-standby-clone"> can use
@@ -48,7 +51,7 @@
    </itemizedlist>
    </para>
 
-  <sect2 id="cloning-from-barman-prerequisites" xreflabel="Prerequisites for cloning from Barman">
+  <sect2 id="cloning-from-barman-prerequisites">
    <title>Prerequisites for cloning from Barman</title>
    <para>
     In order to enable Barman support for <command>repmgr standby clone</command>, following
@@ -70,7 +73,8 @@
       <para>
         the <varname>restore_command</varname> setting in <filename>repmgr.conf</filename> is configured to
         use a copy of the <command>barman-wal-restore</command> script shipped with the
-        <literal>barman-cli</literal> package (see below);
+        <literal>barman-cli</literal> package (see section <xref linkend="cloning-from-barman-restore-command">
+        below).
       </para>
      </listitem>
      <listitem>
@@ -122,6 +126,11 @@
    </para>
   </sect2>
   <sect2 id="cloning-from-barman-restore-command" xreflabel="Using Barman as a WAL file source">
+  <indexterm>
+    <primary>Barman</primary>
+    <secondary>fetching archived WAL</secondary>
+   </indexterm>
+
    <title>Using Barman as a WAL file source</title>
    <para>
     As a fallback in case streaming replication is interrupted, PostgreSQL can optionally
@@ -188,11 +197,10 @@
      To enable &repmgr; to use replication slots, set the boolean parameter
      <varname>use_replication_slots</varname> in <filename>repmgr.conf</filename>:
      <programlisting>
-       use_replication_slots=true
-     </programlisting>
+       use_replication_slots=true</programlisting>
    </para>
    <para>
-    Replication slots must be enabled in <filename>postgresql.conf</filename>` by
+    Replication slots must be enabled in <filename>postgresql.conf</filename> by
     setting the parameter <varname>max_replication_slots</varname> to at least the
     number of expected standbys (changes to this parameter require a server restart).
    </para>
@@ -339,16 +347,36 @@
 
    <sect2 id="cloning-advanced-pg-basebackup-options" xreflabel="pg_basebackup options when cloning a standby">
     <title>pg_basebackup options when cloning a standby</title>
+    <para>
+      As &repmgr; uses <command>pg_basebackup</command> to clone a standby, it's possible to
+      provide additional parameters for <command>pg_basebackup</command> to customise the
+      cloning process.
+    </para>
     <para>
      By default, <command>pg_basebackup</command> performs a checkpoint before beginning the backup
      process. However, a normal checkpoint may take some time to complete;
      a fast checkpoint can be forced with the <literal>-c/--fast-checkpoint</literal> option.
-     However this may impact performance of the server being cloned from
+     Note that this may impact performance of the server being cloned from (typically the primary)
      so should be used with care.
     </para>
+    <tip>
+      <simpara>
+        If <application>Barman</application> is set up for the cluster, it's possible to
+        clone the standby directly from Barman, without any impact on the server the standby
+        is being cloned from. For more details see <xref linkend="cloning-from-barman">.
+      </simpara>
+    </tip>
+    <para>
+      Other options can be passed to <command>pg_basebackup</command> by including them
+      in the <filename>repmgr.conf</filename> setting <varname>pg_basebackup_options</varname>.
+    </para>
+    <para>
+      If using a separate directory to store WAL files, provide the option <literal>--waldir</literal>
+      (<literal>--xlogdir</literal> in PostgreSQL 9.6 and earlier) with the absolute path to the
+      WAL directory. Any WALs generated during the cloning process will be copied here, and
+      a symlink will automatically be created from the main data directory.
+    </para>
     <para>
-     Further options can be passed to the <command>pg_basebackup</command> utility via
-     the setting <varname>pg_basebackup_options</varname> in <filename>repmgr.conf</filename>.
      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>
@@ -356,11 +384,16 @@
 
    <sect2 id="cloning-advanced-managing-passwords" xreflabel="Managing passwords">
     <title>Managing passwords</title>
+    <indexterm>
+      <primary>cloning</primary>
+      <secondary>using passwords</secondary>
+    </indexterm>
+
     <para>
      If replication connections to a standby's upstream server are password-protected,
-     the standby must be able to provide the password so it can begin streaming
-     replication.
+     the standby must be able to provide the password so it can begin streaming replication.
     </para>
+
     <para>
      The recommended way to do this is to store the password in the <literal>postgres</literal> system
      user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
@@ -368,19 +401,38 @@
      security reasons. For more details see the
      <ulink url="https://www.postgresql.org/docs/current/static/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
     </para>
+
+    <note>
+      <para>
+        If using a <filename>pgpass</filename> file, an entry for the replication user (by default the
+        user who connects to the <literal>repmgr</literal> database) <emphasis>must</emphasis>
+        be provided, with database name set to <literal>replication</literal>, e.g.:
+        <programlisting>
+          node1:5432:replication:repmgr:12345</programlisting>
+      </para>
+    </note>
+
     <para>
      If, for whatever reason, you wish to include the password in <filename>recovery.conf</filename>,
      set <varname>use_primary_conninfo_password</varname> to <literal>true</literal> in
      <filename>repmgr.conf</filename>. This will read a password set in <varname>PGPASSWORD</varname>
-     (but not <filename>~/.pgpass</filename>) and place it into the <literal>primary_conninfo</literal>
+     (but not <filename>~/.pgpass</filename>) and place it into the <varname>primary_conninfo</varname>
      string in <filename>recovery.conf</filename>. Note that <varname>PGPASSWORD</varname>
      will need to be set during any action which causes <filename>recovery.conf</filename> to be
      rewritten, e.g. <xref linkend="repmgr-standby-follow">.
     </para>
     <para>
      It is of course also possible to include the password value in the <varname>conninfo</varname>
-     string for each node, but this is obviously a security risk and should be
-     avoided.
+     string for each node, but this is obviously a security risk and should be avoided.
+    </para>
+    <para>
+      From PostgreSQL 9.6, <application>libpq</application> supports the <varname>passfile</varname>
+      parameter in connection strings, which can be used to specify a password file other than
+      the default <filename>~/.pgpass</filename>.
+    </para>
+    <para>
+      To have &repmgr; write a custom password file in <varname>primary_conninfo</varname>,
+      specify its location in <varname>passfile</varname> in <filename>repmgr.conf</filename>.
     </para>
    </sect2>
 
@@ -392,7 +444,7 @@
      the replication user should be set in <filename>repmgr.conf</filename> via the parameter
      <varname>replication_user</varname>; &repmgr; will use this value when making
      replication connections and generating <filename>recovery.conf</filename>. This
-     value will also be stored in the <literal>repmgr.nodes</literal>
+     value will also be stored in the parameter <literal>repmgr.nodes</literal>
      table for each node; it no longer needs to be explicitly specified when
      cloning a node or executing <xref linkend="repmgr-standby-follow">.
     </para>

doc/configuration-file-settings.sgml

@@ -1,5 +1,10 @@
 <sect1 id="configuration-file-settings" xreflabel="configuration file settings">
- <title>Configuration file settings</title>
+  <indexterm>
+    <primary>repmgr.conf</primary>
+    <secondary>basic settings</secondary>
+  </indexterm>
+
+ <title>Basic configuration file settings</title>
  <para>
    Each <filename>repmgr.conf</filename> file must contain the following parameters:
  </para>
@@ -87,7 +92,10 @@
 
   <para>
     For a full list of annotated configuration items, see the file
-    <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</>.
+    <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
+  </para>
+  <para>
+    For <application>repmgrd</application>-specific settings, see <xref linkend="repmgrd-configuration">.
   </para>
 
   <note>

doc/configuration-file.sgml

@@ -1,4 +1,14 @@
 <sect1 id="configuration-file" xreflabel="configuration file location">
+  <indexterm>
+    <primary>repmgr.conf</primary>
+    <secondary>location</secondary>
+  </indexterm>
+
+  <indexterm>
+    <primary>configuration</primary>
+    <secondary>repmgr.conf location</secondary>
+  </indexterm>
+
   <title>Configuration file location</title>
   <para>
     <application>repmgr</application> and <application>repmgrd</application>
@@ -7,7 +17,7 @@
     <filename>repmgr.conf</filename> must contain a number of required parameters, including
     the database connection string for the local node and the location
     of its data directory; other values will be inferred from defaults if
-    not explicitly supplied. See section `configuration file parameters`
+    not explicitly supplied. See section <xref linkend="configuration-file-settings">
     for more details.
   </para>
 
@@ -15,7 +25,7 @@
    The configuration file will be searched for in the following locations:
    <itemizedlist spacing="compact" mark="bullet">
     <listitem>
-     <para>a configuration file specified by the `-f/--config-file` command line option</para>
+     <para>a configuration file specified by the <literal>-f/--config-file</literal> command line option</para>
     </listitem>
     <listitem>
      <para>
@@ -37,10 +47,23 @@
   </para>
 
   <para>
-   Note that if a file is explicitly specified with <application>-f/--config-file</application>,
-   an error will be raised if it is not found or not readable and no attempt will be made to
+   Note that if a file is explicitly specified with <literal>-f/--config-file</literal>,
+   an error will be raised if it is not found or not readable, and no attempt will be made to
    check default locations; this is to prevent <application>repmgr</application> unexpectedly
-   reading the wrong file.
+   reading the wrong configuraton file.
   </para>
 
+  <note>
+    <para>
+      If providing the configuration file location with <literal>-f/--config-file</literal>,
+      avoid using a relative path, particularly when executing <xref linkend="repmgr-primary-register">
+      and <xref linkend="repmgr-standby-register">, as &repmgr; stores the configuration file location
+      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>
 </sect1>

doc/configuration-service-commands.sgml

@@ -0,0 +1,123 @@
+<sect1 id="configuration-service-commands" xreflabel="service command settings">
+  <indexterm>
+    <primary>repmgr.conf</primary>
+    <secondary>service command settings</secondary>
+  </indexterm>
+  <indexterm>
+    <primary>service command settings</primary>
+    <secondary>configuration in repmgr.conf</secondary>
+  </indexterm>
+  <title>Service command settings</title>
+
+  <para>
+    In some circumstances, &repmgr; (and <application>repmgrd</application>) need to
+    be able to stop, start or restart PostgreSQL. &repmgr; commands which need to do this
+    include <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>,
+    <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link> and
+    <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>.
+  </para>
+  <para>
+    By default, &repmgr; will use PostgreSQL's <command>pg_ctl</command> to control the PostgreSQL
+    server. However this can lead to various problems, particularly when PostgreSQL has been
+    installed from packages, and expecially so if <application>systemd</application> is in use.
+  </para>
+
+
+  <note>
+    <para>
+      If using <application>systemd</application>, ensure you have <varname>RemoveIPC</varname> set to <literal>off</literal>.
+      See the <ulink url="https://wiki.postgresql.org/wiki/Systemd">systemd</ulink>
+      entry in the <ulink url="https://wiki.postgresql.org/wiki/Main_Page">PostgreSQL wiki</ulink> for details.
+    </para>
+  </note>
+
+
+  <para>
+    With this in mind, we recommend to <emphasis>always</emphasis> configure &repmgr; to use the
+    available system service commands.
+  </para>
+
+  <para>
+    To do this, specify the appropriate command for each action
+    in <filename>repmgr.conf</filename> using the following configuration
+    parameters:
+    <programlisting>
+    service_start_command
+    service_stop_command
+    service_restart_command
+    service_reload_command</programlisting>
+  </para>
+  <note>
+    <para>
+      It's also possible to specify a <varname>service_promote_command</varname>.
+      This is intended for systems which provide a package-level promote command,
+      such as Debian's <application>pg_ctlcluster</application>, to promote the
+      PostgreSQL from standby to primary.
+    </para>
+    <para>
+      If your packaging system does not provide such a command, it can be left empty,
+      and &repmgr; will generate the appropriate <command>pg_ctl ... promote</command> command.
+    </para>
+    <para>
+      Do not confuse this with <varname>promote_command</varname>, which is used
+      by <application>repmgrd</application> to execute <xref linkend="repmgr-standby-promote">.
+    </para>
+  </note>
+
+
+  <para>
+    To confirm which command &repmgr; will execute for each action, use
+    <command>repmgr node service --list --action=...</command>, e.g.:
+    <programlisting>
+      repmgr -f /etc/repmgr.conf node service --list --action=stop
+      repmgr -f /etc/repmgr.conf node service --list --action=start
+      repmgr -f /etc/repmgr.conf node service --list --action=restart
+      repmgr -f /etc/repmgr.conf node service --list --action=reload</programlisting>
+  </para>
+
+  <para>
+     These commands will be executed by the system user which &repmgr; runs as (usually <literal>postgres</literal>)
+     and will probably require passwordless sudo access to be able to execute the command.
+  </para>
+  <para>
+    For example, using <application>systemd</application> on CentOS 7, the service commands can be
+    set as follows:
+    <programlisting>
+      service_start_command   = 'sudo systemctl start postgresql-9.6'
+      service_stop_command    = 'sudo systemctl stop postgresql-9.6'
+      service_restart_command = 'sudo systemctl restart postgresql-9.6'
+      service_reload_command  = 'sudo systemctl reload postgresql-9.6'</programlisting>
+    and <filename>/etc/sudoers</filename> should be set as follows:
+    <programlisting>
+      Defaults:postgres !requiretty
+      postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.6, \
+        /usr/bin/systemctl start postgresql-9.6, \
+        /usr/bin/systemctl restart postgresql-9.6 \
+        /usr/bin/systemctl reload postgresql-9.6</programlisting>
+  </para>
+
+  <important>
+    <indexterm>
+      <primary>pg_ctlcluster</primary>
+      <secondary>service command settings</secondary>
+    </indexterm>
+    <para>
+      Debian/Ubuntu users: instead of calling <command>sudo systemctl</command> directly, use
+      <command>sudo pg_ctlcluster</command>, e.g.:
+    <programlisting>
+      service_start_command   = 'sudo pg_ctlcluster 9.6 main start'
+      service_stop_command    = 'sudo pg_ctlcluster 9.6 main stop'
+      service_restart_command = 'sudo pg_ctlcluster 9.6 main restart'
+      service_reload_command  = 'sudo pg_ctlcluster 9.6 main reload'</programlisting>
+      and set <filename>/etc/sudoers</filename> accordingly.
+    </para>
+    <para>
+      While <command>pg_ctlcluster</command> will work when executed as user <literal>postgres</literal>,
+      it's strongly recommended to use <command>sudo pg_ctlcluster</command> on <application>systemd</application>
+      systems, to ensure <application>systemd</application> has a correct picture of
+      the PostgreSQL application state.
+    </para>
+
+  </important>
+
+</sect1>

doc/configuration.sgml

@@ -1,7 +1,25 @@
 <chapter id="configuration" xreflabel="Configuration">
- <title>repmgr configuration</title>
+  <title>repmgr configuration</title>
 
   &configuration-file;
   &configuration-file-settings;
+  &configuration-service-commands;
 
+  <sect1 id="configuration-permissions" xreflabel="User permissions">
+    <indexterm>
+      <primary>configuration</primary>
+      <secondary>user permissions</secondary>
+    </indexterm>
+
+    <title>repmgr user permissions</title>
+    <para>
+      &repmgr; will create an extension database containing objects
+      for administering &repmgr; metadata. The user defined in the <varname>conninfo</varname>
+      setting must be able to access all objects. Additionally, superuser permissions
+      are required to install the &repmgr; extension. The easiest way to do this
+      is create the &repmgr; user as a superuser, however if this is not
+      desirable, the &repmgr; user can be created as a normal user and a
+      superuser specified with <literal>--superuser</literal> when registering a &repmgr; node.
+    </para>
+  </sect1>
 </chapter>

doc/configuring-witness-server.sgml

@@ -0,0 +1,86 @@
+<chapter id="using-witness-server">
+ <indexterm>
+  <primary>witness server</primary>
+  <seealso>Using a witness server with repmgrd</seealso>
+ </indexterm>
+
+
+ <title>Using a witness server</title>
+ <para>
+   A <xref linkend="witness-server"> is a normal PostgreSQL instance which
+   is not part of the streaming replication cluster; its purpose is, if a
+   failover situation occurs, to provide proof that the primary server
+   itself is unavailable.
+ </para>
+
+ <para>
+   A typical use case for a witness server is a two-node streaming replication
+   setup, where the primary and standby are in different locations (data centres).
+   By creating a witness server in the same location as the primary, if the primary
+   becomes unavailable  it's possible for the standby to decide whether it can
+   promote itself without risking a "split brain" scenario: if it can't see either the
+   witness or the primary server, it's likely there's a network-level interruption
+   and it should not promote itself. If it can 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).
+ </para>
+ <para>
+   For more complex replication scenarios,e.g. with multiple datacentres, it may
+   be preferable to use location-based failover, which ensures that only nodes
+   in the same location as the primary will ever be promotion candidates;
+   see <xref linkend="repmgrd-network-split"> for more details.
+ </para>
+
+ <note>
+   <simpara>
+     A witness server will only be useful if <application>repmgrd</application>
+     is in use.
+   </simpara>
+ </note>
+
+ <sect1 id="creating-witness-server">
+   <title>Creating a witness server</title>
+ <para>
+   To create a witness server, set up a normal PostgreSQL instance on a server
+   in the same physical location as the cluster's primary server.
+ </para>
+ <para>
+   This instance should *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>
+ <note>
+   <simpara>
+     &repmgr; 3.3 and earlier provided a <command>repmgr create witness</command>
+     command, which would automatically create a PostgreSQL instance. However
+     this often resulted in an unsatisfactory, hard-to-customise instance.
+   </simpara>
+ </note>
+ <para>
+   The witness server should be configured in the same way as a normal
+   &repmgr; node; see section <xref linkend="configuration">.
+ </para>
+ <para>
+   Register the witness server with <xref linkend="repmgr-witness-register">.
+   This will create the &repmgr; extension on the witness server, and make
+   a copy of the &repmgr; metadata.
+ </para>
+ <note>
+   <simpara>
+    As the witness server is not part of the replication cluster, further
+    changes to the &repmgr; metadata will be synchronised by
+    <application>repmgrd</application>.
+   </simpara>
+ </note>
+ <para>
+   Once the witness server has been configured, <application>repmgrd</application>
+   should be started; for more details see <xref linkend="repmgrd-witness-server">.
+ </para>
+
+ <para>
+  To unregister a witness server, use <xref linkend="repmgr-witness-unregister">.
+ </para>
+
+ </sect1>
+</chapter>

doc/event-notifications.sgml

@@ -1,12 +1,17 @@
 <chapter id="event-notifications" xreflabel="event notifications">
+
+ <indexterm>
+   <primary>event notifications</primary>
+ </indexterm>
+
  <title>Event Notifications</title>
  <para>
-  Each time `repmgr` or `repmgrd` perform a significant event, a record
-  of that event is written into the `repmgr.events` table together with
+  Each time &repmgr; or <application>repmgrd</application> perform a significant event, a record
+  of that event is written into the <literal>repmgr.events</literal> table together with
   a timestamp, an indication of failure or success, and further details
   if appropriate. This is useful for gaining an overview of events
   affecting the replication cluster. However note that this table has
-  advisory character and should be used in combination with the `repmgr`
+  advisory character and should be used in combination with the &repmgr;
   and PostgreSQL logs to obtain details of any events.
  </para>
  <para>
@@ -28,11 +33,11 @@
  <para>
   Additionally, event notifications can be passed to a user-defined program
   or script which can take further action, e.g. send email notifications.
-  This is done by setting the `event_notification_command` parameter in
-  `repmgr.conf`.
+  This is done by setting the <literal>event_notification_command</literal> parameter in
+  <filename>repmgr.conf</filename>.
  </para>
  <para>
-  This parameter accepts the following format placeholders:
+  The following format placeholders are provided for all event notifications:
  </para>
 
  <variablelist>
@@ -55,10 +60,10 @@
   </varlistentry>
 
   <varlistentry>
-   <term><option>%t</option></term>
+   <term><option>%s</option></term>
    <listitem>
     <para>
-     success (1 or 0)
+     success (1) or failure (0)
     </para>
    </listitem>
   </varlistentry>
@@ -80,6 +85,7 @@
    </listitem>
   </varlistentry>
  </variablelist>
+
  <para>
   The values provided for <literal>%t</literal> and <literal>%d</literal>
   will probably contain spaces, so should be quoted in the provided command
@@ -88,42 +94,75 @@
     event_notification_command='/path/to/some/script %n %e %s "%t" "%d"'
   </programlisting>
  </para>
+
  <para>
-  Additionally the following format placeholders are available for the event
-  type <varname>bdr_failover</varname> and optionally <varname>bdr_recovery</varname>:
+   The following parameters are provided for a subset of event notifications:
  </para>
+
  <variablelist>
+  <varlistentry>
+   <term><option>%p</option></term>
+   <listitem>
+    <para>
+     node ID of the current primary (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+    </para>
+    <para>
+     node ID of the demoted primary (<xref linkend="repmgr-standby-switchover"> only)
+    </para>
+   </listitem>
+  </varlistentry>
   <varlistentry>
    <term><option>%c</option></term>
    <listitem>
     <para>
-     conninfo string of the next available node
+     <literal>conninfo</literal> string of the primary node
+     (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+    </para>
+    <para>
+      <literal>conninfo</literal> string of the next available node
+      (<varname>bdr_failover</varname> and  <varname>bdr_recovery</varname>)
     </para>
    </listitem>
   </varlistentry>
+
   <varlistentry>
    <term><option>%a</option></term>
    <listitem>
     <para>
-     name of the next available node
+     name of the current primary node (<xref linkend="repmgr-standby-register"> and <xref linkend="repmgr-standby-follow">)
+    </para>
+    <para>
+     name of the next available node (<varname>bdr_failover</varname> and  <varname>bdr_recovery</varname>)
     </para>
    </listitem>
   </varlistentry>
+
  </variablelist>
+
  <para>
-  These should always be quoted.
+  The values provided for <literal>%c</literal> and <literal>%a</literal>
+  will probably contain spaces, so should always be quoted.
  </para>
+
  <para>
   By default, all notification types will be passed to the designated script;
-  the notification types can be filtered to explicitly named ones:
+  the notification types can be filtered to explicitly named ones using the
+  <varname>event_notifications</varname> parameter:
+
   <itemizedlist spacing="compact" mark="bullet">
 
    <listitem>
     <simpara><literal>primary_register</literal></simpara>
    </listitem>
+   <listitem>
+    <simpara><literal>primary_unregister</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>standby_register</literal></simpara>
    </listitem>
+   <listitem>
+    <simpara><literal>standby_register_sync</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>standby_unregister</literal></simpara>
    </listitem>
@@ -139,6 +178,21 @@
    <listitem>
     <simpara><literal>standby_disconnect_manual</literal></simpara>
    </listitem>
+   <listitem>
+    <simpara><literal>standby_failure</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>standby_recovery</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>witness_register</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>witness_unregister</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>node_rejoin</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>repmgrd_start</literal></simpara>
    </listitem>
@@ -151,6 +205,18 @@
    <listitem>
     <simpara><literal>repmgrd_failover_follow</literal></simpara>
    </listitem>
+   <listitem>
+     <simpara><literal>repmgrd_failover_aborted</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>repmgrd_upstream_disconnect</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>repmgrd_upstream_reconnect</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>repmgrd_promote_error</literal></simpara>
+   </listitem>
    <listitem>
     <simpara><literal>bdr_failover</literal></simpara>
    </listitem>
@@ -169,6 +235,7 @@
 
   </itemizedlist>
  </para>
+
  <para>
   Note that under some circumstances (e.g. when no replication cluster primary
   could be located), it will not be possible to write an entry into the

doc/filelist.sgml

@@ -39,10 +39,13 @@
 <!ENTITY configuration      SYSTEM "configuration.sgml">
 <!ENTITY configuration-file      SYSTEM "configuration-file.sgml">
 <!ENTITY configuration-file-settings      SYSTEM "configuration-file-settings.sgml">
+<!ENTITY configuration-service-commands   SYSTEM "configuration-service-commands.sgml">
 <!ENTITY cloning-standbys  SYSTEM "cloning-standbys.sgml">
 <!ENTITY promoting-standby  SYSTEM "promoting-standby.sgml">
 <!ENTITY follow-new-primary  SYSTEM "follow-new-primary.sgml">
 <!ENTITY switchover  SYSTEM "switchover.sgml">
+<!ENTITY configuring-witness-server SYSTEM "configuring-witness-server.sgml">
+
 <!ENTITY event-notifications  SYSTEM "event-notifications.sgml">
 <!ENTITY upgrading-repmgr  SYSTEM "upgrading-repmgr.sgml">
 
@@ -53,6 +56,8 @@
 <!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-bdr SYSTEM "repmgrd-bdr.sgml">
 
 <!ENTITY repmgr-primary-register SYSTEM "repmgr-primary-register.sgml">
 <!ENTITY repmgr-primary-unregister SYSTEM "repmgr-primary-unregister.sgml">
@@ -62,6 +67,8 @@
 <!ENTITY repmgr-standby-promote SYSTEM "repmgr-standby-promote.sgml">
 <!ENTITY repmgr-standby-follow SYSTEM "repmgr-standby-follow.sgml">
 <!ENTITY repmgr-standby-switchover SYSTEM "repmgr-standby-switchover.sgml">
+<!ENTITY repmgr-witness-register SYSTEM "repmgr-witness-register.sgml">
+<!ENTITY repmgr-witness-unregister SYSTEM "repmgr-witness-unregister.sgml">
 <!ENTITY repmgr-node-status SYSTEM "repmgr-node-status.sgml">
 <!ENTITY repmgr-node-check SYSTEM "repmgr-node-check.sgml">
 <!ENTITY repmgr-node-rejoin SYSTEM "repmgr-node-rejoin.sgml">
@@ -71,7 +78,10 @@
 <!ENTITY repmgr-cluster-event SYSTEM "repmgr-cluster-event.sgml">
 <!ENTITY repmgr-cluster-cleanup SYSTEM "repmgr-cluster-cleanup.sgml">
 
+<!ENTITY appendix-release-notes  SYSTEM "appendix-release-notes.sgml">
+<!ENTITY appendix-faq      SYSTEM "appendix-faq.sgml">
 <!ENTITY appendix-signatures      SYSTEM "appendix-signatures.sgml">
+<!ENTITY appendix-packages      SYSTEM "appendix-packages.sgml">
 
 <!ENTITY bookindex  SYSTEM "bookindex.sgml">
 

doc/follow-new-primary.sgml

@@ -1,4 +1,9 @@
-<chapter id="follow-new-primary" xreflabel="Following a new primary">
+<chapter id="follow-new-primary">
+ <indexterm>
+  <primary>Following a new primary</primary>
+  <seealso>repmgr standby follow</seealso>
+ </indexterm>
+
  <title>Following a new primary</title>
  <para>
    Following the failure or removal of the replication cluster's existing primary
@@ -22,7 +27,8 @@
   </programlisting>
  </para>
  <para>
-   The standby is now replicating from the new primary and `repmgr cluster show`
+   The standby is now replicating from the new primary and
+   <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>
    output reflects this:
    <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show

doc/install-packages.sgml

@@ -1,32 +1,249 @@
 <sect1 id="installation-packages" xreflabel="Installing from packages">
  <title>Installing &repmgr; from packages</title>
  <para>
-We recommend installing `repmgr` using the available packages for your
-system.
+  We recommend installing &repmgr; using the available packages for your
+  system.
  </para>
 
- <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, Fedora and CentOS">
-   <title>RedHat/Fedora/CentOS</title>
-   <para>
-     RPM packages for `repmgr` are available via Yum through
-     the PostgreSQL Global Development Group RPM repository
-     ( <ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</>).
-     Follow the instructions for your distribution (RedHat, CentOS,
-     Fedora, etc.) and architecture as detailed at yum.postgresql.org.
-   </para>
-   <para>
-     2ndQuadrant also provides its own RPM packages which are made available
-     at the same time as each `repmgr` release, as it can take some days for
-     them to become available via the main PGDG repository. See here for details:
-     <ulink url="http://repmgr.org/yum-repository.html">http://repmgr.org/yum-repository.html</>
-   </para>
- </sect2>
- <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
-  <title>Debian/Ubuntu</title>
-  <para>.deb packages for `repmgr` are available from the
-  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</> ).
-  Instructions can be found in the APT section of the PostgreSQL Wiki
-  (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</> ).
+ <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, CentOS and Fedora">
+
+  <indexterm>
+   <primary>installation</primary>
+   <secondary>on Red Hat/CentOS/Fedora etc.</secondary>
+  </indexterm>
+
+  <title>RedHat/CentOS/Fedora</title>
+  <para>
+	&repmgr; RPM packages for RedHat/CentOS variants and Fedora are available from the
+	<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+	<ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink>; see following
+	section for details.
   </para>
+  <para>
+   RPM packages for &repmgr; are also available via Yum through
+   the PostgreSQL Global Development Group RPM repository
+   (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</ulink>).
+   Follow the instructions for your distribution (RedHat, CentOS,
+   Fedora, etc.) and architecture as detailed there. Note that it can take some days
+   for new &repmgr; packages to become available via the this repository.
+  </para>
+  <note>
+    <para>
+      &repmgr; packages are designed to be compatible with the community-provided PostgreSQL packages.
+      They may not work with vendor-specific packages such as those provided by RedHat for RHEL
+      customers, as the filesystem layout may be different to the community RPMs.
+      Please contact your support vendor for assistance.
+    </para>
+  </note>
+
+  <para>
+    For more information on the package contents, including details of installation
+    paths and relevant <link linkend="configuration-service-commands">service commands</link>,
+    see the appendix section <xref linkend="packages-centos">.
+  </para>
+
+
+  <sect3 id="installation-packages-redhat-2ndq">
+    <title>2ndQuadrant public RPM yum repository</title>
+
+	<note>
+	  <para>
+		<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink> previously provided a dedicated
+        &repmgr; repository at
+        <ulink url="http://packages.2ndquadrant.com/repmgr/">http://packages.2ndquadrant.com/repmgr/</ulink>.
+		This repository will be deprecated in a future release as it is now replaced by
+		the <ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink>
+		documented below.
+	  </para>
+	</note>
+
+    <para>
+      Beginning with <ulink url="https://repmgr.org/docs/4.0/release-4.0.5.html">repmgr 4.0.5</ulink>,
+      <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a dedicated <literal>yum</literal>
+	  <ulink url="https://rpm.2ndquadrant.com/">public RPM repository</ulink> for 2ndQuadrant software,
+	  including &repmgr;. We recommend using this for all future &repmgr; releases.
+	</para>
+	<para>
+	  General instructions for using this repository can be found on its
+	  <ulink url="https://rpm.2ndquadrant.com/">homepage</ulink>. Specific instructions
+	  for installing &repmgr; follow below.
+	</para>
+    <para>
+      <emphasis>Installation</emphasis>
+
+      <itemizedlist>
+		<listitem>
+		  <para>
+			Locate the repository RPM for your PostgreSQL version from the list at:
+			<ulink url="https://rpm.2ndquadrant.com/">https://rpm.2ndquadrant.com/</ulink>
+		  </para>
+		</listitem>
+
+        <listitem>
+          <para>
+            Install the repository RPM for your distribution and PostgreSQL version
+			(this enables the 2ndQuadrant repository as a source of &repmgr; packages).
+		  </para>
+		  <para>
+			For example, for PostgreSQL 10 on CentOS, execute:
+			<programlisting>
+sudo yum install https://rpm.2ndquadrant.com/site/content/2ndquadrant-repo-10-1-1.el7.noarch.rpm
+			</programlisting>
+		  </para>
+		  <para>
+			Verify that the repository is installed with:
+			<programlisting>
+sudo yum repolist</programlisting>
+			The output should contain two entries like this:
+			<programlisting>
+2ndquadrant-repo-10/7/x86_64         2ndQuadrant packages for PG10 for rhel 7 - x86_64           1
+2ndquadrant-repo-10-debug/7/x86_64   2ndQuadrant packages for PG10 for rhel 7 - x86_64 - Debug   1</programlisting>
+		  </para>
+		</listitem>
+
+        <listitem>
+          <para>
+            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            <programlisting>
+$ yum install repmgr10</programlisting>
+          </para>
+        </listitem>
+      </itemizedlist>
+    </para>
+
+    <para>
+      <emphasis>Compatibility with PGDG Repositories</emphasis>
+    </para>
+    <para>
+      The 2ndQuadrant &repmgr; yum repository packages use the same definitions and file system layout as the
+      main PGDG repository.
+    </para>
+    <para>
+      Normally <application>yum</application> will prioritize the repository with the most recent &repmgr; version.
+      Once the PGDG repository has been updated, it doesn't matter which repository
+      the packages are installed from.
+    </para>
+    <para>
+      To ensure the 2ndQuadrant repository is always prioritised, install <literal>yum-plugin-priorities</literal>
+      and set the repository priorities accordingly.
+    </para>
+
+    <para>
+      <emphasis>Installing a specific package version</emphasis>
+    </para>
+    <para>
+      To install a specific package version, execute <command>yum --showduplicates list</command>
+      for the package in question:
+      <programlisting>
+        [root@localhost ~]# yum --showduplicates list repmgr10
+        Loaded plugins: fastestmirror
+        Loading mirror speeds from cached hostfile
+         * base: ftp.iij.ad.jp
+         * extras: ftp.iij.ad.jp
+         * updates: ftp.iij.ad.jp
+        Available Packages
+		repmgr10.x86_64                       4.0.3-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.4-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.5-1.el7                          2ndquadrant-repo-10</programlisting>
+      then append the appropriate version number to the package name with a hyphen, e.g.:
+      <programlisting>
+        [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
+    </para>
+  </sect3>
  </sect2>
+
+ <sect2 id="installation-packages-debian" xreflabel="Installing from packages on Debian or Ubuntu">
+
+  <indexterm>
+   <primary>installation</primary>
+   <secondary>on Debian/Ubuntu etc.</secondary>
+  </indexterm>
+
+  <title>Debian/Ubuntu</title>
+  <para>.deb packages for &repmgr; are available from the
+  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
+  Instructions can be found in the APT section of the PostgreSQL Wiki
+  (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink>).
+  </para>
+  <para>
+    For more information on the package contents, including details of installation
+    paths and relevant <link linkend="configuration-service-commands">service commands</link>,
+    see the appendix section <xref linkend="packages-debian-ubuntu">.
+  </para>
+
+  <sect3 id="installation-packages-debian-ubuntu-2ndq">
+    <title>2ndQuadrant public apt repository for Debian/Ubuntu</title>
+
+    <para>
+      Beginning with <ulink url="https://repmgr.org/docs/4.0/release-4.0.5.html">repmgr 4.0.5</ulink>,
+      <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a
+	  <ulink url="https://apt.2ndquadrant.com/">public apt repository</ulink> for 2ndQuadrant software,
+	  including &repmgr;.
+	</para>
+	<para>
+	  General instructions for using this repository can be found on its
+	  <ulink url="https://apt.2ndquadrant.com/">homepage</ulink>. Specific instructions
+	  for installing &repmgr; follow below.
+	</para>
+
+    <para>
+      <emphasis>Installation</emphasis>
+
+      <itemizedlist>
+
+		<listitem>
+		  <para>
+			If not already present, install the  <application>apt-transport-https</application> package:
+			<programlisting>
+sudo apt-get install apt-transport-https</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Create <filename>/etc/apt/sources.list.d/2ndquadrant.list</filename> as follows:
+			<programlisting>
+sudo sh -c 'echo "deb https://apt.2ndquadrant.com/ $(lsb_release -cs)-2ndquadrant main" > /etc/apt/sources.list.d/2ndquadrant.list'</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Install the 2ndQuadrant <ulink url="https://apt.2ndquadrant.com/site/keys/9904CD4BD6BAF0C3.asc">repository key</ulink>:
+			<programlisting>
+sudo apt-get install curl ca-certificates
+curl https://apt.2ndquadrant.com/site/keys/9904CD4BD6BAF0C3.asc | sudo apt-key add -</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+			Update the package list
+			<programlisting>
+ sudo apt-get update</programlisting>
+		  </para>
+		</listitem>
+
+		<listitem>
+		  <para>
+            Install the &repmgr version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            <programlisting>
+$ apt-get install postgresql-10-repmgr</programlisting>
+		  </para>
+          <note>
+            <para>
+            For packages for PostgreSQL 9.6 and earlier, the package name includes
+            a period between major and minor version numbers, e.g.
+            <literal>postgresql-9.6-repmgr</literal>.
+            </para>
+          </note>
+		</listitem>
+
+	  </itemizedlist>
+
+	</para>
+
+  </sect3>
+ </sect2>
+
 </sect1>

doc/install-requirements.sgml

@@ -1,4 +1,10 @@
 <sect1 id="install-requirements" xreflabel="installation requirements">
+
+  <indexterm>
+   <primary>installation</primary>
+   <secondary>requirements</secondary>
+  </indexterm>
+
   <title>Requirements for installing repmgr</title>
   <para>
     repmgr is developed and tested on Linux and OS X, but should work on any
@@ -7,17 +13,14 @@
   </para>
 
   <para>
-   From version 4.0, repmgr is compatible with all PostgreSQL versions from 9.4, including PostgreSQL 10.
-  </para>
-  <para>
-   PostgreSQL 9.3 is supported by repmgr 3.3.
+   From version 4.0, repmgr is compatible with all PostgreSQL versions from 9.3, including PostgreSQL 10.
+   Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4.
   </para>
 
   <note>
-    <simpara>
-If upgrading from `repmgr 3`, please see the separate upgrade guide
-`doc/upgrading-from-repmgr3.md`.
-    </simpara>
+   <simpara>
+    If upgrading from &repmgr; 3.x, please see the section <xref linkend="upgrading-from-repmgr-3">.
+   </simpara>
   </note>
 
   <para>
@@ -26,42 +29,44 @@ If upgrading from `repmgr 3`, please see the separate upgrade guide
   </para>
 
   <para>
-   `repmgr` must be installed on each server in the replication cluster.
+   &repmgr; must be installed on each server in the replication cluster.
    If installing repmgr from packages, the package version must match the PostgreSQL
    version. If installing from source, repmgr must be compiled against the same
    major version.
   </para>
 
   <para>
-   A dedicated system user for `repmgr` is *not* required; as many `repmgr` and
-  `repmgrd` actions require direct access to the PostgreSQL data directory,
-  these commands should be executed by the `postgres` user.
+   A dedicated system user for &repmgr; is *not* required; as many &repmgr; and
+   <application>repmgrd</application> actions require direct access to the PostgreSQL data directory,
+   these commands should be executed by the <literal>postgres</literal> user.
   </para>
 
-
   <para>
-   Passwordless `ssh` connectivity between all servers in the replication cluster
+   Passwordless <command>ssh</command> connectivity between all servers in the replication cluster
    is not required, but is necessary in the following cases:
    <itemizedlist>
      <listitem>
-       <simpara>if you need `repmgr` to copy configuration files from outside the PostgreSQL
-  data directory (in which case `rsync` is also required)</simpara>
+       <simpara>if you need &repmgr; to copy configuration files from outside the PostgreSQL
+       data directory (in which case <command>rsync</command> is also required)</simpara>
      </listitem>
      <listitem>
-       <simpara>to perform switchover operations</simpara>
+       <simpara>to perform <link linkend="performing-switchover">switchover operations</link></simpara>
      </listitem>
      <listitem>
-       <simpara>when executing `repmgr cluster matrix` and `repmgr cluster crosscheck`</simpara>
+       <simpara>
+        when executing <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command>
+        and <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command>
+       </simpara>
      </listitem>
    </itemizedlist>
   </para>
 
   <tip>
    <simpara>
-    We recommend using a session multiplexer utility such as `screen` or
-    `tmux` when performing long-running actions (such as cloning a database)
-    on a remote server - this will ensure the `repmgr` action won't be prematurely
-    terminated if your `ssh` session to the server is interrupted or closed.
+    We recommend using a session multiplexer utility such as <command>screen</command> or
+    <command>tmux</command> when performing long-running actions (such as cloning a database)
+    on a remote server - this will ensure the &repmgr; action won't be prematurely
+    terminated if your <command>ssh</command> session to the server is interrupted or closed.
     </simpara>
   </tip>
  </sect1>

doc/install-source.sgml

@@ -1,4 +1,9 @@
 <sect1 id="installation-source" xreflabel="Installing from source code">
+  <indexterm>
+   <primary>installation</primary>
+   <secondary>from source</secondary>
+  </indexterm>
+
  <title>Installing &repmgr; from source</title>
 
  <sect2 id="installation-source-prereqs">
@@ -25,8 +30,7 @@
       building PostgreSQL with:
       <programlisting>
        sudo apt-get update
-       sudo apt-get build-dep postgresql-9.6
-      </programlisting>
+       sudo apt-get build-dep postgresql-9.6</programlisting>
       </para>
     </listitem>
     <listitem>
@@ -39,8 +43,7 @@
        sudo yum check-update
        sudo yum groupinstall "Development Tools"
        sudo yum install yum-utils openjade docbook-dtds docbook-style-dsssl docbook-style-xsl
-       sudo yum-builddep postgresql96
-      </programlisting>
+       sudo yum-builddep postgresql96</programlisting>
      </para>
     </listitem>
    </itemizedlist>
@@ -77,14 +80,13 @@
    </para>
 
    <para>
-    There are also tags for each &repmgr; release, e.g. <filename>REL4_0_STABLE</filename>.
+    There are also tags for each &repmgr; release, e.g. <filename>4.0.5</filename>.
    </para>
 
    <para>
     Clone the source code using <application>git</application>:
     <programlisting>
-     git clone https://github.com/2ndQuadrant/repmgr
-    </programlisting>
+     git clone https://github.com/2ndQuadrant/repmgr</programlisting>
    </para>
 
    <para>
@@ -129,11 +131,45 @@
    To installing &repmgr; from source, simply execute:
 
    <programlisting>
-    ./configure && make install
-   </programlisting>
+    ./configure && make install</programlisting>
 
-   Ensure `pg_config` for the target PostgreSQL version is in `$PATH`.
+   Ensure <command>pg_config</command> for the target PostgreSQL version is in
+   <varname>$PATH</varname>.
   </para>
  </sect2>
 
+
+
+ <sect2 id="installation-build-repmgr-docs">
+   <title>Building &repmgr; documentation</title>
+   <para>
+    The &repmgr; documentation is (like the main PostgreSQL project)
+    written in DocBook format. To build it locally as HTML, you'll need to
+    install the required packages as described in the
+    <ulink url="https://www.postgresql.org/docs/9.6/static/docguide-toolsets.html">
+      PostgreSQL documentation</ulink> then execute:
+   <programlisting>
+    ./configure && make install-doc</programlisting>
+   </para>
+   <para>
+     The generated HTML files will be placed in the <filename>doc/html</filename>
+     subdirectory of your source tree.
+   </para>
+
+   <para>
+     To build the documentation as a single HTML file, execute:
+   <programlisting>
+    cd doc/ && make repmgr.html</programlisting>
+   </para>
+
+   <note>
+     <simpara>
+       Due to changes in PostgreSQL's documentation build system from PostgreSQL 10,
+       the documentation can currently only be built agains PostgreSQL 9.6 or earlier.
+       This limitation will be fixed when time and resources permit.
+     </simpara>
+   </note>
+ </sect2>
+
+
 </sect1>

doc/install.sgml

@@ -1,4 +1,8 @@
 <chapter id="installation" xreflabel="Installation">
+ <indexterm>
+  <primary>installation</primary>
+ </indexterm>
+
  <title>Installation</title>
 
  <para>

doc/legal.sgml

@@ -1,9 +1,9 @@
-<!-- doc/src/sgml/legal.sgml -->
+<!-- doc/legal.sgml -->
 
 <date>2017</date>
 
 <copyright>
- <year>2010-2017</year>
+ <year>2010-2018</year>
  <holder>2ndQuadrant, Ltd.</holder>
 </copyright>
 
@@ -11,10 +11,27 @@
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2017
-  by 2ndQuadrant, Ltd.
+  <productname>repmgr</productname> is Copyright &copy; 2010-2018
+  by 2ndQuadrant, Ltd. All rights reserved.
  </para>
 
- <para>add license</para>
+ <para>
+   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
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+ </para>
+ <para>
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+ </para>
+ <para>
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see
+   <ulink url="https://www.gnu.org/licenses/">https://www.gnu.org/licenses/</ulink>
+   to obtain one.
+ </para>
 
 </legalnotice>

doc/overview.sgml

@@ -2,9 +2,15 @@
  <title>repmgr overview</title>
 
  <para>
-  This chapter provides a high-level overview of repmgr's components and functionality.
+  This chapter provides a high-level overview of &repmgr;'s components and
+  functionality.
  </para>
  <sect1 id="repmgr-concepts" xreflabel="Concepts">
+
+  <indexterm>
+    <primary>concepts</primary>
+  </indexterm>
+
   <title>Concepts</title>
 
   <para>
@@ -15,13 +21,13 @@
    streaming replication</>.
   </para>
   <para>
-   The following terms are used throughout the `repmgr` documentation.
+   The following terms are used throughout the &repmgr; documentation.
    <variablelist>
     <varlistentry>
      <term>replication cluster</term>
      <listitem>
       <simpara>
-       In the `repmgr` documentation, "replication cluster" refers to the network
+       In the &repmgr; documentation, "replication cluster" refers to the network
        of PostgreSQL servers connected by streaming replication.
       </simpara>
      </listitem>
@@ -31,7 +37,7 @@
      <term>node</term>
      <listitem>
       <simpara>
-       A node is a server within a replication cluster.
+       A node is a single PostgreSQL server within a replication cluster.
       </simpara>
      </listitem>
     </varlistentry>
@@ -41,7 +47,7 @@
      <listitem>
       <simpara>
        The node a standby server connects to, in order to receive streaming replication.
-       This is either the primary server or in the case of cascading replication, another
+       This is either the primary server, or in the case of cascading replication, another
        standby.
       </simpara>
      </listitem>
@@ -52,7 +58,7 @@
      <listitem>
       <simpara>
        This is the action which occurs if a primary server fails and a suitable standby
-       is  promoted as the new primary. The `repmgrd` daemon supports automatic failover
+       is  promoted as the new primary. The <application>repmgrd</application> daemon supports automatic failover
        to minimise downtime.
       </simpara>
      </listitem>
@@ -66,7 +72,7 @@
        it's necessary to take a primary server offline; in this case a controlled
        switchover is necessary, whereby a suitable standby is promoted and the
        existing primary removed from the replication cluster in a controlled manner.
-       The `repmgr` command line client provides this functionality.
+       The &repmgr; command line client provides this functionality.
       </simpara>
      </listitem>
     </varlistentry>
@@ -82,13 +88,37 @@
       </simpara>
      </listitem>
     </varlistentry>
+   <varlistentry id="witness-server">
+     <term>witness server</term>
+     <listitem>
+      <para>
+        &repmgr; provides functionality to set up a so-called "witness server" to
+        assist in determining a new primary server in a failover situation with more
+        than one standby. The witness server itself is not part of the replication
+        cluster, although it does contain a copy of the repmgr metadata schema.
+      </para>
+      <para>
+        The purpose of a witness server is to provide a "casting vote" where servers
+        in the replication cluster are split over more than one location. In the event
+        of a loss of connectivity between locations, the presence or absence of
+        the witness server will decide whether a server at that location is promoted
+        to primary; this is to prevent a "split-brain" situation where an isolated
+        location interprets a network outage as a failure of the (remote) primary and
+        promotes a (local) standby.
+      </para>
+      <para>
+        A witness server only needs to be created if <application>repmgrd</application>
+        is in use.
+      </para>
+     </listitem>
+    </varlistentry>
    </variablelist>
   </para>
  </sect1>
  <sect1 id="repmgr-components" xreflabel="Components">
   <title>Components</title>
   <para>
-  `repmgr` is a suite of open-source tools to manage replication and failover
+  &repmgr; is a suite of open-source tools to manage replication and failover
   within a cluster of PostgreSQL servers. It supports and enhances PostgreSQL's
   built-in streaming replication, which provides a single read/write primary server
   and one or more read-only standbys containing near-real time copies of the primary
@@ -147,11 +177,12 @@
  <sect1 id="repmgr-user-metadata" xreflabel="Repmgr user and metadata">
   <title>Repmgr user and metadata</title>
   <para>
-   In order to effectively manage a replication cluster, `repmgr` needs to store
+   In order to effectively manage a replication cluster, &repmgr; needs to store
    information about the servers in the cluster in a dedicated database schema.
-   This schema is automatically by the `repmgr` extension, which is installed
-   during the first step in initialising a `repmgr`-administered cluster
-   (`repmgr primary register`) and contains the following objects:
+   This schema is automatically created by the &repmgr; extension, which is installed
+   during the first step in initializing a &repmgr;-administered cluster
+   (<command><link linkend="repmgr-primary-register">repmgr primary register</link></command>)
+   and contains the following objects:
    <variablelist>
     <varlistentry>
      <term>Tables</term>
@@ -159,14 +190,15 @@
       <para>
        <itemizedlist>
         <listitem>
-          <simpara>repmgr.events: records events of interest</simpara>
+          <simpara><literal>repmgr.events</literal>: records events of interest</simpara>
         </listitem>
         <listitem>
-          <simpara>repmgr.nodes: connection and status information for each server in the
+          <simpara><literal>repmgr.nodes</literal>: connection and status information for each server in the
     replication cluster</simpara>
         </listitem>
         <listitem>
-          <simpara>repmgr.monitoring_history: historical standby monitoring information written by `repmgrd`</simpara>
+          <simpara><literal>repmgr.monitoring_history</literal>: historical standby monitoring information
+            written by <application>repmgrd</application></simpara>
         </listitem>
        </itemizedlist>
       </para>
@@ -178,12 +210,12 @@
       <para>
        <itemizedlist>
         <listitem>
-          <simpara>repmgr.show_nodes: based on the table `repl_nodes`, additionally showing the
-     name of the server's upstream node</simpara>
+          <simpara>repmgr.show_nodes: based on the table <literal>repmgr.nodes</literal>, additionally showing the
+           name of the server's upstream node</simpara>
         </listitem>
         <listitem>
-          <simpara>repmgr.replication_status: when `repmgrd`'s monitoring is enabled, shows current monitoring
-    status for each standby.</simpara>
+          <simpara>repmgr.replication_status: when <application>repmgrd</application>'s monitoring is enabled, shows
+            current monitoring status for each standby.</simpara>
         </listitem>
        </itemizedlist>
       </para>
@@ -193,16 +225,16 @@
   </para>
 
   <para>
-   The `repmgr` metadata schema can be stored in an existing database or in its own
-   dedicated database. Note that the `repmgr` metadata schema cannot reside on a database
-   server which is not part of the replication cluster managed by `repmgr`.
+   The &repmgr; metadata schema can be stored in an existing database or in its own
+   dedicated database. Note that the &repmgr; metadata schema cannot reside on a database
+   server which is not part of the replication cluster managed by &repmgr;.
   </para>
   <para>
-   A database user must be available for `repmgr` to access this database and perform
+   A database user must be available for &repmgr; to access this database and perform
    necessary changes. This user does not need to be a superuser, however some operations
-   such as initial installation of the `repmgr` extension will require a superuser
+   such as initial installation of the &repmgr; extension will require a superuser
    connection (this can be specified where required with the command line option
-   `--superuser`).
+   <literal>--superuser</literal>).
   </para>
  </sect1>
 

doc/promoting-standby.sgml

@@ -1,4 +1,8 @@
 <chapter id="promoting-standby" xreflabel="Promoting a standby">
+ <indexterm>
+   <primary>promoting a standby</primary>
+   <seealso>repmgr standby promote</seealso>
+ </indexterm>
  <title>Promoting a standby server with repmgr</title>
  <para>
    If a primary server fails or needs to be removed from the replication cluster,

doc/quickstart.sgml

@@ -5,12 +5,17 @@
   This section gives a quick introduction to &repmgr;, including setting up a
   sample &repmgr; installation and a basic replication cluster.
  </para>
-
  <para>
-  These instructions are not suitable for a production install, as they may not
-  take into account security considerations, proper system administration
-  procedures etc..
+  These instructions for demonstration purposes and are not suitable for a production
+  install, as issues such as account security considerations, and system administration
+  best practices are omitted.
  </para>
+ <note>
+   <simpara>
+     To upgrade an existing &repmgr; 3.x installation, see section
+     <xref linkend="upgrading-from-repmgr-3">.
+   </simpara>
+ </note>
 
  <sect1 id="quickstart-prerequisites">
    <title>Prerequisites for setting up a basic replication cluster with &repmgr;</title>
@@ -98,11 +103,11 @@
     # ignores archiving. Use something more sensible.
     archive_command = '/bin/true'
 
-    # If you have configured `pg_basebackup_options`
-    # in `repmgr.conf` to include the setting `--xlog-method=fetch` (from
-    # PostgreSQL 10 `--wal-method=fetch`), *and* you have not set
-    # `restore_command` in `repmgr.conf`to fetch WAL files from another
-    # source such as Barman, you'll need to set `wal_keep_segments` to a
+    # If you have configured "pg_basebackup_options"
+    # in "repmgr.conf" to include the setting "--xlog-method=fetch" (from
+    # PostgreSQL 10 "--wal-method=fetch"), *and* you have not set
+    # "restore_command" in "repmgr.conf"to fetch WAL files from another
+    # source such as Barman, you'll need to set "wal_keep_segments" to a
     # high enough value to ensure that all WAL files generated while
     # the standby is being cloned are retained until the standby starts up.
     #
@@ -116,6 +121,11 @@
      <command>include 'postgresql.replication.conf</command>.
     </simpara>
    </tip>
+   <para>
+     Additionally, if you are intending to use <application>pg_rewind</application>,
+     and the cluster was not initialised using data checksums, you may want to consider enabling
+     <varname>wal_log_hints</varname>; for more details see <xref linkend="repmgr-node-rejoin-pg-rewind">.
+   </para>
  </sect1>
 
  <sect1 id="quickstart-repmgr-user-database">
@@ -286,7 +296,7 @@
     slot_name        |
     config_file      | /etc/repmgr.conf</programlisting>
   <para>
-    Each server in the replication cluster will have its own record. If <command>repmgrd</command>
+    Each server in the replication cluster will have its own record. If <application>repmgrd</application>
     is in use, the fields <literal>upstream_node_id</literal>, <literal>active</literal> and
     <literal>type</literal> will be updated when the node's status or role changes.
   </para>
@@ -301,11 +311,10 @@
    (and possibly <literal>data_directory</literal>) adjusted accordingly, e.g.:
   </para>
   <programlisting>
-    node=2
+    node_id=2
     node_name=node2
     conninfo='host=node2 user=repmgr dbname=repmgr connect_timeout=2'
-    data_directory='/var/lib/postgresql/data'
-  </programlisting>
+    data_directory='/var/lib/postgresql/data'</programlisting>
   <para>
    Use the <command>--dry-run</command> option to check the standby can be cloned:
   </para>

doc/repmgr-cluster-cleanup.sgml

@@ -1,23 +1,41 @@
-<chapter id="repmgr-cluster-cleanup" xreflabel="repmgr cluster cleanup">
+<refentry id="repmgr-cluster-cleanup">
   <indexterm>
     <primary>repmgr cluster cleanup</primary>
   </indexterm>
-  <title>repmgr cluster cleanup</title>
-  <para>
-   Purges monitoring history from the <literal>repmgr.monitoring_history</literal> table to
-   prevent excessive table growth. Use the <literal>-k/--keep-history</literal> to specify the
-   number of days of monitoring history to retain. This command can be used
-   manually or as a cronjob.
-  </para>
-  <para>
-   This command requires a valid <filename>repmgr.conf</filename> file for the node on which it is
-   executed; no additional arguments are required.
-  </para>
-  <note>
-   <simpara>
-    Monitoring history will only be written if <command>repmgrd</command> is active, and
-    <varname>monitoring_history</varname> is set to <literal>true</literal> in
-    <filename>repmgr.conf</filename>.
-   </simpara>
-  </note>
-</chapter>
+ <refmeta>
+    <refentrytitle>repmgr cluster cleanup</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr cluster cleanup</refname>
+    <refpurpose>purge monitoring history</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Purges monitoring history from the <literal>repmgr.monitoring_history</literal> table to
+      prevent excessive table growth. Use the <literal>-k/--keep-history</literal> to specify the
+      number of days of monitoring history to retain. This command can be used
+      manually or as a cronjob.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Usage</title>
+    <para>
+      This command requires a valid <filename>repmgr.conf</filename> file for the node on which it is
+      executed; no additional arguments are required.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Notes</title>
+
+    <para>
+      Monitoring history will only be written if <application>repmgrd</application> is active, and
+      <varname>monitoring_history</varname> is set to <literal>true</literal> in
+      <filename>repmgr.conf</filename>.
+    </para>
+  </refsect1>
+</refentry>

doc/repmgr-cluster-crosscheck.sgml

@@ -1,15 +1,27 @@
-<chapter id="repmgr-cluster-crosscheck" xreflabel="repmgr cluster crosscheck">
+<refentry id="repmgr-cluster-crosscheck">
   <indexterm>
     <primary>repmgr cluster crosscheck</primary>
   </indexterm>
-  <title>repmgr cluster crosscheck</title>
-  <para>
-    <command>repmgr cluster crosscheck</command> is similar to <xref linkend="repmgr-cluster-matrix">,
-    but cross-checks connections between each combination of nodes. In "Example 3" in
-    <xref linkend="repmgr-cluster-matrix"> we have no information about the state of <literal>node3</literal>.
-    However by running <command>repmgr cluster crosscheck</command> it's possible to get a better
-    overview of the cluster situation:
-    <programlisting>
+
+
+  <refmeta>
+    <refentrytitle>repmgr cluster crosscheck</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr cluster crosscheck</refname>
+    <refpurpose>cross-checks connections between each combination of nodes</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr cluster crosscheck</command> is similar to <xref linkend="repmgr-cluster-matrix">,
+        but cross-checks connections between each combination of nodes. In "Example 3" in
+        <xref linkend="repmgr-cluster-matrix"> we have no information about the state of <literal>node3</literal>.
+        However by running <command>repmgr cluster crosscheck</command> it's possible to get a better
+        overview of the cluster situation:
+          <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster crosscheck
 
     Name   | Id |  1 |  2 |  3
@@ -17,12 +29,43 @@
      node1 |  1 |  * |  * |  x
      node2 |  2 |  * |  * |  *
      node3 |  3 |  * |  * |  *</programlisting>
-  </para>
-  <para>
-   What happened is that <command>repmgr cluster crosscheck</command> merged its own
-   <command>repmgr cluster matrix</command> with the <command>repmgr cluster matrix</command>
-   output from <literal>node2</literal>; the latter is able to connect to <literal>node3</literal>
-   and therefore determine the state of outbound connections from that node.
-  </para>
-</chapter>
+    </para>
+    <para>
+      What happened is that <command>repmgr cluster crosscheck</command> merged its own
+      <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command> with the
+      <command>repmgr cluster matrix</command> output from <literal>node2</literal>; the latter is
+      able to connect to <literal>node3</literal>
+      and therefore determine the state of outbound connections from that node.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Exit codes</title>
+    <para>
+      Following exit codes can be emitted by <command>repmgr cluster crosscheck</command>:
+    </para>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>SUCCESS (0)</option></term>
+        <listitem>
+          <para>
+            The check completed successfully and all nodes are reachable.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_CLUSTER_CHECK (25)</option></term>
+        <listitem>
+          <para>
+            One or more nodes could not be reached.
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
+</refentry>
 

doc/repmgr-cluster-event.sgml

@@ -1,37 +1,63 @@
-<chapter id="repmgr-cluster-event" xreflabel="repmgr cluster event">
- <indexterm>
-  <primary>repmgr cluster event</primary>
- </indexterm>
- <title>repmgr cluster event</title>
- <para>
-  This outputs a formatted list of cluster events, as stored in the
-  <literal>repmgr.events</literal> table. Output is in reverse chronological order, and
-  can be filtered with the following options:
- <itemizedlist spacing="compact" mark="bullet">
-  <listitem>
-    <simpara><literal>--all</literal>: outputs all entries</simpara>
-  </listitem>
-  <listitem>
-    <simpara><literal>--limit</literal>: set the maximum number of entries to output (default: 20)</simpara>
-  </listitem>
-  <listitem>
-    <simpara><literal>--node-id</literal>: restrict entries to node with this ID</simpara>
-  </listitem>
-  <listitem>
-    <simpara><literal>--node-name</literal>: restrict entries to node with this name</simpara>
-  </listitem>
-  <listitem>
-    <simpara><literal>--event</literal>: filter specific event</simpara>
-  </listitem>
- </itemizedlist>
- </para>
- <para>
-  Example:
-  <programlisting>
+<refentry id="repmgr-cluster-event">
+  <indexterm>
+    <primary>repmgr cluster event</primary>
+  </indexterm>
+
+  <refmeta>
+    <refentrytitle>repmgr cluster event</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr cluster event</refname>
+    <refpurpose>output a formatted list of cluster events</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Outputs a formatted list of cluster events, as stored in the <literal>repmgr.events</literal> table.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Usage</title>
+
+    <para>
+      Output is in reverse chronological order, and
+      can be filtered with the following options:
+      <itemizedlist spacing="compact" mark="bullet">
+        <listitem>
+          <simpara><literal>--all</literal>: outputs all entries</simpara>
+        </listitem>
+        <listitem>
+          <simpara><literal>--limit</literal>: set the maximum number of entries to output (default: 20)</simpara>
+        </listitem>
+        <listitem>
+          <simpara><literal>--node-id</literal>: restrict entries to node with this ID</simpara>
+        </listitem>
+        <listitem>
+          <simpara><literal>--node-name</literal>: restrict entries to node with this name</simpara>
+        </listitem>
+        <listitem>
+          <simpara><literal>--event</literal>: filter specific event (see <xref linkend="event-notifications"> for a full list)</simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+    <para>
+      The "Details" column can be omitted by providing <literal>--terse</literal>.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
+      <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster event --event=standby_register
      Node ID | Name  | Event            | OK | Timestamp           | Details
     ---------+-------+------------------+----+---------------------+--------------------------------
      3       | node3 | standby_register | t  | 2017-08-17 10:28:55 | standby registration succeeded
      2       | node2 | standby_register | t  | 2017-08-17 10:28:53 | standby registration succeeded</programlisting>
- </para>
-</chapter>
+    </para>
+  </refsect1>
+</refentry>

doc/repmgr-cluster-matrix.sgml

@@ -1,27 +1,44 @@
-<chapter id="repmgr-cluster-matrix" xreflabel="repmgr cluster matrix">
+<refentry id="repmgr-cluster-matrix">
   <indexterm>
     <primary>repmgr cluster matrix</primary>
   </indexterm>
-  <title>repmgr cluster matrix</title>
-  <para>
-    <command>repmgr cluster matrix</command> runs  <command>repmgr cluster show</command> on each
-    node and arranges the results in a matrix, recording success or failure.
-  </para>
-  <para>
-    <command>repmgr cluster matrix</command> requires a valid <filename>repmgr.conf</filename>
-    file on each node.  Additionally passwordless `ssh` connections are required between
-    all nodes.
-  </para>
-  <para>
+
+  <refmeta>
+    <refentrytitle>repmgr cluster matrix</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr cluster matrix</refname>
+    <refpurpose>
+      runs repmgr cluster show on each node and summarizes output
+    </refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr cluster matrix</command> runs <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command> on each
+      node and arranges the results in a matrix, recording success or failure.
+    </para>
+    <para>
+      <command>repmgr cluster matrix</command> requires a valid <filename>repmgr.conf</filename>
+      file on each node. Additionally, passwordless <command>ssh</command> connections are required between
+      all nodes.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
     Example 1 (all nodes up):
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster matrix
 
     Name   | Id |  1 |  2 |  3
     -------+----+----+----+----
-    node1 |  1 |  * |  * |  *
-    node2 |  2 |  * |  * |  *
-    node3 |  3 |  * |  * |  *</programlisting>
+     node1 |  1 |  * |  * |  *
+     node2 |  2 |  * |  * |  *
+     node3 |  3 |  * |  * |  *</programlisting>
   </para>
   <para>
     Example 2 (<literal>node1</literal> and <literal>node2</literal> up, <literal>node3</literal> down):
@@ -46,7 +63,7 @@
   <para>
     The other two nodes are up; the corresponding rows have <literal>x</literal> in the
     column corresponding to <literal>node3</literal>, meaning that inbound connections to
-    that node have failed, and `*` in the columns corresponding to
+    that node have failed, and <literal>*</literal> in the columns corresponding to
     <literal>node1</literal> and <literal>node2</literal>, meaning that inbound connections
     to these nodes have succeeded.
   </para>
@@ -79,5 +96,36 @@
     In this case, the <xref linkend="repmgr-cluster-crosscheck"> command will produce a more
     useful result.
   </para>
-</chapter>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Exit codes</title>
+    <para>
+      Following exit codes can be emitted by <command>repmgr cluster matrix</command>:
+    </para>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>SUCCESS (0)</option></term>
+        <listitem>
+          <para>
+            The check completed successfully and all nodes are reachable.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_CLUSTER_CHECK (25)</option></term>
+        <listitem>
+          <para>
+            One or more nodes could not be reached.
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
+</refentry>
 

doc/repmgr-cluster-show.sgml

@@ -1,22 +1,46 @@
-<chapter id="repmgr-cluster-show" xreflabel="repmgr cluster show">
+<refentry id="repmgr-cluster-show">
   <indexterm>
     <primary>repmgr cluster show</primary>
   </indexterm>
-  <title>repmgr cluster show</title>
-  <para>
-    Displays information about each active node in the replication cluster. This
-    command polls each registered server and shows its role (<literal>primary</literal> /
-    <literal>standby</literal> / <literal>bdr</literal>) and status. It polls each server
-    directly and can be run on any node in the cluster; this is also useful when analyzing
-    connectivity from a particular node.
-  </para>
-  <para>
-    This command requires either a valid <filename>repmgr.conf</filename> file or a database
-    connection string to one of the registered nodes; no  additional arguments are needed.
-  </para>
 
-  <para>
-    Example:
+  <refmeta>
+    <refentrytitle>repmgr cluster show</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr cluster show</refname>
+    <refpurpose>display information about each registered node in the replication cluster</refpurpose>
+  </refnamediv>
+
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Displays information about each registered node in the replication cluster. This
+      command polls each registered server and shows its role (<literal>primary</literal> /
+      <literal>standby</literal> / <literal>bdr</literal>) and status. It polls each server
+      directly and can be run on any node in the cluster; this is also useful when analyzing
+      connectivity from a particular node.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Execution</title>
+    <para>
+      This command requires either a valid <filename>repmgr.conf</filename> file or a database
+      connection string to one of the registered nodes; no additional arguments are needed.
+    </para>
+
+    <para>
+      To show database connection errors when polling nodes, run the command in
+      <literal>--verbose</literal> mode.
+    </para>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
 
@@ -26,42 +50,67 @@
      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. <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, e.g.:
+      <programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster show
 
-  <para>
-    To show database connection errors when polling nodes, run the command in
-    <literal>--verbose</literal> mode.
-  </para>
-  <para>
-    The `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:
-    <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>
+  </refsect1>
+
+  <refsect1>
+    <title>Options</title>
+    <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:
+      <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>
-      <simpara>
-        availability (0 = available, -1 = unavailable)
-      </simpara>
-      <simpara>
-        recovery state (0 = not in recovery, 1 = in recovery, -1 = unknown)
-      </simpara>
-     </listitem>
-    </itemizedlist>
-  </para>
+    </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>
+  </refsect1>
 
-  <para>
-   Note that the 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>
-</chapter>
+</refentry>

doc/repmgr-node-check.sgml

@@ -1,32 +1,48 @@
-<chapter id="repmgr-node-check" xreflabel="repmgr node check">
+<refentry id="repmgr-node-check">
   <indexterm>
     <primary>repmgr node check</primary>
   </indexterm>
-  <title>repmgr node check</title>
-  <para>
-    Performs some health checks on a node from a replication perspective.
-    This command must be run on the local node.
-  </para>
-  <para>
-   Sample output (execute <command>repmgr node check</command>):
-   <programlisting>
+
+  <refmeta>
+    <refentrytitle>repmgr node check</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr node check</refname>
+    <refpurpose>performs some health checks on a node from a replication perspective</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Performs some health checks on a node from a replication perspective.
+      This command must be run on the local node.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
+      <programlisting>
+       $ repmgr -f /etc/repmgr.conf node check
        Node "node1":
             Server role: OK (node is primary)
             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 replication slots)
-   </programlisting>
-  </para>
-  <para>
-   Additionally each check can be performed individually by supplying
-   an additional command line parameter, e.g.:
-   <programlisting>
-     $ repmgr node check --role
-     OK (node is primary)
-   </programlisting>
-  </para>
-  <para>
+            Replication slots: OK (node has no replication slots)</programlisting>
+    </para>
+  </refsect1>
+  <refsect1>
+    <title>Individual checks</title>
+    <para>
+      Each check can be performed individually by supplying
+      an additional command line parameter, e.g.:
+      <programlisting>
+        $ repmgr node check --role
+        OK (node is primary)</programlisting>
+    </para>
+    <para>
    Parameters for individual checks are as follows:
     <itemizedlist spacing="compact" mark="bullet">
 
@@ -63,8 +79,26 @@
 
     </itemizedlist>
   </para>
-  <para>
-   Individual checks can also be output in a Nagios-compatible format by additionally
-   providing the option <literal>--nagios</literal>.
-  </para>
-</chapter>
+  </refsect1>
+
+  <refsect1>
+    <title>Output format</title>
+    <para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <literal>--csv</literal>: generate output in CSV format (not available
+            for individual checks)
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <literal>--nagios</literal>: generate output in a Nagios-compatible format
+          </simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+  </refsect1>
+</refentry>

doc/repmgr-node-rejoin.sgml

@@ -1,13 +1,233 @@
-<chapter id="repmgr-node-rejoin" xreflabel="repmgr node rejoin">
+<refentry id="repmgr-node-rejoin">
+
   <indexterm>
     <primary>repmgr node rejoin</primary>
   </indexterm>
-  <title>repmgr node rejoin</title>
-  <para>
-   Enables a dormant (stopped) node to be rejoined to the replication cluster.
-  </para>
-  <para>
-    This can optionally use <command>pg_rewind</command> to re-integrate a node which has diverged
-    from the rest of the cluster, typically a failed primary.
-  </para>
-</chapter>
+
+  <refmeta>
+    <refentrytitle>repmgr node rejoin</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr node rejoin</refname>
+    <refpurpose>rejoin a dormant (stopped) node to the replication cluster</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Enables a dormant (stopped) node to be rejoined to the replication cluster.
+    </para>
+    <para>
+      This can optionally use <application>pg_rewind</application> to re-integrate
+      a node which has diverged from the rest of the cluster, typically a failed primary.
+    </para>
+
+    <tip>
+      <para>
+        If the node is running and needs to be attached to the current primary, use
+        <xref linkend="repmgr-standby-follow">.
+      </para>
+    </tip>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Usage</title>
+
+    <para>
+      <programlisting>
+      repmgr node rejoin -d '$conninfo'</programlisting>
+
+      where <literal>$conninfo</literal> is the conninfo string of any reachable node in the cluster.
+      <filename>repmgr.conf</filename> for the stopped node *must* be supplied explicitly if not
+      otherwise available.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually execute the rejoin.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--force-rewind[=/path/to/pg_rewind]</option></term>
+        <listitem>
+          <para>
+            Execute <application>pg_rewind</application> if necessary.
+          </para>
+          <para>
+            It is only necessary to provide the <application>pg_rewind</application>
+            if using PostgreSQL 9.3 or 9.4, and <application>pg_rewind</application>
+            is not installed in the PostgreSQL <filename>bin</filename> directory.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--config-files</option></term>
+        <listitem>
+          <para>
+            comma-separated list of configuration files to retain after
+            executing <application>pg_rewind</application>.
+          </para>
+          <para>
+            Currently <application>pg_rewind</application> will overwrite
+            the local node's configuration files with the files from the source node,
+            so it's advisable to use this option to ensure they are kept.
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>--config-archive-dir</option></term>
+        <listitem>
+          <para>
+            Directory to temporarily store configuration files specified with
+            <option>--config-files</option>; default: <filename>/tmp</filename>.
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>-W/--no-wait</option></term>
+        <listitem>
+          <para>
+            Don't wait for the node to rejoin cluster.
+          </para>
+          <para>
+            If this option is supplied, &repmgr; will restart the node but
+            not wait for it to connect to the primary.
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>node_rejoin</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Notes</title>
+    <para>
+      Currently <command>repmgr node rejoin</command> can only be used to attach
+      a standby to the current primary, not another standby.
+    </para>
+    <para>
+      The node must have been shut down cleanly; if this was not the case, it will
+      need to be manually started (remove any existing <filename>recovery.conf</filename> file first)
+      until it has reached a consistent recovery point, then shut down cleanly.
+    </para>
+    <tip>
+      <para>
+        If <application>PostgreSQL</application> is started in single-user mode and
+        input is directed from <filename>/dev/null/</filename>, it will perform recovery
+        then immediately quit, and will then be in a state suitable for use by
+        <application>pg_rewind</application>.
+        <programlisting>
+          rm -f /var/lib/pgsql/data/recovery.conf
+          postgres --single -D /var/lib/pgsql/data/ &lt; /dev/null</programlisting>
+      </para>
+    </tip>
+  </refsect1>
+
+  <refsect1 id="repmgr-node-rejoin-pg-rewind" xreflabel="Using pg_rewind">
+
+   <indexterm>
+      <primary>pg_rewind</primary>
+      <secondary>using with "repmgr node rejoin"</secondary>
+    </indexterm>
+
+    <title>Using <command>pg_rewind</command></title>
+    <para>
+      <command>repmgr node rejoin</command> can optionally use <command>pg_rewind</command> to re-integrate a
+      node which has diverged from the rest of the cluster, typically a failed primary.
+      <command>pg_rewind</command> is available in PostgreSQL 9.5 and later as part of the core distribution,
+      and can be installed from external sources for PostgreSQL 9.3 and 9.4.
+    </para>
+    <note>
+      <para>
+        <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/static/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
+      </para>
+    </note>
+
+    <para>
+      To have <command>repmgr node rejoin</command> use <command>pg_rewind</command> if required,
+      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>
+
+    <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=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-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=node1 dbname=repmgr user=repmgr'</programlisting>
+    <programlisting>
+    $ 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
+    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 1 is now attached to node 2</programlisting>
+    </para>
+
+  </refsect1>
+
+  <refsect1>
+    <title>See also</title>
+    <para>
+     <xref linkend="repmgr-standby-follow">
+    </para>
+  </refsect1>
+</refentry>

doc/repmgr-node-status.sgml

@@ -1,16 +1,30 @@
-
-<chapter id="repmgr-node-status" xreflabel="repmgr node status">
+<refentry id="repmgr-node-status">
   <indexterm>
     <primary>repmgr node status</primary>
   </indexterm>
-  <title>repmgr node status</title>
-  <para>
-   Displays an overview of a node's basic information and replication
-   status. This command must be run on the local node.
-  </para>
-  <para>
-   Sample output (execute <command>repmgr node status</command>):
-   <programlisting>
+
+  <refmeta>
+    <refentrytitle>repmgr node status</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr node status</refname>
+    <refpurpose>show overview of a node's basic information and replication status</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Displays an overview of a node's basic information and replication
+      status. This command must be run on the local node.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
+    <programlisting>
+        $ repmgr -f /etc/repmgr.conf node status
         Node "node1":
             PostgreSQL version: 10beta1
             Total data size: 30 MB
@@ -20,10 +34,28 @@
             Archive command: (none)
             Replication connections: 2 (of maximal 10)
             Replication slots: 0 (of maximal 10)
-            Replication lag: n/a
-   </programlisting>
-  </para>
-  <para>
-    See <xref linkend="repmgr-node-check"> to diagnose issues.
-  </para>
-</chapter>
+            Replication lag: n/a</programlisting>
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Output format</title>
+    <para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <literal>--csv</literal>: generate output in CSV format
+          </simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>See also</title>
+    <para>
+      See <xref linkend="repmgr-node-check"> to diagnose issues.
+    </para>
+  </refsect1>
+</refentry>

doc/repmgr-primary-register.sgml

@@ -1,18 +1,85 @@
-<chapter id="repmgr-primary-register" xreflabel="repmgr primary register">
-  <indexterm><primary>repmgr primary register</primary></indexterm>
-  <title>repmgr primary register</title>
-  <para>
-   <command>repmgr primary register</command> registers a primary node in a
-   streaming replication cluster, and configures it for use with repmgr, including
-   installing the &repmgr; extension. This command needs to be executed before any
-   standby nodes are registered.
-  </para>
-  <para>
-   Execute with the <literal>--dry-run</literal> option to check what would happen without
-   actually registering the primary.
-  </para>
-  <para>
-   <command>repmgr master register</command> can be used as an alias for
-   <command>repmgr primary register</command>.
-  </para>
-</chapter>
+<refentry id="repmgr-primary-register">
+  <indexterm>
+    <primary>repmgr primary register</primary>
+  </indexterm>
+
+  <refmeta>
+    <refentrytitle>repmgr primary register</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr primary register</refname>
+    <refpurpose>initialise a repmgr installation and register the primary node</refpurpose>
+  </refnamediv>
+
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr primary register</command> registers a primary node in a
+      streaming replication cluster, and configures it for use with repmgr, including
+      installing the &repmgr; extension. This command needs to be executed before any
+      standby nodes are registered.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Execution</title>
+    <para>
+      Execute with the <option>--dry-run</option> option to check what would happen without
+      actually registering the primary.
+    </para>
+    <para>
+      <command>repmgr master register</command> can be used as an alias for
+      <command>repmgr primary register</command>.
+    </para>
+
+    <note>
+    <para>
+      If providing the configuration file location with <option>-f/--config-file</option>,
+      avoid using a relative path, as &repmgr; stores the configuration file location
+      in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
+      <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
+        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>
+
+  <refsect1>
+
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually register the primary.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+       <term><option>-F</option>, <option>--force</option></term>
+        <listitem>
+          <para>
+            Overwrite an existing node record
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>primary_register</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr-primary-unregister.sgml

@@ -1,18 +1,74 @@
-<chapter id="repmgr-primary-unregister" xreflabel="repmgr primary unregister">
-  <indexterm><primary>repmgr primary unregister</primary></indexterm>
-  <title>repmgr primary unregister</title>
-  <para>
-   <command>repmgr primary register</command> unregisters an inactive primary node
-   from the &repmgr; metadata. This is typically when the primary has failed and is
-   being removed from the cluster after a new primary has been promoted.
-  </para>
-  <para>
-   Execute with the <literal>--dry-run</literal> option to check what would happen without
-   actually unregistering the node.
-  </para>
+<refentry id="repmgr-primary-unregister">
+  <indexterm>
+    <primary>repmgr primary unregister</primary>
+  </indexterm>
+  <refmeta>
+    <refentrytitle>repmgr primary unregister</refentrytitle>
+  </refmeta>
+  <refnamediv>
+    <refname>repmgr primary unregister</refname>
+    <refpurpose>unregister an inactive primary node</refpurpose>
+  </refnamediv>
 
-  <para>
-   <command>repmgr master unregister</command> can be used as an alias for
-   <command>repmgr primary unregister</command>/
-  </para>
-</chapter>
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr primary unregister</command> unregisters an inactive primary node
+      from the &repmgr; metadata. This is typically when the primary has failed and is
+      being removed from the cluster after a new primary has been promoted.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Execution</title>
+    <para>
+      <command>repmgr primary unregister</command> can be run on any active &repmgr; node,
+      with the ID of the node to unregister passed as <option>--node-id</option>.
+    </para>
+    <para>
+      Execute with the <literal>--dry-run</literal> option to check what would happen without
+      actually unregistering the node.
+    </para>
+
+    <para>
+      <command>repmgr master unregister</command> can be used as an alias for
+      <command>repmgr primary unregister</command>.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually unregister the primary.
+          </para>
+        </listitem>
+      </varlistentry>
+
+     <varlistentry>
+        <term><option>--node-id</option></term>
+        <listitem>
+          <para>
+            ID of the inactive primary to be unregistered.
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>primary_unregister</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr-standby-clone.sgml

@@ -1,25 +1,39 @@
-<chapter id="repmgr-standby-clone" xreflabel="repmgr standby clone">
+<refentry id="repmgr-standby-clone">
   <indexterm>
     <primary>repmgr standby clone</primary>
     <seealso>cloning</seealso>
   </indexterm>
-  <title>repmgr standby clone</title>
-  <para>
-   <command>repmgr standby clone</command> clones a PostgreSQL node from another
-   PostgreSQL node, typically the primary, but optionally from any other node in
-   the cluster or from Barman. It creates the <filename>recovery.conf</filename> file required
-   to attach the cloned node to the primary node (or another standby, if cascading replication
-   is in use).
-  </para>
-  <note>
-   <simpara>
-    <command>repmgr standby clone</command> does not start the standby, and after cloning
-    <command>repmgr standby register</command> must be executed to notify &repmgr; of its presence.
-   </simpara>
-  </note>
+
+  <refmeta>
+    <refentrytitle>repmgr standby clone</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby clone</refname>
+    <refpurpose>clone a PostgreSQL standby node from another PostgreSQL node</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr standby clone</command> clones a PostgreSQL node from another
+      PostgreSQL node, typically the primary, but optionally from any other node in
+      the cluster or from Barman. It creates the <filename>recovery.conf</filename> file required
+      to attach the cloned node to the primary node (or another standby, if cascading replication
+      is in use).
+    </para>
+    <note>
+      <simpara>
+        <command>repmgr standby clone</command> does not start the standby, and after cloning
+        a standby, the command <command>repmgr standby register</command> must be executed to
+        notify &repmgr; of its existence.
+      </simpara>
+    </note>
+
+  </refsect1>
 
 
-  <sect1 id="repmgr-standby-clone-config-file-copying" xreflabel="Copying configuration files">
+  <refsect1 id="repmgr-standby-clone-config-file-copying" xreflabel="Copying configuration files">
    <title>Handling configuration files</title>
 
    <para>
@@ -51,14 +65,78 @@
      configuration management tool such as Ansible, Chef, Puppet or Salt.
     </simpara>
    </tip>
-  </sect1>
+  </refsect1>
 
-  <sect1 id="repmgr-standby-clone-wal-management" xreflabel="Managing WAL during the cloning process">
+  <refsect1 id="repmgr-standby-clone-recovery-conf">
+   <indexterm>
+     <primary>recovery.conf</primary>
+     <secondary>customising with "repmgr standby clone"</secondary>
+   </indexterm>
+
+   <title>Customising recovery.conf</title>
+   <para>
+     By default, &repmgr; will create a minimal <filename>recovery.conf</filename>
+     containing following parameters:
+   </para>
+
+   <itemizedlist spacing="compact" mark="bullet">
+
+     <listitem>
+       <simpara><varname>standby_mode</varname> (always <literal>'on'</literal>)</simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>recovery_target_timeline</varname> (always <literal>'latest'</literal>)</simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>primary_conninfo</varname></simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>primary_slot_name</varname> (if replication slots in use)</simpara>
+     </listitem>
+
+   </itemizedlist>
+
+   <para>
+     The following additional parameters can be specified in <filename>repmgr.conf</filename>
+     for inclusion in <filename>recovery.conf</filename>:
+   </para>
+
+   <itemizedlist spacing="compact" mark="bullet">
+
+     <listitem>
+       <simpara><varname>restore_command</varname></simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>archive_cleanup_command</varname></simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>recovery_min_apply_delay</varname></simpara>
+     </listitem>
+
+   </itemizedlist>
+
+   <note>
+     <para>
+       We recommend using <ulink url="https://www.pgbarman.org/">Barman</ulink> to manage
+       WAL file archiving. For more details on combining &repmgr; and <application>Barman</application>,
+       in particular using <varname>restore_command</varname> to configure Barman as a backup source of
+       WAL files, see <xref linkend="cloning-from-barman">.
+     </para>
+   </note>
+
+  </refsect1>
+
+  <refsect1 id="repmgr-standby-clone-wal-management">
    <title>Managing WAL during the cloning process</title>
    <para>
     When initially cloning a standby, you will need to ensure
     that all required WAL files remain available while the cloning is taking
-    place. To ensure this happens when using the default `pg_basebackup` method,
+    place. To ensure this happens when using the default <command>pg_basebackup</command> method,
     &repmgr; will set <command>pg_basebackup</command>'s <literal>--xlog-method</literal>
     parameter to <literal>stream</literal>,
     which will ensure all WAL files generated during the cloning process are
@@ -86,6 +164,178 @@
       <literal>--wal-method</literal>.
     </simpara>
    </note>
-  </sect1>
-</chapter>
+  </refsect1>
+
+
+  <refsect1 id="repmgr-standby-create-recovery-conf">
+
+   <indexterm>
+     <primary>recovery.conf</primary>
+     <secondary>generating for a standby cloned by another method</secondary>
+   </indexterm>
+
+   <title>Using a standby cloned by another method</title>
+   <para>
+     &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
+     <command><ulink url="http://docs.pgbarman.org/release/2.4/#recover">barman recover</ulink></command> command).
+   </para>
+   <para>
+     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>.
+     This will create the <filename>recovery.conf</filename> file needed to attach
+     the node to its upstream, and will also create a replication slot on the
+     upstream node if required.
+   </para>
+   <para>
+     Note that the upstream node must be running. An existing
+     <filename>recovery.conf</filename> will not be overwritten unless the
+     <option>-F/--force</option> option is provided.
+   </para>
+   <para>
+     Execute <command>repmgr standby clone --recovery-conf-only --dry-run</command>
+     to check the prerequisites for creating the <filename>recovery.conf</filename> file,
+     and display the contents of the file without actually creating it.
+   </para>
+
+   <note>
+     <para>
+       <option>--recovery-conf-only</option> was introduced in &repmgr; <link linkend="release-4.0.4">4.0.4</link>.
+     </para>
+   </note>
+
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually clone the standby.
+          </para>
+          <para>
+            If <option>--recovery-conf-only</option> specified, the contents of
+            the generated <filename>recovery.conf</filename> file will be displayed
+            but the file itself not written.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-c, --fast-checkpoint</option></term>
+        <listitem>
+          <para>
+            Force fast checkpoint (not effective when cloning from Barman).
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--copy-external-config-files[={samepath|pgdata}]</option></term>
+        <listitem>
+          <para>
+            Copy configuration files located outside the data directory on the source
+            node to the same path on the standby (default) or to the
+            PostgreSQL data directory.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--no-upstream-connection</option></term>
+        <listitem>
+          <para>
+            When using Barman, do not connect to upstream node.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-R, --remote-user=USERNAME</option></term>
+        <listitem>
+          <para>
+            Remote system username for SSH operations (default: current local system username).
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option> --recovery-conf-only</option></term>
+        <listitem>
+          <para>
+            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr 4.0.4 and later.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--replication-user</option></term>
+        <listitem>
+          <para>
+            User to make replication connections with (optional, not usually required).
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--superuser</option></term>
+        <listitem>
+          <para>
+            If the &repmgr; user is not a superuser, the name of a valid superuser must
+            be provided with this option.
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>--upstream-conninfo</option></term>
+        <listitem>
+          <para>
+            <literal>primary_conninfo</literal> value to write in recovery.conf
+            when the intended upstream server does not yet exist.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--upstream-node-id</option></term>
+        <listitem>
+          <para>
+            ID of the upstream node to replicate from (optional, defaults to primary node)
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>--without-barman </option></term>
+        <listitem>
+          <para>
+            Do not use Barman even if configured.
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_clone</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>See also</title>
+    <para>
+      See <xref linkend="cloning-standbys"> for details about various aspects of cloning.
+    </para>
+  </refsect1>
+</refentry>
 

doc/repmgr-standby-follow.sgml

@@ -1,21 +1,116 @@
-<chapter id="repmgr-standby-follow" xreflabel="repmgr standby follow">
+<refentry id="repmgr-standby-follow">
   <indexterm>
     <primary>repmgr standby follow</primary>
   </indexterm>
-  <title>repmgr standby follow</title>
-  <para>
-   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>
-   This command will force a restart of the standby server, which must be
-   running. It can only be used to attach a standby to a new primary node.
-  </para>
-  <para>
-   To re-add an inactive node to the replication cluster, see
-   <xref linkend="repmgr-node-rejoin">
-  </para>
-</chapter>
+
+  <refmeta>
+    <refentrytitle>repmgr standby follow</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby follow</refname>
+    <refpurpose>attach a standby to a new primary</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      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>
+      This command will force a restart of the standby server, which must be
+      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
+		<xref linkend="repmgr-node-rejoin">.
+      </para>
+	</tip>
+
+	<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 primary.
+	</para>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
+      <programlisting>
+      $ repmgr -f /etc/repmgr.conf standby follow
+      INFO: setting node 3's primary to node 2
+      NOTICE: restarting server using "pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/postgres/data' restart"
+      waiting for server to shut down........ done
+      server stopped
+      waiting for server to start.... done
+      server started
+      NOTICE: STANDBY FOLLOW successful
+      DETAIL: node 3 is now attached to node 2</programlisting>
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually follow a new standby.
+          </para>
+          <important>
+            <para>
+              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>-w</option></term>
+        <term><option>--wait</option></term>
+        <listitem>
+          <para>
+            Wait for a primary to appear. &repmgr; will wait for up to
+            <varname>primary_follow_timeout</varname> seconds
+            (default: 60 seconds) to verify that the standby is following the new primary.
+            This value can be defined in <filename>repmgr.conf</filename>.
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <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 primary
+      being followed, <literal>%c</literal> with its <literal>conninfo</literal> string, and
+      <literal>%a</literal> with its node name.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>See also</title>
+    <para>
+     <xref linkend="repmgr-node-rejoin">
+    </para>
+  </refsect1>
+</refentry>
 

doc/repmgr-standby-promote.sgml

@@ -1,18 +1,60 @@
-<chapter id="repmgr-standby-promote" xreflabel="repmgr standby promote">
+<refentry id="repmgr-standby-promote">
   <indexterm>
     <primary>repmgr standby promote</primary>
   </indexterm>
-  <title>repmgr standby promote</title>
-  <para>
-   Promotes a standby to a primary if the current primary has failed. This
-   command requires a valid <filename>repmgr.conf</filename> file for the standby, either
-   specified explicitly  with <literal>-f/--config-file</literal> or located in a
-    default location; no additional arguments are required.
-  </para>
-  <para>
-   If the standby promotion succeeds, the server will not need to be
-   restarted. However any other standbys will need to follow the new server,
-   by using <xref linkend="repmgr-standby-follow">; if <command>repmgrd</command>
-   is active, it will handle this automatically.
-  </para>
-</chapter>
+
+  <refmeta>
+    <refentrytitle>repmgr standby promote</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby promote</refname>
+    <refpurpose>promote a standby to a primary</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Promotes a standby to a primary if the current primary has failed. This
+      command requires a valid <filename>repmgr.conf</filename> file for the standby, either
+      specified explicitly  with <literal>-f/--config-file</literal> or located in a
+      default location; no additional arguments are required.
+    </para>
+    <para>
+      If the standby promotion succeeds, the server will not need to be
+      restarted. However any other standbys will need to follow the new server,
+      by using <xref linkend="repmgr-standby-follow">; if <application>repmgrd</application>
+        is active, it will handle this automatically.
+    </para>
+    <para>
+      Note that &repmgr; will wait for up to <varname>promote_check_timeout</varname> seconds
+      (default: 60 seconds) to verify that the standby has been promoted, and will
+      check the promotion every <varname>promote_check_interval</varname> seconds (default: 1 second).
+      Both values can be defined in <filename>repmgr.conf</filename>.
+    </para>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Example</title>
+    <para>
+      <programlisting>
+      $ repmgr -f /etc/repmgr.conf standby promote
+      NOTICE: promoting standby to primary
+      DETAIL: promoting server "node2" (ID: 2) using "pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/postgres/data' promote"
+      server promoting
+      DEBUG: setting node 2 as primary and marking existing primary as failed
+      NOTICE: STANDBY PROMOTE successful
+      DETAIL: server "node2" (ID: 2) was successfully promoted to primary</programlisting>
+    </para>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_promote</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr-standby-register.sgml

@@ -1,50 +1,183 @@
-<chapter id="repmgr-standby-register" xreflabel="repmgr standby register">
-  <indexterm><primary>repmgr standby register</primary></indexterm>
-  <title>repmgr standby register</title>
-  <para>
-   <command>repmgr standby register</command> adds a standby's information to
-   the &repmgr; metadata. This command needs to be executed to enable
-   promote/follow operations and to allow <command>repmgrd</command> to work with the node.
-   An existing standby can be registered using this command. Execute with the
-   <literal>--dry-run</literal> option to check what would happen without actually registering the
-   standby.
-  </para>
+<refentry id="repmgr-standby-register" xreflabel="repmgr standby register">
+  <indexterm>
+    <primary>repmgr standby register</primary>
+  </indexterm>
 
-  <sect1 id="repmgr-standby-register-wait" xreflabel="repmgr standby register --wait">
+  <refmeta>
+    <refentrytitle>repmgr standby register</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby register</refname>
+    <refpurpose>add a standby's information to the &repmgr; metadata</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr standby register</command> adds a standby's information to
+      the &repmgr; metadata. This command needs to be executed to enable
+      promote/follow operations and to allow <application>repmgrd</application> to work with the node.
+      An existing standby can be registered using this command. Execute with the
+      <literal>--dry-run</literal> option to check what would happen without actually registering the
+      standby.
+    </para>
+
+    <note>
+      <para>
+        If providing the configuration file location with <literal>-f/--config-file</literal>,
+        avoid using a relative path, as &repmgr; stores the configuration file location
+        in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
+        <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
+          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>
+
+  <refsect1 id="repmgr-standby-register-wait-start" xreflabel="repmgr standby register --wait-start">
+   <title>Waiting for the the standby to start</title>
+   <para>
+     By default, &repmgr; will wait 30 seconds for the standby to become available before
+     aborting with a connection error. This is useful when setting up a standby from a script,
+     as the standby may not have fully started up by the time <command>repmgr standby register</command>
+     is executed.
+   </para>
+   <para>
+     To change the timeout, pass the desired value with the <literal>--wait-start</literal> option.
+     A value of <literal>0</literal> will disable the timeout.
+   </para>
+   <para>
+     The timeout will be ignored if <literal>-F/--force</literal> was provided.
+   </para>
+  </refsect1>
+
+  <refsect1 id="repmgr-standby-register-wait-sync" xreflabel="repmgr standby register --wait-sync">
    <title>Waiting for the registration to propagate to the standby</title>
    <para>
-     Depending on your environment and workload, it may take some time for
-     the standby's node record to propagate from the primary to the standby. Some
-     actions (such as starting <command>repmgrd</command>) require that the standby's node record
+     Depending on your environment and workload, it may take some time for the standby's node record
+     to propagate from the primary to the standby. Some actions (such as starting
+     <application>repmgrd</application>) require that the standby's node record
      is present and up-to-date to function correctly.
    </para>
    <para>
-    By providing the option <literal>--wait-sync</literal> to the
+    By providing the option <option>--wait-sync</option> to the
     <command>repmgr standby register</command> command, &repmgr; will wait
     until the record is synchronised before exiting. An optional timeout (in
-    seconds) can be added to this option (e.g. <literal>--wait-sync=60</literal>).
+    seconds) can be added to this option (e.g. <option>--wait-sync=60</option>).
    </para>
-  </sect1>
+  </refsect1>
 
-  <sect1 id="rempgr-standby-register-inactive-node" xreflabel="Registering an inactive node">
+  <refsect1 id="repmgr-standby-register-inactive-node" xreflabel="Registering an inactive node">
    <title>Registering an inactive node</title>
    <para>
     Under some circumstances you may wish to register a standby which is not
     yet running; this can be the case when using provisioning tools to create
-    a complex replication cluster. In this case, by using the <literal>-F/--force</literal>
+    a complex replication cluster. In this case, by using the <option>-F/--force</option>
     option and providing the connection parameters to the primary server,
     the standby can be registered.
    </para>
    <para>
     Similarly, with cascading replication it may be necessary to register
     a standby whose upstream node has not yet been registered - in this case,
-    using <literal>-F/--force</literal> will result in the creation of an inactive placeholder
+    using <option>-F/--force</option> will result in the creation of an inactive placeholder
     record for the upstream node, which will however later need to be registered
-    with the <literal>-F/--force</literal> option too.
+    with the <option>-F/--force</option> option too.
    </para>
    <para>
     When used with <command>repmgr standby register</command>, care should be taken that use of the
-    <literal>-F/--force</literal> option does not result in an incorrectly configured cluster.
+    <option>-F/--force</option> option does not result in an incorrectly configured cluster.
    </para>
-  </sect1>
-</chapter>
+  </refsect1>
+
+  <refsect1 id="repmgr-standby-register-node-cloned-other-source">
+    <title>Registering a node not cloned by repmgr</title>
+    <para>
+      If you've cloned a standby using another method (e.g. <application>barman</application>'s
+     <command>barman recover</command> command), first execute
+     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
+     to add the <filename>recovery.conf</filename> file, then register the standby as usual.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually register the standby.
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+       <term><option>-F</option><option>--force</option></term>
+        <listitem>
+          <para>
+            Overwrite an existing node record
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>--upstream-node-id</option></term>
+        <listitem>
+          <para>
+            ID of the upstream node to replicate from (optional)
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--wait-start</option></term>
+        <listitem>
+          <para>
+            wait for the standby to start (timeout in seconds, default 30 seconds)
+          </para>
+        </listitem>
+      </varlistentry>
+
+     <varlistentry>
+        <term><option>--wait-sync</option></term>
+        <listitem>
+          <para>
+            wait for the node record to synchronise to the standby (optional timeout in seconds)
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_register</literal> <link linkend="event-notifications">event notification</link>
+      will be generated immediately after the node record is updated on the primary.
+    </para>
+
+    <para>
+      If the <option>--wait-sync</option> option is provided, a <literal>standby_register_sync</literal>
+      event notification  will be generated immediately after the node record has synchronised to the
+      standby.
+    </para>
+
+    <para>
+      If provided, &repmgr; will substitute the placeholders <literal>%p</literal> with the node ID of the
+      primary node, <literal>%c</literal> with its <literal>conninfo</literal> string, and
+      <literal>%a</literal> with its node name.
+    </para>
+
+  </refsect1>
+
+</refentry>

doc/repmgr-standby-switchover.sgml

@@ -1,27 +1,256 @@
-<chapter id="repmgr-standby-switchover" xreflabel="repmgr standby switchover">
+<refentry id="repmgr-standby-switchover">
   <indexterm>
     <primary>repmgr standby switchover</primary>
   </indexterm>
-  <title>repmgr standby switchover</title>
-  <para>
-    Promotes a standby to primary and demotes the existing primary to a standby.
-    This command must be run on the standby to be promoted, and requires a
-    passwordless SSH connection to the current primary.
-  </para>
-  <para>
-    If other standbys are connected to the demotion candidate, &repmgr; can instruct
-    these to follow the new primary if the option <literal>--siblings-follow</literal>
-    is specified.
-  </para>
-  <para>
-    Execute with the <literal>--dry-run</literal> option to test the switchover as far as
-    possible without actually changing the status of either node.
-  </para>
-  <para>
-    <command>repmgrd</command> should not be active on any nodes while a switchover is being
-    executed. This restriction may be lifted in a later version.
-  </para>
-  <para>
-    For more details see the section <xref linkend="performing-switchover">.
-  </para>
-</chapter>
+
+  <refmeta>
+    <refentrytitle>repmgr standby switchover</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby switchover</refname>
+    <refpurpose>promote a standby to primary and demote the existing primary to a standby</refpurpose>
+  </refnamediv>
+
+
+  <refsect1>
+    <title>Description</title>
+
+    <para>
+      Promotes a standby to primary and demotes the existing primary to a standby.
+      This command must be run on the standby to be promoted, and requires a
+      passwordless SSH connection to the current primary.
+    </para>
+    <para>
+      If other standbys are connected to the demotion candidate, &repmgr; can instruct
+      these to follow the new primary if the option <literal>--siblings-follow</literal>
+      is specified. This requires a passwordless SSH connection between the promotion
+      candidate (new primary) and the standbys attached to the demotion candidate
+      (existing primary).
+    </para>
+    <note>
+      <para>
+        Performing a switchover is a non-trivial operation. In particular it
+        relies on the current primary being able to shut down cleanly and quickly.
+        &repmgr; will attempt to check for potential issues but cannot guarantee
+        a successful switchover.
+      </para>
+    </note>
+    <para>
+      For more details on performing a switchover, including preparation and configuration,
+      see section <xref linkend="performing-switchover">.
+    </para>
+
+    <note>
+      <para>
+        <application>repmgrd</application> should not be active on any nodes while a switchover is being
+        executed. This restriction may be lifted in a later version.
+      </para>
+    </note>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--always-promote</option></term>
+        <listitem>
+          <para>
+            Promote standby to primary, even if it is behind original primary
+            (original primary will be shut down in any case).
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually execute a switchover.
+          </para>
+          <important>
+            <para>
+              Success of <option>--dry-run</option> does not imply the switchover will
+              complete successfully, only that
+              the prerequisites for performing the operation are met.
+            </para>
+          </important>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-F</option></term>
+        <term><option>--force</option></term>
+        <listitem>
+          <para>
+            Ignore warnings and continue anyway.
+          </para>
+          <para>
+            Specifically, if a problem is encountered when shutting down the current primary,
+            using <option>-F/--force</option> will cause &repmgr; to continue by promoting
+            the standby to be the new primary, and if <option>--siblings-follow</option> is
+            specified, attach any other standbys to the new primary.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--force-rewind[=/path/to/pg_rewind]</option></term>
+        <listitem>
+          <para>
+            Use <application>pg_rewind</application> to reintegrate the old primary if necessary
+            (and the prerequisites for using <application>pg_rewind</application> are met).
+            If using PostgreSQL 9.3 or 9.4, and the <application>pg_rewind</application>
+            binary is not installed in the PostgreSQL <filename>bin</filename> directory,
+            provide its full path. For more details see also <xref linkend="switchover-pg-rewind">.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-R</option></term>
+        <term><option>--remote-user</option></term>
+        <listitem>
+          <para>
+            System username for remote SSH operations (defaults to local system user).
+          </para>
+        </listitem>
+      </varlistentry>
+
+     <varlistentry>
+        <term><option>--siblings-follow</option></term>
+        <listitem>
+          <para>
+            Have standbys attached to the old primary follow the new primary.
+          </para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+
+  </refsect1>
+
+  <refsect1>
+    <title>Configuration file settings</title>
+
+    <para>
+     Note that following parameters in <filename>repmgr.conf</filename> are relevant to the
+     switchover operation:
+     <itemizedlist spacing="compact" mark="bullet">
+       <listitem>
+         <simpara>
+           <literal>reconnect_attempts</literal>: number of times to check the original primary
+           for a clean shutdown after executing the shutdown command, before aborting
+         </simpara>
+       </listitem>
+       <listitem>
+         <simpara>
+           <literal>reconnect_interval</literal>: interval (in seconds) to check the original
+           primary for a clean shutdown after executing the shutdown command (up to a maximum
+           of <literal>reconnect_attempts</literal> tries)
+         </simpara>
+       </listitem>
+       <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>
+
+       <listitem>
+         <simpara>
+           <literal>standby_reconnect_timeout</literal>:
+           Number of seconds to attempt to reconnect to the demoted primary
+           once it has been restarted.
+         </simpara>
+       </listitem>
+
+     </itemizedlist>
+    </para>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Execution</title>
+
+    <para>
+      Execute with the <literal>--dry-run</literal> option to test the switchover as far as
+      possible without actually changing the status of either node.
+    </para>
+    <important>
+      <para>
+        <application>repmgrd</application> must be shut down on all nodes while a switchover is being
+        executed. This restriction will be removed in a future &repmgr; version.
+      </para>
+    </important>
+    <para>
+      External database connections, e.g. from an application, should not be permitted while
+      the switchover is taking place. In particular, active transactions on the primary
+      can potentially disrupt the shutdown process.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      <literal>standby_switchover</literal> and <literal>standby_promote</literal>
+      <link linkend="event-notifications">event notifications</link> will be generated for the new primary,
+      and a <literal>node_rejoin</literal> event notification for the former primary (new standby).
+    </para>
+    <para>
+      If using an event notification script, <literal>standby_switchover</literal>
+      will populate the placeholder parameter <literal>%p</literal> with the node ID of
+      the former primary.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Exit codes</title>
+    <para>
+      Following exit codes can be emitted by <command>repmgr standby switchover</command>:
+    </para>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>SUCCESS (0)</option></term>
+        <listitem>
+          <para>
+            The switchover completed successfully.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_SWITCHOVER_FAIL (18)</option></term>
+        <listitem>
+          <para>
+            The switchover could not be executed.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>ERR_SWITCHOVER_INCOMPLETE (22)</option></term>
+        <listitem>
+          <para>
+            The switchover was executed but a problem was encountered.
+            Typically this means the former primary could not be reattached
+            as a standby. Check preceding log messages for more information.
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>See also</title>
+    <para>
+      For more details see the section <xref linkend="performing-switchover">.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr-standby-unregister.sgml

@@ -1,29 +1,70 @@
-<chapter id="repmgr-standby-unregister" xreflabel="repmgr standby unregister">
-  <indexterm><primary>repmgr standby unregister</primary></indexterm>
-  <title>repmgr standby unregister</title>
-  <para>
-    Unregisters a standby with `repmgr`. This command does not affect the actual
-    replication, just removes the standby's entry from the &repmgr; metadata.
-  </para>
-  <para>
-    To unregister a running standby, execute:
-    <programlisting>
-      repmgr standby unregister -f /etc/repmgr.conf</programlisting>
-  </para>
-  <para>
-    This will remove the standby record from &repmgr;'s internal metadata
-    table (<literal>repmgr.nodes</literal>). A <literal>standby_unregister</literal>
-    event notification will be recorded in the <literal>repmgr.events</literal> table.
-  </para>
-  <para>
-   If the standby is not running, the command can be executed on another
-   node by providing the id of the node to be unregistered using
-   the command line parameter <literal>--node-id</literal>, e.g. executing the following
-   command on the master server will unregister the standby with
-   id <literal>3</literal>:
-   <programlisting>
-    repmgr standby unregister -f /etc/repmgr.conf --node-id=3
-   </programlisting>
-  </para>
-</chapter>
+<refentry id="repmgr-standby-unregister">
+  <indexterm>
+    <primary>repmgr standby unregister</primary>
+  </indexterm>
+
+  <refmeta>
+    <refentrytitle>repmgr standby unregister</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr standby unregister</refname>
+    <refpurpose>remove a standby's information from the &repmgr; metadata</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      Unregisters a standby with &repmgr;. This command does not affect the actual
+      replication, just removes the standby's entry from the &repmgr; metadata.
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Execution</title>
+    <para>
+      To unregister a running standby, execute:
+      <programlisting>
+        repmgr standby unregister -f /etc/repmgr.conf</programlisting>
+    </para>
+    <para>
+      This will remove the standby record from &repmgr;'s internal metadata
+      table (<literal>repmgr.nodes</literal>). A <literal>standby_unregister</literal>
+      event notification will be recorded in the <literal>repmgr.events</literal> table.
+    </para>
+    <para>
+      If the standby is not running, the command can be executed on another
+      node by providing the id of the node to be unregistered using
+      the command line parameter <literal>--node-id</literal>, e.g. executing the following
+      command on the primary server will unregister the standby with
+      id <literal>3</literal>:
+      <programlisting>
+        repmgr standby unregister -f /etc/repmgr.conf --node-id=3</programlisting>
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--node-id</option></term>
+        <listitem>
+          <para>
+            <varname>node_id</varname> of the node to unregister (optional)
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>standby_unregister</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>
 

doc/repmgr-witness-register.sgml

@@ -0,0 +1,60 @@
+<refentry id="repmgr-witness-register">
+  <indexterm>
+    <primary>repmgr witness register</primary>
+    <seealso>witness server</seealso>
+  </indexterm>
+
+  <refmeta>
+    <refentrytitle>repmgr witness register</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr witness register</refname>
+    <refpurpose>add a witness node's information to the &repmgr; metadata</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr witness register</command> adds a witness server's node
+      record to the &repmgr; metadata, and if necessary initialises the witness
+      node by installing the &repmgr; extension and copying the &repmgr; metadata
+      to the witness server. This command needs to be executed to enable
+      use of the witness server with <application>repmgrd</application>.
+    </para>
+    <para>
+      When executing <command>repmgr witness register</command>, connection information
+      for the cluster primary server must also be provided. &repmgr; will automatically
+      use the <varname>user</varname> and <varname>dbname</varname> values defined
+      in the <varname>conninfo</varname> string defined in the  witness node's
+      <filename>repmgr.conf</filename>, if these are not explicitly provided.
+    </para>
+    <para>
+      Execute with the <literal>--dry-run</literal> option to check what would happen
+      without actually registering the witness server.
+    </para>
+  </refsect1>
+  <refsect1>
+    <title>Example</title>
+    <para>
+      <programlisting>
+    $ repmgr -f /etc/repmgr.conf witness register -h node1
+    INFO: connecting to witness node "node3" (ID: 3)
+    INFO: connecting to primary node
+    NOTICE: attempting to install extension "repmgr"
+    NOTICE: "repmgr" extension successfully installed
+    INFO: witness registration complete
+    NOTICE: witness node "node3" (ID: 3) successfully registered
+      </programlisting>
+    </para>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>witness_register</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr-witness-unregister.sgml

@@ -0,0 +1,73 @@
+<refentry id="repmgr-witness-unregister" xreflabel="repmgr witness unregister">
+  <indexterm>
+    <primary>repmgr witness unregister</primary>
+  </indexterm>
+
+  <refmeta>
+    <refentrytitle>repmgr witness unregister</refentrytitle>
+  </refmeta>
+
+  <refnamediv>
+    <refname>repmgr witness unregister</refname>
+    <refpurpose>remove a witness node's information to the &repmgr; metadata</refpurpose>
+  </refnamediv>
+
+  <refsect1>
+    <title>Description</title>
+    <para>
+      <command>repmgr witness unregister</command> removes a witness server's node
+      record from the &repmgr; metadata.
+    </para>
+    <para>
+      The node does not have to be running to be unregistered, however if this is the
+      case then connection information for the primary server must be provided.
+    </para>
+    <para>
+      Execute with the <literal>--dry-run</literal> option to check what would happen
+      without actually registering the witness server.
+    </para>
+  </refsect1>
+  <refsect1>
+    <title>Examples</title>
+    <para>
+      Unregistering a running witness node:
+      <programlisting>
+    $ repmgr -f /etc/repmgr.conf witness unregister
+    INFO: connecting to witness node "node3" (ID: 3)
+    INFO: unregistering witness node 3
+    INFO: witness unregistration complete
+    DETAIL: witness node with id 3 (conninfo: host=node3 dbname=repmgr user=repmgr port=5499) successfully unregistered</programlisting>
+    </para>
+    <para>
+      Unregistering a non-running witness node:
+      <programlisting>
+        $ repmgr -f /etc/repmgr.conf witness unregister -h node1 -p 5501  -F
+        INFO: connecting to witness node "node3" (ID: 3)
+        NOTICE: unable to connect to witness node "node3" (ID: 3), removing node record on cluster primary only
+        INFO: unregistering witness node 3
+        INFO: witness unregistration complete
+        DETAIL: witness node with id 3 (conninfo: host=node3 dbname=repmgr user=repmgr port=5499) successfully unregistered</programlisting>
+    </para>
+  </refsect1>
+
+  <refsect1>
+    <title>Notes</title>
+    <para>
+      This command will not make any changes to the witness node itself and will neither
+      remove any data from the witness database nor stop the PostgreSQL instance.
+    </para>
+    <para>
+      A witness node which has been unregistered, can be re-registered with
+      <link linkend="repmgr-witness-register">repmgr witness register --force</link>.
+    </para>
+  </refsect1>
+
+
+  <refsect1>
+    <title>Event notifications</title>
+    <para>
+      A <literal>witness_unregister</literal> <link linkend="event-notifications">event notification</link> will be generated.
+    </para>
+  </refsect1>
+
+</refentry>

doc/repmgr.sgml

@@ -23,13 +23,19 @@
 
   <abstract>
    <para>
-   Thisis the official documentation of &repmgr; &repmgrversion; for
+   This is the official documentation of &repmgr; &repmgrversion; for
    use with PostgreSQL 9.3 - PostgreSQL 10.
-   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 was 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
@@ -73,6 +79,7 @@
   &promoting-standby;
   &follow-new-primary;
   &switchover;
+  &configuring-witness-server;
   &event-notifications;
   &upgrading-repmgr;
  </part>
@@ -84,8 +91,10 @@
   &repmgrd-demonstration;
   &repmgrd-cascading-replication;
   &repmgrd-network-split;
+  &repmgrd-witness-server;
   &repmgrd-degraded-monitoring;
   &repmgrd-monitoring;
+  &repmgrd-bdr;
  </part>
 
  <part id="repmgr-command-reference">
@@ -99,6 +108,8 @@
   &repmgr-standby-promote;
   &repmgr-standby-follow;
   &repmgr-standby-switchover;
+  &repmgr-witness-register;
+  &repmgr-witness-unregister;
   &repmgr-node-status;
   &repmgr-node-check;
   &repmgr-node-rejoin;
@@ -109,7 +120,10 @@
   &repmgr-cluster-cleanup;
  </part>
 
+ &appendix-release-notes;
  &appendix-signatures;
+ &appendix-faq;
+ &appendix-packages;
 
  <![%include-index;[&bookindex;]]>
  <![%include-xslt-index;[<index id="bookindex"></index>]]>

doc/repmgrd-automatic-failover.sgml

@@ -1,8 +1,13 @@
 <chapter id="repmgrd-automatic-failover" xreflabel="Automatic failover with repmgrd">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>automatic failover</secondary>
+ </indexterm>
+
  <title>Automatic failover with repmgrd</title>
 
  <para>
-  <command>repmgrd</command> is a management and monitoring daemon which runs
+  <application>repmgrd</application> is a management and monitoring daemon which runs
   on each node in a replication cluster. It can automate actions such as
   failover and updating standbys to follow the new primary, as well as
   providing monitoring information about the state of each standby.

doc/repmgrd-bdr.sgml

@@ -0,0 +1,415 @@
+<chapter id="repmgrd-bdr">
+  <indexterm>
+    <primary>repmgrd</primary>
+    <secondary>BDR</secondary>
+  </indexterm>
+
+  <indexterm>
+    <primary>BDR</primary>
+  </indexterm>
+
+  <title>BDR failover with repmgrd</title>
+  <para>
+    &repmgr; 4.x provides support for monitoring BDR nodes and taking action in
+    case one of the nodes fails.
+  </para>
+  <note>
+    <simpara>
+      Due to the nature of BDR, it's only safe to use this solution for
+      a two-node scenario. Introducing additional nodes will create an inherent
+      risk of node desynchronisation if a node goes down without being cleanly
+      removed from the cluster.
+    </simpara>
+  </note>
+  <para>
+    In contrast to streaming replication, there's no concept of "promoting" a new
+    primary node with BDR. Instead, "failover" involves monitoring both nodes
+    with <application>repmgrd</application> and redirecting queries from the failed node to the remaining
+    active node. This can be done by using an
+    <link linkend="event-notifications">event notification</link> script
+    which is called by <application>repmgrd</application> to dynamically
+    reconfigure a proxy server/connection pooler such as <application>PgBouncer</application>.
+  </para>
+
+  <sect1 id="bdr-prerequisites" xreflabel="BDR prequisites">
+    <title>Prerequisites</title>
+    <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
+      must be installed on each node before attempting to configure
+      <application>repmgr</application>.
+    </para>
+    <note>
+      <simpara>
+        &repmgr; 4 will refuse to install if it detects more than two BDR nodes.
+      </simpara>
+    </note>
+    <para>
+      Application database connections *must* be passed through a proxy server/
+      connection pooler such as <application>PgBouncer</application>, and it must be possible to dynamically
+      reconfigure that from <application>repmgrd</application>. The example demonstrated in this document
+      will use <application>PgBouncer</application>
+    </para>
+    <para>
+      The proxy server / connection poolers must <emphasis>not</emphasis>
+      be installed on the database servers.
+    </para>
+    <para>
+      For this example, it's assumed password-less SSH connections are available
+      from the PostgreSQL servers to the servers where <application>PgBouncer</application>
+      runs, and that the user on those servers has permission to alter the
+      <application>PgBouncer</application> configuration files.
+    </para>
+    <para>
+      PostgreSQL connections must be possible between each node, and each node
+      must be able to connect to each PgBouncer instance.
+    </para>
+  </sect1>
+
+  <sect1 id="bdr-configuration" xreflabel="BDR configuration">
+    <title>Configuration</title>
+    <para>
+      A sample configuration for <filename>repmgr.conf</filename> on each
+      BDR node would look like this:
+      <programlisting>
+        # Node information
+        node_id=1
+        node_name='node1'
+        conninfo='host=node1 dbname=bdrtest user=repmgr connect_timeout=2'
+        data_directory='/var/lib/postgresql/data'
+        replication_type='bdr'
+
+        # Event notification configuration
+        event_notifications=bdr_failover
+        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&1'
+
+        # repmgrd options
+        monitor_interval_secs=5
+        reconnect_attempts=6
+        reconnect_interval=5</programlisting>
+    </para>
+    <para>
+      Adjust settings as appropriate; copy and adjust for the second node (particularly
+      the values <varname>node_id</varname>, <varname>node_name</varname>
+      and <varname>conninfo</varname>).
+    </para>
+    <para>
+      Note that the values provided for the <varname>conninfo</varname> string
+      must be valid for connections from <emphasis>both</emphasis> nodes in the
+      replication cluster. The database must be the BDR-enabled database.
+    </para>
+    <para>
+      If defined, the <varname>event_notifications</varname> parameter will restrict
+      execution of the script defined in  <varname>event_notification_command</varname>
+      to the specified event(s).
+    </para>
+    <note>
+      <simpara>
+        <varname>event_notification_command</varname> is the script which does the actual "heavy lifting"
+        of reconfiguring the proxy server/ connection pooler. It is fully
+        user-definable; see section <xref linkend="bdr-event-notification-command"> for a reference
+        implementation.
+      </simpara>
+    </note>
+
+  </sect1>
+
+  <sect1 id="bdr-repmgr-setup" xreflabel="repmgr setup with BDR">
+    <title>repmgr setup</title>
+    <para>
+      Register both nodes; example on <literal>node1</literal>:
+      <programlisting>
+        $ repmgr -f /etc/repmgr.conf bdr register
+        NOTICE: attempting to install extension "repmgr"
+        NOTICE: "repmgr" extension successfully installed
+        NOTICE: node record created for node 'node1' (ID: 1)
+        NOTICE: BDR node 1 registered (conninfo: host=node1 dbname=bdrtest user=repmgr)</programlisting>
+    </para>
+    <para>
+      and on <literal>node1</literal>:
+      <programlisting>
+        $ repmgr -f /etc/repmgr.conf bdr register
+        NOTICE: node record created for node 'node2' (ID: 2)
+        NOTICE: BDR node 2 registered (conninfo: host=node2 dbname=bdrtest user=repmgr)</programlisting>
+    </para>
+    <para>
+      The <literal>repmgr</literal> extension will be automatically created
+      when the first node is registered, and will be propagated to the second
+      node.
+    </para>
+    <important>
+      <simpara>
+        Ensure the &repmgr; package is available on both nodes before
+        attempting to register the first node.
+      </simpara>
+    </important>
+    <para>
+      At this point the meta data for both nodes has been created; executing
+      <xref linkend="repmgr-cluster-show"> (on either node) should produce output like this:
+      <programlisting>
+        $ repmgr -f /etc/repmgr.conf cluster show
+        ID | Name  | Role | Status    | Upstream | Location | Connection string
+       ----+-------+------+-----------+----------+--------------------------------------------------------
+        1  | node1 | bdr  | * running |          | default  | host=node1 dbname=bdrtest user=repmgr connect_timeout=2
+        2  | node2 | bdr  | * running |          | default  | host=node2 dbname=bdrtest user=repmgr connect_timeout=2</programlisting>
+    </para>
+    <para>
+      Additionally it's possible to display log of significant events;  executing
+      <xref linkend="repmgr-cluster-event"> (on either node) should produce output like this:
+      <programlisting>
+        $ repmgr -f /etc/repmgr.conf cluster event
+        Node ID | Event        | OK | Timestamp           | Details
+       ---------+--------------+----+---------------------+----------------------------------------------
+        2       | bdr_register | t  | 2017-07-27 17:51:48 | node record created for node 'node2' (ID: 2)
+        1       | bdr_register | t  | 2017-07-27 17:51:00 | node record created for node 'node1' (ID: 1)
+      </programlisting>
+    </para>
+    <para>
+      At this point there will only be records for the two node registrations (displayed here
+      in reverse chronological order).
+    </para>
+  </sect1>
+
+  <sect1 id="bdr-event-notification-command" xreflabel="Defining the BDR failover &quot;event_notification command&quot;">
+    <title>Defining the BDR failover "event_notification_command"</title>
+    <para>
+      Key to "failover" execution is the <literal>event_notification_command</literal>,
+      which is a user-definable script specified in <filename>repmpgr.conf</filename>
+      and which can use a &repmgr; <link linkend="event-notifications">event notification</link>
+      to reconfigure the proxy server / connection pooler so it points to the other, still-active node.
+      Details of the event will be passed as parameters to the script.
+    </para>
+    <para>
+      Following parameter placeholders are available for the script definition in <filename>repmpgr.conf</filename>;
+      these will be replaced with the appropriate value when the script is executed:
+    </para>
+
+    <variablelist>
+      <varlistentry>
+        <term><option>%n</option></term>
+        <listitem>
+          <para>
+            node ID
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>%e</option></term>
+        <listitem>
+          <para>
+            event type
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>%t</option></term>
+        <listitem>
+          <para>
+            success (1 or 0)
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>%t</option></term>
+        <listitem>
+          <para>
+            timestamp
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>%d</option></term>
+        <listitem>
+          <para>
+            details
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>%c</option></term>
+        <listitem>
+          <para>
+            conninfo string of the next available node (<varname>bdr_failover</varname> and <varname>bdr_recovery</varname>)
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>%a</option></term>
+        <listitem>
+          <para>
+            name of the next available node (<varname>bdr_failover</varname> and <varname>bdr_recovery</varname>)
+          </para>
+        </listitem>
+      </varlistentry>
+    </variablelist>
+
+    <para>
+      Note that <literal>%c</literal> and <literal>%a</literal> are only provided with
+      particular failover events, in this case <varname>bdr_failover</varname>.
+    </para>
+    <para>
+      The provided sample script
+     (<literal><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/scripts/bdr-pgbouncer.sh">scripts/bdr-pgbouncer.sh</ulink></literal>)
+      is configured as follows:
+      <programlisting>
+        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a"'</programlisting>
+    </para>
+    <para>
+      and parses the placeholder parameters like this:
+      <programlisting>
+        NODE_ID=$1
+        EVENT_TYPE=$2
+        SUCCESS=$3
+        NEXT_CONNINFO=$4
+        NEXT_NODE_NAME=$5</programlisting>
+    </para>
+    <note>
+      <para>
+        The sample script also contains some hard-coded values for the <application>PgBouncer</application>
+        configuration for both nodes; these will need to be adjusted for your local environment
+        (ideally the scripts would be maintained as templates and generated by some
+        kind of provisioning system).
+      </para>
+    </note>
+
+    <para>
+      The script performs following steps:
+      <itemizedlist spacing="compact" mark="bullet">
+        <listitem>
+          <simpara>pauses <application>PgBouncer</application> on all nodes</simpara>
+        </listitem>
+        <listitem>
+          <simpara>recreates the <application>PgBouncer</application> configuration file on each
+            node using the information provided by <application>repmgrd</application>
+            (primarily the <varname>conninfo</varname> string) to configure
+            <application>PgBouncer</application></simpara>
+        </listitem>
+        <listitem>
+          <simpara>reloads the <application>PgBouncer</application> configuration</simpara>
+        </listitem>
+        <listitem>
+          <simpara>executes the <command>RESUME</command> command (in <application>PgBouncer</application>)</simpara>
+        </listitem>
+      </itemizedlist>
+    </para>
+    <para>
+      Following successful script execution, any connections to PgBouncer on the failed BDR node
+      will be redirected to the active node.
+    </para>
+  </sect1>
+
+  <sect1 id="bdr-monitoring-failover" xreflabel="Node monitoring and failover">
+    <title>Node monitoring and failover</title>
+    <para>
+      At the intervals specified by <varname>monitor_interval_secs</varname>
+      in <filename>repmgr.conf</filename>, <application>repmgrd</application>
+      will ping each node to check if it's available. If a node isn't available,
+      <application>repmgrd</application> will enter failover mode and check <varname>reconnect_attempts</varname>
+      times at intervals of <varname>reconnect_interval</varname> to confirm the node is definitely unreachable.
+      This buffer period is necessary to avoid false positives caused by transient
+      network outages.
+    </para>
+    <para>
+      If the node is still unavailable, <application>repmgrd</application> will enter failover mode and execute
+      the script defined in <varname>event_notification_command</varname>; an entry will be logged
+      in the <literal>repmgr.events</literal> table and <application>repmgrd</application> will
+      (unless otherwise configured) resume monitoring of the node in "degraded" mode until it reappears.
+    </para>
+    <para>
+      <application>repmgrd</application> logfile output during a failover event will look something like this
+      on one node (usually the node which has failed, here <literal>node2</literal>):
+      <programlisting>
+            ...
+    [2017-07-27 21:08:39] [INFO] starting continuous BDR node monitoring
+    [2017-07-27 21:08:39] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
+    [2017-07-27 21:08:55] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
+    [2017-07-27 21:09:11] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
+    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
+    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
+    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
+    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
+    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
+    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
+    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
+    [2017-07-27 21:09:28] [NOTICE] setting node record for node 2 to inactive
+    [2017-07-27 21:09:28] [INFO] executing notification command for event "bdr_failover"
+    [2017-07-27 21:09:28] [DETAIL] command is:
+      /path/to/bdr-pgbouncer.sh 2 bdr_failover 1 "host=host=node1 dbname=bdrtest user=repmgr connect_timeout=2" "node1"
+    [2017-07-27 21:09:28] [INFO] node 'node2' (ID: 2) detected as failed; next available node is 'node1' (ID: 1)
+    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
+    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
+    ...</programlisting>
+    </para>
+    <para>
+      Output on the other node (<literal>node1</literal>) during the same event will look like this:
+      <programlisting>
+    ...
+    [2017-07-27 21:08:35] [INFO] starting continuous BDR node monitoring
+    [2017-07-27 21:08:35] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
+    [2017-07-27 21:08:51] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
+    [2017-07-27 21:09:07] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
+    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
+    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
+    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
+    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
+    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
+    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
+    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
+    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
+    [2017-07-27 21:09:28] [NOTICE] other node's repmgrd is handling failover
+    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
+    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
+    ...</programlisting>
+    </para>
+    <para>
+      This assumes only the PostgreSQL instance on <literal>node2</literal> has failed. In this case the
+      <application>repmgrd</application> instance running on <literal>node2</literal> has performed the failover. However if
+      the entire server becomes unavailable, <application>repmgrd</application> on <literal>node1</literal> will perform
+      the failover.
+    </para>
+  </sect1>
+  <sect1 id="bdr-node-recovery" xreflabel="Node recovery">
+    <title>Node recovery</title>
+    <para>
+      Following failure of a BDR node, if the node subsequently becomes available again,
+      a <varname>bdr_recovery</varname> event will be generated. This could potentially be used to
+      reconfigure PgBouncer automatically to bring the node back into the available pool,
+      however it would be prudent to manually verify the node's status before
+      exposing it to the application.
+    </para>
+    <para>
+      If the failed node comes back up and connects correctly, output similar to this
+      will be visible in the <application>repmgrd</application> log:
+      <programlisting>
+        [2017-07-27 21:25:30] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
+        [2017-07-27 21:25:46] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
+        [2017-07-27 21:25:46] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
+        [2017-07-27 21:25:55] [INFO] active replication slot for node "node1" found after 1 seconds
+        [2017-07-27 21:25:55] [NOTICE] node "node2" (ID: 2) has recovered after 986 seconds</programlisting>
+    </para>
+  </sect1>
+
+  <sect1 id="bdr-complete-shutdown" xreflabel="Shutdown of both nodes">
+    <title>Shutdown of both nodes</title>
+    <para>
+      If both PostgreSQL instances are shut down, <application>repmgrd</application> will try and handle the
+      situation as gracefully as possible, though with no failover candidates available
+      there's not much it can do. Should this case ever occur, we recommend shutting
+      down <application>repmgrd</application> on both nodes and restarting it once the PostgreSQL instances
+      are running properly.
+    </para>
+  </sect1>
+</chapter>
+

doc/repmgrd-cascading-replication.sgml

@@ -1,9 +1,14 @@
 <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
-  <command>repmgrd</command> support cascading replication by keeping track of the relationship
+  <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>

doc/repmgrd-configuration.sgml

@@ -1,54 +1,244 @@
 <chapter id="repmgrd-configuration">
- <title>repmgrd configuration</title>
- <para>
-  To use <command>repmgrd</command>, its associated function library must be
-  included in <filename>postgresql.conf</filename> with:
 
-  <programlisting>
-    shared_preload_libraries = 'repmgr'</programlisting>
- </para>
- <para>
-  Changing this setting requires a restart of PostgreSQL; for more details see
-  the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
- </para>
- <para>
-  Additionally the following <command>repmgrd</command> options *must* be set in
-  <filename>repmgr.conf</filename> (adjust configuration file locations as appropriate):
-  <programlisting>
-    failover=automatic
-    promote_command='repmgr standby promote -f /etc/repmgr.conf --log-to-file'
-    follow_command='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 <command>repmgrd</command>,
-  to be logged to the same destination configured to receive log output for <command>repmgrd</command>.
-  See <filename>repmgr.conf.sample</filename> for further <command>repmgrd</command>-specific settings.
- </para>
- <para>
-  When <varname>failover</varname> is set to <literal>automatic</literal>, upon detecting failure
-  of the current  primary, <command>repmgrd</command> will execute one of
-  <varname>promote_command</varname> or <varname>follow_command</varname>,
-  depending on whether the current server is to become the new primary, or
-  needs to follow another server which has become the new primary. Note that
-  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>
- <para>
-  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
-  <command>repmgrd</command> 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>
- <sect1 id="repmgrd-connection-settings">
- <title>repmgrd connection settings</title>
+  <indexterm>
+    <primary>repmgrd</primary>
+    <secondary>configuration</secondary>
+  </indexterm>
+
+  <title>repmgrd configuration</title>
+
+  <para>
+    <application>repmgrd</application> is a daemon which runs on each PostgreSQL node,
+    monitoring the local node, and (unless it's the primary node) the upstream server
+    (the primary server or with cascading replication, another standby) which it's
+    connected to.
+  </para>
+  <para>
+    <application>repmgrd</application> can be configured to provide failover
+    capability in case the primary upstream node becomes unreachable, and/or
+    provide monitoring data to the &repmgr; metadatabase.
+  </para>
+
+  <sect1 id="repmgrd-basic-configuration">
+    <title>repmgrd basic configuration</title>
+
+    <para>
+      To use <application>repmgrd</application>, its associated function library <emphasis>must</emphasis> be
+      included in <filename>postgresql.conf</filename> with:
+
+      <programlisting>
+        shared_preload_libraries = 'repmgr'</programlisting>
+    </para>
+    <para>
+      Changing this setting requires a restart of PostgreSQL; for more details see
+      the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
+    </para>
+
+    <para>
+      To apply configuration file changes to a running <application>repmgrd</application>
+      daemon, execute the operating system's r<application>repmgrd</application> service reload command
+      (see <xref linkend="appendix-packages"> for examples),
+      or for instances  which were manually started, execute <command>kill -HUP</command>, e.g.
+      <command>kill -HUP `cat /tmp/repmgrd.pid`</command>.
+    </para>
+    <note>
+      <para>
+        Check the <application>repmgrd</application> log to see what changes were
+        applied, or if any issues were encountered when reloading the configuration.
+      </para>
+    </note>
+    <para>
+      Note that only a subset of configuration file parameters can be changed on a
+      running <application>repmgrd</application> daemon.
+    </para>
+
+    <sect2 id="repmgrd-automatic-failover-configuration">
+      <title>automatic failover configuration</title>
+      <para>
+        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>
+        Adjust file paths as appropriate; we recomment specifying the full path to the &repmgr; binary.
+      </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>.
+        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>
+      <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 <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>
+    </sect2>
+
+    <sect2 id="repmgrd-service-configuration">
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>PostgreSQL service configuration</secondary>
+      </indexterm>
+      <title>PostgreSQL service configuration</title>
+      <para>
+        If using automatic failover, currently <application>repmgrd</application> will need to execute
+        <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>
+        to restart PostgreSQL on standbys to have them follow a new primary.
+      </para>
+      <para>
+        To ensure this happens smoothly, it's essential to provide the appropriate system/service restart
+        command appropriate to your operating system via <varname>service_restart_command</varname>
+        in <filename>repmgr.conf</filename>. If you don't do this, <application>repmgrd</application>
+        will default to using <command>pg_ctl</command>, which can result in unexpected problems,
+        particularly on <application>systemd</application>-based systems.
+      </para>
+      <para>
+        For more details, see <xref linkend="configuration-service-commands">.
+      </para>
+    </sect2>
+
+    <sect2 id="repmgrd-monitoring-configuration">
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>monitoring configuration</secondary>
+      </indexterm>
+      <title>Monitoring configuration</title>
+      <para>
+        To enable monitoring, set:
+        <programlisting>
+          monitoring_history=yes</programlisting>
+        in <filename>repmgr.conf</filename>.
+      </para>
+      <para>
+        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">.
+      </para>
+    </sect2>
+
+  </sect1>
+
+  <sect1 id="repmgrd-daemon">
+    <indexterm>
+      <primary>repmgrd</primary>
+      <secondary>starting and stopping</secondary>
+    </indexterm>
+    <title>repmgrd daemon</title>
+    <para>
+      If installed from a package, the <application>repmgrd</application> can be started
+      via the operating system's service command, e.g. in <application>systemd</application>
+      using <command>systemctl</command>.
+    </para>
+    <para>
+      See appendix <xref linkend="appendix-packages"> for details of service commands
+      for different distributions.
+    </para>
+    <para>
+      <application>repmgrd</application> can be started manually like this:
+      <programlisting>
+        repmgrd -f /etc/repmgr.conf --pid-file /tmp/repmgrd.pid --daemonize</programlisting>
+      and stopped with <command>kill `cat /tmp/repmgrd.pid`</command>. Adjust paths as appropriate.
+    </para>
+
+    <sect2 id="repmgrd-configuration-debian-ubuntu">
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>Debian/Ubuntu and daemon configuration</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>Debian/Ubuntu</primary>
+        <secondary>repmgrd daemon configuration</secondary>
+      </indexterm>
+
+      <title>repmgrd daemon configuration on Debian/Ubuntu</title>
+
+      <para>
+        If &repmgr; was installed from Debian/Ubuntu packages, additional configuration
+        is required before <application>repmgrd</application> is started as a daemon.
+      </para>
+      <para>
+        This is done via the file <filename>/etc/default/repmgrd</filename>, which by default
+        looks like this:
+        <programlisting>
+# default settings for repmgrd. This file is source by /bin/sh from
+# /etc/init.d/repmgrd
+
+# disable repmgrd by default so it won't get started upon installation
+# valid values: yes/no
+REPMGRD_ENABLED=no
+
+# configuration file (required)
+#REPMGRD_CONF="/path/to/repmgr.conf"
+
+# additional options
+#REPMGRD_OPTS=""
+
+# user to run repmgrd as
+#REPMGRD_USER=postgres
+
+# repmgrd binary
+#REPMGRD_BIN=/usr/bin/repmgrd
+
+# pid file
+#REPMGRD_PIDFILE=/var/run/repmgrd.pid</programlisting>
+      </para>
+      <para>
+        Set <varname>REPMGRD_ENABLED</varname> to <literal>yes</literal>, and <varname>REPMGRD_CONF</varname>
+        to the <filename>repmgr.conf</filename> file you are using.
+      </para>
+      <para>
+        If using <application>systemd</application>, you may need to execute <command>systemctl daemon-reload</command>.
+        Also, if you attempted to start <application>repmgrd</application> using <command>systemctl start repmgrd</command>,
+        you'll need to execute <command>systemctl stop repmgrd</command>. Because that's how <application>systemd</application>
+        rolls.
+      </para>
+
+    </sect2>
+  </sect1>
+
+  <sect1 id="repmgrd-connection-settings">
+    <title>repmgrd connection settings</title>
  <para>
   In addition to the &repmgr; configuration settings, parameters in the
   <varname>conninfo</varname> string influence how &repmgr; makes a network connection to
@@ -70,12 +260,21 @@
   <ulink url="https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-PARAMKEYWORDS">PostgreSQL documentation</ulink>.
  </para>
  </sect1>
+
+
+
  <sect1 id="repmgrd-log-rotation">
+   <indexterm>
+     <primary>log rotation</primary>
+     <secondary>repmgrd</secondary>
+   </indexterm>
+
   <title>repmgrd log rotation</title>
   <para>
-   To ensure the current <command>repmgrd</command> logfile does not grow
-   indefinitely, configure your system's <command>logrotate</command> to
-   regularly rotate it.
+   To ensure the current <application>repmgrd</application> logfile
+   (specified in <filename>repmgr.conf</filename> with the parameter
+   <option>log_file</option> does not grow indefinitely, configure your
+   system's <command>logrotate</command> to regularly rotate it.
   </para>
   <para>
    Sample configuration to rotate logfiles weekly with retention for

doc/repmgrd-degraded-monitoring.sgml

@@ -1,9 +1,14 @@
 <chapter id="repmgrd-degraded-monitoring">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>degraded monitoring</secondary>
+ </indexterm>
+
  <title>"degraded monitoring" mode</title>
  <para>
-  In certain circumstances, <command>repmgrd</command> is not able to fulfill its primary mission
+  In certain circumstances, <application>repmgrd</application> is not able to fulfill its primary mission
   of monitoring the nodes' upstream server. In these cases it enters "degraded
-  monitoring" mode, where <command>repmgrd</command> remains active but is waiting for the situation
+  monitoring" mode, where <application>repmgrd</application> remains active but is waiting for the situation
   to be resolved.
  </para>
  <para>
@@ -35,7 +40,7 @@
    </listitem>
 
    <listitem>
-    <simpara>repmgrd is monitoring the primary node, but it is not available</simpara>
+    <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>
@@ -63,8 +68,16 @@
  <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 <command>repmgrd</command> will terminate.
-
+  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

@@ -10,19 +10,19 @@
     ----+-------+---------+-----------+----------+----------+--------------------------------------
      1  | node1 | primary | * running |          | default  | host=node1 dbname=repmgr user=repmgr
      2  | node2 | standby |   running | node1    | default  | host=node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node1    | default  | host=node3 dbname=repmgr user=repmgr  </programlisting>
+     3  | node3 | standby |   running | node1    | default  | host=node3 dbname=repmgr user=repmgr</programlisting>
  </para>
  <para>
-  Start <command>repmgrd</command> on each standby and verify that it's running by examining the
+  Start <application>repmgrd</application> on each standby and verify that it's running by examining the
   log output, which at log level <literal>INFO</literal> will look like this:
   <programlisting>
     [2017-08-24 17:31:00] [NOTICE] using configuration file "/etc/repmgr.conf"
     [2017-08-24 17:31:00] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr"
     [2017-08-24 17:31:00] [NOTICE] starting monitoring of node <literal>node2</literal> (ID: 2)
-    [2017-08-24 17:31:00] [INFO] monitoring connection to upstream node "node1" (node ID: 1)  </programlisting>
+    [2017-08-24 17:31:00] [INFO] monitoring connection to upstream node "node1" (node ID: 1)</programlisting>
  </para>
  <para>
-  Each <command>repmgrd</command> should also have recorded its successful startup as an event:
+  Each <application>repmgrd</application> should also have recorded its successful startup as an event:
   <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
      Node ID | Name  | Event         | OK | Timestamp           | Details
@@ -38,8 +38,8 @@
  </para>
  <para>
   This will force the primary to shut down straight away, aborting all processes
-  and transactions.  This will cause a flurry of activity in the <command>repmgrd</command> log
-  files as each <command>repmgrd</command> detects the failure of the primary and a failover
+  and transactions.  This will cause a flurry of activity in the <application>repmgrd</application> log
+  files as each <application>repmgrd</application> detects the failure of the primary and a failover
   decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
   which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
   <programlisting>
@@ -61,7 +61,7 @@
     [2017-08-24 23:32:12] [NOTICE] this node is the winner, will now promote self and inform other nodes
     INFO: connecting to standby database
     NOTICE: promoting standby
-    DETAIL: promoting server using '/home/barwick/devel/builds/HEAD/bin/pg_ctl -l /tmp/postgres.5602.log -w -D '/tmp/repmgr-test/node_2/data' promote'
+    DETAIL: promoting server using 'pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' promote'
     INFO: reconnecting to promoted server
     NOTICE: STANDBY PROMOTE successful
     DETAIL: node 2 was successfully promoted to primary

doc/repmgrd-monitoring.sgml

@@ -1,7 +1,16 @@
 <chapter id="repmgrd-monitoring">
+ <indexterm>
+   <primary>repmgrd</primary>
+   <secondary>monitoring</secondary>
+ </indexterm>
+ <indexterm>
+   <primary>monitoring</primary>
+   <secondary>with repmgrd</secondary>
+ </indexterm>
+
  <title>Monitoring with repmgrd</title>
  <para>
-  When `repmgrd` is running with the option <literal>monitoring_history=true</literal>,
+   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
@@ -39,7 +48,7 @@
   specify how many day's worth of data should be retained.
  </para>
  <para>
-  It's possible to use <command>repmgrd</command> to run in monitoring
+  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,

doc/repmgrd-network-split.sgml

@@ -1,4 +1,9 @@
-<chapter id="repmgrd-network-split">
+<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
@@ -10,7 +15,7 @@
   in the main data centre and promoted a standby among themselves.
  </para>
  <para>
-  Previous &repmgr; versions used the concept of a "witness server" to
+  &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
@@ -32,8 +37,8 @@
     location='dc1'</programlisting>
  </para>
  <para>
-  In a failover situation, <command>repmgrd</command> will check if any servers in the
-  same location as the current primary node are visible.  If not, <command>repmgrd</command>
+  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 <xref linkend="repmgrd-degraded-monitoring"> mode until
   a primary becomes visible).

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

@@ -1,4 +1,9 @@
 <chapter id="performing-switchover" xreflabel="Performing a switchover with repmgr">
+
+ <indexterm>
+  <primary>switchover</primary>
+ </indexterm>
+
  <title>Performing a switchover with repmgr</title>
  <para>
   A typical use-case for replication is a combination of primary and standby
@@ -14,7 +19,7 @@
  </para>
  <para>
   <command>repmgr standby switchover</command> differs from other &repmgr;
-  actions in that it lso performs actions on another server (the demotion
+  actions in that it also performs actions on another server (the demotion
   candidate), which means passwordless SSH access is required to that server
   from the one where <command>repmgr standby switchover</command> is executed.
  </para>
@@ -39,7 +44,7 @@
   </simpara>
   <simpara>
    Please also read carefully the sections <xref linkend="preparing-for-switchover"> and
-  `Caveats` below.
+   <xref linkend="switchover-caveats"> below.
   </simpara>
  </note>
 
@@ -49,45 +54,99 @@
      <secondary>preparation</secondary>
    </indexterm>
    <title>Preparing for switchover</title>
+
    <para>
-    As mentioned above, success of the switchover operation depends on &repmgr;
-    being able to shut down the current primary server quickly and cleanly.
+    As mentioned in the previous section, success of the switchover operation depends on
+    &repmgr;  being able to shut down the current primary server quickly and cleanly.
    </para>
+
+   <para>
+     Ensure that a passwordless SSH connection is possible from the promotion candidate
+     (standby) to the demotion candidate (current primary). If <literal>--siblings-follow</literal>
+     will be used, ensure that passwordless SSH connections are possible from the
+     promotion candidate to all standbys attached to the demotion candidate.
+   </para>
+
+   <note>
+     <simpara>
+       &repmgr; expects to find the &repmgr; binary in the same path on the remote
+       server as on the local server.
+     </simpara>
+   </note>
+
    <para>
     Double-check which commands will be used to stop/start/restart the current
-    primary; on the primary execute:
+    primary; on the current primary execute:
     <programlisting>
-     repmgr -f /etc./repmgr.conf node service --list --action=stop
-     repmgr -f /etc./repmgr.conf node service --list --action=start
-     repmgr -f /etc./repmgr.conf node service --list --action=restart
-    </programlisting>
+     repmgr -f /etc/repmgr.conf node service --list --action=stop
+     repmgr -f /etc/repmgr.conf node service --list --action=start
+     repmgr -f /etc/repmgr.conf node service --list --action=restart</programlisting>
+
    </para>
+
+   <para>
+     These commands can be defined in <filename>repmgr.conf</filename> with
+     <option>service_start_command</option>, <option>service_stop_command</option>
+     and <option>service_restart_command</option>.
+   </para>
+
+   <important>
+     <para>
+       If &repmgr; is installed from a package. you should set these commands
+       to use the appropriate service commands defined by the package/operating
+       system as these will ensure PostgreSQL is stopped/started properly
+       taking into account configuration and log file locations etc.
+     </para>
+     <para>
+       If the <option>service_*_command</option> options aren't defined, &repmgr; will
+       fall back to using <application>pg_ctl</application> to stop/start/restart
+       PostgreSQL, which may not work properly, particularly when executed on a remote
+       server.
+     </para>
+     <para>
+       For more details, see <xref linkend="configuration-service-commands">.
+     </para>
+   </important>
+
    <note>
     <simpara>
      On <literal>systemd</literal> systems we strongly recommend using the appropriate
      <command>systemctl</command> commands (typically run via <command>sudo</command>) to ensure
-     <literal>systemd</literal> informed about the status of the PostgreSQL service.
+     <literal>systemd</literal> is informed about the status of the PostgreSQL service.
+    </simpara>
+    <simpara>
+     If using <command>sudo</command> for the <command>systemctl</command> calls, make sure the
+     <command>sudo</command> specification doesn't require a real tty for the user. If not set
+     this way, <command>repmgr</command> will fail to stop the primary.
     </simpara>
    </note>
+
+
    <para>
     Check that access from applications is minimalized or preferably blocked
     completely, so applications are not unexpectedly interrupted.
    </para>
+
    <para>
     Check there is no significant replication lag on standbys attached to the
     current primary.
    </para>
+
    <para>
     If WAL file archiving is set up, check that there is no backlog of files waiting
-    to be archived, as PostgreSQL will not finally shut down until all these have been
+    to be archived, as PostgreSQL will not finally shut down until all of these have been
     archived. If there is a backlog exceeding <varname>archive_ready_warning</varname> WAL files,
-    `repmgr` will emit a warning before attempting to perform a switchover; you can also check
+    &repmgr; will emit a warning before attempting to perform a switchover; you can also check
     manually with <command>repmgr node check --archive-ready</command>.
    </para>
-   <para>
-    Ensure that <command>repmgrd</command> is *not* running anywhere to prevent it unintentionally
-    promoting a node.
-   </para>
+
+   <note>
+     <para>
+       Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
+       promoting a node. This restriction will be removed in a future &repmgr; version.
+     </para>
+   </note>
+
    <para>
     Finally, consider executing <command>repmgr standby switchover</command> with the
     <literal>--dry-run</literal> option; this will perform any necessary checks and inform you about
@@ -96,7 +155,7 @@
     <programlisting>
       $ repmgr standby switchover -f /etc/repmgr.conf --siblings-follow --dry-run
       NOTICE: checking switchover on node "node2" (ID: 2) in --dry-run mode
-      INFO: SSH connection to host "localhost" succeeded
+      INFO: SSH connection to host "node1" succeeded
       INFO: archive mode is "off"
       INFO: replication lag on this standby is 0 seconds
       INFO: all sibling nodes are reachable via SSH
@@ -105,6 +164,74 @@
         "pg_ctl -l /var/log/postgresql/startup.log -D '/var/lib/postgresql/data' -m fast -W stop"
     </programlisting>
    </para>
+
+   <important>
+     <para>
+       Be aware that <option>--dry-run</option> checks the prerequisites
+       for performing the switchover and some basic sanity checks on the
+       state of the database which might effect the switchover operation
+       (e.g. replication lag); it cannot however guarantee the switchover
+       operation will succeed. In particular, if the current primary
+       does not shut down cleanly, &repmgr; will not be able to reliably
+       execute the switchover (as there would be a danger of divergence
+       between the former and new primary nodes).
+     </para>
+   </important>
+
+
+   <note>
+     <simpara>
+       See <xref linkend="repmgr-standby-switchover"> for a full list of available
+       command line options and <filename>repmgr.conf</filename> settings relevant
+       to performing a switchover.
+     </simpara>
+   </note>
+
+  <sect2 id="switchover-pg-rewind" xreflabel="Switchover and pg_rewind">
+    <indexterm>
+      <primary>pg_rewind</primary>
+      <secondary>using with "repmgr standby switchover"</secondary>
+    </indexterm>
+    <title>Switchover and pg_rewind</title>
+    <para>
+      If the demotion candidate does not shut down smoothly or cleanly, there's a risk it
+      will have a slightly divergent timeline and will not be able to attach to the new
+      primary. To fix this situation without needing to reclone the old primary, it's
+      possible to use the <application>pg_rewind</application> utility, which will usually be
+      able to resync the two servers.
+    </para>
+    <para>
+      To have &repmgr; execute <application>pg_rewind</application> if it detects this
+      situation after promoting the new primary, add the <option>--force-rewind</option>
+      option.
+    </para>
+    <note>
+      <simpara>
+        If &repmgr; detects a situation where it needs to execute <application>pg_rewind</application>,
+        it will execute a <literal>CHECKPOINT</literal> on the new primary before executing
+        <application>pg_rewind</application>.
+      </simpara>
+    </note>
+    <para>
+      For more details on <application>pg_rewind</application>, see:
+      <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
+      version 9.5. Users of versions 9.3 and 9.4 will need to manually install it; the source code is available here:
+      <ulink url="https://github.com/vmware/pg_rewind">https://github.com/vmware/pg_rewind</ulink>.
+      If the <application>pg_rewind</application>
+      binary is not installed in the PostgreSQL <filename>bin</filename> directory, provide
+      its full path  on the demotion candidate  with <option>--force-rewind</option>.
+    </para>
+    <para>
+      Note that building the 9.3/9.4 version of <application>pg_rewind</application> requires the PostgreSQL
+      source code. Also, PostgreSQL 9.3 does not provide <varname>wal_log_hints</varname>,
+      meaning data checksums must have been enabled when the database was initialized.
+    </para>
+  </sect2>
+
+
  </sect1>
 
  <sect1 id="switchover-execution" xreflabel="Executing the switchover command">
@@ -128,7 +255,7 @@
     INFO: searching for primary node
     INFO: checking if node 1 is primary
     INFO: current primary node is 1
-    INFO: SSH connection to host "localhost" succeeded
+    INFO: SSH connection to host "node1" succeeded
     INFO: archive mode is "off"
     INFO: replication lag on this standby is 0 seconds
     NOTICE: local node "node2" (ID: 2) will be promoted to primary; current primary "node1" (ID: 1) will be demoted to standby
@@ -190,15 +317,15 @@
     </listitem>
     <listitem>
      <simpara>
-      <command>repmgrd</command> should not be running with setting <varname>failover=automatic</varname>
+      <application>repmgrd</application> should not be running with setting <varname>failover=automatic</varname>
       in <filename>repmgr.conf</filename> when a switchover is carried out, otherwise the
-      <command>repmgrd</command> daemon may try and promote a standby by itself.
+      <application>repmgrd</application> daemon may try and promote a standby by itself.
      </simpara>
     </listitem>
    </itemizedlist>
   </para>
   <para>
-   We hope to remove some of these restrictions in future versions of `repmgr`.
+   We hope to remove some of these restrictions in future versions of &repmgr;.
   </para>
  </sect1>
 </chapter>

doc/upgrading-from-repmgr3.md

@@ -1,140 +1,9 @@
 Upgrading from repmgr 3
 =======================
 
-The upgrade process consists of two steps:
+This document has been integrated into the main `repmgr` documentation
+and is now located here:
 
-    1) converting the repmgr.conf configuration files
-    2) upgrading the repmgr schema
-
-A script is provided to assist with converting `repmgr.conf`.
-
-The schema upgrade (which converts the `repmgr` metadata into
-a packaged PostgreSQL extension) is normally carried out
-automatically when the `repmgr` extension is created.
+> [Upgrading from repmgr 3.x](https://repmgr.org/docs/4.0/upgrading-from-repmgr-3.html)
 
 
-Converting repmgr.conf configuration files
-------------------------------------------
-
-With a completely new repmgr version, we've taken the opportunity
-to rename some configuration items have had their names changed for
-clarity and consistency, both between the configuration file and
-the column names in `repmgr.nodes` (e.g. `node` → `node_id`), and
-also for consistency with PostgreSQL naming conventions
-(e.g. `loglevel` → `log_level`).
-
-Other configuration items have been changed to command line options,
-and vice-versa, e.g. to avoid hard-coding items such as a a node's
-upstream ID, which might change over time.
-
-`repmgr` will issue a warning about deprecated/altered options.
-
-
-### Changed parameters
-
-Following parameters have been added:
-
-    - `data_directory`: this is mandatory and must contain the path
-        to the node's data directory
-    - `monitoring_history`: this replaces the `repmgrd` command line
-        option `--monitoring-history`
-
-Following parameters have been renamed:
-
-    - `node` → `node_id`
-    - `loglevel` → `log_level`
-    - `logfacility` → `log_facility`
-    - `logfile` → `log_file`
-    - `master_reponse_timeout` → `async_query_timeout`
-
-Following parameters have been removed:
-
-    - `cluster` is no longer required and will be ignored.
-    - `upstream_node_id` is replaced by the command-line parameter
-         `--upstream-node-id`
-
-### Conversion script
-
-To assist with conversion of `repmgr.conf` files, a Perl script
-is provided in `contrib/convert-config.pl`. Use like this:
-
-    $ ./convert-config.pl /etc/repmgr.conf
-    node_id=2
-    node_name=node2
-    conninfo=host=node2 dbname=repmgr user=repmgr connect_timeout=2
-    pg_ctl_options='-l /var/log/postgres/startup.log'
-    rsync_options=--exclude=postgresql.local.conf --archive
-    log_level=INFO
-    pg_basebackup_options=--no-slot
-    data_directory=
-
-The converted file is printed to `STDOUT` and the original file is not
-changed.
-
-Please note that the parameter `data_directory` *must* be provided;
-if not already present, the conversion script will add an empty
-placeholder parameter.
-
-
-Upgrading the repmgr schema
----------------------------
-
-Ensure `repmgrd` is not running, or any cron jobs which execute the
-`repmgr` binary.
-
-Install `repmgr4`; any `repmgr3` packages should be uninstalled
-(if not automatically uninstalled already).
-
-### Upgrading from repmgr 3.1.1 or earlier
-
-If your repmgr version is 3.1.1 or earlier, you will need to update
-the schema to the latest version in the 3.x series (3.3.2) before
-converting the installation to repmgr 4.
-
-To do this, apply the following upgrade scripts as appropriate for
-your current version:
-
-    - repmgr3.0_repmgr3.1.sql
-    - repmgr3.1.1_repmgr3.1.2.sql
-
-For more details see:
-
-    https://repmgr.org/release-notes-3.3.2.html#upgrading
-
-### Manually create the repmgr extension
-
-In the database used by the existing `repmgr` configuration, execute:
-
-    CREATE EXTENSION repmgr FROM unpackaged;
-
-This will move and convert all objects from the existing schema
-into the new, standard `repmgr` schema.
-
-> *NOTE* there must be only one schema matching 'repmgr_%' in the
-> database, otherwise this step may not work.
-
-### Re-register each node
-
-This is necessary to update the `repmgr` metadata with some additional items.
-
-On the primary node, execute e.g.
-
-    repmgr primary register -f /etc/repmgr.conf --force
-
-On each standby node, execute e.g.
-
-    repmgr standby register -f /etc/repmgr.conf --force
-
-Check the data is updated as expected by examining the `repmgr.nodes` table;
-restart `repmgrd` if required.
-
-The original `repmgr_$cluster` schema can be dropped at any time.
-
-* * *
-
-> *TIP* If you don't care about any data from the existing `repmgr` installation,
-> (e.g. the contents of the `events` and `monitoring` tables), the manual
-> "CREATE EXTENSION" step can be skipped; just re-register each node, starting
-> with the primary node, and the `repmgr` extension will be automatically created.
-
-* * *

doc/upgrading-repmgr.sgml

@@ -1,24 +1,104 @@
 <chapter id="upgrading-repmgr" xreflabel="Upgrading repmgr">
+
+ <indexterm>
+  <primary>upgrading</primary>
+ </indexterm>
+
  <title>Upgrading repmgr</title>
+
  <para>
   &repmgr; is updated regularly with point releases (e.g. 4.0.1 to 4.0.2)
   containing bugfixes and other minor improvements. Any substantial new
   functionality will be included in a feature release (e.g. 4.0.x to 4.1.x).
  </para>
- <para>
-  &repmgr; is implemented as a PostgreSQL extension; to upgrade it, first
-  install the updated package (or compile the updated source), then in the
-  database where the &repmgr; extension is installed, execute
-  <command>ALTER EXTENSION repmgr UPDATE</command>.
- </para>
- <para>
-  If <command>repmgrd</command> is running, it may be necessary to restart
-  the PostgreSQL server if the upgrade contains changes to the shared object
-  file used by <command>repmgrd</command>; check the release notes for details.
- </para>
 
- <sect1 id="upgrading-from-repmgr-3">
-  <title>Upgrading from repmgr 3</title>
+ <sect1 id="upgrading-repmgr-extension" xreflabel="Upgrading repmgr 4.x and later">
+  <indexterm>
+   <primary>upgrading</primary>
+   <secondary>repmgr 4.x and later</secondary>
+  </indexterm>
+  <title>Upgrading repmgr 4.x and later</title>
+  <para>
+    &repmgr; 4.x is implemented as a PostgreSQL extension; normally the upgrade consists
+    of the two following steps:
+    <orderedlist>
+      <listitem>
+        <simpara>
+          Install the updated package (or compile the updated source)
+        </simpara>
+      </listitem>
+      <listitem>
+        <simpara>
+          In the database where the &repmgr; extension is installed, execute
+          <command>ALTER EXTENSION repmgr UPDATE</command>.
+        </simpara>
+      </listitem>
+    </orderedlist>
+  </para>
+
+  <para>
+    Always check the <link linkend="appendix-release-notes">release notes</link> for every
+    release as they may contain upgrade instructions particular to individual versions.
+  </para>
+
+  <para>
+    If the <application>repmgrd</application> daemon is in use, we recommend stopping it
+    before upgrading &repmgr;.
+  </para>
+  <para>
+    Note that it may be necessary to restart the PostgreSQL server if the upgrade contains
+    changes to the shared object file used by <application>repmgrd</application>; check the
+    release notes for details.
+  </para>
+ </sect1>
+
+ <sect1 id="upgrading-and-pg-upgrade" xreflabel="pg_upgrade and repmgr">
+  <indexterm>
+   <primary>upgrading</primary>
+   <secondary>pg_upgrade</secondary>
+  </indexterm>
+  <indexterm>
+    <primary>pg_upgrade</primary>
+  </indexterm>
+  <title>pg_upgrade and repmgr</title>
+
+  <para>
+    <application>pg_upgrade</application> requires that if any functions are
+    dependent on a shared library, this library must be present in both
+    the old and new installations before <application>pg_upgrade</application>
+    can be executed.
+  </para>
+  <para>
+    To minimize the risk of any upgrade issues (particularly if an upgrade to
+    a new major &repmgr; version is involved), we recommend upgrading
+    &repmgr; on the old server <emphasis>before</emphasis> running
+    <application>pg_upgrade</application> to ensure that old and new
+    versions are the same.
+  </para>
+  <note>
+    <simpara>
+      This issue applies to any PostgreSQL extension which has
+      dependencies on a shared library.
+    </simpara>
+  </note>
+  <para>
+    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>
+    be recreated by <application>pg_upgrade</application>. These will need to
+    be recreated manually.
+  </para>
+ </sect1>
+
+
+ <sect1 id="upgrading-from-repmgr-3" xreflabel="Upgrading from repmgr 3.x">
+  <indexterm>
+   <primary>upgrading</primary>
+   <secondary>from repmgr 3.x</secondary>
+  </indexterm>
+
+  <title>Upgrading from repmgr 3.x</title>
   <para>
    The upgrade process consists of two steps:
    <orderedlist>
@@ -29,7 +109,7 @@
     </listitem>
     <listitem>
      <simpara>
-       upgrading the repmgr schema
+       upgrading the repmgr schema using <command>CREATE EXTENSION</command>
      </simpara>
     </listitem>
    </orderedlist>
@@ -42,11 +122,19 @@
    a packaged PostgreSQL extension) is normally carried out
    automatically when the &repmgr; extension is created.
   </para>
+  <para>
+   The shared library has been renamed from <literal>repmgr_funcs</literal> to
+   <literal>repmgr</literal> - if it's set in <varname>shared_preload_libraries</varname>
+   in <filename>postgresql.conf</filename> it will need to be updated to the new name:
+   <programlisting>
+    shared_preload_libraries = 'repmgr'</programlisting>
+  </para>
+
   <sect2 id="converting-repmgr-conf">
    <title>Converting repmgr.conf configuration files</title>
    <para>
     With a completely new repmgr version, we've taken the opportunity
-    to rename some configuration items have had their names changed for
+    to rename some configuration items for
     clarity and consistency, both between the configuration file and
     the column names in <structname>repmgr.nodes</structname>
     (e.g. <varname>node</varname> to <varname>node_id</varname>), and
@@ -72,7 +160,7 @@
       </listitem>
       <listitem>
         <simpara><varname>monitoring_history</varname>: this replaces the
-          <command>repmgrd</command> command line option
+          <application>repmgrd</application> command line option
           <literal>--monitoring-history</literal></simpara>
       </listitem>
      </itemizedlist>
@@ -106,6 +194,10 @@
         <entry><varname>logfile</varname></entry>
         <entry><varname>log_file</varname></entry>
        </row>
+       <row>
+        <entry><varname>barman_server</varname></entry>
+        <entry><varname>barman_host</varname></entry>
+       </row>
        <row>
         <entry><varname>master_reponse_timeout</varname></entry>
         <entry><varname>async_query_timeout</varname></entry>
@@ -113,6 +205,16 @@
       </tbody>
      </tgroup>
     </table>
+    <note>
+      <para>
+        From &repmgr; 4, <literal>barman_server</literal> refers
+        to the server configured in Barman (in &repmgr; 3, the deprecated
+        <literal>cluster</literal> parameter was used for this);
+        the physical Barman hostname is configured with
+        <literal>barman_host</literal> (see <xref linkend="cloning-from-barman-prerequisites">
+          for details).
+      </para>
+    </note>
     <para>
      Following parameters have been removed:
      <itemizedlist spacing="compact" mark="bullet">
@@ -121,7 +223,7 @@
         be ignored.</simpara>
       </listitem>
       <listitem>
-        <simpara><varname>upstream_node_id</varname>:  is replaced by the
+        <simpara><varname>upstream_node</varname>:  is replaced by the
         command-line parameter <literal>--upstream-node-id</literal></simpara>
       </listitem>
      </itemizedlist>
@@ -137,7 +239,7 @@
     $ ./convert-config.pl /etc/repmgr.conf
     node_id=2
     node_name=node2
-    conninfo=host=localhost dbname=repmgr user=repmgr connect_timeout=2
+    conninfo=host=node2 dbname=repmgr user=repmgr connect_timeout=2
     pg_ctl_options='-l /var/log/postgres/startup.log'
     rsync_options=--exclude=postgresql.local.conf --archive
     log_level=INFO
@@ -149,21 +251,22 @@
       changed.
     </para>
     <para>
-      Please note that the parameter <varname>data_directory</varname> <emphasis>must</emphasis>
-      be provided; if not already present, the conversion script will add an empty
-      placeholder parameter.
+      Please note that the the conversion script will add an empty
+      placeholder parameter for <varname>data_directory</varname>, which
+      is a required parameter in repmgr4 and which <emphasis>must</emphasis>
+      be provided.
     </para>
    </sect3>
   </sect2>
   <sect2>
    <title>Upgrading the repmgr schema</title>
    <para>
-    Ensure <command>repmgrd</command> is not running, or any cron jobs which execute the
+    Ensure <application>repmgrd</application> is not running, or any cron jobs which execute the
     <command>repmgr</command> binary.
    </para>
    <para>
-    Install <literal>repmgr4</literal>; any <literal>repmgr3</literal> packages should be uninstalled
-    (if not automatically uninstalled already).
+    Install <literal>repmgr 4</literal> packages; any <literal>repmgr 3.x</literal> packages
+    should be uninstalled (if not automatically uninstalled already by your packaging system).
    </para>
    <sect3>
     <title>Upgrading from repmgr 3.1.1 or earlier</title>
@@ -203,7 +306,8 @@
     </para>
     <note>
       <simpara>there must be only one schema matching <literal>repmgr_%</literal> in the
-        database, otherwise this step may not work.</simpara>
+        database, otherwise this step may not work.
+      </simpara>
     </note>
    </sect3>
    <sect3>
@@ -223,7 +327,7 @@
     </para>
     <para>
      Check the data is updated as expected by examining the <structname>repmgr.nodes</structname>
-     table; restart <command>repmgrd</command> if required.
+     table; restart <application>repmgrd</application> if required.
     </para>
     <para>
      The original <literal>repmgr_$cluster</literal> schema can be dropped at any time.

doc/version.sgml

@@ -1 +1 @@
-<!ENTITY repmgrversion "4.0dev">
+<!ENTITY repmgrversion "4.0.6">

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -43,5 +43,9 @@
 #define ERR_BARMAN 19
 #define ERR_REGISTRATION_SYNC 20
 #define ERR_OUT_OF_MEMORY 21
+#define ERR_SWITCHOVER_INCOMPLETE 22
+#define ERR_FOLLOW_FAIL 23
+#define ERR_REJOIN_FAIL 24
+#define ERR_CLUSTER_CHECK 25
 
 #endif							/* _ERRCODE_H_ */

expected/repmgr_extension.out

@@ -38,33 +38,27 @@ SELECT repmgr.am_bdr_failover_handler(-1);
  
 (1 row)
 
+SELECT repmgr.am_bdr_failover_handler(NULL);
+ am_bdr_failover_handler 
+-------------------------
+ 
+(1 row)
+
 SELECT repmgr.get_new_primary();
  get_new_primary 
 -----------------
                 
 (1 row)
 
-SELECT repmgr.get_voting_status();
- get_voting_status 
--------------------
-                  
-(1 row)
-
 SELECT repmgr.notify_follow_primary(-1);
  notify_follow_primary 
 -----------------------
  
 (1 row)
 
-SELECT repmgr.other_node_is_candidate(-1,-1);
- other_node_is_candidate 
--------------------------
- 
-(1 row)
-
-SELECT repmgr.request_vote(-1,-1);
- request_vote 
---------------
+SELECT repmgr.notify_follow_primary(NULL);
+ notify_follow_primary 
+-----------------------
  
 (1 row)
 
@@ -80,10 +74,10 @@ SELECT repmgr.set_local_node_id(-1);
  
 (1 row)
 
-SELECT repmgr.set_voting_status_initiated();
- set_voting_status_initiated 
------------------------------
-                            
+SELECT repmgr.set_local_node_id(NULL);
+ set_local_node_id 
+-------------------
+ 
 (1 row)
 
 SELECT repmgr.standby_get_last_updated();

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -329,6 +329,13 @@ logger_set_terse(void)
 }
 
 
+void
+logger_set_min_level(int min_log_level)
+{
+	if (min_log_level > log_level)
+		log_level = min_log_level;
+}
+
 int
 detect_log_level(const char *level)
 {

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -128,6 +128,7 @@ bool		logger_shutdown(void);
 
 void		logger_set_verbose(void);
 void		logger_set_terse(void);
+void		logger_set_min_level(int min_log_level);
 
 void
 log_detail(const char *fmt,...)

repmgr--4.0.sql

@@ -6,7 +6,7 @@ CREATE TABLE repmgr.nodes (
   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','bdr')),
+  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,
@@ -79,6 +79,19 @@ 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 */
 /* ================= */
@@ -90,6 +103,11 @@ CREATE FUNCTION set_local_node_id(INT)
   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'
@@ -102,49 +120,6 @@ CREATE FUNCTION standby_get_last_updated()
 
 /* failover functions */
 
-
-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 FUNCTION request_vote(INT,INT)
-  RETURNS pg_lsn
-  AS 'MODULE_PATHNAME', 'request_vote'
-  LANGUAGE C STRICT;
-    $repmgr_func$;
-  ELSE
-    EXECUTE $repmgr_func$
-CREATE FUNCTION request_vote(INT,INT)
-  RETURNS TEXT
-  AS 'MODULE_PATHNAME', 'request_vote'
-  LANGUAGE C STRICT;
-    $repmgr_func$;
-  END IF;
-END$repmgr$;
-
-
-CREATE FUNCTION get_voting_status()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_voting_status'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_voting_status_initiated()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'set_voting_status_initiated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION other_node_is_candidate(INT, INT)
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'other_node_is_candidate'
-  LANGUAGE C STRICT;
-
 CREATE FUNCTION notify_follow_primary(INT)
   RETURNS VOID
   AS 'MODULE_PATHNAME', 'notify_follow_primary'
@@ -160,13 +135,11 @@ CREATE FUNCTION reset_voting_status()
   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'

repmgr--unpackaged--4.0.sql

@@ -32,7 +32,7 @@ CREATE TABLE repmgr.nodes (
   upstream_node_id INTEGER     NULL REFERENCES repmgr.nodes (node_id) DEFERRABLE,
   active           BOOLEAN     NOT NULL DEFAULT TRUE,
   node_name        TEXT        NOT NULL,
-  type             TEXT        NOT NULL CHECK (type IN('primary','standby','bdr')),
+  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,
@@ -54,8 +54,34 @@ SELECT id, upstream_node_id, active, name,
 
 ALTER TABLE repmgr.repl_events RENAME TO events;
 
+-- create new table "repmgr.voting_term"
+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;
+
+INSERT INTO repmgr.voting_term (term) VALUES (1);
+
+
 -- convert "repmgr_$cluster.repl_monitor" to "monitoring_history"
 
+
+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,
@@ -65,12 +91,32 @@ CREATE TABLE repmgr.monitoring_history (
   last_wal_standby_location      PG_LSN,
   replication_lag                BIGINT NOT NULL,
   apply_lag                      BIGINT NOT NULL
-);
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
+  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
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
 
-INSERT INTO repmgr.monitoring_history
-  (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
-SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
-  FROM repmgr.repl_monitor;
+  END IF;
+END$repmgr$;
 
 CREATE INDEX idx_monitoring_history_time
           ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
@@ -95,6 +141,16 @@ LEFT JOIN repmgr.nodes un
 
 /* 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 '$libdir/repmgr', 'standby_set_last_updated'
@@ -108,26 +164,6 @@ CREATE FUNCTION standby_get_last_updated()
 
 /* failover functions */
 
-CREATE FUNCTION request_vote(INT,INT)
-  RETURNS pg_lsn
-  AS '$libdir/repmgr', 'request_vote'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_voting_status()
-  RETURNS INT
-  AS '$libdir/repmgr', 'get_voting_status'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_voting_status_initiated()
-  RETURNS INT
-  AS '$libdir/repmgr', 'set_voting_status_initiated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION other_node_is_candidate(INT, INT)
-  RETURNS BOOL
-  AS '$libdir/repmgr', 'other_node_is_candidate'
-  LANGUAGE C STRICT;
-
 CREATE FUNCTION notify_follow_primary(INT)
   RETURNS VOID
   AS '$libdir/repmgr', 'notify_follow_primary'

repmgr-action-bdr.c

@@ -1,9 +1,9 @@
 /*
- * repmgr-action-standby.c
+ * repmgr-action-bdr.c
  *
  * Implements BDR-related actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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 @@
 /*
  * do_bdr_register()
  *
- * As each BDR node is its own master, registering a BDR node
+ * As each BDR node is its own primary, registering a BDR node
  * will create the repmgr metadata schema if necessary.
  */
 void
@@ -92,7 +92,39 @@ do_bdr_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* check whether repmgr extension exists, and that any other nodes are BDR */
+	/* check for a matching BDR node */
+	{
+		PQExpBufferData bdr_local_node_name;
+		bool		node_match = false;
+
+		initPQExpBuffer(&bdr_local_node_name);
+		node_match = bdr_node_name_matches(conn, config_file_options.node_name, &bdr_local_node_name);
+
+		if (node_match == false)
+		{
+			if (strlen(bdr_local_node_name.data))
+			{
+				log_error(_("local node BDR node name is \"%s\", expected: \"%s\""),
+						  bdr_local_node_name.data,
+						  config_file_options.node_name);
+				log_hint(_("\"node_name\" in repmgr.conf must match \"node_name\" in bdr.bdr_nodes"));
+			}
+			else
+			{
+				log_error(_("local node does not report BDR node name"));
+				log_hint(_("ensure this is an active BDR node"));
+			}
+
+			PQfinish(conn);
+			pfree(dbname);
+			termPQExpBuffer(&bdr_local_node_name);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		termPQExpBuffer(&bdr_local_node_name);
+	}
+
+	/* check whether repmgr extension exists, and there are no non-BDR nodes registered */
 	extension_status = get_repmgr_extension_status(conn);
 
 	if (extension_status == REPMGR_UNKNOWN)
@@ -142,17 +174,9 @@ do_bdr_register(void)
 
 	pfree(dbname);
 
-	/* check for a matching BDR node */
+	if (bdr_node_has_repmgr_set(conn, config_file_options.node_name) == false)
 	{
-		bool		node_exists = bdr_node_exists(conn, config_file_options.node_name);
-
-		if (node_exists == false)
-		{
-			log_error(_("no BDR node with node_name \"%s\" found"), config_file_options.node_name);
-			log_hint(_("\"node_name\" in repmgr.conf must match \"node_name\" in bdr.bdr_nodes"));
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
+		bdr_node_set_repmgr_set(conn, config_file_options.node_name);
 	}
 
 	/*

repmgr-action-bdr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-bdr.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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, 2010-2017
+ * 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
@@ -82,6 +82,7 @@ do_cluster_show(void)
 	NodeInfoListCell *cell = NULL;
 	int			i = 0;
 	ItemList	warnings = {NULL, NULL};
+	bool		success = false;
 
 	/* Connect to local database to obtain cluster connection data */
 	log_verbose(LOG_INFO, _("connecting to database"));
@@ -91,11 +92,19 @@ do_cluster_show(void)
 	else
 		conn = establish_db_connection_by_params(&source_conninfo, true);
 
-	get_all_node_records_with_upstream(conn, &nodes);
+	success = get_all_node_records_with_upstream(conn, &nodes);
+
+	if (success == false)
+	{
+		/* get_all_node_records_with_upstream() will print error message */
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
 
 	if (nodes.node_count == 0)
 	{
-		log_error(_("unable to retrieve any node records"));
+		log_error(_("no node records were found"));
+		log_hint(_("ensure at least one node is registered"));
 		PQfinish(conn);
 		exit(ERR_BAD_CONFIG);
 	}
@@ -131,8 +140,14 @@ do_cluster_show(void)
 		}
 		else
 		{
+			char		error[MAXLEN];
+
+			strncpy(error, PQerrorMessage(cell->node_info->conn), MAXLEN);
 			cell->node_info->node_status = NODE_STATUS_DOWN;
 			cell->node_info->recovery_type = RECTYPE_UNKNOWN;
+			item_list_append_format(&warnings,
+									"when attempting to connect to node \"%s\" (ID: %i), following error encountered :\n\"%s\"",
+									cell->node_info->node_name, cell->node_info->node_id, trim(error));
 		}
 
 		initPQExpBuffer(&details);
@@ -158,15 +173,13 @@ do_cluster_show(void)
 									break;
 								case RECTYPE_STANDBY:
 									appendPQExpBuffer(&details, "! running as standby");
-									item_list_append_format(
-															&warnings,
+									item_list_append_format(&warnings,
 															"node \"%s\" (ID: %i) is registered as primary but running as standby",
 															cell->node_info->node_name, cell->node_info->node_id);
 									break;
 								case RECTYPE_UNKNOWN:
 									appendPQExpBuffer(&details, "! unknown");
-									item_list_append_format(
-															&warnings,
+									item_list_append_format(&warnings,
 															"node \"%s\" (ID: %i) has unknown replication status",
 															cell->node_info->node_name, cell->node_info->node_id);
 									break;
@@ -177,16 +190,14 @@ do_cluster_show(void)
 							if (cell->node_info->recovery_type == RECTYPE_PRIMARY)
 							{
 								appendPQExpBuffer(&details, "! running");
-								item_list_append_format(
-														&warnings,
+								item_list_append_format(&warnings,
 														"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
 														cell->node_info->node_name, cell->node_info->node_id);
 							}
 							else
 							{
 								appendPQExpBuffer(&details, "! running as standby");
-								item_list_append_format(
-														&warnings,
+								item_list_append_format(&warnings,
 														"node \"%s\" (ID: %i) is registered as an inactive primary but running as standby",
 														cell->node_info->node_name, cell->node_info->node_id);
 							}
@@ -199,8 +210,7 @@ do_cluster_show(void)
 						if (cell->node_info->active == true)
 						{
 							appendPQExpBuffer(&details, "? unreachable");
-							item_list_append_format(
-													&warnings,
+							item_list_append_format(&warnings,
 													"node \"%s\" (ID: %i) is registered as an active primary but is unreachable",
 													cell->node_info->node_name, cell->node_info->node_id);
 						}
@@ -226,8 +236,7 @@ do_cluster_show(void)
 									break;
 								case RECTYPE_PRIMARY:
 									appendPQExpBuffer(&details, "! running as primary");
-									item_list_append_format(
-															&warnings,
+									item_list_append_format(&warnings,
 															"node \"%s\" (ID: %i) is registered as standby but running as primary",
 															cell->node_info->node_name, cell->node_info->node_id);
 									break;
@@ -245,16 +254,14 @@ do_cluster_show(void)
 							if (cell->node_info->recovery_type == RECTYPE_STANDBY)
 							{
 								appendPQExpBuffer(&details, "! running");
-								item_list_append_format(
-														&warnings,
+								item_list_append_format(&warnings,
 														"node \"%s\" (ID: %i) is running but the repmgr node record is inactive",
 														cell->node_info->node_name, cell->node_info->node_id);
 							}
 							else
 							{
 								appendPQExpBuffer(&details, "! running as primary");
-								item_list_append_format(
-														&warnings,
+								item_list_append_format(&warnings,
 														"node \"%s\" (ID: %i) is running as primary but the repmgr node record is inactive",
 														cell->node_info->node_name, cell->node_info->node_id);
 							}
@@ -267,8 +274,7 @@ do_cluster_show(void)
 						if (cell->node_info->active == true)
 						{
 							appendPQExpBuffer(&details, "? unreachable");
-							item_list_append_format(
-													&warnings,
+							item_list_append_format(&warnings,
 													"node \"%s\" (ID: %i) is registered as an active standby but is unreachable",
 													cell->node_info->node_name, cell->node_info->node_id);
 						}
@@ -279,6 +285,7 @@ do_cluster_show(void)
 					}
 				}
 				break;
+			case WITNESS:
 			case BDR:
 				{
 					/* node is reachable */
@@ -415,7 +422,7 @@ do_cluster_show(void)
 		printf(_("\nWARNING: following issues were detected\n"));
 		for (cell = warnings.head; cell; cell = cell->next)
 		{
-			printf(_("  %s\n"), cell->string);
+			printf(_("  - %s\n"), cell->string);
 		}
 	}
 }
@@ -435,82 +442,18 @@ void
 do_cluster_event(void)
 {
 	PGconn	   *conn = NULL;
-	PQExpBufferData query;
-	PQExpBufferData where_clause;
 	PGresult   *res;
 	int			i = 0;
+	int			column_count = EVENT_HEADER_COUNT;
 
 	conn = establish_db_connection(config_file_options.conninfo, true);
 
-	initPQExpBuffer(&query);
-	initPQExpBuffer(&where_clause);
-
-	/* LEFT JOIN used here as a node record may have been removed */
-	appendPQExpBuffer(
-					  &query,
-					  "   SELECT e.node_id, n.node_name, e.event, e.successful, \n"
-					  "          TO_CHAR(e.event_timestamp, 'YYYY-MM-DD HH24:MI:SS') AS timestamp, \n"
-					  "          e.details \n"
-					  "     FROM repmgr.events e \n"
-					  "LEFT JOIN repmgr.nodes n ON e.node_id = n.node_id ");
-
-	if (runtime_options.node_id != UNKNOWN_NODE_ID)
-	{
-
-		append_where_clause(&where_clause,
-							"n.node_id=%i", runtime_options.node_id);
-	}
-	else if (runtime_options.node_name[0] != '\0')
-	{
-		char	   *escaped = escape_string(conn, runtime_options.node_name);
-
-		if (escaped == NULL)
-		{
-			log_error(_("unable to escape value provided for node name"));
-		}
-		else
-		{
-			append_where_clause(&where_clause,
-								"n.node_name='%s'",
-								escaped);
-			pfree(escaped);
-		}
-	}
-
-	if (runtime_options.event[0] != '\0')
-	{
-		char	   *escaped = escape_string(conn, runtime_options.event);
-
-		if (escaped == NULL)
-		{
-			log_error(_("unable to escape value provided for event"));
-		}
-		else
-		{
-			append_where_clause(&where_clause,
-								"e.event='%s'",
-								escaped);
-			pfree(escaped);
-		}
-	}
-
-	appendPQExpBuffer(&query, "\n%s\n",
-					  where_clause.data);
-
-	appendPQExpBuffer(&query,
-					  " ORDER BY e.event_timestamp DESC");
-
-	if (runtime_options.all == false && runtime_options.limit > 0)
-	{
-		appendPQExpBuffer(&query, " LIMIT %i",
-						  runtime_options.limit);
-	}
-
-	log_debug("do_cluster_event():\n%s", query.data);
-	res = PQexec(conn, query.data);
-
-	termPQExpBuffer(&query);
-	termPQExpBuffer(&where_clause);
+	res = get_event_records(conn,
+							runtime_options.node_id,
+							runtime_options.node_name,
+							runtime_options.event,
+							runtime_options.all,
+							runtime_options.limit);
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
@@ -537,7 +480,11 @@ do_cluster_event(void)
 	strncpy(headers_event[EV_TIMESTAMP].title, _("Timestamp"), MAXLEN);
 	strncpy(headers_event[EV_DETAILS].title, _("Details"), MAXLEN);
 
-	for (i = 0; i < EVENT_HEADER_COUNT; i++)
+	/* if --terse provided, simply omit the "Details" column */
+	if (runtime_options.terse == true)
+		column_count --;
+
+	for (i = 0; i < column_count; i++)
 	{
 		headers_event[i].max_length = strlen(headers_event[i].title);
 	}
@@ -546,7 +493,7 @@ do_cluster_event(void)
 	{
 		int			j;
 
-		for (j = 0; j < EVENT_HEADER_COUNT; j++)
+		for (j = 0; j < column_count; j++)
 		{
 			headers_event[j].cur_length = strlen(PQgetvalue(res, i, j));
 			if (headers_event[j].cur_length > headers_event[j].max_length)
@@ -557,7 +504,7 @@ do_cluster_event(void)
 
 	}
 
-	for (i = 0; i < EVENT_HEADER_COUNT; i++)
+	for (i = 0; i < column_count; i++)
 	{
 		if (i == 0)
 			printf(" ");
@@ -570,14 +517,14 @@ do_cluster_event(void)
 	}
 	printf("\n");
 	printf("-");
-	for (i = 0; i < EVENT_HEADER_COUNT; i++)
+	for (i = 0; i < column_count; i++)
 	{
 		int			j;
 
 		for (j = 0; j < headers_event[i].max_length; j++)
 			printf("-");
 
-		if (i < (EVENT_HEADER_COUNT - 1))
+		if (i < (column_count - 1))
 			printf("-+-");
 		else
 			printf("-");
@@ -590,13 +537,13 @@ do_cluster_event(void)
 		int			j;
 
 		printf(" ");
-		for (j = 0; j < EVENT_HEADER_COUNT; j++)
+		for (j = 0; j < column_count; j++)
 		{
 			printf("%-*s",
 				   headers_event[j].max_length,
 				   PQgetvalue(res, i, j));
 
-			if (j < (EVENT_HEADER_COUNT - 1))
+			if (j < (column_count - 1))
 				printf(" | ");
 		}
 
@@ -622,6 +569,8 @@ do_cluster_crosscheck(void)
 
 	t_node_status_cube **cube;
 
+	bool		error_found = false;
+
 	n = build_cluster_crosscheck(&cube, &name_length);
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -701,9 +650,11 @@ do_cluster_crosscheck(void)
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -742,6 +693,11 @@ do_cluster_crosscheck(void)
 
 		free(cube);
 	}
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 
@@ -757,6 +713,8 @@ do_cluster_matrix()
 
 	t_node_matrix_rec **matrix_rec_list;
 
+	bool		error_found = false;
+
 	n = build_cluster_matrix(&matrix_rec_list, &name_length);
 
 	if (runtime_options.output_mode == OM_CSV)
@@ -795,9 +753,11 @@ do_cluster_matrix()
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -823,6 +783,11 @@ do_cluster_matrix()
 	}
 
 	free(matrix_rec_list);
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 
@@ -1017,8 +982,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length)
 
 		initPQExpBuffer(&command_output);
 
-		(void) remote_command(
-							  host,
+		(void) remote_command(host,
 							  runtime_options.remote_user,
 							  command.data,
 							  &command_output);
@@ -1197,13 +1161,12 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length)
 		/* fix to work with --node-id */
 		if (cube[i]->node_id == config_file_options.node_id)
 		{
-			(void) local_command(
-								 command.data,
-								 &command_output);
+			(void) local_command_simple(command.data,
+										&command_output);
 		}
 		else
 		{
-			t_conninfo_param_list remote_conninfo;
+			t_conninfo_param_list remote_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 			char	   *host = NULL;
 			PQExpBufferData quoted_command;
 
@@ -1223,8 +1186,7 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length)
 
 			log_verbose(LOG_DEBUG, "build_cluster_crosscheck(): executing\n  %s", quoted_command.data);
 
-			(void) remote_command(
-								  host,
+			(void) remote_command(host,
 								  runtime_options.remote_user,
 								  quoted_command.data,
 								  &command_output);
@@ -1323,7 +1285,7 @@ do_cluster_cleanup(void)
 
 	conn = establish_db_connection(config_file_options.conninfo, true);
 
-	/* check if there is a master in this cluster */
+	/* check if there is a primary in this cluster */
 	log_info(_("connecting to primary server"));
 	primary_conn = establish_primary_db_connection(conn, true);
 

repmgr-action-cluster.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-cluster.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -22,7 +22,6 @@
 extern void do_node_status(void);
 extern void do_node_check(void);
 
-
 extern void do_node_rejoin(void);
 extern void do_node_service(void);
 

repmgr-action-primary.c

@@ -3,7 +3,7 @@
  *
  * Implements primary actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -74,7 +74,11 @@ do_primary_register(void)
 
 	log_verbose(LOG_INFO, _("server is not in recovery"));
 
-	/* create the repmgr extension if it doesn't already exist */
+	/*
+	 * create the repmgr extension if it doesn't already exist;
+	 * note that create_repmgr_extension() will take into account
+	 * the --dry-run option
+	 */
 	if (!create_repmgr_extension(conn))
 	{
 		PQfinish(conn);
@@ -92,6 +96,7 @@ do_primary_register(void)
 		return;
 	}
 
+	initialize_voting_term(conn);
 
 	/* Ensure there isn't another registered node which is primary */
 	primary_conn = get_primary_connection(conn, &current_primary_id, NULL);
@@ -543,7 +548,8 @@ do_primary_help(void)
 	printf(_("  \"primary unregister\" unregisters an inactive primary node.\n"));
 	puts("");
 	printf(_("  --dry-run                           check what would happen, but don't actually unregister the primary\n"));
-	printf(_("  -F, --force                         force removal of the record\n"));
+	printf(_("  --node-id                           ID of the inactive primary node to unregister.\n"));
+	printf(_("  -F, --force                         force removal of an active record\n"));
 
 	puts("");
 

repmgr-action-primary.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-primary.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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, 2010-2017
+ * 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, t_node_info *primary_node_record, PQExpBufferData *output);
+extern bool do_standby_follow_internal(PGconn *primary_conn, t_node_info *primary_node_record, PQExpBufferData *output, int *error_code);
 
 
 

repmgr-action-witness.c

@@ -0,0 +1,484 @@
+/*
+ * repmgr-action-witness.c
+ *
+ * Implements witness actions for the repmgr command line utility
+ *
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <sys/stat.h>
+
+#include "repmgr.h"
+#include "dirutil.h"
+#include "compat.h"
+#include "controldata.h"
+
+#include "repmgr-client-global.h"
+#include "repmgr-action-witness.h"
+
+static char		repmgr_user[MAXLEN];
+static char		repmgr_db[MAXLEN];
+
+void
+do_witness_register(void)
+{
+	PGconn	   *witness_conn = NULL;
+	PGconn	   *primary_conn = NULL;
+	RecoveryType recovery_type = RECTYPE_UNKNOWN;
+	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
+	t_node_info node_record = T_NODE_INFO_INITIALIZER;
+	RecordStatus record_status = RECORD_NOT_FOUND;
+	bool		record_created = false;
+
+	log_info(_("connecting to witness node \"%s\" (ID: %i)"),
+			 config_file_options.node_name,
+			 config_file_options.node_id);
+
+	witness_conn = establish_db_connection_quiet(config_file_options.conninfo);
+
+	if (PQstatus(witness_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to connect to witness node \"%s\" (ID: %i)"),
+				  config_file_options.node_name,
+				  config_file_options.node_id);
+		log_detail("%s",
+				   PQerrorMessage(witness_conn));
+		log_hint(_("the witness node must be running before it can be registered"));
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* check witness node's recovery type */
+	recovery_type = get_recovery_type(witness_conn);
+
+	if (recovery_type == RECTYPE_STANDBY)
+	{
+		log_error(_("provided node is a standby"));
+		log_hint(_("a witness node must run on an independent primary server"));
+
+		PQfinish(witness_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* check that witness node is not a BDR node */
+	if (is_bdr_db_quiet(witness_conn) == true)
+	{
+		log_error(_("witness node is a BDR node"));
+		log_hint(_("a witness node cannot be configured for a BDR cluster"));
+
+		PQfinish(witness_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+
+	/* connect to primary with provided parameters */
+	log_info(_("connecting to primary node"));
+
+	/*
+	 * Extract the repmgr user and database names from the conninfo string
+	 * provided in repmgr.conf
+	 */
+	get_conninfo_value(config_file_options.conninfo, "user", repmgr_user);
+	get_conninfo_value(config_file_options.conninfo, "dbname", repmgr_db);
+
+	param_set_ine(&source_conninfo, "user", repmgr_user);
+	param_set_ine(&source_conninfo, "dbname", repmgr_db);
+
+	/* We need to connect to check configuration and copy it */
+	primary_conn = establish_db_connection_by_params(&source_conninfo, false);
+
+	if (PQstatus(primary_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to connect to the primary node"));
+		log_hint(_("a primary node must be configured before registering a witness node"));
+
+		PQfinish(witness_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* check primary node's recovery type */
+	recovery_type = get_recovery_type(primary_conn);
+
+	if (recovery_type == RECTYPE_STANDBY)
+	{
+		log_error(_("provided primary node is a standby"));
+		log_hint(_("provide the connection details of the cluster's primary server"));
+
+		PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* check that primary node is not a BDR node */
+	if (is_bdr_db_quiet(primary_conn) == true)
+	{
+		log_error(_("primary node is a BDR node"));
+		log_hint(_("a witness node cannot be configured for a BDR cluster"));
+
+		PQfinish(witness_conn);
+		PQfinish(primary_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
+	 */
+
+	/* create repmgr extension, if does not exist */
+	if (runtime_options.dry_run == false &&  !create_repmgr_extension(witness_conn))
+	{
+		PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/*
+	 * check if node record exists on primary, overwrite if -F/--force provided,
+	 * otherwise exit with error
+	 */
+
+	record_status = get_node_record(primary_conn,
+									config_file_options.node_id,
+									&node_record);
+
+	if (record_status == RECORD_FOUND)
+	{
+		/*
+		 * If node is not a witness, cowardly refuse to do anything, let the
+		 * user work out what's the correct thing to do.
+		 */
+		if (node_record.type != WITNESS)
+		{
+			log_error(_("node \"%s\" (ID: %i) is already registered as a %s node"),
+					  config_file_options.node_name,
+					  config_file_options.node_id,
+					  get_node_type_string(node_record.type));
+			log_hint(_("use \"repmgr %s unregister\" to remove a non-witness node record"),
+					 get_node_type_string(node_record.type));
+
+			PQfinish(witness_conn);
+			PQfinish(primary_conn);
+
+			exit(ERR_BAD_CONFIG);
+		}
+
+		if (!runtime_options.force)
+		{
+			log_error(_("witness node is already registered"));
+			log_hint(_("use option -F/--force to reregister the node"));
+
+			PQfinish(witness_conn);
+			PQfinish(primary_conn);
+
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+	/*
+	 * Check that an active node with the same node_name doesn't exist already
+	 */
+
+	record_status = get_node_record_by_name(primary_conn,
+											config_file_options.node_name,
+											&node_record);
+
+
+	if (record_status == RECORD_FOUND)
+	{
+		if (node_record.active == true && node_record.node_id != config_file_options.node_id)
+		{
+			log_error(_("node %i exists already with node_name \"%s\""),
+					  node_record.node_id,
+					  config_file_options.node_name);
+			PQfinish(primary_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+	/*
+	 * if repmgr.nodes contains entries, delete if -F/--force provided,
+	 * otherwise exit with error
+	 */
+	get_all_node_records(witness_conn, &nodes);
+
+	log_verbose(LOG_DEBUG, "%i node records found", nodes.node_count);
+
+	if (nodes.node_count > 0)
+	{
+		if (!runtime_options.force)
+		{
+			log_error(_("witness node is already initialised and contains node records"));
+			log_hint(_("use option -F/--force to reinitialise the node"));
+			PQfinish(primary_conn);
+			PQfinish(witness_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+	clear_node_info_list(&nodes);
+
+	if (runtime_options.dry_run == true)
+	{
+		log_info(_("prerequisites for registering the witness node are met"));
+		PQfinish(primary_conn);
+		PQfinish(witness_conn);
+		exit(SUCCESS);
+	}
+
+	/* create record on primary */
+
+	/*
+	 * node record exists - update it (at this point we have already
+	 * established that -F/--force is in use)
+	 */
+
+	init_node_record(&node_record);
+
+	/* 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 = get_primary_node_id(primary_conn);
+
+	if (record_status == RECORD_FOUND)
+	{
+		record_created = update_node_record(primary_conn,
+											"witness register",
+											&node_record);
+	}
+	else
+	{
+		record_created = create_node_record(primary_conn,
+											"witness register",
+											&node_record);
+	}
+
+	if (record_created == false)
+	{
+		log_error(_("unable to create or update node record on primary"));
+		PQfinish(primary_conn);
+		PQfinish(witness_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* sync records from primary */
+	if (witness_copy_node_records(primary_conn, witness_conn) == false)
+	{
+		log_error(_("unable to copy repmgr node records from primary"));
+		PQfinish(primary_conn);
+		PQfinish(witness_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* create event */
+	create_event_record(primary_conn,
+						&config_file_options,
+						config_file_options.node_id,
+						"witness_register",
+						true,
+						NULL);
+
+	PQfinish(primary_conn);
+	PQfinish(witness_conn);
+
+	log_info(_("witness registration complete"));
+	log_notice(_("witness node \"%s\" (ID: %i) successfully registered"),
+			   config_file_options.node_name, config_file_options.node_id);
+
+	return;
+}
+
+
+void
+do_witness_unregister(void)
+{
+	PGconn	   *witness_conn = NULL;
+	PGconn	   *primary_conn = NULL;
+	t_node_info node_record = T_NODE_INFO_INITIALIZER;
+	RecordStatus record_status = RECORD_NOT_FOUND;
+	bool		node_record_deleted = false;
+	bool		witness_available = true;
+
+	log_info(_("connecting to witness node \"%s\" (ID: %i)"),
+			 config_file_options.node_name,
+			 config_file_options.node_id);
+
+	witness_conn = establish_db_connection_quiet(config_file_options.conninfo);
+
+	if (PQstatus(witness_conn) != CONNECTION_OK)
+	{
+		if (!runtime_options.force)
+		{
+			log_error(_("unable to connect to witness node \"%s\" (ID: %i)"),
+					  config_file_options.node_name,
+					  config_file_options.node_id);
+			log_detail("%s", PQerrorMessage(witness_conn));
+			log_hint(_("provide -F/--force to remove the witness record if the server is not running"));
+			exit(ERR_BAD_CONFIG);
+		}
+
+		log_notice(_("unable to connect to witness node \"%s\" (ID: %i), removing node record on cluster primary only"),
+				   config_file_options.node_name,
+				   config_file_options.node_id);
+		witness_available = false;
+	}
+
+	if (witness_available == true)
+	{
+		primary_conn = get_primary_connection_quiet(witness_conn, NULL, NULL);
+	}
+	else
+	{
+		/*
+		 * Extract the repmgr user and database names from the conninfo string
+		 * provided in repmgr.conf
+		 */
+		get_conninfo_value(config_file_options.conninfo, "user", repmgr_user);
+		get_conninfo_value(config_file_options.conninfo, "dbname", repmgr_db);
+
+		param_set_ine(&source_conninfo, "user", repmgr_user);
+		param_set_ine(&source_conninfo, "dbname", repmgr_db);
+
+		primary_conn = establish_db_connection_by_params(&source_conninfo, false);
+
+	}
+
+	if (PQstatus(primary_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to connect to primary"));
+		log_detail("%s", PQerrorMessage(primary_conn));
+
+		if (witness_available == true)
+		{
+			PQfinish(witness_conn);
+		}
+		else
+		{
+			log_hint(_("provide connection details to primary server"));
+		}
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* Check node exists and is really a witness */
+	record_status = get_node_record(primary_conn, config_file_options.node_id, &node_record);
+
+	if (record_status != RECORD_FOUND)
+	{
+		log_error(_("no record found for node %i"), config_file_options.node_id);
+
+		if (witness_available == true)
+			PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	if (node_record.type != WITNESS)
+	{
+		log_error(_("node %i is not a witness node"), config_file_options.node_id);
+		log_detail(_("node %i is a %s node"), config_file_options.node_id, get_node_type_string(node_record.type));
+
+		if (witness_available == true)
+			PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	if (runtime_options.dry_run == true)
+	{
+		log_info(_("prerequisites for unregistering the witness node are met"));
+		if (witness_available == true)
+			PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(SUCCESS);
+	}
+
+	log_info(_("unregistering witness node %i"), config_file_options.node_id);
+	node_record_deleted = delete_node_record(primary_conn,
+										     config_file_options.node_id);
+
+	if (node_record_deleted == false)
+	{
+		PQfinish(primary_conn);
+		PQfinish(witness_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* sync records from primary */
+	if (witness_available == true && witness_copy_node_records(primary_conn, witness_conn) == false)
+	{
+		log_error(_("unable to copy repmgr node records from primary"));
+		PQfinish(primary_conn);
+		PQfinish(witness_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* Log the event */
+	create_event_record(primary_conn,
+						&config_file_options,
+						config_file_options.node_id,
+						"witness_unregister",
+						true,
+						NULL);
+
+	PQfinish(primary_conn);
+
+	if (witness_available == true)
+		PQfinish(witness_conn);
+
+	log_info(_("witness unregistration complete"));
+	log_detail(_("witness node with id %i (conninfo: %s) successfully unregistered"),
+			    config_file_options.node_id, config_file_options.conninfo);
+
+	return;
+}
+
+
+void do_witness_help(void)
+{
+	print_help_header();
+
+	printf(_("Usage:\n"));
+	printf(_("    %s [OPTIONS] witness register\n"), progname());
+	printf(_("    %s [OPTIONS] witness unregister\n"), progname());
+
+	printf(_("WITNESS REGISTER\n"));
+	puts("");
+	printf(_("  \"witness register\" registers a witness node.\n"));
+	puts("");
+	printf(_("  Requires provision of connection information for the primary\n"));
+	puts("");
+	printf(_("  --dry-run                           check prerequisites but don't make any changes\n"));
+	printf(_("  -F, --force                         overwrite an existing node record\n"));
+	puts("");
+
+	printf(_("WITNESS UNREGISTER\n"));
+	puts("");
+	printf(_("  \"witness register\" unregisters a witness node.\n"));
+	puts("");
+	printf(_("  --dry-run                           check prerequisites but don't make any changes\n"));
+	printf(_("  -F, --force                         unregister when witness node not running\n"));
+	puts("");
+
+	return;
+}

repmgr-action-witness.h

@@ -0,0 +1,27 @@
+/*
+ * repmgr-action-witness.h
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _REPMGR_ACTION_WITNESS_H_
+#define _REPMGR_ACTION_WITNESS_H_
+
+extern void do_witness_register(void);
+extern void do_witness_unregister(void);
+
+extern void do_witness_help(void);
+
+#endif							/* _REPMGR_ACTION_WITNESS_H_ */

repmgr-client-global.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client-global.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -42,6 +42,7 @@ typedef struct
 	bool		force;
 	char		pg_bindir[MAXLEN];	/* overrides setting in repmgr.conf */
 	bool		wait;
+	bool		no_wait;
 
 	/* logging options */
 	char		log_level[MAXLEN];	/* overrides setting in repmgr.conf */
@@ -68,6 +69,7 @@ typedef struct
 	int			node_id;
 	char		node_name[MAXLEN];
 	char		data_dir[MAXPGPATH];
+	int			remote_node_id;
 
 	/* "standby clone" options */
 	bool		copy_external_config_files;
@@ -79,6 +81,7 @@ typedef struct
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
+	bool		recovery_conf_only;
 
 	/* "standby clone"/"standby follow" options */
 	int			upstream_node_id;
@@ -86,10 +89,12 @@ typedef struct
 	/* "standby register" options */
 	bool		wait_register_sync;
 	int			wait_register_sync_seconds;
+	int			wait_start;
 
 	/* "standby switchover" options */
 	bool		always_promote;
-	bool		force_rewind;
+	bool		force_rewind_used;
+	char		force_rewind_path[MAXPGPATH];
 	bool		siblings_follow;
 
 	/* "node status" options */
@@ -101,6 +106,8 @@ typedef struct
 	bool		replication_lag;
 	bool		role;
 	bool		slots;
+	bool		has_passfile;
+	bool		replication_connection;
 
 	/* "node join" options */
 	char		config_files[MAXLEN];
@@ -128,30 +135,30 @@ typedef struct
 		/* configuration metadata */ \
 		false, false, false, false,	\
 		/* general configuration options */	\
-		"", false, false, "", false,	\
+		"", false, false, "", false, false,	\
 		/* logging options */ \
 		"", false, false, false, \
 		/* output options */ \
 		false, false, false,  \
 		/* database connection options */ \
-		"", "", "",	"",				  \
+		"", "", "",	"", \
 		/* other connection options */ \
-		"",	"",  \
-		/* node options */ \
-		UNKNOWN_NODE_ID, "", "", \
+		"",	"", \
+		/* general node options */ \
+		UNKNOWN_NODE_ID, "", "", UNKNOWN_NODE_ID, \
 		/* "standby clone" options */ \
 		false, CONFIG_FILE_SAMEPATH, false, false, false, "", "", "", \
-		false,  \
+		false, false, \
 		/* "standby clone"/"standby follow" options */ \
 		NO_UPSTREAM_NODE, \
 		/* "standby register" options */ \
-		false, 0, \
+		false, 0, DEFAULT_WAIT_START,   \
 		/* "standby switchover" options */ \
-		false, false, false, \
+		false, false, "", false,		   \
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, \
+		false, false, false, false, false, false, false, \
 		/* "node join" options */ \
 		"", \
 		/* "node service" options */ \
@@ -160,7 +167,7 @@ typedef struct
 		false, "", CLUSTER_EVENT_LIMIT,	\
 		/* "cluster cleanup" options */ \
 		0, \
-		/* Following options for internal use */ \
+		/* following options for internal use */ \
 		"/tmp", OM_TEXT	\
 }
 
@@ -177,6 +184,7 @@ typedef enum
 	ACTION_NONE,
 	ACTION_START,
 	ACTION_STOP,
+	ACTION_STOP_WAIT,
 	ACTION_RESTART,
 	ACTION_RELOAD,
 	ACTION_PROMOTE
@@ -202,6 +210,7 @@ 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);
 
@@ -222,7 +231,9 @@ extern void print_help_header(void);
 /* server control functions */
 extern void get_server_action(t_server_action action, char *script, char *data_dir);
 extern bool data_dir_required_for_action(t_server_action action);
+extern void get_node_config_directory(char *config_dir_buf);
 extern void get_node_data_directory(char *data_dir_buf);
 extern void init_node_record(t_node_info *node_record);
+extern bool can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *reason);
 
 #endif							/* _REPMGR_CLIENT_GLOBAL_H_ */

repmgr-client.c

@@ -1,7 +1,7 @@
 /*
  * repmgr-client.c - Command interpreter for the repmgr package
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -53,13 +53,14 @@
 
 #include "repmgr.h"
 #include "compat.h"
+#include "controldata.h"
 #include "repmgr-client.h"
 #include "repmgr-client-global.h"
 #include "repmgr-action-primary.h"
 #include "repmgr-action-standby.h"
+#include "repmgr-action-witness.h"
 #include "repmgr-action-bdr.h"
 #include "repmgr-action-node.h"
-
 #include "repmgr-action-cluster.h"
 
 #include <storage/fd.h>			/* for PG_TEMP_FILE_PREFIX */
@@ -72,7 +73,7 @@ t_runtime_options runtime_options = T_RUNTIME_OPTIONS_INITIALIZER;
 t_configuration_options config_file_options = T_CONFIGURATION_OPTIONS_INITIALIZER;
 
 /* conninfo params for the node we're operating on */
-t_conninfo_param_list source_conninfo;
+t_conninfo_param_list source_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 
 bool		config_file_required = true;
 char		pg_bindir[MAXLEN] = "";
@@ -90,11 +91,12 @@ 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)
 {
-	t_conninfo_param_list default_conninfo;
+	t_conninfo_param_list default_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 
 	int			optindex;
 	int			c;
@@ -176,7 +178,7 @@ main(int argc, char **argv)
 		strncpy(runtime_options.username, pw->pw_name, MAXLEN);
 	}
 
-	while ((c = getopt_long(argc, argv, "?Vb:f:Fd:h:p:U:R:S:L:vtD:crC:", long_options,
+	while ((c = getopt_long(argc, argv, "?Vb:f:FwWd:h:p:U:R:S:D:ck:L:tvC:", long_options,
 							&optindex)) != -1)
 	{
 		/*
@@ -241,11 +243,16 @@ main(int argc, char **argv)
 				strncpy(runtime_options.replication_user, optarg, MAXLEN);
 				break;
 
-				/* -W/--wait */
-			case 'W':
+				/* -w/--wait */
+			case 'w':
 				runtime_options.wait = true;
 				break;
 
+				/* -W/--no-wait */
+			case 'W':
+				runtime_options.no_wait = true;
+				break;
+
 				/*----------------------------
 				 * database connection options
 				 *----------------------------
@@ -328,6 +335,11 @@ main(int argc, char **argv)
 				strncpy(runtime_options.node_name, optarg, MAXLEN);
 				break;
 
+				/* --remote-node-id */
+			case OPT_REMOTE_NODE_ID:
+				runtime_options.remote_node_id = repmgr_atoi(optarg, "--remote-node-id", &cli_errors, false);
+				break;
+
 				/*
 				 * standby options * ---------------
 				 */
@@ -383,12 +395,21 @@ main(int argc, char **argv)
 				runtime_options.without_barman = true;
 				break;
 
+			case OPT_RECOVERY_CONF_ONLY:
+				runtime_options.recovery_conf_only = true;
+				break;
+
+
 				/*---------------------------
 				 * "standby register" options
 				 *---------------------------
 				 */
 
-			case OPT_REGISTER_WAIT:
+			case OPT_WAIT_START:
+				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)
 				{
@@ -406,7 +427,13 @@ main(int argc, char **argv)
 				break;
 
 			case OPT_FORCE_REWIND:
-				runtime_options.force_rewind = true;
+				runtime_options.force_rewind_used = true;
+
+				if (optarg != NULL)
+				{
+					strncpy(runtime_options.force_rewind_path, optarg, MAXPGPATH);
+				}
+
 				break;
 
 			case OPT_SIBLINGS_FOLLOW:
@@ -446,6 +473,14 @@ main(int argc, char **argv)
 				runtime_options.slots = true;
 				break;
 
+			case OPT_HAS_PASSFILE:
+				runtime_options.has_passfile = true;
+				break;
+
+			case OPT_REPL_CONN:
+				runtime_options.replication_connection = true;
+				break;
+
 				/*--------------------
 				 * "node rejoin" options
 				 *--------------------
@@ -473,10 +508,6 @@ main(int argc, char **argv)
 				runtime_options.list_actions = true;
 				break;
 
-			case OPT_CHECK:
-				runtime_options.check = true;
-				break;
-
 			case OPT_CHECKPOINT:
 				runtime_options.checkpoint = true;
 				break;
@@ -603,7 +634,7 @@ main(int argc, char **argv)
 	 * If -d/--dbname appears to be a conninfo string, validate by attempting
 	 * to parse it (and if successful, store the parsed parameters)
 	 */
-	if (runtime_options.dbname)
+	if (runtime_options.dbname[0])
 	{
 		if (strncmp(runtime_options.dbname, "postgresql://", 13) == 0 ||
 			strncmp(runtime_options.dbname, "postgres://", 11) == 0 ||
@@ -707,6 +738,7 @@ main(int argc, char **argv)
 	 *
 	 *   { PRIMARY | MASTER } REGISTER |
 	 *   STANDBY { REGISTER | UNREGISTER | CLONE [node] | PROMOTE | FOLLOW [node] | SWITCHOVER } |
+	 *   WITNESS { CREATE | REGISTER | UNREGISTER }
 	 *   BDR { REGISTER | UNREGISTER } |
 	 *   NODE { STATUS | CHECK | REJOIN | SERVICE } |
 	 *   CLUSTER { CROSSCHECK | MATRIX | SHOW | EVENT | CLEANUP }
@@ -731,7 +763,6 @@ main(int argc, char **argv)
 
 	if (repmgr_command != NULL)
 	{
-#ifndef BDR_ONLY
 		if (strcasecmp(repmgr_command, "PRIMARY") == 0 || strcasecmp(repmgr_command, "MASTER") == 0)
 		{
 			if (help_option == true)
@@ -775,10 +806,19 @@ main(int argc, char **argv)
 			else if (strcasecmp(repmgr_action, "STATUS") == 0)
 				action = NODE_STATUS;
 		}
+		else if (strcasecmp(repmgr_command, "WITNESS") == 0)
+		{
+			if (help_option == true)
+			{
+				do_witness_help();
+				exit(SUCCESS);
+			}
+			else if (strcasecmp(repmgr_action, "REGISTER") == 0)
+				action = WITNESS_REGISTER;
+			else if (strcasecmp(repmgr_action, "UNREGISTER") == 0)
+				action = WITNESS_UNREGISTER;
+		}
 		else if (strcasecmp(repmgr_command, "BDR") == 0)
-#else
-		if (strcasecmp(repmgr_command, "BDR") == 0)
-#endif
 		{
 			if (help_option == true)
 			{
@@ -970,32 +1010,10 @@ main(int argc, char **argv)
 		runtime_options.output_mode = OM_OPTFORMAT;
 	}
 
-
-
-	/* check for conflicts between runtime options and configuration file */
-	/* ================================================================== */
-
-	if (action == STANDBY_CLONE)
-	{
-		standy_clone_mode mode = get_standby_clone_mode();
-
-		if (mode == barman && runtime_options.without_barman == false
-			&& config_file_options.use_replication_slots == true)
-		{
-			log_error(_("STANDBY CLONE in Barman mode is incompatible with configuration option \"use_replication_slots\""));
-			log_hint(_("set \"use_replication_slots\" to \"no\" in repmgr.conf, or use --without-barman fo clone directly from the upstream server"));
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-
-
 	/*
 	 * Check for configuration file items which can be overriden by runtime
 	 * options
-	 */
-
-	/*
-	 * ============================================================================
+	 * =====================================================================
 	 */
 
 	/*
@@ -1049,6 +1067,17 @@ main(int argc, char **argv)
 	if (runtime_options.terse)
 		logger_set_terse();
 
+	/*
+	 * If --dry-run specified, ensure log_level is at least LOG_INFO, regardless
+	 * of what's in the configuration file or -L/--log-level paremeter, otherwise
+	 * some or output might not be displayed.
+	 */
+	if (runtime_options.dry_run == true)
+	{
+		logger_set_min_level(LOG_INFO);
+	}
+
+
 	/*
 	 * Node configuration information is not needed for all actions, with
 	 * STANDBY CLONE being the main exception.
@@ -1139,7 +1168,6 @@ main(int argc, char **argv)
 
 	switch (action)
 	{
-#ifndef BDR_ONLY
 			/* PRIMARY */
 		case PRIMARY_REGISTER:
 			do_primary_register();
@@ -1168,20 +1196,13 @@ main(int argc, char **argv)
 			do_standby_switchover();
 			break;
 
+			/* WITNESS */
+		case WITNESS_REGISTER:
+			do_witness_register();
 			break;
-#else
-			/* we won't ever reach here, but stop the compiler complaining */
-		case PRIMARY_REGISTER:
-		case PRIMARY_UNREGISTER:
-		case STANDBY_CLONE:
-		case STANDBY_REGISTER:
-		case STANDBY_UNREGISTER:
-		case STANDBY_PROMOTE:
-		case STANDBY_FOLLOW:
-		case STANDBY_SWITCHOVER:
+		case WITNESS_UNREGISTER:
+			do_witness_unregister();
 			break;
-
-#endif
 			/* BDR */
 		case BDR_REGISTER:
 			do_bdr_register();
@@ -1298,7 +1319,7 @@ check_cli_parameters(const int action)
 
 					/*
 					 * XXX if -D/--pgdata provided, and also
-					 * config_file_options.pgdaga, warn -D/--pgdata will be
+					 * config_file_options.pgdata, warn -D/--pgdata will be
 					 * ignored
 					 */
 
@@ -1317,6 +1338,15 @@ check_cli_parameters(const int action)
 										 _("--no-upstream-connection only effective in Barman mode"));
 					}
 				}
+
+				if (strlen(config_file_options.config_directory))
+				{
+					if (runtime_options.copy_external_config_files == false)
+					{
+						item_list_append(&cli_warnings,
+										 _("\"config_directory\" set in repmgr.conf, but --copy-external-config-files not provided"));
+					}
+				}
 			}
 			break;
 
@@ -1328,6 +1358,22 @@ check_cli_parameters(const int action)
 				 */
 			}
 			break;
+		case WITNESS_REGISTER:
+			{
+				if (!runtime_options.host_param_provided)
+				{
+					item_list_append_format(&cli_errors,
+											_("host name for the source node must be provided when executing %s"),
+											action_name(action));
+				}
+			}
+			break;
+		case NODE_CHECK:
+			if (runtime_options.has_passfile == true)
+			{
+				config_file_required = false;
+			}
+			break;
 		case NODE_STATUS:
 			if (runtime_options.node_id != UNKNOWN_NODE_ID)
 			{
@@ -1376,6 +1422,8 @@ check_cli_parameters(const int action)
 			case STANDBY_CLONE:
 			case STANDBY_FOLLOW:
 			case STANDBY_REGISTER:
+			case WITNESS_REGISTER:
+			case WITNESS_UNREGISTER:
 			case CLUSTER_SHOW:
 			case CLUSTER_MATRIX:
 			case CLUSTER_CROSSCHECK:
@@ -1463,6 +1511,39 @@ check_cli_parameters(const int action)
 		}
 	}
 
+	if (runtime_options.replication_user[0])
+	{
+		switch (action)
+		{
+			case PRIMARY_REGISTER:
+			case STANDBY_REGISTER:
+			case STANDBY_CLONE:
+				break;
+
+			case STANDBY_FOLLOW:
+				item_list_append_format(&cli_warnings,
+										_("--replication-user ignored when executing %s"),
+										action_name(action));
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--replication-user not required when executing %s"),
+										action_name(action));
+		}
+	}
+
+	if (runtime_options.recovery_conf_only == true)
+	{
+		switch (action)
+		{
+			case STANDBY_CLONE:
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--create-recovery-conf will be ignored when executing %s"),
+										action_name(action));
+		}
+	}
+
 	if (runtime_options.event[0])
 	{
 		switch (action)
@@ -1476,25 +1557,6 @@ check_cli_parameters(const int action)
 		}
 	}
 
-	if (runtime_options.replication_user[0])
-	{
-		switch (action)
-		{
-			case PRIMARY_REGISTER:
-			case STANDBY_REGISTER:
-				break;
-			case STANDBY_CLONE:
-			case STANDBY_FOLLOW:
-				item_list_append_format(&cli_warnings,
-										_("--replication-user ignored when executing %s)"),
-										action_name(action));
-			default:
-				item_list_append_format(&cli_warnings,
-										_("--replication-user not required when executing %s"),
-										action_name(action));
-		}
-	}
-
 	if (runtime_options.limit_provided)
 	{
 		switch (action)
@@ -1533,6 +1595,41 @@ check_cli_parameters(const int action)
 		}
 	}
 
+	/* --wait/--no-wait */
+
+	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)
+		{
+			switch (action)
+			{
+				case STANDBY_FOLLOW:
+					break;
+				default:
+					item_list_append_format(&cli_warnings,
+											_("--wait will be ignored when executing %s"),
+											action_name(action));
+			}
+		}
+		else if (runtime_options.wait)
+		{
+			switch (action)
+			{
+				case NODE_REJOIN:
+					break;
+				default:
+					item_list_append_format(&cli_warnings,
+											_("--no-wait will be ignored when executing %s"),
+											action_name(action));
+			}
+		}
+	}
+
 	/* repmgr node service --action */
 	if (runtime_options.action[0] != '\0')
 	{
@@ -1555,8 +1652,7 @@ check_cli_parameters(const int action)
 			case NODE_STATUS:
 				break;
 			default:
-				item_list_append_format(
-										&cli_warnings,
+				item_list_append_format(&cli_warnings,
 										_("--is-shutdown-cleanly will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1569,14 +1665,13 @@ check_cli_parameters(const int action)
 			case STANDBY_SWITCHOVER:
 				break;
 			default:
-				item_list_append_format(
-										&cli_warnings,
+				item_list_append_format(&cli_warnings,
 										_("--always-promote will be ignored when executing %s"),
 										action_name(action));
 		}
 	}
 
-	if (runtime_options.force_rewind == true)
+	if (runtime_options.force_rewind_used == true)
 	{
 		switch (action)
 		{
@@ -1584,8 +1679,7 @@ check_cli_parameters(const int action)
 			case NODE_REJOIN:
 				break;
 			default:
-				item_list_append_format(
-										&cli_warnings,
+				item_list_append_format(&cli_warnings,
 										_("--force-rewind will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1599,8 +1693,7 @@ check_cli_parameters(const int action)
 			case NODE_REJOIN:
 				break;
 			default:
-				item_list_append_format(
-										&cli_warnings,
+				item_list_append_format(&cli_warnings,
 										_("--config-files will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1614,12 +1707,15 @@ check_cli_parameters(const int action)
 			case PRIMARY_UNREGISTER:
 			case STANDBY_CLONE:
 			case STANDBY_REGISTER:
+			case STANDBY_FOLLOW:
 			case STANDBY_SWITCHOVER:
+			case WITNESS_REGISTER:
+			case WITNESS_UNREGISTER:
+			case NODE_REJOIN:
 			case NODE_SERVICE:
 				break;
 			default:
-				item_list_append_format(
-										&cli_warnings,
+				item_list_append_format(&cli_warnings,
 										_("--dry-run is not effective when executing %s"),
 										action_name(action));
 		}
@@ -1641,8 +1737,7 @@ check_cli_parameters(const int action)
 		if (used_options > 1)
 		{
 			/* TODO: list which options were used */
-			item_list_append(
-							 &cli_errors,
+			item_list_append(&cli_errors,
 							 "only one of --csv, --nagios and --optformat can be used");
 		}
 	}
@@ -1670,6 +1765,11 @@ action_name(const int action)
 		case STANDBY_FOLLOW:
 			return "STANDBY FOLLOW";
 
+		case WITNESS_REGISTER:
+			return "WITNESS REGISTER";
+		case WITNESS_UNREGISTER:
+			return "WITNESS UNREGISTER";
+
 		case BDR_REGISTER:
 			return "BDR REGISTER";
 		case BDR_UNREGISTER:
@@ -1741,13 +1841,12 @@ do_help(void)
 	print_help_header();
 
 	printf(_("Usage:\n"));
-#ifndef BDR_ONLY
 	printf(_("    %s [OPTIONS] primary {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow}\n"), progname());
-#endif
+	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow|switchover}\n"), progname());
 	printf(_("    %s [OPTIONS] bdr     {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] node    status\n"), progname());
+	printf(_("    %s [OPTIONS] node    {status|check|rejoin|service}\n"), progname());
 	printf(_("    %s [OPTIONS] cluster {show|event|matrix|crosscheck}\n"), progname());
+	printf(_("    %s [OPTIONS] witness {register|unregister}\n"), progname());
 
 	puts("");
 
@@ -2064,6 +2163,8 @@ test_ssh_connection(char *host, char *remote_user)
 }
 
 
+
+
 /*
  * Execute a command locally. "outputbuf" should either be an
  * initialised PQexpbuffer, or NULL
@@ -2071,9 +2172,26 @@ test_ssh_connection(char *host, char *remote_user)
 bool
 local_command(const char *command, PQExpBufferData *outputbuf)
 {
-	FILE	   *fp;
+	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)
 	{
@@ -2089,27 +2207,46 @@ local_command(const char *command, PQExpBufferData *outputbuf)
 		return false;
 	}
 
-	/* TODO: better error handling */
+
 	while (fgets(output, MAXLEN, fp) != NULL)
 	{
 		appendPQExpBuffer(outputbuf, "%s", output);
+
+		if (!feof(fp) && simple == false)
+		{
+			break;
+		}
 	}
 
-	pclose(fp);
+	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 true;
+	return success;
 }
 
 
+/*
+ * get_superuser_connection()
+ *
+ * Check if provided connection "conn" is a superuser connection, if not attempt to
+ * make a superuser connection "superuser_conn" with the provided --superuser parameter.
+ *
+ * "privileged_conn" is set to whichever connection is the superuser connection.
+ */
 void
 get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privileged_conn)
 {
 	t_connection_user userinfo = T_CONNECTION_USER_INITIALIZER;
+	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	bool		is_superuser = false;
 
 	/* this should never happen */
@@ -2118,6 +2255,7 @@ get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privil
 		log_error(_("no database connection available"));
 		exit(ERR_INTERNAL);
 	}
+
 	is_superuser = is_superuser_connection(*conn, &userinfo);
 
 	if (is_superuser == true)
@@ -2135,9 +2273,11 @@ get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privil
 		exit(ERR_BAD_CONFIG);
 	}
 
-	*superuser_conn = establish_db_connection_as_user(config_file_options.conninfo,
-													  runtime_options.superuser,
-													  false);
+	initialize_conninfo_params(&conninfo_params, false);
+	conn_to_param_list(*conn, &conninfo_params);
+	param_set(&conninfo_params, "user", runtime_options.superuser);
+
+	*superuser_conn = establish_db_connection_by_params(&conninfo_params, false);
 
 	if (PQstatus(*superuser_conn) != CONNECTION_OK)
 	{
@@ -2157,6 +2297,8 @@ get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privil
 		exit(ERR_BAD_CONFIG);
 	}
 
+	log_debug("established superuser connection as \"%s\"", runtime_options.superuser);
+
 	*privileged_conn = *superuser_conn;
 	return;
 }
@@ -2298,9 +2440,6 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 }
 
 
-
-
-
 /*
  * Execute a command via ssh on the remote host.
  *
@@ -2364,7 +2503,12 @@ remote_command(const char *host, const char *user, const char *command, PQExpBuf
 	pclose(fp);
 
 	if (outputbuf != NULL)
-		log_verbose(LOG_DEBUG, "remote_command(): output returned was:\n  %s", outputbuf->data);
+	{
+		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;
 }
@@ -2410,18 +2554,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				{
 					initPQExpBuffer(&command);
 
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
-									  &command,
+					appendShellString(&command,
 									  data_dir);
 
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  " start");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2433,6 +2574,7 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 			}
 
 		case ACTION_STOP:
+		case ACTION_STOP_WAIT:
 			{
 				if (config_file_options.service_stop_command[0] != '\0')
 				{
@@ -2442,19 +2584,23 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  "%s %s -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
-									  &command,
+					appendShellString(&command,
 									  data_dir);
 
-					appendPQExpBuffer(
-									  &command,
-									  " -m fast -W stop");
+					if (action == ACTION_STOP_WAIT)
+						appendPQExpBuffer(&command,
+										  " -w");
+					else
+						appendPQExpBuffer(&command,
+										  " -W");
+
+					appendPQExpBuffer(&command,
+									  " -m fast stop");
 
 					strncpy(script, command.data, MAXLEN);
 
@@ -2473,18 +2619,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
-									  &command,
+					appendShellString(&command,
 									  data_dir);
 
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  " restart");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2504,18 +2647,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
-									  &command,
+					appendShellString(&command,
 									  data_dir);
 
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  " reload");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2536,18 +2676,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
-									  &command,
+					appendShellString(&command,
 									  data_dir);
 
-					appendPQExpBuffer(
-									  &command,
+					appendPQExpBuffer(&command,
 									  " promote");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2581,6 +2718,7 @@ data_dir_required_for_action(t_server_action action)
 			return true;
 
 		case ACTION_STOP:
+		case ACTION_STOP_WAIT:
 			if (config_file_options.service_stop_command[0] != '\0')
 			{
 				return false;
@@ -2616,6 +2754,33 @@ data_dir_required_for_action(t_server_action action)
 }
 
 
+/*
+ * Copy the location of the configuration file directory into the
+ * provided buffer; if "config_directory" provided, use that, otherwise
+ * default to the data directory.
+ *
+ * This is primarily intended for use with "pg_ctl" (which itself shouldn't
+ * be used outside of development environments).
+ */
+void
+get_node_config_directory(char *config_dir_buf)
+{
+	if (config_file_options.config_directory[0] != '\0')
+	{
+		strncpy(config_dir_buf, config_file_options.config_directory, MAXPGPATH);
+		return;
+	}
+
+	if (config_file_options.data_directory[0] != '\0')
+	{
+		strncpy(config_dir_buf, config_file_options.data_directory, MAXPGPATH);
+		return;
+	}
+
+	return;
+}
+
+
 void
 get_node_data_directory(char *data_dir_buf)
 {
@@ -2651,7 +2816,6 @@ init_node_record(t_node_info *node_record)
 	node_record->priority = config_file_options.priority;
 	node_record->active = true;
 
-
 	if (config_file_options.location[0] != '\0')
 		strncpy(node_record->location, config_file_options.location, MAXLEN);
 	else
@@ -2664,7 +2828,7 @@ init_node_record(t_node_info *node_record)
 
 	if (config_file_options.replication_user[0] != '\0')
 	{
-		/* replication user explicitly provided */
+		/* replication user explicitly provided in configuration file */
 		strncpy(node_record->repluser, config_file_options.replication_user, NAMEDATALEN);
 	}
 	else
@@ -2678,8 +2842,80 @@ init_node_record(t_node_info *node_record)
 
 	if (config_file_options.use_replication_slots == true)
 	{
-		maxlen_snprintf(node_record->slot_name, "repmgr_slot_%i", config_file_options.node_id);
+		create_slot_name(node_record->slot_name, config_file_options.node_id);
+	}
+}
+
+
+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 (server_version_num < 90400)
+	{
+		int			data_checksum_version = get_data_checksum_version(data_directory);
+
+		if (data_checksum_version < 0)
+		{
+			appendPQExpBuffer(reason,
+							  _("unable to determine data checksum version"));
+			can_use = false;
+		}
+		else if (data_checksum_version == 0)
+		{
+			appendPQExpBuffer(reason,
+							  _("this cluster was initialised without data checksums"));
+			can_use = false;
+		}
+
+		return can_use;
 	}
 
+	/* "full_page_writes" must be on in any case */
+	if (guc_set(conn, "full_page_writes", "=", "off"))
+	{
+		if (can_use == false)
+			appendPQExpBuffer(reason, "; ");
 
+		appendPQExpBuffer(reason,
+						  _("\"full_page_writes\" must be set to \"on\""));
+
+		can_use = false;
+	}
+
+	/*
+	 * "wal_log_hints" off - are data checksums available? Note: we're
+	 * checking the local pg_control file here as the value will be the same
+	 * throughout the cluster and saves a round-trip to the demotion
+	 * candidate.
+	 */
+	if (guc_set(conn, "wal_log_hints", "=", "on") == false)
+	{
+		int			data_checksum_version = get_data_checksum_version(data_directory);
+
+		if (data_checksum_version < 0)
+		{
+			if (can_use == false)
+				appendPQExpBuffer(reason, "; ");
+
+			appendPQExpBuffer(reason,
+							  _("\"wal_log_hints\" is set to \"off\" but unable to determine data checksum version"));
+			can_use = false;
+		}
+		else if (data_checksum_version == 0)
+		{
+			if (can_use == false)
+				appendPQExpBuffer(reason, "; ");
+
+			appendPQExpBuffer(reason,
+							  _("\"wal_log_hints\" is set to \"off\" and data checksums are disabled"));
+
+			can_use = false;
+		}
+	}
+
+	return can_use;
 }

repmgr-client.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * 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
@@ -23,7 +23,6 @@
 #include "log.h"
 
 
-
 #define NO_ACTION			   0	/* Dummy default action */
 #define PRIMARY_REGISTER	   1
 #define PRIMARY_UNREGISTER	   2
@@ -33,17 +32,19 @@
 #define STANDBY_PROMOTE		   6
 #define STANDBY_FOLLOW		   7
 #define STANDBY_SWITCHOVER	   8
-#define BDR_REGISTER		   9
-#define BDR_UNREGISTER		   10
-#define NODE_STATUS			   11
-#define NODE_CHECK			   12
-#define NODE_SERVICE		   13
-#define NODE_REJOIN            14
-#define CLUSTER_SHOW		   15
-#define CLUSTER_CLEANUP		   16
-#define CLUSTER_MATRIX		   17
-#define CLUSTER_CROSSCHECK	   18
-#define CLUSTER_EVENT		   19
+#define WITNESS_REGISTER       9
+#define WITNESS_UNREGISTER     10
+#define BDR_REGISTER		   11
+#define BDR_UNREGISTER		   12
+#define NODE_STATUS			   13
+#define NODE_CHECK			   14
+#define NODE_SERVICE		   15
+#define NODE_REJOIN            16
+#define CLUSTER_SHOW		   17
+#define CLUSTER_CLEANUP		   18
+#define CLUSTER_MATRIX		   19
+#define CLUSTER_CROSSCHECK	   20
+#define CLUSTER_EVENT		   21
 
 /* command line options without short versions */
 #define OPT_HELP						   1001
@@ -55,7 +56,7 @@
 #define OPT_NODE_NAME					   1007
 #define OPT_WITHOUT_BARMAN				   1008
 #define OPT_NO_UPSTREAM_CONNECTION		   1009
-#define OPT_REGISTER_WAIT				   1010
+#define OPT_WAIT_SYNC				       1010
 #define OPT_LOG_TO_FILE					   1011
 #define OPT_UPSTREAM_CONNINFO			   1012
 #define OPT_REPLICATION_USER			   1013
@@ -66,21 +67,27 @@
 #define OPT_UPSTREAM_NODE_ID			   1018
 #define OPT_ACTION						   1019
 #define OPT_LIST_ACTIONS				   1020
-#define OPT_CHECK						   1021
-#define OPT_CHECKPOINT					   1022
-#define OPT_IS_SHUTDOWN_CLEANLY			   1023
-#define OPT_ALWAYS_PROMOTE				   1024
-#define OPT_FORCE_REWIND				   1025
-#define OPT_NAGIOS						   1026
-#define OPT_ARCHIVE_READY				   1027
-#define OPT_OPTFORMAT					   1028
-#define OPT_REPLICATION_LAG				   1029
-#define OPT_CONFIG_FILES				   1030
-#define OPT_SIBLINGS_FOLLOW				   1031
-#define OPT_ROLE						   1032
-#define OPT_DOWNSTREAM					   1033
-#define OPT_SLOTS						   1034
-#define OPT_CONFIG_ARCHIVE_DIR			   1035
+#define OPT_CHECKPOINT					   1021
+#define OPT_IS_SHUTDOWN_CLEANLY			   1022
+#define OPT_ALWAYS_PROMOTE				   1023
+#define OPT_FORCE_REWIND				   1024
+#define OPT_NAGIOS						   1025
+#define OPT_ARCHIVE_READY				   1026
+#define OPT_OPTFORMAT					   1027
+#define OPT_REPLICATION_LAG				   1028
+#define OPT_CONFIG_FILES				   1029
+#define OPT_SIBLINGS_FOLLOW				   1030
+#define OPT_ROLE						   1031
+#define OPT_DOWNSTREAM					   1032
+#define OPT_SLOTS						   1033
+#define OPT_CONFIG_ARCHIVE_DIR			   1034
+#define OPT_HAS_PASSFILE                   1035
+#define OPT_WAIT_START                     1036
+#define OPT_REPL_CONN                      1037
+#define OPT_REMOTE_NODE_ID                 1038
+#define OPT_RECOVERY_CONF_ONLY             1039
+#define OPT_NO_WAIT                        1040
+
 /* deprecated since 3.3 */
 #define OPT_DATA_DIR						999
 #define OPT_NO_CONNINFO_PASSWORD			998
@@ -98,7 +105,8 @@ static struct option long_options[] =
 	{"dry-run", no_argument, NULL, OPT_DRY_RUN},
 	{"force", no_argument, NULL, 'F'},
 	{"pg_bindir", required_argument, NULL, 'b'},
-	{"wait", no_argument, NULL, 'W'},
+	{"wait", no_argument, NULL, 'w'},
+	{"no-wait", no_argument, NULL, 'W'},
 
 /* connection options */
 	{"dbname", required_argument, NULL, 'd'},
@@ -112,6 +120,7 @@ static struct option long_options[] =
 	{"pgdata", required_argument, NULL, 'D'},
 	{"node-id", required_argument, NULL, OPT_NODE_ID},
 	{"node-name", required_argument, NULL, OPT_NODE_NAME},
+	{"remote-node-id", required_argument, NULL, OPT_REMOTE_NODE_ID},
 
 /* logging options */
 	{"log-level", required_argument, NULL, 'L'},
@@ -133,15 +142,16 @@ static struct option long_options[] =
 	{"upstream-conninfo", required_argument, NULL, OPT_UPSTREAM_CONNINFO},
 	{"upstream-node-id", required_argument, NULL, OPT_UPSTREAM_NODE_ID},
 	{"without-barman", no_argument, NULL, OPT_WITHOUT_BARMAN},
+	{"recovery-conf-only", no_argument, NULL, OPT_RECOVERY_CONF_ONLY},
 
 /* "standby register" options */
-	{"wait-sync", optional_argument, NULL, OPT_REGISTER_WAIT},
+	{"wait-start", required_argument, NULL, OPT_WAIT_START},
+	{"wait-sync", optional_argument, NULL, OPT_WAIT_SYNC},
 
 /* "standby switchover" options
  *
  * Note: --force-rewind accepted to pass to "node join"
  */
-	{"remote-config-file", required_argument, NULL, 'C'},
 	{"always-promote", no_argument, NULL, OPT_ALWAYS_PROMOTE},
 	{"siblings-follow", no_argument, NULL, OPT_SIBLINGS_FOLLOW},
 
@@ -154,15 +164,16 @@ static struct option long_options[] =
 	{"replication-lag", no_argument, NULL, OPT_REPLICATION_LAG},
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
+	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
+	{"replication-connection", no_argument, NULL, OPT_REPL_CONN},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},
     {"config-archive-dir", required_argument, NULL, OPT_CONFIG_ARCHIVE_DIR},
-	{"force-rewind", no_argument, NULL, OPT_FORCE_REWIND},
+	{"force-rewind", optional_argument, NULL, OPT_FORCE_REWIND},
 
 /* "node service" options */
 	{"action", required_argument, NULL, OPT_ACTION},
-	{"check", no_argument, NULL, OPT_CHECK},
 	{"list-actions", no_argument, NULL, OPT_LIST_ACTIONS},
 	{"checkpoint", no_argument, NULL, OPT_CHECKPOINT},
 
@@ -177,6 +188,8 @@ static struct option long_options[] =
 /* deprecated */
 	{"check-upstream-config", no_argument, NULL, OPT_CHECK_UPSTREAM_CONFIG},
 	{"no-conninfo-password", no_argument, NULL, OPT_NO_CONNINFO_PASSWORD},
+	/* previously used by "standby switchover" */
+	{"remote-config-file", required_argument, NULL, 'C'},
 	/* legacy alias for -D/--pgdata */
 	{"data-dir", required_argument, NULL, OPT_DATA_DIR},
 	/* replaced by --node-id */

repmgr.c

@@ -1,7 +1,7 @@
 /*
  * repmgr.c - repmgr extension
  *
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  *
  * This is the actual extension code; see repmgr-client.c for the code which
  * generates the repmgr binary
@@ -67,7 +67,6 @@ typedef struct repmgrdSharedState
 	TimestampTz last_updated;
 	int			local_node_id;
 	/* streaming failover */
-	NodeState	node_state;
 	NodeVotingStatus voting_status;
 	int			current_electoral_term;
 	int			candidate_node_id;
@@ -87,52 +86,30 @@ void		_PG_fini(void);
 static void repmgr_shmem_startup(void);
 
 Datum		set_local_node_id(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(set_local_node_id);
 
-Datum		standby_set_last_updated(PG_FUNCTION_ARGS);
+Datum		get_local_node_id(PG_FUNCTION_ARGS);
+PG_FUNCTION_INFO_V1(get_local_node_id);
 
+Datum		standby_set_last_updated(PG_FUNCTION_ARGS);
 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		request_vote(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(request_vote);
-
-Datum		get_voting_status(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(get_voting_status);
-
-Datum		set_voting_status_initiated(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(set_voting_status_initiated);
-
-Datum		other_node_is_candidate(PG_FUNCTION_ARGS);
-
-PG_FUNCTION_INFO_V1(other_node_is_candidate);
-
 Datum		notify_follow_primary(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(notify_follow_primary);
 
 Datum		get_new_primary(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(get_new_primary);
 
 Datum		reset_voting_status(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(reset_voting_status);
 
 Datum		am_bdr_failover_handler(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(am_bdr_failover_handler);
 
 Datum		unset_bdr_failover_handler(PG_FUNCTION_ARGS);
-
 PG_FUNCTION_INFO_V1(unset_bdr_failover_handler);
 
 
@@ -144,7 +121,6 @@ _PG_init(void)
 {
 	elog(DEBUG1, "repmgr init");
 
-	/* error here? */
 	if (!process_shared_preload_libraries_in_progress)
 		return;
 
@@ -227,12 +203,17 @@ repmgr_shmem_startup(void)
 Datum
 set_local_node_id(PG_FUNCTION_ARGS)
 {
-	int			local_node_id = PG_GETARG_INT32(0);
+	int			local_node_id = UNKNOWN_NODE_ID;
 
 	if (!shared_state)
 		PG_RETURN_NULL();
 
-	LWLockAcquire(shared_state->lock, LW_SHARED);
+	if (PG_ARGISNULL(0))
+		PG_RETURN_NULL();
+
+	local_node_id = PG_GETARG_INT32(0);
+
+	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 
 	/* only set local_node_id once, as it should never change */
 	if (shared_state->local_node_id == UNKNOWN_NODE_ID)
@@ -245,6 +226,23 @@ set_local_node_id(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+
+Datum
+get_local_node_id(PG_FUNCTION_ARGS)
+{
+	int			local_node_id = UNKNOWN_NODE_ID;
+
+	if (!shared_state)
+		PG_RETURN_NULL();
+
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+	local_node_id = shared_state->local_node_id;
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_INT32(local_node_id);
+}
+
+
 /* update and return last updated with current timestamp */
 Datum
 standby_set_last_updated(PG_FUNCTION_ARGS)
@@ -254,7 +252,7 @@ standby_set_last_updated(PG_FUNCTION_ARGS)
 	if (!shared_state)
 		PG_RETURN_NULL();
 
-	LWLockAcquire(shared_state->lock, LW_SHARED);
+	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 	shared_state->last_updated = last_updated;
 	LWLockRelease(shared_state->lock);
 
@@ -272,7 +270,7 @@ standby_get_last_updated(PG_FUNCTION_ARGS)
 	if (!shared_state)
 		PG_RETURN_NULL();
 
-	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+	LWLockAcquire(shared_state->lock, LW_SHARED);
 	last_updated = shared_state->last_updated;
 	LWLockRelease(shared_state->lock);
 
@@ -286,210 +284,20 @@ standby_get_last_updated(PG_FUNCTION_ARGS)
 /* failover functions */
 /* ===================*/
 
-Datum
-request_vote(PG_FUNCTION_ARGS)
-{
-#ifndef BDR_ONLY
-	StringInfoData query;
-
-#if (PG_VERSION_NUM >= 90400)
-	XLogRecPtr	our_lsn = InvalidXLogRecPtr;
-	bool		isnull;
-#else
-	char *value = NULL;
-	char lsn_text[64] = "";
-#endif
-
-	/* node_id used for logging purposes */
-	int			requesting_node_id = PG_GETARG_INT32(0);
-	int			current_electoral_term = PG_GETARG_INT32(1);
-
-	int			ret;
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	/* only do something if local_node_id is initialised */
-	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
-	{
-		/* this node has initiated voting or already responded to another node */
-		if (shared_state->voting_status != VS_NO_VOTE)
-		{
-			LWLockRelease(shared_state->lock);
-
-			PG_RETURN_NULL();
-		}
-
-		elog(INFO, "node %i has received request from node %i for electoral term %i (our term: %i)",
-			 shared_state->local_node_id,
-			 requesting_node_id, current_electoral_term,
-			 shared_state->current_electoral_term);
-
-		SPI_connect();
-
-		initStringInfo(&query);
-
-		appendStringInfo(
-			&query,
-#if (PG_VERSION_NUM >= 100000)
-			"SELECT pg_catalog.pg_last_wal_receive_lsn()");
-#else
-		    "SELECT pg_catalog.pg_last_xlog_receive_location()");
-#endif
-
-		elog(DEBUG1, "query: %s", query.data);
-		ret = SPI_execute(query.data, true, 0);
-
-		if (ret < 0)
-		{
-			SPI_finish();
-			elog(WARNING, "unable to retrieve last received LSN");
-			LWLockRelease(shared_state->lock);
-
-#if (PG_VERSION_NUM >= 90400)
-			PG_RETURN_LSN(InvalidOid);
-#else
-			PG_RETURN_TEXT_P(cstring_to_text("0/0"));
-#endif
-		}
-
-#if (PG_VERSION_NUM >= 90400)
-		our_lsn = DatumGetLSN(SPI_getbinval(SPI_tuptable->vals[0],
-											SPI_tuptable->tupdesc,
-											1, &isnull));
-
-		elog(DEBUG1, "our LSN is %X/%X",
-			 (uint32) (our_lsn >> 32),
-			 (uint32) our_lsn);
-#else
-		value = SPI_getvalue(SPI_tuptable->vals[0],
-							 SPI_tuptable->tupdesc,
-							 1);
-		strncpy(lsn_text, value, 64);
-		pfree(value);
-		elog(DEBUG1, "our LSN is %s", lsn_text);
-#endif
-
-		/* indicate this node has responded to a vote request */
-		shared_state->voting_status = VS_VOTE_REQUEST_RECEIVED;
-		shared_state->current_electoral_term = current_electoral_term;
-
-		/* should we free "query" here? */
-		SPI_finish();
-	}
-
-	LWLockRelease(shared_state->lock);
-
-#if (PG_VERSION_NUM >= 90400)
-	PG_RETURN_LSN(our_lsn);
-#else
-	PG_RETURN_TEXT_P(cstring_to_text(lsn_text));
-#endif
-#else
-	PG_RETURN(InvalidOid);
-#endif
-}
-
-
-
-Datum
-get_voting_status(PG_FUNCTION_ARGS)
-{
-#ifndef BDR_ONLY
-	NodeVotingStatus voting_status;
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-	voting_status = shared_state->voting_status;
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_INT32(voting_status);
-#else
-	PG_RETURN_INT32(VS_UNKNOWN);
-#endif
-}
-
-Datum
-set_voting_status_initiated(PG_FUNCTION_ARGS)
-{
-#ifndef BDR_ONLY
-	int			electoral_term = -1;
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	/* only do something if local_node_id is initialised */
-	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
-	{
-		shared_state->voting_status = VS_VOTE_INITIATED;
-		shared_state->current_electoral_term += 1;
-
-		electoral_term = shared_state->current_electoral_term;
-
-		elog(INFO, "setting voting term to %i", electoral_term);
-	}
-
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_INT32(electoral_term);
-#else
-	PG_RETURN_INT32(-1);
-#endif
-}
-
-Datum
-other_node_is_candidate(PG_FUNCTION_ARGS)
-{
-#ifndef BDR_ONLY
-	int			requesting_node_id = PG_GETARG_INT32(0);
-	int			electoral_term = PG_GETARG_INT32(1);
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	/* only do something if local_node_id is initialised */
-	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
-	{
-		if (shared_state->current_electoral_term == electoral_term)
-		{
-			if (shared_state->candidate_node_id != UNKNOWN_NODE_ID)
-			{
-				elog(INFO, "node %i requesting candidature, but node %i already candidate",
-					 requesting_node_id,
-					 shared_state->candidate_node_id);
-				PG_RETURN_BOOL(false);
-			}
-		}
-
-		shared_state->candidate_node_id = requesting_node_id;
-		elog(INFO, "node %i is candidate", requesting_node_id);
-	}
-
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_BOOL(true);
-#else
-	PG_RETURN_BOOL(false);
-#endif
-}
 
 Datum
 notify_follow_primary(PG_FUNCTION_ARGS)
 {
-#ifndef BDR_ONLY
-	int			primary_node_id = PG_GETARG_INT32(0);
+	int			primary_node_id = UNKNOWN_NODE_ID;
 
 	if (!shared_state)
 		PG_RETURN_NULL();
 
+	if (PG_ARGISNULL(0))
+		PG_RETURN_NULL();
+
+	primary_node_id = PG_GETARG_INT32(0);
+
 	LWLockAcquire(shared_state->lock, LW_SHARED);
 
 	/* only do something if local_node_id is initialised */
@@ -499,13 +307,15 @@ notify_follow_primary(PG_FUNCTION_ARGS)
 			 shared_state->local_node_id,
 			 primary_node_id);
 
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 		/* Explicitly set the primary node id */
 		shared_state->candidate_node_id = primary_node_id;
 		shared_state->follow_new_primary = true;
 	}
 
 	LWLockRelease(shared_state->lock);
-#endif
+
 	PG_RETURN_VOID();
 }
 
@@ -518,14 +328,16 @@ get_new_primary(PG_FUNCTION_ARGS)
 	if (!shared_state)
 		PG_RETURN_NULL();
 
-#ifndef BDR_ONLY
 	LWLockAcquire(shared_state->lock, LW_SHARED);
 
 	if (shared_state->follow_new_primary == true)
 		new_primary_node_id = shared_state->candidate_node_id;
 
 	LWLockRelease(shared_state->lock);
-#endif
+
+	if (new_primary_node_id == UNKNOWN_NODE_ID)
+		PG_RETURN_NULL();
+
 	PG_RETURN_INT32(new_primary_node_id);
 }
 
@@ -533,7 +345,6 @@ get_new_primary(PG_FUNCTION_ARGS)
 Datum
 reset_voting_status(PG_FUNCTION_ARGS)
 {
-#ifndef BDR_ONLY
 	if (!shared_state)
 		PG_RETURN_NULL();
 
@@ -542,13 +353,16 @@ reset_voting_status(PG_FUNCTION_ARGS)
 	/* only do something if local_node_id is initialised */
 	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
 	{
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+
 		shared_state->voting_status = VS_NO_VOTE;
 		shared_state->candidate_node_id = UNKNOWN_NODE_ID;
 		shared_state->follow_new_primary = false;
 	}
 
 	LWLockRelease(shared_state->lock);
-#endif
+
 	PG_RETURN_VOID();
 }
 
@@ -556,16 +370,23 @@ reset_voting_status(PG_FUNCTION_ARGS)
 Datum
 am_bdr_failover_handler(PG_FUNCTION_ARGS)
 {
-	int			node_id = PG_GETARG_INT32(0);
+	int			node_id = UNKNOWN_NODE_ID;
 	bool		am_handler = false;
 
 	if (!shared_state)
 		PG_RETURN_NULL();
 
+	if (PG_ARGISNULL(0))
+		PG_RETURN_NULL();
+
+	node_id = PG_GETARG_INT32(0);
+
 	LWLockAcquire(shared_state->lock, LW_SHARED);
 
 	if (shared_state->bdr_failover_handler == UNKNOWN_NODE_ID)
 	{
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 		shared_state->bdr_failover_handler = node_id;
 		am_handler = true;
 	}
@@ -586,11 +407,16 @@ unset_bdr_failover_handler(PG_FUNCTION_ARGS)
 	if (!shared_state)
 		PG_RETURN_NULL();
 
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+
 	/* only do something if local_node_id is initialised */
 	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
 	{
-		LWLockAcquire(shared_state->lock, LW_SHARED);
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+
 		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
+
 		LWLockRelease(shared_state->lock);
 	}