Add dummy include file

This is a workaround required to facilitate Debian package builds
against PostgreSQL Extended.

CONTRIBUTING.md

@@ -2,7 +2,7 @@ License and Contributions
 =========================
 
 `repmgr` is licensed under the GPL v3.  All of its code and documentation is
-Copyright 2010-2020, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+Copyright 2010-2021, EnterpriseDB Corporation.  See the files COPYRIGHT and LICENSE for
 details.
 
 The development of repmgr has primarily been sponsored by 2ndQuadrant customers.
@@ -12,10 +12,10 @@ which has received funding from the European Union's Seventh Framework Programme
 (FP7/2007-2013) under grant agreement 258862.
 
 Contributions to `repmgr` are welcome, and will be listed in the file `CREDITS`.
-2ndQuadrant Limited requires that any contributions provide a copyright
+EnterpriseDB Corporation requires that any contributions provide a copyright
 assignment and a disclaimer of any work-for-hire ownership claims from the
 employer of the developer.  This lets us make sure that all of the repmgr
-distribution remains free code.  Please contact info@2ndQuadrant.com for a
+distribution remains free code.  Please contact info@enterprise.com for a
 copy of the relevant Copyright Assignment Form.
 
 Code style

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2020, 2ndQuadrant Limited
+Copyright (c) 2010-2021, EnterpriseDB Corporation
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

FAQ.md

@@ -5,6 +5,6 @@ The repmgr 4 FAQ is located here: [repmgr FAQ (Frequently Asked Questions)](http
 
 The repmgr 3.x FAQ can be found here:
 
-    https://github.com/2ndQuadrant/repmgr/blob/REL3_3_STABLE/FAQ.md
+    https://github.com/EnterpriseDB/repmgr/blob/REL3_3_STABLE/FAQ.md
 
 Note that repmgr 3.x is no longer supported.

HISTORY

@@ -1,4 +1,25 @@
-5.2.0   2020-??-??
+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)
+
+5.2.1   2020-12-07
+        config: fix parsing of "replication_type"; GitHub #672 (Ian)
+        standby clone: handle missing "postgresql.auto.conf" (Ian)
+        standby clone: add option --recovery-min-apply-delay (Ian)
+        standby clone: fix data directory permissions handling for
+          PostgreSQL 11 and later (Ian)
+        repmgrd: prevent termination when local node not available and
+          standby_disconnect_on_failover; GitHub #675 (Ian)
+        repmgrd: ensure reconnect_interval" is correctly handled;
+          GitHub #673 (Ian)
+
+5.2.0   2020-10-22
         general: add support for PostgreSQL 13 (Ian)
         general: remove support for PostgreSQL 9.3 (Ian)
         config: add support for file inclusion directives (Ian)
@@ -32,7 +53,7 @@
         repmgr: ensure postgresql.auto.conf is created with correct permissions (Ian)
         repmgr: minimize requirement to check upstream data directory location
           during "standby clone" (Ian)
-        repmgr: warn about missing pg_rewind prerequisites when excuting
+        repmgr: warn about missing pg_rewind prerequisites when executing
           "standby clone" (Ian)
         repmgr: add --upstream option to "node check"
         repmgr: report error code on follow/rejoin failure due to non-available

Makefile.in

@@ -12,6 +12,8 @@ EXTENSION = repmgr
 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 \
@@ -26,7 +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
 
@@ -75,10 +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) $(LIBS) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
 
 repmgrd: $(REPMGRD_OBJS)
-	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
 
 $(REPMGR_CLIENT_OBJS): $(HEADERS)
 $(REPMGRD_OBJS): $(HEADERS)

README.md

@@ -7,10 +7,10 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-PostgreSQL 12, 11, 10, 9.6 and 9.5 are fully supported.
-PostgreSQL 9.4 and 9.3 are supported, with some restrictions.
+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.
 
-`repmgr` is distributed under the GNU GPL 3 and maintained by 2ndQuadrant.
+`repmgr` is distributed under the GNU GPL 3 and maintained by EnterpriseDB.
 
 Documentation
 -------------
@@ -21,10 +21,11 @@ The full `repmgr` documentation is available here:
 
 The old `README` file for `repmgr` 3.x is available here:
 
-> https://github.com/2ndQuadrant/repmgr/blob/REL3_3_STABLE/README.md
+> 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 as soon as possible.
+please upgrade to the [current repmgr version](https://repmgr.org/docs/current/appendix-release-notes.html)
+as soon as possible.
 
 Versions
 --------
@@ -54,11 +55,11 @@ Directories
 Support and Assistance
 ----------------------
 
-2ndQuadrant provides 24x7 production support for `repmgr`, including
+EnterpriseDB provides 24x7 production support for `repmgr`, including
 configuration assistance, installation verification and training for
 running a robust replication cluster. For further details see:
 
-* https://2ndquadrant.com/en/support/
+* [EDB Support Services](https://www.enterprisedb.com/support/postgresql-support-overview-get-the-most-out-of-postgresql)
 
 There is a mailing list/forum to discuss contributions or issues:
 
@@ -68,23 +69,12 @@ The IRC channel #repmgr is registered with freenode.
 
 Please report bugs and other issues to:
 
-* https://github.com/2ndQuadrant/repmgr
-
-See 
+* https://github.com/EnterpriseDB/repmgr
 
 Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
-news are always welcome. Send us an email at info@2ndQuadrant.com, or
-send a postcard to
-
-    repmgr
-    c/o 2ndQuadrant
-    7200 The Quorum
-    Oxford Business Park North
-    Oxford
-    OX4 2JZ
-    United Kingdom
+news are always welcome.
 
 Thanks from the repmgr core team.
 
@@ -100,7 +90,4 @@ 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/)
-* https://blog.2ndquadrant.com/repmgr-3-2-is-here-barman-support-brand-new-high-availability-features/
-* https://blog.2ndquadrant.com/improvements-in-repmgr-3-1-4/
-* https://blog.2ndquadrant.com/managing-useful-clusters-repmgr/
-* https://blog.2ndquadrant.com/easier_postgresql_90_clusters/
+* [How to implement repmgr for PostgreSQL automatic failover](https://www.enterprisedb.com/postgres-tutorials/how-implement-repmgr-postgresql-automatic-failover)

TODO.md

@@ -1,7 +1,7 @@
 TODO
 ====
 
-This file contains a list of improvements which are desireable and/or have
+This file contains a list of improvements which are desirable and/or have
 been requested, and which we aim to address/implement when time and resources
 permit.
 
@@ -17,4 +17,4 @@ repmgrd nodes to prevent unintended failover; this is obviously inconvenient.
 We'll need to implement some way of notifying each repmgrd to suspend automatic
 failover until further notice.
 
-Requested in GitHub #410 ( https://github.com/2ndQuadrant/repmgr/issues/410 )
+Requested in GitHub #410 ( https://github.com/EnterpriseDB/repmgr/issues/410 )

bdr_api_version.h

@@ -0,0 +1,7 @@
+/*
+ * bdr_version_api.h
+ *
+ * This is a dummy file to facilitated building Debian packages against
+ * PostgreSQL Extended. It may be removed in the future. Do not add any
+ * code to this file.
+ */

compat.c

@@ -6,7 +6,7 @@
  *    supported PostgreSQL versions. They're unlikely to change but
  *    it would be worth keeping an eye on them for any fixes/improvements.
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

compat.h

@@ -1,6 +1,6 @@
 /*
  * compat.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

configdata.c

@@ -1,7 +1,7 @@
 /*
  * configdata.c - contains structs with parsed configuration data
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -120,10 +120,10 @@ struct ConfigFileSetting config_file_settings[] =
 	/* replication_type */
 	{
 		"replication_type",
-		CONFIG_INT,
-		{ .intptr = &config_file_options.replication_type },
-		{ .intdefault = REPLICATION_TYPE_PHYSICAL },
-		{ .intminval = -1 },
+		CONFIG_REPLICATION_TYPE,
+		{ .replicationtypeptr = &config_file_options.replication_type },
+		{ .replicationtypedefault = DEFAULT_REPLICATION_TYPE },
+		{},
 		{},
 		{}
 	},
@@ -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-scan.l

@@ -107,9 +107,9 @@ ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList
 
 
 extern bool
-ProcessPostgresConfigFile(const char *config_file, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+ProcessPostgresConfigFile(const char *config_file, const char *base_dir, bool strict, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
 {
-	return ProcessConfigFile(base_dir, config_file, NULL, true, 0, contents, error_list, warning_list);
+	return ProcessConfigFile(base_dir, config_file, NULL, strict, 0, contents, error_list, warning_list);
 }
 
 static bool

configfile.c

@@ -1,7 +1,7 @@
 /*
  * configfile.c - parse repmgr.conf and other configuration-related functionality
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -313,6 +313,9 @@ _parse_config(ItemList *error_list, ItemList *warning_list)
 			case CONFIG_CONNECTION_CHECK_TYPE:
 				*setting->val.checktypeptr = setting->defval.checktypedefault;
 				break;
+			case CONFIG_REPLICATION_TYPE:
+				*setting->val.replicationtypeptr = setting->defval.replicationtypedefault;
+				break;
 			case CONFIG_EVENT_NOTIFICATION_LIST:
 			case CONFIG_TABLESPACE_MAPPING:
 				/* no default for these types; lists cleared above */
@@ -566,6 +569,20 @@ parse_configuration_item(ItemList *error_list, ItemList *warning_list, const cha
 					}
 					break;
 				}
+				case CONFIG_REPLICATION_TYPE:
+				{
+					if (strcasecmp(value, "physical") == 0)
+					{
+						*(ReplicationType *)setting->val.replicationtypeptr = REPLICATION_TYPE_PHYSICAL;
+					}
+					else
+					{
+						item_list_append_format(error_list,
+												_("value for \"%s\" must be \"physical\"\n"),
+												name);
+					}
+					break;
+				}
 				case CONFIG_EVENT_NOTIFICATION_LIST:
 				{
 					parse_event_notifications_list((EventNotificationList *)setting->val.notificationlistptr,
@@ -1394,6 +1411,9 @@ dump_config(void)
 			case CONFIG_CONNECTION_CHECK_TYPE:
 				printf("%s", print_connection_check_type(*setting->val.checktypeptr));
 				break;
+			case CONFIG_REPLICATION_TYPE:
+				printf("%s", print_replication_type(*setting->val.replicationtypeptr));
+				break;
 			case CONFIG_EVENT_NOTIFICATION_LIST:
 			{
 				char *list = print_event_notification_list(setting->val.notificationlistptr);
@@ -1765,7 +1785,7 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 
 	FILE	   *fp;
 	mode_t		um;
-	struct stat auto_conf_st;
+	struct stat data_dir_st;
 
 	KeyValueList config = {NULL, NULL};
 	KeyValueListCell *cell = NULL;
@@ -1776,7 +1796,12 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 	appendPQExpBuffer(&auto_conf, "%s/%s",
 					  data_dir, PG_AUTOCONF_FILENAME);
 
-	success = ProcessPostgresConfigFile(auto_conf.data, NULL, &config, NULL, NULL);
+	success = ProcessPostgresConfigFile(auto_conf.data,
+										NULL,
+										false, /* we don't care if the file does not exist */
+										&config,
+										NULL,
+										NULL);
 
 	if (success == false)
 	{
@@ -1787,7 +1812,7 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 	}
 
 	/*
-	 * Append requested items to items extracted from the existing file.
+	 * Append requested items to any items extracted from the existing file.
 	 */
 	for (cell = items->head; cell; cell = cell->next)
 	{
@@ -1816,27 +1841,46 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 						  cell->key, cell->value);
 	}
 
-	stat(auto_conf.data, &auto_conf_st);
+	/* stat the data directory for the file mode */
+	if (stat(data_dir, &data_dir_st) != 0)
+	{
+		/*
+		 * This is highly unlikely to happen, but if it does (e.g. freak
+		 * race condition with some rogue process which is messing about
+		 * with the data directory), there's not a lot we can do.
+		 */
+		log_error(_("error encountered when checking \"%s\""),
+				  data_dir);
+		log_detail("%s", strerror(errno));
+		exit(ERR_BAD_CONFIG);
+	}
 
 	/*
-	 * Set umask so the temporary file is created in the same mode as the original
-	 * postgresql.auto.conf file.
+	 * Set umask so the temporary file is created in the same mode as the data
+	 * directory. In PostgreSQL 11 and later this can be 0700 or 0750.
 	 */
-	um = umask(~(auto_conf_st.st_mode));
+	um = umask(~(data_dir_st.st_mode));
+
 	fp = fopen(auto_conf_tmp.data, "w");
+
 	umask(um);
 
 	if (fp == NULL)
 	{
-		fprintf(stderr, "unable to open \"%s\": %s\n",
+		fprintf(stderr, "unable to open \"%s\" for writing: %s\n",
 				auto_conf_tmp.data,
 				strerror(errno));
+		success = false;
 	}
 	else
 	{
 		if (fwrite(auto_conf_contents.data, strlen(auto_conf_contents.data), 1, fp) != 1)
 		{
+			fprintf(stderr, "unable to write to \"%s\": %s\n",
+					auto_conf_tmp.data,
+					strerror(errno));
 			fclose(fp);
+			success = false;
 		}
 		else
 		{
@@ -1845,7 +1889,7 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 			/*
 			 * Note: durable_rename() is not exposed to frontend code before Pg 10.
 			 * We only really need to be modifying postgresql.auto.conf from Pg 12,
-			 * but provide backwards compatibitilty for Pg 9.6 and earlier for the
+			 * but provide backwards compatibility for Pg 9.6 and earlier for the
 			 * (unlikely) event that a repmgr built against one of those versions
 			 * is being used against Pg 12 and later.
 			 */
@@ -2167,6 +2211,20 @@ parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_opti
 }
 
 
+const char *
+print_replication_type(ReplicationType type)
+{
+	switch (type)
+	{
+		case REPLICATION_TYPE_PHYSICAL:
+			return "physical";
+	}
+
+	/* should never reach here */
+	return "UNKNOWN";
+}
+
+
 const char *
 print_connection_check_type(ConnectionCheckType type)
 {
@@ -2192,6 +2250,7 @@ print_event_notification_list(EventNotificationList *list)
 	PQExpBufferData buf;
 	char *ptr;
 	EventNotificationListCell *cell;
+	int ptr_len;
 
 	initPQExpBuffer(&buf);
 	cell = list->head;
@@ -2206,8 +2265,10 @@ print_event_notification_list(EventNotificationList *list)
 		cell = cell->next;
 	}
 
-	ptr = palloc0(strlen(buf.data) + 1);
-	strncpy(ptr, buf.data, strlen(buf.data));
+	ptr_len = strlen(buf.data);
+	ptr = palloc0(ptr_len + 1);
+
+	strncpy(ptr, buf.data, ptr_len);
 
 	termPQExpBuffer(&buf);
 

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -50,6 +50,11 @@ typedef enum
 	CHECK_CONNECTION
 } ConnectionCheckType;
 
+typedef enum
+{
+	REPLICATION_TYPE_PHYSICAL
+} ReplicationType;
+
 typedef struct EventNotificationListCell
 {
 	struct EventNotificationListCell *next;
@@ -86,7 +91,8 @@ typedef enum
 	CONFIG_FAILOVER_MODE,
 	CONFIG_CONNECTION_CHECK_TYPE,
 	CONFIG_EVENT_NOTIFICATION_LIST,
-	CONFIG_TABLESPACE_MAPPING
+	CONFIG_TABLESPACE_MAPPING,
+    CONFIG_REPLICATION_TYPE
 } ConfigItemType;
 
 
@@ -103,6 +109,7 @@ typedef struct ConfigFileSetting
 		ConnectionCheckType *checktypeptr;
 		EventNotificationList *notificationlistptr;
 		TablespaceList *tablespacemappingptr;
+		ReplicationType *replicationtypeptr;
 	} val;
 	union {
 		int			intdefault;
@@ -110,6 +117,7 @@ typedef struct ConfigFileSetting
 		bool		booldefault;
 		failover_mode_opt failovermodedefault;
 		ConnectionCheckType checktypedefault;
+		ReplicationType replicationtypedefault;
 	} defval;
 	union {
 		int				intminval;
@@ -138,7 +146,7 @@ typedef struct
 	char		config_directory[MAXPGPATH];
 	char		pg_bindir[MAXPGPATH];
 	char		repmgr_bindir[MAXPGPATH];
-	int			replication_type;
+	ReplicationType	replication_type;
 
 	/* log settings */
 	char		log_level[MAXLEN];
@@ -198,6 +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;
@@ -241,7 +250,7 @@ typedef struct
 	/*
 	 * undocumented settings
 	 *
-	 * These settings are for testing or experimential features
+	 * These settings are for testing or experimental features
 	 * and may be changed without notice.
 	 */
 
@@ -356,6 +365,7 @@ const char *format_failover_mode(failover_mode_opt failover);
 void		exit_with_cli_errors(ItemList *error_list, const char *repmgr_command);
 
 void		print_item_list(ItemList *item_list);
+const char *print_replication_type(ReplicationType type);
 const char *print_connection_check_type(ConnectionCheckType type);
 char 	   *print_event_notification_list(EventNotificationList *list);
 char 	   *print_tablespace_mapping(TablespaceList *tablespacemappingptr);
@@ -364,6 +374,6 @@ extern bool modify_auto_conf(const char *data_dir, KeyValueList *items);
 
 extern bool ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList *error_list, ItemList *warning_list);
 
-extern bool ProcessPostgresConfigFile(const char *config_file, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
+extern bool ProcessPostgresConfigFile(const char *config_file, const char *base_dir, bool strict, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
 
 #endif							/* _REPMGR_CONFIGFILE_H_ */

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 5.2.
+# Generated by GNU Autoconf 2.69 for repmgr 5.3.0.
 #
 # 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) 2010-2020, 2ndQuadrant Ltd.
+# Copyright (c) 2010-2021, EnterpriseDB Corporation
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='5.2'
-PACKAGE_STRING='repmgr 5.2'
+PACKAGE_VERSION='5.3.0'
+PACKAGE_STRING='repmgr 5.3.0'
 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 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.3.0 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:";;
+     short | recursive ) echo "Configuration of repmgr 5.3.0:";;
    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
+repmgr configure 5.3.0
 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) 2010-2020, 2ndQuadrant Ltd.
+Copyright (c) 2010-2021, 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, which was
+It was created by repmgr $as_me 5.3.0, 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
@@ -1824,12 +1824,12 @@ if test "$major_version_num" -lt '10'; then
     version_num_int=$(echo "$version_num"|
                     $SED -e 's/^\([0-9]*\)\.\([0-9]*\)$/\1\2/')
 
-    if test "$version_num_int" -lt '93'; then
+    if test "$version_num_int" -lt '94'; then
         as_fn_error $? "repmgr is not compatible with detected PostgreSQL version: $version_num" "$LINENO" 5
     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, which was
+This file was extended by repmgr $as_me 5.3.0, 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
+repmgr config.status 5.3.0
 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], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.3.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2020, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2021, 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 "$version_num"; then
         AC_MSG_ERROR([could not detect the PostgreSQL version, wrong or broken pg_config?])
@@ -32,12 +32,12 @@ if test "$major_version_num" -lt '10'; then
     version_num_int=$(echo "$version_num"|
                     $SED -e 's/^\([[0-9]]*\)\.\([[0-9]]*\)$/\1\2/')
 
-    if test "$version_num_int" -lt '93'; then
+    if test "$version_num_int" -lt '94'; then
         AC_MSG_ERROR([repmgr is not compatible with detected PostgreSQL version: $version_num])
     fi
 else
     version_num=$(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?])

controldata.c

@@ -2,11 +2,11 @@
  * controldata.c - functions for reading the pg_control file
  *
  * The functions provided here enable repmgr to read a pg_control file
- * in a version-indepent way, even if the PostgreSQL instance is not
+ * in a version-independent way, even if the PostgreSQL instance is not
  * running. For that reason we can't use on the pg_control_*() functions
  * provided in PostgreSQL 9.6 and later.
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -333,7 +333,7 @@ get_controlfile(const char *DataDir)
 		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
 		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
 #else
-		fprintf(stderr, "ERROR: please use a repmgr version built for PostgreSQL 12\n");
+		fprintf(stderr, "ERROR: please use a repmgr version built for PostgreSQL 12 or later\n");
 		exit(ERR_BAD_CONFIG);
 #endif
 	}

controldata.h

@@ -1,6 +1,6 @@
 /*
  * controldata.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

dbutils.c

@@ -1,7 +1,7 @@
 /*
  * dbutils.c - Database connection/management functions
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -730,6 +730,8 @@ validate_conninfo_string(const char *conninfo_str, char **errmsg)
 	if (connOptions == NULL)
 		return false;
 
+	PQconninfoFree(connOptions);
+
 	return true;
 }
 
@@ -1255,7 +1257,7 @@ bool
 pg_reload_conf(PGconn *conn)
 {
 	PGresult   *res = NULL;
-	bool		success = false;
+	bool		success = true;
 
 	res = PQexec(conn, "SELECT pg_catalog.pg_reload_conf()");
 
@@ -4240,7 +4242,7 @@ _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)
 						{
@@ -4825,7 +4827,7 @@ cancel_query(PGconn *conn, int timeout)
  * Wait until current query finishes, ignoring any results.
  * Usually this will be an async query or query cancellation.
  *
- * Returns 1 for success; 0 if any error ocurred; -1 if timeout reached.
+ * Returns 1 for success; 0 if any error occurred; -1 if timeout reached.
  */
 int
 wait_connection_availability(PGconn *conn, int timeout)
@@ -6006,6 +6008,43 @@ 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

@@ -1,7 +1,7 @@
 /*
  * dbutils.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -602,6 +602,9 @@ 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);

dirutil.c

@@ -3,7 +3,7 @@
  * dirmod.c
  *	  directory handling functions
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -109,9 +109,56 @@ create_dir(const char *path)
 
 
 bool
-set_dir_permissions(const char *path)
+set_dir_permissions(const char *path, int server_version_num)
 {
-	return (chmod(path, 0700) != 0) ? false : true;
+	struct stat stat_buf;
+	bool no_group_access =
+		(server_version_num != UNKNOWN_SERVER_VERSION_NUM) &&
+		(server_version_num < 110000);
+	/*
+	 * At this point the path should exist, so this check is very
+	 * much just-in-case.
+	 */
+	if (stat(path, &stat_buf) != 0)
+	{
+		if (errno == ENOENT)
+		{
+			log_warning(_("directory \"%s\" does not exist"), path);
+		}
+		else
+		{
+			log_warning(_("could not read permissions of directory \"%s\""),
+						path);
+			log_detail("%s", strerror(errno));
+		}
+
+		return false;
+	}
+
+	/*
+	 * If mode is not 0700 or 0750, attempt to change.
+	 */
+	if ((no_group_access == true  && (stat_buf.st_mode & (S_IRWXG | S_IRWXO)))
+	 || (no_group_access == false && (stat_buf.st_mode & (S_IWGRP | S_IRWXO))))
+	{
+		/*
+		 * Currently we default to 0700.
+		 * There is no facility to override this directly,
+		 * but the user can manually create the directory with
+		 * the desired permissions.
+		 */
+
+		if (chmod(path, 0700) != 0) {
+			log_error(_("unable to change permissions of directory \"%s\""), path);
+			log_detail("%s", strerror(errno));
+			return false;
+		}
+
+		return true;
+	}
+
+	/* Leave as-is */
+	return true;
 }
 
 
@@ -158,7 +205,7 @@ mkdir_p(char *path, mode_t omode)
 			/*
 			 * POSIX 1003.2: For each dir operand that does not name an
 			 * existing directory, effects equivalent to those caused by the
-			 * following command shall occcur:
+			 * following command shall occur:
 			 *
 			 * mkdir -p -m $(umask -S),u+wx $(dirname dir) && mkdir [-m mode]
 			 * dir
@@ -242,7 +289,7 @@ is_pg_running(const char *path)
 	{
 		/*
 		 * No PID file - PostgreSQL shouldn't be running. From 9.3 (the
-		 * earliesty version we care about) removal of the PID file will
+		 * earliest version we care about) removal of the PID file will
 		 * cause the postmaster to shut down, so it's highly unlikely
 		 * that PostgreSQL will still be running.
 		 */
@@ -303,7 +350,7 @@ create_pg_dir(const char *path, bool force)
 	switch (check_dir(path))
 	{
 		case DIR_NOENT:
-			/* directory does not exist, attempt to create it */
+			/* Directory does not exist, attempt to create it. */
 			log_info(_("creating directory \"%s\"..."), path);
 
 			if (!create_dir(path))
@@ -314,14 +361,23 @@ create_pg_dir(const char *path, bool force)
 			}
 			break;
 		case DIR_EMPTY:
-			/* exists but empty, fix permissions and use it */
+			/*
+			 * Directory exists but empty, fix permissions and use it.
+			 *
+			 * Note that at this point the caller might not know the server
+			 * version number, so in this case "set_dir_permissions()" will
+			 * accept 0750 as a valid setting. As this is invalid in Pg10 and
+			 * earlier,  the caller should call "set_dir_permissions()" again
+			 * when it has the number.
+			 *
+			 * We need to do the permissions check here in any case to catch
+			 * fatal permissions early.
+			 */
 			log_info(_("checking and correcting permissions on existing directory \"%s\""),
 					 path);
 
-			if (!set_dir_permissions(path))
+			if (!set_dir_permissions(path, UNKNOWN_SERVER_VERSION_NUM))
 			{
-				log_error(_("unable to change permissions of directory \"%s\""), path);
-				log_detail("%s", strerror(errno));
 				return false;
 			}
 			break;

dirutil.h

@@ -1,6 +1,6 @@
 /*
  * dirutil.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,7 +35,7 @@ typedef enum
 } PgDirState;
 
 extern int	mkdir_p(char *path, mode_t omode);
-extern bool set_dir_permissions(const char *path);
+extern bool set_dir_permissions(const char *path, int server_version_num);
 
 extern DataDirState	check_dir(const char *path);
 extern bool create_dir(const char *path);

doc/Makefile

@@ -95,6 +95,7 @@ clean:
 	rm -f repmgr.html
 	rm -f repmgr-A4.pdf
 	rm -f repmgr-US.pdf
+	rm -f *.fo
 	rm -f html/*
 
 maintainer-clean:

doc/appendix-faq.xml

@@ -62,7 +62,7 @@
 
       <tip>
         <para>
-          2ndQuadrant's recommended configuration is to configure
+          Our recommended configuration is to configure
           <ulink url="https://www.pgbarman.org/">Barman</ulink> as a fallback
           source of WAL files, rather than maintain replication slots for
           each standby. See also: <link linkend="cloning-from-barman-restore-command">Using Barman as a WAL file source</link>.
@@ -127,7 +127,7 @@
         filesystem layouts.
       </para>
       <para>
-        Either use PostgreSQL packages provided by the community or 2ndQuadrant; if this
+        Either use PostgreSQL packages provided by the community or EnterpriseDB; if this
         is not possible, contact your vendor for assistance.
       </para>
     </sect2>
@@ -170,7 +170,7 @@
       <para>
         If different &quot;minor&quot; &repmgr; versions (e.g. 4.1.1 and 4.1.6) are installed,
         &repmgr; will function, but we strongly recommend always running the same version
-        to ensure there are no unexpected suprises, e.g. a newer version behaving slightly
+        to ensure there are no unexpected surprises, e.g. a newer version behaving slightly
         differently to the older version.
       </para>
       <para>
@@ -212,11 +212,11 @@
       </para>
     </sect2>
 
-    <sect2 id="faq-third-party-packages" xreflabel="Compatability with third party vendor packages">
+    <sect2 id="faq-third-party-packages" xreflabel="Compatibility with third party vendor packages">
       <title>Are &repmgr; packages compatible with <literal>$third_party_vendor</literal>'s packages?</title>
       <para>
-        &repmgr; packages provided by 2ndQuadrant are compatible with the community-provided PostgreSQL
-        packages and any software provided by 2ndQuadrant.
+        &repmgr; packages provided by EnterpriseDB are compatible with the community-provided PostgreSQL
+        packages and specified software provided by EnterpriseDB.
       </para>
       <para>
         A number of other vendors provide their own versions of PostgreSQL packages, often with different
@@ -311,7 +311,7 @@
       </para>
     </sect2>
 
-    <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
+    <sect2 id="faq-repmgr-shared-preload-libraries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
       <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
         in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
       <para>
@@ -459,7 +459,7 @@
       </title>
       <para>
         <varname>promote_command</varname> or <varname>follow_command</varname> can be user-defined scripts,
-        so &repmgr; will not apply <option>pg_bindir</option> even if excuting &repmgr;. Always provide the full
+        so &repmgr; will not apply <option>pg_bindir</option> even if executing &repmgr;. Always provide the full
         path; see <xref linkend="repmgrd-automatic-failover-configuration"/> for more details.
       </para>
     </sect2>
@@ -479,7 +479,7 @@
         is out-of-date, which may lead to incorrect failover behaviour.
       </para>
       <para>
-        The onus is therefore on the adminstrator to manually set the cluster to a stable, healthy state before
+        The onus is therefore on the administrator to manually set the cluster to a stable, healthy state before
         starting &repmgrd;.
       </para>
     </sect2>

doc/appendix-packages.xml

@@ -52,8 +52,7 @@
       <para>
         &repmgr; packages are available from the public 2ndQuadrant repository, and also the
         PostgreSQL community repository. The 2ndQuadrant repository is updated immediately
-        after each
-        &repmgr; release.
+        after each &repmgr; release.
       </para>
 
       <table id="centos-2ndquadrant-repository">
@@ -398,7 +397,7 @@
     </indexterm>
     <indexterm>
       <primary>packages</primary>
-      <secondary>snaphots</secondary>
+      <secondary>snapshots</secondary>
     </indexterm>
 
     <para>
@@ -439,7 +438,7 @@ curl https://dl.2ndquadrant.com/default/snapshot/get/9.6/rpm | sudo bash</progra
       The package name will be formatted like this:
       <programlisting>
 repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
-      containg the snapshot build number (here: <literal>320</literal>) and the hash
+      containing the snapshot build number (here: <literal>320</literal>) and the hash
       of the <application>git</application> commit it was built from (here: <literal>g5113ab0</literal>).
     </para>
 

doc/appendix-release-notes.xml

@@ -16,16 +16,202 @@
   </para>
 
 <!-- remember to update the release date in ../repmgr_version.h.in -->
+  <sect1 id="release-5.3.0">
+    <title id="release-current">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>
+    <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>:
+              if using <option>--replication-conf-only</option> on a node
+              which was set up without replication slots, but the &repmgr; configuration
+              was since changed to <option>use_replication_slots=1</option>,
+              &repmgr; will now set <varname>slot_name</varname> in the
+              node record, if it was previously empty.
+            </para>
+           </listitem>
+
+
+           <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>
+      </para>
+    </sect2>
+  </sect1>
+
+  <sect1 id="release-5.2.1">
+    <title>Release 5.2.1</title>
+    <para><emphasis>Mon 7 December, 2020</emphasis></para>
+
+    <para>
+      &repmgr; 5.2.1 is a minor release.
+    </para>
+    <sect2>
+      <title>Improvements</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>:
+              option <option>--recovery-min-apply-delay</option> added, overriding any
+              setting present in <filename>repmgr.conf</filename>.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+         <itemizedlist>
+          <listitem>
+            <para>
+              Configuration: fix parsing of <option>replication_type</option> configuration parameter.  GitHub #672.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>:
+              handle case where <filename>postgresql.auto.conf</filename> is absent on the
+              source node.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>:
+              in PostgreSQL 11 and later, an existing data directory's permissions
+              will not be changed to <option>0700</option> if they are already set to
+              <option>0750</option>.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgrd;: prevent termination when local node not available and
+              <option>standby_disconnect_on_failover</option> is set.  GitHub #675.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: ensure <option>reconnect_interval</option> is correctly handled.
+              GitHub #673.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <command>repmgr witness --help</command>: fix <command>witness unregister</command>
+              description.  GitHub #676.
+            </para>
+          </listitem>
+
+       </itemizedlist>
+      </para>
+    </sect2>
+  </sect1>
+
 
   <sect1 id="release-5.2.0">
     <title>Release 5.2.0</title>
-    <para><emphasis>??? ?? ???, 2020</emphasis></para>
+    <para><emphasis>Thu 22 October, 2020</emphasis></para>
 
     <para>
       &repmgr; 5.2.0 is a major release.
     </para>
     <para>
-      This release provides support for <ulink url="https://www.postgresql.org/docs/13/release-13.htmll">PostgreSQL 13</ulink>, released in September 2020.
+      This release provides support for <ulink url="https://www.postgresql.org/docs/13/release-13.html">PostgreSQL 13</ulink>, released in September 2020.
     </para>
     <para>
       This release removes support for PostgreSQL 9.3, which was
@@ -220,7 +406,7 @@
   </sect1>
 
   <sect1 id="release-5.1.0">
-    <title id="release-current">Release 5.1.0</title>
+    <title>Release 5.1.0</title>
     <para><emphasis>Mon 13 April, 2020</emphasis></para>
 
     <para>
@@ -1123,7 +1309,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             </para>
             <para>
               Possible values are <literal>ping</literal> (default; uses <command>PQping()</command> to
-              determine server availability), <literal>connection</literal> (attempst to make a new connection to
+              determine server availability), <literal>connection</literal> (attempts to make a new connection to
               the upstream node), and <literal>query</literal> (determines server availability
               by executing an SQL statement on the node via the existing connection).
             </para>

doc/appendix-support.xml

@@ -20,7 +20,7 @@
     A mailing list/forum is provided via Google groups to discuss contributions or issues: <ulink url="https://groups.google.com/group/repmgr">https://groups.google.com/group/repmgr</ulink>.
   </para>
   <para>
-    Please report bugs and other issues to: <ulink url="https://github.com/2ndQuadrant/repmgr">https://github.com/2ndQuadrant/repmgr</ulink>.
+    Please report bugs and other issues to: <ulink url="https://github.com/EnterpriseDB/repmgr">https://github.com/EnterpriseDB/repmgr</ulink>.
   </para>
 
   <important>
@@ -64,7 +64,7 @@
 
      <listitem>
       <simpara>
-        <filename>repmpgr.conf</filename> files (suitably anonymized if necessary)
+        <filename>repmgr.conf</filename> files (suitably anonymized if necessary)
       </simpara>
      </listitem>
 

doc/cloning-standbys.xml

@@ -319,7 +319,7 @@ description = "Main cluster"
     Cascading replication, introduced with PostgreSQL 9.2, enables a standby server
     to replicate from another standby server rather than directly from the primary,
     meaning replication changes "cascade" down through a hierarchy of servers. This
-    can be used to reduce load on the primary and minimize bandwith usage between
+    can be used to reduce load on the primary and minimize bandwidth usage between
     sites. For more details, see the
     <ulink url="https://www.postgresql.org/docs/current/warm-standby.html#CASCADING-REPLICATION">
     PostgreSQL cascading replication documentation</ulink>.
@@ -391,7 +391,7 @@ description = "Main cluster"
      cluster, you may wish to clone a downstream standby whose upstream node
      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 explictly set the upstream's <varname>primary_conninfo</varname> string
+     to explicitly set the upstream's <varname>primary_conninfo</varname> string
      in <filename>recovery.conf</filename>.
     </simpara>
    </tip>

doc/configuration-file-optional-settings.xml

@@ -7,6 +7,14 @@
     <secondary>optional settings</secondary>
   </indexterm>
 
+  <note>
+    <simpara>
+      This section documents a subset of optional configuration settings; for a full
+      for a full and annotated view of all configuration options see the
+      see the <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">sample repmgr.conf file</ulink>
+    </simpara>
+  </note>
+
   <variablelist>
 
 
@@ -132,5 +140,50 @@ ssh_options='-q -o ConnectTimeout=10'</programlisting>
       </listitem>
     </varlistentry>
 
+    <varlistentry id="repmgr-conf-pg-bindir" xreflabel="pg_bindir">
+      <term><varname>pg_bindir</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>pg_bindir</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Path to the PostgreSQL binary directory (location of <application>pg_ctl</application>,
+          <application>pg_basebackup</application> etc.). Only required
+	  if these are not in the system <varname>PATH</varname>.
+        </para>
+        <tip>
+          <para>
+            When &repmgr; is executed via <application>SSH</application> (e.g. when running
+            <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
+            <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command> or
+            <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command>,
+            or if it is executed as cronjob), a login shell will not be used and only the
+            default system <varname>PATH</varname> will be set. Therefore it's recommended to set
+            <varname>pg_bindir</varname> so &repmgr; can correctly invoke binaries on a remote
+            system and avoid potential path issues.
+          </para>
+        </tip>
+
+        <para>
+          Debian/Ubuntu users: you will probably need to  set this to the directory where
+          <application>pg_ctl</application> is located, e.g. <filename>/usr/lib/postgresql/9.6/bin/</filename>.
+        </para>
+        <para>
+          <emphasis>NOTE</emphasis>: <varname>pg_bindir</varname> is only used when &repmgr; directly
+	  executes PostgreSQL binaries; any user-defined scripts
+	  <emphasis>must</emphasis> be specified with the full path.
+        </para>
+
+      </listitem>
+    </varlistentry>
   </variablelist>
+
+  <tip>
+    <simpara>
+      See the <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">sample repmgr.conf file</ulink>
+      for a full and annotated view of all configuration options.
+    </simpara>
+  </tip>
+
 </sect1>

doc/configuration-file-required-settings.xml

@@ -96,6 +96,9 @@
   </variablelist>
  </para>
 
+ <para>
+   See <xref linkend="configuration-file-optional-settings"/> for further configuration options.
+ </para>
 
 
 </sect1>

doc/configuration-file-service-commands.xml

@@ -27,7 +27,9 @@
   <note>
     <para>
       If using <application>systemd</application>, ensure you have <varname>RemoveIPC</varname> set to <literal>off</literal>.
-      See the <ulink url="https://wiki.postgresql.org/wiki/Systemd">systemd</ulink>
+      See the <ulink url="https://www.postgresql.org/docs/current/index.html">PostgreSQL documentation</ulink> section
+      <ulink url="https://www.postgresql.org/docs/current/kernel-resources.html#SYSTEMD-REMOVEIPC">systemd RemoveIPC</ulink>
+      and also the <ulink url="https://wiki.postgresql.org/wiki/Systemd">systemd</ulink>
       entry in the <ulink url="https://wiki.postgresql.org/wiki/Main_Page">PostgreSQL wiki</ulink> for details.
     </para>
   </note>

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-requirements.xml

@@ -93,7 +93,7 @@
     <table id="repmgr-compatibility-matrix">
       <title>&repmgr; compatibility matrix</title>
 
-      <tgroup cols="3">
+      <tgroup cols="4">
         <thead>
           <row>
             <entry>
@@ -112,10 +112,9 @@
         </thead>
 
         <tbody>
-
           <row>
             <entry>
-              &repmgr; 5.2
+              &repmgr; 5.3
             </entry>
             <entry>
               YES
@@ -123,6 +122,21 @@
             <entry>
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
+            <entry>
+              9.4, 9.5, 9.6, 10, 11, 12, 13, 14
+            </entry>
+          </row>
+
+          <row>
+            <entry>
+              &repmgr; 5.2
+            </entry>
+            <entry>
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-5.2.0">5.2.0</link> (2020-10-22)
+            </entry>
             <entry>
               9.4, 9.5, 9.6, 10, 11, 12, 13
             </entry>
@@ -133,10 +147,10 @@
               &repmgr; 5.1
             </entry>
             <entry>
-              YES
+              NO
             </entry>
             <entry>
-              <link linkend="release-5.1.0">5.1</link> (2020-04-13)
+              <link linkend="release-5.1.0">5.1.0</link> (2020-04-13)
             </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12

doc/install-source.xml

@@ -178,18 +178,18 @@ deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlist
 
    <para>
     The source for &repmgr; is maintained at
-    <ulink url="https://github.com/2ndQuadrant/repmgr">https://github.com/2ndQuadrant/repmgr</ulink>.
+    <ulink url="https://github.com/EnterpriseDB/repmgr">https://github.com/EnterpriseDB/repmgr</ulink>.
    </para>
 
    <para>
-    There are also tags for each <ulink url="https://github.com/2ndQuadrant/repmgr/releases">&repmgr; release</ulink>, e.g.
-    <literal><ulink url="https://github.com/2ndQuadrant/repmgr/releases/tag/v4.4.0">v4.4.0</ulink></literal>.
+    There are also tags for each <ulink url="https://github.com/EnterpriseDB/repmgr/releases">&repmgr; release</ulink>, e.g.
+    <literal><ulink url="https://github.com/EnterpriseDB/repmgr/releases/tag/v4.4.0">v4.4.0</ulink></literal>.
    </para>
 
    <para>
     Clone the source code using <application>git</application>:
     <programlisting>
-     git clone https://github.com/2ndQuadrant/repmgr</programlisting>
+     git clone https://github.com/EnterpriseDB/repmgr</programlisting>
    </para>
 
    <para>

doc/legal.xml

@@ -3,16 +3,16 @@
 <date>2017</date>
 
 <copyright>
- <year>2010-2020</year>
- <holder>2ndQuadrant, Ltd.</holder>
+ <year>2010-2021</year>
+ <holder>EnterpriseDB Corporation</holder>
 </copyright>
 
 <legalnotice id="legalnotice">
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2020
-  by 2ndQuadrant, Ltd. All rights reserved.
+  <productname>repmgr</productname> is Copyright &copy; 2010-2021
+  by EnterpriseDB Corporation All rights reserved.
  </para>
 
  <para>

doc/quickstart.xml

@@ -284,7 +284,7 @@
 
   <tip>
    <simpara>
-    For Debian-based distributions we recommend explictly setting
+    For Debian-based distributions we recommend explicitly setting
     <option>pg_bindir</option> to the directory where <command>pg_ctl</command> and other binaries
     not in the standard path are located. For PostgreSQL 9.6 this would be <filename>/usr/lib/postgresql/9.6/bin/</filename>.
    </simpara>
@@ -302,7 +302,7 @@
 
   <para>
    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>
     for details of all available configuration parameters.
   </para>
 

doc/repmgr-daemon-start.xml

@@ -25,7 +25,7 @@
     </para>
     <para>
       By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
-      started. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
+      started. This behaviour can be overridden by specifying a different value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
 

doc/repmgr-daemon-stop.xml

@@ -26,7 +26,7 @@
 
     <para>
       By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
-      stopped. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
+      stopped. This behaviour can be overridden by specifying a different value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
     <note>

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

@@ -22,6 +22,10 @@
       This can optionally use <application>pg_rewind</application> to re-integrate
       a node which has diverged from the rest of the cluster, typically a failed primary.
     </para>
+    <para>
+      Note that <command>repmgr node rejoin</command> can only be used to attach
+      a standby to the current primary, not another standby.
+    </para>
 
     <tip>
       <para>
@@ -281,6 +285,7 @@
       <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose --dry-run
+    NOTICE: rejoin target is node "node3" (node ID: 3)
     INFO: replication connection to the rejoin target node was successful
     INFO: local and rejoin target system identifiers match
     DETAIL: system identifier is 6652184002263212600
@@ -339,6 +344,7 @@
         <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind --dry-run
+    NOTICE: rejoin target is node "node3" (node ID: 3)
     INFO: replication connection to the rejoin target node was successful
     INFO: local and rejoin target system identifiers match
     DETAIL: system identifier is 6652460429293670710
@@ -449,15 +455,16 @@
      </para>
      <para>
        Currently it is not possible to resolve this situation using <application>pg_rewind</application>.
-       A <ulink url="https://www.postgresql.org/message-id/flat/CABvVfJU-LDWvoz4-Yow3Ay5LZYTuPD7eSjjE4kGyNZpXC6FrVQ@mail.gmail.com">patch</ulink>
-       has been submitted and will hopefully be included in a forthcoming PostgreSQL minor release.
+       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.
      </para>
      <para>
        As a workaround, start the primary server the standby was previously attached to,
        and ensure the standby can be attached to it. If <application>pg_rewind</application> was actually executed,
        it will have copied in the <filename>.history</filename> file from the target primary server; this must
        be removed. <command>repmgr node rejoin</command> can then be used to attach the standby to the original
-       primary. Ensure any changes pending on the primary have propogated to the standby. Then shut down the primary
+       primary. Ensure any changes pending on the primary have propagated to the standby. Then shut down the primary
        server <emphasis>first</emphasis>, before shutting down the standby. It should then be possible to
        use <command>repmgr node rejoin</command> to attach the standby to the new primary.
      </para>

doc/repmgr-standby-clone.xml

@@ -260,16 +260,29 @@ pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
      upstream node if required.
    </para>
    <para>
-     Note that the upstream node must be running. In PostgreSQL 11 and earlier, an existing
-     <filename>recovery.conf</filename> will not be overwritten unless the
-     <option>-F/--force</option> option is provided.
+     The upstream node must be running so the correct replication configuration can be obtained.
    </para>
    <para>
-     Execute <command>repmgr standby clone --replication-conf-only --dry-run</command>
-     to check the prerequisites for creating the recovery configuration,
-     and display the contents of the configuration which would be added without actually
-	 making any changes.
+     If the standby is running, the replication configuration will not be written unless the
+     <option>-F/--force</option> option is provided.
    </para>
+   <tip>
+     <para>
+       Execute <command>repmgr standby clone --replication-conf-only --dry-run</command>
+       to check the prerequisites for creating the recovery configuration,
+       and display the configuration changes which would be made without actually
+	   making any changes.
+     </para>
+   </tip>
+   <para>
+     In PostgreSQL 13 and later, the PostgreSQL configuration must be reloaded for replication
+     configuration changes to take effect.
+   </para>
+   <para>
+     In PostgreSQL 12 and earlier, the PostgreSQL instance must be restarted for replication
+     configuration changes to take effect.
+   </para>
+
 
   </refsect1>
 
@@ -331,6 +344,25 @@ pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
         </listitem>
       </varlistentry>
 
+
+      <varlistentry>
+        <term><option>--recovery-min-apply-delay</option></term>
+        <listitem>
+          <para>
+            Set PostgreSQL configuration <option>recovery_min_apply_delay</option> parameter
+            to the provided value.
+          </para>
+          <para>
+            This overrides any <option>recovery_min_apply_delay</option> provided via
+            <filename>repmgr.conf</filename>.
+          </para>
+          <para>
+            For more details on this parameter, see:
+            <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-RECOVERY-MIN-APPLY-DELAY">recovery_min_apply_delay</ulink>.
+          </para>
+        </listitem>
+      </varlistentry>
+
       <varlistentry>
         <term><option>-R, --remote-user=USERNAME</option></term>
         <listitem>
@@ -346,14 +378,14 @@ pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
           <para>
             Create recovery configuration for a previously cloned instance.
           </para>
-		  <para>
-			In PostgreSQL 11 and earlier, the replication configuration will be
-			written to <filename>recovery.conf</filename>.
-		  </para>
 		  <para>
 			In PostgreSQL 12 and later, the replication configuration will be
 			written to <filename>postgresql.auto.conf</filename>.
 		  </para>
+		  <para>
+			In PostgreSQL 11 and earlier, the replication configuration will be
+			written to <filename>recovery.conf</filename>.
+		  </para>
         </listitem>
       </varlistentry>
 

doc/repmgr-standby-promote.xml

@@ -189,14 +189,14 @@
               </listitem>
               <listitem>
                 <simpara>
-                  If the promotion candidate has insufficient free walsenders to accomodate the standbys which will
+                  If the promotion candidate has insufficient free walsenders to accommodate the standbys which will
                   be attached to it, the standby will be promoted anyway.
                 </simpara>
               </listitem>
               <listitem>
                 <simpara>
                   If replication slots are in use but the promotion candidate has insufficient free replication slots
-                  to accomodate the standbys which will be attached to it, the standby will be promoted anyway.
+                  to accommodate the standbys which will be attached to it, the standby will be promoted anyway.
                 </simpara>
               </listitem>
             </itemizedlist>

doc/repmgr.xml

@@ -18,7 +18,7 @@
  <title>repmgr &repmgrversion; Documentation</title>
 
  <bookinfo>
-  <corpauthor>2ndQuadrant Ltd</corpauthor>
+  <corpauthor>EnterpriseDB Corporation</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 14.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -38,20 +38,20 @@
 
    <para>
     &repmgr; is developed by
-    <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+    <ulink url="https://2ndquadrant.com">2ndQuadrant (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/2ndQuadrant/repmgr">github</ulink>
+    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 customers contribute funding
+    Multiple 2ndQuadrant (EDB) customers contribute funding
     to make repmgr development possible.
    </para>
 
    <para>
-     &repmgr; is fully supported by 2ndQuadrant's
+     &repmgr; is fully supported by 2ndQuadrant (EDB)'s
      <ulink url="https://www.2ndquadrant.com/en/support/support-postgresql/">24/7 Production Support</ulink>.
-     2ndQuadrant, a Major Sponsor of the PostgreSQL project, continues to develop and maintain &repmgr;.
-     Other organisations as well as individual developers are welcome to participate in the efforts.
+     EnterpriseDB Corporation, 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

@@ -586,7 +586,7 @@ INFO:  node 3 received notification to rerun promotion candidate election
   <sect2 id="repmgrd-primary-child-disconnection-caveats">
 	<title>Standby disconnections monitoring caveats</title>
 	<para>
-	  The follwing caveats should be considered if you are intending to use this functionality.
+	  The following caveats should be considered if you are intending to use this functionality.
 	</para>
 	<para>
 	  <itemizedlist mark="bullet">

doc/repmgrd-configuration.xml

@@ -89,6 +89,10 @@
                   <literal>query</literal> - determines server availability
                   by executing an SQL statement on the node via the existing connection
                 </simpara>
+                <simpara>
+                  The query is a minimal throwaway query - <command>SELECT 1</command> -
+                  which is used to determine that the server can accept queries.
+                </simpara>
               </listitem>
 
             </itemizedlist>
@@ -152,7 +156,7 @@
     </variablelist>
 
       <para>
-        See also <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file.
+        See also <filename><ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file.
       </para>
 
     <sect2 id="repmgrd-automatic-failover-configuration">
@@ -329,7 +333,7 @@
       <title>Optional configuration for automatic failover</title>
 
       <para>
-        The following configuraton options can be use to fine-tune automatic failover:
+        The following configuraton options can be used to fine-tune automatic failover:
       </para>
       <variablelist>
 
@@ -481,6 +485,32 @@
           </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>
@@ -539,7 +569,7 @@
       </indexterm>
       <para>
         For further details and a reference implementation, see the separate document
-        <ulink url="https://github.com/2ndQuadrant/repmgr/blob/master/doc/repmgrd-node-fencing.md">Fencing a failed master node with repmgrd and PgBouncer</ulink>.
+        <ulink url="https://github.com/EnterpriseDB/repmgr/blob/master/doc/repmgrd-node-fencing.md">Fencing a failed master node with repmgrd and PgBouncer</ulink>.
       </para>
     </sect2>
 
@@ -969,7 +999,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
       </para>
       <para>
         If none of the above apply, &repmgrd; will create a PID file
-        in the operating system's temporary directory (as setermined by the environment variable
+        in the operating system's temporary directory (as determined by the environment variable
         <varname>TMPDIR</varname>, or if that is not set, will use <filename>/tmp</filename>).
       </para>
       <para>
@@ -1049,6 +1079,29 @@ 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/switchover.xml

@@ -120,16 +120,19 @@
    </important>
 
    <note>
-    <simpara>
+    <para>
      On <literal>systemd</literal> systems we strongly recommend using the appropriate
      <command>systemctl</command> commands (typically run via <command>sudo</command>) to ensure
      <literal>systemd</literal> is informed about the status of the PostgreSQL service.
-    </simpara>
-    <simpara>
+    </para>
+    <para>
      If using <command>sudo</command> for the <command>systemctl</command> calls, make sure the
      <command>sudo</command> specification doesn't require a real tty for the user. If not set
      this way, <command>repmgr</command> will fail to stop the primary.
-    </simpara>
+    </para>
+    <para>
+      See the <xref linkend="configuration-file-service-commands"/> documentation section for further details.
+    </para>
    </note>
 
    <para>

doc/upgrading-repmgr.xml

@@ -482,7 +482,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
      <simpara>
       If you don't care about any data from the existing &repmgr; installation,
       (e.g. the contents of the <structname>events</structname> and <structname>monitoring</structname>
-      tables), the follwing steps can be skipped; proceed to <xref linkend="upgrade-reregister-nodes"/>.
+      tables), the following steps can be skipped; proceed to <xref linkend="upgrade-reregister-nodes"/>.
      </simpara>
     </tip>
 
@@ -497,10 +497,10 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
       <itemizedlist spacing="compact" mark="bullet">
       <listitem>
         <simpara>
-          <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/REL3_3_STABLE/sql/repmgr3.0_repmgr3.1.sql">repmgr3.0_repmgr3.1.sql</ulink></simpara>
+          <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/REL3_3_STABLE/sql/repmgr3.0_repmgr3.1.sql">repmgr3.0_repmgr3.1.sql</ulink></simpara>
       </listitem>
       <listitem>
-        <simpara><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/REL3_3_STABLE/sql/repmgr3.1.1_repmgr3.1.2.sql">repmgr3.1.1_repmgr3.1.2.sql</ulink></simpara>
+        <simpara><ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/REL3_3_STABLE/sql/repmgr3.1.1_repmgr3.1.2.sql">repmgr3.1.1_repmgr3.1.2.sql</ulink></simpara>
       </listitem>
       </itemizedlist>
     </para>
@@ -532,7 +532,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   <sect2>
    <title>Upgrading the repmgr schema (PostgreSQL 13 and later)</title>
    <para>
-     Beginning with PostgreSQL 13, the <command>CREATE EXTENSION ... FROM</command>
+     Beginning with PostgreSQL 13, the <command>CREATE EXTENSION ... FROM unpackaged</command>
      syntax is no longer available. In the unlikely event you have ended up with an
      installation running PostgreSQL 13 or later and containing the legacy &repmgr;
      schema, there is no convenient way of upgrading this; instead you'll just need

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr--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--5.2.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', 'set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_last_seen(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_last_seen()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_upstream_last_seen'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_upstream_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
+  LANGUAGE C STRICT;
+
+/* failover functions */
+
+CREATE FUNCTION notify_follow_primary(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'notify_follow_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_new_primary()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_new_primary'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION reset_voting_status()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'reset_voting_status'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION 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', '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--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-cluster.c

@@ -3,7 +3,7 @@
  *
  * Implements cluster information actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-cluster.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-cluster.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-daemon.c

@@ -2,7 +2,7 @@
  * repmgr-action-daemon.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-daemon.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-daemon.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-node.c

@@ -3,7 +3,7 @@
  *
  * Implements actions available for any kind of node
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,6 +35,7 @@
 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,
@@ -2024,7 +2037,6 @@ 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 +2171,53 @@ 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
  */
@@ -2612,6 +2671,13 @@ do_node_rejoin(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	/*
+	 * Emit a notice about the identity of the rejoin target
+	 */
+	log_notice(_("rejoin target is node \"%s\" (ID: %i)"),
+			   primary_node_record.node_name,
+			   primary_node_record.node_id);
+
 	/* connect to registered primary and check it's not in recovery */
 	primary_conn = establish_db_connection(primary_node_record.conninfo, false);
 
@@ -2813,7 +2879,8 @@ 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)
 				{
@@ -2838,7 +2905,7 @@ 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)
@@ -3562,6 +3629,25 @@ 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)
 {
@@ -3599,11 +3685,12 @@ do_node_help(void)
 	printf(_("  Following options check an individual status:\n"));
 	printf(_("    --archive-ready           number of WAL files ready for archiving\n"));
 	printf(_("    --downstream              whether all downstream nodes are connected\n"));
-	printf(_("    --uptream                 whether the node is connected to its upstream\n"));
+	printf(_("    --upstream                whether the node is connected to its upstream\n"));
 	printf(_("    --replication-lag         replication lag in seconds (standbys only)\n"));
 	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("");
@@ -3617,7 +3704,7 @@ do_node_help(void)
 	printf(_("    --dry-run               check that the prerequisites are met for rejoining the node\n" \
 			 "                              (including usability of \"pg_rewind\" if requested)\n"));
 	printf(_("    --force-rewind[=VALUE]  execute \"pg_rewind\" if necessary\n"));
-	printf(_("                              (9.3 and 9.4 - provide full \"pg_rewind\" path)\n"));
+	printf(_("                              (PostgreSQL 9.4 - provide full \"pg_rewind\" path)\n"));
 
 	printf(_("    --config-files          comma-separated list of configuration files to retain\n" \
 			 "                            after executing \"pg_rewind\"\n"));

repmgr-action-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-primary.c

@@ -3,7 +3,7 @@
  *
  * Implements primary actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-primary.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-primary.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-service.c

@@ -2,7 +2,7 @@
  * repmgr-action-service.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-service.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-service.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-standby.c

@@ -3,7 +3,7 @@
  *
  * Implements standby actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -20,6 +20,7 @@
  */
 
 #include <sys/stat.h>
+#include <time.h>
 
 #include "repmgr.h"
 #include "dirutil.h"
@@ -173,21 +174,6 @@ 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 +201,19 @@ 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 +669,15 @@ 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"));
@@ -733,7 +741,7 @@ do_standby_clone(void)
 			drop_replication_slot_if_exists(source_conn, UNKNOWN_NODE_ID, local_node_record.slot_name);
 		}
 
-		log_error(_("unable to take a base backup of the primary server"));
+		log_error(_("unable to take a base backup of the source server"));
 		log_hint(_("data directory (\"%s\") may need to be cleaned up manually"),
 				 local_data_directory);
 
@@ -763,7 +771,7 @@ do_standby_clone(void)
 			exit(ERR_BAD_CONFIG);
 		}
 
-		appendPQExpBufferStr(&command, " ");
+		appendPQExpBufferChar(&command, ' ');
 
 		/* Somewhat inconsistent, but pg_verifybackup doesn't accept a -D option  */
 		appendShellString(&command,
@@ -838,6 +846,16 @@ do_standby_clone(void)
 			break;
 	}
 
+	/*
+	 * Do a final check on the data directory permissions - if the user
+	 * is cloning into an existing directory set to 0750, and the server
+	 * is Pg10 or earlier, Pg will refuse to start. We might not have
+	 * known the server version when creating the data directory
+	 * (mainly if cloning from Barman with no upstream connection), hence
+	 * the additional check here.
+	 */
+	set_dir_permissions(local_data_directory, source_server_version_num);
+
 	/*
 	 * TODO: It might be nice to provide an option to have repmgr start the
 	 * PostgreSQL server automatically
@@ -1290,6 +1308,64 @@ _do_create_replication_conf(void)
 		PQExpBufferData msg;
 		t_replication_slot slot_info = T_REPLICATION_SLOT_INITIALIZER;
 
+		/*
+		 * Check the node record has slot_name set; if not we'll need to
+		 * update it.
+		 */
+		if (local_node_record.slot_name[0] == '\0')
+		{
+			PGconn	   *primary_conn = NULL;
+
+			create_slot_name(local_node_record.slot_name, local_node_record.node_id);
+
+			/* Check we can connect to the primary so we can update the record */
+
+			if (get_recovery_type(upstream_conn) == RECTYPE_PRIMARY)
+			{
+				primary_conn = upstream_conn;
+			}
+			else
+			{
+				primary_conn = establish_primary_db_connection(upstream_conn, false);
+
+				if (primary_conn == NULL)
+				{
+					log_error(_("unable to connect to primary to update slot name for node \"%s\" (ID: %i)"),
+							  local_node_record.node_name,
+							  local_node_record.node_id);
+					PQfinish(upstream_conn);
+					termPQExpBuffer(&msg);
+					exit(ERR_BAD_CONFIG);
+				}
+			}
+
+			if (runtime_options.dry_run == true)
+			{
+				log_info(_("would set \"slot_name\" for node \"%s\" (ID: %i) to \"%s\""),
+						  local_node_record.node_name,
+						  local_node_record.node_id,
+						  local_node_record.slot_name);
+			}
+			else
+			{
+				bool success = update_node_record_slot_name(primary_conn,
+															local_node_record.node_id,
+															local_node_record.slot_name);
+
+				if (primary_conn != upstream_conn)
+					PQfinish(primary_conn);
+
+				if (success == false)
+				{
+					log_error(_("unable to update slot name for node \"%s\" (ID: %i)"),
+							  local_node_record.node_name,
+							  local_node_record.node_id);
+					PQfinish(upstream_conn);
+					exit(ERR_BAD_CONFIG);
+				}
+			}
+		}
+
 		record_status = get_slot_record(upstream_conn, local_node_record.slot_name, &slot_info);
 
 		/* check if replication slot exists*/
@@ -1444,7 +1520,18 @@ _do_create_replication_conf(void)
 
 			if (node_is_running == true)
 			{
-				log_hint(_("node must be restarted for the new file to take effect"));
+				if (PQserverVersion(upstream_conn) >= 130000)
+				{
+					log_hint(_("configuration must be reloaded for the configuration changes to take effect"));
+				}
+				else if (PQserverVersion(upstream_conn) >= 120000)
+				{
+					log_hint(_("node must be restarted for the configuration changes to take effect"));
+				}
+				else
+				{
+					log_hint(_("node must be restarted for the new file to take effect"));
+				}
 			}
 		}
 	}
@@ -1459,7 +1546,7 @@ _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"));
 			}
@@ -1911,7 +1998,7 @@ do_standby_register(void)
 	/*
 	 * If --upstream-node-id not provided, we're defaulting to the primary as
 	 * upstream node. If local node is available, double-check that it's attached
-	 * to the primary, in case --upstream-node-id was an accidental ommission.
+	 * to the primary, in case --upstream-node-id was an accidental omission.
 	 *
 	 * Currently we'll only do this for newly registered nodes.
 	 */
@@ -1920,7 +2007,7 @@ 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 */
@@ -3374,7 +3461,7 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 					goto cleanup;
 				}
 
-				/* In the unlikley event that fails, we'll fall back to a restart */
+				/* In the unlikely event that fails, we'll fall back to a restart */
 				log_warning(_("unable to reload server configuration"));
 			}
 
@@ -3565,8 +3652,9 @@ 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;
@@ -3583,6 +3671,9 @@ 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;
 
@@ -3605,7 +3696,7 @@ do_standby_switchover(void)
 	 * SANITY CHECKS
 	 *
 	 * We'll be doing a bunch of operations on the remote server (primary to
-	 * be demoted) - careful checks needed before proceding.
+	 * be demoted) - careful checks needed before proceeding.
 	 */
 
 	local_conn = establish_db_connection(config_file_options.conninfo, true);
@@ -3725,24 +3816,24 @@ 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 */
@@ -4087,7 +4178,7 @@ do_standby_switchover(void)
 
 	if (command_success == false || command_output.data[0] == '0')
 	{
-		log_error(_("expected configuration file not found on the demotion candiate \"%s\" (ID: %i)"),
+		log_error(_("expected configuration file not found on the demotion candidate \"%s\" (ID: %i)"),
 				  remote_node_record.node_name,
 				  remote_node_record.node_id);
 		log_detail(_("registered configuration file is \"%s\""),
@@ -4187,7 +4278,7 @@ do_standby_switchover(void)
 				else if (remote_error == REMOTE_ERROR_CONNINFO_PARSE)
 				{
 					/* highly unlikely */
-					log_detail(_("an error was encountered when parsing the \"conninfo\" parameter in \"rempgr.conf\" on node \"%s\" (ID: %i)"),
+					log_detail(_("an error was encountered when parsing the \"conninfo\" parameter in \"repmgr.conf\" on node \"%s\" (ID: %i)"),
 							   remote_node_record.node_name,
 							   remote_node_record.node_id);
 				}
@@ -4690,6 +4781,7 @@ 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));
@@ -4718,7 +4810,7 @@ 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));
@@ -4749,8 +4841,9 @@ 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);
 
@@ -4801,7 +4894,7 @@ 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++;
@@ -4814,7 +4907,7 @@ 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++;
@@ -4835,14 +4928,14 @@ 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);
 
@@ -5142,6 +5235,18 @@ 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).
 	 *
@@ -5267,6 +5372,21 @@ 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);
@@ -5280,78 +5400,161 @@ 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
@@ -5464,7 +5667,7 @@ 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);
 
@@ -5472,7 +5675,7 @@ 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);
 
@@ -5483,7 +5686,7 @@ 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++;
@@ -5492,7 +5695,7 @@ 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));
@@ -5962,19 +6165,22 @@ check_source_server_via_barman()
 
 	initPQExpBuffer(&command_output);
 	maxlen_snprintf(buf,
-					"ssh %s \"psql -Aqt \\\"%s\\\" -c \\\""
+					"psql -AqtX -d \\\"%s\\\" -c \\\""
 					" SELECT conninfo"
 					" FROM repmgr.nodes"
 					" WHERE %s"
 					" AND active IS TRUE"
-					"\\\"\"",
-					config_file_options.barman_host,
+					"\\\"",
 					repmgr_conninfo_buf.data,
 					where_condition);
 
 	termPQExpBuffer(&repmgr_conninfo_buf);
 
-	command_success = local_command(buf, &command_output);
+	command_success = remote_command(config_file_options.barman_host,
+									 runtime_options.remote_user,
+									 buf,
+									 config_file_options.ssh_options,
+									 &command_output);
 
 	if (command_success == false)
 	{
@@ -6773,6 +6979,13 @@ 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);
 
 	/*
@@ -7506,7 +7719,7 @@ stop_backup:
 						if (record_status == RECORD_FOUND)
 						{
 							log_verbose(LOG_INFO,
-										_("replication slot \"%s\" aleady exists on upstream node %i"),
+										_("replication slot \"%s\" already exists on upstream node %i"),
 										local_node_record->slot_name,
 										upstream_node_id);
 						}
@@ -7759,7 +7972,9 @@ static void
 tablespace_data_append(TablespaceDataList *list, const char *name, const char *oid, const char *location)
 {
 	TablespaceDataListCell *cell = NULL;
-
+	int oid_len = strlen(oid);
+	int name_len = strlen(name);
+	int location_len = strlen(location);
 	cell = (TablespaceDataListCell *) pg_malloc0(sizeof(TablespaceDataListCell));
 
 	if (cell == NULL)
@@ -7768,13 +7983,13 @@ tablespace_data_append(TablespaceDataList *list, const char *name, const char *o
 		exit(ERR_OUT_OF_MEMORY);
 	}
 
-	cell->oid = pg_malloc(1 + strlen(oid));
-	cell->name = pg_malloc(1 + strlen(name));
-	cell->location = pg_malloc(1 + strlen(location));
+	cell->oid = pg_malloc0(1 + oid_len);
+	cell->name = pg_malloc0(1 + name_len);
+	cell->location = pg_malloc0(1 + location_len);
 
-	strncpy(cell->oid, oid, 1 + strlen(oid));
-	strncpy(cell->name, name, 1 + strlen(name));
-	strncpy(cell->location, location, 1 + strlen(location));
+	strncpy(cell->oid, oid, oid_len);
+	strncpy(cell->name, name, name_len);
+	strncpy(cell->location, location, location_len);
 
 	if (list->tail)
 		list->tail->next = cell;
@@ -7934,9 +8149,9 @@ 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 */
@@ -7956,20 +8171,17 @@ 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;
 		}
@@ -8908,6 +9120,8 @@ do_standby_help(void)
 #endif
 	printf(_("  --without-barman                    do not clone from Barman even if configured\n"));
 	printf(_("  --replication-conf-only             generate replication configuration for a previously cloned instance\n"));
+	printf(_("  --recovery-min-apply-delay          set PostgreSQL configuration parameter \"recovery_min_apply_delay\"\n" \
+			 "                                      (overrides any setting in repmgr.conf)\n"));
 
 	puts("");
 
@@ -8960,7 +9174,7 @@ do_standby_help(void)
 	printf(_("  --dry-run                           perform checks etc. but don't actually execute switchover\n"));
 	printf(_("  -F, --force                         ignore warnings and continue anyway\n"));
 	printf(_("  --force-rewind[=VALUE]              use \"pg_rewind\" to reintegrate the old primary if necessary\n"));
-	printf(_("                                        (9.3 and 9.4 - provide \"pg_rewind\" path)\n"));
+	printf(_("                                        (PostgreSQL 9.4 - provide \"pg_rewind\" path)\n"));
 
 	printf(_("  -R, --remote-user=USERNAME          database server username for SSH operations (default: \"%s\")\n"), runtime_options.username);
 	printf(_("  -S, --superuser=USERNAME            superuser to use, if repmgr user is not superuser\n"));

repmgr-action-standby.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-standby.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-witness.c

@@ -3,7 +3,7 @@
  *
  * Implements witness actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -560,7 +560,7 @@ void do_witness_help(void)
 
 	printf(_("WITNESS UNREGISTER\n"));
 	puts("");
-	printf(_("  \"witness register\" unregisters a witness node.\n"));
+	printf(_("  \"witness unregister\" unregisters a witness node.\n"));
 	puts("");
 	printf(_("  --dry-run                check prerequisites but don't make any changes\n"));
 	printf(_("  -F, --force              unregister when witness node not running\n"));

repmgr-action-witness.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-witness.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-client-global.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client-global.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -84,7 +84,7 @@ typedef struct
 	bool		fast_checkpoint;
 	bool		rsync_only;
 	bool		no_upstream_connection;
-	char		recovery_min_apply_delay[MAXLEN];
+	char		recovery_min_apply_delay[MAXLEN];	/* overrides setting in repmgr.conf */
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
@@ -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

@@ -1,7 +1,7 @@
 /*
  * repmgr-client.c - Command interpreter for the repmgr package
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This module is a command-line utility to easily setup a cluster of
  * hot standby servers for an HA environment
@@ -122,7 +122,7 @@ main(int argc, char **argv)
 	/*
 	 * Tell the logger we're a command-line program - this will ensure any
 	 * output logged before the logger is initialized will be formatted
-	 * correctly. Can be overriden with "--log-to-file".
+	 * correctly. Can be overridden with "--log-to-file".
 	 */
 	logger_output_mode = OM_COMMAND_LINE;
 
@@ -438,6 +438,11 @@ main(int argc, char **argv)
 				runtime_options.replication_conf_only = true;
 				break;
 
+				/* --recovery-min-apply-delay */
+			case OPT_RECOVERY_MIN_APPLY_DELAY:
+				strncpy(runtime_options.recovery_min_apply_delay, optarg, sizeof(runtime_options.recovery_min_apply_delay));
+				break;
+
 				/* --verify-backup */
 			case OPT_VERIFY_BACKUP:
 				runtime_options.verify_backup = true;
@@ -544,6 +549,10 @@ 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;
@@ -1105,10 +1114,25 @@ main(int argc, char **argv)
 		exit(SUCCESS);
 	}
 
-
-
 	check_cli_parameters(action);
 
+
+	/*
+	 * Command-line parameter --recovery-min-apply-delay overrides the equivalent
+	 * setting in the config file. Note we'll need to parse it here to handle
+	 * any formatting errors.
+	 */
+
+	if (*runtime_options.recovery_min_apply_delay != '\0')
+	{
+		parse_time_unit_parameter("--recovery-min-apply-delay",
+								  runtime_options.recovery_min_apply_delay,
+								  config_file_options.recovery_min_apply_delay,
+								  &cli_errors);
+
+		config_file_options.recovery_min_apply_delay_provided = true;
+	}
+
 	/*
 	 * Sanity checks for command line parameters completed by now; any further
 	 * errors will be runtime ones
@@ -1169,7 +1193,7 @@ main(int argc, char **argv)
 	}
 
 	/*
-	 * Check for configuration file items which can be overriden by runtime
+	 * Check for configuration file items which can be overridden by runtime
 	 * options
 	 * =====================================================================
 	 */
@@ -2715,7 +2739,7 @@ do_help(void)
  *
  * Note:
  *   This is one of two places where superuser rights are required.
- *   We should also consider possible scenarious where a non-superuser
+ *   We should also consider possible scenarios where a non-superuser
  *   has sufficient privileges to install the extension.
  */
 
@@ -2750,7 +2774,7 @@ create_repmgr_extension(PGconn *conn)
 			log_detail(_("version %s is installed but newer version %s is available"),
 					   extversions.installed_version,
 					   extversions.default_version);
-			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\""));
+			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\" in the repmgr database"));
 			return false;
 
 		case REPMGR_INSTALLED:
@@ -2916,7 +2940,7 @@ check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *
 	 * PostgreSQL from a particular PostgreSQL release onwards (e.g. 4.4 with PostgreSQL
 	 * 12 and later due to recovery.conf removal), set MAX_UNSUPPORTED_VERSION and
 	 * MAX_UNSUPPORTED_VERSION_NUM in "repmgr.h" to define the first PostgreSQL
-	 * version which can't be suppored.
+	 * version which can't be supported.
 	 */
 #ifdef MAX_UNSUPPORTED_VERSION_NUM
 	if (conn_server_version_num >= MAX_UNSUPPORTED_VERSION_NUM)
@@ -3641,11 +3665,11 @@ 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);
 }
 
@@ -3653,13 +3677,15 @@ 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));
@@ -4066,7 +4092,7 @@ check_standby_join(PGconn *upstream_conn, t_node_info *upstream_node_record, t_n
 
 			 if (node_attached == NODE_NOT_ATTACHED)
 			 {
-				 log_detail(_("node \"%s\" (ID: %i) is currrently attached to its upstream node in state \"%s\""),
+				 log_detail(_("node \"%s\" (ID: %i) is currently attached to its upstream node in state \"%s\""),
 							upstream_node_record->node_name,
 							standby_node_record->node_id,
 							node_state);

repmgr-client.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -99,6 +99,8 @@
 #define OPT_REPLICATION_CONFIG_OWNER	   1046
 #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
@@ -164,6 +166,7 @@ static struct option long_options[] =
 	{"without-barman", no_argument, NULL, OPT_WITHOUT_BARMAN},
 	{"replication-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
 	{"verify-backup", no_argument, NULL, OPT_VERIFY_BACKUP },
+	{"recovery-min-apply-delay", required_argument, NULL, OPT_RECOVERY_MIN_APPLY_DELAY },
 	/* deprecate this once Pg11 and earlier are unsupported */
 	{"recovery-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
 
@@ -191,6 +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

@@ -1,7 +1,7 @@
 /*
  * repmgr.c - repmgr extension
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This is the actual extension code; see repmgr-client.c for the code which
  * generates the repmgr binary
@@ -88,59 +88,24 @@ void		_PG_fini(void);
 
 static void repmgr_shmem_startup(void);
 
-Datum		set_local_node_id(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(set_local_node_id);
-
-Datum		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);
 
 
 /*
@@ -194,7 +159,7 @@ repmgr_shmem_startup(void)
 	shared_state = NULL;
 
 	/*
-	 * Create or attach to the shared memory state, including hash table
+	 * Create or attach to the shared memory state
 	 */
 	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
 
@@ -233,7 +198,7 @@ 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 +268,7 @@ 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 +285,7 @@ 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 +302,7 @@ 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 +319,7 @@ 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 +342,7 @@ 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 +376,7 @@ 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 +391,7 @@ 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 +427,7 @@ 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 +470,7 @@ 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 +492,7 @@ 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 +700,7 @@ 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

@@ -238,7 +238,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 
 #primary_follow_timeout=60		# The max length of time (in seconds) to wait
 					# for the new primary to become available
-#standby_follow_timeout=15		# The max length of time (in seconds) to wait
+#standby_follow_timeout=30		# The max length of time (in seconds) to wait
 					# for the standby to connect to the primary
 #standby_follow_restart=false		# Restart the standby instead of sending a SIGHUP
 					# (only for PostgreSQL 13 and later)
@@ -301,7 +301,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 
 #connection_check_type=ping		# How to check availability of the upstream node; valid options:
 					#  'ping': use PQping() to check if the node is accepting connections
-					#  'connection': execute a throwaway query on the current connection
+					#  'connection': attempt to make a new connection to the node
 					#  'query': execute an SQL statement on the node via the existing connection
 #reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
@@ -323,7 +323,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for the the local node to restart and become ready to accept connections after
 					# executing "follow_command" (defaults to the value set in "standby_reconnect_timeout")
 
-#monitoring_history=no			# Whether to write monitoring data to the "montoring_history" table
+#monitoring_history=no			# Whether to write monitoring data to the "monitoring_history" table
 #monitor_interval_secs=2		# Interval (in seconds) at which to write monitoring data
 #degraded_monitoring_timeout=-1		# Interval (in seconds) after which repmgrd will terminate if the
 					# server(s) being monitored are no longer available. -1 (default)
@@ -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)

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

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -77,8 +77,6 @@
 #define MIN_SUPPORTED_VERSION		"9.4"
 #define MIN_SUPPORTED_VERSION_NUM	90400
 
-#define REPLICATION_TYPE_PHYSICAL 1
-
 #define UNKNOWN_SERVER_VERSION_NUM -1
 #define UNKNOWN_REPMGR_VERSION_NUM -1
 
@@ -122,6 +120,7 @@
 #define DEFAULT_NODE_REJOIN_TIMEOUT          60  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */
+#define	DEFAULT_REPLICATION_TYPE             REPLICATION_TYPE_PHYSICAL
 #define	DEFAULT_REPLICATION_LAG_WARNING      300 /* seconds */
 #define DEFAULT_REPLICATION_LAG_CRITICAL     600 /* seconds */
 #define DEFAULT_WITNESS_SYNC_INTERVAL        15  /* seconds */
@@ -136,6 +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 "5.2dev"
-#define REPMGR_VERSION_NUM 50200
-#define REPMGR_RELEASE_DATE "2020-XX-XX"
+#define REPMGR_VERSION "5.3.0"
+#define REPMGR_VERSION_NUM 50300
+#define REPMGR_EXTENSION_VERSION "5.3"
+#define REPMGR_EXTENSION_NUM 50300
+#define REPMGR_RELEASE_DATE "2021-10-12"
 #define PG_ACTUAL_VERSION_NUM 

repmgrd-physical.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd-physical.c - physical (streaming) replication functionality for repmgrd
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -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;
+			}
 		}
 	}
 
@@ -737,7 +818,7 @@ check_primary_status(int degraded_monitoring_elapsed)
 			/* refresh our copy of the node record from the primary */
 			record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info);
 
-			/* this is unlikley to happen */
+			/* this is unlikely to happen */
 			if (record_status != RECORD_FOUND)
 			{
 				log_warning(_("unable to retrieve local node record from primary node %i"), primary_node_id);
@@ -1111,7 +1192,7 @@ execute_child_nodes_disconnect_command(NodeInfoList *db_child_node_records, t_ch
 	/* calculate number of connected child nodes */
 	for (cell = db_child_node_records->head; cell; cell = cell->next)
 	{
-		/* exclude witness server from total, if necessay */
+		/* exclude witness server from total, if necessary */
 		if (config_file_options.child_nodes_connected_include_witness == false &&
 			cell->node_info->type == WITNESS)
 			continue;
@@ -1149,7 +1230,7 @@ execute_child_nodes_disconnect_command(NodeInfoList *db_child_node_records, t_ch
 				instr_time  current_time = current_time_base;
 				int seconds_since_detached;
 
-				/* exclude witness server from calculatin if neccessary */
+				/* exclude witness server from calculation, if requested */
 				if (config_file_options.child_nodes_connected_include_witness == false &&
 					child_node_rec->type == WITNESS)
 					continue;
@@ -1813,6 +1894,7 @@ 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 +1907,16 @@ 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);
 
@@ -3254,7 +3340,7 @@ update_monitoring_history(void)
  *
  * Attach cascaded standby to another node, currently the primary.
  *
- * Note that in contrast to a primary failover, where one of the downstrean
+ * Note that in contrast to a primary failover, where one of the downstream
  * standby nodes will become a primary, a cascaded standby failover (where the
  * upstream standby has gone away) is "just" a case of attaching the standby to
  * another node.
@@ -3674,6 +3760,7 @@ 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 +3777,16 @@ 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);
 	}
@@ -3921,6 +4011,7 @@ follow_new_primary(int new_primary_id)
 
 				termPQExpBuffer(&event_details);
 
+				close_connection(&upstream_conn);
 				close_connection(&old_primary_conn);
 
 				return FAILOVER_STATE_PRIMARY_REAPPEARED;
@@ -3931,6 +4022,8 @@ follow_new_primary(int new_primary_id)
 			close_connection(&old_primary_conn);
 		}
 
+		close_connection(&upstream_conn);
+
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}
 
@@ -5381,7 +5474,7 @@ try_primary_reconnect(PGconn **conn, PGconn *local_conn, t_node_info *node_info)
 		time_t started_at = time(NULL);
 		int up_to;
 		bool sleep_now = false;
-		bool max_sleep_seconds;
+		int max_sleep_seconds;
 
 		log_info(_("checking state of node \"%s\" (ID: %i), %i of %i attempts"),
 				 node_info->node_name,

repmgrd-physical.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-physical.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -19,7 +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

@@ -1,7 +1,7 @@
 /*
  * repmgrd.c - Replication manager daemon
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -131,7 +131,7 @@ main(int argc, char **argv)
 
 	memset(pid_file, 0, MAXPGPATH);
 
-	while ((c = getopt_long(argc, argv, "?Vf:L:vdp:m", long_options, &optindex)) != -1)
+	while ((c = getopt_long(argc, argv, "?Vf:L:vdp:sm", long_options, &optindex)) != -1)
 	{
 		switch (c)
 		{
@@ -249,7 +249,7 @@ main(int argc, char **argv)
 	/*
 	 * Parse the configuration file, if provided (if no configuration file was
 	 * provided, an attempt will be made to find one in one of the default
-	 * locations). If no conifguration file is available, or it can't be parsed
+	 * locations). If no configuration file is available, or it can't be parsed
 	 * parse_config() will abort anyway, with an appropriate message.
 	 */
 	load_config(config_file, verbose, false, argv[0]);
@@ -307,7 +307,7 @@ main(int argc, char **argv)
 	}
 
 
-	/* Some configuration file items can be overriden by command line options */
+	/* Some configuration file items can be overridden by command line options */
 
 	/*
 	 * Command-line parameter -L/--log-level overrides any setting in config
@@ -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"));
 
@@ -410,13 +411,14 @@ 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\""));
+			log_hint(_("update the installed extension version by executing \"ALTER EXTENSION repmgr UPDATE\" in the repmgr database"));
 
 			close_connection(&local_conn);
 			exit(ERR_BAD_CONFIG);
@@ -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)

repmgrd.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  */
 
 

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -369,7 +369,6 @@ check_status_list_free(CheckStatusList *list)
 }
 
 
-
 const char *
 output_check_status(CheckStatus status)
 {

strutil.h

@@ -1,6 +1,6 @@
 /*
  * strutil.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

sysutils.c

@@ -3,7 +3,7 @@
  *
  * Functions which need to be executed on the local system.
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -289,10 +289,19 @@ disable_wal_receiver(PGconn *conn)
 
 	if (wal_retrieve_retry_interval < WALRECEIVER_DISABLE_TIMEOUT_VALUE)
 	{
+		bool success;
+
 		log_notice(_("setting \"wal_retrieve_retry_interval\" to %i milliseconds"),
 				   new_wal_retrieve_retry_interval);
 		alter_system_int(conn, "wal_retrieve_retry_interval", new_wal_retrieve_retry_interval);
-		pg_reload_conf(conn);
+
+		success = pg_reload_conf(conn);
+
+		if (success == false)
+		{
+			log_warning(_("unable to reload configuration"));
+			return UNKNOWN_PID;
+		}
 	}
 
 	/*
@@ -354,6 +363,12 @@ enable_wal_receiver(PGconn *conn, bool wait_startup)
 	/* make timeout configurable */
 	int i, timeout = 30;
 
+	if (PQstatus(conn) != CONNECTION_OK)
+	{
+		log_error(_("database connection not available"));
+		return UNKNOWN_PID;
+	}
+
 	if (is_superuser_connection(conn, NULL) == false)
 	{
 		log_error(_("superuser connection required"));
@@ -394,7 +409,13 @@ enable_wal_receiver(PGconn *conn, bool wait_startup)
 			return UNKNOWN_PID;
 		}
 
-		pg_reload_conf(conn);
+		success = pg_reload_conf(conn);
+
+		if (success == false)
+		{
+			log_warning(_("unable to reload configuration"));
+			return UNKNOWN_PID;
+		}
 	}
 	else
 	{

sysutils.h

@@ -1,6 +1,6 @@
 /*
  * sysutils.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

voting.h

@@ -1,6 +1,6 @@
 /*
  * voting.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by