autoreconf run

Exclusive backup functionality was removed in core commit 39969e2a
so we can and must avoid checking for exclusive backups.

HISTORY

@@ -1,4 +1,26 @@
-5.2.2.  2021-??-??
+5.3.3   2022-10-17
+        Support for PostgreSQL added
+        repmgrd: ensure event notification script is called for event
+          "repmgrd_upstream_disconnect"; GitHub #760 (Ian)
+
+5.3.2   2022-05-25
+        standby clone: don't error out if unable to determine cluster size (Ian)
+        node check: fix --downstream --nagios output; GitHub #749 (Ian)
+        repmgrd: ensure witness node marked active (hslightdb)
+        repmgrd: improve walsender disable check (Ian)
+        general: ensure replication slots can be dropped by a
+          replication-only user (Ian)
+
+5.3.1   2022-02-15
+        repmgrd: fixes for potential connection leaks (hslightdb)
+        repmgr: fix upgrade path from repmgr 4.2 and 4.3 to repmgr 5.3 (Ian)
+
+5.3.0   2021-10-12
+        standby switchover: improve handling of node rejoin failure (Ian)
+        repmgrd: prefix all shared library functions with "repmgr_" to
+          minimize the risk of clashes with other shared libraries (Ian)
+        repmgrd: at startup, if node record is marked as "inactive", attempt
+          to set it to "active" (Ian)
         standby clone: set "slot_name" in node record if required (Ian)
         node rejoin: emit rejoin target note information as NOTICE (Ian)
         repmgrd: ensure short option "-s" is accepted (Ian)
@@ -52,7 +74,7 @@
           "standby clone" (Ian)
         repmgr: add --upstream option to "node check"
         repmgr: report error code on follow/rejoin failure due to non-available
-0          replication slot (Ian)
+          replication slot (Ian)
         repmgr: ensure "node rejoin" checks for available replication slots (Ian)
         repmgr: improve "standby switchover" completion checks (Ian)
         repmgr: add replication configuration file ownership check to

Makefile.in

@@ -13,6 +13,7 @@ DATA = \
   repmgr--unpackaged--4.0.sql \
   repmgr--unpackaged--5.1.sql \
   repmgr--unpackaged--5.2.sql \
+  repmgr--unpackaged--5.3.sql \
   repmgr--4.0.sql \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \
@@ -27,7 +28,9 @@ DATA = \
   repmgr--5.0--5.1.sql \
   repmgr--5.1.sql \
   repmgr--5.1--5.2.sql \
-  repmgr--5.2.sql
+  repmgr--5.2.sql \
+  repmgr--5.2--5.3.sql \
+  repmgr--5.3.sql
 
 REGRESS = repmgr_extension
 
@@ -76,10 +79,10 @@ configfile-scan.c: configfile-scan.l
 $(REPMGR_CLIENT_OBJS): repmgr-client.h repmgr_version.h
 
 repmgr: $(REPMGR_CLIENT_OBJS)
-	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
 
 repmgrd: $(REPMGRD_OBJS)
-	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
 
 $(REPMGR_CLIENT_OBJS): $(HEADERS)
 $(REPMGRD_OBJS): $(HEADERS)

README.md

@@ -7,8 +7,8 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-The most recent `repmgr` version (5.2.1) supports all PostgreSQL versions from
-9.5 to 13. PostgreSQL 9.4 is also supported, with some restrictions.
+The most recent `repmgr` version (5.3.2) supports all PostgreSQL versions from
+9.5 to 14. PostgreSQL 9.4 is also supported, with some restrictions.
 
 `repmgr` is distributed under the GNU GPL 3 and maintained by EnterpriseDB.
 
@@ -19,14 +19,6 @@ The full `repmgr` documentation is available here:
 
 > [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
-The old `README` file for `repmgr` 3.x is available here:
-
-> https://github.com/EnterpriseDB/repmgr/blob/REL3_3_STABLE/README.md
-
-Note that the `repmgr` 3.x series is no longer supported and contains known bugs;
-please upgrade to the [current repmgr version](https://repmgr.org/docs/current/appendix-release-notes.html)
-as soon as possible.
-
 Versions
 --------
 
@@ -90,3 +82,4 @@ Further reading
 * [repmgr documentation](https://repmgr.org/docs/current/index.html)
 * [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 1](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-1/)
 * [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 2](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-2/)
+* [How to implement repmgr for PostgreSQL automatic failover](https://www.enterprisedb.com/postgres-tutorials/how-implement-repmgr-postgresql-automatic-failover)

configdata.c

@@ -581,6 +581,16 @@ struct ConfigFileSetting config_file_settings[] =
 		{ .strmaxlen = sizeof(config_file_options.repmgrd_pid_file) },
 		{ .postprocess_func = &repmgr_canonicalize_path }
 	},
+	/* repmgrd_exit_on_inactive_node */
+	{
+		"repmgrd_exit_on_inactive_node",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.repmgrd_exit_on_inactive_node},
+		{ .booldefault = DEFAULT_REPMGRD_EXIT_ON_INACTIVE_NODE },
+		{},
+		{},
+		{}
+	},
 	/* standby_disconnect_on_failover */
 	{
 		"standby_disconnect_on_failover",

configfile.h

@@ -206,6 +206,7 @@ typedef struct
 	int			primary_notification_timeout;
 	int			repmgrd_standby_startup_timeout;
 	char		repmgrd_pid_file[MAXPGPATH];
+	bool		repmgrd_exit_on_inactive_node;
 	bool		standby_disconnect_on_failover;
 	int			sibling_nodes_disconnect_timeout;
 	ConnectionCheckType connection_check_type;

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 5.2.1.
+# Generated by GNU Autoconf 2.69 for repmgr 5.3.3.
 #
 # Report bugs to <repmgr@googlegroups.com>.
 #
@@ -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) 2010-2021, EnterpriseDB Corporation
+# Copyright (c) 2010-2022, EnterpriseDB Corporation
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='5.2.1'
-PACKAGE_STRING='repmgr 5.2.1'
+PACKAGE_VERSION='5.3.3'
+PACKAGE_STRING='repmgr 5.3.3'
 PACKAGE_BUGREPORT='repmgr@googlegroups.com'
 PACKAGE_URL='https://repmgr.org/'
 
@@ -1181,7 +1181,7 @@ 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 5.2.1 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.3.3 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1242,7 +1242,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 5.2.1:";;
+     short | recursive ) echo "Configuration of repmgr 5.3.3:";;
    esac
   cat <<\_ACEOF
 
@@ -1316,14 +1316,14 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 5.2.1
+repmgr configure 5.3.3
 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) 2010-2021, EnterpriseDB Corporation
+Copyright (c) 2010-2022, EnterpriseDB Corporation
 _ACEOF
   exit
 fi
@@ -1335,7 +1335,7 @@ 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 5.2.1, which was
+It was created by repmgr $as_me 5.3.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1811,11 +1811,11 @@ fi
 pgac_pg_config_version=$($PG_CONFIG --version 2>/dev/null)
 
 major_version_num=$(echo "$pgac_pg_config_version"|
-              $SED -e 's/^PostgreSQL \([0-9]\{1,2\}\).*$/\1/')
+              $SED -e 's/^[^0-9]\+ \([0-9]\{1,2\}\).*$/\1/')
 
 if test "$major_version_num" -lt '10'; then
     version_num=$(echo "$pgac_pg_config_version"|
-                $SED -e 's/^PostgreSQL \([0-9]*\)\.\([0-9]*\)\([a-zA-Z0-9.]*\)$/\1.\2/')
+                $SED -e 's/^[^0-9]\+ \([0-9]*\)\.\([0-9]*\)\([a-zA-Z0-9.]*\)$/\1.\2/')
 
     if test -z "$version_num"; then
         as_fn_error $? "could not detect the PostgreSQL version, wrong or broken pg_config?" "$LINENO" 5
@@ -1829,7 +1829,7 @@ if test "$major_version_num" -lt '10'; then
     fi
 else
     version_num=$(echo "$pgac_pg_config_version"|
-                $SED -e 's/^PostgreSQL \(.\+\)$/\1/')
+                $SED -e 's/^[^0-9]\+ \(.\+\)$/\1/')
 
     if test -z "$version_num"; then
         as_fn_error $? "could not detect the PostgreSQL version, wrong or broken pg_config?" "$LINENO" 5
@@ -2487,7 +2487,7 @@ 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 5.2.1, which was
+This file was extended by repmgr $as_me 5.3.3, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2550,7 +2550,7 @@ _ACEOF
 cat >>$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 5.2.1
+repmgr config.status 5.3.3
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [5.2.1], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.3.3], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2021, EnterpriseDB Corporation])
+AC_COPYRIGHT([Copyright (c) 2010-2022, EnterpriseDB Corporation])
 
 AC_CONFIG_HEADER(config.h)
 
@@ -19,11 +19,11 @@ fi
 pgac_pg_config_version=$($PG_CONFIG --version 2>/dev/null)
 
 major_version_num=$(echo "$pgac_pg_config_version"|
-              $SED -e 's/^PostgreSQL \([[0-9]]\{1,2\}\).*$/\1/')
+              $SED -e 's/^[[^0-9]]\+ \([[0-9]]\{1,2\}\).*$/\1/')
 
 if test "$major_version_num" -lt '10'; then
     version_num=$(echo "$pgac_pg_config_version"|
-                $SED -e 's/^PostgreSQL \([[0-9]]*\)\.\([[0-9]]*\)\([[a-zA-Z0-9.]]*\)$/\1.\2/')
+                $SED -e 's/^[[^0-9]]\+ \([[0-9]]*\)\.\([[0-9]]*\)\([[a-zA-Z0-9.]]*\)$/\1.\2/')
 
     if test -z "$version_num"; then
         AC_MSG_ERROR([could not detect the PostgreSQL version, wrong or broken pg_config?])
@@ -37,7 +37,7 @@ if test "$major_version_num" -lt '10'; then
     fi
 else
     version_num=$(echo "$pgac_pg_config_version"|
-                $SED -e 's/^PostgreSQL \(.\+\)$/\1/')
+                $SED -e 's/^[[^0-9]]\+ \(.\+\)$/\1/')
 
     if test -z "$version_num"; then
         AC_MSG_ERROR([could not detect the PostgreSQL version, wrong or broken pg_config?])

dbutils.c

@@ -61,6 +61,8 @@ static ReplSlotStatus _verify_replication_slot(PGconn *conn, char *slot_name, PQ
 
 static bool _create_event(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details, t_event_info *event_info, bool send_notification);
 
+static NodeAttached _is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state, bool quiet);
+
 /*
  * This provides a standardized way of logging database errors. Note
  * that the provided PGconn can be a normal or a replication connection;
@@ -1289,21 +1291,16 @@ get_cluster_size(PGconn *conn, char *size)
 	initPQExpBuffer(&query);
 	appendPQExpBufferStr(&query,
 						 "SELECT pg_catalog.pg_size_pretty(pg_catalog.sum(pg_catalog.pg_database_size(oid))::bigint) "
-						 "	 FROM pg_catalog.pg_database ");
+						 "  FROM pg_catalog.pg_database ");
 
 	log_verbose(LOG_DEBUG, "get_cluster_size():\n%s", query.data);
 
 	res = PQexec(conn, query.data);
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
-	{
-		log_db_error(conn, query.data, _("get_cluster_size(): unable to execute query"));
 		success = false;
-	}
 	else
-	{
 		snprintf(size, MAXLEN, "%s", PQgetvalue(res, 0, 0));
-	}
 
 	termPQExpBuffer(&query);
 	PQclear(res);
@@ -1826,6 +1823,30 @@ get_timeline_history(PGconn *repl_conn, TimeLineID tli)
 }
 
 
+pid_t
+get_wal_receiver_pid(PGconn *conn)
+{
+	PGresult   *res = NULL;
+	pid_t		wal_receiver_pid = UNKNOWN_PID;
+
+	res = PQexec(conn, "SELECT repmgr.get_wal_receiver_pid()");
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_error(_("unable to execute \"SELECT repmgr.get_wal_receiver_pid()\""));
+		log_detail("%s", PQerrorMessage(conn));
+	}
+	else if (!PQgetisnull(res, 0, 0))
+	{
+		wal_receiver_pid = atoi(PQgetvalue(res, 0, 0));
+	}
+
+	PQclear(res);
+
+	return wal_receiver_pid;
+}
+
+
 /* =============================== */
 /* user/role information functions */
 /* =============================== */
@@ -1867,6 +1888,42 @@ can_execute_pg_promote(PGconn *conn)
 }
 
 
+/*
+ * Determine if the user associated with the current connection
+ * has sufficient permissions to disable the walsender
+ */
+bool
+can_disable_walsender(PGconn *conn)
+{
+	/*
+	 * Requires PostgreSQL 9.5 or later, because ALTER SYSTEM
+	 */
+	if (PQserverVersion(conn) < 90500)
+	{
+		log_warning(_("\"standby_disconnect_on_failover\" specified, but not available for this PostgreSQL version"));
+		/* TODO: format server version */
+		log_detail(_("available from PostgreSQL 9.5; this PostgreSQL version is %i"), PQserverVersion(conn));
+
+		return false;
+	}
+
+	/*
+	 * Superusers can do anything
+	 */
+	if (is_superuser_connection(conn, NULL) == true)
+		return true;
+
+	/*
+	 * As of PostgreSQL 14, it is not possible for a non-superuser
+	 * to execute ALTER SYSTEM, so further checks are superfluous.
+	 * This will need modifying for PostgreSQL 15.
+	 */
+	log_warning(_("\"standby_disconnect_on_failover\" specified, but repmgr user is not a superuser"));
+	log_detail(_("superuser permission required to disable standbys on failover"));
+
+	return false;
+}
+
 /*
  * Determine if the user associated with the current connection is
  * a member of the "pg_monitor" default role, or optionally one
@@ -2082,7 +2139,13 @@ server_in_exclusive_backup_mode(PGconn *conn)
 {
 	BackupState backup_state = BACKUP_STATE_UNKNOWN;
 	const char *sqlquery = "SELECT pg_catalog.pg_is_in_backup()";
-	PGresult   *res = PQexec(conn, sqlquery);
+	PGresult   *res = NULL;
+
+	/* Exclusive backup removed from PostgreSQL 15 */
+	if (PQserverVersion(conn) >= 150000)
+		return BACKUP_STATE_NO_BACKUP;
+
+	res = PQexec(conn, sqlquery);
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
@@ -2246,29 +2309,6 @@ repmgrd_pause(PGconn *conn, bool pause)
 	return success;
 }
 
-pid_t
-get_wal_receiver_pid(PGconn *conn)
-{
-	PGresult   *res = NULL;
-	pid_t		wal_receiver_pid = UNKNOWN_PID;
-
-	res = PQexec(conn, "SELECT repmgr.get_wal_receiver_pid()");
-
-	if (PQresultStatus(res) != PGRES_TUPLES_OK)
-	{
-		log_error(_("unable to execute \"SELECT repmgr.get_wal_receiver_pid()\""));
-		log_detail("%s", PQerrorMessage(conn));
-	}
-	else if (!PQgetisnull(res, 0, 0))
-	{
-		wal_receiver_pid = atoi(PQgetvalue(res, 0, 0));
-	}
-
-	PQclear(res);
-
-	return wal_receiver_pid;
-}
-
 
 int
 repmgrd_get_upstream_node_id(PGconn *conn)
@@ -4242,7 +4282,7 @@ _create_event(PGconn *conn, t_configuration_options *options, int node_id, char
 						}
 						break;
 					case 'p':
-						/* %p: primary id ("standby_switchover": former primary id) */
+						/* %p: primary id ("standby_switchover"/"repmgrd_failover_promote": former primary id) */
 						src_ptr++;
 						if (event_info->node_id != UNKNOWN_NODE_ID)
 						{
@@ -4576,17 +4616,17 @@ drop_replication_slot_replprot(PGconn *repl_conn, char *slot_name)
 	initPQExpBuffer(&query);
 
 	appendPQExpBuffer(&query,
-					  "DROP_REPLICATION_SLOT %s",
+					  "DROP_REPLICATION_SLOT %s;",
 					  slot_name);
 
 	log_verbose(LOG_DEBUG, "drop_replication_slot_replprot():\n  %s", query.data);
 
 	res = PQexec(repl_conn, query.data);
 
-	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	if (PQresultStatus(res) != PGRES_TUPLES_OK || !PQntuples(res))
 	{
 		log_db_error(repl_conn, query.data,
-					 _("drop_replication_slot_sql(): unable to drop replication slot \"%s\""),
+					 _("drop_replication_slot_replprot(): unable to drop replication slot \"%s\""),
 					 slot_name);
 
 		success = false;
@@ -5704,7 +5744,7 @@ get_node_timeline(PGconn *conn, char *timeline_id_str)
 	TimeLineID timeline_id  = UNKNOWN_TIMELINE_ID;
 
 	/*
-	 * PG_control_checkpoint() was introduced in PostgreSQL 9.6
+	 * pg_control_checkpoint() was introduced in PostgreSQL 9.6
 	 */
 	if (PQserverVersion(conn) >= 90600)
 	{
@@ -5792,6 +5832,19 @@ get_node_replication_stats(PGconn *conn, t_node_info *node_info)
 NodeAttached
 is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state)
 {
+	return _is_downstream_node_attached(conn, node_name, node_state, false);
+}
+
+NodeAttached
+is_downstream_node_attached_quiet(PGconn *conn, char *node_name, char **node_state)
+{
+	return _is_downstream_node_attached(conn, node_name, node_state, true);
+}
+
+NodeAttached
+_is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state, bool quiet)
+{
+
 	PQExpBufferData query;
 	PGresult   *res = NULL;
 
@@ -5826,9 +5879,12 @@ is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state)
 	 */
 	if (PQntuples(res) > 1)
 	{
-		log_error(_("multiple entries with \"application_name\" set to  \"%s\" found in \"pg_stat_replication\""),
-				  node_name);
-		log_hint(_("verify that a unique node name is configured for each node"));
+		if (quiet == false)
+		{
+			log_error(_("multiple entries with \"application_name\" set to  \"%s\" found in \"pg_stat_replication\""),
+					  node_name);
+			log_hint(_("verify that a unique node name is configured for each node"));
+		}
 
 		PQclear(res);
 
@@ -5837,7 +5893,8 @@ is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state)
 
 	if (PQntuples(res) == 0)
 	{
-		log_warning(_("node \"%s\" not found in \"pg_stat_replication\""), node_name);
+		if (quiet == false)
+			log_warning(_("node \"%s\" not found in \"pg_stat_replication\""), node_name);
 
 		PQclear(res);
 
@@ -5863,9 +5920,10 @@ is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state)
 
 		if (strcmp(state, "streaming") != 0)
 		{
-			log_warning(_("node \"%s\" attached in state \"%s\""),
-						node_name,
-						state);
+			if (quiet == false)
+				log_warning(_("node \"%s\" attached in state \"%s\""),
+							node_name,
+							state);
 
 			PQclear(res);
 
@@ -6008,6 +6066,43 @@ is_wal_replay_paused(PGconn *conn, bool check_pending_wal)
 	return is_paused;
 }
 
+/* repmgrd status functions */
+
+CheckStatus
+get_repmgrd_status(PGconn *conn)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+	CheckStatus	repmgrd_status = CHECK_STATUS_CRITICAL;
+
+	initPQExpBuffer(&query);
+
+	appendPQExpBufferStr(&query,
+						 " SELECT "
+						 " CASE "
+						 "   WHEN repmgr.repmgrd_is_running() "
+						 "   THEN "
+						 "     CASE "
+						 "       WHEN repmgr.repmgrd_is_paused() THEN 1 ELSE 0 "
+						 "     END "
+						 "   ELSE 2 "
+						 " END AS repmgrd_status");
+	res = PQexec(conn, query.data);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, query.data, _("unable to execute repmgrd status query"));
+	}
+	else
+	{
+		repmgrd_status = atoi(PQgetvalue(res, 0, 0));
+	}
+
+	termPQExpBuffer(&query);
+	PQclear(res);
+	return repmgrd_status;
+}
+
 
 /* miscellaneous debugging functions */
 

dbutils.h

@@ -450,9 +450,11 @@ int			get_ready_archive_files(PGconn *conn, const char *data_directory);
 bool		identify_system(PGconn *repl_conn, t_system_identification *identification);
 uint64		system_identifier(PGconn *conn);
 TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
+pid_t		get_wal_receiver_pid(PGconn *conn);
 
 /* user/role information functions */
 bool		can_execute_pg_promote(PGconn *conn);
+bool		can_disable_walsender(PGconn *conn);
 bool		connection_has_pg_monitor_role(PGconn *conn, const char *subrole);
 bool		is_replication_role(PGconn *conn, char *rolname);
 bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
@@ -467,7 +469,6 @@ pid_t		repmgrd_get_pid(PGconn *conn);
 bool		repmgrd_is_running(PGconn *conn);
 bool		repmgrd_is_paused(PGconn *conn);
 bool		repmgrd_pause(PGconn *conn, bool pause);
-pid_t		get_wal_receiver_pid(PGconn *conn);
 int			repmgrd_get_upstream_node_id(PGconn *conn);
 bool		repmgrd_set_upstream_node_id(PGconn *conn, int node_id);
 
@@ -597,11 +598,15 @@ int			get_replication_lag_seconds(PGconn *conn);
 TimeLineID	get_node_timeline(PGconn *conn, char *timeline_id_str);
 void		get_node_replication_stats(PGconn *conn, t_node_info *node_info);
 NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state);
+NodeAttached is_downstream_node_attached_quiet(PGconn *conn, char *node_name, char **node_state);
 void		set_upstream_last_seen(PGconn *conn, int upstream_node_id);
 int			get_upstream_last_seen(PGconn *conn, t_server_type node_type);
 
 bool		is_wal_replay_paused(PGconn *conn, bool check_pending_wal);
 
+/* repmgrd status functions */
+CheckStatus	get_repmgrd_status(PGconn *conn);
+
 /* miscellaneous debugging functions */
 const char *print_node_status(NodeStatus node_status);
 const char *print_pqping_status(PGPing ping_status);

doc/appendix-faq.xml

@@ -249,16 +249,16 @@
         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 --replication-conf-only</link></command>
-        can be used to create the correct <filename>recovery.conf</filename> file for
+        can be used to create the correct replication configuration 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>
+      <title>What does &repmgr; write in the replication configuration, and what options can be set there?</title>
       <para>
-        See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
+        See section <link linkend="repmgr-standby-clone-recovery-conf">Customising replication configuration</link>.
       </para>
     </sect2>
 
@@ -366,11 +366,11 @@
       </para>
     </sect2>
 
-    <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in recovery.conf">
-      <title>Why are some values in <filename>recovery.conf</filename> surrounded by pairs of single quotes?</title>
+    <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in replication.conf">
+      <title>Why are some values in <filename>recovery.conf</filename> (PostgreSQL 11 and earlier) surrounded by pairs of single quotes?</title>
       <para>
         This is to ensure that user-supplied values which are written as parameter values in <filename>recovery.conf</filename>
-        are escaped correctly and do not cause errors when <filename>recovery.conf</filename> is parsed.
+        are escaped correctly and do not cause errors when the file is parsed.
       </para>
       <para>
         The escaping is performed by an internal PostgreSQL routine, which leaves strings consisting
@@ -419,9 +419,9 @@
       <para>
         &repmgrd; can monitor delayed standbys - those set up with
         <varname>recovery_min_apply_delay</varname> set to a non-zero value
-        in <filename>recovery.conf</filename> - but as it's not currently possible
-        to directly examine the value applied to the standby, &repmgrd;
-        may not be able to properly evaluate the node as a promotion candidate.
+        in the replication configuration. However &repmgrd; does not currently
+        consider this setting, and therefore may not be able to properly evaluate
+        the node as a promotion candidate.
       </para>
       <para>
         We recommend that delayed standbys are explicitly excluded from promotion

doc/appendix-packages.xml

@@ -50,18 +50,18 @@
       <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
+        &repmgr; packages are available from the public EDB repository, and also the
+        PostgreSQL community repository. The EDB repository is updated immediately
         after each &repmgr; release.
       </para>
 
       <table id="centos-2ndquadrant-repository">
-        <title>2ndQuadrant public repository</title>
+        <title>EDB public repository</title>
         <tgroup cols="2">
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="https://dl.2ndquadrant.com/">https://dl.2ndquadrant.com/</ulink></entry>
+              <entry><ulink url="https://dl.enterprisedb.com/">https://dl.enterprisedb.com/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -252,7 +252,7 @@
     </indexterm>
 
     <para>
-      &repmgr; <literal>.deb</literal> packages are provided by 2ndQuadrant as well as the
+      &repmgr; <literal>.deb</literal> packages are provided by EDB as well as the
       PostgreSQL Community APT repository, and are available for each community-supported
       PostgreSQL version, currently supported Debian releases, and currently supported
       Ubuntu LTS releases.
@@ -262,12 +262,12 @@
       <title>APT repositories</title>
 
       <table id="apt-2ndquadrant-repository">
-        <title>2ndQuadrant public repository</title>
+        <title>EDB public repository</title>
         <tgroup cols="2">
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="https://dl.2ndquadrant.com/">https://dl.2ndquadrant.com/</ulink></entry>
+              <entry><ulink url="https://dl.enterprisedb.com/">https://dl.enterprisedb.com/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -401,7 +401,7 @@
     </indexterm>
 
     <para>
-      For testing new features and bug fixes, from time to time 2ndQuadrant provides
+      For testing new features and bug fixes, from time to time EDB provides
       so-called &quot;snapshot packages&quot; via its public repository. These packages
       are built from the &repmgr; source at a particular point in time, and are not formal
       releases.
@@ -413,22 +413,22 @@
       </para>
     </note>
     <para>
-      To install a snapshot package, it's necessary to install the 2ndQuadrant public snapshot repository,
-      following the instructions here: <ulink url="https://dl.2ndquadrant.com/default/release/site/">https://dl.2ndquadrant.com/default/release/site/</ulink> but replace <literal>release</literal> with <literal>snapshot</literal>
+      To install a snapshot package, it's necessary to install the EDB public snapshot repository,
+      following the instructions here: <ulink url="https://dl.enterprisedb.com/default/release/site/">https://dl.enterprisedb.com/default/release/site/</ulink> but replace <literal>release</literal> with <literal>snapshot</literal>
       in the appropriate URL.
     </para>
     <para>
       For example, to install the snapshot RPM repository for PostgreSQL 9.6, execute (as <literal>root</literal>):
       <programlisting>
-curl https://dl.2ndquadrant.com/default/snapshot/get/9.6/rpm | bash</programlisting>
+curl https://dl.enterprisedb.com/default/snapshot/get/9.6/rpm | bash</programlisting>
 
       or as a normal user with root sudo access:
       <programlisting>
-curl https://dl.2ndquadrant.com/default/snapshot/get/9.6/rpm | sudo bash</programlisting>
+curl https://dl.enterprisedb.com/default/snapshot/get/9.6/rpm | sudo bash</programlisting>
     </para>
     <para>
       Alternatively you can browse the repository here:
-      <ulink url="https://dl.2ndquadrant.com/default/snapshot/browse/">https://dl.2ndquadrant.com/default/snapshot/browse/</ulink>.
+      <ulink url="https://dl.enterprisedb.com/default/snapshot/browse/">https://dl.enterprisedb.com/default/snapshot/browse/</ulink>.
     </para>
     <para>
       Once the repository is installed, installing or updating &repmgr; will result in the latest snapshot
@@ -493,32 +493,6 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
           yum install repmgr96-4.0.6-1.rhel6</programlisting>
       </para>
 
-      <sect3 id="packages-old-versions-rhel-centos-repmgr3">
-        <title>repmgr 3 packages</title>
-        <para>
-          Old &repmgr; 3 RPM packages (<literal>3.2</literal> and later) can be retrieved from the
-          (deprecated) 2ndQuadrant repository at
-          <ulink url="http://packages.2ndquadrant.com/repmgr/yum/">http://packages.2ndquadrant.com/repmgr/yum/</ulink>
-          by installing the appropriate repository RPM:
-        </para>
-
-        <itemizedlist spacing="compact" mark="bullet">
-
-          <listitem>
-            <simpara>
-              <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-fedora-1.0-1.noarch.rpm</ulink>
-            </simpara>
-          </listitem>
-
-          <listitem>
-            <simpara>
-              <ulink url="http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm">http://packages.2ndquadrant.com/repmgr/yum-repo-rpms/repmgr-rhel-1.0-1.noarch.rpm</ulink>
-            </simpara>
-          </listitem>
-
-        </itemizedlist>
-      </sect3>
-
     </sect2>
   </sect1>
 

doc/appendix-release-notes.xml

@@ -15,18 +15,216 @@
     See also: <xref linkend="upgrading-repmgr"/>
   </para>
 
-<!-- remember to update the release date in ../repmgr_version.h.in -->
-  <sect1 id="release-5.2.2">
-    <title id="release-current">Release 5.2.2</title>
-    <para><emphasis>??? ? ???, 2021</emphasis></para>
+  <!-- remember to update the release date in ../repmgr_version.h.in -->
+  <sect1 id="release-5.3.3">
+    <title id="release-current">Release 5.3.3</title>
+    <para><emphasis>Mon 17 October, 2022</emphasis></para>
     <para>
-      &repmgr; 5.2.2 is a minor release.
+      &repmgr; 5.3.3 is a minor release providing support for
+      <ulink url="https://www.postgresql.org/docs/15/release-15.html">PostgreSQL 15</ulink>
+      and a &repmgrd; bug fix.
+    </para>
+    <para>
+      If upgrading from an earlier &repmgr; version, any running &repmgrd; instances should be restarted.
+    </para>
+    <para>
+      If upgrading from &repmgr; 5.2.1 or earlier, a PostgreSQL restart <emphasis>is</emphasis> required.
+    </para>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              &repmgrd;: ensure <link linkend="event-notifications">event notification</link> script is called for event
+              <literal>repmgrd_upstream_disconnect</literal>.  GitHub #760.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+
+  <sect1 id="release-5.3.2">
+    <title>Release 5.3.2</title>
+    <para><emphasis>Wed 25 May, 2022</emphasis></para>
+    <para>
+      &repmgr; 5.3.2 is a minor release.
+    </para>
+    <para>
+      Any running &repmgrd; instances should be restarted following this upgrade.
+    </para>
+    <para>
+      If upgrading from &repmgr; 5.2.1 or earlier, a PostgreSQL restart <emphasis>is</emphasis> required.
+    </para>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-node-status">repmgr node status</link></command>:
+              fix output with <option>--downstream</option> <option>--nagios</option> option combination.
+              GitHub #749.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
+              don't treat inability to determine the cluster size as a fatal error.
+            </para>
+            <para>
+              The cluster size is displayed for informational purposes and is not essential
+              for execution of the clone operation. As the &repmgr; user may not have permissions
+              for all databases in the cluster, ignore the cluster size query if it fails.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: ensure the witness node record on the primary is always marked
+              as <literal>active</literal> if previously marked <literal>inactive</literal>.
+              GitHub #754.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: if <varname>standby_disconnect_on_failover</varname> is set, verify
+              &repmgr; is a superuser before attempting to disable the WAL receiver.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              If the &repmgr; user is a non-superuser, and a replication-only user exists,
+              ensure redundant replication slots are dropped correctly even
+              if the <option>-S/--superuser</option> option is not provided.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+
+  <sect1 id="release-5.3.1">
+    <title>Release 5.3.1</title>
+    <para><emphasis>Tue 15 February, 2022</emphasis></para>
+    <para>
+      &repmgr; 5.3.1 is a minor release.
+    </para>
+    <para>
+      If &repmgrd; is in use, it should be restarted on all nodes where it is running.
+    </para>
+    <para>
+      If upgrading from &repmgr; 5.2.1 or earlier, a PostgreSQL restart <emphasis>is</emphasis> required.
     </para>
     <sect2>
       <title>Bug fixes</title>
       <para>
+        <itemizedlist>
+           <listitem>
+             <para>
+               Fix upgrade path from &repmgr; 4.2 and 4.3 to &repmgr; 5.3.
+             </para>
+           </listitem>
+           <listitem>
+             <para>
+               &repmgrd;: ensure potentially open connections are closed.
+             </para>
+             <para>
+                In some cases, when recovering from degraded state in local node monitoring,
+                new connection was opened to the local node without closing
+                the old one, which will result in memory leakage.
+             </para>
+           </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
 
-         <itemizedlist>
+  <sect1 id="release-5.3.0">
+    <title>Release 5.3.0</title>
+    <para><emphasis>Tue 12 October, 2021</emphasis></para>
+    <para>
+      &repmgr; 5.3.0 is a major release.
+    </para>
+    <para>
+      This release provides support for <ulink url="https://www.postgresql.org/docs/14/release-14.html">PostgreSQL 14</ulink>,
+      released in September 2021.
+    </para>
+    <para>
+      Note that this release includes changes to the &repmgr; shared library module, meaning a
+      PostgreSQL restart <emphasis>is</emphasis> required on all nodes where &repmgr; is installed.
+    </para>
+
+    <sect2>
+      <title>Improvements</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              Improve handling of node rejoin failure on the demotion candidate.
+            </para>
+            <para>
+              Previously &repmgr; did not check whether <command>repmgr node rejoin</command> actually
+              succeeded on the demotion candidate, and would always wait up to <varname>node_rejoin_timeout</varname>
+              seconds for it to attach to the promotion candidate, even if this would never happen.
+            </para>
+            <para>
+              This makes it easier to identify unexpected events during a switchover operation, such as
+              the demotion candidate being unexpectedly restarted by an external process.
+            </para>
+            <para>
+              Note that the output of the <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>
+              operation on the demotion candidate will now be logged to a temporary file on that node;
+              the location of the file will be reported in the error message, if one is emitted.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: at startup, if node record is marked as "inactive", attempt
+              to set it to "active".
+            </para>
+            <para>
+              This behaviour can be overridden by setting the configuration parameter
+              <varname>repmgrd_exit_on_inactive_node</varname> to <literal>true</literal>.
+            </para>
+          </listitem>
+           <listitem>
+             <para>
+               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
+               emit rejoin target note information as <literal>NOTICE</literal>.
+             </para>
+             <para>
+               This makes it clearer what &repmgr; is trying to do.
+             </para>
+           </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check">repmgr node check</link>:
+              option <option>--repmgrd</option> added to check &repmgrd;
+              status.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add <literal>%p</literal> <link linkend="event-notifications">event notification parameter</link>
+              providing the node ID of the former primary for the <literal>repmgrd_failover_promote</literal> event.
+            </para>
+          </listitem>
+
+        </itemizedlist>
+
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
            <listitem>
             <para>
               <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>:
@@ -38,22 +236,24 @@
             </para>
            </listitem>
 
+
            <listitem>
-             <para>
-               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
-               emit rejoin target note information as <literal>NOTICE</literal>.
-             </para>
-             <para>
-               This makes it clearer what &repmgr; is trying to do.
-             </para>
-           </listitem>
+            <para>
+              &repmgrd;: rename internal shared library functions to minimize the
+              risk of clashes with other shared libraries.
+            </para>
+            <para>
+              This does not affect user-facing SQL functions. However an upgrade
+              of the installed extension version is required.
+            </para>
+          </listitem>
+
           <listitem>
             <para>
               &repmgrd;: ensure short option <option>-s</option> is accepted.
             </para>
           </listitem>
-
-         </itemizedlist>
+        </itemizedlist>
       </para>
     </sect2>
   </sect1>

doc/appendix-support.xml

@@ -7,13 +7,13 @@
   </indexterm>
 
   <para>
-    <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides 24x7
+    <ulink url="https://www.enterprisedb.com/">EDB</ulink> provides 24x7
     production support for &repmgr; and other PostgreSQL
     products, including configuration assistance, installation
     verification and training for running a robust replication cluster.
   </para>
   <para>
-    For further details see: <ulink url="https://2ndquadrant.com/en/support/">https://2ndquadrant.com/en/support/</ulink>
+    For further details see: <ulink url="https://www.enterprisedb.com/support/postgresql-support-overview-get-the-most-out-of-postgresql">Support Center</ulink>
   </para>
 
   <para>

doc/cloning-standbys.xml

@@ -15,7 +15,7 @@
 
    <para>
     <xref linkend="repmgr-standby-clone"/> can use
-    <ulink url="https://www.2ndquadrant.com/">2ndQuadrant</ulink>'s
+    <ulink url="https://www.enterprisedb.com/">EDB</ulink>'s
     <ulink url="https://www.pgbarman.org/">Barman</ulink> application
     to clone a standby (and also as a fallback source for WAL files).
    </para>
@@ -197,7 +197,7 @@ description = "Main cluster"
    <para>
     As a fallback in case streaming replication is interrupted, PostgreSQL can optionally
     retrieve WAL files from an archive, such as that provided by Barman. This is done by
-    setting <varname>restore_command</varname> in <filename>recovery.conf</filename> to
+    setting <varname>restore_command</varname> in the replication configuration to
     a valid shell command which can retrieve a specified WAL file from the archive.
    </para>
    <para>
@@ -299,7 +299,7 @@ description = "Main cluster"
      build up indefinitely, possibly leading to server failure.
     </simpara>
     <simpara>
-     As an alternative we recommend using 2ndQuadrant's <ulink url="https://www.pgbarman.org/">Barman</ulink>,
+     As an alternative we recommend using EDB's <ulink url="https://www.pgbarman.org/">Barman</ulink>,
      which offloads WAL management to a separate server, removing the requirement to use a replication
      slot for each individual standby to reserve WAL. See section <xref linkend="cloning-from-barman"/>
      for more details on using &repmgr; together with Barman.
@@ -328,9 +328,9 @@ description = "Main cluster"
     &repmgr; supports cascading replication. When cloning a standby,
     set the command-line parameter <literal>--upstream-node-id</literal> to the
     <varname>node_id</varname> of the server the standby should connect to, and
-    &repmgr; will create <filename>recovery.conf</filename> to point to it. Note
+    &repmgr; will create a replication configuration file to point to it. Note
     that if <literal>--upstream-node-id</literal> is not explicitly provided,
-    &repmgr; will set the standby's <filename>recovery.conf</filename> to
+    &repmgr; will set the standby's replication configuration to
     point to the primary node.
    </para>
    <para>
@@ -392,7 +392,7 @@ description = "Main cluster"
      does not yet exist. In this case you can clone from the primary (or
      another upstream node); provide the parameter <literal>--upstream-conninfo</literal>
      to explicitly set the upstream's <varname>primary_conninfo</varname> string
-     in <filename>recovery.conf</filename>.
+     in the replication configuration.
     </simpara>
    </tip>
  </sect1>
@@ -491,12 +491,12 @@ description = "Main cluster"
     </note>
 
     <para>
-     If, for whatever reason, you wish to include the password in <filename>recovery.conf</filename>,
+     If, for whatever reason, you wish to include the password in the replication configuration file,
      set <varname>use_primary_conninfo_password</varname> to <literal>true</literal> in
      <filename>repmgr.conf</filename>. This will read a password set in <varname>PGPASSWORD</varname>
      (but not <filename>~/.pgpass</filename>) and place it into the <varname>primary_conninfo</varname>
-     string in <filename>recovery.conf</filename>. Note that <varname>PGPASSWORD</varname>
-     will need to be set during any action which causes <filename>recovery.conf</filename> to be
+     string in the replication configuration. Note that <varname>PGPASSWORD</varname>
+     will need to be set during any action which causes the replication configuration file to be
      rewritten, e.g. <xref linkend="repmgr-standby-follow"/>.
     </para>
    </sect2>
@@ -508,7 +508,7 @@ description = "Main cluster"
      user (in addition to the user who manages the &repmgr; metadata). In this case,
      the replication user should be set in <filename>repmgr.conf</filename> via the parameter
      <varname>replication_user</varname>; &repmgr; will use this value when making
-     replication connections and generating <filename>recovery.conf</filename>. This
+     replication connections and generating the replication configuration. This
      value will also be stored in the parameter <literal>repmgr.nodes</literal>
      table for each node; it no longer needs to be explicitly specified when
      cloning a node or executing <xref linkend="repmgr-standby-follow"/>.

doc/configuration-file.xml

@@ -164,7 +164,7 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
     </para>
     <para>
       For a full list of annotated configuration items, see the file
-      <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
+      <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
     </para>
     <para>
       For &repmgrd;-specific settings, see <xref linkend="repmgrd-configuration"/>.
@@ -262,7 +262,7 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
 
     <indexterm>
       <primary>repmgr.conf</primary>
-      <secondary>ostgreSQL major version upgrades</secondary>
+      <secondary>PostgreSQL major version upgrades</secondary>
     </indexterm>
 
     <para>

doc/configuration-permissions.xml

@@ -7,19 +7,186 @@
   </indexterm>
 
   <para>
-    &repmgr; requires that the database defined in the <varname>conninfo</varname>
-    setting contains the <literal>repmgr</literal> extension. The database user defined in the
-    <varname>conninfo</varname> setting must be able to access this database and
-    the database objects contained within the extension.
-  </para>
-  <para>
-    The <literal>repmgr</literal> extension can only be installed by a superuser.
-    If the &repmgr; user is a superuser, &repmgr; will create the extension automatically.
+    If the &repmgr; database user (the PostgreSQL user defined in the
+    <varname>conninfo</varname> setting is a superuser, no further user permissions need
+    to be granted.
   </para>
 
-  <para>
-    Alternatively, the extension can be created manually by a superuser
-    (with &quot;<command>CREATE EXTENSION repmgr</command>&quot;) before executing
-    <link linkend="repmgr-primary-register">repmgr primary register</link>.
-  </para>
+  <sect2 id="configuration-permissions-no-superuser" xreflabel="Non-super user permissions">
+    <title>repmgr user as a non-superuser</title>
+    <para>
+      In principle the &repmgr; database user does not need to be a superuser.
+      In this case the &repmgr; will need to be granted execution permissions on certain
+      functions, and membership of certain roles. However be aware that &repmgr; does
+      expect to be able to execute certain commands which are restricted to superusers;
+      in this case either a superuser must be specified with the <option>-S</option>/<option>--superuser</option>
+      (where available) option, or the corresponding action should be executed manually as a superuser.
+    </para>
+    <para>
+      The following sections describe the actions needed to use &repmgr; with a non-superuser,
+      and relevant caveats.
+    </para>
+    <sect3 id="configuration-permissions-replication" xreflabel="Replication role">
+      <title>Replication role</title>
+      <para>
+        &repmgr; requires a database user with the <literal>REPLICATION</literal> role
+        to be able to create a replication connection and (if configured) to administer
+        replication slots.
+      </para>
+      <para>
+        By default this is the database user defined in the <varname>conninfo</varname>
+        setting. This user can be:
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara>
+              a superuser
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              a non-superuser with the <literal>REPLICATION</literal> role
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              another user defined in the <filename>repmgr.conf</filename> parameter <varname>replication_user</varname> with the <literal>REPLICATION</literal> role
+            </simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect3>
+
+    <sect3 id="configuration-permissions-roles" xreflabel="Database roles for non-superusers">
+      <title>Database roles</title>
+      <para>
+        A non-superuser &repmgr; database user should be a member of the following
+        <ulink url="https://www.postgresql.org/docs/current/predefined-roles.html">predefined roles</ulink>
+        (PostgreSQL 10 and later):
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara>
+              <varname>pg_read_all_stats</varname>
+              (to read the <varname>status</varname> column of <literal>pg_stat_replication</literal>
+              and execute <function>pg_database_size()</function> on all databases)
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              <varname>pg_read_all_settings</varname> (to access the <varname>data_directory</varname> setting)
+            </simpara>
+          </listitem>
+        </itemizedlist>
+        Alternatively the meta-role <varname>pg_monitor</varname> can be granted, which includes membership
+        of the above predefined roles.
+      </para>
+      <para>
+        Membership of these roles can be granted with e.g. <command>GRANT pg_read_all_stats TO repmgr</command>.
+      </para>
+      <para>
+        Users of PostgreSQL 9.6 or earlier should upgrade to a supported PostgreSQL version, or provide
+        the <option>-S</option>/<option>--superuser</option> where available.
+      </para>
+    </sect3>
+
+    <sect3 id="configuration-permissions-extension" xreflabel="Extension creation">
+      <title>Extension creation</title>
+      <para>
+        &repmgr; requires that the database defined in the <varname>conninfo</varname>
+        setting contains the <literal>repmgr</literal> extension. The database user defined in the
+        <varname>conninfo</varname> setting must be able to access this database and
+        the database objects contained within the extension.
+      </para>
+      <para>
+        The <literal>repmgr</literal> extension can only be installed by a superuser.
+        If the &repmgr; user is a superuser, &repmgr; will create the extension automatically.
+      </para>
+
+      <para>
+        Alternatively, the extension can be created manually by a superuser
+        (with &quot;<command>CREATE EXTENSION repmgr</command>&quot;) before executing
+        <link linkend="repmgr-primary-register">repmgr primary register</link>.
+      </para>
+    </sect3>
+
+
+    <sect3 id="configuration-permissions-functions" xreflabel="Function permissions for non-superusers">
+      <title>Function permissions</title>
+      <para>
+        If the &repmgr; database user is not a superuser, <literal>EXECUTE</literal> permission should be
+        granted on the following function:
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara>
+              <function>pg_wal_replay_resume()</function> (required by &repmgrd; during failover operations;
+              if permission is not granted, the failoved process may not function reliably if a node
+              has WAL replay paused)
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              <function>pg_promote()</function> (PostgreSQL 12 and later; if permission is not granted,
+              &repmgr; will fall back to <command>pg_ctl promote</command>)
+            </simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+      <para>
+        <literal>EXECUTE</literal> permission on functions can be granted with e.g.:
+        <command>GRANT EXECUTE ON FUNCTION pg_catalog.pg_wal_replay_resume() TO repmgr</command>.
+      </para>
+    </sect3>
+
+    <sect3 id="configuration-permissions-superuser-required" xreflabel="repmgr actions requiring a superuser">
+      <title>repmgr actions requiring a superuser</title>
+      <para>
+        In some circumstances, &repmgr; may need to perform an operation which cannot be delegated to a
+        non-superuser.
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara>
+              The <command>CHECKPOINT</command> command is executed by
+              <link linkend="repmgr-standby-switchover">repmgr standby switchover</link>. This can only
+              be executed by a superuser; if the &repmgr; user is not a superuser,
+              the <option>-S</option>/<option>--superuser</option> should be used.
+            </simpara>
+            <simpara>
+              If &repmgr; is not able to execute <command>CHECKPOINT</command>,
+              there is a risk that the demotion candidate may not  be able to shut down as smoothly as might otherwise
+              have been the case.
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              The <command>ALTER SYSTEM</command> is executed by &repmgrd; if
+              <varname>standby_disconnect_on_failover</varname> is set to <literal>true</literal> in
+              <filename>repmgr.conf</filename>. <command>ALTER SYSTEM</command> can only be executed by
+              a superuser; if the &repmgr; user is not a superuser, this functionality will not be available.
+            </simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect3>
+
+    <sect3 id="configuration-permissions-superuser-option" xreflabel="repmgr commands with --superuser option">
+      <title>repmgr commands with --superuser option</title>
+      <para>
+        The following repmgr commands provide the <option>-S</option>/<option>--superuser</option> option:
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara><link linkend="repmgr-standby-clone">repmgr standby clone</link> (to be able to copy configuration files outside of the data directory if <option>--copy-external-config-files</option> provided)</simpara>
+          </listitem>
+          <listitem>
+            <simpara><link linkend="repmgr-standby-switchover">repmgr standby switchover</link> (to execute <command>CHECKPOINT</command>)</simpara>
+          </listitem>
+          <listitem>
+            <simpara><link linkend="repmgr-node-check">repmgr node check</link> (to execute <command>repmgr node check --data-directory-config</command>; note this is also called by <link linkend="repmgr-standby-switchover">repmgr standby switchover</link>)</simpara>
+          </listitem>
+          <listitem>
+            <simpara><link linkend="repmgr-node-service">repmgr node service</link> (to execute <command>CHECKPOINT</command> via the <option>--checkpoint</option>; note this is also called by <link linkend="repmgr-standby-switchover">repmgr standby switchover</link>)</simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect3>
+
+  </sect2>
 </sect1>

doc/event-notifications.xml

@@ -95,7 +95,8 @@
  </para>
 
  <para>
-   The following parameters are provided for a subset of event notifications:
+   The following parameters are provided for a subset of event notifications; their meaning may
+   change according to context:
  </para>
 
  <variablelist>
@@ -108,6 +109,9 @@
     <para>
      node ID of the demoted primary (<xref linkend="repmgr-standby-switchover"/> only)
     </para>
+    <para>
+     node ID of the former primary (<literal>repmgrd_failover_promote</literal> only)
+    </para>
    </listitem>
   </varlistentry>
   <varlistentry>
@@ -133,7 +137,7 @@
 
  <para>
   The values provided for <literal>%c</literal> and <literal>%a</literal>
-  will probably contain spaces, so should always be quoted.
+  may contain spaces, so should always be quoted.
  </para>
 
  <para>

doc/install-packages.xml

@@ -22,16 +22,15 @@
 
   <para>
 	&repmgr; RPM packages for RedHat/CentOS variants and Fedora are available from the
-	<ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
-	<ulink url="https://dl.2ndquadrant.com/">public repository</ulink>; see following
+	<ulink url="https://www.enterprisedb.com">EDB</ulink>
+	<ulink url="https://dl.enterprisedb.com/">public repository</ulink>; see following
 	section for details.
   </para>
   <note>
     <para>
-      Currently the <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
-	  <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> provides
-      support for RedHat/CentOS versions 5, 6 and 7. Support for version 8 is
-      available via the PGDG repository; see below for details.
+      Currently the <ulink url="https://www.enterprisedb.com">EDB</ulink>
+	  <ulink url="https://dl.enterprisedb.com/">public repository</ulink> provides
+      support for RedHat/CentOS versions 6,7 and 8.
     </para>
   </note>
   <para>
@@ -45,7 +44,7 @@
   <note>
     <para>
       &repmgr; RPM packages are designed to be compatible with the community-provided PostgreSQL packages
-      and 2ndQuadrant's <ulink url="https://www.2ndquadrant.com/en/resources/2ndqpostgres/">2ndQPostgres</ulink>.
+      and EDB's PostgreSQL Extended Server (formerly 2ndQPostgres).
       They may not work with vendor-specific packages such as those provided by RedHat for RHEL
       customers, as the PostgreSQL filesystem layout may be different to the community RPMs.
       Please contact your support vendor for assistance.
@@ -64,16 +63,16 @@
 
 
   <sect3 id="installation-packages-redhat-2ndq">
-    <title>2ndQuadrant public RPM yum repository</title>
+    <title>EDB public RPM yum repository</title>
 
     <para>
-      <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a dedicated <literal>yum</literal>
-      <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> for 2ndQuadrant software,
+      <ulink url="https://www.enterprisedb.com/">EDB</ulink> provides a dedicated <literal>yum</literal>
+      <ulink url="https://dl.enterprisedb.com/">public repository</ulink> for EDB 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://dl.2ndquadrant.com/">homepage</ulink>. Specific instructions
+      <ulink url="https://dl.enterprisedb.com/">homepage</ulink>. Specific instructions
       for installing &repmgr; follow below.
     </para>
     <para>
@@ -83,57 +82,46 @@
 	<listitem>
 	  <para>
 	    Locate the repository RPM for your PostgreSQL version from the list at:
-	    <ulink url="https://dl.2ndquadrant.com/">https://dl.2ndquadrant.com/</ulink>
+	    <ulink url="https://dl.enterprisedb.com/">https://dl.enterprisedb.com/</ulink>
 	  </para>
 	</listitem>
 
-        <listitem>
-          <para>
-            Install the repository definition for your distribution and PostgreSQL version
-	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages).
+    <listitem>
+      <para>
+        Install the repository definition for your distribution and PostgreSQL version
+	    (this enables the EDB repository as a source of &repmgr; packages).
 	  </para>
 	  <para>
-	    For example, for PostgreSQL 11 on CentOS, execute:
+	    For example, for PostgreSQL 14 on Rocky Linux 8, execute:
 	    <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/11/rpm | sudo bash</programlisting>
+curl https://dl.enterprisedb.com/default/release/get/14/rpm | sudo bash</programlisting>
 	  </para>
 
-	  <para>
-	    For PostgreSQL 9.6 on CentOS, execute:
-	    <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/9.6/rpm | sudo bash</programlisting>
-	  </para>
-
-
 	  <para>
 	    Verify that the repository is installed with:
 	    <programlisting>
-sudo yum repolist</programlisting>
+sudo dnf repolist</programlisting>
 	    The output should contain two entries like this:
 	    <programlisting>
-2ndquadrant-dl-default-release-pg11/7/x86_64         2ndQuadrant packages (PG11) for 7 - x86_64               18
-2ndquadrant-dl-default-release-pg11-debug/7/x86_64   2ndQuadrant packages (PG11) for 7 - x86_64 - Debug        8</programlisting>
+2ndquadrant-dl-default-release-pg14                  2ndQuadrant packages (PG14) for 8 - x86_64
+2ndquadrant-dl-default-release-pg14-debug            2ndQuadrant packages (PG14) for 8 - x86_64 - Debug</programlisting>
 	  </para>
 	</listitem>
 
         <listitem>
           <para>
-            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr14</literal>):
             <programlisting>
-sudo yum install repmgr11</programlisting>
+sudo dnf install repmgr14</programlisting>
           </para>
-          <note>
-            <para>
-              For packages for PostgreSQL 9.6 and earlier, the package name does not contain
-              a period between major and minor version numbers, e.g.
-              <literal>repmgr96</literal>.
-            </para>
-          </note>
           <tip>
             <para>
               To determine the names of available packages, execute:
               <programlisting>
-yum search repmgr</programlisting>
+dnf search repmgr</programlisting>
+            </para>
+            <para>
+              In CentOS 7 and earlier, use <literal>yum</literal> instead of <literal>dnf</literal>.
             </para>
           </tip>
 
@@ -145,7 +133,7 @@ yum search repmgr</programlisting>
       <emphasis>Compatibility with PGDG Repositories</emphasis>
     </para>
     <para>
-      The 2ndQuadrant &repmgr; yum repository packages use the same definitions and file system layout as the
+      The EDB &repmgr; yum repository packages use the same definitions and file system layout as the
       main PGDG repository.
     </para>
     <para>
@@ -154,36 +142,42 @@ yum search repmgr</programlisting>
       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.
+      To ensure the EDB repository is always prioritised, set the <literal>priority</literal> option
+      in the repository configuration file (e.g. <filename>/etc/yum.repos.d/2ndquadrant-dl-default-release-pg14.repo</filename>
+      accordingly.
     </para>
+    <note>
+      <para>
+        With CentOS 7 and earlier, the package <literal>yum-plugin-priorities</literal> must be installed
+        to be able to set the repository priority.
+      </para>
+    </note>
 
     <para>
       <emphasis>Installing a specific package version</emphasis>
     </para>
     <para>
-      To install a specific package version, execute <command>yum --showduplicates list</command>
+      To install a specific package version, execute <command>dnf --showduplicates list</command>
       for the package in question:
       <programlisting>
-[root@localhost ~]# yum --showduplicates list repmgr11
-Loaded plugins: fastestmirror
-Loading mirror speeds from cached hostfile
- * base: ftp.tsukuba.wide.ad.jp
- * epel: nrt.edge.kernel.org
- * extras: ftp.tsukuba.wide.ad.jp
- * updates: ftp.tsukuba.wide.ad.jp
+[root@localhost ~]# dnf --showduplicates list repmgr10
+Last metadata expiration check: 0:09:15 ago on Fri 11 Mar 2022 01:09:19 AM UTC.
 Installed Packages
-repmgr11.x86_64                        4.4.0-1.rhel7                         @pgdg11
+repmgr10.x86_64                            5.3.1-1.el8                              @2ndquadrant-dl-default-release-pg10
 Available Packages
-repmgr11.x86_64                        4.2-1.el7                             2ndquadrant-dl-default-release-pg11
-repmgr11.x86_64                        4.2-2.el7                             2ndquadrant-dl-default-release-pg11
-repmgr11.x86_64                        4.3-1.el7                             2ndquadrant-dl-default-release-pg11
-repmgr11.x86_64                        4.4-1.el7                             2ndquadrant-dl-default-release-pg11</programlisting>
+repmgr10.x86_64                            5.0.0-1.rhel8                            pgdg10
+repmgr10.x86_64                            5.1.0-1.el8                              2ndquadrant-dl-default-release-pg10
+repmgr10.x86_64                            5.1.0-1.rhel8                            pgdg10
+repmgr10.x86_64                            5.1.0-2.el8                              2ndquadrant-dl-default-release-pg10
+repmgr10.x86_64                            5.2.0-1.el8                              2ndquadrant-dl-default-release-pg10
+repmgr10.x86_64                            5.2.0-1.rhel8                            pgdg10
+repmgr10.x86_64                            5.2.1-1.el8                              2ndquadrant-dl-default-release-pg10
+repmgr10.x86_64                            5.3.0-1.el8                              2ndquadrant-dl-default-release-pg10
+repmgr10.x86_64                            5.3.1-1.el8                              2ndquadrant-dl-default-release-pg10</programlisting>
       then append the appropriate version number to the package name with a hyphen, e.g.:
       <programlisting>
-[root@localhost ~]# yum install repmgr11-4.3-1.el7</programlisting>
+[root@localhost ~]# dnf install repmgr10-5.3.0-1.el8</programlisting>
     </para>
-
     <para>
       <emphasis>Installing old packages</emphasis>
     </para>
@@ -191,7 +185,6 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
       See appendix <link linkend="packages-old-versions-rhel-centos">Installing old package versions</link>
       for details on how to retrieve older package versions.
     </para>
-
   </sect3>
 
  </sect2>
@@ -217,16 +210,16 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
   </para>
 
   <sect3 id="installation-packages-debian-ubuntu-2ndq">
-    <title>2ndQuadrant public apt repository for Debian/Ubuntu</title>
+    <title>EDB public apt repository for Debian/Ubuntu</title>
 
     <para>
-      <ulink url="https://2ndquadrant.com/">2ndQuadrant</ulink> provides a
-      <ulink url="https://dl.2ndquadrant.com/">public apt repository</ulink> for 2ndQuadrant software,
+      <ulink url="https://www.enterprisedb.com/">EDB</ulink> provides a
+      <ulink url="https://dl.enterprisedb.com/">public apt repository</ulink> for EDB software,
       including &repmgr;.
     </para>
     <para>
       General instructions for using this repository can be found on its
-      <ulink url="https://dl.2ndquadrant.com/">homepage</ulink>. Specific instructions
+      <ulink url="https://dl.enterprisedb.com/">homepage</ulink>. Specific instructions
       for installing &repmgr; follow below.
     </para>
 
@@ -239,9 +232,9 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
 	    <listitem>
 	      <para>
             Install the repository definition for your distribution and PostgreSQL version
-	        (this enables the 2ndQuadrant repository as a source of &repmgr; packages) by executing:
+	        (this enables the EDB repository as a source of &repmgr; packages) by executing:
             <programlisting>
-              curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlisting>
+              curl https://dl.enterprisedb.com/default/release/get/deb | sudo bash</programlisting>
 	      </para>
           <note>
             <para>

doc/install-requirements.xml

@@ -108,14 +108,16 @@
             <entry>
               Supported PostgreSQL versions
             </entry>
+            <entry>
+              Notes
+            </entry>
           </row>
         </thead>
 
         <tbody>
-
           <row>
             <entry>
-              &repmgr; 5.2
+              &repmgr; 5.3
             </entry>
             <entry>
               YES
@@ -123,9 +125,30 @@
             <entry>
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
+            <entry>
+              9.4, 9.5, 9.6, 10, 11, 12, 13, 14, 15
+            </entry>
+            <entry>
+              PostgreSQL 15 supported from &repmgr; 5.3.3
+            </entry>
+          </row>
+
+          <row>
+            <entry>
+              &repmgr; 5.2
+            </entry>
+            <entry>
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-5.2.1">5.2.1</link> (2020-12-07)
+            </entry>
             <entry>
               9.4, 9.5, 9.6, 10, 11, 12, 13
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -141,6 +164,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -156,6 +182,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
 
@@ -172,6 +201,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -187,6 +219,9 @@
             <entry>
               9.3, 9.4, 9.5, 9.6
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
 
           <row>
@@ -202,6 +237,9 @@
             <entry>
               9.0, 9.1, 9.2, 9.3, 9.4
             </entry>
+            <entry>
+              &nbsp;
+            </entry>
           </row>
         </tbody>
 

doc/legal.xml

@@ -1,18 +1,18 @@
 <!-- doc/legal.xml -->
 
-<date>2017</date>
+<date>2022</date>
 
 <copyright>
- <year>2010-2021</year>
- <holder>EnterpriseDB Corporation</holder>
+ <year>2010-2022</year>
+ <holder>EDB</holder>
 </copyright>
 
 <legalnotice id="legalnotice">
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2021
-  by EnterpriseDB Corporation All rights reserved.
+  <productname>repmgr</productname> is Copyright &copy; 2010-2022
+  by EDB All rights reserved.
  </para>
 
  <para>

doc/quickstart.xml

@@ -405,9 +405,10 @@
   </programlisting>
   <para>
    This has cloned the PostgreSQL data directory files from the primary <literal>node1</literal>
-   using PostgreSQL's <command>pg_basebackup</command> utility. A <filename>recovery.conf</filename>
-   file containing the correct parameters to start streaming from this primary server will be created
-   automatically.
+   using PostgreSQL's <command>pg_basebackup</command> utility. Replication configuration
+   containing the correct parameters to start streaming from this primary server will be
+   automatically appended to <filename>postgresql.auto.conf</filename>. (In PostgreSQL 11
+   and earlier the file <filename>recovery.conf</filename> will be created).
   </para>
   <note>
    <simpara>
@@ -481,9 +482,10 @@
     sender_port           | 5432
     conninfo              | user=repmgr dbname=replication host=node1 application_name=node2
    </programlisting>
-   Note that the <varname>conninfo</varname> value is that generated in <filename>recovery.conf</filename>
-   and will differ slightly from the primary's <varname>conninfo</varname> as set in <filename>repmgr.conf</filename> -
-   among others it will contain the connecting node's name as <varname>application_name</varname>.
+   Note that the <varname>conninfo</varname> value is that generated in <filename>postgresql.auto.conf</filename>
+   (PostgreSQL 11 and earlier: <filename>recovery.conf</filename>) and will differ slightly from the primary's
+   <varname>conninfo</varname> as set in <filename>repmgr.conf</filename> - among others it will contain the
+   connecting node's name as <varname>application_name</varname>.
   </para>
  </sect1>
 

doc/repmgr-node-check.xml

@@ -125,12 +125,29 @@
         is correctly configured.
       </simpara>
      </listitem>
-
-
     </itemizedlist>
   </para>
   </refsect1>
 
+
+  <refsect1>
+    <title>repmgrd</title>
+    <para>
+      A separate check is available to verify whether &repmgrd; is running,
+      This is not included in the general output, as this does not
+      per-se constitute a check of the node's replication status.
+    </para>
+    <itemizedlist spacing="compact" mark="bullet">
+     <listitem>
+      <simpara>
+        <option>--repmgrd</option>: checks whether &repmgrd; is running.
+        If &repmgrd; is running but paused, status <literal>1</literal>
+        (<literal>WARNING</literal>) is returned.
+      </simpara>
+     </listitem>
+    </itemizedlist>
+  </refsect1>
+
   <refsect1>
     <title>Additional checks</title>
     <para>

doc/repmgr-node-rejoin.xml

@@ -271,6 +271,10 @@
         data checksums were enabled when the cluster was initialized. See the
         <ulink url="https://www.postgresql.org/docs/current/app-pgrewind.html"><command>pg_rewind</command> documentation</ulink> for details.
       </para>
+      <para>
+        Additionally, <varname>full_page_writes</varname> must be enabled; this is the default and
+        normally should never be disabled.
+      </para>
     </note>
 
     <para>
@@ -426,7 +430,7 @@
 
    <warning>
      <para>
-       In all current PostgreSQL versions (as of September 2020), <application>pg_rewind</application>
+       In all PostgreSQL released before February 2021, <application>pg_rewind</application>
        contains a corner-case bug which affects standbys in a very specific situation.
      </para>
      <para>
@@ -456,8 +460,7 @@
      <para>
        Currently it is not possible to resolve this situation using <application>pg_rewind</application>.
        A <ulink url="https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=2b4f3130382fe2f8705863e4d38589d4d69cd695">patch</ulink>
-       has been successfully submitted and will be included the next PostgreSQL minor release round, scheduled for
-       February 2021.
+       was submitted and is included in all PostgreSQL versions released in February 2021 or later.
      </para>
      <para>
        As a workaround, start the primary server the standby was previously attached to,

doc/repmgr-standby-clone.xml

@@ -332,6 +332,12 @@ pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
             node to the same path on the standby (default) or to the
             PostgreSQL data directory.
           </para>
+          <para>
+            Note that to be able to use this option, the &repmgr; user must be a superuser or
+            member of the <literal>pg_read_all_settings</literal> predefined role.
+            If this is not the case, provide a valid superuser with the
+            <option>-S</option>/<option>--superuser</option> option.
+          </para>
         </listitem>
       </varlistentry>
 
@@ -399,11 +405,15 @@ pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
       </varlistentry>
 
       <varlistentry>
-        <term><option>--superuser</option></term>
+        <term><option>-S</option>/<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.
+            The name of a valid PostgreSQL superuser can  be provided with this option.
+          </para>
+          <para>
+            This is only required if the <option>--copy-external-config-files</option> was provided
+            and the &repmgr; user is not a superuser or member of the <literal>pg_read_all_settings</literal>
+            predefined role.
           </para>
         </listitem>
       </varlistentry>

doc/repmgr-standby-switchover.xml

@@ -64,6 +64,13 @@
 
   <refsect1>
     <title>User permission requirements</title>
+    <para><emphasis>data_directory</emphasis></para>
+    <para>
+      &repmgr; needs to be able to determine the location of the data directory on the
+      demotion candidate. If the &repmgr; is not a superuser or member of the <varname>pg_read_all_settings</varname>
+      <ulink url="https://www.postgresql.org/docs/current/predefined-roles.html">predefined roles</ulink>,
+      the name of a superuser should be provided with the <option>-S</option>/<option>--superuser</option> option.
+    </para>
     <para><emphasis>CHECKPOINT</emphasis></para>
     <para>
       &repmgr; executes <command>CHECKPOINT</command> on the demotion candidate as part of the shutdown
@@ -72,7 +79,7 @@
     <para>
       Note that <command>CHECKPOINT</command> requires database superuser permissions to execute.
       If the <literal>repmgr</literal> user is not a superuser, the name of a superuser should be
-      provided with the <option>-S</option>/<option>--superuser</option>.
+      provided with the <option>-S</option>/<option>--superuser</option> option.
     </para>
     <para>
       If &repmgr; is unable to execute the <command>CHECKPOINT</command> command, the switchover

doc/repmgr.xml

@@ -18,7 +18,7 @@
  <title>repmgr &repmgrversion; Documentation</title>
 
  <bookinfo>
-  <corpauthor>EnterpriseDB Corporation</corpauthor>
+  <corpauthor>EDB</corpauthor>
   <productname>repmgr</productname>
   <productnumber>&repmgrversion;</productnumber>
   &legal;
@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.4 - PostgreSQL 13.
+   use with PostgreSQL 9.4 - PostgreSQL 15.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -38,19 +38,18 @@
 
    <para>
     &repmgr; is developed by
-    <ulink url="https://2ndquadrant.com">2ndQuadrant (EDB)</ulink>
+    <ulink url="https://www.enterprisedb.com/">EDB</ulink>
     along with contributions from other individuals and organisations.
     Contributions from the community are appreciated and welcome - get
     in touch via <ulink url="https://github.com/EnterpriseDB/repmgr">github</ulink>
     or <ulink url="https://groups.google.com/group/repmgr">the mailing list/forum</ulink>.
-    Multiple 2ndQuadrant (EDB) customers contribute funding
-    to make repmgr development possible.
+    Multiple EDB customers contribute funding to make &repmgr; development possible.
    </para>
 
    <para>
-     &repmgr; is fully supported by 2ndQuadrant (EDB)'s
-     <ulink url="https://www.2ndquadrant.com/en/support/support-postgresql/">24/7 Production Support</ulink>.
-     EnterpriseDB Corporation, a Major Sponsor of the PostgreSQL project, continues to maintain &repmgr;.
+     &repmgr; is fully supported by EDB's
+     <ulink url="https://www.enterprisedb.com/support/postgresql-support-overview-get-the-most-out-of-postgresql">24/7 Production Support</ulink>.
+     EDB, a Major Sponsor of the PostgreSQL project, continues to maintain &repmgr;.
      We welcome participation from other organisations and individual developers.
    </para>
   </abstract>

doc/repmgrd-automatic-failover.xml

@@ -81,11 +81,15 @@
  </para>
  <note>
    <simpara>
-     &repmgr; 3.3 and earlier provided a <command>repmgr create witness</command>
-     command, which would automatically create a PostgreSQL instance. However
-     this often resulted in an unsatisfactory, hard-to-customise instance.
+     A PostgreSQL instance can only accommodate a single witness server.
+   </simpara>
+   <simpara>
+     If you are planning to use a single server to support more than one
+     witness server, a separate PostgreSQL instance is required for each
+     witness server in use.
    </simpara>
  </note>
+
  <para>
    The witness server should be configured in the same way as a normal
    &repmgr; node; see section <xref linkend="configuration"/>.

doc/repmgrd-configuration.xml

@@ -345,14 +345,18 @@
             </indexterm>
 
             <para>
-              Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes;
-			  a value of zero prevents the node being promoted to primary.
+              Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes.
             </para>
             <para>
               Note that the priority setting is only applied if two or more nodes are
               determined as promotion candidates; in that case the node with the
               higher priority is selected.
             </para>
+            <para>
+              A value of zero will always prevent the node being promoted to primary, even if there
+              is no other promotion candidate.
+            </para>
+
           </listitem>
         </varlistentry>
 
@@ -485,6 +489,32 @@
           </listitem>
         </varlistentry>
 
+        <varlistentry>
+
+          <term><option>repmgrd_exit_on_inactive_node</option></term>
+          <listitem>
+            <indexterm>
+              <primary>repmgrd_exit_on_inactive_node</primary>
+            </indexterm>
+            <para>
+              This parameter is available in &repmgr; 5.3 and later.
+            </para>
+            <para>
+              If a node was marked as inactive but is running, and this option is set to
+              <literal>true</literal>, &repmgrd; will abort on startup.
+            </para>
+            <para>
+              By default, <option>repmgrd_exit_on_inactive_node</option> is set
+              to <literal>false</literal>, in which case &repmgrd; will set the
+              node record to active on startup.
+            </para>
+            <para>
+              Setting this parameter to <literal>true</literal> causes &repmgrd;
+              to behave in the same way it did in &repmgr; 5.2 and earlier.
+            </para>
+          </listitem>
+        </varlistentry>
+
       </variablelist>
 
       <para>
@@ -1053,6 +1083,29 @@ REPMGRD_OPTS="--daemonize=false"
       </para>
 
     </sect2>
+
+    <sect2 id="repmgrd-daemon-monitoring">
+      <title>repmgrd daemon monitoring</title>
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>monitoring</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>monitoring</primary>
+        <secondary>repmgrd</secondary>
+      </indexterm>
+
+      <para>
+        The command <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+        provides an overview of the &repmgrd; daemon status (including pause status)
+        on all nodes in the cluster.
+      </para>
+      <para>
+        From &repmgr; 5.3, <command><link linkend="repmgr-node-check">repmgr node check --repmgrd</link></command>
+        can be used to check the status of &repmgrd; (including pause status)
+        on the local node.
+      </para>
+    </sect2>
   </sect1>
 
   <sect1 id="repmgrd-connection-settings">

doc/upgrading-repmgr.xml

@@ -71,6 +71,12 @@
 	  <secondary>minor release</secondary>
 	</indexterm>
 
+    <para>
+	  A minor release upgrade involves updating &repmgr; from one minor release to another
+	  minor release within the same major release (e.g. <literal>5.3.1</literal> to <literal>5.3.2</literal>).
+	  An upgrade between minor releases of differing major releases (e.g. <literal>5.2.1</literal> to <literal>5.3.2</literal>)
+	  is a <link linkend="upgrading-major-version">major upgrade</link>.
+    </para>
     <para>
       The process for installing minor version upgrades is quite straightforward:
 
@@ -105,15 +111,17 @@
 	</para>
 
 	<para>
-	  A PostgreSQL restart is <emphasis>not</emphasis> required for minor version upgrades.
+	  A PostgreSQL restart is usually <emphasis>not</emphasis> required for minor version upgrades
+	  within the same major version (e.g. <literal>5.3.1</literal> to <literal>5.3.2</literal>).
+	  Be sure to check the <link linkend="appendix-release-notes">release notes</link>.
 	</para>
 
     <note>
 	  <para>
-	    The same &repmgr; &quot;major version&quot; (e.g. <literal>4.2</literal>) must be
-	    installed on all nodes in the replication cluster. While it's possible to have differing
-	    &repmgr; &quot;minor versions&quot; (e.g. <literal>4.2.1</literal>)  on different nodes,
-	    we strongly recommend updating all nodes to the latest minor version.
+		The same &repmgr; &quot;major version&quot; (e.g. <literal>5.3</literal>) must be
+		installed on all nodes in the replication cluster. While it's possible to have differing
+		&repmgr; &quot;minor versions&quot; (e.g. <literal>5.3.1</literal> and <literal>5.3.2</literal>)
+		on different nodes, we strongly recommend updating all nodes to the latest minor version.
 	  </para>
     </note>
 

repmgr--4.2--4.3.sql

@@ -1,17 +1,10 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+\echo Use "ALTER EXTENSION repmgr UPDATE" to load this file. \quit
 
-CREATE FUNCTION set_upstream_last_seen()
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
-  LANGUAGE C STRICT;
+-- This script is intentionally empty and exists to skip the CREATE FUNCTION
+-- commands contained in the 4.2--4.3 and 4.3--4.4 extension upgrade scripts,
+-- which reference C functions which no longer exist in 5.3 and later.
+--
+-- These functions will be explicitly created in the 5.2--5.3 extension
+-- upgrade step with the correct C function references.
 
-CREATE FUNCTION get_upstream_last_seen()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_wal_receiver_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_wal_receiver_pid'
-  LANGUAGE C STRICT;

repmgr--4.3--4.4.sql

@@ -1,19 +1,9 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+\echo Use "ALTER EXTENSION repmgr UPDATE" to load this file. \quit
 
-DROP FUNCTION set_upstream_last_seen();
-
-CREATE FUNCTION set_upstream_last_seen(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_upstream_node_id()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_upstream_node_id(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
-  LANGUAGE C STRICT;
+-- This script is intentionally empty and exists to skip the CREATE FUNCTION
+-- commands contained in the 4.3--4.4 extension upgrade script, which reference
+-- C functions which no longer exist in 5.3 and later.
+--
+-- These functions will be explicitly created in the 5.2--5.3 extension
+-- upgrade step with the correct C function references.

repmgr--5.2--5.3.sql

@@ -0,0 +1,64 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+CREATE OR REPLACE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION repmgr.get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION get_upstream_last_seen()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_node_id'
+  LANGUAGE C STRICT;
+
+/* failover functions */
+
+CREATE OR REPLACE FUNCTION notify_follow_primary(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_notify_follow_primary'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION get_new_primary()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_new_primary'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION reset_voting_status()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_reset_voting_status'
+  LANGUAGE C STRICT;
+
+CREATE OR REPLACE FUNCTION get_wal_receiver_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_wal_receiver_pid'
+  LANGUAGE C STRICT;

repmgr--5.3.sql

@@ -0,0 +1,192 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+CREATE TABLE repmgr.nodes (
+  node_id          INTEGER     PRIMARY KEY,
+  upstream_node_id INTEGER     NULL REFERENCES nodes (node_id) DEFERRABLE,
+  active           BOOLEAN     NOT NULL DEFAULT TRUE,
+  node_name        TEXT        NOT NULL,
+  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
+  location         TEXT        NOT NULL DEFAULT 'default',
+  priority         INT         NOT NULL DEFAULT 100,
+  conninfo         TEXT        NOT NULL,
+  repluser         VARCHAR(63) NOT NULL,
+  slot_name        TEXT        NULL,
+  config_file      TEXT        NOT NULL
+);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.nodes', '');
+
+CREATE TABLE repmgr.events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.events', '');
+
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+);
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.monitoring_history', '');
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+
+/* ================= */
+/* repmgrd functions */
+/* ================= */
+
+/* monitoring functions */
+
+CREATE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_last_seen()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_node_id'
+  LANGUAGE C STRICT;
+
+/* failover functions */
+
+CREATE FUNCTION notify_follow_primary(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_notify_follow_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_new_primary()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_new_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION reset_voting_status()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_reset_voting_status'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pidfile()
+  RETURNS TEXT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
+  LANGUAGE C CALLED ON NULL INPUT;
+
+CREATE FUNCTION repmgrd_is_running()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_running'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_pause(BOOL)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgrd_pause'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_is_paused()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_wal_receiver_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_wal_receiver_pid'
+  LANGUAGE C STRICT;
+
+
+
+
+/* views */
+
+CREATE VIEW repmgr.replication_status AS
+  SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
+ 	     n.type AS node_type, n.active, last_monitor_time,
+         CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
+         m.last_wal_standby_location,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
+         CASE WHEN n.type='standby' THEN
+           CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
+           ELSE NULL
+         END AS replication_time_lag,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
+         AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
+    FROM repmgr.monitoring_history m
+    JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
+   WHERE (m.standby_node_id, m.last_monitor_time) IN (
+	          SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
+			    FROM repmgr.monitoring_history m1 GROUP BY 1
+         );
+

repmgr--unpackaged--5.3.sql

@@ -0,0 +1,245 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+-- extract the current schema name
+-- NOTE: this assumes there will be only one schema matching 'repmgr_%';
+-- user is responsible for ensuring this is the case
+
+CREATE TEMPORARY TABLE repmgr_old_schema (schema_name TEXT);
+INSERT INTO repmgr_old_schema (schema_name)
+SELECT nspname AS schema_name
+  FROM pg_catalog.pg_namespace
+ WHERE nspname LIKE 'repmgr_%'
+ LIMIT 1;
+
+-- move old objects into new schema
+DO $repmgr$
+DECLARE
+  old_schema TEXT;
+BEGIN
+  SELECT schema_name FROM repmgr_old_schema
+    INTO old_schema;
+  EXECUTE format('ALTER TABLE %I.repl_nodes SET SCHEMA repmgr', old_schema);
+  EXECUTE format('ALTER TABLE %I.repl_events SET SCHEMA repmgr', old_schema);
+  EXECUTE format('ALTER TABLE %I.repl_monitor SET SCHEMA repmgr', old_schema);
+  EXECUTE format('DROP VIEW IF EXISTS %I.repl_show_nodes', old_schema);
+  EXECUTE format('DROP VIEW IF EXISTS %I.repl_status', old_schema);
+END$repmgr$;
+
+-- convert "repmgr_$cluster.repl_nodes" to "repmgr.nodes"
+CREATE TABLE repmgr.nodes (
+  node_id          INTEGER     PRIMARY KEY,
+  upstream_node_id INTEGER     NULL REFERENCES repmgr.nodes (node_id) DEFERRABLE,
+  active           BOOLEAN     NOT NULL DEFAULT TRUE,
+  node_name        TEXT        NOT NULL,
+  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
+  location         TEXT        NOT NULL DEFAULT 'default',
+  priority         INT         NOT NULL DEFAULT 100,
+  conninfo         TEXT        NOT NULL,
+  repluser         VARCHAR(63) NOT NULL,
+  slot_name        TEXT        NULL,
+  config_file      TEXT        NOT NULL
+);
+
+INSERT INTO repmgr.nodes
+  (node_id, upstream_node_id, active, node_name, type, location, priority, conninfo, repluser, slot_name, config_file)
+SELECT id, upstream_node_id, active, name,
+       CASE WHEN type = 'master' THEN 'primary' ELSE type END,
+       'default', priority, conninfo, 'unknown', slot_name, 'unknown'
+  FROM repmgr.repl_nodes
+ ORDER BY id;
+
+
+-- convert "repmgr_$cluster.repl_event" to "event"
+
+CREATE TABLE repmgr.events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
+INSERT INTO repmgr.events
+  (node_id, event, successful, event_timestamp, details)
+  SELECT node_id, event, successful, event_timestamp, details
+    FROM repmgr.repl_events;
+
+-- create new table "repmgr.voting_term"
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+INSERT INTO repmgr.voting_term (term) VALUES (1);
+
+-- convert "repmgr_$cluster.repl_monitor" to "monitoring_history"
+
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+);
+
+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;
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+
+/* ================= */
+/* repmgrd functions */
+/* ================= */
+
+/* monitoring functions */
+
+CREATE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'repmgr_standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_last_seen()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_set_upstream_node_id'
+  LANGUAGE C STRICT;
+
+/* failover functions */
+
+CREATE FUNCTION notify_follow_primary(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_notify_follow_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_new_primary()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_new_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION reset_voting_status()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgr_reset_voting_status'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pidfile()
+  RETURNS TEXT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
+  LANGUAGE C CALLED ON NULL INPUT;
+
+CREATE FUNCTION repmgrd_is_running()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_running'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_pause(BOOL)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'repmgrd_pause'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgrd_is_paused()
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_wal_receiver_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'repmgr_get_wal_receiver_pid'
+  LANGUAGE C STRICT;
+
+
+/* views */
+
+CREATE VIEW repmgr.replication_status AS
+  SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
+ 	     n.type AS node_type, n.active, last_monitor_time,
+         CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
+         m.last_wal_standby_location,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
+         CASE WHEN n.type='standby' THEN
+           CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
+           ELSE NULL
+         END AS replication_time_lag,
+         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
+         AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
+    FROM repmgr.monitoring_history m
+    JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
+   WHERE (m.standby_node_id, m.last_monitor_time) IN (
+	          SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
+			    FROM repmgr.monitoring_history m1 GROUP BY 1
+         );
+
+
+
+/* drop old tables */
+DROP TABLE repmgr.repl_nodes;
+DROP TABLE repmgr.repl_monitor;
+DROP TABLE repmgr.repl_events;
+
+-- remove temporary table
+DROP TABLE repmgr_old_schema;

repmgr-action-node.c

@@ -35,6 +35,7 @@
 static bool copy_file(const char *src_file, const char *dest_file);
 static void format_archive_dir(PQExpBufferData *archive_dir);
 static t_server_action parse_server_action(const char *action);
+static const char *output_repmgrd_status(CheckStatus status);
 
 static void exit_optformat_error(const char *error, int errcode);
 
@@ -52,9 +53,11 @@ static CheckStatus do_node_check_role(PGconn *conn, OutputMode mode, t_node_info
 static CheckStatus do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
+static CheckStatus do_node_check_repmgrd(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_db_connection(PGconn *conn, OutputMode mode);
 
+
 /*
  * NODE STATUS
  *
@@ -941,6 +944,16 @@ do_node_check(void)
 		exit(return_code);
 	}
 
+	if (runtime_options.repmgrd == true)
+	{
+		return_code = do_node_check_repmgrd(conn,
+											runtime_options.output_mode,
+											&node_info,
+											NULL);
+		PQfinish(conn);
+		exit(return_code);
+	}
+
 	if (runtime_options.replication_config_owner == true)
 	{
 		return_code = do_node_check_replication_config_owner(conn,
@@ -1314,7 +1327,7 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info,
 			continue;
 		}
 
-		if (is_downstream_node_attached(conn, cell->node_info->node_name, NULL) != NODE_ATTACHED)
+		if (is_downstream_node_attached_quiet(conn, cell->node_info->node_name, NULL) != NODE_ATTACHED)
 		{
 			missing_nodes_count++;
 			item_list_append_format(&missing_nodes,
@@ -1382,49 +1395,32 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info,
 	{
 		case OM_NAGIOS:
 			{
-				printf("REPMGR_DOWNSTREAM_SERVERS %s: %s | ",
-					   output_check_status(status),
-					   details.data);
-
 				if (missing_nodes_count)
 				{
 					ItemListCell *missing_cell = NULL;
 					bool		first = true;
 
-					printf("missing: ");
+					appendPQExpBufferStr(&details, " (missing: ");
+
 					for (missing_cell = missing_nodes.head; missing_cell; missing_cell = missing_cell->next)
 					{
 						if (first == false)
-							printf(", ");
+							appendPQExpBufferStr(&details, ", ");
 						else
 							first = false;
 
 						if (first == false)
-							printf("%s", missing_cell->string);
+							appendPQExpBufferStr(&details, missing_cell->string);
 					}
+
+					appendPQExpBufferChar(&details, ')');
 				}
 
-				if (expected_nodes_count - missing_nodes_count)
-				{
-					ItemListCell *attached_cell = NULL;
-					bool		first = true;
-
-					if (missing_nodes_count)
-						printf("; ");
-					printf("attached: ");
-					for (attached_cell = attached_nodes.head; attached_cell; attached_cell = attached_cell->next)
-					{
-						if (first == false)
-							printf(", ");
-						else
-							first = false;
-
-						if (first == false)
-							printf("%s", attached_cell->string);
-					}
-				}
-				printf("\n");
-
+				printf("REPMGR_DOWNSTREAM_SERVERS %s: %s | attached=%i, missing=%i\n",
+					   output_check_status(status),
+					   details.data,
+					   expected_nodes_count - missing_nodes_count,
+					   missing_nodes_count);
 			}
 			break;
 		case OM_CSV:
@@ -1522,7 +1518,7 @@ do_node_check_upstream(PGconn *conn, OutputMode mode, t_node_info *node_info, Ch
 	{
 		case OM_NAGIOS:
 			{
-				printf("REPMGR_UPSTREAM_SERVER %s: %s | ",
+				printf("REPMGR_UPSTREAM_SERVER %s: %s\n",
 					   output_check_status(status),
 					   details.data);
 			}
@@ -2024,7 +2020,6 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 	return status;
 }
 
-
 CheckStatus
 do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
 {
@@ -2159,6 +2154,53 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	return status;
 }
 
+CheckStatus
+do_node_check_repmgrd(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
+{
+	CheckStatus status = CHECK_STATUS_OK;
+
+	if (mode == OM_CSV && list_output == NULL)
+	{
+		log_error(_("--csv output not provided with --repmgrd option"));
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	status = get_repmgrd_status(conn);
+	switch (mode)
+	{
+		case OM_OPTFORMAT:
+			printf("--repmgrd=%s\n",
+				   output_check_status(status));
+			break;
+		case OM_NAGIOS:
+			printf("REPMGRD %s: %s\n",
+				   output_check_status(status),
+				   output_repmgrd_status(status));
+
+			break;
+		case OM_CSV:
+		case OM_TEXT:
+			if (list_output != NULL)
+			{
+				check_status_list_set(list_output,
+									  "repmgrd",
+									  status,
+									  output_repmgrd_status(status));
+			}
+			else
+			{
+				printf("%s (%s)\n",
+					   output_check_status(status),
+					   output_repmgrd_status(status));
+			}
+		default:
+			break;
+	}
+
+	return status;
+}
+
 /*
  * This is not included in the general list output
  */
@@ -2820,7 +2862,8 @@ do_node_rejoin(void)
 				log_notice(_("temporarily removing \"standby.signal\""));
 				log_detail(_("this is required so pg_rewind can fix the unclean shutdown"));
 
-				make_standby_signal_path(standby_signal_file_path);
+				make_standby_signal_path(config_file_options.data_directory,
+										 standby_signal_file_path);
 
 				if (unlink(standby_signal_file_path) < 0 && errno != ENOENT)
 				{
@@ -2845,7 +2888,7 @@ do_node_rejoin(void)
 				 * of whether the pg_rewind operation failed.
 				 */
 				log_notice(_("recreating \"standby.signal\""));
-				write_standby_signal();
+				write_standby_signal(config_file_options.data_directory);
 			}
 
 			if (ret == false)
@@ -3569,6 +3612,25 @@ copy_file(const char *src_file, const char *dest_file)
 }
 
 
+static const char *
+output_repmgrd_status(CheckStatus status)
+{
+	switch (status)
+	{
+		case CHECK_STATUS_OK:
+			return "repmgrd running";
+		case CHECK_STATUS_WARNING:
+			return "repmgrd running but paused";
+		case CHECK_STATUS_CRITICAL:
+			return "repmgrd not running";
+		case CHECK_STATUS_UNKNOWN:
+			return "repmgrd status unknown";
+	}
+
+	return "UNKNOWN";
+}
+
+
 void
 do_node_help(void)
 {
@@ -3611,6 +3673,7 @@ do_node_help(void)
 	printf(_("    --role                    check node has expected role\n"));
 	printf(_("    --slots                   check for inactive replication slots\n"));
 	printf(_("    --missing-slots           check for missing replication slots\n"));
+	printf(_("    --repmgrd                 check if repmgrd is running\n"));
 	printf(_("    --data-directory-config   check repmgr's data directory configuration\n"));
 
 	puts("");

repmgr-action-standby.c

@@ -20,6 +20,7 @@
  */
 
 #include <sys/stat.h>
+#include <time.h>
 
 #include "repmgr.h"
 #include "dirutil.h"
@@ -94,6 +95,8 @@ static char barman_command_buf[MAXLEN] = "";
  * be run and which of the available users, which will be one
  * of the repmgr user, the replication user (if available) or
  * the superuser (if available).
+ *
+ * This is determined in check_source_server().
  */
 static t_user_type SettingsUser = REPMGR_USER;
 
@@ -173,21 +176,6 @@ do_standby_clone(void)
 
 	initialize_conninfo_params(&recovery_conninfo, false);
 
-	/*
-	 * --replication-conf-only provided - we'll handle that separately
-	 */
-	if (runtime_options.replication_conf_only == true)
-	{
-		return _do_create_replication_conf();
-	}
-
-	/*
-	 * conninfo params for the actual upstream node (which might be different
-	 * to the node we're cloning from) to write to recovery.conf
-	 */
-
-	mode = get_standby_clone_mode();
-
 	/*
 	 * Copy the provided data directory; if a configuration file was provided,
 	 * use the (mandatory) value from that; if -D/--pgdata was provided, use
@@ -215,6 +203,19 @@ do_standby_clone(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	/*
+	 * --replication-conf-only provided - we'll handle that separately
+	 */
+	if (runtime_options.replication_conf_only == true)
+	{
+		return _do_create_replication_conf();
+	}
+
+	/*
+	 * conninfo params for the actual upstream node (which might be different
+	 * to the node we're cloning from) to write to recovery.conf
+	 */
+	mode = get_standby_clone_mode();
 
 	if (mode == barman)
 	{
@@ -670,6 +671,15 @@ do_standby_clone(void)
 			log_hint(_("consider using the -c/--fast-checkpoint option"));
 		}
 
+		if (mode == pg_basebackup)
+		{
+			/*
+			 * In --dry-run mode, this will just output the pg_basebackup command which
+			 * would be executed.
+			 */
+			run_basebackup(&local_node_record);
+		}
+
 		PQfinish(source_conn);
 
 		log_info(_("all prerequisites for \"standby clone\" are met"));
@@ -1538,7 +1548,7 @@ _do_create_replication_conf(void)
 		}
 		else
 		{
-			if (write_standby_signal() == false)
+			if (write_standby_signal(local_data_directory) == false)
 			{
 				log_error(_("unable to write \"standby.signal\" file"));
 			}
@@ -1999,7 +2009,7 @@ do_standby_register(void)
 		/* only do this if record does not exist */
 		if (record_status != RECORD_FOUND)
 		{
-			log_warning(_("--upstream-node-id not supplied, assuming upstream node is primary (node ID %i)"),
+			log_warning(_("--upstream-node-id not supplied, assuming upstream node is primary (node ID: %i)"),
 						primary_node_id);
 
 			/* check our standby is connected */
@@ -3338,10 +3348,9 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 			update_node_record_slot_name(primary_conn, config_file_options.node_id, local_node_record.slot_name);
 		}
 
-
 		if (create_replication_slot(follow_target_conn,
 									local_node_record.slot_name,
-									NULL,
+									follow_target_node_record,
 									output) == false)
 		{
 			log_error("%s", output->data);
@@ -3644,8 +3653,9 @@ do_standby_switchover(void)
 	PQExpBufferData remote_command_str;
 	PQExpBufferData command_output;
 	PQExpBufferData node_rejoin_options;
-	PQExpBufferData errmsg;
+	PQExpBufferData logmsg;
 	PQExpBufferData detailmsg;
+	PQExpBufferData event_details;
 
 	int			r,
 				i;
@@ -3662,6 +3672,9 @@ do_standby_switchover(void)
 	/* store list of configuration files on the demotion candidate */
 	KeyValueList remote_config_files = {NULL, NULL};
 
+	/* temporary log file for "repmgr node rejoin" on the demotion candidate */
+	char		node_rejoin_log[MAXPGPATH] = "";
+
 	NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 	SiblingNodeStats sibling_nodes_stats = T_SIBLING_NODES_STATS_INITIALIZER;
 
@@ -3804,24 +3817,24 @@ do_standby_switchover(void)
 	 * the demotion candidate as the rejoin will fail if we are unable to to write to that.
 	 */
 
-	initPQExpBuffer(&errmsg);
+	initPQExpBuffer(&logmsg);
 	initPQExpBuffer(&detailmsg);
 
 	if (check_replication_config_owner(PQserverVersion(local_conn),
 									   config_file_options.data_directory,
-									   &errmsg, &detailmsg) == false)
+									   &logmsg, &detailmsg) == false)
 	{
-		log_error("%s", errmsg.data);
+		log_error("%s", logmsg.data);
 		log_detail("%s", detailmsg.data);
 
-		termPQExpBuffer(&errmsg);
+		termPQExpBuffer(&logmsg);
 		termPQExpBuffer(&detailmsg);
 
 		PQfinish(local_conn);
 		exit(ERR_BAD_CONFIG);
 	}
 
-	termPQExpBuffer(&errmsg);
+	termPQExpBuffer(&logmsg);
 	termPQExpBuffer(&detailmsg);
 
 	/* check remote server connection and retrieve its record */
@@ -4769,6 +4782,7 @@ do_standby_switchover(void)
 
 		repmgrd_info = (RepmgrdInfo **) pg_malloc0(sizeof(RepmgrdInfo *) * all_nodes.node_count);
 
+		log_notice(_("attempting to pause repmgrd on %i nodes"), all_nodes.node_count);
 		for (cell = all_nodes.head; cell; cell = cell->next)
 		{
 			repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
@@ -4797,7 +4811,7 @@ do_standby_switchover(void)
 					unreachable_node_count++;
 
 					item_list_append_format(&repmgrd_connection_errors,
-											_("unable to connect to node \"%s\" (ID %i):\n%s"),
+											_("unable to connect to node \"%s\" (ID: %i):\n%s"),
 											cell->node_info->node_name,
 											cell->node_info->node_id,
 											PQerrorMessage(cell->node_info->conn));
@@ -4828,8 +4842,9 @@ do_standby_switchover(void)
 
 			initPQExpBuffer(&msg);
 			appendPQExpBuffer(&msg,
-							  _("unable to connect to %i node(s), unable to pause all repmgrd instances"),
-							  unreachable_node_count);
+							  _("unable to connect to %i of %i node(s), unable to pause all repmgrd instances"),
+							  unreachable_node_count,
+							  all_nodes.node_count);
 
 			initPQExpBuffer(&detail);
 
@@ -4880,7 +4895,7 @@ do_standby_switchover(void)
 				 */
 				if (repmgrd_info[i]->pg_running == false)
 				{
-					log_warning(_("node \"%s\" (ID %i) unreachable, unable to pause repmgrd"),
+					log_warning(_("node \"%s\" (ID: %i) unreachable, unable to pause repmgrd"),
 								cell->node_info->node_name,
 								cell->node_info->node_id);
 					i++;
@@ -4893,7 +4908,7 @@ do_standby_switchover(void)
 				 */
 				if (repmgrd_info[i]->running == false)
 				{
-					log_warning(_("repmgrd not running on node \"%s\" (ID %i)"),
+					log_notice(_("repmgrd not running on node \"%s\" (ID: %i), not pausing"),
 								cell->node_info->node_name,
 								cell->node_info->node_id);
 					i++;
@@ -4914,14 +4929,14 @@ do_standby_switchover(void)
 
 				if (runtime_options.dry_run == true)
 				{
-					log_info(_("would pause repmgrd on node \"%s\" (ID %i)"),
+					log_info(_("would pause repmgrd on node \"%s\" (ID: %i)"),
 							 cell->node_info->node_name,
 							 cell->node_info->node_id);
 				}
 				else
 				{
 					/* XXX check result  */
-					log_debug("pausing repmgrd on node \"%s\" (ID %i)",
+					log_debug("pausing repmgrd on node \"%s\" (ID: %i)",
 							 cell->node_info->node_name,
 							 cell->node_info->node_id);
 
@@ -5221,6 +5236,18 @@ do_standby_switchover(void)
 			  format_lsn(replication_info.last_wal_receive_lsn),
 			  format_lsn(remote_last_checkpoint_lsn));
 
+	/*
+	 * optionally add a delay before promoting the standby; this is mainly
+	 * useful for testing (e.g. for reappearance of the original primary) and
+	 * is not documented.
+	 */
+	if (config_file_options.promote_delay > 0)
+	{
+		log_debug("sleeping %i seconds before promoting standby",
+				  config_file_options.promote_delay);
+		sleep(config_file_options.promote_delay);
+	}
+
 	/*
 	 * Promote standby (local node).
 	 *
@@ -5346,6 +5373,21 @@ do_standby_switchover(void)
 		pfree(conninfo_normalized);
 	}
 
+	/* */
+	snprintf(node_rejoin_log, MAXPGPATH,
+#if defined(__i386__) || defined(__i386)
+			 "/tmp/node-rejoin.%u.log",
+			 (unsigned)time(NULL)
+#else
+			 "/tmp/node-rejoin.%lu.log",
+			 (unsigned long)time(NULL)
+#endif
+		);
+
+	appendPQExpBuffer(&remote_command_str,
+					  " > %s 2>&1 && echo \"1\" || echo \"0\"",
+					  node_rejoin_log);
+
 	termPQExpBuffer(&node_rejoin_options);
 
 	log_debug("executing:\n  %s", remote_command_str.data);
@@ -5359,78 +5401,161 @@ do_standby_switchover(void)
 
 	termPQExpBuffer(&remote_command_str);
 
-	/* TODO: verify this node's record was updated correctly */
+	initPQExpBuffer(&logmsg);
+	initPQExpBuffer(&detailmsg);
 
+	/* This is failure to execute the ssh command */
 	if (command_success == false)
 	{
 		log_error(_("rejoin failed with error code %i"), r);
+		switchover_success = false;
+
+		appendPQExpBuffer(&logmsg,
+						  _("unable to execute \"repmgr node rejoin\" on demotion candidate \"%s\" (ID: %i)"),
+						  remote_node_record.node_name,
+						  remote_node_record.node_id);
+		appendPQExpBufferStr(&detailmsg,
+							 command_output.data);
 
-		create_event_notification_extended(local_conn,
-										   &config_file_options,
-										   config_file_options.node_id,
-										   "standby_switchover",
-										   false,
-										   command_output.data,
-										   &event_info);
 	}
 	else
 	{
-		PQExpBufferData event_details;
-		standy_join_status join_success = check_standby_join(local_conn,
-															 &local_node_record,
-															 &remote_node_record);
+		standy_join_status join_success = JOIN_UNKNOWN;
 
-		initPQExpBuffer(&event_details);
-
-		switch (join_success) {
-			case JOIN_FAIL_NO_PING:
-				appendPQExpBuffer(&event_details,
-								  _("node \"%s\" (ID: %i) promoted to primary, but demote node \"%s\" (ID: %i) did not beome available"),
-								  config_file_options.node_name,
-								  config_file_options.node_id,
-								  remote_node_record.node_name,
-								  remote_node_record.node_id);
-				switchover_success = false;
-
-				break;
-			case JOIN_FAIL_NO_REPLICATION:
-				appendPQExpBuffer(&event_details,
-								  _("node \"%s\" (ID: %i) promoted to primary, but demote node \"%s\" (ID: %i) did not connect to the new primary"),
-								  config_file_options.node_name,
-								  config_file_options.node_id,
-								  remote_node_record.node_name,
-								  remote_node_record.node_id);
-				switchover_success = false;
-				break;
-			case JOIN_SUCCESS:
-				appendPQExpBuffer(&event_details,
-								  _("node \"%s\" (ID: %i) promoted to primary, node \"%s\" (ID: %i) demoted to standby"),
-								  config_file_options.node_name,
-								  config_file_options.node_id,
-								  remote_node_record.node_name,
-								  remote_node_record.node_id);
-		}
-
-		create_event_notification_extended(local_conn,
-										   &config_file_options,
-										   config_file_options.node_id,
-										   "standby_switchover",
-										   switchover_success,
-										   event_details.data,
-										   &event_info);
-		if (switchover_success == true)
+		/* "rempgr node rejoin" failed on the demotion candidate */
+		if (command_output.data[0] == '0')
 		{
-			log_notice("%s", event_details.data);
+			appendPQExpBuffer(&logmsg,
+							  _("execution of \"repmgr node rejoin\" on demotion candidate \"%s\" (ID: %i) failed"),
+							  remote_node_record.node_name,
+							  remote_node_record.node_id);
+
+			/*
+			 * Speculatively check if the demotion candidate has been restarted, e.g. by
+			 * an external watchdog process which isn't aware a switchover is happening.
+			 * This falls into the category "thing outside of our control which shouldn't
+			 * happen, but if it does, make it easier to find out what happened".
+			 */
+			remote_conn = establish_db_connection(remote_node_record.conninfo, false);
+
+			if (PQstatus(remote_conn) == CONNECTION_OK)
+			{
+				if (get_recovery_type(remote_conn) == RECTYPE_PRIMARY)
+				{
+					appendPQExpBuffer(&detailmsg,
+									  _("PostgreSQL instance on demotion candidate \"%s\" (ID: %i) is running as a primary\n"),
+									  remote_node_record.node_name,
+									  remote_node_record.node_id);
+					log_warning("%s", detailmsg.data);
+				}
+			}
+			PQfinish(remote_conn);
+
+			appendPQExpBuffer(&detailmsg,
+							  "check log file \"%s\" on \"%s\" for details",
+							  node_rejoin_log,
+							  remote_node_record.node_name);
+
+			switchover_success = false;
+			join_success = JOIN_COMMAND_FAIL;
 		}
 		else
 		{
-			log_error("%s", event_details.data);
+			join_success = check_standby_join(local_conn,
+											  &local_node_record,
+											  &remote_node_record);
+
+
+
+			switch (join_success) {
+				case JOIN_FAIL_NO_PING:
+					appendPQExpBuffer(&logmsg,
+									  _("node \"%s\" (ID: %i) promoted to primary, but demotion candidate \"%s\" (ID: %i) did not become available"),
+									  config_file_options.node_name,
+									  config_file_options.node_id,
+									  remote_node_record.node_name,
+									  remote_node_record.node_id);
+
+					switchover_success = false;
+
+					break;
+				case JOIN_FAIL_NO_REPLICATION:
+					appendPQExpBuffer(&logmsg,
+									  _("node \"%s\" (ID: %i) promoted to primary, but demotion candidate \"%s\" (ID: %i) did not connect to the new primary"),
+									  config_file_options.node_name,
+									  config_file_options.node_id,
+									  remote_node_record.node_name,
+									  remote_node_record.node_id);
+					switchover_success = false;
+					break;
+				case JOIN_SUCCESS:
+					appendPQExpBuffer(&logmsg,
+									  _("node \"%s\" (ID: %i) promoted to primary, node \"%s\" (ID: %i) demoted to standby"),
+									  config_file_options.node_name,
+									  config_file_options.node_id,
+									  remote_node_record.node_name,
+									  remote_node_record.node_id);
+					break;
+				/* check_standby_join() does not return this */
+				case JOIN_COMMAND_FAIL:
+					break;
+				/* should never happen*/
+				case JOIN_UNKNOWN:
+					appendPQExpBuffer(&logmsg,
+									  "unable to determine success of node rejoin action for demotion candidate \"%s\" (ID: %i)",
+									  remote_node_record.node_name,
+									  remote_node_record.node_id);
+					switchover_success = false;
+					break;
+			}
+
+			if (switchover_success == false)
+			{
+				appendPQExpBuffer(&detailmsg,
+								  "check the PostgreSQL log file on  demotion candidate \"%s\" (ID: %i)",
+								  remote_node_record.node_name,
+								  remote_node_record.node_id);
+			}
 		}
-		termPQExpBuffer(&event_details);
 	}
 
+	if (switchover_success == true)
+	{
+		/* TODO: verify demotion candidates's node record was updated correctly */
+
+		log_notice("%s", logmsg.data);
+	}
+	else
+	{
+		log_error("%s", logmsg.data);
+	}
+
+	initPQExpBuffer(&event_details);
+
+	appendPQExpBufferStr(&event_details, logmsg.data);
+
+	if (detailmsg.data[0] != '\0')
+	{
+		log_detail("%s", detailmsg.data);
+		appendPQExpBuffer(&event_details, "\n%s",
+						  detailmsg.data);
+	}
+
+
+	create_event_notification_extended(local_conn,
+									   &config_file_options,
+									   config_file_options.node_id,
+									   "standby_switchover",
+									   switchover_success,
+									   event_details.data,
+									   &event_info);
+
+	termPQExpBuffer(&event_details);
+	termPQExpBuffer(&logmsg);
+	termPQExpBuffer(&detailmsg);
 	termPQExpBuffer(&command_output);
 
+
 	/*
 	 * If --siblings-follow specified, attempt to make them follow the new
 	 * primary
@@ -5543,7 +5668,7 @@ do_standby_switchover(void)
 
 				if (repmgrd_info[i]->paused == true && runtime_options.repmgrd_force_unpause == false)
 				{
-					log_debug("repmgrd on node \"%s\" (ID %i) paused before switchover, --repmgrd-force-unpause not provided, not unpausing",
+					log_debug("repmgrd on node \"%s\" (ID: %i) paused before switchover, --repmgrd-force-unpause not provided, not unpausing",
 							  cell->node_info->node_name,
 							  cell->node_info->node_id);
 
@@ -5551,7 +5676,7 @@ do_standby_switchover(void)
 					continue;
 				}
 
-				log_debug("unpausing repmgrd on node \"%s\" (ID %i)",
+				log_debug("unpausing repmgrd on node \"%s\" (ID: %i)",
 						  cell->node_info->node_name,
 						  cell->node_info->node_id);
 
@@ -5562,7 +5687,7 @@ do_standby_switchover(void)
 					if (repmgrd_pause(cell->node_info->conn, false) == false)
 					{
 						item_list_append_format(&repmgrd_unpause_errors,
-												_("unable to unpause node \"%s\" (ID %i)"),
+												_("unable to unpause node \"%s\" (ID: %i)"),
 												cell->node_info->node_name,
 												cell->node_info->node_id);
 						error_node_count++;
@@ -5571,7 +5696,7 @@ do_standby_switchover(void)
 				else
 				{
 					item_list_append_format(&repmgrd_unpause_errors,
-											_("unable to connect to node \"%s\" (ID %i):\n%s"),
+											_("unable to connect to node \"%s\" (ID: %i):\n%s"),
 											cell->node_info->node_name,
 											cell->node_info->node_id,
 											PQerrorMessage(cell->node_info->conn));
@@ -5659,20 +5784,18 @@ check_source_server()
 	}
 
 	/*
-	 * If a connection was established, perform some sanity checks on the
-	 * provided upstream connection.
+	 * The server version check will also serve as a sanity-check that we can
+	 * actually execute queries on this connection.
 	 */
-
 	source_server_version_num = check_server_version(source_conn, "primary", true, NULL);
 
 	/*
-	 * It's not essential to know the cluster size, but useful to sanity-check
-	 * we can actually run a query before going any further.
+	 * The cluster size is nice to have, but not essential to know, so only display
+	 * something if the user has sufficient permissions to retrieve the size of
+	 * all databases.
 	 */
-	if (get_cluster_size(source_conn, cluster_size) == false)
-		exit(ERR_DB_QUERY);
-
-	log_detail(_("current installation size is %s"),
+	if (get_cluster_size(source_conn, cluster_size) == true)
+		log_detail(_("current installation size is %s"),
 			   cluster_size);
 
 	/*
@@ -6855,6 +6978,13 @@ run_basebackup(t_node_info *node_record)
 
 	termPQExpBuffer(&params);
 
+	if (runtime_options.dry_run == true)
+	{
+		log_info(_("would execute:\n  %s"), script.data);
+		termPQExpBuffer(&script);
+		return SUCCESS;
+	}
+
 	log_info(_("executing:\n  %s"), script.data);
 
 	/*
@@ -8018,9 +8148,9 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_co
 		free(escaped);
 	}
 
-
-
-
+	/*
+	 * Caller requests the generated file to be written into a buffer
+	 */
 	if (as_file == false)
 	{
 		/* create file in buffer */
@@ -8040,20 +8170,17 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_co
 		return true;
 	}
 
-
 	/*
 	 * PostgreSQL 12 and later: modify postgresql.auto.conf
-	 *
 	 */
 	if (server_version_num >= 120000)
 	{
-
 		if (modify_auto_conf(dest, &recovery_config) == false)
 		{
 			return false;
 		}
 
-		if (write_standby_signal() == false)
+		if (write_standby_signal(dest) == false)
 		{
 			return false;
 		}

repmgr-client-global.h

@@ -120,6 +120,7 @@ typedef struct
 	bool		missing_slots;
 	bool		has_passfile;
 	bool		replication_connection;
+	bool		repmgrd;
 	bool		data_directory_config;
 	bool		replication_config_owner;
 	bool		db_connection;
@@ -175,7 +176,7 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, false, false, false,	false, false, false, false, \
+		false, false, false, false, false, false, false, false,	false, false, false, false, false, \
 		/* "node rejoin" options */ \
 		"", \
 		/* "node service" options */ \
@@ -219,7 +220,9 @@ typedef enum
 
 typedef enum
 {
+	JOIN_UNKNOWN = -1,
 	JOIN_SUCCESS,
+	JOIN_COMMAND_FAIL,
 	JOIN_FAIL_NO_PING,
 	JOIN_FAIL_NO_REPLICATION
 } standy_join_status;
@@ -282,8 +285,8 @@ 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);
-extern void make_standby_signal_path(char *buf);
-extern bool write_standby_signal(void);
+extern void make_standby_signal_path(const char *data_dir, char *buf);
+extern bool write_standby_signal(const char *data_dir);
 
 extern bool create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_node_record, PQExpBufferData *error_msg);
 extern bool drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);

repmgr-client.c

@@ -51,6 +51,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <pwd.h>
 #include <unistd.h>
 #include <sys/stat.h>
 #include <signal.h>
@@ -89,17 +90,22 @@ char		pg_bindir[MAXPGPATH] = "";
  */
 t_node_info target_node_info = T_NODE_INFO_INITIALIZER;
 
-/* used by create_replication_slot() */
+/* set by the first call to _determine_replication_slot_user() */
 static t_user_type ReplicationSlotUser = USER_TYPE_UNKNOWN;
 
 /* Collate command line errors and warnings here for friendlier reporting */
 static ItemList cli_errors = {NULL, NULL};
 static ItemList cli_warnings = {NULL, NULL};
 
+
 static void _determine_replication_slot_user(PGconn *conn,
 											 t_node_info *upstream_node_record,
 											 char **replication_user);
 
+static PGconn *_get_replication_slot_connection(PGconn *conn,
+												char *replication_user,
+												bool *use_replication_protocol);
+
 int
 main(int argc, char **argv)
 {
@@ -549,6 +555,10 @@ main(int argc, char **argv)
 				runtime_options.data_directory_config = true;
 				break;
 
+			case OPT_REPMGRD:
+				runtime_options.repmgrd = true;
+				break;
+
 			case OPT_REPLICATION_CONFIG_OWNER:
 				runtime_options.replication_config_owner = true;
 				break;
@@ -3182,6 +3192,11 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 								 " --exclude=pg_xlog/* --exclude=pg_log/*");
 		}
 
+		/*
+		 * From PostgreSQL 15, the core server no longer uses pg_stat_tmp,
+		 * but some extensions (e.g. pg_stat_statements) may still do, so
+		 * keep excluding it.
+		 */
 		appendPQExpBufferStr(&rsync_flags,
 							 " --exclude=pg_stat_tmp/*");
 
@@ -3619,8 +3634,8 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 	/* "full_page_writes" must be on in any case */
 	if (guc_set(conn, "full_page_writes", "=", "off"))
 	{
-		appendPQExpBuffer(reason,
-						  _("\"full_page_writes\" must be set to \"on\""));
+		appendPQExpBufferStr(reason,
+							 _("\"full_page_writes\" must be set to \"on\""));
 
 		can_use = false;
 	}
@@ -3638,18 +3653,18 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 		if (data_checksum_version == UNKNOWN_DATA_CHECKSUM_VERSION)
 		{
 			if (can_use == false)
-				appendPQExpBuffer(reason, "; ");
+				appendPQExpBufferStr(reason, "; ");
 
-			appendPQExpBuffer(reason,
-							  _("\"wal_log_hints\" is set to \"off\" but unable to determine data checksum version"));
+			appendPQExpBufferStr(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, "; ");
+				appendPQExpBufferStr(reason, "; ");
 
-			appendPQExpBuffer(reason,
+			appendPQExpBufferStr(reason,
 							  _("\"wal_log_hints\" is set to \"off\" and data checksums are disabled"));
 
 			can_use = false;
@@ -3661,11 +3676,11 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 
 
 void
-make_standby_signal_path(char *buf)
+make_standby_signal_path(const char *data_dir, char *buf)
 {
 	snprintf(buf, MAXPGPATH,
 			 "%s/%s",
-			 config_file_options.data_directory,
+			 data_dir,
 			 STANDBY_SIGNAL_FILE);
 }
 
@@ -3673,13 +3688,15 @@ make_standby_signal_path(char *buf)
  * create standby.signal (PostgreSQL 12 and later)
  */
 bool
-write_standby_signal(void)
+write_standby_signal(const char *data_dir)
 {
 	char	    standby_signal_file_path[MAXPGPATH] = "";
 	FILE	   *file;
 	mode_t		um;
 
-	make_standby_signal_path(standby_signal_file_path);
+	Assert(data_dir != NULL);
+
+	make_standby_signal_path(data_dir, standby_signal_file_path);
 
 	/* Set umask to 0600 */
 	um = umask((~(S_IRUSR | S_IWUSR)) & (S_IRWXG | S_IRWXO));
@@ -3727,6 +3744,7 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 	char *replication_user = NULL;
 
 	_determine_replication_slot_user(conn, upstream_node_record, &replication_user);
+
 	/*
 	 * If called in --dry-run context, if the replication slot user is not the
 	 * repmgr user, attempt to validate the connection.
@@ -3738,7 +3756,7 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 			case USER_TYPE_UNKNOWN:
 				log_error("unable to determine user for replication slot creation");
 				return false;
-			case  REPMGR_USER:
+			case REPMGR_USER:
 				log_info(_("replication slots will be created by user \"%s\""),
 						 PQuser(conn));
 				return true;
@@ -3784,65 +3802,12 @@ create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_nod
 				PQfinish(superuser_conn);
 			}
 		}
-
 	}
 
-	/*
-	 * If we can't create a replication slot with the connection provided to
-	 * the function, create an connection with appropriate permissions.
-	 */
-	switch (ReplicationSlotUser)
-	{
-		case USER_TYPE_UNKNOWN:
-			log_error("unable to determine user for replication slot creation");
-			return false;
-		case  REPMGR_USER:
-			slot_conn = conn;
-			log_info(_("creating replication slot as user \"%s\""),
-					 PQuser(conn));
-			break;
+	slot_conn = _get_replication_slot_connection(conn, replication_user, &use_replication_protocol);
 
-		case REPLICATION_USER_NODE:
-		case REPLICATION_USER_OPT:
-		{
-			slot_conn = duplicate_connection(conn,
-											 replication_user,
-											 true);
-			if (slot_conn == NULL || PQstatus(slot_conn) != CONNECTION_OK)
-			{
-				log_error(_("unable to create replication connection as user \"%s\""),
-						  runtime_options.replication_user);
-				log_detail("%s", PQerrorMessage(slot_conn));
-
-				PQfinish(slot_conn);
-					return false;
-			}
-			use_replication_protocol = true;
-			log_info(_("creating replication slot as replication user \"%s\""),
-					 replication_user);
-		}
-			break;
-
-		case SUPERUSER:
-		{
-			slot_conn = duplicate_connection(conn,
-											 runtime_options.superuser,
-											 false);
-			if (slot_conn == NULL || PQstatus(slot_conn )!= CONNECTION_OK)
-			{
-				log_error(_("unable to create super connection as user \"%s\""),
-						  runtime_options.superuser);
-				log_detail("%s", PQerrorMessage(slot_conn));
-
-				PQfinish(slot_conn);
-
-				return false;
-			}
-			log_info(_("creating replication slot as superuser \"%s\""),
-					 runtime_options.superuser);
-		}
-			break;
-	}
+	if (slot_conn == NULL)
+		return false;
 
 	if (use_replication_protocol == true)
 	{
@@ -3885,34 +3850,53 @@ drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name)
 
 	if (record_status != RECORD_FOUND)
 	{
-		/* this is not a bad good thing */
+		/* no slot, no problem */
 		log_verbose(LOG_INFO,
 					_("slot \"%s\" does not exist on node %i, nothing to remove"),
 					slot_name, node_id);
 		return true;
 	}
 
-	if (slot_info.active == false)
+	if (slot_info.active == true)
 	{
-		if (drop_replication_slot_sql(conn, slot_name) == true)
+		/*
+		 * If an active replication slot exists, bail out as we have a problem
+		 * we can't solve here.
+		 */
+		log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
+		success = false;
+	}
+	else
+	{
+		/*
+		 * Create the appropriate connection with which to drop the slot
+		 */
+
+		bool use_replication_protocol = false;
+		PGconn *slot_conn = _get_replication_slot_connection(conn,
+															 replication_user,
+															 &use_replication_protocol);
+
+		if (use_replication_protocol == true)
+		{
+			success = drop_replication_slot_replprot(slot_conn, slot_name);
+		}
+		else
+		{
+			success = drop_replication_slot_sql(slot_conn, slot_name);
+		}
+
+		if (success == true)
 		{
 			log_notice(_("replication slot \"%s\" deleted on node %i"), slot_name, node_id);
 		}
 		else
 		{
 			log_error(_("unable to delete replication slot \"%s\" on node %i"), slot_name, node_id);
-			success = false;
 		}
-	}
 
-	/*
-	 * If an active replication slot exists, call Houston as we have a
-	 * problem.
-	 */
-	else
-	{
-		log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
-		success = false;
+		if (slot_conn != conn)
+			PQfinish(slot_conn);
 	}
 
 	return success;
@@ -3974,10 +3958,88 @@ _determine_replication_slot_user(PGconn *conn, t_node_info *upstream_node_record
 			ReplicationSlotUser = REPLICATION_USER_NODE;
 			*replication_user = upstream_node_record->repluser;
 		}
+		else
+		{
+			/* This should never happen */
+			log_error("unable to determine replication slot user");
+			if (upstream_node_record != NULL)
+			{
+				log_debug("%i %s %s", upstream_node_record->node_id, upstream_node_record->repluser, PQuser(conn));
+			}
+			else
+			{
+				log_debug("upstream_node_record not provided");
+			}
+		}
 	}
 }
 
 
+static PGconn *
+_get_replication_slot_connection(PGconn *conn, char *replication_user, bool *use_replication_protocol)
+{
+	PGconn *slot_conn = NULL;
+	/*
+	 * If we can't create a replication slot with the connection provided to
+	 * the function, create an connection with appropriate permissions.
+	 */
+	switch (ReplicationSlotUser)
+	{
+		case USER_TYPE_UNKNOWN:
+			log_error("unable to determine user for managing replication slots");
+			return NULL;
+
+		case  REPMGR_USER:
+			slot_conn = conn;
+			log_verbose(LOG_INFO, _("managing replication slot as user \"%s\""),
+						PQuser(conn));
+			break;
+
+		case REPLICATION_USER_NODE:
+		case REPLICATION_USER_OPT:
+		{
+			slot_conn = duplicate_connection(conn,
+											 replication_user,
+											 true);
+			if (slot_conn == NULL || PQstatus(slot_conn) != CONNECTION_OK)
+			{
+				log_error(_("unable to manage replication connection as replication user \"%s\""),
+						  runtime_options.replication_user);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+				return NULL;
+			}
+			*use_replication_protocol = true;
+			log_verbose(LOG_INFO, _("managing replication slot as replication user \"%s\""),
+						replication_user);
+		}
+		break;
+
+		case SUPERUSER:
+		{
+			slot_conn = duplicate_connection(conn,
+											 runtime_options.superuser,
+											 false);
+			if (slot_conn == NULL || PQstatus(slot_conn )!= CONNECTION_OK)
+			{
+				log_error(_("unable to create superuser connection as user \"%s\""),
+						  runtime_options.superuser);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+
+				return NULL;
+			}
+			log_verbose(LOG_INFO, _("creating replication slot as superuser \"%s\""),
+						runtime_options.superuser);
+		}
+		break;
+	}
+
+	return slot_conn;
+}
+
 bool
 check_replication_slots_available(int node_id, PGconn* conn)
 {

repmgr-client.h

@@ -100,6 +100,7 @@
 #define OPT_DB_CONNECTION				   1047
 #define OPT_VERIFY_BACKUP				   1048
 #define OPT_RECOVERY_MIN_APPLY_DELAY       1049
+#define OPT_REPMGRD						   1050
 
 /* These options are for internal use only */
 #define OPT_CONFIG_ARCHIVE_DIR			   2001
@@ -193,6 +194,7 @@ static struct option long_options[] =
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
 	{"missing-slots", no_argument, NULL, OPT_MISSING_SLOTS},
+	{"repmgrd", no_argument, NULL, OPT_REPMGRD},
 	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
 	{"replication-connection", no_argument, NULL, OPT_REPL_CONN},
 	{"data-directory-config", no_argument, NULL, OPT_DATA_DIRECTORY_CONFIG},

repmgr.c

@@ -80,67 +80,36 @@ typedef struct repmgrdSharedState
 
 static repmgrdSharedState *shared_state = NULL;
 
+#if (PG_VERSION_NUM >= 150000)
+static shmem_request_hook_type prev_shmem_request_hook = NULL;
+#endif
 static shmem_startup_hook_type prev_shmem_startup_hook = NULL;
 
-
 void		_PG_init(void);
-void		_PG_fini(void);
 
+#if (PG_VERSION_NUM >= 150000)
+static void repmgr_shmem_request(void);
+#endif
 static void repmgr_shmem_startup(void);
 
-Datum		set_local_node_id(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(set_local_node_id);
-
-Datum		get_local_node_id(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_local_node_id);
-
-Datum		standby_set_last_updated(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(standby_set_last_updated);
-
-Datum		standby_get_last_updated(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(standby_get_last_updated);
-
-Datum		set_upstream_last_seen(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(set_upstream_last_seen);
-
-Datum		get_upstream_last_seen(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_upstream_last_seen);
-
-Datum		get_upstream_node_id(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_upstream_node_id);
-
-Datum		set_upstream_node_id(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(set_upstream_node_id);
-
-Datum		notify_follow_primary(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(notify_follow_primary);
-
-Datum		get_new_primary(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_new_primary);
-
-Datum		reset_voting_status(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(reset_voting_status);
-
-Datum		set_repmgrd_pid(PG_FUNCTION_ARGS);
+PG_FUNCTION_INFO_V1(repmgr_set_local_node_id);
+PG_FUNCTION_INFO_V1(repmgr_get_local_node_id);
+PG_FUNCTION_INFO_V1(repmgr_standby_set_last_updated);
+PG_FUNCTION_INFO_V1(repmgr_standby_get_last_updated);
+PG_FUNCTION_INFO_V1(repmgr_set_upstream_last_seen);
+PG_FUNCTION_INFO_V1(repmgr_get_upstream_last_seen);
+PG_FUNCTION_INFO_V1(repmgr_get_upstream_node_id);
+PG_FUNCTION_INFO_V1(repmgr_set_upstream_node_id);
+PG_FUNCTION_INFO_V1(repmgr_notify_follow_primary);
+PG_FUNCTION_INFO_V1(repmgr_get_new_primary);
+PG_FUNCTION_INFO_V1(repmgr_reset_voting_status);
 PG_FUNCTION_INFO_V1(set_repmgrd_pid);
-
-Datum		get_repmgrd_pid(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(get_repmgrd_pid);
-
-Datum		get_repmgrd_pidfile(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(get_repmgrd_pidfile);
-
-Datum		repmgrd_is_running(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(repmgrd_is_running);
-
-Datum		repmgrd_pause(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(repmgrd_pause);
-
-Datum		repmgrd_is_paused(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(repmgrd_is_paused);
-
-Datum		get_wal_receiver_pid(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(get_wal_receiver_pid);
+PG_FUNCTION_INFO_V1(repmgr_get_wal_receiver_pid);
 
 
 /*
@@ -152,35 +121,47 @@ _PG_init(void)
 	if (!process_shared_preload_libraries_in_progress)
 		return;
 
+#if (PG_VERSION_NUM < 150000)
 	RequestAddinShmemSpace(MAXALIGN(sizeof(repmgrdSharedState)));
 
 #if (PG_VERSION_NUM >= 90600)
 	RequestNamedLWLockTranche(TRANCHE_NAME, 1);
 #else
 	RequestAddinLWLocks(1);
+#endif
 #endif
 
 	/*
 	 * Install hooks.
 	 */
+#if (PG_VERSION_NUM >= 150000)
+	prev_shmem_request_hook = shmem_request_hook;
+	shmem_request_hook = repmgr_shmem_request;
+#endif
+
 	prev_shmem_startup_hook = shmem_startup_hook;
 	shmem_startup_hook = repmgr_shmem_startup;
+
 }
 
-
+#if (PG_VERSION_NUM >= 150000)
 /*
- * Module unload callback
+ * shmem_requst_hook: request shared memory
  */
-void
-_PG_fini(void)
+static void
+repmgr_shmem_request(void)
 {
-	/* Uninstall hook */
-	shmem_startup_hook = prev_shmem_startup_hook;
-}
+	if (prev_shmem_request_hook)
+		prev_shmem_request_hook();
 
+	RequestAddinShmemSpace(MAXALIGN(sizeof(repmgrdSharedState)));
+
+	RequestNamedLWLockTranche(TRANCHE_NAME, 1);
+}
+#endif
 
 /*
- * shmem_startup hook: allocate or attach to shared memory,
+ * shmem_startup hook: allocate or attach to shared memory
  */
 static void
 repmgr_shmem_startup(void)
@@ -233,7 +214,7 @@ repmgr_shmem_startup(void)
 /* ==================== */
 
 Datum
-set_local_node_id(PG_FUNCTION_ARGS)
+repmgr_set_local_node_id(PG_FUNCTION_ARGS)
 {
 	int			local_node_id = UNKNOWN_NODE_ID;
 	int			stored_node_id = UNKNOWN_NODE_ID;
@@ -303,7 +284,7 @@ set_local_node_id(PG_FUNCTION_ARGS)
 
 
 Datum
-get_local_node_id(PG_FUNCTION_ARGS)
+repmgr_get_local_node_id(PG_FUNCTION_ARGS)
 {
 	int			local_node_id = UNKNOWN_NODE_ID;
 
@@ -320,7 +301,7 @@ get_local_node_id(PG_FUNCTION_ARGS)
 
 /* update and return last updated with current timestamp */
 Datum
-standby_set_last_updated(PG_FUNCTION_ARGS)
+repmgr_standby_set_last_updated(PG_FUNCTION_ARGS)
 {
 	TimestampTz last_updated = GetCurrentTimestamp();
 
@@ -337,7 +318,7 @@ standby_set_last_updated(PG_FUNCTION_ARGS)
 
 /* get last updated timestamp */
 Datum
-standby_get_last_updated(PG_FUNCTION_ARGS)
+repmgr_standby_get_last_updated(PG_FUNCTION_ARGS)
 {
 	TimestampTz last_updated;
 
@@ -354,7 +335,7 @@ standby_get_last_updated(PG_FUNCTION_ARGS)
 
 
 Datum
-set_upstream_last_seen(PG_FUNCTION_ARGS)
+repmgr_set_upstream_last_seen(PG_FUNCTION_ARGS)
 {
 	int			upstream_node_id = UNKNOWN_NODE_ID;
 
@@ -377,7 +358,7 @@ set_upstream_last_seen(PG_FUNCTION_ARGS)
 
 
 Datum
-get_upstream_last_seen(PG_FUNCTION_ARGS)
+repmgr_get_upstream_last_seen(PG_FUNCTION_ARGS)
 {
 	long		secs;
 	int			microsecs;
@@ -411,7 +392,7 @@ get_upstream_last_seen(PG_FUNCTION_ARGS)
 
 
 Datum
-get_upstream_node_id(PG_FUNCTION_ARGS)
+repmgr_get_upstream_node_id(PG_FUNCTION_ARGS)
 {
 	int			upstream_node_id = UNKNOWN_NODE_ID;
 
@@ -426,7 +407,7 @@ get_upstream_node_id(PG_FUNCTION_ARGS)
 }
 
 Datum
-set_upstream_node_id(PG_FUNCTION_ARGS)
+repmgr_set_upstream_node_id(PG_FUNCTION_ARGS)
 {
 	int			upstream_node_id = UNKNOWN_NODE_ID;
 	int			local_node_id = UNKNOWN_NODE_ID;
@@ -462,7 +443,7 @@ set_upstream_node_id(PG_FUNCTION_ARGS)
 
 
 Datum
-notify_follow_primary(PG_FUNCTION_ARGS)
+repmgr_notify_follow_primary(PG_FUNCTION_ARGS)
 {
 	int			primary_node_id = UNKNOWN_NODE_ID;
 
@@ -505,7 +486,7 @@ notify_follow_primary(PG_FUNCTION_ARGS)
 
 
 Datum
-get_new_primary(PG_FUNCTION_ARGS)
+repmgr_get_new_primary(PG_FUNCTION_ARGS)
 {
 	int			new_primary_node_id = UNKNOWN_NODE_ID;
 
@@ -527,7 +508,7 @@ get_new_primary(PG_FUNCTION_ARGS)
 
 
 Datum
-reset_voting_status(PG_FUNCTION_ARGS)
+repmgr_reset_voting_status(PG_FUNCTION_ARGS)
 {
 	if (!shared_state)
 		PG_RETURN_NULL();
@@ -735,7 +716,7 @@ repmgrd_is_paused(PG_FUNCTION_ARGS)
 
 
 Datum
-get_wal_receiver_pid(PG_FUNCTION_ARGS)
+repmgr_get_wal_receiver_pid(PG_FUNCTION_ARGS)
 {
 	int wal_receiver_pid;
 

repmgr.conf.sample

@@ -69,7 +69,7 @@
 #------------------------------------------------------------------------------
 
 #replication_user='repmgr'	 # User to make replication connections with, if not set
-				 #  defaults to the user defined in "conninfo".
+				 # defaults to the user defined in "conninfo".
 
 #replication_type='physical'	 # Must "physical" (the default).
 
@@ -314,7 +314,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #follow_command=''			# command repmgrd executes when instructing a standby to follow a new primary;
 					# use something like:
 					#
-					#     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
+					#     repmgr standby follow -f /etc/repmgr.conf --upstream-node-id=%n
 					#
 #primary_notification_timeout=60	# Interval (in seconds) which repmgrd on a standby
 					# will wait for a notification from the new primary,
@@ -337,6 +337,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# "--no-pid-file" will force PID file creation to be skipped.
 					# Note: there is normally no need to set this, particularly if
 					# repmgr was installed from packages.
+#repmgrd_exit_on_inactive_node=false	# If "true", and the node record is marked as "inactive", abort repmgrd startup
 #standby_disconnect_on_failover=false	# If "true", in a failover situation wait for all standbys to
 					# disconnect their WAL receivers before electing a new primary
 					# (PostgreSQL 9.5 and later only; repmgr user must be a superuser for this)
@@ -397,7 +398,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #
 # Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
 #
-# For more details, see: https://repmgr.org/docs/current/configuration-service-commands.html
+# For more details, see: https://repmgr.org/docs/current/configuration-file-service-commands.html
 
 #service_start_command = ''
 #service_stop_command = ''

repmgr.control

@@ -1,8 +1,7 @@
 # repmgr extension
 comment = 'Replication manager for PostgreSQL'
-default_version = '5.2'
+default_version = '5.3'
 module_pathname = '$libdir/repmgr'
 relocatable = false
 schema = repmgr
 
-

repmgr.h

@@ -135,6 +135,7 @@
 #define DEFAULT_ASYNC_QUERY_TIMEOUT          60  /* seconds */
 #define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
 #define DEFAULT_REPMGRD_STANDBY_STARTUP_TIMEOUT -1 /*seconds */
+#define DEFAULT_REPMGRD_EXIT_ON_INACTIVE_NODE false,
 #define DEFAULT_STANDBY_DISCONNECT_ON_FAILOVER false
 #define DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT 30 /* seconds */
 #define DEFAULT_CONNECTION_CHECK_TYPE        CHECK_PING

repmgr_version.h.in

@@ -1,5 +1,7 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "5.2.1"
-#define REPMGR_VERSION_NUM 50201
-#define REPMGR_RELEASE_DATE "2020-12-07"
+#define REPMGR_VERSION "5.3.3"
+#define REPMGR_VERSION_NUM 50303
+#define REPMGR_EXTENSION_VERSION "5.3"
+#define REPMGR_EXTENSION_NUM 50300
+#define REPMGR_RELEASE_DATE "2022-10-17"
 #define PG_ACTUAL_VERSION_NUM 

repmgrd-physical.c

@@ -169,45 +169,126 @@ handle_sigint_physical(SIGNAL_ARGS)
 /* perform some sanity checks on the node's configuration */
 
 void
-do_physical_node_check(void)
+do_physical_node_check(PGconn *conn)
 {
 	/*
-	 * Check if node record is active - if not, and `failover=automatic`, the
-	 * node won't be considered as a promotion candidate; this often happens
-	 * when a failed primary is recloned and the node was not re-registered,
-	 * giving the impression failover capability is there when it's not. In
-	 * this case abort with an error and a hint about registering.
+	 * If node record is "inactive"; if not, attempt to set it to "active".
 	 *
-	 * If `failover=manual`, repmgrd can continue to passively monitor the
-	 * node, but we should nevertheless issue a warning and the same hint.
+	 * Usually it will have become inactive due to e.g. a standby being shut down
+	 * while repmgrd was running in an unpaused state. In this case it's
+	 * perfectly reasonable to automatically mark the node as "active".
 	 */
 
 	if (local_node_info.active == false)
 	{
 		char	   *hint = "Check that \"repmgr (primary|standby) register\" was executed for this node";
+		RecoveryType recovery_type = get_recovery_type(conn);
 
-		switch (config_file_options.failover)
+		/*
+		 * If the local node's recovery status is incompatible with its registered
+		 * status, e.g. registered as primary but running as a standby, refuse to start.
+		 *
+		 * This typically happens when a failed primary is recloned but the node was not
+		 * re-registered, leaving the cluster in a potentially ambiguous state. In
+		 * this case it would not be possible or desirable to attempt to set the
+		 * node to active; the user should ensure the cluster is in the correct state.
+		 */
+		if (recovery_type != RECTYPE_UNKNOWN && local_node_info.type != UNKNOWN)
 		{
-			/* "failover" is an enum, all values should be covered here */
+			bool	require_reregister = false;
+			PQExpBufferData event_details;
+			initPQExpBuffer(&event_details);
 
-			case FAILOVER_AUTOMATIC:
-				log_error(_("this node is marked as inactive and cannot be used as a failover target"));
+			if (recovery_type == RECTYPE_STANDBY && local_node_info.type != STANDBY)
+			{
+				appendPQExpBuffer(&event_details,
+								  _("node is registered as a %s but running as a standby"),
+								  get_node_type_string(local_node_info.type));
+
+				require_reregister = true;
+			}
+			else if (recovery_type == RECTYPE_PRIMARY && local_node_info.type == STANDBY)
+			{
+				log_error(_("node is registered as a standby but running as a %s"), get_node_type_string(local_node_info.type));
+				require_reregister = true;
+			}
+
+			if (require_reregister == true)
+			{
+				log_error("%s", event_details.data);
 				log_hint(_("%s"), hint);
 
 				create_event_notification(NULL,
 										  &config_file_options,
 										  config_file_options.node_id,
-										  "repmgrd_shutdown",
+										  "repmgrd_start",
 										  false,
-										  "node is inactive and cannot be used as a failover target");
+										  event_details.data);
 
+				termPQExpBuffer(&event_details);
 				terminate(ERR_BAD_CONFIG);
-				break;
+			}
 
-			case FAILOVER_MANUAL:
-				log_warning(_("this node is marked as inactive and will be passively monitored only"));
-				log_hint(_("%s"), hint);
-				break;
+			termPQExpBuffer(&event_details);
+		}
+
+		/*
+		 * Attempt to set node record active (unless explicitly configured not to)
+		 */
+		log_notice(_("setting node record for node \"%s\" (ID: %i) to \"active\""),
+				   local_node_info.node_name,
+				   local_node_info.node_id);
+
+		if (config_file_options.repmgrd_exit_on_inactive_node == false)
+		{
+			PGconn *primary_conn = get_primary_connection(conn, NULL, NULL);
+			bool	success = true;
+
+			if (PQstatus(primary_conn) != CONNECTION_OK)
+			{
+				log_error(_("unable to connect to the primary node to activate the node record"));
+				success = false;
+			}
+			else
+			{
+				success = update_node_record_set_active(primary_conn, local_node_info.node_id, true);
+				PQfinish(primary_conn);
+			}
+
+			if (success == true)
+			{
+				local_node_info.active = true;
+			}
+		}
+
+		/*
+		 * Corner-case where it was not possible to set the node to "active"
+		 */
+		if (local_node_info.active == false)
+		{
+			switch (config_file_options.failover)
+			{
+				/* "failover" is an enum, all values should be covered here */
+
+				case FAILOVER_AUTOMATIC:
+					log_error(_("this node is marked as inactive and cannot be used as a failover target"));
+					log_hint(_("%s"), hint);
+
+					create_event_notification(NULL,
+											  &config_file_options,
+											  config_file_options.node_id,
+											  "repmgrd_start",
+											  false,
+											  "node is inactive and cannot be used as a failover target");
+
+					terminate(ERR_BAD_CONFIG);
+					break;
+
+				case FAILOVER_MANUAL:
+					log_warning(_("this node is marked as inactive and will be passively monitored only"));
+					log_hint(_("%s"), hint);
+					break;
+			}
 		}
 	}
 
@@ -504,6 +585,7 @@ monitor_streaming_primary(void)
 
 			if (is_server_available(local_node_info.conninfo) == true)
 			{
+				close_connection(&local_conn);
 				local_conn = establish_db_connection(local_node_info.conninfo, false);
 
 				if (PQstatus(local_conn) != CONNECTION_OK)
@@ -1505,22 +1587,22 @@ monitor_streaming_standby(void)
 					/* TODO: possibly add pre-action event here */
 					if (upstream_node_info.type == STANDBY)
 					{
-						create_event_record(primary_conn,
-											&config_file_options,
-											config_file_options.node_id,
-											"repmgrd_upstream_disconnect",
-											true,
-											event_details.data);
+						create_event_notification(primary_conn,
+												  &config_file_options,
+												  config_file_options.node_id,
+												  "repmgrd_upstream_disconnect",
+												  true,
+												  event_details.data);
 					}
 					else
 					{
 						/* primary connection lost - script notification only */
-						create_event_record(NULL,
-											&config_file_options,
-											config_file_options.node_id,
-											"repmgrd_upstream_disconnect",
-											true,
-											event_details.data);
+						create_event_notification(NULL,
+												  &config_file_options,
+												  config_file_options.node_id,
+												  "repmgrd_upstream_disconnect",
+												  true,
+												  event_details.data);
 					}
 
 					log_warning("%s", event_details.data);
@@ -1732,7 +1814,10 @@ monitor_streaming_standby(void)
 			if (upstream_check_result == true)
 			{
 				if (config_file_options.connection_check_type != CHECK_QUERY)
+				{
+					close_connection(&upstream_conn);
 					upstream_conn = establish_db_connection(upstream_node_info.conninfo, false);
+				}
 
 				if (PQstatus(upstream_conn) == CONNECTION_OK)
 				{
@@ -1813,6 +1898,7 @@ monitor_streaming_standby(void)
 						int			former_upstream_node_id = local_node_info.upstream_node_id;
 						NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 						PQExpBufferData event_details;
+						t_event_info event_info = T_EVENT_INFO_INITIALIZER;
 
 						update_node_record_set_primary(local_conn,  local_node_info.node_id);
 						record_status = get_node_record(local_conn, local_node_info.node_id, &local_node_info);
@@ -1825,12 +1911,16 @@ monitor_streaming_standby(void)
 						initPQExpBuffer(&event_details);
 						appendPQExpBufferStr(&event_details,
 											 _("promotion command failed but promotion completed successfully"));
-						create_event_notification(local_conn,
-												  &config_file_options,
-												  local_node_info.node_id,
-												  "repmgrd_failover_promote",
-												  true,
-												  event_details.data);
+
+						event_info.node_id = former_upstream_node_id;
+
+						create_event_notification_extended(local_conn,
+														   &config_file_options,
+														   local_node_info.node_id,
+														   "repmgrd_failover_promote",
+														   true,
+														   event_details.data,
+														   &event_info);
 
 						termPQExpBuffer(&event_details);
 
@@ -2292,6 +2382,18 @@ monitor_streaming_witness(void)
 			log_warning(_("unable to retrieve node record from primary"));
 		}
 
+		/* refresh local node record from the primary */
+		record_status = get_node_record(primary_conn, config_file_options.node_id, &local_node_info);
+
+		if (record_status != RECORD_FOUND)
+		{
+			log_error(_("no metadata record found for this node on the current primary - terminating"));
+			log_hint(_("check that 'repmgr witness register' was executed for this node"));
+			close_connection(&primary_conn);
+			close_connection(&local_conn);
+			terminate(ERR_BAD_CONFIG);
+		}
+
 		initPQExpBuffer(&event_details);
 
 		appendPQExpBuffer(&event_details,
@@ -2380,12 +2482,12 @@ monitor_streaming_witness(void)
 									  _("unable to connect to primary node \"%s\" (ID: %i)"),
 									  upstream_node_info.node_name, upstream_node_info.node_id);
 
-					create_event_record(NULL,
-										&config_file_options,
-										config_file_options.node_id,
-										"repmgrd_upstream_disconnect",
-										true,
-										event_details.data);
+					create_event_notification(NULL,
+											  &config_file_options,
+											  config_file_options.node_id,
+											  "repmgrd_upstream_disconnect",
+											  true,
+											  event_details.data);
 					termPQExpBuffer(&event_details);
 				}
 
@@ -2460,8 +2562,10 @@ monitor_streaming_witness(void)
 			if (check_upstream_connection(&primary_conn, upstream_node_info.conninfo, NULL) == true)
 			{
 				if (config_file_options.connection_check_type != CHECK_QUERY)
+				{
+					close_connection(&primary_conn);
 					primary_conn = establish_db_connection(upstream_node_info.conninfo, false);
-
+				}
 				if (PQstatus(primary_conn) == CONNECTION_OK)
 				{
 					PQExpBufferData event_details;
@@ -2758,6 +2862,7 @@ do_primary_failover(void)
 	bool final_result = false;
 	NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 	int new_primary_id = UNKNOWN_NODE_ID;
+	bool standby_disconnect_on_failover = false;
 
 	/*
 	 * Double-check status of the local connection
@@ -2770,20 +2875,20 @@ do_primary_failover(void)
 	 */
 	if (config_file_options.standby_disconnect_on_failover == true)
 	{
-		NodeInfoListCell *cell = NULL;
-		NodeInfoList check_sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
-		int i;
+		/*
+		 * Determine whether we can actually disable the walsender; this depends
+		 * on PostgreSQL version and user permissions.
+		 */
+		standby_disconnect_on_failover = can_disable_walsender(local_conn);
 
-		bool sibling_node_wal_receiver_connected = false;
+		if (standby_disconnect_on_failover == true)
+		{
+			NodeInfoListCell *cell = NULL;
+			NodeInfoList check_sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
+			int i;
+
+			bool sibling_node_wal_receiver_connected = false;
 
-		if (PQserverVersion(local_conn) < 90500)
-		{
-			log_warning(_("\"standby_disconnect_on_failover\" specified, but not available for this PostgreSQL version"));
-			/* TODO: format server version */
-			log_detail(_("available from PostgreSQL 9.5, this PostgreSQL version is %i"), PQserverVersion(local_conn));
-		}
-		else
-		{
 			disable_wal_receiver(local_conn);
 
 			/*
@@ -2867,7 +2972,7 @@ do_primary_failover(void)
 	log_debug("election result: %s", _print_election_result(election_result));
 
 	/* Reenable WAL receiver, if disabled */
-	if (config_file_options.standby_disconnect_on_failover == true)
+	if (standby_disconnect_on_failover == true)
 	{
 		/* adjust "wal_retrieve_retry_interval" but don't wait for WAL receiver to start */
 		enable_wal_receiver(local_conn, false);
@@ -2975,7 +3080,6 @@ do_primary_failover(void)
 
 				t_node_info new_primary = T_NODE_INFO_INITIALIZER;
 				RecordStatus record_status = RECORD_NOT_FOUND;
-				PGconn	   *new_primary_conn;
 
 				record_status = get_node_record(local_conn, new_primary_id, &new_primary);
 
@@ -2987,6 +3091,7 @@ do_primary_failover(void)
 				else
 				{
 					PQExpBufferData event_details;
+					PGconn	   *new_primary_conn;
 
 					initPQExpBuffer(&event_details);
 					appendPQExpBuffer(&event_details,
@@ -3007,7 +3112,6 @@ do_primary_failover(void)
 											  event_details.data);
 					close_connection(&new_primary_conn);
 					termPQExpBuffer(&event_details);
-
 				}
 				failover_state = FAILOVER_STATE_REQUIRES_MANUAL_FAILOVER;
 			}
@@ -3674,6 +3778,7 @@ promote_self(void)
 
 	{
 		PQExpBufferData event_details;
+		t_event_info event_info = T_EVENT_INFO_INITIALIZER;
 
 		/* update own internal node record */
 		record_status = get_node_record(local_conn, local_node_info.node_id, &local_node_info);
@@ -3690,13 +3795,16 @@ promote_self(void)
 						  failed_primary.node_name,
 						  failed_primary.node_id);
 
+		event_info.node_id = failed_primary.node_id;
+
 		/* local_conn is now the primary connection */
-		create_event_notification(local_conn,
-								  &config_file_options,
-								  local_node_info.node_id,
-								  "repmgrd_failover_promote",
-								  true,
-								  event_details.data);
+		create_event_notification_extended(local_conn,
+										   &config_file_options,
+										   local_node_info.node_id,
+										   "repmgrd_failover_promote",
+										   true,
+										   event_details.data,
+										   &event_info);
 
 		termPQExpBuffer(&event_details);
 	}

repmgrd-physical.h

@@ -19,7 +19,7 @@
 #ifndef _REPMGRD_PHYSICAL_H_
 #define _REPMGRD_PHYSICAL_H_
 
-void		do_physical_node_check(void);
+void		do_physical_node_check(PGconn *conn);
 
 void		monitor_streaming_primary(void);
 void		monitor_streaming_standby(void);

repmgrd.c

@@ -396,13 +396,14 @@ main(int argc, char **argv)
 		 * extension is the latest available according to "pg_available_extensions" -
 		 * - does our (major) version match that?
 		 */
-		log_verbose(LOG_DEBUG, "binary version: %i; extension version: %i",
-					REPMGR_VERSION_NUM, extversions.installed_version_num);
-		if ((REPMGR_VERSION_NUM/100) < (extversions.installed_version_num / 100))
+		log_verbose(LOG_DEBUG, "expected extension version: %i; extension version: %i",
+					REPMGR_EXTENSION_NUM, extversions.installed_version_num);
+		if ((REPMGR_EXTENSION_NUM/100) < (extversions.installed_version_num / 100))
 		{
 			log_error(_("this \"repmgr\" version is older than the installed \"repmgr\" extension version"));
-			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
+			log_detail(_("\"repmgr\" version %s providing extension version %s is installed but extension is version %s"),
 					   REPMGR_VERSION,
+					   REPMGR_EXTENSION_VERSION,
 					   extversions.installed_version);
 			log_hint(_("update the repmgr binaries to match the installed extension version"));
 
@@ -410,11 +411,12 @@ main(int argc, char **argv)
 			exit(ERR_BAD_CONFIG);
 		}
 
-		if ((REPMGR_VERSION_NUM/100) > (extversions.installed_version_num / 100))
+		if ((REPMGR_EXTENSION_NUM/100) > (extversions.installed_version_num / 100))
 		{
 			log_error(_("this \"repmgr\" version is newer than the installed \"repmgr\" extension version"));
-			log_detail(_("\"repmgr\" version %s is installed but extension is version %s"),
+			log_detail(_("\"repmgr\" version %s providing extension version %s is installed but extension is version %s"),
 					   REPMGR_VERSION,
+					   REPMGR_EXTENSION_VERSION,
 					   extversions.installed_version);
 			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\" in the repmgr database"));
 
@@ -477,7 +479,7 @@ main(int argc, char **argv)
 		switch (config_file_options.replication_type)
 		{
 			case REPLICATION_TYPE_PHYSICAL:
-				log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
+				log_hint(_("check that 'repmgr (primary|standby|witness) register' was executed for this node"));
 				break;
 		}
 
@@ -510,7 +512,7 @@ main(int argc, char **argv)
 		log_debug("node id is %i, upstream node id is %i",
 				  local_node_info.node_id,
 				  local_node_info.upstream_node_id);
-		do_physical_node_check();
+		do_physical_node_check(local_conn);
 	}
 
 	if (daemonize == true)

strutil.c

@@ -369,7 +369,6 @@ check_status_list_free(CheckStatusList *list)
 }
 
 
-
 const char *
 output_check_status(CheckStatus status)
 {