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

Per user report on mailing list.

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

FAQ.md

@@ -1,9 +1,7 @@
 FAQ - Frequently Asked Questions about repmgr
 =============================================
 
-The repmgr 4 FAQ is located here:
+The repmgr 4 FAQ is located here: [repmgr FAQ (Frequently Asked Questions)](https://repmgr.org/docs/4.0/appendix-faq.html "repmgr FAQ")
-
-    https://repmgr.org/docs/appendix-faq.html
 
 The repmgr 3.x FAQ can be found here:
 

HISTORY

@@ -1,6 +1,116 @@
+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.html
+        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)

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
@@ -288,6 +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;
 
@@ -303,7 +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;
@@ -314,9 +315,24 @@ _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
 	 *-----------------
@@ -336,7 +352,7 @@ _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
@@ -455,6 +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)
@@ -500,15 +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);
@@ -549,13 +583,13 @@ _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)
+		else if (strcmp(name, "standby_reconnect_timeout") == 0)
-			options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+			options->standby_reconnect_timeout = repmgr_atoi(value, name, error_list, 0);
 
 		/* witness settings */
 		else if (strcmp(name, "witness_sync_interval") == 0)
@@ -671,7 +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))
@@ -1028,7 +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;
@@ -1072,7 +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);
@@ -1099,7 +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);
@@ -1108,7 +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);
@@ -1128,7 +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);
@@ -1165,7 +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);
@@ -1205,18 +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;
@@ -1224,9 +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;
@@ -1600,31 +1634,109 @@ clear_event_notification_list(t_configuration_options *options)
 }
 
 
-bool
+int
-parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_options *backup_options, int server_version_num, ItemList *error_list)
+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;
+	options_len = strlen(string) + 1;
-	int			c,
+	options_string = pg_malloc0(options_len);
-				argc_item = 1;
+	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[] =
@@ -1650,56 +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() */
+	argc_item = parse_output_to_argv(pg_basebackup_options, &argv_array);
-	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;
 
 	/* Reset getopt's optind variable */
 	optind = 0;
@@ -1743,15 +1811,7 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 		backup_options_ok = false;
 	}
 
-	pfree(options_string);
+	free_parsed_argv(&argv_array);
-
-	{
-		int			i;
-
-		for (i = 0; i < argc_item + 2; i++)
-			pfree(argv_array[i]);
-	}
-	pfree(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;
 
@@ -82,16 +83,25 @@ 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;
 	int			archive_ready_critical;
@@ -114,7 +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;
@@ -153,11 +163,16 @@ 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 */ \
+		/* standby clone settings */ \
-		false, "", "", { NULL, NULL }, "", false, false, "",	\
+		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, \
@@ -171,7 +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 */ \
@@ -248,7 +263,6 @@ typedef struct
 }
 
 
-
 void		set_progname(const char *argv0);
 const char *progname(void);
 
@@ -263,12 +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 4.0.0.
+# 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='4.0.0'
+PACKAGE_VERSION='4.0.5'
-PACKAGE_STRING='repmgr 4.0.0'
+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 4.0.0 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 4.0.0:";;
+     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 4.0.0
+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 4.0.0, 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 4.0.0, 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 4.0.0
+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], [4.0.0], [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->state;
-		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;
 
-	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)
+	checkPoint = control_file_info->checkPoint;
-		return InvalidXLogRecPtr;
 
-	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 = (int) control_file_info->data_checksum_version;
-	{
-		data_checksum_version = -1;
-	}
-	else
-	{
-		data_checksum_version = (int) control_file_info->control_file->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",
+		log_warning(_("could not open file \"%s\" for reading"),
-				  ControlFilePath, strerror(errno));
+					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",
+		expected_size = sizeof(ControlFileData95);
-				  ControlFilePath, strerror(errno));
+		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
@@ -74,10 +74,19 @@ typedef enum
 {
 	NODE_STATUS_UNKNOWN = -1,
 	NODE_STATUS_UP,
+	NODE_STATUS_SHUTTING_DOWN,
 	NODE_STATUS_DOWN,
 	NODE_STATUS_UNCLEAN_SHUTDOWN
 } NodeStatus;
 
+typedef enum
+{
+	CONN_UNKNOWN = -1,
+	CONN_OK,
+	CONN_BAD,
+	CONN_ERROR
+} ConnectionStatus;
+
 typedef enum
 {
 	SLOT_UNKNOWN = -1,
@@ -174,11 +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 \
 }
 
 
@@ -332,9 +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);
@@ -345,10 +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);
@@ -356,10 +365,11 @@ 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);
 bool		commit_transaction(PGconn *conn);
@@ -369,10 +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,
+int		    guc_set(PGconn *conn, const char *parameter, const char *op, const char *value);
-		const char *value);
+int			guc_set_typed(PGconn *conn, const char *parameter, const char *op, const char *value, const char *datatype);
-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 */
@@ -380,7 +388,6 @@ 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);
@@ -399,6 +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);
 
@@ -409,7 +418,8 @@ 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);
@@ -418,13 +428,14 @@ 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);
 
 /* PostgreSQL configuration file location functions */
@@ -437,11 +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);
@@ -452,6 +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
@@ -473,6 +490,7 @@ bool		delete_monitoring_records(PGconn *primary_conn, int keep_history);
 
 
 /* node voting functions */
+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);
@@ -498,12 +516,17 @@ 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_name_matches(PGconn *conn, const char *node_name, PQExpBufferData *bdr_local_node_name);
-bool		bdr_node_exists(PGconn *conn, const char *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
+ * Check if a directory exists, and if so whether it is empty.
- * we use this function to check the new data directory and
- * the directories for tablespaces
  *
- * This is the same check initdb does on the new PGDATA dir
+ * This function is used for checking both the data directory
- *
+ * and tablespace directories.
- * Returns 0 if nonexistent, 1 if exists and empty, 2 if not empty,
- * or -1 if trouble accessing directory
  */
-int
+DataDirState
 check_dir(char *path)
 {
-	DIR		   *chkdir;
+	DIR		   *chkdir = NULL;
-	struct dirent *file;
+	struct dirent *file = NULL;
-	int			result = 1;
+	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"),
+	log_error(_("unable to create directory \"%s\""), path);
-			  path, strerror(errno));
+	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 can be used as a PGDATA dir */
-
-	/* Check this directory could be used as a PGDATA dir */
 	switch (check_dir(path))
 	{
-		case 0:
+		case DIR_NOENT:
-			/* dir not there, must create it */
+			/* 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:
+		case DIR_EMPTY:
-			/* Present but empty, fix permissions and use it */
+			/* exists but empty, fix permissions and use it */
-			log_info(_("checking and correcting permissions on existing directory %s"),
+			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"),
+				log_error(_("unable to change permissions of directory \"%s\""), path);
-						  path, strerror(errno));
+				log_detail("%s", strerror(errno));
 				return false;
 			}
 			break;
-		case 2:
+		case DIR_NOT_EMPTY:
-			/* Present and not empty */
+			/* exists but is not empty */
 			log_warning(_("directory \"%s\" exists but is not empty"),
 						path);
 
-			pg_dir = is_pg_dir(path);
+			if (is_pg_dir(path))
-
-			if (pg_dir && force)
 			{
-				/* TODO: check DB state, if not running overwrite */
+				if (force == true)
-
-				if (false)
 				{
-					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;
 			}
-
+			else
-			return false;
+			{
-		default:
+				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

@@ -1,5 +1,5 @@
 <appendix id="appendix-faq" xreflabel="FAQ">
-<indexterm>
+ <indexterm>
   <primary>FAQ (Frequently Asked Questions)</primary>
  </indexterm>
 
@@ -24,8 +24,9 @@
       series will no longer be actively maintained.
      </para>
      <para>
-      repmgr 2.x supports PostgreSQL 9.0 ~ 9.3. While it is compatible
+      &repmgr; 2.x supports PostgreSQL 9.0 ~ 9.3. While it is compatible
-      with PostgreSQL 9.3, we recommend using repmgr 4.x.
+      with PostgreSQL 9.3, we recommend using repmgr 4.x. &repmgr; 2.x is
+      no longer maintained.
      </para>
   </sect2>
 
@@ -35,7 +36,7 @@
     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
+    and if used &repmgr; will no longer insist on a fixed minimum number
     (default: 5000) of WAL files being retained.
    </para>
    <para>
@@ -69,12 +70,50 @@
     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="">
+  <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
@@ -83,6 +122,26 @@
    </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>
@@ -91,19 +150,23 @@
     needs to be re-registered as a standby.
    </para>
    <para>
-    In PostgreSQL 9.5 and later, it's possible to use <command>pg_rewind</command>
+    It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
-    to re-synchronise the existing data directory, which will usually be much
+    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>
-    &repmgr; provides the command <command>repmgr node rejoin</command> which can
+     Note that <command>pg_rewind</command> is available as part of the core PostgreSQL
-    optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin">
+     distribution from PostgreSQL 9.5, and as a third-party utility for PostgreSQL 9.3 and 9.4.
-    documentation for details.
    </para>
    <para>
-    If <command>pg_rewind</command> cannot be used, then the data directory will have
+    &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>
 
@@ -180,6 +243,9 @@
    </para>
   </sect2>
 
+
+
+
  </sect1>
 
  <sect1 id="faq-repmgrd" xreflabel="repmgrd">

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-release-notes.sgml

@@ -1,45 +1,860 @@
-<appendix id="appendix-release-notes" xreflabel="Release notes">
+<appendix id="appendix-release-notes">
- <title>Release notes</title>
+  <title>Release notes</title>
- <indexterm>
+  <indexterm>
-  <primary>Release notes</primary>
+    <primary>Release notes</primary>
- </indexterm>
+  </indexterm>
-
- <para>
-  Changes to each &repmgr; release are documented in the release notes.
-  Please read the release notes for all versions between
-  your current version and the version you are plan to upgrade to
-  before performing an upgrade, as there may be version-specific upgrade steps.
- </para>
-
-
- <para>
-  See also: <xref linkend="upgrading-repmgr">
- </para>
-
- <sect1 id="release-4.0">
-  <title>Release 4.0beta1</title>
-
-  <para><emphasis>Thu Oct 5, 2017</emphasis></para>
 
   <para>
-    repmgr 4.0 is an entirely new version of &repmgr;, providing many
+    Changes to each &repmgr; release are documented in the release notes.
-    improvements together with some changes in the way it works.
+    Please read the release notes for all versions between
-    In particular changes have been made to some configuration file
+    your current version and the version you are plan to upgrade to
-    settings and command line options for consistency and clarity.
+    before performing an upgrade, as there may be version-specific upgrade steps.
-  </para>
-  <para>
-    For detailed instructions on upgrading from repmgr 3.x, see
-    <xref linkend="upgrading-from-repmgr-3">.
   </para>
 
-  <note>
+  <para>
+    See also: <xref linkend="upgrading-repmgr">
+  </para>
+
+  <sect1 id="release-4.0.6">
+    <title>Release 4.0.6</title>
+    <para><emphasis>June 14, 2018</emphasis></para>
     <para>
+	  &repmgr; 4.0.6 contains a number of bug fixes and usability enhancements.
+    </para>
+	<para>
+	  We recommend upgrading to this version as soon as possible.
+	  This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.5;
+      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      for more details.
+	</para>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command> and
+              <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command>:
+              return non-zero exit code if node connection issues detected (GitHub #447)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Improve handling of external configuration file copying,  including consideration in
+			   <option>--dry-run</option> check
+			   (GitHub #443)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              When using <option>--dry-run</option>, force log level to <literal>INFO</literal>
+			  to ensure output will always be displayed
+			  (GitHub #441)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Improve documentation of <option>--recovery-conf-only</option> mode
+			   (GitHub #438)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+			   Don't require presence of <varname>user</varname> parameter in conninfo string
+			   (GitHub #437)
+           </para>
+          </listitem>
+
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>:
+              prevent registration of a witness server with the same name as an existing node
+           </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>:
+			   check node has actually connected to new primary before reporting success
+			   (GitHub #444)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
+			   Fix bug when parsing <option>--config-files</option> parameter
+			   (GitHub #442)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: ensure local node is counted as quorum member
+			  (GitHub #439)
+           </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
+  <sect1 id="release-4.0.5">
+    <title>Release 4.0.5</title>
+    <para><emphasis>Wed May 2, 2018</emphasis></para>
+    <para>
+      &repmgr; 4.0.5 contains a number of usability enhancements related to
+      <application>pg_rewind</application> usage, <filename>recovery.conf</filename>
+      generation and (in <application>repmgrd</application>) handling of various
+      corner-case situations, as well as a number of bug fixes.
+    </para>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Various documentation improvements, with particular emphasis on
+              the importance of setting appropriate <link linkend="configuration-service-commands">service commands</link>
+              instead of relying on <application>pg_ctl</application>.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Poll demoted primary after restart as a standby during a switchover operation (GitHub #408).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add configuration parameter <option>config_directory</option> (GitHub #424).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add sanity check if <option>--upstream-node-id</option> not supplied when executing
+              <xref linkend="repmgr-standby-register"> (GitHub #395).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Enable <link linkend="repmgr-node-rejoin-pg-rewind">pg_rewind</link> to be used with
+              PostgreSQL 9.3/9.4 (GitHub #413).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              When generating replication connection strings, set <literal>dbname=replication</literal>
+              if appropriate (GitHub #421).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Enable provision of <option>archive_cleanup_command</option> in <filename>recovery.conf</filename>
+              (GitHub #416).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Actively check for node to <link linkend="repmgr-node-rejoin">rejoin</link> cluster (GitHub #415).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: set <literal>connect_timeout=2</literal> (if not explicitly set)
+              when pinging a server.
+           </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+
+    </sect2>
+
+   <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              Fix display of conninfo parsing error messages.
+           </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              Fix minimum accepted value for <varname>degraded_monitoring_timeout</varname> (GitHub #411).
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Fix superuser password handling (GitHub #400)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Fix parsing of <varname>archive_ready_critical</varname> configuration file parameter (GitHub #426).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Fix <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command>
+              output (GitHub #389)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               Fix memory leaks in witness code (GitHub #402).
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: handle <command>pg_ctl promote</command> timeout (GitHub #425).
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: handle failover situation with only two nodes in the primary
+          location, and at least one node in another location (GitHub #407).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+               <application>repmgrd</application>: prevent standby connection handle from going stale.
+           </para>
+          </listitem>
+
+
+
+        </itemizedlist>
+      </para>
+   </sect2>
+
+  </sect1>
+
+
+  <sect1 id="release-4.0.4">
+    <title>Release 4.0.4</title>
+    <para><emphasis>Fri Mar 9, 2018</emphasis></para>
+
+    <para>
+      &repmgr; 4.0.4 contains some bug fixes and and a number of
+      usability enhancements related to logging/diagnostics,
+      event notifications and pre-action checks.
+    </para>
+    <para>
+      This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.3;
+      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      for more details.
+    </para>
+
+    <note>
+      <para>
+        It is not possible to perform a switchover where the demotion candidate is
+        running &repmgr; 4.0.2 or lower; all nodes should be upgraded to the latest version (4.0.4).
+        This is due to additional checks introduced in 4.0.3 which require the presence of
+        4.0.3 or later versions on all nodes.
+      </para>
+    </note>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              add <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>
+              option to enable integration of a standby cloned from another source into a &repmgr; cluster (GitHub #382)
+            </para>
+          </listitem>
+
+         <listitem>
+            <para>
+              remove restriction on using replication slots when cloning from a Barman server (GitHub #379)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              make <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command>
+              timeout values configurable (GitHub #387)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              add missing options to main <literal>--help</literal> output (GitHub #391, #392)
+            </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              ensure <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
+              honours the <option>--dry-run</option> option (GitHub #383)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              improve replication slot warnings generated by
+              <command><link linkend="repmgr-node-status">repmgr node status</link></command>
+              (GitHub #385)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              fix --superuser handling when cloning a standby (GitHub #380)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: improve detection of status change from primary to
+              standby
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>:  improve reconnection to the local node after a
+              failover (previously a connection error due to the node starting up was being
+              interpreted as the node being unavailable)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: when running on a witness server, correctly connect
+              to new primary after a failover
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: add <link linkend="event-notifications">event notification</link>
+              <literal>repmgrd_shutdown</literal> (GitHub #393)
+           </para>
+          </listitem>
+
+        </itemizedlist>
+
+      </para>
+    </sect2>
+
+  </sect1>
+
+  <sect1 id="release-4.0.3">
+    <title>Release 4.0.3</title>
+    <para><emphasis>Thu Feb 15, 2018</emphasis></para>
+
+    <para>
+      &repmgr; 4.0.3 contains some bug fixes and and a number of
+      usability enhancements related to logging/diagnostics,
+      event notifications and pre-action checks.
+    </para>
+
+    <para>
+      This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.2;
+      repmgrd (if running) should be restarted.
+    </para>
+    <note>
+      <para>
+        It is not possible to perform a switchover where the demotion candidate is
+        running &repmgr; 4.0.2 or lower; all nodes should be upgraded to 4.0.3. This is due
+        to additional checks introduced in 4.0.3 which require the presence of
+        4.0.3 or later versions on all nodes.
+      </para>
+    </note>
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              improve <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>
+              behaviour when <command>pg_ctl</command> is used to control the server and logging output is
+              not explicitly redirected
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              improve <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>
+              log messages and provide new exit code <literal>ERR_SWITCHOVER_INCOMPLETE</literal> when old primary could
+              not be shut down cleanly
+            </para>
+          </listitem>
+
+         <listitem>
+            <para>
+              add check to verify the demotion candidate can make a replication connection to the
+              promotion candidate before executing a switchover (GitHub #370)
+            </para>
+         </listitem>
+
+         <listitem>
+            <para>
+              add check for sufficient walsenders and replication slots on the promotion candidate  before executing
+              <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>
+              (GitHub #371)
+            </para>
+         </listitem>
+
+          <listitem>
+            <para>
+              add --dry-run mode to <command><link linkend="repmgr-standby-switchover">repmgr standby follow</link></command>
+              (GitHub #368)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              provide information about the primary node for
+              <command><link linkend="repmgr-standby-register">repmgr standby register</link></command> and
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command> event notifications (GitHub #375)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              add <literal>standby_register_sync</literal> <link linkend="event-notifications">event notification</link>, which is fired when
+              <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>
+              is run with the <option>--wait-sync</option> option and the new or updated standby node
+              record has synchronised to the standby (GitHub #374)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              when running <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>,
+              if any node is unreachable, output the error message encountered in the list of warnings
+              (GitHub #369)
+            </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              ensure an inactive data directory can be overwritten when
+              cloning a standby (GitHub #366)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-node-status">repmgr node status</link></command>
+              upstream node display fixed (GitHub #363)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-primary-unregister">repmgr primary unregister</link></command>:
+              clarify usage and fix <literal>--help</literal> output (GitHub #373)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              parsing of <varname>pg_basebackup_options</varname> fixed (GitHub #376)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              ensure the <filename>pg_subtrans</filename> directory is created when cloning a
+              standby in Barman mode
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-witness-register">repmgr witness register</link></command>:
+              fix primary node check (GitHub #377).
+            </para>
+          </listitem>
+        </itemizedlist>
+
+      </para>
+    </sect2>
+
+  </sect1>
+
+
+  <sect1 id="release-4.0.2">
+    <title>Release 4.0.2</title>
+    <para><emphasis>Thu Jan 18, 2018</emphasis></para>
+
+    <para>
+      &repmgr; 4.0.2 contains some bug fixes and small usability enhancements.
+    </para>
+    <para>
+      This release can be installed as a simple package upgrade from &repmgr; 4.0.1 or 4.0;
+      <application>repmgrd</application> (if running) should be restarted.
+    </para>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Recognize the <option>-t</option>/<option>--terse</option> option for
+              <command><link linkend="repmgr-cluster-event">repmgr cluster event</link></command> to hide
+              the <literal>Details</literal> column (GitHub #360)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add "--wait-start" option for
+              <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>
+              (GitHub #356)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add <literal>%p</literal> <link linkend="event-notifications">event notification parameter</link>
+              for <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Add missing -W option to <literal>getopt_long()</literal> invocation (GitHub #350)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Automatically create slot name if missing (GitHub #343)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Fixes to parsing output of remote repmgr invocations (GitHub #349)
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              When registering BDR nodes, automatically create missing connection replication set (GitHub #347)
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              Handle missing node record in <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
+              (GitHub #358)
+            </para>
+          </listitem>
+
+
+        </itemizedlist>
+      </para>
+
+    </sect2>
+
+    <sect2>
+      <title>Documentation</title>
+
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              The documentation can now be built as a single HTML file (GitHub pull request #353)
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
+ <sect1 id="release-4.0.1">
+  <title>Release 4.0.1</title>
+
+  <para><emphasis>Wed Dec 13, 2017</emphasis></para>
+
+  <para>
+    &repmgr; 4.0.1 is a bugfix release.
+  </para>
+  <sect2>
+    <title>Bug fixes</title>
+    <para>
+      <itemizedlist>
+        <listitem>
+          <para>
+            ensure correct return codes are returned for
+            <command><link linkend="repmgr-node-check">repmgr node check --action=</link></command> operations
+            (GitHub #340)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Fix <xref linkend="repmgr-cluster-show"> when <literal>repmgr</literal> schema not set in search path
+            (GitHub #341)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            When using <literal>--force-rewind</literal> with <xref linkend="repmgr-node-rejoin">
+            delete any replication slots copied by <application>pg_rewind</application>
+            (GitHub #334)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Only perform sanity check on accessibility of configuration files outside
+            the data directory when <literal>--copy-external-config-files</literal>
+            provided (GitHub #342)
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            Initialise "voting_term" table in application, not extension SQL
+            (GitHub #344)
+          </para>
+        </listitem>
+
+      </itemizedlist>
+    </para>
+  </sect2>
+ </sect1>
+
+
+
+ <sect1 id="release-4.0.0">
+  <title>Release 4.0.0</title>
+
+  <para><emphasis>Tue Nov 21, 2017</emphasis></para>
+
+  <para>
+    repmgr 4.0 is an entirely new version of &repmgr;, implementing &repmgr;
+    as a native PostgreSQL extension, adding new and improving existing features,
+    and making &repmgr; more user-friendly and intuitive to use. The new code base
+    will make it easier to add additional functionality for future releases.
+  </para>
+  <note>
+    <simpara>
+      With the new version, the opportunity has been taken to
+      make some changes in the way &repmgr; is set up and
+      configured. In particular changes have been made to some
+      configuration file settings consistency for and clarity.
+      Changes are covered in detail below
+    </simpara>
+    <simpara>
       To standardise terminology, from this release <literal>primary</literal> is used to
       denote the read/write node in a streaming replication cluster. <literal>master</literal>
       is still accepted as an alias for &repmgr; commands
       (e.g. <link linkend="repmgr-primary-register"><command>repmgr master register</command></link>).
-    </para>
+    </simpara>
   </note>
+
+  <para>
+    For detailed instructions on upgrading from repmgr 3.x, see <xref linkend="upgrading-from-repmgr-3">.
+  </para>
+
+  <sect2>
+    <title>Features and improvements</title>
+    <para>
+
+      <itemizedlist>
+        <listitem>
+          <para>
+            <emphasis>improved switchover</emphasis>:
+            the <command>switchover</command> process has been improved and streamlined,
+            speeding up the switchover process and can also instruct other standbys
+            to follow the new primary once the switchover has completed. See
+             <xref linkend="performing-switchover"> for more details.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+           <emphasis>"--dry-run" option</emphasis>: many &repmgr; commands now provide
+           a <literal>--dry-run</literal> option which will execute the command as far
+           as possible without making any changes, which will enable possible issues
+           to be identified before the intended operation is actually carried out.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <emphasis>easier upgrades</emphasis>: &repmgr; is now implemented as a native
+            PostgreSQL extension, which means future upgrades can be carried out by
+            installing the upgraded package and issuing
+            <ulink url="https://www.postgresql.org/docs/current/static/sql-alterextension.html">ALTER EXTENSION repmgr UPDATE</ulink>.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>improved logging output</emphasis>:
+            &repmgr; (and <application>repmgrd</application>) now provide more explicit
+            logging output giving a better picture of what is going on. Where appropriate,
+            <literal>DETAIL</literal> and <literal>HINT</literal> log lines provide additional
+            detail and suggestions for resolving problems. Additionally, <application>repmgrd</application>
+            now emits informational log lines at regular, configurable intervals
+            to confirm that it's running correctly and which node(s) it's monitoring.
+          </para>
+        </listitem>
+
+        <listitem>
+          <para>
+            <emphasis>automatic configuration file location in packages</emphasis>:
+            Many operating system packages place the &repmgr; configuration files
+            in a version-specific subdirectory, e.g. <filename>/etc/repmgr/9.6/repmgr.conf</filename>;
+            &repmgr; now makes it easy for package maintainers to provide a patch
+            with the actual file location, meaning <filename>repmgr.conf</filename>
+            does not need to be provided explicitly. This is currently the case
+            for 2ndQuadrant-provided <literal>.deb</literal> and <literal>.rpm</literal> packages.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>monitoring and status checks</emphasis>:
+            New commands <xref linkend="repmgr-node-check"> and
+            <xref linkend="repmgr-node-status"> providing information
+            about a node's status and replication-related monitoring
+            output.
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>node rejoin</emphasis>:
+            New commands <xref linkend="repmgr-node-rejoin"> enables a failed
+            primary to be rejoined to a replication cluster, optionally using
+            <application>pg_rewind</application> to synchronise its data,
+            (note that <application>pg_rewind</application> may not be useable
+            in some circumstances).
+          </para>
+        </listitem>
+
+
+        <listitem>
+          <para>
+            <emphasis>automatic failover</emphasis>:
+            improved detection of node status; promotion decision based on a consensual
+            model, with the promoted primary explicitly informing other standbys to
+            follow it. The <application>repmgrd</application> daemon will continue
+            functioning even if the monitored PostgreSQL instance is down, and resume
+            monitoring if it reappears. Additionally, if the instance's role has changed
+            (typically from a primary to a standby, e.g. following reintegration of a
+            failed primary using <xref linkend="repmgr-node-rejoin">) <application>repmgrd</application>
+            will automatically resume monitoring it as a standby.
+          </para>
+        </listitem>
+
+
+
+        <listitem>
+          <para>
+            <emphasis>new documentation</emphasis>:
+            the existing documentation spread over multiple text files
+            has been consolidated into DocBook format (as used by the
+            main PostgreSQL project) and is now available online in
+            HTML format.
+          </para>
+          <para>
+            The DocBook files can easily be used to create versions
+            of the documentation in other formats such as PDF.
+          </para>
+        </listitem>
+
+      </itemizedlist>
+
+    </para>
+  </sect2>
   <sect2>
     <title>New command line options</title>
     <para>
@@ -236,7 +1051,7 @@
   <sect2>
     <title>repmgrd</title>
     <para>
-      The `repmgr` shared library has been renamed from <literal>repmgr_funcs</literal> to
+      The shared library has been renamed from <literal>repmgr_funcs</literal> to
       <literal>repmgr</literal>,  meaning <varname>shared_preload_libraries</varname>
       in <filename>postgresql.conf</filename> needs to be updated to the new name:
       <programlisting>

doc/appendix-signatures.sgml

@@ -33,34 +33,5 @@
 
  </sect1>
 
- <sect1 id="repmgr-rpm-key" xreflabel="repmgr rpm key">
-   <title>repmgr RPM signing key</title>
-   <para>
-     The signing key ID used for <application>repmgr</application> source code bundles is:
-     <ulink url="http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr">
-       <literal>0x702D883A</literal></ulink>.
-   </para>
-
-   <para>
-     To download the <application>repmgr</application> source key to your computer:
-     <programlisting>
-       curl -s http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr | gpg --import
-       gpg --fingerprint 0x702D883A
-     </programlisting>
-     then verify that the fingerprint is the expected value:
-     <programlisting>
-       AE4E 390E A58E 0037 6148  3F29 888D 018B 702D 883A</programlisting>
-   </para>
-
-   <para>
-     To check a repository RPM, use <application>rpmkeys</application> to load the
-      packaging signing key into the RPM database then use <literal>rpm -K</literal>, e.g.:
-     <programlisting>
-       sudo rpmkeys --import http://packages.2ndquadrant.com/repmgr/RPM-GPG-KEY-repmgr
-       rpm -K postgresql-bdr94-2ndquadrant-redhat-1.0-2.noarch.rpm
-     </programlisting>
-   </para>
-
- </sect1>
 
 </appendix>

doc/cloning-standbys.sgml

@@ -51,7 +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
@@ -356,7 +356,7 @@
      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 (typically the primary)
+     Note that this may impact performance of the server being cloned from (typically the primary)
      so should be used with care.
     </para>
     <tip>
@@ -384,11 +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
+     the standby must be able to provide the password so it can begin streaming replication.
-     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
@@ -396,6 +401,17 @@
      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
@@ -407,8 +423,7 @@
     </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
+     string for each node, but this is obviously a security risk and should be avoided.
-     avoided.
     </para>
     <para>
       From PostgreSQL 9.6, <application>libpq</application> supports the <varname>passfile</varname>

doc/configuration-file-settings.sgml

@@ -1,10 +1,10 @@
 <sect1 id="configuration-file-settings" xreflabel="configuration file settings">
   <indexterm>
     <primary>repmgr.conf</primary>
-    <secondary>settings</secondary>
+    <secondary>basic settings</secondary>
   </indexterm>
 
- <title>Configuration file settings</title>
+ <title>Basic configuration file settings</title>
  <para>
    Each <filename>repmgr.conf</filename> file must contain the following parameters:
  </para>
@@ -92,7 +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-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

@@ -3,6 +3,7 @@
 
   &configuration-file;
   &configuration-file-settings;
+  &configuration-service-commands;
 
   <sect1 id="configuration-permissions" xreflabel="User permissions">
     <indexterm>

doc/event-notifications.sgml

@@ -37,7 +37,7 @@
   <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>
@@ -60,10 +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>
@@ -85,6 +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
@@ -93,42 +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
+   The following parameters are provided for a subset of event notifications:
-  type <varname>bdr_failover</varname> and optionally <varname>bdr_recovery</varname>:
  </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>
@@ -144,6 +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>
@@ -156,6 +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>
@@ -174,6 +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

@@ -39,6 +39,7 @@
 <!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">
@@ -80,6 +81,7 @@
 <!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/install-packages.sgml

@@ -5,28 +5,151 @@
   system.
  </para>
 
- <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, Fedora and CentOS">
+ <sect2 id="installation-packages-redhat" xreflabel="Installing from packages on RHEL, CentOS and Fedora">
 
   <indexterm>
    <primary>installation</primary>
-   <secondary>on Redhat/CentOS/Fedora etc.</secondary>
+   <secondary>on Red Hat/CentOS/Fedora etc.</secondary>
   </indexterm>
 
-  <title>RedHat/Fedora/CentOS</title>
+  <title>RedHat/CentOS/Fedora</title>
   <para>
-   RPM packages for &repmgr; are available via Yum through
+	&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 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.
+   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>
-   <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink> also provides its
+    For more information on the package contents, including details of installation
-   own RPM packages which are made available
+    paths and relevant <link linkend="configuration-service-commands">service commands</link>,
-   at the same time as each &repmgr; release, as it can take some days for
+    see the appendix section <xref linkend="packages-centos">.
-   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>
+
+
+  <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">
@@ -38,10 +161,89 @@
 
   <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/</>).
+  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 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-source.sgml

@@ -80,7 +80,7 @@
    </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>
@@ -155,6 +155,20 @@
      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>
 
 

doc/legal.sgml

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

doc/overview.sgml

@@ -2,7 +2,8 @@
  <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">
 
@@ -178,8 +179,8 @@
   <para>
    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
+   This schema is automatically created by the &repmgr; extension, which is installed
-   during the first step in initialising a &repmgr;-administered cluster
+   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>

doc/quickstart.sgml

@@ -103,11 +103,11 @@
     # ignores archiving. Use something more sensible.
     archive_command = '/bin/true'
 
-    # If you have configured `pg_basebackup_options`
+    # If you have configured "pg_basebackup_options"
-    # in `repmgr.conf` to include the setting `--xlog-method=fetch` (from
+    # in "repmgr.conf" to include the setting "--xlog-method=fetch" (from
-    # PostgreSQL 10 `--wal-method=fetch`), *and* you have not set
+    # PostgreSQL 10 "--wal-method=fetch"), *and* you have not set
-    # `restore_command` in `repmgr.conf`to fetch WAL files from another
+    # "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
+    # 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.
     #
@@ -121,6 +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">
@@ -306,11 +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'
+    data_directory='/var/lib/postgresql/data'</programlisting>
-  </programlisting>
   <para>
    Use the <command>--dry-run</command> option to check the standby can be cloned:
   </para>

doc/repmgr-bdr.sgml

@@ -1,37 +0,0 @@
-<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 `repmgrd` and redirecting queries from the failed node to the remaining
-    active node. This can be done by using an
-    <link linkend="event-notifications">event notification</link> script
-    which is called by <application>repmgrd</application> to dynamically
-    reconfigure a proxy server/connection pooler such as <application>PgBouncer</application>.
-  </para>
-
-  <sect1 id="prerequisites" xreflable="BDR prequisites">
-  </sect1>
-</chapter>
-

doc/repmgr-cluster-crosscheck.sgml

@@ -38,5 +38,34 @@
       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

@@ -40,10 +40,13 @@
           <simpara><literal>--node-name</literal>: restrict entries to node with this name</simpara>
         </listitem>
         <listitem>
-          <simpara><literal>--event</literal>: filter specific event</simpara>
+          <simpara><literal>--event</literal>: filter specific event (see <xref linkend="event-notifications"> for a full list)</simpara>
         </listitem>
       </itemizedlist>
     </para>
+    <para>
+      The "Details" column can be omitted by providing <literal>--terse</literal>.
+    </para>
   </refsect1>
 
   <refsect1>

doc/repmgr-cluster-matrix.sgml

@@ -97,5 +97,35 @@
     useful result.
   </para>
   </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-node-check.sgml

@@ -79,9 +79,26 @@
 
     </itemizedlist>
   </para>
-  <para>
+  </refsect1>
-   Individual checks can also be output in a Nagios-compatible format by additionally
+
-   providing the option <literal>--nagios</literal>.
+  <refsect1>
-  </para>
+    <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

@@ -45,6 +45,84 @@
     </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>
@@ -69,16 +147,24 @@
     </tip>
   </refsect1>
 
-  <refsect1 id="repmgr-node-rejoin-pg-rewind">
+  <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.
+      <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> *requires* that either <varname>wal_log_hints</varname> is enabled, or that
+        <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>

doc/repmgr-node-status.sgml

@@ -24,7 +24,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-        $ repmgr -f /etc/repmgr.comf node status
+        $ repmgr -f /etc/repmgr.conf node status
         Node "node1":
             PostgreSQL version: 10beta1
             Total data size: 30 MB
@@ -38,6 +38,20 @@
     </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>

doc/repmgr-primary-register.sgml

@@ -26,7 +26,7 @@
   <refsect1>
     <title>Execution</title>
     <para>
-      Execute with the <literal>--dry-run</literal> option to check what would happen without
+      Execute with the <option>--dry-run</option> option to check what would happen without
       actually registering the primary.
     </para>
     <para>
@@ -36,7 +36,7 @@
 
     <note>
     <para>
-      If providing the configuration file location with <literal>-f/--config-file</literal>,
+      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
@@ -48,4 +48,38 @@
     </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

@@ -13,7 +13,7 @@
   <refsect1>
     <title>Description</title>
     <para>
-      <command>repmgr primary register</command> unregisters an inactive primary node
+      <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>
@@ -21,6 +21,10 @@
 
   <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.
@@ -28,7 +32,43 @@
 
     <para>
       <command>repmgr master unregister</command> can be used as an alias for
-      <command>repmgr primary unregister</command>/
+      <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

@@ -25,9 +25,11 @@
     <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.
+        a standby, the command <command>repmgr standby register</command> must be executed to
+        notify &repmgr; of its existence.
       </simpara>
     </note>
+
   </refsect1>
 
 
@@ -65,7 +67,71 @@
    </tip>
   </refsect1>
 
-  <refsect1 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
@@ -99,5 +165,177 @@
     </simpara>
    </note>
   </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

@@ -26,10 +26,19 @@
       running. It can only be used to attach an active standby to the current primary node
    (and not to another standby).
     </para>
-    <para>
+	<tip>
-      To re-add an inactive node to the replication cluster, see
+      <para>
-      <xref linkend="repmgr-node-rejoin">
+		To re-add an inactive node to the replication cluster, use
-    </para>
+		<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>
@@ -48,7 +57,56 @@
     </para>
   </refsect1>
 
- <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">

doc/repmgr-standby-promote.sgml

@@ -26,6 +26,13 @@
       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>
@@ -41,4 +48,13 @@
       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

@@ -37,19 +37,36 @@
     </note>
   </refsect1>
 
-  <refsect1 id="repmgr-standby-register-wait" xreflabel="repmgr standby register --wait">
+  <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
+     Depending on your environment and workload, it may take some time for the standby's node record
-     the standby's node record to propagate from the primary to the standby. Some
+     to propagate from the primary to the standby. Some actions (such as starting
-     actions (such as starting <application>repmgrd</application>) require that the standby's node record
+     <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>
   </refsect1>
 
@@ -58,20 +75,109 @@
    <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>
   </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

@@ -12,6 +12,7 @@
     <refpurpose>promote a standby to primary and demote the existing primary to a standby</refpurpose>
   </refnamediv>
 
+
   <refsect1>
     <title>Description</title>
 
@@ -22,11 +23,156 @@
     </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>
+      these to follow the new primary if the option <literal>--siblings-follow</literal>
-      is specified.
+      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>
 
@@ -34,12 +180,72 @@
       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>
-      <application>repmgrd</application> should not be active on any nodes while a switchover is being
+      External database connections, e.g. from an application, should not be permitted while
-      executed. This restriction may be lifted in a later version.
+      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>

doc/repmgr-standby-unregister.sgml

@@ -42,5 +42,29 @@
         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

@@ -49,4 +49,12 @@
     </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

@@ -41,7 +41,7 @@
     <para>
       Unregistering a non-running witness node:
       <programlisting>
-        $ repmgr -f /etc/repmgr.conf witness unregister -h localhost -p 5501  -F
+        $ 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
@@ -61,4 +61,13 @@
       <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

@@ -25,7 +25,13 @@
    <para>
    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>
@@ -117,6 +123,7 @@
  &appendix-release-notes;
  &appendix-signatures;
  &appendix-faq;
+ &appendix-packages;
 
  <![%include-index;[&bookindex;]]>
  <![%include-xslt-index;[<index id="bookindex"></index>]]>

doc/repmgrd-bdr.sgml

@@ -24,7 +24,7 @@
   <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 `repmgrd` and redirecting queries from the failed node to the remaining
+    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
@@ -99,15 +99,16 @@
       replication cluster. The database must be the BDR-enabled database.
     </para>
     <para>
-      If defined, the evenr <application>event_notifications</application> parameter
+      If defined, the <varname>event_notifications</varname> parameter will restrict
-      will restrict execution of <varname>event_notification_command</varname>
+      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; a reference implementation is documented below.
+        user-definable; see section <xref linkend="bdr-event-notification-command"> for a reference
+        implementation.
       </simpara>
     </note>
 
@@ -169,22 +170,18 @@
     </para>
   </sect1>
 
-  <sect1 id="bdr-event-notification-command" xreflabel="BDR failover event notification command">
+  <sect1 id="bdr-event-notification-command" xreflabel="Defining the BDR failover &quot;event_notification command&quot;">
-    <title>Defining the "event_notification_command"</title>
+    <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 should reconfigure the proxy server/ connection pooler to point
+      and which can use a &repmgr; <link linkend="event-notifications">event notification</link>
-      to the other, still-active node.
+      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>
-      Each time &repmgr; (or <application>repmgrd</application>) records an event,
+      Following parameter placeholders are available for the script definition in <filename>repmpgr.conf</filename>;
-      it can optionally execute the script defined in
+      these will be replaced with the appropriate value when the script is executed:
-      <literal>event_notification_command</literal> to take further action;
-      details of the event will be passed as parameters.
-    </para>
-    <para>
-      Following placeholders are available to the script:
     </para>
 
     <variablelist>
@@ -231,20 +228,37 @@
           </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> will only be provided during
+      Note that <literal>%c</literal> and <literal>%a</literal> are only provided with
-      <varname>bdr_failover</varname> events, which is what is of interest here.
+      particular failover events, in this case <varname>bdr_failover</varname>.
     </para>
     <para>
-      The provided sample script (`scripts/bdr-pgbouncer.sh`) is configured like
+      The provided sample script
-      this:
+     (<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 configures parameters like this:
+      and parses the placeholder parameters like this:
       <programlisting>
         NODE_ID=$1
         EVENT_TYPE=$2
@@ -252,12 +266,14 @@
         NEXT_CONNINFO=$4
         NEXT_NODE_NAME=$5</programlisting>
     </para>
-    <para>
+    <note>
-      The script also contains some hard-coded values about the <application>PgBouncer</application>
+      <para>
-      configuration for both nodes; these will need to be adjusted for your local environment
+        The sample script also contains some hard-coded values for the <application>PgBouncer</application>
-      (ideally the scripts would be maintained as templates and generated by some
+        configuration for both nodes; these will need to be adjusted for your local environment
-      kind of provisioning system).
+        (ideally the scripts would be maintained as templates and generated by some
-    </para>
+        kind of provisioning system).
+      </para>
+    </note>
 
     <para>
       The script performs following steps:

doc/repmgrd-configuration.sgml

@@ -1,60 +1,244 @@
 <chapter id="repmgrd-configuration">
 
- <indexterm>
+  <indexterm>
-   <primary>repmgrd</primary>
+    <primary>repmgrd</primary>
-   <secondary>configuration</secondary>
+    <secondary>configuration</secondary>
- </indexterm>
+  </indexterm>
 
- <title>repmgrd configuration</title>
+  <title>repmgrd configuration</title>
- <para>
-  To use <application>repmgrd</application>, its associated function library must be
-  included in <filename>postgresql.conf</filename> with:
 
-  <programlisting>
+  <para>
-    shared_preload_libraries = 'repmgr'</programlisting>
+    <application>repmgrd</application> is a daemon which runs on each PostgreSQL node,
- </para>
+    monitoring the local node, and (unless it's the primary node) the upstream server
- <para>
+    (the primary server or with cascading replication, another standby) which it's
-  Changing this setting requires a restart of PostgreSQL; for more details see
+    connected to.
-  the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
+  </para>
- </para>
+  <para>
- <para>
+    <application>repmgrd</application> can be configured to provide failover
-  Additionally the following <application>repmgrd</application> options *must* be set in
+    capability in case the primary upstream node becomes unreachable, and/or
-  <filename>repmgr.conf</filename> (adjust configuration file locations as appropriate):
+    provide monitoring data to the &repmgr; metadatabase.
-  <programlisting>
+  </para>
-    failover=automatic
+
-    promote_command='repmgr standby promote -f /etc/repmgr.conf --log-to-file'
+  <sect1 id="repmgrd-basic-configuration">
-    follow_command='repmgr standby follow -f /etc/repmgr.conf --log-to-file --upstream-node-id=%n'</programlisting>
+    <title>repmgrd basic configuration</title>
- </para>
+
- <para>
+    <para>
-  Note that the <literal>--log-to-file</literal> option will cause
+      To use <application>repmgrd</application>, its associated function library <emphasis>must</emphasis> be
-  output generated by the &repmgr; command, when executed by <application>repmgrd</application>,
+      included in <filename>postgresql.conf</filename> with:
-  to be logged to the same destination configured to receive log output for <application>repmgrd</application>.
+
-  See <filename>repmgr.conf.sample</filename> for further <application>repmgrd</application>-specific settings.
+      <programlisting>
- </para>
+        shared_preload_libraries = 'repmgr'</programlisting>
- <para>
+    </para>
-  When <varname>failover</varname> is set to <literal>automatic</literal>, upon detecting failure
+    <para>
-  of the current  primary, <application>repmgrd</application> will execute one of
+      Changing this setting requires a restart of PostgreSQL; for more details see
-  <varname>promote_command</varname> or <varname>follow_command</varname>,
+      the <ulink url="https://www.postgresql.org/docs/current/static/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
-  depending on whether the current server is to become the new primary, or
+    </para>
-  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
+    <para>
-  two actions happening, but if &repmgr;'s <command>standby follow</command> or
+      To apply configuration file changes to a running <application>repmgrd</application>
-  <command>standby promote</command>
+      daemon, execute the operating system's r<application>repmgrd</application> service reload command
-  commands are not executed (either directly as shown here, or from a script which
+      (see <xref linkend="appendix-packages"> for examples),
-  performs other actions), the &repmgr; metadata will not be updated and
+      or for instances  which were manually started, execute <command>kill -HUP</command>, e.g.
-  &repmgr; will no longer function reliably.
+      <command>kill -HUP `cat /tmp/repmgrd.pid`</command>.
- </para>
+    </para>
- <para>
+    <note>
-  The <varname>follow_command</varname> should provide the <literal>--upstream-node-id=%n</literal>
+      <para>
-  option to <command>repmgr standby follow</command>; the <literal>%n</literal> will be replaced by
+        Check the <application>repmgrd</application> log to see what changes were
-  <application>repmgrd</application> with the ID of the new primary node. If this is not provided, &repmgr;
+        applied, or if any issues were encountered when reloading the configuration.
-  will attempt to determine the new primary by itself, but  if the
+      </para>
-  original primary comes back online after the new primary is promoted, there is a risk that
+    </note>
-  <command>repmgr standby follow</command> will result in the node continuing to follow
+    <para>
-  the original primary.
+      Note that only a subset of configuration file parameters can be changed on a
- </para>
+      running <application>repmgrd</application> daemon.
- <sect1 id="repmgrd-connection-settings">
+    </para>
- <title>repmgrd connection settings</title>
+
+    <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
@@ -76,12 +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 <application>repmgrd</application> logfile does not grow
+   To ensure the current <application>repmgrd</application> logfile
-   indefinitely, configure your system's <command>logrotate</command> to
+   (specified in <filename>repmgr.conf</filename> with the parameter
-   regularly rotate it.
+   <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

@@ -40,7 +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>
@@ -69,7 +69,15 @@
   By default, <literal>repmgrd</literal> will continue in degraded monitoring mode indefinitely.
   However a timeout (in seconds) can be set with <varname>degraded_monitoring_timeout</varname>,
   after which <application>repmgrd</application> will terminate.
-
  </para>
 
+ <note>
+   <para>
+     If <application>repmgrd</application> is monitoring a primary mode which has been stopped
+     and manually restarted as a standby attached to a new primary, it will automatically detect
+     the status change and update the node record to reflect the node's new status
+     as an active standby. It will then resume monitoring the node as a standby.
+   </para>
+ </note>
+
 </chapter>

doc/repmgrd-monitoring.sgml

@@ -3,6 +3,10 @@
    <primary>repmgrd</primary>
    <secondary>monitoring</secondary>
  </indexterm>
+ <indexterm>
+   <primary>monitoring</primary>
+   <secondary>with repmgrd</secondary>
+ </indexterm>
 
  <title>Monitoring with repmgrd</title>
  <para>

doc/switchover.sgml

@@ -54,45 +54,99 @@
      <secondary>preparation</secondary>
    </indexterm>
    <title>Preparing for switchover</title>
+
    <para>
-    As mentioned above, success of the switchover operation depends on &repmgr;
+    As mentioned in the previous section, success of the switchover operation depends on
-    being able to shut down the current primary server quickly and cleanly.
+    &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
+     repmgr -f /etc/repmgr.conf node service --list --action=restart</programlisting>
-    </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
     manually with <command>repmgr node check --archive-ready</command>.
    </para>
-   <para>
+
-    Ensure that <application>repmgrd</application> is *not* running anywhere to prevent it unintentionally
+   <note>
-    promoting a node.
+     <para>
-   </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
@@ -101,7 +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
@@ -110,6 +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">
@@ -133,7 +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

doc/upgrading-repmgr.sgml

@@ -11,22 +11,86 @@
   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 <application>repmgrd</application> is running, 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>
 
- <para>
+ <sect1 id="upgrading-repmgr-extension" xreflabel="Upgrading repmgr 4.x and later">
-   Please check the <link linkend="appendix-release-notes">release notes</link> for every
+  <indexterm>
-   release as they may contain upgrade instructions particular to individual versions.
+   <primary>upgrading</primary>
- </para>
+   <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>
@@ -45,7 +109,7 @@
     </listitem>
     <listitem>
      <simpara>
-       upgrading the repmgr schema
+       upgrading the repmgr schema using <command>CREATE EXTENSION</command>
      </simpara>
     </listitem>
    </orderedlist>
@@ -58,11 +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
@@ -151,7 +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>
@@ -167,7 +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

doc/version.sgml

@@ -1 +1 @@
-<!ENTITY repmgrversion "4.0.0">
+<!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_ */

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

@@ -91,9 +91,6 @@ CREATE RULE voting_term_delete AS
    ON DELETE TO repmgr.voting_term
    DO INSTEAD NOTHING;
 
-/* XXX do this in "repmgr primary register" */
-INSERT INTO repmgr.voting_term (term) VALUES (1);
-
 
 /* ================= */
 /* repmgrd functions */

repmgr--unpackaged--4.0.sql

@@ -71,6 +71,17 @@ 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,
@@ -80,12 +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
+  END IF;
-  (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+END$repmgr$;
-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;
 
 CREATE INDEX idx_monitoring_history_time
           ON repmgr.monitoring_history (last_monitor_time, standby_node_id);

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
@@ -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);
+		bdr_node_set_repmgr_set(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);
-		}
 	}
 
 	/*

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(
+									item_list_append_format(&warnings,
-															&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(
+									item_list_append_format(&warnings,
-															&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(
+								item_list_append_format(&warnings,
-														&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(
+								item_list_append_format(&warnings,
-														&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(
+							item_list_append_format(&warnings,
-													&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(
+									item_list_append_format(&warnings,
-															&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(
+								item_list_append_format(&warnings,
-														&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(
+								item_list_append_format(&warnings,
-														&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(
+							item_list_append_format(&warnings,
-													&warnings,
 													"node \"%s\" (ID: %i) is registered as an active standby but is unreachable",
 													cell->node_info->node_name, cell->node_info->node_id);
 						}
@@ -416,7 +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);
 		}
 	}
 }
@@ -436,82 +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);
+	res = get_event_records(conn,
-	initPQExpBuffer(&where_clause);
+							runtime_options.node_id,
-
+							runtime_options.node_name,
-	/* LEFT JOIN used here as a node record may have been removed */
+							runtime_options.event,
-	appendPQExpBuffer(
+							runtime_options.all,
-					  &query,
+							runtime_options.limit);
-					  "   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);
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
@@ -538,7 +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);
 	}
@@ -547,7 +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)
@@ -558,7 +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(" ");
@@ -571,14 +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("-");
@@ -591,13 +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(" | ");
 		}
 
@@ -623,6 +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)
 	{
@@ -702,9 +650,11 @@ do_cluster_crosscheck(void)
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -743,6 +693,11 @@ do_cluster_crosscheck(void)
 
 		free(cube);
 	}
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 
@@ -758,6 +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)
@@ -796,9 +753,11 @@ do_cluster_matrix()
 				{
 					case -2:
 						c = '?';
+						error_found = true;
 						break;
 					case -1:
 						c = 'x';
+						error_found = true;
 						break;
 					case 0:
 						c = '*';
@@ -824,6 +783,11 @@ do_cluster_matrix()
 	}
 
 	free(matrix_rec_list);
+
+	if (error_found == true)
+	{
+		exit(ERR_CLUSTER_CHECK);
+	}
 }
 
 
@@ -1018,8 +982,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length)
 
 		initPQExpBuffer(&command_output);
 
-		(void) remote_command(
+		(void) remote_command(host,
-							  host,
 							  runtime_options.remote_user,
 							  command.data,
 							  &command_output);
@@ -1198,13 +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(
+			(void) local_command_simple(command.data,
-								 command.data,
+										&command_output);
-								 &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;
 
@@ -1224,8 +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(
+			(void) remote_command(host,
-								  host,
 								  runtime_options.remote_user,
 								  quoted_command.data,
 								  &command_output);

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

@@ -3,7 +3,7 @@
  *
  * Implements witness 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
@@ -65,7 +65,7 @@ do_witness_register(void)
 	if (recovery_type == RECTYPE_STANDBY)
 	{
 		log_error(_("provided node is a standby"));
-		log_error(_("a witness node must run on an independent primary server"));
+		log_hint(_("a witness node must run on an independent primary server"));
 
 		PQfinish(witness_conn);
 
@@ -86,6 +86,7 @@ do_witness_register(void)
 
 	/* 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
@@ -110,12 +111,12 @@ do_witness_register(void)
 	}
 
 	/* check primary node's recovery type */
-	recovery_type = get_recovery_type(witness_conn);
+	recovery_type = get_recovery_type(primary_conn);
 
 	if (recovery_type == RECTYPE_STANDBY)
 	{
 		log_error(_("provided primary node is a standby"));
-		log_error(_("provide the connection details of the cluster's primary server"));
+		log_hint(_("provide the connection details of the cluster's primary server"));
 
 		PQfinish(witness_conn);
 		PQfinish(primary_conn);
@@ -135,8 +136,11 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* XXX sanity check witness node is not part of main cluster */
+	/*
-
+	 * 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))
@@ -182,7 +186,6 @@ do_witness_register(void)
 			log_error(_("witness node is already registered"));
 			log_hint(_("use option -F/--force to reregister the node"));
 
-
 			PQfinish(witness_conn);
 			PQfinish(primary_conn);
 
@@ -190,8 +193,26 @@ do_witness_register(void)
 		}
 	}
 
+	/*
+	 * Check that an active node with the same node_name doesn't exist already
+	 */
 
-	// XXX check other node with same name does not exist
+	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,
@@ -222,6 +243,7 @@ do_witness_register(void)
 		PQfinish(witness_conn);
 		exit(SUCCESS);
 	}
+
 	/* create record on primary */
 
 	/*

repmgr-action-witness.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-witness.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-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 */ \
+		/* general node options */ \
-		UNKNOWN_NODE_ID, "", "", \
+		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
@@ -53,6 +53,7 @@
 
 #include "repmgr.h"
 #include "compat.h"
+#include "controldata.h"
 #include "repmgr-client.h"
 #include "repmgr-client-global.h"
 #include "repmgr-action-primary.h"
@@ -60,7 +61,6 @@
 #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 */
@@ -73,7 +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] = "";
@@ -91,11 +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;
@@ -177,7 +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)
 	{
 		/*
@@ -242,11 +243,16 @@ main(int argc, char **argv)
 				strncpy(runtime_options.replication_user, optarg, MAXLEN);
 				break;
 
-				/* -W/--wait */
+				/* -w/--wait */
-			case 'W':
+			case 'w':
 				runtime_options.wait = true;
 				break;
 
+				/* -W/--no-wait */
+			case 'W':
+				runtime_options.no_wait = true;
+				break;
+
 				/*----------------------------
 				 * database connection options
 				 *----------------------------
@@ -329,6 +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 * ---------------
 				 */
@@ -384,12 +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)
 				{
@@ -407,7 +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:
@@ -447,6 +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
 				 *--------------------
@@ -600,7 +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 ||
@@ -729,7 +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)
@@ -786,9 +819,6 @@ main(int argc, char **argv)
 				action = WITNESS_UNREGISTER;
 		}
 		else if (strcasecmp(repmgr_command, "BDR") == 0)
-#else
-		if (strcasecmp(repmgr_command, "BDR") == 0)
-#endif
 		{
 			if (help_option == true)
 			{
@@ -980,32 +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
-	 */
+	 * =====================================================================
-
-	/*
-	 * ============================================================================
 	 */
 
 	/*
@@ -1059,6 +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.
@@ -1149,7 +1168,6 @@ main(int argc, char **argv)
 
 	switch (action)
 	{
-#ifndef BDR_ONLY
 			/* PRIMARY */
 		case PRIMARY_REGISTER:
 			do_primary_register();
@@ -1185,21 +1203,6 @@ main(int argc, char **argv)
 		case WITNESS_UNREGISTER:
 			do_witness_unregister();
 			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_REGISTER:
-		case WITNESS_UNREGISTER:
-			break;
-
-#endif
 			/* BDR */
 		case BDR_REGISTER:
 			do_bdr_register();
@@ -1316,7 +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
 					 */
 
@@ -1335,6 +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;
 
@@ -1356,6 +1368,12 @@ check_cli_parameters(const int 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)
 			{
@@ -1493,6 +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)
@@ -1506,25 +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)
@@ -1563,6 +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')
 	{
@@ -1585,8 +1652,7 @@ check_cli_parameters(const int action)
 			case NODE_STATUS:
 				break;
 			default:
-				item_list_append_format(
+				item_list_append_format(&cli_warnings,
-										&cli_warnings,
 										_("--is-shutdown-cleanly will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1599,14 +1665,13 @@ check_cli_parameters(const int action)
 			case STANDBY_SWITCHOVER:
 				break;
 			default:
-				item_list_append_format(
+				item_list_append_format(&cli_warnings,
-										&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)
 		{
@@ -1614,8 +1679,7 @@ check_cli_parameters(const int action)
 			case NODE_REJOIN:
 				break;
 			default:
-				item_list_append_format(
+				item_list_append_format(&cli_warnings,
-										&cli_warnings,
 										_("--force-rewind will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1629,8 +1693,7 @@ check_cli_parameters(const int action)
 			case NODE_REJOIN:
 				break;
 			default:
-				item_list_append_format(
+				item_list_append_format(&cli_warnings,
-										&cli_warnings,
 										_("--config-files will be ignored when executing %s"),
 										action_name(action));
 		}
@@ -1644,6 +1707,7 @@ 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:
@@ -1651,8 +1715,7 @@ check_cli_parameters(const int action)
 			case NODE_SERVICE:
 				break;
 			default:
-				item_list_append_format(
+				item_list_append_format(&cli_warnings,
-										&cli_warnings,
 										_("--dry-run is not effective when executing %s"),
 										action_name(action));
 		}
@@ -1674,8 +1737,7 @@ check_cli_parameters(const int action)
 		if (used_options > 1)
 		{
 			/* TODO: list which options were used */
-			item_list_append(
+			item_list_append(&cli_errors,
-							 &cli_errors,
 							 "only one of --csv, --nagios and --optformat can be used");
 		}
 	}
@@ -1779,13 +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());
+	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow|switchover}\n"), progname());
-#endif
 	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("");
 
@@ -2102,6 +2163,8 @@ test_ssh_connection(char *host, char *remote_user)
 }
 
 
+
+
 /*
  * Execute a command locally. "outputbuf" should either be an
  * initialised PQexpbuffer, or NULL
@@ -2109,9 +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)
 	{
@@ -2127,27 +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 */
@@ -2156,6 +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)
@@ -2173,9 +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,
+	initialize_conninfo_params(&conninfo_params, false);
-													  runtime_options.superuser,
+	conn_to_param_list(*conn, &conninfo_params);
-													  false);
+	param_set(&conninfo_params, "user", runtime_options.superuser);
+
+	*superuser_conn = establish_db_connection_by_params(&conninfo_params, false);
 
 	if (PQstatus(*superuser_conn) != CONNECTION_OK)
 	{
@@ -2195,6 +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;
 }
@@ -2336,9 +2440,6 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 }
 
 
-
-
-
 /*
  * Execute a command via ssh on the remote host.
  *
@@ -2402,7 +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;
 }
@@ -2448,18 +2554,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				{
 					initPQExpBuffer(&command);
 
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
+					appendShellString(&command,
-									  &command,
 									  data_dir);
 
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  " start");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2471,6 +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')
 				{
@@ -2480,19 +2584,23 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  "%s %s -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
+					appendShellString(&command,
-									  &command,
 									  data_dir);
 
-					appendPQExpBuffer(
+					if (action == ACTION_STOP_WAIT)
-									  &command,
+						appendPQExpBuffer(&command,
-									  " -m fast -W stop");
+										  " -w");
+					else
+						appendPQExpBuffer(&command,
+										  " -W");
+
+					appendPQExpBuffer(&command,
+									  " -m fast stop");
 
 					strncpy(script, command.data, MAXLEN);
 
@@ -2511,18 +2619,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
+					appendShellString(&command,
-									  &command,
 									  data_dir);
 
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  " restart");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2542,18 +2647,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
+					appendShellString(&command,
-									  &command,
 									  data_dir);
 
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  " reload");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2574,18 +2676,15 @@ get_server_action(t_server_action action, char *script, char *data_dir)
 				else
 				{
 					initPQExpBuffer(&command);
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  "%s %s -w -D ",
 									  make_pg_path("pg_ctl"),
 									  config_file_options.pg_ctl_options);
 
-					appendShellString(
+					appendShellString(&command,
-									  &command,
 									  data_dir);
 
-					appendPQExpBuffer(
+					appendPQExpBuffer(&command,
-									  &command,
 									  " promote");
 
 					strncpy(script, command.data, MAXLEN);
@@ -2619,6 +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;
@@ -2654,6 +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)
 {
@@ -2701,7 +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
@@ -2715,6 +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
@@ -56,7 +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
@@ -81,6 +81,13 @@
 #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'},
@@ -133,9 +142,11 @@ 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
  *
@@ -153,11 +164,13 @@ 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},

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
@@ -288,7 +288,6 @@ standby_get_last_updated(PG_FUNCTION_ARGS)
 Datum
 notify_follow_primary(PG_FUNCTION_ARGS)
 {
-#ifndef BDR_ONLY
 	int			primary_node_id = UNKNOWN_NODE_ID;
 
 	if (!shared_state)
@@ -316,7 +315,7 @@ notify_follow_primary(PG_FUNCTION_ARGS)
 	}
 
 	LWLockRelease(shared_state->lock);
-#endif
+
 	PG_RETURN_VOID();
 }
 
@@ -329,14 +328,12 @@ 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();
@@ -348,7 +345,6 @@ get_new_primary(PG_FUNCTION_ARGS)
 Datum
 reset_voting_status(PG_FUNCTION_ARGS)
 {
-#ifndef BDR_ONLY
 	if (!shared_state)
 		PG_RETURN_NULL();
 
@@ -366,7 +362,7 @@ reset_voting_status(PG_FUNCTION_ARGS)
 	}
 
 	LWLockRelease(shared_state->lock);
-#endif
+
 	PG_RETURN_VOID();
 }
 

repmgr.conf.sample

@@ -13,67 +13,74 @@
 # repmgr and repmgrd require the following items to be explicitly configured.
 
 
-#node_id=                               # A unique integer greater than zero
+#node_id=    	     	     	 # A unique integer greater than zero
-#node_name=''                           # An arbitrary (but unique) string; we recommend
+#node_name=''			 # An arbitrary (but unique) string; we recommend
-                                        # using the server's hostname or another identifier
+				 # using the server's hostname or another identifier
-                                        # unambiguously associated with the server to avoid
+				 # unambiguously associated with the server to avoid
-                                        # confusion. Avoid choosing names which reflect the
+				 # confusion. Avoid choosing names which reflect the
-                                        # node's current role, e.g. "primary" or "standby1",
+				 # node's current role, e.g. "primary" or "standby1",
-                                        # as roles can change and it will be confusing if
+				 # as roles can change and it will be confusing if
-                                        # the current primary is called "standby1".
+				 # the current primary is called "standby1".
 
-#conninfo=''                            # Database connection information as a conninfo string.
+#conninfo=''			 # Database connection information as a conninfo string.
-                                        # All servers in the cluster must be able to connect to
+				 # All servers in the cluster must be able to connect to
-                                        # the local node using this string.
+				 # the local node using this string.
-                                        #
+				 #
-                                        # For details on conninfo strings, see:
+				 # For details on conninfo strings, see:
-                                        #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING
+				 #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING
-                                        #
+				 #
-                                        # If repmgrd is in use, consider explicitly setting
+				 # If repmgrd is in use, consider explicitly setting
-                                        # "connect_timeout" in the conninfo string to determine
+				 # "connect_timeout" in the conninfo string to determine
-                                        # the length of time which elapses before a network
+				 # the length of time which elapses before a network
-                                        # connection attempt is abandoned; for details see:
+				 # connection attempt is abandoned; for details see:
-                                        #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT
+				 #  https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT
 
-#data_directory                         # The node's data directory. This is needed by repmgr
+#data_directory=''		 # The node's data directory. This is needed by repmgr
-                                        # when performing operations when the PostgreSQL instance
+				 # when performing operations when the PostgreSQL instance
-                                        # is not running and there's no other way of determining
+				 # is not running and there's no other way of determining
-                                        # the data directory.
+				 # the data directory.
 
-#replication_user                       # User to make replication connections with, if not set defaults
-                                        # to the user defined in "conninfo".
 
 # =============================================================================
 
 # Optional configuration items
 # =============================================================================
 
+
+#------------------------------------------------------------------------------
+# Server settings
+#------------------------------------------------------------------------------
+
+#config_directory=''		 # If configuration files are located outside the data
+				 # directory, specify the directory where the main
+				 # postgresql.conf file is located.
+
 #------------------------------------------------------------------------------
 # Replication settings
 #------------------------------------------------------------------------------
 
-#replication_type=physical              # Must be one of 'physical' or 'bdr'.
+#replication_user='repmgr'	 # User to make replication connections with, if not set defaults
+				 # to the user defined in "conninfo".
 
-#location=default                       # arbitrary string defining the location of the node; this
+#replication_type=physical	 # Must be one of 'physical' or 'bdr'.
-                                        # is used during failover to check visibilty of the
-                                        # current primary node. See the 'repmgrd' documentation
-                                        # in README.md for further details.
 
-#use_replication_slots=no               # whether to use physical replication slots
+#location=default		 # arbitrary string defining the location of the node; this
-                                        # NOTE: when using replication slots,
+				 # is used during failover to check visibilty of the
-                                        # 'max_replication_slots' should be configured for
+				 # current primary node. See the 'repmgrd' documentation
-                                        # at least the number of standbys which will connect
+				 # in README.md for further details.
-                                        # to the primary.
 
-#recovery_min_apply_delay=              # If provided, "recovery_min_apply_delay" in recovery.conf
+#use_replication_slots=no	 # whether to use physical replication slots
-                                        # will be set to this value.
+				 # NOTE: when using replication slots,
+				 # 'max_replication_slots' should be configured for
+				 # at least the number of standbys which will connect
+				 # to the primary.
 
 #------------------------------------------------------------------------------
 # Witness server settings
 #------------------------------------------------------------------------------
 
-#witness_sync_interval=15               # interval (in seconds) to synchronise node records
+#witness_sync_interval=15	 # interval (in seconds) to synchronise node records
-                                        # to the witness server
+				 # to the witness server
 
 #------------------------------------------------------------------------------
 # Logging settings
@@ -85,14 +92,14 @@
 # This is mainly intended for those cases when `repmgr` is executed directly
 # by `repmgrd`.
 
-#log_level=INFO                         # Log level: possible values are DEBUG, INFO, NOTICE,
+#log_level=INFO			 # Log level: possible values are DEBUG, INFO, NOTICE,
-                                        # WARNING, ERROR, ALERT, CRIT or EMERG
+				 # WARNING, ERROR, ALERT, CRIT or EMERG
 
-#log_facility=STDERR                    # Logging facility: possible values are STDERR, or for
+#log_facility=STDERR		 # Logging facility: possible values are STDERR, or for
-                                        # syslog integration, one of LOCAL0, LOCAL1, ..., LOCAL7, USER
+				 # syslog integration, one of LOCAL0, LOCAL1, ..., LOCAL7, USER
 
-#log_file=''                            # stderr can be redirected to an arbitrary file:
+#log_file=''			 # stderr can be redirected to an arbitrary file
-#log_status_interval=300                # interval (in seconds) for repmgrd to log a status message
+#log_status_interval=300	 # interval (in seconds) for repmgrd to log a status message
 
 
 #------------------------------------------------------------------------------
@@ -118,28 +125,28 @@
 #
 #   event_notifications=primary_register,standby_register
 
-#event_notification_command=''          # An external program or script which
+#event_notification_command=''		# An external program or script which
-                                        # can be executed by the user under which
+					# can be executed by the user under which
-                                        # repmgr/repmgrd are run.
+					# repmgr/repmgrd are run.
 
-#event_notifications=''                 # A commas-separated list of notification
+#event_notifications=''			# A commas-separated list of notification
-                                        # types
+					# types
 
 #------------------------------------------------------------------------------
 # Environment/command settings
 #------------------------------------------------------------------------------
 
-#pg_bindir=''                           # Path to PostgreSQL binary directory (location
+#pg_bindir=''				# Path to PostgreSQL binary directory (location
-                                        # of pg_ctl, pg_basebackup etc.). Only needed
+					# of pg_ctl, pg_basebackup etc.). Only needed
-                                        # if these files are not in the system $PATH.
+					# if these files are not in the system $PATH.
-                                        #
+					#
-                                        # Debian/Ubuntu users: you will probably need to
+					# Debian/Ubuntu users: you will probably need to
-                                        # set this to the directory where `pg_ctl` is located,
+					# set this to the directory where `pg_ctl` is located,
-                                        # e.g. /usr/lib/postgresql/9.6/bin/
+					# e.g. /usr/lib/postgresql/9.6/bin/
-#use_primary_conninfo_password=false    # explicitly set "password" in recovery.conf's
+#use_primary_conninfo_password=false	# explicitly set "password" in recovery.conf's
-                                        # "primary_conninfo" parameter using the value contained
+					# "primary_conninfo" parameter using the value contained
-                                        # in the environment variable PGPASSWORD
+					# in the environment variable PGPASSWORD
-#passfile=''                            # path to .pgpass file to include in "primary_conninfo"
+#passfile=''				# path to .pgpass file to include in "primary_conninfo"
 #------------------------------------------------------------------------------
 # external command options
 #------------------------------------------------------------------------------
@@ -153,16 +160,15 @@
 #   rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
 #   ssh_options=-o "StrictHostKeyChecking no"
 
-#pg_ctl_options=''                      # Options to append to "pg_ctl"
+#pg_ctl_options='' 			# Options to append to "pg_ctl"
-#pg_basebackup_options=''               # Options to append to "pg_basebackup"
+#pg_basebackup_options=''		# Options to append to "pg_basebackup"
-#rsync_options=''                       # Options to append to "rsync"
+#rsync_options=''			# Options to append to "rsync"
-ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
+ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
-
 
 
 
 #------------------------------------------------------------------------------
-# Standby clone settings
+# "standby clone" settings
 #------------------------------------------------------------------------------
 #
 # These settings apply when cloning a standby ("repmgr standby clone").
@@ -172,12 +178,33 @@ ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
 #   tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
 #   restore_command = 'cp /path/to/archived/wals/%f %p'
 
-#tablespace_mapping=''                  # Tablespaces can be remapped from one
+#tablespace_mapping=''	  		# Tablespaces can be remapped from one
-                                        # file system location to another. This
+					# file system location to another. This
-                                        # parameter can be provided multiple times.
+					# parameter can be provided multiple times.
+
+#restore_command=''			# This will be placed in the recovery.conf file generated
+                                        # by repmgr.
+
+#archive_cleanup_command=''		# This will be placed in the recovery.conf file generated
+                                        # by repmgr. Note we recommend using Barman for managing
+                                        # WAL archives (see: https://www.pgbarman.org )
+
+#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" in recovery.conf
+					# will be set to this value (PostgreSQL 9.4 and later).
+
+
+#------------------------------------------------------------------------------
+# "standby promote" settings
+#------------------------------------------------------------------------------
+
+# These settings apply when instructing a standby to promote itself to the
+# new primary ("repmgr standby promote").
+
+#promote_check_timeout=60		# The length of time (in seconds) to wait
+					# for the new primary to finish promoting
+#promote_check_interval=1		# The interval (in seconds) to check whether
+					# the new primary has finished promoting
 
-#restore_command=''                     # This will be placed in the recovery.conf
-                                        # file generated by repmgr
 
 #------------------------------------------------------------------------------
 # Standby follow settings
@@ -186,19 +213,21 @@ ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
 # These settings apply when instructing a standby to follow the new primary
 # ("repmgr standby follow").
 
-#primary_follow_timeout=60              # The length of time (in seconds) to wait
+#primary_follow_timeout=60		# The max length of time (in seconds) to wait
-                                        # for the new primary to become available
+					# for the new primary to become available
+#standby_follow_timeout=15		# The max length of time (in seconds) to wait
+					# for the standby to connect to the primary
 
 
 #------------------------------------------------------------------------------
 # Barman options
 #------------------------------------------------------------------------------
 
-#barman_server=''                       # The barman configuration section
+#barman_server=''			# The barman configuration section
-#barman_host=''                         # The host name of the barman server
+#barman_host=''				# The host name of the barman server
-#barman_config=''                       # The Barman configuration file on the
+#barman_config=''			# The Barman configuration file on the
-                                        # Barman server (needed if the file is
+					# Barman server (needed if the file is
-                                        # in a non-standard location)
+					# in a non-standard location)
 
 #------------------------------------------------------------------------------
 # Failover and monitoring settings (repmgrd)
@@ -207,42 +236,45 @@ ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
 # These settings are only applied when repmgrd is running. Values shown
 # are defaults.
 
-#failover=manual                        # one of 'automatic', 'manual'.
+#failover=manual			# one of 'automatic', 'manual'.
-                                        # determines what action to take in the event of upstream failure
+					# determines what action to take in the event of upstream failure
-                                        #
+					#
-                                        # 'automatic': repmgrd will automatically attempt to promote the
+					# 'automatic': repmgrd will automatically attempt to promote the
-                                        #    node or follow the new upstream node
+					#    node or follow the new upstream node
-                                        # 'manual': repmgrd will take no action and the node will require
+					# 'manual': repmgrd will take no action and the node will require
-                                        #    manual attention to reattach it to replication
+					#    manual attention to reattach it to replication
-                                        # (does not apply to BDR mode)
+					# (does not apply to BDR mode)
 
-#priority=100                           # indicate a preferred priorty for promoting nodes;
+#priority=100				# indicate a preferred priorty for promoting nodes;
-                                        # a value of zero prevents the node being promoted to primary
+					# a value of zero prevents the node being promoted to primary
-                                        # (default: 100)
+					# (default: 100)
 
-#reconnect_attempts=6                   # Number attempts which will be made to reconnect to an unreachable
+#reconnect_attempts=6			# Number attempts which will be made to reconnect to an unreachable
-                                        # primary (or other upstream node)
+					# primary (or other upstream node)
-#reconnect_interval=10                  # Interval between attempts  to reconnect to an unreachable
+#reconnect_interval=10			# Interval between attempts  to reconnect to an unreachable
-                                        # primary (or other upstream node)
+					# primary (or other upstream node)
-#promote_command=                       # command to execute when promoting a new primary; use something like:
+#promote_command=			# command repmgrd executes when promoting a new primary; use something like:
-                                        #
+					#
-                                        #     repmgr standby promote -f /etc/repmgr.conf
+					#     repmgr standby promote -f /etc/repmgr.conf
-                                        #
+					#
-#follow_command=                        # command to execute when instructing a standby to follow a new primary;
+#follow_command=			# command repmgrd executes when instructing a standby to follow a new primary;
-                                        # use something like:
+					# use something like:
-                                        #
+					#
-                                        #     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
+					#     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
-                                        #
+					#
-#primary_notification_timeout=60        # Interval (in seconds) which repmgrd on a standby
+#primary_notification_timeout=60	# Interval (in seconds) which repmgrd on a standby
-                                        # will wait for a notification from the new primary,
+					# will wait for a notification from the new primary,
-                                        # before falling back to degraded monitoring
+					# before falling back to degraded monitoring
-#monitoring_history=no
+#standby_reconnect_timeout=60	# Interval (in seconds) which repmgrd on a standby will wait
+					# to reconnect to the local node after executing "follow_command"
 
-#degraded_monitoring_timeout=-1         # Interval (in seconds) after which repmgrd will terminate if the
+#monitoring_history=no                  # Whether to write monitoring data to the "montoring_history" table
-                                        # server being monitored is no longer available. -1 (default)
+#monitor_interval_secs=2                # Interval (in seconds) at which to write monitoring data
-                                        # disables the timeout completely.
+#degraded_monitoring_timeout=-1		# Interval (in seconds) after which repmgrd will terminate if the
-#async_query_timeout=60                 # Interval (in seconds) which repmgrd will wait before
+					# server being monitored is no longer available. -1 (default)
-                                        # cancelling an asynchronous query.
+					# disables the timeout completely.
+#async_query_timeout=60			# Interval (in seconds) which repmgrd will wait before
+					# cancelling an asynchronous query.
 
 #------------------------------------------------------------------------------
 # service control commands
@@ -270,16 +302,19 @@ ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
 #       /usr/bin/systemctl start postgresql-9.6, \
 #       /usr/bin/systemctl restart postgresql-9.6
 #
+# Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
+#
+# For more details, see: https://repmgr.org/docs/4.0/configuration-service-commands.html
 
 #service_start_command = ''
 #service_stop_command = ''
 #service_restart_command = ''
 #service_reload_command = ''
-#service_promote_command = ''            # Note: this overrides any value contained in the setting
+#service_promote_command = ''		# This parameter is intended for systems which provide a
-                                         # "promote_command". This is intended for systems which
+					# package-level promote command, such as Debian's
-                                         # provide a package-level promote command, such as Debian's
+					# "pg_ctlcluster". *IMPORTANT*: it is *not* a substitute
-                                         # "pg_ctlcluster"
+					# for "promote_command"; do not use "repmgr standby promote"
-
+					# (or a script which executes "repmgr standby promote") here.
 
 #------------------------------------------------------------------------------
 # Status check thresholds
@@ -287,25 +322,25 @@ ssh_options='-q -o ConnectTimeout=10'   # Options to append to "ssh"
 
 # Various warning/critical thresholds used by "repmgr node check".
 
-#archive_ready_warning=16                # repmgr node check --archiver
+#archive_ready_warning=16  	      	# repmgr node check --archive-ready
-#archive_ready_critical=128              #
+#archive_ready_critical=128		#
-                                         # Numbers of files pending archiving via PostgreSQL's
+					# Numbers of files pending archiving via PostgreSQL's
-                                         # "archive_command" configuration parameter. If
+					# "archive_command" configuration parameter. If
-                                         # files can't be archived fast enough, or the archive
+					# files can't be archived fast enough, or the archive
-                                         # command is failing, the buildup of files can
+					# command is failing, the buildup of files can
-                                         # cause various issues, such as server shutdown being
+					# cause various issues, such as server shutdown being
-                                         # delayed until all files are archived, or excessive
+					# delayed until all files are archived, or excessive
-                                         # space being occupied by unarchived files.
+					# space being occupied by unarchived files.
-                                         #
+					#
-                                         # Note that these values will be checked when executing
+					# Note that these values will be checked when executing
-                                         # "repmgr standby switchover" to warn about potential
+					# "repmgr standby switchover" to warn about potential
-                                         # issues with shutting down the demotion candidate.
+					# issues with shutting down the demotion candidate.
 
-#replication_lag_warning=300             # repmgr node check --replication-lag
+#replication_lag_warning=300		# repmgr node check --replication-lag
-#replication_lag_critical=600            #
+#replication_lag_critical=600		#
-                                         # Note that these values will be checked when executing
+					# Note that these values will be checked when executing
-                                         # "repmgr standby switchover" to warn about potential
+					# "repmgr standby switchover" to warn about potential
-                                         # issues with shutting down the demotion candidate.
+					# issues with shutting down the demotion candidate.
 
 
 #------------------------------------------------------------------------------

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.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
@@ -56,6 +56,7 @@
 #define NO_UPSTREAM_NODE	-1
 #define UNKNOWN_NODE_ID		-1
 
+#define VOTING_TERM_NOT_SET -1
 
 /*
  * various default values - ensure repmgr.conf.sample is update
@@ -69,12 +70,17 @@
 #define DEFAULT_ASYNC_QUERY_TIMEOUT          60  /* seconds */
 #define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
 #define DEFAULT_PRIMARY_FOLLOW_TIMEOUT       60  /* seconds */
+#define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
 #define DEFAULT_BDR_RECOVERY_TIMEOUT         30  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */
 #define	DEFAULT_REPLICATION_LAG_WARNING      300 /* seconds */
 #define DEFAULT_REPLICATION_LAG_CRITICAL     600 /* seconds */
 #define DEFAULT_WITNESS_SYNC_INTERVAL        15  /* seconds */
+#define DEFAULT_WAIT_START                   30  /* seconds */
+#define DEFAULT_PROMOTE_CHECK_TIMEOUT        60  /* seconds */
+#define DEFAULT_PROMOTE_CHECK_INTERVAL       1   /* seconds */
+#define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */
 
 #ifndef RECOVERY_COMMAND_FILE
 #define RECOVERY_COMMAND_FILE "recovery.conf"

repmgr_version.h.in

@@ -1,3 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.0.0"
+#define REPMGR_VERSION "4.0.6"
 

repmgrd-bdr.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd-bdr.c - BDR functionality for repmgrd
  *
- * 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
@@ -35,6 +35,29 @@ do_bdr_node_check(void)
 	/* nothing to do at the moment */
 }
 
+void
+handle_sigint_bdr(SIGNAL_ARGS)
+{
+	PQExpBufferData event_details;
+
+	initPQExpBuffer(&event_details);
+
+	appendPQExpBuffer(&event_details,
+					  "%s signal received",
+					  postgres_signal_arg == SIGTERM
+					  ? "TERM" : "INT");
+
+	create_event_notification(local_conn,
+							  &config_file_options,
+							  config_file_options.node_id,
+							  "repmgrd_shutdown",
+							  true,
+							  event_details.data);
+	termPQExpBuffer(&event_details);
+
+	terminate(SUCCESS);
+}
+
 
 void
 monitor_bdr(void)
@@ -98,23 +121,6 @@ monitor_bdr(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* Retrieve record for this node from the local database */
-	record_status = get_node_record(local_conn, config_file_options.node_id, &local_node_info);
-
-	/*
-	 * Terminate if we can't find the local node record. This is a
-	 * "fix-the-config" situation, not a lot else we can do.
-	 */
-	if (record_status != RECORD_FOUND)
-	{
-		log_error(_("unable to retrieve record for local node (ID: %i), terminating"),
-				  local_node_info.node_id);
-		log_hint(_("check that \"repmgr bdr register\" was executed for this node"));
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-
 	if (local_node_info.active == false)
 	{
 		log_error(_("local node (ID: %i) is marked as inactive in repmgr"),
@@ -124,9 +130,9 @@ monitor_bdr(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	if (is_active_bdr_node(local_conn, local_node_info.node_name))
+	if (is_active_bdr_node(local_conn, local_node_info.node_name) == false)
 	{
-		log_error(_("BDR node %s is not active, terminating"),
+		log_error(_("BDR node \"%s\" is not active, terminating"),
 				  local_node_info.node_name);
 		PQfinish(local_conn);
 		exit(ERR_BAD_CONFIG);
@@ -152,15 +158,16 @@ monitor_bdr(void)
 		cell->node_info->node_status = NODE_STATUS_UP;
 	}
 
-	log_debug("main_loop_bdr() monitoring local node %i", config_file_options.node_id);
+	log_info(_("starting continuous BDR node monitoring on node %i"),
+			 config_file_options.node_id);
 
-	log_info(_("starting continuous BDR node monitoring"));
+	INSTR_TIME_SET_CURRENT(log_status_interval_start);
 
 	while (true)
 	{
 
 		/* monitoring loop */
-		log_verbose(LOG_DEBUG, "BDR check loop...");
+		log_verbose(LOG_DEBUG, "BDR check loop - checking %i nodes", nodes.node_count);
 
 		for (cell = nodes.head; cell; cell = cell->next)
 		{
@@ -262,7 +269,6 @@ loop:
 		if (config_file_options.log_status_interval > 0)
 		{
 			int			log_status_interval_elapsed = calculate_elapsed(log_status_interval_start);
-
 			if (log_status_interval_elapsed >= config_file_options.log_status_interval)
 			{
 				log_info(_("monitoring BDR replication status on node \"%s\" (ID: %i)"),
@@ -273,8 +279,7 @@ loop:
 				{
 					if (cell->node_info->monitoring_state == MS_DEGRADED)
 					{
-						log_detail(
+						log_detail(_("monitoring node \"%s\" (ID: %i) in degraded mode"),
-								   _("monitoring node \"%s\" (ID: %i) in degraded mode"),
 								   cell->node_info->node_name,
 								   cell->node_info->node_id);
 					}

repmgrd-bdr.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-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
@@ -22,4 +22,5 @@
 extern void do_bdr_node_check(void);
 extern void monitor_bdr(void);
 
+extern void	handle_sigint_bdr(SIGNAL_ARGS);
 #endif							/* _REPMGRD_BDR_H_ */

repmgrd-physical.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-physical.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
@@ -24,6 +24,7 @@ void		do_physical_node_check(void);
 void		monitor_streaming_primary(void);
 void		monitor_streaming_standby(void);
 void		monitor_streaming_witness(void);
-void		close_connections_physical(void);
+
+void		handle_sigint_physical(SIGNAL_ARGS);
 
 #endif							/* _REPMGRD_PHYSICAL_H_ */

repmgrd.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd.c - Replication manager daemon
  *
- * 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
@@ -53,9 +53,6 @@ bool		startup_event_logged = false;
 MonitoringState monitoring_state = MS_NORMAL;
 instr_time	degraded_monitoring_start;
 
-static void close_connections(void);
-void		(*_close_connections) (void) = NULL;
-
 /*
  * Record receipt of SIGHUP; will cause configuration file to be reread
  * at the appropriate point in the main loop.
@@ -73,7 +70,6 @@ static void start_monitoring(void);
 #ifndef WIN32
 static void setup_event_handlers(void);
 static void handle_sighup(SIGNAL_ARGS);
-static void handle_sigint(SIGNAL_ARGS);
 #endif
 
 int			calculate_elapsed(instr_time start_time);
@@ -89,6 +85,7 @@ main(int argc, char **argv)
 	bool		cli_monitoring_history = false;
 
 	RecordStatus record_status;
+	ExtensionStatus extension_status = REPMGR_UNKNOWN;
 
 	FILE	   *fd;
 
@@ -254,6 +251,8 @@ main(int argc, char **argv)
 		strncpy(config_file_options.log_level, cli_log_level, MAXLEN);
 	}
 
+	log_notice(_("repmgrd (repmgr %s) starting up"), REPMGR_VERSION);
+
 	/*
 	 * -m/--monitoring-history, if provided, will override repmgr.conf's
 	 * monitoring_history; this is for backwards compatibility as it's
@@ -318,15 +317,60 @@ main(int argc, char **argv)
 	 * repmgr has not been properly configured.
 	 */
 
+	/* Check "repmgr" the extension is installed */
+	extension_status = get_repmgr_extension_status(local_conn);
+
+	if (extension_status != REPMGR_INSTALLED)
+	{
+		/* this is unlikely to happen */
+		if (extension_status == REPMGR_UNKNOWN)
+		{
+			log_error(_("unable to determine status of \"repmgr\" extension"));
+			log_detail("%s", PQerrorMessage(local_conn));
+			close_connection(&local_conn);
+			exit(ERR_DB_QUERY);
+		}
+
+		log_error(_("repmgr extension not found on this node"));
+
+		if (extension_status == REPMGR_AVAILABLE)
+		{
+			log_detail(_("repmgr extension is available but not installed in database \"%s\""),
+					   PQdb(local_conn));
+		}
+		else if (extension_status == REPMGR_UNAVAILABLE)
+		{
+			log_detail(_("repmgr extension is not available on this node"));
+		}
+
+		log_hint(_("check that this node is part of a repmgr cluster"));
+		close_connection(&local_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
 	/* Retrieve record for this node from the local database */
 	record_status = get_node_record(local_conn, config_file_options.node_id, &local_node_info);
 
+	/*
+	 * Terminate if we can't find the local node record. This is a
+	 * "fix-the-config" situation, not a lot else we can do.
+	 */
+
 	if (record_status != RECORD_FOUND)
 	{
 		log_error(_("no metadata record found for this node - terminating"));
-		log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
 
-		PQfinish(local_conn);
+		switch (config_file_options.replication_type)
+		{
+			case REPLICATION_TYPE_PHYSICAL:
+				log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
+				break;
+			case REPLICATION_TYPE_BDR:
+				log_hint(_("check that 'repmgr bdr register' was executed for this node"));
+				break;
+		}
+
+		close_connection(&local_conn);
 		terminate(ERR_BAD_CONFIG);
 	}
 
@@ -345,7 +389,7 @@ main(int argc, char **argv)
 		{
 			log_error(_("unable to write to shared memory"));
 			log_hint(_("ensure \"shared_preload_libraries\" includes \"repmgr\""));
-			PQfinish(local_conn);
+			close_connection(&local_conn);
 			terminate(ERR_BAD_CONFIG);
 		}
 	}
@@ -357,7 +401,6 @@ main(int argc, char **argv)
 	}
 	else
 	{
-		_close_connections = close_connections_physical;
 		log_debug("node id is %i, upstream node id is %i",
 				  local_node_info.node_id,
 				  local_node_info.upstream_node_id);
@@ -400,7 +443,6 @@ start_monitoring(void)
 	{
 		switch (local_node_info.type)
 		{
-#ifndef BDR_ONLY
 			case PRIMARY:
 				monitor_streaming_primary();
 				break;
@@ -410,11 +452,6 @@ start_monitoring(void)
 			case WITNESS:
 				monitor_streaming_witness();
 				break;
-#else
-			case PRIMARY:
-			case STANDBY:
-				return;
-#endif
 			case BDR:
 				monitor_bdr();
 				return;
@@ -587,11 +624,6 @@ check_and_create_pid_file(const char *pid_file)
 
 
 #ifndef WIN32
-static void
-handle_sigint(SIGNAL_ARGS)
-{
-	terminate(SUCCESS);
-}
 
 /* SIGHUP: set flag to re-read config file at next convenient time */
 static void
@@ -604,8 +636,23 @@ static void
 setup_event_handlers(void)
 {
 	pqsignal(SIGHUP, handle_sighup);
-	pqsignal(SIGINT, handle_sigint);
+
-	pqsignal(SIGTERM, handle_sigint);
+	/*
+	 * we want to be able to write a "repmgrd_shutdown" event, so delegate
+	 * signal handling to the respective replication type handler, as it
+	 * will know best which database connection to use
+	 */
+	switch (config_file_options.replication_type)
+	{
+		case REPLICATION_TYPE_BDR:
+			pqsignal(SIGINT, handle_sigint_bdr);
+			pqsignal(SIGTERM, handle_sigint_bdr);
+			break;
+		case REPLICATION_TYPE_PHYSICAL:
+			pqsignal(SIGINT, handle_sigint_physical);
+			pqsignal(SIGTERM, handle_sigint_physical);
+			break;
+	}
 }
 #endif
 
@@ -654,17 +701,29 @@ PGconn *
 try_reconnect(t_node_info *node_info)
 {
 	PGconn	   *conn;
+	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
 
 	int			i;
 
 	int			max_attempts = config_file_options.reconnect_attempts;
 
+	initialize_conninfo_params(&conninfo_params, false);
+
+
+	/* we assume by now the conninfo string is parseable */
+	(void) parse_conninfo_string(node_info->conninfo, &conninfo_params, NULL, false);
+
+	/* set some default values if not explicitly provided */
+	param_set_ine(&conninfo_params, "connect_timeout", "2");
+	param_set_ine(&conninfo_params, "fallback_application_name", "repmgr");
+
 	for (i = 0; i < max_attempts; i++)
 	{
 		log_info(_("checking state of node %i, %i of %i attempts"),
 				 node_info->node_id, i + 1, max_attempts);
-		if (is_server_available(node_info->conninfo) == true)
+		if (is_server_available_params(&conninfo_params) == true)
 		{
+
 			log_notice(_("node has recovered, reconnecting"));
 
 			/*
@@ -672,14 +731,18 @@ try_reconnect(t_node_info *node_info)
 			 * connection denied due to connection exhaustion - fall back to
 			 * degraded monitoring? - make that configurable
 			 */
-			conn = establish_db_connection(node_info->conninfo, false);
+
+			conn = establish_db_connection_by_params(&conninfo_params, false);
+
 			if (PQstatus(conn) == CONNECTION_OK)
 			{
+				free_conninfo_params(&conninfo_params);
+
 				node_info->node_status = NODE_STATUS_UP;
 				return conn;
 			}
 
-			PQfinish(conn);
+			close_connection(&conn);
 			log_notice(_("unable to reconnect to node"));
 		}
 
@@ -691,13 +754,14 @@ try_reconnect(t_node_info *node_info)
 		}
 	}
 
-
 	log_warning(_("unable to reconnect to node %i after %i attempts"),
 				node_info->node_id,
 				max_attempts);
 
 	node_info->node_status = NODE_STATUS_DOWN;
 
+	free_conninfo_params(&conninfo_params);
+
 	return NULL;
 }
 
@@ -733,24 +797,9 @@ print_monitoring_state(MonitoringState monitoring_state)
 }
 
 
-static void
-close_connections()
-{
-	if (_close_connections != NULL)
-		_close_connections();
-
-	if (local_conn != NULL && PQstatus(local_conn) == CONNECTION_OK)
-	{
-		PQfinish(local_conn);
-		local_conn = NULL;
-	}
-
-}
-
 void
 terminate(int retval)
 {
-	close_connections();
 	logger_shutdown();
 
 	if (pid_file)

repmgrd.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd.h
- * Copyright (c) 2ndQuadrant, 2010-2017
+ * Copyright (c) 2ndQuadrant, 2010-2018
  */
 
 

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * 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

strutil.h

@@ -1,6 +1,6 @@
 /*
  * strutil.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
@@ -33,12 +33,17 @@
 #define MAXLEN_STR STR(MAXLEN)
 
 
+/*
+ * These values must match the Nagios return codes defined here:
+ *
+ * https://assets.nagios.com/downloads/nagioscore/docs/nagioscore/3/en/pluginapi.html
+ */
 typedef enum
 {
-	CHECK_STATUS_OK = 0,
+	CHECK_STATUS_OK       = 0,
-	CHECK_STATUS_WARNING,
+	CHECK_STATUS_WARNING  = 1,
-	CHECK_STATUS_CRITICAL,
+	CHECK_STATUS_CRITICAL = 2,
-	CHECK_STATUS_UNKNOWN
+	CHECK_STATUS_UNKNOWN  = 3
 } CheckStatus;
 
 typedef enum

voting.h

@@ -1,6 +1,6 @@
 /*
  * voting.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