Bump version to 5.1.0

The removal of some extensions functions means it's not possible to
follow the conventional incremental upgrade path; instead we'll
create a script for direct upgrades to 5.1.

CONTRIBUTING.md

@@ -2,7 +2,7 @@ License and Contributions
 =========================
 
 `repmgr` is licensed under the GPL v3.  All of its code and documentation is
-Copyright 2010-2019, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+Copyright 2010-2020, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
 details.
 
 The development of repmgr has primarily been sponsored by 2ndQuadrant customers.

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2019, 2ndQuadrant Limited
+Copyright (c) 2010-2020, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

HISTORY

@@ -1,4 +1,29 @@
-5.0     2019-10-??
+5.1.0   2020-04-13
+        repmgr: remove BDR 2.x support
+        repmgr: don't query upstream's data directory (Ian)
+        repmgr: rename --recovery-conf-only to --replication-conf-only (Ian)
+        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
+          "standby clone" (Ian)
+        repmgr: add --upstream option to "node check"
+        repmgr: report error code on follow/rejoin failure due to non-available
+          replication slot (Ian)
+        repmgr: ensure "node rejoin" checks for available replication slots (Ian)
+        repmgr: improve "standby switchover" completion checks (Ian)
+        repmgr: add replication configuration file ownership check to
+          "standby switchover" (Ian)
+        repmgr: check the demotion candidate's registered repmgr.conf file can
+          be found (laixiong; GitHub 615)
+        repmgr: consolidate replication connection code (Ian)
+        repmgr: check permissions for "pg_promote()" and fall back to pg_ctl
+          if necessary (Ian)
+        repmgr: in --dry-run mode, display promote command which will be used (Ian)
+        repmgr: enable "service_promote_command" in PostgreSQL 12 (Ian)
+        repmgr: accept option -S/--superuser for "node check"; GitHub #612 (Ian)
+
+5.0     2019-10-15
         general: add PostgreSQL 12 support (Ian)
         general: parse configuration file using flex (Ian)
         repmgr: rename "repmgr daemon ..." commands to "repmgr service ..." (Ian)

Makefile.in

@@ -11,6 +11,7 @@ EXTENSION = repmgr
 
 DATA = \
   repmgr--unpackaged--4.0.sql \
+  repmgr--unpackaged--5.1.sql \
   repmgr--4.0.sql \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \
@@ -21,7 +22,9 @@ DATA = \
   repmgr--4.3--4.4.sql \
   repmgr--4.4.sql \
   repmgr--4.4--5.0.sql \
-  repmgr--5.0.sql
+  repmgr--5.0.sql \
+  repmgr--5.0--5.1.sql \
+  repmgr--5.1.sql
 
 REGRESS = repmgr_extension
 
@@ -53,9 +56,9 @@ $(info Building against PostgreSQL $(MAJORVERSION))
 
 REPMGR_CLIENT_OBJS = repmgr-client.o \
 	repmgr-action-primary.o repmgr-action-standby.o repmgr-action-witness.o \
-	repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
+	repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
 	configfile.o configfile-scan.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
-REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o configfile-scan.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.o
+REPMGRD_OBJS = repmgrd.o repmgrd-physical.o configfile.o configfile-scan.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.o
 DATE=$(shell date "+%Y-%m-%d")
 
 repmgr_version.h: repmgr_version.h.in

README.md

@@ -7,32 +7,30 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-`repmgr 4` is a complete rewrite of the existing `repmgr` codebase, allowing
+PostgreSQL 12, 11, 10, 9.6 and 9.5 are fully supported.
-the use of all of the latest features in PostgreSQL replication.
-
-PostgreSQL 11, 10, 9.6 and 9.5 are fully supported.
 PostgreSQL 9.4 and 9.3 are supported, with some restrictions.
 
 `repmgr` is distributed under the GNU GPL 3 and maintained by 2ndQuadrant.
 
-### BDR support
-
-`repmgr 4` supports monitoring of a two-node BDR 2.0 cluster on PostgreSQL 9.6
-only. Note that BDR 2.0 is not publicly available; please contact 2ndQuadrant
-for details.
-
-
 Documentation
 -------------
 
-The main `repmgr` documentation is available here:
+The full `repmgr` documentation is available here:
 
 > [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
-The `README` file for `repmgr` 3.x 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
 
+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.
+
+Versions
+--------
+
+For an overview of `repmgr` versions and PostgreSQL compatibility, see the
+[repmgr compatibility matrix](https://repmgr.org/docs/current/install-requirements.html#INSTALL-COMPATIBILITY-MATRIX).
 
 Files
 ------
@@ -72,6 +70,8 @@ Please report bugs and other issues to:
 
 * https://github.com/2ndQuadrant/repmgr
 
+See 
+
 Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
@@ -98,6 +98,8 @@ 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/

compat.c

@@ -6,7 +6,7 @@
  *    supported PostgreSQL versions. They're unlikely to change but
  *    it would be worth keeping an eye on them for any fixes/improvements.
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

configfile.c

@@ -1,7 +1,7 @@
 /*
  * config.c - parse repmgr.conf and other configuration-related functionality
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -378,13 +378,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	 */
 	options->witness_sync_interval = DEFAULT_WITNESS_SYNC_INTERVAL;
 
-	/*-------------
-	 * BDR settings
-	 *-------------
-	 */
-	options->bdr_local_monitoring_only = false;
-	options->bdr_recovery_timeout = DEFAULT_BDR_RECOVERY_TIMEOUT;
-
 	/*-------------------------
 	 * service command settings
 	 *-------------------------
@@ -569,8 +562,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 void
 parse_configuration_item(t_configuration_options *options, ItemList *error_list, ItemList *warning_list, const char *name, const char *value)
 {
-	bool		known_parameter = true;
-
 	if (strcmp(name, "node_id") == 0)
 	{
 		options->node_id = repmgr_atoi(value, name, error_list, MIN_NODE_ID);
@@ -616,10 +607,8 @@ parse_configuration_item(t_configuration_options *options, ItemList *error_list,
 	{
 		if (strcmp(value, "physical") == 0)
 			options->replication_type = REPLICATION_TYPE_PHYSICAL;
-		else if (strcmp(value, "bdr") == 0)
-			options->replication_type = REPLICATION_TYPE_BDR;
 		else
-			item_list_append(error_list, _("value for \"replication_type\" must be \"physical\" or \"bdr\""));
+			item_list_append(error_list, _("value for \"replication_type\" must be \"physical\""));
 	}
 
 	/* log settings */
@@ -778,12 +767,6 @@ parse_configuration_item(t_configuration_options *options, ItemList *error_list,
 	else if (strcmp(name, "witness_sync_interval") == 0)
 		options->witness_sync_interval = repmgr_atoi(value, name, error_list, 1);
 
-	/* BDR settings */
-	else if (strcmp(name, "bdr_local_monitoring_only") == 0)
-		options->bdr_local_monitoring_only = parse_bool(value, name, error_list);
-	else if (strcmp(name, "bdr_recovery_timeout") == 0)
-		options->bdr_recovery_timeout = repmgr_atoi(value, name, error_list, 0);
-
 	/* service settings */
 	else if (strcmp(name, "pg_ctl_options") == 0)
 		strncpy(options->pg_ctl_options, value, sizeof(options->pg_ctl_options));
@@ -841,73 +824,47 @@ parse_configuration_item(t_configuration_options *options, ItemList *error_list,
 	{
 		item_list_append(warning_list,
 						 _("parameter \"cluster\" is deprecated and will be ignored"));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "node") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"node\" has been renamed to \"node_id\""));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "upstream_node") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"upstream_node\" has been removed; use \"--upstream-node-id\" when cloning a standby"));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "loglevel") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"loglevel\" has been renamed to \"log_level\""));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "logfacility") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"logfacility\" has been renamed to \"log_facility\""));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "logfile") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"logfile\" has been renamed to \"log_file\""));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "master_reponse_timeout") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"master_reponse_timeout\" has been removed; use \"async_query_timeout\" instead"));
-		known_parameter = false;
 	}
 	else if (strcmp(name, "retry_promote_interval_secs") == 0)
 	{
 		item_list_append(warning_list,
 						 _("parameter \"retry_promote_interval_secs\" has been removed; use \"primary_notification_timeout\" instead"));
-		known_parameter = false;
 	}
 	else
 	{
-		known_parameter = false;
 		log_warning(_("%s/%s: unknown name/value pair provided; ignoring"), name, value);
 	}
 
-	/*
-	 * Raise an error if a known parameter is provided with an empty
-	 * value. Currently there's no reason why empty parameters are needed;
-	 * if we want to accept those, we'd need to add stricter default
-	 * checking, as currently e.g. an empty `node_id` value will be converted
-	 * to '0'.
-	 */
-	if (known_parameter == true && !strlen(value))
-	{
-		char		error_message_buf[MAXLEN] = "";
-
-		maxlen_snprintf(error_message_buf,
-						_("\"%s\": no value provided"),
-						name);
-
-		item_list_append(error_list, error_message_buf);
-	}
 }
 
 
@@ -1112,8 +1069,6 @@ parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemL
  * with these):
  *
  * - async_query_timeout
- * - bdr_local_monitoring_only
- * - bdr_recovery_timeout
  * - child_nodes_check_interval
  * - child_nodes_connected_min_count
  * - child_nodes_connected_include_witness
@@ -1180,7 +1135,8 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	_parse_config(&new_options, &config_errors, &config_warnings);
 
 
-	if (server_type == PRIMARY || server_type == STANDBY)
+	if (new_options.failover == FAILOVER_AUTOMATIC
+		&& (server_type == PRIMARY || server_type == STANDBY))
 	{
 		if (new_options.promote_command[0] == '\0')
 		{
@@ -1249,24 +1205,6 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
-	/* bdr_local_monitoring_only */
-	if (orig_options->bdr_local_monitoring_only != new_options.bdr_local_monitoring_only)
-	{
-		orig_options->bdr_local_monitoring_only = new_options.bdr_local_monitoring_only;
-		log_info(_("\"bdr_local_monitoring_only\" is now \"%s\""), new_options.bdr_local_monitoring_only == true ? "TRUE" : "FALSE");
-
-		config_changed = true;
-	}
-
-	/* bdr_recovery_timeout */
-	if (orig_options->bdr_recovery_timeout != new_options.bdr_recovery_timeout)
-	{
-		orig_options->bdr_recovery_timeout = new_options.bdr_recovery_timeout;
-		log_info(_("\"bdr_recovery_timeout\" is now \"%i\""), new_options.bdr_recovery_timeout);
-
-		config_changed = true;
-	}
-
 	/* child_nodes_check_interval */
 	if (orig_options->child_nodes_check_interval != new_options.child_nodes_check_interval)
 	{
@@ -1882,6 +1820,9 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 	PQExpBufferData auto_conf_contents;
 
 	FILE	   *fp;
+	mode_t		um;
+	struct stat auto_conf_st;
+
 	KeyValueList config = {NULL, NULL};
 	KeyValueListCell *cell = NULL;
 
@@ -1937,7 +1878,16 @@ modify_auto_conf(const char *data_dir, KeyValueList *items)
 						  cell->key, cell->value);
 	}
 
+	stat(auto_conf.data, &auto_conf_st);
+
+	/*
+	 * Set umask so the temporary file is created in the same mode as the original
+	 * postgresql.auto.conf file.
+	 */
+	um = umask(~(auto_conf_st.st_mode));
 	fp = fopen(auto_conf_tmp.data, "w");
+	umask(um);
+
 	if (fp == NULL)
 	{
 		fprintf(stderr, "unable to open \"%s\": %s\n",

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -161,10 +161,6 @@ typedef struct
 	int			child_nodes_disconnect_timeout;
 	char		child_nodes_disconnect_command[MAXPGPATH];
 
-	/* BDR settings */
-	bool		bdr_local_monitoring_only;
-	bool		bdr_recovery_timeout;
-
 	/* service settings */
 	char		pg_ctl_options[MAXLEN];
 	char		service_start_command[MAXPGPATH];
@@ -238,8 +234,6 @@ typedef struct
 		DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT, \
 		DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS, \
 		DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT, "", \
-		/* BDR settings */ \
-		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
 		"", "", "", "", "", "", \
 		/* repmgrd service settings */ \

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 5.0.
+# Generated by GNU Autoconf 2.69 for repmgr 5.1.0.
 #
 # 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) 2010-2019, 2ndQuadrant Ltd.
+# Copyright (c) 2010-2020, 2ndQuadrant Ltd.
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='5.0'
+PACKAGE_VERSION='5.1.0'
-PACKAGE_STRING='repmgr 5.0'
+PACKAGE_STRING='repmgr 5.1.0'
 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 5.0 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.1.0 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 5.0:";;
+     short | recursive ) echo "Configuration of repmgr 5.1.0:";;
    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 5.0
+repmgr configure 5.1.0
 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) 2010-2019, 2ndQuadrant Ltd.
+Copyright (c) 2010-2020, 2ndQuadrant Ltd.
 _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 5.0, which was
+It was created by repmgr $as_me 5.1.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -2487,7 +2487,7 @@ cat >>$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 5.0, which was
+This file was extended by repmgr $as_me 5.1.0, 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 5.0
+repmgr config.status 5.1.0
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [5.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.1.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2020, 2ndQuadrant Ltd.])
 
 AC_CONFIG_HEADER(config.h)
 

controldata.c

@@ -6,7 +6,7 @@
  * running. For that reason we can't use on the pg_control_*() functions
  * provided in PostgreSQL 9.6 and later.
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

controldata.h

@@ -1,6 +1,6 @@
 /*
  * controldata.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

dbutils.h

@@ -1,7 +1,7 @@
 /*
  * dbutils.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -60,11 +60,6 @@
 	"NULL AS attached "
 
 
-
-#define BDR2_NODES_COLUMNS "node_sysid, node_timeline, node_dboid, node_name, node_local_dsn, ''"
-#define BDR3_NODES_COLUMNS "ns.node_id, 0, 0, ns.node_name, ns.interface_connstr, ns.peer_state_name"
-
-
 #define ERRBUFF_SIZE 512
 
 typedef enum
@@ -72,8 +67,7 @@ typedef enum
 	UNKNOWN = 0,
 	PRIMARY,
 	STANDBY,
-	WITNESS,
+	WITNESS
-	BDR
 } t_server_type;
 
 typedef enum
@@ -133,6 +127,8 @@ typedef enum
 typedef enum
 {
 	SLOT_UNKNOWN = -1,
+	SLOT_NOT_FOUND,
+	SLOT_NOT_PHYSICAL,
 	SLOT_INACTIVE,
 	SLOT_ACTIVE
 } ReplSlotStatus;
@@ -170,6 +166,7 @@ typedef struct
 	char		current_timestamp[MAXLEN];
 	bool		in_recovery;
 	TimeLineID	timeline_id;
+	char		timeline_id_str[MAXLEN];
 	XLogRecPtr	last_wal_receive_lsn;
 	XLogRecPtr	last_wal_replay_lsn;
 	char		last_xact_replay_timestamp[MAXLEN];
@@ -324,45 +321,6 @@ typedef struct s_connection_user
 #define T_CONNECTION_USER_INITIALIZER { "", false }
 
 
-/* represents an entry in bdr.bdr_nodes */
-typedef struct s_bdr_node_info
-{
-	char		node_sysid[MAXLEN];
-	uint32		node_timeline;
-	uint32		node_dboid;
-	char		node_name[MAXLEN];
-	char		node_local_dsn[MAXLEN];
-	char		peer_state_name[MAXLEN];
-} t_bdr_node_info;
-
-#define T_BDR_NODE_INFO_INITIALIZER { \
-	"", InvalidOid, InvalidOid, \
-    "", "", "" \
-}
-
-
-/* structs to store a list of BDR node records */
-typedef struct BdrNodeInfoListCell
-{
-	struct BdrNodeInfoListCell *next;
-	t_bdr_node_info *node_info;
-} BdrNodeInfoListCell;
-
-typedef struct BdrNodeInfoList
-{
-	BdrNodeInfoListCell *head;
-	BdrNodeInfoListCell *tail;
-	int			node_count;
-} BdrNodeInfoList;
-
-#define T_BDR_NODE_INFO_LIST_INITIALIZER { \
-	NULL, \
-	NULL, \
-	0 \
-}
-
-
-
 typedef struct
 {
 	char		filepath[MAXPGPATH];
@@ -372,6 +330,7 @@ typedef struct
 
 #define T_CONFIGFILE_INFO_INITIALIZER { "", "", false }
 
+
 typedef struct
 {
 	int			size;
@@ -381,6 +340,7 @@ typedef struct
 
 #define T_CONFIGFILE_LIST_INITIALIZER { 0, 0, NULL }
 
+
 typedef struct
 {
 	uint64		system_identifier;
@@ -420,10 +380,6 @@ typedef struct RepmgrdInfo {
 /* utility functions */
 
 XLogRecPtr	parse_lsn(const char *str);
-
-extern void
-wrap_ddl_query(PQExpBufferData *query_buf, int replication_type, const char *fmt,...)
-__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 bool		atobool(const char *value);
 
 /* connection functions */
@@ -432,13 +388,19 @@ PGconn	   *establish_db_connection(const char *conninfo,
 PGconn	   *establish_db_connection_quiet(const char *conninfo);
 PGconn	   *establish_db_connection_by_params(t_conninfo_param_list *param_list,
 								  const bool exit_on_error);
+PGconn	   *establish_db_connection_with_replacement_param(const char *conninfo,
+														   const char *param,
+														   const char *value,
+														   const bool exit_on_error);
+PGconn	   *establish_replication_connection_from_conn(PGconn *conn, const char *repluser);
+PGconn	   *establish_replication_connection_from_conninfo(const char *conninfo, const char *repluser);
+
 PGconn	   *establish_primary_db_connection(PGconn *conn,
 								const bool exit_on_error);
 PGconn	   *get_primary_connection(PGconn *standby_conn, int *primary_id, char *primary_conninfo_out);
 PGconn	   *get_primary_connection_quiet(PGconn *standby_conn, int *primary_id, char *primary_conninfo_out);
+PGconn	   *duplicate_connection(PGconn *conn, const char *user, bool replication);
 
-bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
-bool		connection_has_pg_settings(PGconn *conn);
 void		close_connection(PGconn **conn);
 
 /* conninfo manipulation functions */
@@ -467,6 +429,7 @@ bool		set_config(PGconn *conn, const char *config_param, const char *config_valu
 bool		set_config_bool(PGconn *conn, const char *config_param, bool state);
 int		    guc_set(PGconn *conn, const char *parameter, const char *op, const char *value);
 bool		get_pg_setting(PGconn *conn, const char *setting, char *output);
+bool		get_pg_setting_bool(PGconn *conn, const char *setting, bool *output);
 bool		get_pg_setting_int(PGconn *conn, const char *setting, int *output);
 bool		alter_system_int(PGconn *conn, const char *name, int value);
 bool		pg_reload_conf(PGconn *conn);
@@ -482,6 +445,12 @@ bool		identify_system(PGconn *repl_conn, t_system_identification *identification
 uint64		system_identifier(PGconn *conn);
 TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
 
+/* user/role information functions */
+bool		can_execute_pg_promote(PGconn *conn);
+bool		connection_has_pg_settings(PGconn *conn);
+bool		is_replication_role(PGconn *conn, char *rolname);
+bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
+
 /* repmgrd shared memory functions */
 bool		repmgrd_set_local_node_id(PGconn *conn, int local_node_id);
 int			repmgrd_get_local_node_id(PGconn *conn);
@@ -559,10 +528,14 @@ PGresult   *get_event_records(PGconn *conn, int node_id, const char *node_name,
 
 /* replication slot functions */
 void		create_slot_name(char *slot_name, int node_id);
-bool		create_replication_slot(PGconn *conn, char *slot_name, PQExpBufferData *error_msg);
+
-bool		drop_replication_slot(PGconn *conn, char *slot_name);
+bool		create_replication_slot_sql(PGconn *conn, char *slot_name, PQExpBufferData *error_msg);
+bool		create_replication_slot_replprot(PGconn *conn, PGconn *repl_conn, char *slot_name, PQExpBufferData *error_msg);
+bool		drop_replication_slot_sql(PGconn *conn, char *slot_name);
+bool		drop_replication_slot_replprot(PGconn *repl_conn, char *slot_name);
+
 RecordStatus get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record);
-int			get_free_replication_slot_count(PGconn *conn);
+int			get_free_replication_slot_count(PGconn *conn, int *max_replication_slots);
 int			get_inactive_replication_slots(PGconn *conn, KeyValueList *list);
 
 /* tablespace functions */
@@ -614,7 +587,7 @@ XLogRecPtr	get_last_wal_receive_location(PGconn *conn);
 void		init_replication_info(ReplInfo *replication_info);
 bool		get_replication_info(PGconn *conn, t_server_type node_type, ReplInfo *replication_info);
 int			get_replication_lag_seconds(PGconn *conn);
-TimeLineID	get_node_timeline(PGconn *conn);
+TimeLineID	get_node_timeline(PGconn *conn, char *timeline_id_str);
 void		get_node_replication_stats(PGconn *conn, t_node_info *node_info);
 NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name);
 void		set_upstream_last_seen(PGconn *conn, int upstream_node_id);
@@ -622,27 +595,6 @@ int			get_upstream_last_seen(PGconn *conn, t_server_type node_type);
 
 bool		is_wal_replay_paused(PGconn *conn, bool check_pending_wal);
 
-/* BDR functions */
-int			get_bdr_version_num(void);
-void		get_all_bdr_node_records(PGconn *conn, BdrNodeInfoList *node_list);
-RecordStatus get_bdr_node_record_by_name(PGconn *conn, const char *node_name, t_bdr_node_info *node_info);
-bool		is_bdr_db(PGconn *conn, PQExpBufferData *output);
-bool		is_bdr_db_quiet(PGconn *conn);
-bool		is_active_bdr_node(PGconn *conn, const char *node_name);
-bool		is_bdr_repmgr(PGconn *conn);
-char	   *get_default_bdr_replication_set(PGconn *conn);
-bool		is_table_in_bdr_replication_set(PGconn *conn, const char *tablename, const char *set);
-bool		add_table_to_bdr_replication_set(PGconn *conn, const char *tablename, const char *set);
-void		add_extension_tables_to_bdr_replication_set(PGconn *conn);
-bool		bdr_node_name_matches(PGconn *conn, const char *node_name, PQExpBufferData *bdr_local_node_name);
-ReplSlotStatus get_bdr_node_replication_slot_status(PGconn *conn, const char *node_name);
-void		get_bdr_other_node_name(PGconn *conn, int node_id, char *name_buf);
-
-bool		am_bdr_failover_handler(PGconn *conn, int node_id);
-void		unset_bdr_failover_handler(PGconn *conn);
-bool		bdr_node_has_repmgr_set(PGconn *conn, const char *node_name);
-bool		bdr_node_set_repmgr_set(PGconn *conn, const char *node_name);
-
 /* miscellaneous debugging functions */
 const char *print_node_status(NodeStatus node_status);
 const char *print_pqping_status(PGPing ping_status);

dirutil.c

@@ -3,7 +3,7 @@
  * dirmod.c
  *	  directory handling functions
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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

dirutil.h

@@ -1,6 +1,6 @@
 /*
  * dirutil.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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

doc/appendix-faq.xml

@@ -245,7 +245,7 @@
       <para>
         For a standby which has been manually cloned or recovered from an external
         backup manager such as Barman, the command
-        <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>
+        <command><link linkend="repmgr-standby-clone">repmgr standby clone --replication-conf-only</link></command>
         can be used to create the correct <filename>recovery.conf</filename> file for
         use with &repmgr; (and will create a replication slot if required). Once this has been done,
         <link linkend="repmgr-standby-register">register the node</link> as usual.

doc/appendix-packages.xml

@@ -253,20 +253,14 @@
     </indexterm>
 
     <para>
-      &repmgr; <literal>.deb</literal> packages are provided via the
+      &repmgr; <literal>.deb</literal> packages are provided by 2ndQuadrant as well as the
       PostgreSQL Community APT repository, and are available for each community-supported
       PostgreSQL version, currently supported Debian releases, and currently supported
       Ubuntu LTS releases.
     </para>
 
     <sect2 id="packages-apt-repository">
-      <title>APT repository</title>
+      <title>APT repositories</title>
-
-      <para>
-        &repmgr; packages are available from the  PostgreSQL Community APT repository,
-        which is updated immediately after each &repmgr; release.
-      </para>
-
 
       <table id="apt-2ndquadrant-repository">
         <title>2ndQuadrant public repository</title>
@@ -291,7 +285,7 @@
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink></entry>
+              <entry><ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -382,9 +376,9 @@
       </table>
       <note>
         <para>
-          Instead of using the <application>systemd</application> service command directly,
+          When using Debian packages, instead of using the <application>systemd</application> service
-          it's recommended to execute <command>pg_ctlcluster</command> (as <literal>root</literal>,
+          command directly,  it's recommended to execute <command>pg_ctlcluster</command>
-          either directly or via <command>sudo</command>), e.g.:
+          (as <literal>root</literal>, either directly or via <command>sudo</command>), e.g.:
           <programlisting>
             <command>pg_ctlcluster 11 main [start|stop|restart|reload]</command></programlisting>
         </para>

doc/appendix-release-notes.xml

@@ -17,9 +17,202 @@
 
 <!-- remember to update the release date in ../repmgr_version.h.in -->
 
+  <sect1 id="release-5.1-0">
+    <title>Release 5.1.0</title>
+    <para><emphasis>Mon 13 April, 2020</emphasis></para>
+
+    <para>
+      &repmgr; 5.1.0 is a major release.
+    </para>
+    <para>
+      For details on how to upgrade an existing &repmgr; installation, see
+      documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
+    </para>
+    <para>
+      If &repmgrd; is in use, a PostgreSQL restart <emphasis>is</emphasis> required;
+      in that case we suggest combining this &repmgr; upgrade with the next PostgreSQL
+      minor release, which will require a PostgreSQL restart in any case.
+    </para>
+
+
+    <sect2>
+      <title>Compatibility changes</title>
+      <para>
+        The <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>
+        <option>--recovery-conf-only</option> option has been renamed to
+        <option>--replication-conf-only</option>. <option>--recovery-conf-only</option> will
+        still be accepted as an alias.
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>General improvements</title>
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              The requirement that the &repmgr; user is a database superuser has been
+              removed as far as possible.
+            </para>
+            <para>
+              In theory, &repmgr; can be operated with a normal database user for managing
+              the &repmgr; database, and a separate replication user for managing replication
+              connections (and replication slots, if these are in use).
+            </para>
+            <para>
+              Some operations will still require superuser permissions, e.g. for issuing
+              a <command>CHECKPOINT</command> as par of a switchover operation; in this case
+              a valid superuser should be provided with the <option>-S</option>/<option>--superuser</option>
+              option.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>:
+              Warn if neither of data page checksums or <option>wal_log_hints</option> are active,
+              as this will preclude later usage of <command>pg_rewind</command>.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>:
+              when executed with <option>--dry-run</option>, the method which would be used to promote the node
+              will be displayed.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>:
+              Improve logging and checking of potential failure situations.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              Replication configuration files (PostgreSQL 11 and earlier:
+              <filename>recovery.conf</filename>; PostgreSQL 12 and later: <filename>postgresql.auto.conf</filename>)
+              will be checked to ensure they are owned by the same user who owns the PostgreSQL
+              data directory.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              Provide additional information in <option>--dry-run mode</option> output.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              Checks that the demotion candidate's registered repmgr.conf file can be found, to
+              prevent confusing references to an incorrectly configured data directory. GitHub 615.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check"><command>repmgr node check</command></link>:
+              accept option <option>-S</option>/<option>--superuser</option>. GitHub #621.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check"><command>repmgr node check</command></link>:
+              add  <option>--upstream</option> option to check whether the node is attached
+              to the expected upstream node.
+            </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+       <itemizedlist>
+          <listitem>
+            <para>
+              Ensure <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>
+              checks for available replication slots on the rejoin target.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link> and
+              <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link> will now return
+              an error code if the operation fails if a replication slot is not available or cannot
+              be created on the follow/rejoin target.
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>:
+              in <option>--dry-run mode</option>, display promote command which will be executed.
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>
+              will check if the <literal>repmgr</literal> user has permission to execute
+              <function>pg_promote()</function> and fall back to <command>pg_ctl promote</command> if
+              necessary.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              check for demotion candidate reattachment as late as possible to avoid spurious failure
+              reports.
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              &repmgrd;: check for presence of <option>promote_command</option> and
+              <option>follow_command</option> on receipt of <literal>SIGHUP</literal>. GitHub 614.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Fix situation where replication connections were not created correctly, which
+              could lead to spurious replication connection failures in some situations, e.g.
+              where password files are used.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Ensure <filename>postgresql.auto.conf</filename> is created with
+              correct permissions (PostgreSQL 12 and later).
+            </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
   <sect1 id="release-5.0">
     <title id="release-current">Release 5.0</title>
-    <para><emphasis>?? September ??, 2019</emphasis></para>
+    <para><emphasis>Tue 15 October, 2019</emphasis></para>
 
     <para>
       &repmgr; 5.0 is a major release.
@@ -167,6 +360,10 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
               function, which enables a standby to be promoted to primary using an SQL
               command.
             </para>
+            <para>
+              For an overview of general changes to replication configuration, see this blog entry:
+              <ulink url="https://www.2ndquadrant.com/en/blog/replication-configuration-changes-in-postgresql-12/">Replication configuration changes in PostgreSQL 12</ulink>
+            </para>
           </listitem>
 
 
@@ -261,7 +458,7 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
 
   <sect1 id="release-4.4">
     <title>Release 4.4</title>
-    <para><emphasis>27 June, 2019</emphasis></para>
+    <para><emphasis>Thu 27 June, 2019</emphasis></para>
 
     <para>
       &repmgr; 4.4 is a major release.

doc/appendix-support.xml

@@ -43,6 +43,12 @@
 
     <itemizedlist spacing="compact" mark="bullet">
 
+     <listitem>
+      <simpara>
+        PostgreSQL version
+      </simpara>
+     </listitem>
+
      <listitem>
       <simpara>
         &repmgr; version
@@ -68,9 +74,18 @@
       </simpara>
      </listitem>
 
+
      <listitem>
       <simpara>
-        PostgreSQL version
+        PostgreSQL 11 and earlier: contents of the <filename>recovery.conf</filename> file
+        (suitably anonymized if necessary).
+      </simpara>
+     </listitem>
+     <listitem>
+      <simpara>
+        PostgreSQL 12 and later: contents of the <filename>postgresql.auto.conf</filename> file
+        (suitably anonymized if necessary), and whether or not the PostgreSQL data directory
+        contains the files <filename>standby.signal</filename> and/or <filename>recovery.signal</filename>.
       </simpara>
      </listitem>
 
@@ -90,8 +105,8 @@
     </para>
     <para>
       In all cases it is <emphasis>extremely</emphasis> useful to receive
-      information on how to reliably reproduce an issue with as much detail as
+      as much detail as possible on how to reliably reproduce
-      possible.
+      an issue.
     </para>
 
   </sect1>

doc/bdr-failover.md

@@ -1,8 +0,0 @@
-BDR failover with repmgrd
-=========================
-
-This document has been integrated into the main `repmgr` documentation
-and is now located here:
-
-> [BDR failover with repmgrd](https://repmgr.org/docs/current/repmgrd-bdr.html)
-

doc/cloning-standbys.xml

@@ -64,8 +64,9 @@
     </para>
     <para>
       Barman's parallel restore facility can be used by executing it manually on
-      the Barman server and integrating the resulting cloned standby using
+      the Barman server and configuring replication on the resulting cloned
-      <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>.
+      standby using
+      <command><link linkend="repmgr-standby-clone">repmgr standby clone --replication-conf-only</link></command>.
     </para>
    </note>
 
@@ -103,15 +104,28 @@
      <filename>repmgr.conf</filename> should contain the following entries:
     <programlisting>
     barman_host='barman@barmansrv'
-    barman_server='somedb'</programlisting>
+    barman_server='pg'</programlisting>
+   </para>
+   <para>
+     Here <literal>pg</literal> corresponds to a section in Barman's configuration file for a specific
+     server backup configuration, which would look something like:
+     <programlisting>
+[pg]
+description = "Main cluster"
+...
+     </programlisting>
+   </para>
+   <para>
+     More details on Barman configuration can be found in the
+     <ulink url="https://docs.pgbarman.org/">Barman documentation</ulink>'s
+     <ulink url="https://docs.pgbarman.org/#configuration">configuration section</ulink>.
    </para>
-
    <note>
     <para>
      To use a non-default Barman configuration file on the Barman server,
      specify this in <filename>repmgr.conf</filename> with <filename>barman_config</filename>:
      <programlisting>
-      barman_config=/path/to/barman.conf</programlisting>
+      barman_config='/path/to/barman.conf'</programlisting>
     </para>
    </note>
 
@@ -189,8 +203,8 @@
     <filename>repmgr.conf</filename> should include the following lines:
     <programlisting>
     barman_host='barman@barmansrv'
-    barman_server='somedb'
+    barman_server='pg'
-    restore_command='/usr/bin/barman-wal-restore barmansrv somedb %f %p'</programlisting>
+    restore_command='/usr/bin/barman-wal-restore barmansrv pg %f %p'</programlisting>
    </para>
    <note>
     <simpara>
@@ -444,10 +458,8 @@
 
     <para>
      The recommended way to do this is to store the password in the <literal>postgres</literal> system
-     user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
+     user's <filename>~/.pgpass</filename> file.  For more information on using the password file, see
-     environment variable <varname>PGPASSWORD</varname>, however this is not recommended for
+     the documentation section <xref linkend="configuration-password-file"/>.
-     security reasons. For more details see the
-     <ulink url="https://www.postgresql.org/docs/current/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
     </para>
 
     <note>
@@ -469,19 +481,6 @@
      will need to be set during any action which causes <filename>recovery.conf</filename> to be
      rewritten, e.g. <xref linkend="repmgr-standby-follow"/>.
     </para>
-    <para>
-     It is of course also possible to include the password value in the <varname>conninfo</varname>
-     string for each node, but this is obviously a security risk and should be avoided.
-    </para>
-    <para>
-      From PostgreSQL 9.6, <application>libpq</application> supports the <varname>passfile</varname>
-      parameter in connection strings, which can be used to specify a password file other than
-      the default <filename>~/.pgpass</filename>.
-    </para>
-    <para>
-      To have &repmgr; write a custom password file in <varname>primary_conninfo</varname>,
-      specify its location in <varname>passfile</varname> in <filename>repmgr.conf</filename>.
-    </para>
    </sect2>
 
    <sect2 id="cloning-advanced-replication-user" xreflabel="Separate replication user">
@@ -497,6 +496,34 @@
      cloning a node or executing <xref linkend="repmgr-standby-follow"/>.
     </para>
    </sect2>
+
+
+   <sect2 id="cloning-advanced-tablespace-mapping" xreflabel="Tablespace mapping">
+    <title>Tablespace mapping</title>
+    <indexterm>
+      <primary>tablespace mapping</primary>
+    </indexterm>
+    <para>
+      &repmgr; provides a <option>tablespace_mapping</option> configuration
+      file option, which will makes it possible to map the tablespace on the source node to
+      a different location on the local node.
+    </para>
+    <para>
+      To use this, add <option>tablespace_mapping</option> to <filename>repmgr.conf</filename>
+      like this:
+<programlisting>
+  tablespace_mapping='/var/lib/pgsql/tblspc1=/data/pgsql/tblspc1'
+</programlisting>
+    </para>
+    <para>
+      where the left-hand value represents the tablespace on the source node,
+      and the right-hand value represents  the tablespace on the standby to be cloned.
+    </para>
+    <para>
+      This parameter can be provided multiple times.
+    </para>
+   </sect2>
+
  </sect1>
 
 

doc/configuration-file-optional-settings.xml

@@ -66,17 +66,8 @@
       </term>
       <listitem>
         <para>
-          Must be one of <literal>physical</literal> (for standard streaming replication)
+          Must be <literal>physical</literal> (the default).
-          or <literal>bdr</literal>.
         </para>
-        <note>
-          <para>
-	    Replication type <literal>bdr</literal> can only be used with BDR 2.x
-          </para>
-          <para>
-            BDR 3.x users should use <literal>physical</literal>.
-          </para>
-        </note>
       </listitem>
     </varlistentry>
 
@@ -119,6 +110,27 @@
       </listitem>
     </varlistentry>
 
+    <varlistentry id="repmgr-conf-ssh-options" xreflabel="ssh_options">
+      <term><varname>ssh_options</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>ssh_options</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Options to append to the <command>ssh</command> command when executed
+          by &repmgr;.
+        </para>
+        <para>
+          We recommend adding <literal>-q</literal> to suppress any superfluous
+          SSH chatter such as login banners, and also an explicit
+          <option>ConnectTimeout</option> value,
+          e.g.:
+<programlisting>
+ssh_options='-q -o ConnectTimeout=10'</programlisting>
+        </para>
+      </listitem>
+    </varlistentry>
 
   </variablelist>
 </sect1>

doc/configuration-password-management.xml

@@ -0,0 +1,147 @@
+<sect1 id="configuration-password-management" xreflabel="password management">
+
+  <title>Password Management</title>
+  <indexterm>
+    <primary>passwords</primary>
+  </indexterm>
+
+  <sect2 id="configuration-password-management-options" xreflabel="password management options">
+  <title>Password Management Options</title>
+  <indexterm>
+    <primary>passwords</primary>
+    <secondary>options for managing</secondary>
+  </indexterm>
+
+  <para>
+    For security purposes it's desirable to protect database access using a password.
+  </para>
+  <para>
+    PostgreSQL has three ways of providing a password:
+    <itemizedlist spacing="compact" mark="bullet">
+
+       <listitem>
+         <simpara>
+           including the password in the <option>conninfo</option> string
+           (e.g. &quot;<literal>host=node1 dbname=repmgr user=repmgr password=foo</literal>&quot;)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           exporting the password as an environment variable (<envar>PGPASSWORD</envar>)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           storing the password in a dedicated password file
+         </simpara>
+       </listitem>
+    </itemizedlist>
+  </para>
+  <para>
+    We strongly advise against including the password in the <option>conninfo</option> string, as
+    this will result in the database password being exposed in various places, including in the
+    <filename>repmgr.conf</filename> file, the <literal>repmgr.nodes</literal> table, any output
+    generated by &repmgr; which lists the node <option>conninfo</option> strings (e.g.
+    <link linkend="repmgr-cluster-show">repmgr cluster show</link>) and in the &repmgr; log file,
+    particularly at <option>log_level=DEBUG</option>.
+  </para>
+  <note>
+    <para>
+      Currently &repmgr; does not fully support use of the <option>password</option> option in the
+      <option>conninfo</option> string.
+    </para>
+  </note>
+  <para>
+    Exporting the password as an environment variable (<envar>PGPASSWORD</envar>) is considered
+    less insecure, but the PostgreSQL documentation explicitly recommends against doing this:
+   <blockquote>
+     <attribution><ulink url="https://www.postgresql.org/docs/current/libpq-envars.html">Environment Variables</ulink></attribution>
+     <para>
+       <envar>PGPASSWORD</envar> behaves the same as the <option>password</option>
+       connection parameter. Use of this environment variable
+       is not recommended for security reasons, as some operating systems
+       allow non-root users to see process environment variables via
+       <application>ps</application>; instead consider using a password file.
+     </para>
+    </blockquote>
+
+  </para>
+  <para>
+    The most secure option for managing passwords is to use a dedicated password file; see the following
+    section for more details.
+  </para>
+
+  </sect2>
+
+  <sect2 id="configuration-password-file" xreflabel="password file">
+    <title>Using a password file</title>
+    <indexterm>
+      <primary>pgpass</primary>
+    </indexterm>
+
+    <indexterm>
+      <primary>.pgpass</primary>
+    </indexterm>
+
+    <indexterm>
+      <primary>passwords</primary>
+      <secondary>using a password file</secondary>
+    </indexterm>
+
+    <para>
+      The most secure way of storing passwords is in a password file,
+      which by default is <filename>~/.pgpass</filename>. This file
+      can only be read by the system user who owns the file, and
+      PostgreSQL will refuse to use the file unless read/write
+      permissions are restricted to the file owner. The password(s)
+      contained in the file will not be directly accessed by
+      &repmgr; (or any other libpq-based client software such as <application>psql</application>).
+    </para>
+    <para>
+       For full details see the
+       <ulink url="https://www.postgresql.org/docs/current/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
+    </para>
+    <para>
+      For use with &repmgr;, the <filename>~/.pgpass</filename> must two entries for each
+      node in the replication cluster: one for the &repmgr; user who accesses the &repmgr; metadatabase,
+      and one for replication connections (regardless of whether a dedicated replication user is used).
+      The file must be present on each node in the replication cluster.
+    </para>
+    <para>
+      A <filename>~/.pgpass</filename> file for a 3-node cluster where the <literal>repmgr</literal> database user
+      is used for both for accessing the  &repmgr; metadatabase and for replication connections would look like this:
+      <programlisting>
+node1:5432:repmgr:repmgr:foo
+node1:5432:replication:repmgr:foo
+node2:5432:repmgr:repmgr:foo
+node2:5432:replication:repmgr:foo
+node3:5432:repmgr:repmgr:foo
+node3:5432:replication:repmgr:foo</programlisting>
+      If a dedicated replication user (here: <literal>repluser</literal>) is in use, the file would look like this:
+      <programlisting>
+node1:5432:repmgr:repmgr:foo
+node1:5432:replication:repluser:foo
+node2:5432:repmgr:repmgr:foo
+node2:5432:replication:repluser:foo
+node3:5432:repmgr:repmgr:foo
+node3:5432:replication:repluser:foo</programlisting>
+
+    </para>
+    <note>
+      <para>
+        It's possible to specify an alternative location for the <filename>~/.pgpass</filename> file, either via
+        the environment variable <envar>PGPASSFILE</envar>, or (from PostgreSQL 9.6) using the
+        <varname>passfile</varname> parameter in connection strings.
+      </para>
+      <para>
+        If using the <varname>passfile</varname> parameter, it's essential to ensure the file is in the same
+        location on all nodes, as when connecting to a remote node, the file referenced is the one on the
+        local node.
+      </para>
+    </note>
+
+  </sect2>
+
+</sect1>

doc/configuration-permissions.xml

@@ -0,0 +1,25 @@
+<sect1 id="configuration-permissions" xreflabel="Database user permissions">
+  <title>repmgr database user permissions</title>
+
+  <indexterm>
+    <primary>configuration</primary>
+    <secondary>database user permissions</secondary>
+  </indexterm>
+
+  <para>
+    &repmgr; requires that the database defined in the <varname>conninfo</varname>
+    setting contains the <literal>repmgr</literal> extension. The database user defined in the
+    <varname>conninfo</varname> setting must be able to access this database and
+    the database objects contained within the extension.
+  </para>
+  <para>
+    The <literal>repmgr</literal> extension can only be installed by a superuser.
+    If the &repmgr; user is a superuser, &repmgr; will create the extension automatically.
+  </para>
+
+  <para>
+    Alternatively, the extension can be created manually by a superuser
+    (with &quot;<command>CREATE EXTENSION repmgr</command>&quot;) before executing
+    <link linkend="repmgr-primary-register">repmgr primary register</link>.
+  </para>
+</sect1>

doc/configuration.xml

@@ -318,23 +318,7 @@
   &configuration-file-optional-settings;
   &configuration-file-log-settings;
   &configuration-file-service-commands;
+  &configuration-permissions;
+  &configuration-password-management;
 
-  <sect1 id="configuration-permissions" xreflabel="Database user permissions">
-    <title>repmgr database user permissions</title>
-
-    <indexterm>
-      <primary>configuration</primary>
-      <secondary>database user permissions</secondary>
-    </indexterm>
-
-    <para>
-      &repmgr; will create an extension database containing objects
-      for administering &repmgr; metadata. The user defined in the <varname>conninfo</varname>
-      setting must be able to access all objects. Additionally, superuser permissions
-      are required to install the &repmgr; extension. The easiest way to do this
-      is create the &repmgr; user as a superuser, however if this is not
-      desirable, the &repmgr; user can be created as a normal user and a
-      superuser specified with <literal>--superuser</literal> when registering a &repmgr; node.
-    </para>
-  </sect1>
 </chapter>

doc/event-notifications.xml

@@ -117,10 +117,6 @@
      <literal>conninfo</literal> string of the primary node
      (<xref linkend="repmgr-standby-register"/> and <xref linkend="repmgr-standby-follow"/>)
     </para>
-    <para>
-      <literal>conninfo</literal> string of the next available node
-      (<varname>bdr_failover</varname> and  <varname>bdr_recovery</varname>)
-    </para>
    </listitem>
   </varlistentry>
 
@@ -130,9 +126,6 @@
     <para>
      name of the current primary node (<xref linkend="repmgr-standby-register"/> and <xref linkend="repmgr-standby-follow"/>)
     </para>
-    <para>
-     name of the next available node (<varname>bdr_failover</varname> and  <varname>bdr_recovery</varname>)
-    </para>
    </listitem>
   </varlistentry>
 
@@ -148,7 +141,7 @@
   the notification types can be filtered to explicitly named ones using the
   <varname>event_notifications</varname> parameter, e.g.:
     <programlisting>
-    event_notifications=primary_register,standby_register,witness_register</programlisting>
+    event_notifications='primary_register,standby_register,witness_register'</programlisting>
 
  </para>
 
@@ -273,28 +266,6 @@
    </itemizedlist>
  </para>
 
-  <para>
-   Events generated by &repmgrd; (BDR mode):
-   <itemizedlist spacing="compact" mark="bullet">
-   <listitem>
-    <simpara><literal>bdr_failover</literal></simpara>
-   </listitem>
-   <listitem>
-    <simpara><literal>bdr_reconnect</literal></simpara>
-   </listitem>
-   <listitem>
-    <simpara><literal>bdr_recovery</literal></simpara>
-   </listitem>
-   <listitem>
-    <simpara><literal>bdr_register</literal></simpara>
-   </listitem>
-   <listitem>
-    <simpara><literal>bdr_unregister</literal></simpara>
-   </listitem>
-
-  </itemizedlist>
- </para>
-
  <para>
   Note that under some circumstances (e.g. when no replication cluster primary
   could be located), it will not be possible to write an entry into the

doc/filelist.xml

@@ -21,6 +21,8 @@
 <!ENTITY configuration-file-optional-settings      SYSTEM "configuration-file-optional-settings.xml">
 <!ENTITY configuration-file-log-settings      SYSTEM "configuration-file-log-settings.xml">
 <!ENTITY configuration-file-service-commands   SYSTEM "configuration-file-service-commands.xml">
+<!ENTITY configuration-permissions   SYSTEM "configuration-permissions.xml">
+<!ENTITY configuration-password-management   SYSTEM "configuration-password-management.xml">
 <!ENTITY cloning-standbys  SYSTEM "cloning-standbys.xml">
 <!ENTITY promoting-standby  SYSTEM "promoting-standby.xml">
 <!ENTITY follow-new-primary  SYSTEM "follow-new-primary.xml">
@@ -33,7 +35,6 @@
 <!ENTITY repmgrd-automatic-failover SYSTEM "repmgrd-automatic-failover.xml">
 <!ENTITY repmgrd-configuration SYSTEM "repmgrd-configuration.xml">
 <!ENTITY repmgrd-operation SYSTEM "repmgrd-operation.xml">
-<!ENTITY repmgrd-bdr SYSTEM "repmgrd-bdr.xml">
 
 <!ENTITY repmgr-primary-register SYSTEM "repmgr-primary-register.xml">
 <!ENTITY repmgr-primary-unregister SYSTEM "repmgr-primary-unregister.xml">

doc/install-packages.xml

@@ -26,10 +26,18 @@
 	<ulink url="https://dl.2ndquadrant.com/">public repository</ulink>; see following
 	section for details.
   </para>
+  <note>
+    <para>
+      Currently the <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+	  <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> provides
+      support for RedHat/CentOS versions 5, 6 and 7. Support for version 8 is
+      available via the PGDG repository; see below for details.
+    </para>
+  </note>
   <para>
    RPM packages for &repmgr; are also available via Yum through
-   the PostgreSQL Global Development Group RPM repository
+   the PostgreSQL Global Development Group (PGDG) RPM repository
-   (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</ulink>).
+   (<ulink url="https://yum.postgresql.org/">https://yum.postgresql.org/</ulink>).
    Follow the instructions for your distribution (RedHat, CentOS,
    Fedora, etc.) and architecture as detailed there. Note that it can take some days
    for new &repmgr; packages to become available via the this repository.
@@ -198,7 +206,7 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
   </indexterm>
 
   <para>.deb packages for &repmgr; are available from the
-  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
+  PostgreSQL Community APT repository (<ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink>).
   Instructions can be found in the APT section of the PostgreSQL Wiki
   (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink>).
   </para>

doc/install-requirements.xml

@@ -99,6 +99,9 @@
             <entry>
               &repmgr; version
             </entry>
+            <entry>
+              Supported?
+            </entry>
             <entry>
               Latest release
             </entry>
@@ -114,6 +117,9 @@
             <entry>
               &repmgr; 5.x
             </entry>
+            <entry>
+              YES
+            </entry>
             <entry>
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
@@ -127,7 +133,10 @@
               &repmgr; 4.x
             </entry>
             <entry>
-              <link linkend="release-4.4">4.4</link> (27 June, 2019)
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-4.4">4.4</link> (2019-06-27)
             </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
@@ -138,6 +147,9 @@
             <entry>
               &repmgr; 3.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-3.3.2.html">3.3.2</ulink> (2017-05-30)
             </entry>
@@ -150,6 +162,9 @@
             <entry>
               &repmgr; 2.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-2.0.3.html">2.0.3</ulink> (2015-04-16)
             </entry>
@@ -167,8 +182,23 @@
         The &repmgr; 2.x and 3.x series are no longer maintained or supported.
         We strongly recommend  upgrading to the latest &repmgr; version.
       </para>
+      <para>
+        Following the release of &repmgr; 5.0, there will be no further releases of
+        the &repmgr; 4.x series. Note that &repmgr; 5.x is an incremental development
+        of the 4.x series and &repmgr; 4.x users should upgrade to this as soon as possible.
+      </para>
     </important>
 
+  </sect2>
+
+  <sect2 id="install-postgresql-93-94">
+
+    <title>PostgreSQL 9.3 and 9.4 support</title>
+
+    <indexterm>
+      <primary>PostgreSQL 9.3</primary>
+      <secondary>repmgr support</secondary>
+    </indexterm>
 
     <para>
       Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4:
@@ -190,5 +220,26 @@
       </listitem>
     </itemizedlist>
 
+    <important>
+      <para>
+        PostgreSQL 9.3 has reached the end of its community support period (final release was
+        <ulink url="https://www.postgresql.org/docs/9.3/release-9-3-25.html">9.3.25</ulink>
+        in November 2018) and will no longer be updated with security or bugfixes.
+      </para>
+      <para>
+        PostgreSQL 9.4 has reached the end of its community support period (final release was
+        <ulink url="https://www.postgresql.org/docs/9.4/release-9-4-26.html">9.4.26</ulink>
+        in February 2020) and will no longer be updated with security or bugfixes.
+      </para>
+      <para>
+        We recommend that users of these versions migrate to a recent PostgreSQL version
+        as soon as possible.
+      </para>
+      <para>
+        For further details, see the  <ulink url="https://www.postgresql.org/support/versioning/">PostgreSQL Versioning Policy</ulink>.
+      </para>
+    </important>
+
   </sect2>
+
  </sect1>

doc/install-source.xml

@@ -24,8 +24,7 @@
     <listitem>
      <para>
       <literal>Debian</literal> and <literal>Ubuntu</literal>: First
-      add the <ulink
+      add the <ulink url="https://apt.postgresql.org/">apt.postgresql.org</ulink>
-      url="http://apt.postgresql.org/">apt.postgresql.org</ulink>
       repository to your <filename>sources.list</filename> if you
       have not already done so, and ensure the source repository is enabled.
      </para>
@@ -36,8 +35,8 @@
          line in the repository file, which is usually
          <filename>/etc/apt/sources.list.d/pgdg.list</filename>, e.g.:
          <programlisting>
-deb http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
+deb https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
-deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
+deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
        </para>
      </tip>
      <para>

doc/legal.xml

@@ -3,7 +3,7 @@
 <date>2017</date>
 
 <copyright>
- <year>2010-2019</year>
+ <year>2010-2020</year>
  <holder>2ndQuadrant, Ltd.</holder>
 </copyright>
 
@@ -11,7 +11,7 @@
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2019
+  <productname>repmgr</productname> is Copyright &copy; 2010-2020
   by 2ndQuadrant, Ltd. All rights reserved.
  </para>
 

doc/quickstart.xml

@@ -167,7 +167,7 @@
     For the sake of simplicity, the <literal>repmgr</literal> user is created
     as a superuser. If desired, it's possible to create the <literal>repmgr</literal>
     user as a normal user. However for certain operations superuser permissions
-    are requiredl; in this case the command line option <command>--superuser</command>
+    are required; in this case the command line option <command>--superuser</command>
     can be provided to specify a superuser.
    </para>
    <para>

doc/repmgr-cluster-show.xml

@@ -18,7 +18,7 @@
     <para>
       Displays information about each registered node in the replication cluster. This
       command polls each registered server and shows its role (<literal>primary</literal> /
-      <literal>standby</literal> / <literal>bdr</literal>) and status. It polls each server
+      <literal>standby</literal>) and status. It polls each server
       directly and can be run on any node in the cluster; this is also useful when analyzing
       connectivity from a particular node.
     </para>
@@ -53,12 +53,13 @@
     <para>
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
-
      ID | Name  | Role    | Status    | Upstream | Location | Priority | Timeline | Connection string
-    ----+-------+---------+-----------+----------+----------+----------+-----------------------------------------
+    ----+-------+---------+-----------+----------+----------+----------+----------+-----------------------------------------
      1  | node1 | primary | * running |          | default  | 100      | 1        | host=db_node1 dbname=repmgr user=repmgr
      2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=db_node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr</programlisting>
+     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr
+     4  | node4 | standby |   running | node1    | default  | 100      | 1        | host=db_node4 dbname=repmgr user=repmgr
+     5  | node5 | witness | * running | node1    | default  | 0        | n/a      | host=db_node5 dbname=repmgr user=repmgr</programlisting>
   </para>
   </refsect1>
   <refsect1>
@@ -82,18 +83,22 @@
 	  (but <literal>node3</literal> is not attached to it, and its metadata has not yet been updated);
 	  <literal>node4</literal> is running but rejecting connections (from <literal>node3</literal> at least).
       <programlisting>
-	 ID | Name  | Role    | Status               | Upstream | Location | Priority | Connection string
+     ID | Name  | Role    | Status               | Upstream | Location | Priority | Timeline | Connection string
-	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
+    ----+-------+---------+----------------------+----------+----------+----------+----------+----------------------------------------------------
-	 1  | node1 | primary | ? unreachable        |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
+     1  | node1 | primary | ? unreachable        |          | default  | 100      |          | host=db_node1 dbname=repmgr user=repmgr
-	 2  | node2 | standby | ! running as primary | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
+     2  | node2 | standby | ! running as primary | ? node1  | default  | 100      | 2        | host=db_node2 dbname=repmgr user=repmgr
-	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
+     3  | node3 | standby |   running            | ? node1  | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr
-	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
+     4  | node4 | standby | ? running            | ? node1  | default  | 100      |          | host=db_node4 dbname=repmgr user=repmgr
 
-	WARNING: following issues were detected
+    WARNING: following issues were detected
-	  - unable to connect to node "node1" (ID: 1)
+      - unable to connect to node "node1" (ID: 1)
-	  - node "node1" (ID: 1) is registered as an active primary but is unreachable
+      - node "node1" (ID: 1) is registered as an active primary but is unreachable
-	  - node "node2" (ID: 2) is registered as standby but running as primary
+      - node "node2" (ID: 2) is registered as standby but running as primary
-	  - unable to connect to node "node4" (ID: 4)
+      - unable to connect to node "node2" (ID: 2)'s upstream node "node1" (ID: 1)
+      - unable to determine if node "node2" (ID: 2) is attached to its upstream node "node1" (ID: 1)
+      - unable to connect to node "node3" (ID: 3)'s upstream node "node1" (ID: 1)
+      - unable to determine if node "node3" (ID: 3) is attached to its upstream node "node1" (ID: 1)
+      - unable to connect to node "node4" (ID: 4)
     HINT: execute with --verbose option to see connection error messages</programlisting>
     </para>
 	<para>

doc/repmgr-node-check.xml

@@ -31,15 +31,32 @@
   <refsect1>
     <title>Example</title>
     <para>
+      Execution on the primary server:
       <programlisting>
        $ repmgr -f /etc/repmgr.conf node check
        Node "node1":
             Server role: OK (node is primary)
             Replication lag: OK (N/A - node is primary)
             WAL archiving: OK (0 pending files)
+            Upstream connection: OK (N/A - is primary)
             Downstream servers: OK (2 of 2 downstream nodes attached)
             Replication slots: OK (node has no physical replication slots)
-            Missing replication slots: OK (node has no missing physical replication slots)</programlisting>
+            Missing replication slots: OK (node has no missing physical replication slots)
+            Configured data directory: OK (configured "data_directory" is "/var/lib/postgresql/data")</programlisting>
+    </para>
+    <para>
+      Execution on a standby server:
+      <programlisting>
+       $ repmgr -f /etc/repmgr.conf node check
+       Node "node2":
+            Server role: OK (node is standby)
+            Replication lag: OK (0 seconds)
+            WAL archiving: OK (0 pending archive ready files)
+            Upstream connection: OK (node "node2" (ID: 2) is attached to expected upstream node "node1" (ID: 1))
+            Downstream servers: OK (this node has no downstream nodes)
+            Replication slots: OK (node has no physical replication slots)
+            Missing physical replication slots: OK (node has no missing physical replication slots)
+            Configured data directory: OK (configured "data_directory" is "/var/lib/postgresql/data")</programlisting>
     </para>
   </refsect1>
   <refsect1>
@@ -57,20 +74,20 @@
 
      <listitem>
       <simpara>
-        <literal>--role</literal>: checks if the node has the expected role
+        <option>--role</option>: checks if the node has the expected role
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--replication-lag</literal>: checks if the node is lagging by more than
+        <option>--replication-lag</option>: checks if the node is lagging by more than
         <varname>replication_lag_warning</varname> or <varname>replication_lag_critical</varname>
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--archive-ready</literal>: checks for WAL files which have not yet been archived,
+        <option>--archive-ready</option>: checks for WAL files which have not yet been archived,
         and returns <literal>WARNING</literal> or <literal>CRITICAL</literal> if the number
         exceeds <varname>archive_ready_warning</varname> or <varname>archive_ready_critical</varname> respectively.
       </simpara>
@@ -78,25 +95,31 @@
 
      <listitem>
       <simpara>
-        <literal>--downstream</literal>: checks that the expected downstream nodes are attached
+        <option>--downstream</option>: checks that the expected downstream nodes are attached
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--slots</literal>: checks there are no inactive physical replication slots
+        <option>--upstream</option>: checks that the node is attached to its expected upstream
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--missing-slots</literal>: checks there are no missing physical replication slots
+        <option>--slots</option>: checks there are no inactive physical replication slots
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <literal>--data-directory-config</literal>: checks the data directory configured in
+        <option>--missing-slots</option>: checks there are no missing physical replication slots
+      </simpara>
+     </listitem>
+
+     <listitem>
+      <simpara>
+        <option>--data-directory-config</option>: checks the data directory configured in
         <filename>repmgr.conf</filename> matches the actual data directory.
         This check is not directly related to replication, but is useful to verify &repmgr;
         is correctly configured.
@@ -108,6 +131,22 @@
   </para>
   </refsect1>
 
+  <refsect1>
+    <title>Connection options</title>
+    <para>
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <option>-S</option>/<option>--superuser</option>: connect as the
+            named superuser instead of the &repmgr; user
+          </simpara>
+        </listitem>
+
+      </itemizedlist>
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Output format</title>
     <para>
@@ -115,14 +154,14 @@
 
         <listitem>
           <simpara>
-            <literal>--csv</literal>: generate output in CSV format (not available
+            <option>--csv</option>: generate output in CSV format (not available
             for individual checks)
           </simpara>
         </listitem>
 
         <listitem>
           <simpara>
-            <literal>--nagios</literal>: generate output in a Nagios-compatible format
+            <option>--nagios</option>: generate output in a Nagios-compatible format
             (for individual checks only)
           </simpara>
         </listitem>
@@ -130,13 +169,15 @@
     </para>
   </refsect1>
 
+
+
   <refsect1>
     <title>Exit codes</title>
 
     <para>
       When executing <command>repmgr node check</command> with one of the individual
       checks listed above, &repmgr; will emit one of the following Nagios-style exit codes
-      (even if <literal>--nagios</literal> is not supplied):
+      (even if <option>--nagios</option> is not supplied):
 
       <itemizedlist spacing="compact" mark="bullet">
 

doc/repmgr-node-service.xml

@@ -75,8 +75,22 @@
           <para>
             Issue a <command>CHECKPOINT</command> before stopping or restarting the node.
           </para>
+          <para>
+            Note that a superuser connection is required to be able to execute the
+             <command>CHECKPOINT</command> command.
+          </para>
         </listitem>
      </varlistentry>
+
+     <varlistentry>
+        <term><option>-S</option>/<option>--superuser</option></term>
+        <listitem>
+          <para>
+           Connect as the named superuser instead of the normal &repmgr; user.
+          </para>
+        </listitem>
+     </varlistentry>
+
     </variablelist>
 
   </refsect1>

doc/repmgr-primary-register.xml

@@ -24,10 +24,15 @@
 
     <note>
       <para>
-        It's possibly to install the &repmgr; extension manually before executing
+        &repmgr; will attempt to install the &repmgr; extension as part of this command,
+        however this will fail if the <literal>repmgr</literal> user is not a superuser.
+      </para>
+      <para>
+        It's possible to install the &repmgr; extension manually before executing
         <command>repmgr primary register</command>; in this case &repmgr; will
         detect the presence of the extension and skip that step.
       </para>
+ 
     </note>
 
   </refsect1>
@@ -59,6 +64,21 @@
 
   </refsect1>
 
+  <refsect1>
+    <title>User permission requirements</title>
+    <para>
+      The <literal>repmgr</literal> user must be a superuser in order for &repmgr;
+      to be able to install the <literal>repmgr</literal> extension.
+    </para>
+    <para>
+      If this is not the case, the <literal>repmgr</literal> extension can be installed
+      manually before executing <command>repmgr primary register</command>.
+    </para>
+    <para>
+      A future &repmgr; release will enable the provision of a <option>--superuser</option>
+      name for the installation of the extension.
+    </para>
+  </refsect1>
   <refsect1>
 
     <title>Options</title>

doc/repmgr-standby-clone.xml

@@ -188,18 +188,18 @@
    </note>
   </refsect1>
 
-
+<!-- don't rename this id as it may be used in external links -->
   <refsect1 id="repmgr-standby-create-recovery-conf">
 
    <title>Using a standby cloned by another method</title>
 
    <indexterm>
-     <primary>recovery.conf</primary>
+     <primary>replication configuration</primary>
      <secondary>generating for a standby cloned by another method</secondary>
    </indexterm>
 
    <indexterm>
-     <primary>replication configuration</primary>
+     <primary>recovery.conf</primary>
      <secondary>generating for a standby cloned by another method</secondary>
    </indexterm>
 
@@ -224,7 +224,7 @@
      </para>
    </tip>
    <para>
-     Then execute the command <command>repmgr standby clone --recovery-conf-only</command>.
+     Then execute the command <command>repmgr standby clone --replication-conf-only</command>.
      This will create the <filename>recovery.conf</filename> file needed to attach
      the node to its upstream (in PostgreSQL 12 and later: append replication configuration
      to <filename>postgresql.auto.conf</filename>), and will also create a replication slot on the
@@ -236,7 +236,7 @@
      <option>-F/--force</option> option is provided.
    </para>
    <para>
-     Execute <command>repmgr standby clone --recovery-conf-only --dry-run</command>
+     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.
@@ -266,7 +266,7 @@
             Check prerequisites but don't actually clone the standby.
           </para>
           <para>
-            If <option>--recovery-conf-only</option> specified, the contents of
+            If <option>--replication-conf-only</option> specified, the contents of
             the generated recovery configuration will be displayed
             but not written.
           </para>
@@ -312,7 +312,7 @@
       </varlistentry>
 
       <varlistentry>
-        <term><option> --recovery-conf-only</option></term>
+        <term><option>--replication-conf-only</option></term>
         <listitem>
           <para>
             Create recovery configuration for a previously cloned instance.

doc/repmgr-standby-promote.xml

@@ -86,6 +86,7 @@
   </refsect1>
 
 
+
   <refsect1>
     <title>Example</title>
     <para>
@@ -101,6 +102,40 @@
   </refsect1>
 
 
+  <refsect1>
+    <title>User permission requirements</title>
+    <para><emphasis>pg_promote() (PostgreSQL 12 and later)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; will attempt to use the built-in <function>pg_promote()</function>
+      function to promote a standby to primary.
+    </para>
+    <para>
+      By default, execution of <function>pg_promote()</function> is restricted to superusers.
+      If the <literal>repmgr</literal> user does not have permission to execute
+      <function>pg_promote()</function>, &repmgr; will fall back to using &quot;<command>pg_ctl promote</command>&quot;.
+    </para>
+    <tip>
+      <para>
+        Execute <command>repmgr standby promote</command> with the <option>--dry-run</option>
+        to check whether the &repmgr; user has permission to execute <function>pg_promote()</function>.
+      </para>
+      <para>
+        If the <literal>repmgr</literal> user is not a superuser, execution permission for this
+        function can be granted with e.g.:
+        <programlisting>
+    GRANT EXECUTE ON FUNCTION pg_catalog.pg_promote TO repmgr</programlisting>
+      </para>
+      <para>
+        Note that permissions are only effective for the database they are granted in, so
+        this <emphasis>must</emphasis> be executed in the &repmgr; database to be effective.
+      </para>
+    </tip>
+    <para>
+      For more details on <function>pg_promote()</function>, see the
+      <ulink url="https://www.postgresql.org/docs/current/functions-admin.html#FUNCTIONS-RECOVERY-CONTROL-TABLE">PostgreSQL documentation</ulink>.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Options</title>
     <variablelist>
@@ -172,6 +207,23 @@
 		 </simpara>
 	   </listitem>
 
+       <listitem>
+        <indexterm>
+          <primary>service_promote_command</primary>
+          <secondary>with &quot;repmgr standby promote &quot;</secondary>
+        </indexterm>
+         <simpara>
+           <literal>service_promote_command</literal>:
+           a command which will be executed instead of <command>pg_ctl promote</command>
+           or (in PostgreSQL 12 and later) <function>pg_promote()</function>.
+         </simpara>
+         <simpara>
+           This is intended for systems which provide a package-level promote command,
+           such as Debian's <application>pg_ctlcluster</application>, to promote the
+           PostgreSQL from standby to primary.
+         </simpara>
+       </listitem>
+
 	  </itemizedlist>
 	</para>
 

doc/repmgr-standby-register.xml

@@ -111,7 +111,7 @@
      <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command>
      command), register the node as detailed in section
      <xref linkend="repmgr-standby-register-inactive-node"/> then execute
-     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
+     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --replication-conf-only</link>
      to generate the appropriate replication configuration.
     </para>
   </refsect1>

doc/repmgr-standby-switchover.xml

@@ -63,6 +63,38 @@
   </refsect1>
 
   <refsect1>
+    <title>User permission requirements</title>
+    <para><emphasis>CHECKPOINT</emphasis></para>
+    <para>
+      &repmgr; executes <command>CHECKPOINT</command> on the demotion candidate as part of the shutdown
+      process to ensure it shuts down as smoothly as possible.
+    </para>
+    <para>
+      Note that <command>CHECKPOINT</command> requires database superuser permissions to execute.
+      If the <literal>repmgr</literal> user is not a superuser, the name of a superuser should be
+      provided with the <option>-S</option>/<option>--superuser</option>.
+    </para>
+    <para>
+      If &repmgr; is unable to execute the <command>CHECKPOINT</command> command, the switchover
+      can still be carried out, albeit at a greater risk that the demotion candidate may not
+      be able to shut down as smoothly as might otherwise have been the case.
+    </para>
+    <para><emphasis>pg_promote() (PostgreSQL 12 and later)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; defaults to using the built-in <command>pg_promote()</command> function to
+      promote a standby to primary.
+    </para>
+    <para>
+      Note that execution of <function>pg_promote()</function> is restricted to superusers or to
+      any user who has been granted execution permission for this function. If the &repmgr; user
+      is not permitted to execute <function>pg_promote()</function>, &repmgr; will fall back to using
+      &quot;<command>pg_ctl promote</command>&quot;. For more details see
+      <link linkend="repmgr-standby-promote">repmgr standby promote</link>.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
     <title>Options</title>
     <variablelist>
 
@@ -184,6 +216,17 @@
           </note>
         </listitem>
       </varlistentry>
+
+     <varlistentry>
+        <term><option>-S</option>/<option>--superuser</option></term>
+        <listitem>
+          <para>
+            Use the named superuser instead of the normal &repmgr; user to perform
+            actions requiring superuser permissions.
+          </para>
+        </listitem>
+     </varlistentry>
+
     </variablelist>
 
   </refsect1>

doc/repmgr.xml

@@ -91,7 +91,6 @@
   &repmgrd-automatic-failover;
   &repmgrd-configuration;
   &repmgrd-operation;
-  &repmgrd-bdr;
  </part>
 
  <part id="repmgr-command-reference">

doc/repmgrd-automatic-failover.xml

@@ -192,8 +192,8 @@
     connected. Beginning with <link linkend="release-4.4">&repmgr; 4.4</link>
     it is now possible for the affected standbys to build a consensus about whether
     the primary is still available to some standbys (&quot;primary visibility consensus&quot;).
-    This is done by polling each standby for the time it last saw the primary;
+    This is done by polling each standby (and the witness, if present) for the time it last saw the
-    if any have seen the primary very recently, it's reasonable
+    primary; if any have seen the primary very recently, it's reasonable
     to infer that the primary is still available and a failover should not be started.
   </para>
 
@@ -205,9 +205,10 @@
     <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
- 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
+ 1  | node1 | primary | * running |          | running | 27259 | no      | n/a
- 2  | node2 | standby |   running | node1    | running | 96572 | no      | 1 second(s) ago
+ 2  | node2 | standby |   running | node1    | running | 27272 | no      | 1 second(s) ago
- 3  | node3 | standby |   running | node1    | running | 96584 | no      | 0 second(s) ago</programlisting>
+ 3  | node3 | standby |   running | node1    | running | 27282 | no      | 0 second(s) ago
+ 4  | node4 | witness | * running | node1    | running | 27298 | no      | 1 second(s) ago</programlisting>
 
   </para>
 

doc/repmgrd-bdr.xml

@@ -1,429 +0,0 @@
-<chapter id="repmgrd-bdr">
-  <title>BDR failover with repmgrd</title>
-
-  <indexterm>
-    <primary>repmgrd</primary>
-    <secondary>BDR</secondary>
-  </indexterm>
-
-  <indexterm>
-    <primary>BDR</primary>
-  </indexterm>
-
-  <para>
-    &repmgr; 4.x provides support for monitoring a pair of BDR 2.x nodes and taking action in
-    case one of the nodes fails.
-  </para>
-  <note>
-    <simpara>
-      Due to the nature of BDR 1.x/2.x, it's only safe to use this solution for
-      a two-node scenario. Introducing additional nodes will create an inherent
-      risk of node desynchronisation if a node goes down without being cleanly
-      removed from the cluster.
-    </simpara>
-  </note>
-  <para>
-    In contrast to streaming replication, there's no concept of "promoting" a new
-    primary node with BDR. Instead, "failover" involves monitoring both nodes
-    with &repmgrd; and redirecting queries from the failed node to the remaining
-    active node. This can be done by using an
-    <link linkend="event-notifications">event notification</link> script
-    which is called by &repmgrd; to dynamically
-    reconfigure a proxy server/connection pooler such as <application>PgBouncer</application>.
-  </para>
-
-  <note>
-    <simpara>
-      This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
-      It is <emphasis>not</emphasis> required for later BDR versions.
-    </simpara>
-  </note>
-
-  <sect1 id="bdr-prerequisites" xreflabel="BDR prequisites">
-    <title>Prerequisites</title>
-    <important>
-      <para>
-        This &repmgr; functionality is for BDR 2.x only running on PostgreSQL 9.4/9.6.
-        It is <emphasis>not</emphasis> required for later BDR versions.
-      </para>
-    </important>
-    <para>
-      &repmgr; 4 requires PostgreSQL 9.4 or 9.6 with the BDR 2 extension
-      enabled and configured for a two-node BDR network. &repmgr; 4 packages
-      must be installed on each node before attempting to configure
-      <application>repmgr</application>.
-    </para>
-    <note>
-      <simpara>
-        &repmgr; 4 will refuse to install if it detects more than two BDR nodes.
-      </simpara>
-    </note>
-    <para>
-      Application database connections *must* be passed through a proxy server/
-      connection pooler such as <application>PgBouncer</application>, and it must be possible to dynamically
-      reconfigure that from &repmgrd;. The example demonstrated in this document
-      will use <application>PgBouncer</application>
-    </para>
-    <para>
-      The proxy server / connection poolers must <emphasis>not</emphasis>
-      be installed on the database servers.
-    </para>
-    <para>
-      For this example, it's assumed password-less SSH connections are available
-      from the PostgreSQL servers to the servers where <application>PgBouncer</application>
-      runs, and that the user on those servers has permission to alter the
-      <application>PgBouncer</application> configuration files.
-    </para>
-    <para>
-      PostgreSQL connections must be possible between each node, and each node
-      must be able to connect to each PgBouncer instance.
-    </para>
-  </sect1>
-
-  <sect1 id="bdr-configuration" xreflabel="BDR configuration">
-    <title>Configuration</title>
-    <para>
-      A sample configuration for <filename>repmgr.conf</filename> on each
-      BDR node would look like this:
-      <programlisting>
-        # Node information
-        node_id=1
-        node_name='node1'
-        conninfo='host=node1 dbname=bdrtest user=repmgr connect_timeout=2'
-        data_directory='/var/lib/postgresql/data'
-        replication_type='bdr'
-
-        # Event notification configuration
-        event_notifications=bdr_failover
-        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&amp;1'
-
-        # repmgrd options
-        monitor_interval_secs=5
-        reconnect_attempts=6
-        reconnect_interval=5</programlisting>
-    </para>
-    <para>
-      Adjust settings as appropriate; copy and adjust for the second node (particularly
-      the values <varname>node_id</varname>, <varname>node_name</varname>
-      and <varname>conninfo</varname>).
-    </para>
-    <para>
-      Note that the values provided for the <varname>conninfo</varname> string
-      must be valid for connections from <emphasis>both</emphasis> nodes in the
-      replication cluster. The database must be the BDR-enabled database.
-    </para>
-    <para>
-      If defined, the <varname>event_notifications</varname> parameter will restrict
-      execution of the script defined in  <varname>event_notification_command</varname>
-      to the specified event(s).
-    </para>
-    <note>
-      <simpara>
-        <varname>event_notification_command</varname> is the script which does the actual "heavy lifting"
-        of reconfiguring the proxy server/ connection pooler. It is fully
-        user-definable; see section <xref linkend="bdr-event-notification-command"/> for a reference
-        implementation.
-      </simpara>
-    </note>
-
-  </sect1>
-
-  <sect1 id="bdr-repmgr-setup" xreflabel="repmgr setup with BDR">
-    <title>repmgr setup</title>
-    <para>
-      Register both nodes; example on <literal>node1</literal>:
-      <programlisting>
-        $ repmgr -f /etc/repmgr.conf bdr register
-        NOTICE: attempting to install extension "repmgr"
-        NOTICE: "repmgr" extension successfully installed
-        NOTICE: node record created for node 'node1' (ID: 1)
-        NOTICE: BDR node 1 registered (conninfo: host=node1 dbname=bdrtest user=repmgr)</programlisting>
-    </para>
-    <para>
-      and on <literal>node1</literal>:
-      <programlisting>
-        $ repmgr -f /etc/repmgr.conf bdr register
-        NOTICE: node record created for node 'node2' (ID: 2)
-        NOTICE: BDR node 2 registered (conninfo: host=node2 dbname=bdrtest user=repmgr)</programlisting>
-    </para>
-    <para>
-      The <literal>repmgr</literal> extension will be automatically created
-      when the first node is registered, and will be propagated to the second
-      node.
-    </para>
-    <important>
-      <simpara>
-        Ensure the &repmgr; package is available on both nodes before
-        attempting to register the first node.
-      </simpara>
-    </important>
-    <para>
-      At this point the meta data for both nodes has been created; executing
-      <xref linkend="repmgr-cluster-show"/> (on either node) should produce output like this:
-      <programlisting>
-        $ repmgr -f /etc/repmgr.conf cluster show
-        ID | Name  | Role | Status    | Upstream | Location | Connection string
-       ----+-------+------+-----------+----------+--------------------------------------------------------
-        1  | node1 | bdr  | * running |          | default  | host=node1 dbname=bdrtest user=repmgr connect_timeout=2
-        2  | node2 | bdr  | * running |          | default  | host=node2 dbname=bdrtest user=repmgr connect_timeout=2</programlisting>
-    </para>
-    <para>
-      Additionally it's possible to display log of significant events;  executing
-      <xref linkend="repmgr-cluster-event"/> (on either node) should produce output like this:
-      <programlisting>
-        $ repmgr -f /etc/repmgr.conf cluster event
-        Node ID | Event        | OK | Timestamp           | Details
-       ---------+--------------+----+---------------------+----------------------------------------------
-        2       | bdr_register | t  | 2017-07-27 17:51:48 | node record created for node 'node2' (ID: 2)
-        1       | bdr_register | t  | 2017-07-27 17:51:00 | node record created for node 'node1' (ID: 1)
-      </programlisting>
-    </para>
-    <para>
-      At this point there will only be records for the two node registrations (displayed here
-      in reverse chronological order).
-    </para>
-  </sect1>
-
-  <sect1 id="bdr-event-notification-command" xreflabel="Defining the BDR failover &quot;event_notification command&quot;">
-    <title>Defining the BDR failover "event_notification_command"</title>
-    <para>
-      Key to "failover" execution is the <literal>event_notification_command</literal>,
-      which is a user-definable script specified in <filename>repmpgr.conf</filename>
-      and which can use a &repmgr; <link linkend="event-notifications">event notification</link>
-      to reconfigure the proxy server / connection pooler so it points to the other, still-active node.
-      Details of the event will be passed as parameters to the script.
-    </para>
-    <para>
-      Following parameter placeholders are available for the script definition in <filename>repmpgr.conf</filename>;
-      these will be replaced with the appropriate value when the script is executed:
-    </para>
-
-    <variablelist>
-      <varlistentry>
-        <term><option>%n</option></term>
-        <listitem>
-          <para>
-            node ID
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>%e</option></term>
-        <listitem>
-          <para>
-            event type
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>%t</option></term>
-        <listitem>
-          <para>
-            success (1 or 0)
-          </para>
-        </listitem>
-      </varlistentry>
-      <varlistentry>
-        <term><option>%t</option></term>
-        <listitem>
-          <para>
-            timestamp
-          </para>
-        </listitem>
-      </varlistentry>
-
-      <varlistentry>
-        <term><option>%d</option></term>
-        <listitem>
-          <para>
-            details
-          </para>
-        </listitem>
-      </varlistentry>
-      <varlistentry>
-        <term><option>%c</option></term>
-        <listitem>
-          <para>
-            conninfo string of the next available node (<varname>bdr_failover</varname> and <varname>bdr_recovery</varname>)
-          </para>
-        </listitem>
-      </varlistentry>
-      <varlistentry>
-        <term><option>%a</option></term>
-        <listitem>
-          <para>
-            name of the next available node (<varname>bdr_failover</varname> and <varname>bdr_recovery</varname>)
-          </para>
-        </listitem>
-      </varlistentry>
-    </variablelist>
-
-    <para>
-      Note that <literal>%c</literal> and <literal>%a</literal> are only provided with
-      particular failover events, in this case <varname>bdr_failover</varname>.
-    </para>
-    <para>
-      The provided sample script
-     (<literal><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/scripts/bdr-pgbouncer.sh">scripts/bdr-pgbouncer.sh</ulink></literal>)
-      is configured as follows:
-      <programlisting>
-        event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a"'</programlisting>
-    </para>
-    <para>
-      and parses the placeholder parameters like this:
-      <programlisting>
-        NODE_ID=$1
-        EVENT_TYPE=$2
-        SUCCESS=$3
-        NEXT_CONNINFO=$4
-        NEXT_NODE_NAME=$5</programlisting>
-    </para>
-    <note>
-      <para>
-        The sample script also contains some hard-coded values for the <application>PgBouncer</application>
-        configuration for both nodes; these will need to be adjusted for your local environment
-        (ideally the scripts would be maintained as templates and generated by some
-        kind of provisioning system).
-      </para>
-    </note>
-
-    <para>
-      The script performs following steps:
-      <itemizedlist spacing="compact" mark="bullet">
-        <listitem>
-          <simpara>pauses <application>PgBouncer</application> on all nodes</simpara>
-        </listitem>
-        <listitem>
-          <simpara>recreates the <application>PgBouncer</application> configuration file on each
-            node using the information provided by &repmgrd;
-            (primarily the <varname>conninfo</varname> string) to configure
-            <application>PgBouncer</application></simpara>
-        </listitem>
-        <listitem>
-          <simpara>reloads the <application>PgBouncer</application> configuration</simpara>
-        </listitem>
-        <listitem>
-          <simpara>executes the <command>RESUME</command> command (in <application>PgBouncer</application>)</simpara>
-        </listitem>
-      </itemizedlist>
-    </para>
-    <para>
-      Following successful script execution, any connections to PgBouncer on the failed BDR node
-      will be redirected to the active node.
-    </para>
-  </sect1>
-
-  <sect1 id="bdr-monitoring-failover" xreflabel="Node monitoring and failover">
-    <title>Node monitoring and failover</title>
-    <para>
-      At the intervals specified by <varname>monitor_interval_secs</varname>
-      in <filename>repmgr.conf</filename>, &repmgrd;
-      will ping each node to check if it's available. If a node isn't available,
-      &repmgrd; will enter failover mode and check <varname>reconnect_attempts</varname>
-      times at intervals of <varname>reconnect_interval</varname> to confirm the node is definitely unreachable.
-      This buffer period is necessary to avoid false positives caused by transient
-      network outages.
-    </para>
-    <para>
-      If the node is still unavailable, &repmgrd; will enter failover mode and execute
-      the script defined in <varname>event_notification_command</varname>; an entry will be logged
-      in the <literal>repmgr.events</literal> table and &repmgrd; will
-      (unless otherwise configured) resume monitoring of the node in "degraded" mode until it reappears.
-    </para>
-    <para>
-      &repmgrd; logfile output during a failover event will look something like this
-      on one node (usually the node which has failed, here <literal>node2</literal>):
-      <programlisting>
-            ...
-    [2017-07-27 21:08:39] [INFO] starting continuous BDR node monitoring
-    [2017-07-27 21:08:39] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:08:55] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:11] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
-    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
-    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
-    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
-    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
-    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
-    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
-    [2017-07-27 21:09:28] [NOTICE] setting node record for node 2 to inactive
-    [2017-07-27 21:09:28] [INFO] executing notification command for event "bdr_failover"
-    [2017-07-27 21:09:28] [DETAIL] command is:
-      /path/to/bdr-pgbouncer.sh 2 bdr_failover 1 "host=host=node1 dbname=bdrtest user=repmgr connect_timeout=2" "node1"
-    [2017-07-27 21:09:28] [INFO] node 'node2' (ID: 2) detected as failed; next available node is 'node1' (ID: 1)
-    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-    ...</programlisting>
-    </para>
-    <para>
-      Output on the other node (<literal>node1</literal>) during the same event will look like this:
-      <programlisting>
-    ...
-    [2017-07-27 21:08:35] [INFO] starting continuous BDR node monitoring
-    [2017-07-27 21:08:35] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:08:51] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:07] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:23] [WARNING] unable to connect to node node2 (ID 2)
-    [2017-07-27 21:09:23] [INFO] checking state of node 2, 0 of 5 attempts
-    [2017-07-27 21:09:23] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:24] [INFO] checking state of node 2, 1 of 5 attempts
-    [2017-07-27 21:09:24] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:25] [INFO] checking state of node 2, 2 of 5 attempts
-    [2017-07-27 21:09:25] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:26] [INFO] checking state of node 2, 3 of 5 attempts
-    [2017-07-27 21:09:26] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:27] [INFO] checking state of node 2, 4 of 5 attempts
-    [2017-07-27 21:09:27] [INFO] sleeping 1 seconds until next reconnection attempt
-    [2017-07-27 21:09:28] [WARNING] unable to reconnect to node 2 after 5 attempts
-    [2017-07-27 21:09:28] [NOTICE] other node's repmgrd is handling failover
-    [2017-07-27 21:09:28] [INFO] monitoring BDR replication status on node "node1" (ID: 1)
-    [2017-07-27 21:09:28] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-    ...</programlisting>
-    </para>
-    <para>
-      This assumes only the PostgreSQL instance on <literal>node2</literal> has failed. In this case the
-      &repmgrd; instance running on <literal>node2</literal> has performed the failover. However if
-      the entire server becomes unavailable, &repmgrd; on <literal>node1</literal> will perform
-      the failover.
-    </para>
-  </sect1>
-  <sect1 id="bdr-node-recovery" xreflabel="Node recovery">
-    <title>Node recovery</title>
-    <para>
-      Following failure of a BDR node, if the node subsequently becomes available again,
-      a <varname>bdr_recovery</varname> event will be generated. This could potentially be used to
-      reconfigure PgBouncer automatically to bring the node back into the available pool,
-      however it would be prudent to manually verify the node's status before
-      exposing it to the application.
-    </para>
-    <para>
-      If the failed node comes back up and connects correctly, output similar to this
-      will be visible in the &repmgrd; log:
-      <programlisting>
-        [2017-07-27 21:25:30] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-        [2017-07-27 21:25:46] [INFO] monitoring BDR replication status on node "node2" (ID: 2)
-        [2017-07-27 21:25:46] [DETAIL] monitoring node "node2" (ID: 2) in degraded mode
-        [2017-07-27 21:25:55] [INFO] active replication slot for node "node1" found after 1 seconds
-        [2017-07-27 21:25:55] [NOTICE] node "node2" (ID: 2) has recovered after 986 seconds</programlisting>
-    </para>
-  </sect1>
-
-  <sect1 id="bdr-complete-shutdown" xreflabel="Shutdown of both nodes">
-    <title>Shutdown of both nodes</title>
-    <para>
-      If both PostgreSQL instances are shut down, &repmgrd; will try and handle the
-      situation as gracefully as possible, though with no failover candidates available
-      there's not much it can do. Should this case ever occur, we recommend shutting
-      down &repmgrd; on both nodes and restarting it once the PostgreSQL instances
-      are running properly.
-    </para>
-  </sect1>
-</chapter>
-

doc/repmgrd-configuration.xml

@@ -394,8 +394,8 @@
             </indexterm>
 
             <para>
-              If <literal>true</literal>, only continue with failover if no standbys have seen
+              If <literal>true</literal>, only continue with failover if no standbys
-			  the primary node recently.
+              (or the witness server, if present) have seen the primary node recently.
             </para>
             <note>
               <para>
@@ -486,6 +486,23 @@
 
     </sect2>
 
+
+    <sect2 id="repmgrd-automatic-failover-configuration-pgbouncer-fencing">
+      <title>Configuring &repmgrd; and pgbouncer to fence a failed primary node</title>
+      <indexterm>
+        <primary>fencing</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>PgBouncer</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </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>.
+      </para>
+    </sect2>
+
     <sect2 id="postgresql-service-configuration">
       <title>PostgreSQL service configuration</title>
 
@@ -602,18 +619,6 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
           </simpara>
         </listitem>
 
-        <listitem>
-          <simpara>
-            <varname>bdr_local_monitoring_only</varname>
-          </simpara>
-        </listitem>
-
-        <listitem>
-          <simpara>
-            <varname>bdr_recovery_timeout</varname>
-          </simpara>
-        </listitem>
-
          <listitem>
           <simpara>
             <varname>child_nodes_check_interval</varname>

doc/repmgrd-node-fencing.md

@@ -108,7 +108,7 @@ The actual script is as follows; adjust the configurable items as appropriate:
 
     # 1. Promote this node from standby to primary
 
-    repmgr standby promote -f /etc/repmgr.conf
+    repmgr standby promote -f /etc/repmgr.conf --log-to-file
 
     # 2. Reconfigure pgbouncer instances
 
@@ -146,7 +146,7 @@ Script and template file should be installed on each node where `repmgrd` is run
 Finally, set `promote_command` in `repmgr.conf` on each node to
 point to the custom promote script:
 
-    promote_command=/var/lib/postgres/repmgr/promote.sh
+    promote_command='/var/lib/postgres/repmgr/promote.sh'
 
 and reload/restart any running `repmgrd` instances for the changes to take
 effect.

doc/switchover.xml

@@ -186,6 +186,7 @@
       NOTICE: local node "node2" (ID: 2) will be promoted to primary; current primary "node1" (ID: 1) will be demoted to standby
       INFO: following shutdown command would be run on node "node1":
         "pg_ctl -l /var/log/postgresql/startup.log -D '/var/lib/postgresql/data' -m fast -W stop"
+      INFO: parameter "shutdown_check_timeout" is set to 60 seconds
     </programlisting>
    </para>
 

doc/upgrading-repmgr.xml

@@ -269,6 +269,29 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 	</para>
   </tip>
 
+  <sect2 id="upgrading-pg-upgrade-standby" xreflabel="pg_upgrade and upgrading standbys">
+    <title>Upgrading standbys with pg_upgrade and rsync</title>
+    <para>
+      If you are intending to upgrade a standby using the <command>rsync</command> method described
+      in the <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html#PGUPGRADE-STEP-REPLICAS">pg_upgrade documentation</ulink>,
+      you <emphasis>must</emphasis> ensure the standby's replication configuration is present and correct
+      before starting the standby.
+    </para>
+    <para>
+      Use <link linkend="repmgr-standby-clone">repmgr standby clone --replication-conf-only</link> to generate
+      the correct replication configuration.
+    </para>
+
+    <tip>
+	  <para>
+        If upgrading from PostgreSQL 11 or earlier, be sure to delete <filename>recovery.conf</filename>, if present,
+        otherwise PostgreSQL will refuse to start.
+      </para>
+    </tip>
+
+  </sect2>
+
+
  </sect1>
 
 

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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

expected/repmgr_extension.out

@@ -32,18 +32,6 @@ SELECT * FROM repmgr.show_nodes;
 (0 rows)
 
 -- functions
-SELECT repmgr.am_bdr_failover_handler(-1);
- am_bdr_failover_handler 
--------------------------
- 
-(1 row)
-
-SELECT repmgr.am_bdr_failover_handler(NULL);
- am_bdr_failover_handler 
--------------------------
- 
-(1 row)
-
 SELECT repmgr.get_new_primary();
  get_new_primary 
 -----------------
@@ -92,9 +80,3 @@ SELECT repmgr.standby_set_last_updated();
  
 (1 row)
 
-SELECT repmgr.unset_bdr_failover_handler();
- unset_bdr_failover_handler 
-----------------------------
- 
-(1 row)
-

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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--5.0--5.1.sql

@@ -0,0 +1,5 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+DROP FUNCTION am_bdr_failover_handler(INT);
+DROP FUNCTION unset_bdr_failover_handler();

repmgr--5.0.sql

@@ -153,16 +153,6 @@ CREATE FUNCTION reset_voting_status()
   AS 'MODULE_PATHNAME', 'reset_voting_status'
   LANGUAGE C STRICT;
 
-CREATE FUNCTION am_bdr_failover_handler(INT)
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'am_bdr_failover_handler'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION unset_bdr_failover_handler()
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'unset_bdr_failover_handler'
-  LANGUAGE C STRICT;
-
 CREATE FUNCTION get_repmgrd_pid()
   RETURNS INT
   AS 'MODULE_PATHNAME', 'get_repmgrd_pid'

repmgr--5.1.sql

@@ -0,0 +1,214 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+CREATE TABLE repmgr.nodes (
+  node_id          INTEGER     PRIMARY KEY,
+  upstream_node_id INTEGER     NULL REFERENCES nodes (node_id) DEFERRABLE,
+  active           BOOLEAN     NOT NULL DEFAULT TRUE,
+  node_name        TEXT        NOT NULL,
+  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
+  location         TEXT        NOT NULL DEFAULT 'default',
+  priority         INT         NOT NULL DEFAULT 100,
+  conninfo         TEXT        NOT NULL,
+  repluser         VARCHAR(63) NOT NULL,
+  slot_name        TEXT        NULL,
+  config_file      TEXT        NOT NULL
+);
+
+CREATE TABLE repmgr.events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
+DO $repmgr$
+DECLARE
+  DECLARE server_version_num INT;
+BEGIN
+  SELECT setting
+    FROM pg_catalog.pg_settings
+   WHERE name = 'server_version_num'
+    INTO server_version_num;
+  IF server_version_num >= 90400 THEN
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+  ELSE
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      TEXT NOT NULL,
+  last_wal_standby_location      TEXT,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+  END IF;
+END$repmgr$;
+
+
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+
+/* ================= */
+/* repmgrd functions */
+/* ================= */
+
+/* monitoring functions */
+
+CREATE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'set_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_local_node_id()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_local_node_id'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_set_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_set_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION standby_get_last_updated()
+  RETURNS TIMESTAMP WITH TIME ZONE
+  AS 'MODULE_PATHNAME', 'standby_get_last_updated'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION set_upstream_last_seen(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
+         );
+

repmgr--unpackaged--5.1.sql

@@ -0,0 +1,265 @@
+-- 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"
+
+ALTER TABLE repmgr.repl_events RENAME TO events;
+
+-- create new table "repmgr.voting_term"
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+INSERT INTO repmgr.voting_term (term) VALUES (1);
+
+
+-- convert "repmgr_$cluster.repl_monitor" to "monitoring_history"
+
+
+DO $repmgr$
+DECLARE
+  DECLARE server_version_num INT;
+BEGIN
+  SELECT setting
+    FROM pg_catalog.pg_settings
+   WHERE name = 'server_version_num'
+    INTO server_version_num;
+  IF server_version_num >= 90400 THEN
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
+  ELSE
+    EXECUTE $repmgr_func$
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      TEXT NOT NULL,
+  last_wal_standby_location      TEXT,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+)
+    $repmgr_func$;
+    INSERT INTO repmgr.monitoring_history
+      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
+    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag
+      FROM repmgr.repl_monitor;
+
+  END IF;
+END$repmgr$;
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+
+/* ================= */
+/* 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;
+
+-- remove temporary table
+DROP TABLE repmgr_old_schema;

repmgr-action-bdr.c

@@ -1,557 +0,0 @@
-/*
- * repmgr-action-bdr.c
- *
- * Implements BDR-related actions for the repmgr command line utility
- *
- * Copyright (c) 2ndQuadrant, 2010-2019
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "repmgr.h"
-
-#include "repmgr-client-global.h"
-#include "repmgr-action-bdr.h"
-
-
-/*
- * do_bdr_register()
- *
- * As each BDR node is its own primary, registering a BDR node
- * will create the repmgr metadata schema if necessary.
- */
-void
-do_bdr_register(void)
-{
-	PGconn	   *conn = NULL;
-	BdrNodeInfoList bdr_nodes = T_BDR_NODE_INFO_LIST_INITIALIZER;
-	ExtensionStatus extension_status = REPMGR_UNKNOWN;
-	t_node_info node_info = T_NODE_INFO_INITIALIZER;
-	RecordStatus record_status = RECORD_NOT_FOUND;
-	PQExpBufferData event_details;
-	bool		success = true;
-	char	   *dbname = NULL;
-
-	/* sanity-check configuration for BDR-compatability */
-	if (config_file_options.replication_type != REPLICATION_TYPE_BDR)
-	{
-		log_error(_("cannot run BDR REGISTER on a non-BDR node"));
-		exit(ERR_BAD_CONFIG);
-	}
-
-	dbname = pg_malloc0(MAXLEN);
-
-	if (dbname == NULL)
-	{
-		log_error(_("unable to allocate memory; terminating."));
-		exit(ERR_OUT_OF_MEMORY);
-	}
-
-	/* store the database name for future reference */
-	get_conninfo_value(config_file_options.conninfo, "dbname", dbname);
-
-	conn = establish_db_connection(config_file_options.conninfo, true);
-
-	if (!is_bdr_db(conn, NULL))
-	{
-		log_error(_("database \"%s\" is not BDR-enabled"), dbname);
-		log_hint(_("when using repmgr with BDR, the repmgr schema must be stored in the BDR database"));
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/* Check that there are at most 2 BDR nodes */
-	get_all_bdr_node_records(conn, &bdr_nodes);
-
-	if (bdr_nodes.node_count == 0)
-	{
-		log_error(_("database \"%s\" is BDR-enabled but no BDR nodes were found"), dbname);
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/* BDR 2 implementation is for 2 nodes only */
-	if (get_bdr_version_num() < 3 && bdr_nodes.node_count > 2)
-	{
-		log_error(_("repmgr can only support BDR 2.x clusters with 2 nodes"));
-		log_detail(_("this BDR cluster has %i nodes"), bdr_nodes.node_count);
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (get_bdr_version_num() > 2)
-	{
-		log_error(_("\"repmgr bdr register\" is for BDR 2.x only"));
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-
-	/* check for a matching BDR node */
-	{
-		PQExpBufferData bdr_local_node_name;
-		bool		node_match = false;
-
-		initPQExpBuffer(&bdr_local_node_name);
-		node_match = bdr_node_name_matches(conn, config_file_options.node_name, &bdr_local_node_name);
-
-		if (node_match == false)
-		{
-			if (strlen(bdr_local_node_name.data))
-			{
-				log_error(_("local node BDR node name is \"%s\", expected: \"%s\""),
-						  bdr_local_node_name.data,
-						  config_file_options.node_name);
-				log_hint(_("\"node_name\" in repmgr.conf must match \"node_name\" in bdr.bdr_nodes"));
-			}
-			else
-			{
-				log_error(_("local node does not report BDR node name"));
-				log_hint(_("ensure this is an active BDR node"));
-			}
-
-			PQfinish(conn);
-			pfree(dbname);
-			termPQExpBuffer(&bdr_local_node_name);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		termPQExpBuffer(&bdr_local_node_name);
-	}
-
-	/* check whether repmgr extension exists, and there are no non-BDR nodes registered */
-	extension_status = get_repmgr_extension_status(conn, NULL);
-
-	if (extension_status == REPMGR_UNKNOWN)
-	{
-		log_error(_("unable to determine status of \"repmgr\" extension in database \"%s\""),
-				  dbname);
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (extension_status == REPMGR_UNAVAILABLE)
-	{
-		log_error(_("\"repmgr\" extension is not available"));
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (extension_status == REPMGR_INSTALLED)
-	{
-		if (!is_bdr_repmgr(conn))
-		{
-			log_error(_("repmgr metadatabase contains records for non-BDR nodes"));
-			PQfinish(conn);
-			pfree(dbname);
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-	else
-	{
-		log_debug("creating repmgr extension in database \"%s\"", dbname);
-
-		begin_transaction(conn);
-
-		if (!create_repmgr_extension(conn))
-		{
-			log_error(_("unable to create repmgr extension - see preceding error message(s); aborting"));
-			rollback_transaction(conn);
-			pfree(dbname);
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		commit_transaction(conn);
-	}
-
-	pfree(dbname);
-
-	if (bdr_node_has_repmgr_set(conn, config_file_options.node_name) == false)
-	{
-		log_debug("bdr_node_has_repmgr_set() = false");
-		bdr_node_set_repmgr_set(conn, config_file_options.node_name);
-	}
-
-	/*
-	 * before adding the extension tables to the replication set, if any other
-	 * BDR nodes exist, populate repmgr.nodes with a copy of existing entries
-	 *
-	 * currently we won't copy the contents of any other tables
-	 *
-	 */
-	{
-		NodeInfoList local_node_records = T_NODE_INFO_LIST_INITIALIZER;
-
-		(void) get_all_node_records(conn, &local_node_records);
-
-		if (local_node_records.node_count == 0)
-		{
-			BdrNodeInfoList bdr_nodes = T_BDR_NODE_INFO_LIST_INITIALIZER;
-			BdrNodeInfoListCell *bdr_cell = NULL;
-
-			get_all_bdr_node_records(conn, &bdr_nodes);
-
-			if (bdr_nodes.node_count == 0)
-			{
-				log_error(_("unable to retrieve any BDR node records"));
-				log_detail("%s", PQerrorMessage(conn));
-				PQfinish(conn);
-				exit(ERR_BAD_CONFIG);
-			}
-
-			for (bdr_cell = bdr_nodes.head; bdr_cell; bdr_cell = bdr_cell->next)
-			{
-				PGconn	   *bdr_node_conn = NULL;
-				NodeInfoList existing_nodes = T_NODE_INFO_LIST_INITIALIZER;
-				NodeInfoListCell *cell = NULL;
-				ExtensionStatus other_node_extension_status = REPMGR_UNKNOWN;
-
-				/* skip the local node */
-				if (strncmp(node_info.node_name, bdr_cell->node_info->node_name, sizeof(node_info.node_name)) == 0)
-				{
-					continue;
-				}
-
-				log_debug("connecting to BDR node \"%s\" (conninfo: \"%s\")",
-						  bdr_cell->node_info->node_name,
-						  bdr_cell->node_info->node_local_dsn);
-				bdr_node_conn = establish_db_connection_quiet(bdr_cell->node_info->node_local_dsn);
-
-				if (PQstatus(bdr_node_conn) != CONNECTION_OK)
-				{
-					continue;
-				}
-
-				/* check repmgr schema exists, skip if not */
-				other_node_extension_status = get_repmgr_extension_status(bdr_node_conn, NULL);
-
-				if (other_node_extension_status != REPMGR_INSTALLED)
-				{
-					continue;
-				}
-
-				(void) get_all_node_records(bdr_node_conn, &existing_nodes);
-
-				for (cell = existing_nodes.head; cell; cell = cell->next)
-				{
-					log_debug("creating record for node \"%s\" (ID: %i)",
-							  cell->node_info->node_name, cell->node_info->node_id);
-					create_node_record(conn, "bdr register", cell->node_info);
-				}
-
-				PQfinish(bdr_node_conn);
-				break;
-			}
-		}
-	}
-
-	/* Add the repmgr extension tables to a replication set */
-
-	if (get_bdr_version_num() < 3)
-	{
-		add_extension_tables_to_bdr_replication_set(conn);
-	}
-	else
-	{
-		/* this is the only table we need to replicate */
-		char *replication_set = get_default_bdr_replication_set(conn);
-
-		/*
-		 * this probably won't happen, but we need to be sure we're using
-		 * the replication set metadata correctly...
-		 */
-		if (conn == NULL)
-		{
-			log_error(_("unable to retrieve default BDR replication set"));
-			log_hint(_("see preceding messages"));
-			log_debug("check query in get_default_bdr_replication_set()");
-			exit(ERR_BAD_CONFIG);
-		}
-
-		if (is_table_in_bdr_replication_set(conn, "nodes", replication_set) == false)
-		{
-			add_table_to_bdr_replication_set(conn, "nodes", replication_set);
-		}
-
-		pfree(replication_set);
-	}
-
-	initPQExpBuffer(&event_details);
-
-	begin_transaction(conn);
-
-	/*
-	 * we'll check if a record exists (even if the schema was just created),
-	 * as there's a faint chance of a race condition
-	 */
-
-	record_status = get_node_record(conn, config_file_options.node_id, &node_info);
-
-	/* Update internal node record */
-
-	node_info.type = BDR;
-	node_info.node_id = config_file_options.node_id;
-	node_info.upstream_node_id = NO_UPSTREAM_NODE;
-	node_info.active = true;
-	node_info.priority = config_file_options.priority;
-
-	strncpy(node_info.node_name, config_file_options.node_name, sizeof(node_info.node_name));
-	strncpy(node_info.location, config_file_options.location, sizeof(node_info.location));
-	strncpy(node_info.conninfo, config_file_options.conninfo, sizeof(node_info.conninfo));
-
-	if (record_status == RECORD_FOUND)
-	{
-		bool		node_updated = false;
-
-		/*
-		 * At this point we will have established there are no non-BDR
-		 * records, so no need to verify the node type
-		 */
-		if (!runtime_options.force)
-		{
-			log_error(_("this node is already registered"));
-			log_hint(_("use -F/--force to overwrite the existing node record"));
-			rollback_transaction(conn);
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		/*
-		 * don't permit changing the node name - this must match the BDR node
-		 * name set when the node was registered.
-		 */
-
-		if (strncmp(node_info.node_name, config_file_options.node_name, sizeof(node_info.node_name)) != 0)
-		{
-			log_error(_("a record for node %i is already registered with node_name \"%s\""),
-					  config_file_options.node_id, node_info.node_name);
-			log_hint(_("node_name configured in repmgr.conf is \"%s\""), config_file_options.node_name);
-
-			rollback_transaction(conn);
-			PQfinish(conn);
-			exit(ERR_BAD_CONFIG);
-		}
-
-		node_updated = update_node_record(conn, "bdr register", &node_info);
-
-		if (node_updated == true)
-		{
-			appendPQExpBuffer(&event_details, _("node record updated for node \"%s\" (%i)"),
-							  config_file_options.node_name, config_file_options.node_id);
-			log_verbose(LOG_NOTICE, "%s", event_details.data);
-		}
-		else
-		{
-			success = false;
-		}
-
-	}
-	else
-	{
-		/* create new node record */
-		bool		node_created = create_node_record(conn, "bdr register", &node_info);
-
-		if (node_created == true)
-		{
-			appendPQExpBuffer(&event_details,
-							  _("node record created for node \"%s\" (ID: %i)"),
-							  config_file_options.node_name, config_file_options.node_id);
-			log_notice("%s", event_details.data);
-		}
-		else
-		{
-			success = false;
-		}
-	}
-
-	if (success == false)
-	{
-		rollback_transaction(conn);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
-	}
-
-	commit_transaction(conn);
-	/* Log the event */
-	create_event_notification(
-							  conn,
-							  &config_file_options,
-							  config_file_options.node_id,
-							  "bdr_register",
-							  true,
-							  event_details.data);
-
-	termPQExpBuffer(&event_details);
-
-	PQfinish(conn);
-
-	log_notice(_("BDR node %i registered (conninfo: %s)"),
-			   config_file_options.node_id, config_file_options.conninfo);
-
-	return;
-}
-
-
-void
-do_bdr_unregister(void)
-{
-	PGconn	   *conn = NULL;
-	ExtensionStatus extension_status = REPMGR_UNKNOWN;
-	int			target_node_id = UNKNOWN_NODE_ID;
-	t_node_info node_info = T_NODE_INFO_INITIALIZER;
-	RecordStatus record_status = RECORD_NOT_FOUND;
-	bool		node_record_deleted = false;
-	PQExpBufferData event_details;
-	char	   *dbname;
-
-	/* sanity-check configuration for BDR-compatability */
-
-	if (config_file_options.replication_type != REPLICATION_TYPE_BDR)
-	{
-		log_error(_("cannot run BDR UNREGISTER on a non-BDR node"));
-		exit(ERR_BAD_CONFIG);
-	}
-
-	dbname = pg_malloc0(MAXLEN);
-
-	if (dbname == NULL)
-	{
-		log_error(_("unable to allocate memory; terminating."));
-		exit(ERR_OUT_OF_MEMORY);
-	}
-
-	/* store the database name for future reference */
-	get_conninfo_value(config_file_options.conninfo, "dbname", dbname);
-
-	conn = establish_db_connection(config_file_options.conninfo, true);
-
-	if (!is_bdr_db(conn, NULL))
-	{
-		log_error(_("database \"%s\" is not BDR-enabled"), dbname);
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	extension_status = get_repmgr_extension_status(conn, NULL);
-	if (extension_status != REPMGR_INSTALLED)
-	{
-		log_error(_("repmgr is not installed on database \"%s\""), dbname);
-		PQfinish(conn);
-		pfree(dbname);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	pfree(dbname);
-
-	if (!is_bdr_repmgr(conn))
-	{
-		log_error(_("repmgr metadatabase contains records for non-BDR nodes"));
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	initPQExpBuffer(&event_details);
-	if (runtime_options.node_id != UNKNOWN_NODE_ID)
-		target_node_id = runtime_options.node_id;
-	else
-		target_node_id = config_file_options.node_id;
-
-
-	/* Check node exists and is really a BDR node */
-	record_status = get_node_record(conn, target_node_id, &node_info);
-
-	if (record_status != RECORD_FOUND)
-	{
-		log_error(_("no record found for node %i"), target_node_id);
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	begin_transaction(conn);
-
-	log_debug("unregistering node %i", target_node_id);
-
-	node_record_deleted = delete_node_record(conn, target_node_id);
-
-	if (node_record_deleted == false)
-	{
-		appendPQExpBuffer(&event_details,
-						  "unable to delete node record for node \"%s\" (ID: %i)",
-						  node_info.node_name,
-						  target_node_id);
-		rollback_transaction(conn);
-	}
-	else
-	{
-		appendPQExpBuffer(&event_details,
-						  "node record deleted for node \"%s\" (ID: %i)",
-						  node_info.node_name,
-						  target_node_id);
-		commit_transaction(conn);
-	}
-
-
-	/* Log the event */
-	create_event_notification(
-							  conn,
-							  &config_file_options,
-							  config_file_options.node_id,
-							  "bdr_unregister",
-							  true,
-							  event_details.data);
-
-	PQfinish(conn);
-
-	log_notice(_("bdr node \"%s\" (ID: %i) successfully unregistered"),
-			   node_info.node_name, target_node_id);
-
-	termPQExpBuffer(&event_details);
-
-	return;
-}
-
-
-void
-do_bdr_help(void)
-{
-	print_help_header();
-
-	printf(_("Usage:\n"));
-	printf(_("    %s [OPTIONS] bdr register\n"), progname());
-	printf(_("    %s [OPTIONS] bdr unregister\n"), progname());
-	puts("");
-
-	printf(_("BDR REGISTER\n"));
-	puts("");
-	printf(_("  \"bdr register\" initialises the repmgr cluster and registers the initial bdr node.\n"));
-	puts("");
-	printf(_("  -F, --force                         overwrite an existing node record\n"));
-	puts("");
-
-	printf(_("BDR UNREGISTER\n"));
-	puts("");
-	printf(_("  \"bdr unregister\" unregisters an inactive BDR node.\n"));
-	puts("");
-	printf(_("  --node-id                           ID node to unregister (optional, used when the node to unregister\n" \
-			 "                                        is offline)\n"));
-	puts("");
-}

repmgr-action-bdr.h

@@ -1,28 +0,0 @@
-/*
- * repmgr-action-bdr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _REPMGR_ACTION_BDR_H_
-#define _REPMGR_ACTION_BDR_H_
-
-extern void do_bdr_register(void);
-extern void do_bdr_unregister(void);
-
-extern void do_bdr_help(void);
-
-
-#endif							/* _REPMGR_ACTION_BDR_H_ */

repmgr-action-cluster.c

@@ -3,7 +3,7 @@
  *
  * Implements cluster information actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -67,6 +67,8 @@ static void cube_set_node_status(t_node_status_cube **cube, int n, int node_id,
  * Parameters:
  *   --compact
  *   --csv
+ *   --terse
+ *   --verbose
  */
 void
 do_cluster_show(void)
@@ -206,7 +208,8 @@ do_cluster_show(void)
 		else
 		{
 			/* NOP on pre-9.6 servers */
-			cell->node_info->replication_info->timeline_id = get_node_timeline(cell->node_info->conn);
+			cell->node_info->replication_info->timeline_id = get_node_timeline(cell->node_info->conn,
+																			   cell->node_info->replication_info->timeline_id_str);
 		}
 
 		initPQExpBuffer(&node_status);
@@ -244,18 +247,13 @@ do_cluster_show(void)
 
 		headers_show[SHOW_LOCATION].cur_length = strlen(cell->node_info->location);
 
-		if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
+		/* Format timeline ID */
+		if (cell->node_info->type == WITNESS)
 		{
-			/* display "?" */
+			/* The witness node's timeline ID is irrelevant */
-			headers_show[SHOW_PRIORITY].cur_length = 1;
+			strncpy(cell->node_info->replication_info->timeline_id_str, _("n/a"), MAXLEN);
-		}
-		else
-		{
-			initPQExpBuffer(&buf);
-			appendPQExpBuffer(&buf, "%i", cell->node_info->replication_info->timeline_id);
-			headers_show[SHOW_PRIORITY].cur_length = strlen(buf.data);
-			termPQExpBuffer(&buf);
 		}
+		headers_show[SHOW_TIMELINE_ID].cur_length = strlen(cell->node_info->replication_info->timeline_id_str);
 
 		headers_show[SHOW_CONNINFO].cur_length = strlen(cell->node_info->conninfo);
 
@@ -322,10 +320,7 @@ do_cluster_show(void)
 
 			if (headers_show[SHOW_TIMELINE_ID].display == true)
 			{
-				if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
+				printf("| %-*s ", headers_show[SHOW_TIMELINE_ID].max_length, cell->node_info->replication_info->timeline_id_str);
-					printf("| %-*c ", headers_show[SHOW_TIMELINE_ID].max_length, '?');
-				else
-					printf("| %-*i ", headers_show[SHOW_TIMELINE_ID].max_length, (int)cell->node_info->replication_info->timeline_id);
 			}
 
 			if (headers_show[SHOW_CONNINFO].display == true)
@@ -343,14 +338,25 @@ do_cluster_show(void)
 	/* emit any warnings */
 	if (warnings.head != NULL && runtime_options.terse == false && runtime_options.output_mode != OM_CSV)
 	{
-		ItemListCell *cell = NULL;
 
-		printf(_("\nWARNING: following issues were detected\n"));
+		ItemListCell *cell = NULL;
+		PQExpBufferData warning;
+
+		initPQExpBuffer(&warning);
+
+		appendPQExpBufferStr(&warning,
+							 _("following issues were detected\n"));
 		for (cell = warnings.head; cell; cell = cell->next)
 		{
-			printf(_("  - %s\n"), cell->string);
+			appendPQExpBuffer(&warning,
+							  _("  - %s\n"), cell->string);
 		}
 
+		puts("");
+		log_warning("%s", warning.data);
+
+		termPQExpBuffer(&warning);
+
 		if (runtime_options.verbose == false && connection_error_found == true)
 		{
 			log_hint(_("execute with --verbose option to see connection error messages"));
@@ -1396,6 +1402,10 @@ do_cluster_cleanup(void)
 		log_warning(_("unable to vacuum table \"repmgr.monitoring_history\""));
 		log_detail("%s", PQerrorMessage(primary_conn));
 	}
+	else
+	{
+		log_info(_("vacuum of table \"repmgr.monitoring_history\" completed"));
+	}
 
 	if (runtime_options.keep_history == 0)
 	{

repmgr-action-cluster.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-cluster.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-daemon.c

@@ -2,7 +2,7 @@
  * repmgr-action-daemon.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -44,12 +44,13 @@ static void _do_node_restore_config(void);
 static void do_node_check_replication_connection(void);
 static CheckStatus do_node_check_archive_ready(PGconn *conn, OutputMode mode, CheckStatusList *list_output);
 static CheckStatus do_node_check_downstream(PGconn *conn, OutputMode mode, CheckStatusList *list_output);
+static CheckStatus do_node_check_upstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_role(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
-
+static CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 /*
  * NODE STATUS
  *
@@ -159,7 +160,6 @@ do_node_status(void)
 								 _("- node is registered as standby but running as primary"));
 			}
 			break;
-		case BDR:
 		default:
 			break;
 	}
@@ -717,10 +717,49 @@ do_node_check(void)
 		exit(SUCCESS);
 	}
 
-	if (strlen(config_file_options.conninfo))
+
-		conn = establish_db_connection(config_file_options.conninfo, true);
+	if (config_file_options.conninfo[0] != '\0')
+	{
+		t_conninfo_param_list node_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
+		char	   *errmsg = NULL;
+		bool		parse_success = false;
+
+		initialize_conninfo_params(&node_conninfo, false);
+
+		parse_success = parse_conninfo_string(config_file_options.conninfo,
+											  &node_conninfo,
+											  &errmsg, false);
+
+		if (parse_success == false)
+		{
+			log_error(_("unable to parse conninfo string \"%s\" for local node"),
+					  config_file_options.conninfo);
+			log_detail("%s", errmsg);
+
+			exit(ERR_BAD_CONFIG);
+		}
+
+		/*
+		 * If --superuser option provided, attempt to connect as the specified user
+		 */
+
+		if (runtime_options.superuser[0] != '\0')
+		{
+			conn = establish_db_connection_with_replacement_param(
+				config_file_options.conninfo,
+				"user",
+				runtime_options.superuser,
+				true);
+		}
+		else
+		{
+			conn = establish_db_connection_by_params(&node_conninfo, true);
+		}
+	}
 	else
+	{
 		conn = establish_db_connection_by_params(&source_conninfo, true);
+	}
 
 	if (get_node_record(conn, config_file_options.node_id, &node_info) != RECORD_FOUND)
 	{
@@ -744,6 +783,16 @@ do_node_check(void)
 		exit(return_code);
 	}
 
+	if (runtime_options.upstream == true)
+	{
+		return_code = do_node_check_upstream(conn,
+											 runtime_options.output_mode,
+											 &node_info,
+											 NULL);
+		PQfinish(conn);
+		exit(return_code);
+	}
+
 	if (runtime_options.downstream == true)
 	{
 		return_code = do_node_check_downstream(conn,
@@ -753,7 +802,6 @@ do_node_check(void)
 		exit(return_code);
 	}
 
-
 	if (runtime_options.replication_lag == true)
 	{
 		return_code = do_node_check_replication_lag(conn,
@@ -804,6 +852,16 @@ do_node_check(void)
 		exit(return_code);
 	}
 
+	if (runtime_options.replication_config_owner == true)
+	{
+		return_code = do_node_check_replication_config_owner(conn,
+													   runtime_options.output_mode,
+													   &node_info,
+													   NULL);
+		PQfinish(conn);
+		exit(return_code);
+	}
+
 
 	if (runtime_options.output_mode == OM_NAGIOS)
 	{
@@ -827,6 +885,9 @@ do_node_check(void)
 	if (do_node_check_archive_ready(conn, runtime_options.output_mode, &status_list) != CHECK_STATUS_OK)
 		issue_detected = true;
 
+	if (do_node_check_upstream(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
+		issue_detected = true;
+
 	if (do_node_check_downstream(conn, runtime_options.output_mode, &status_list) != CHECK_STATUS_OK)
 		issue_detected = true;
 
@@ -909,7 +970,6 @@ do_node_check_replication_connection(void)
 	PGconn *repl_conn = NULL;
 	t_node_info node_record = T_NODE_INFO_INITIALIZER;
 	RecordStatus record_status = RECORD_NOT_FOUND;
-	t_conninfo_param_list remote_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PQExpBufferData output;
 
 
@@ -939,17 +999,8 @@ do_node_check_replication_connection(void)
 		return;
 	}
 
-	initialize_conninfo_params(&remote_conninfo, false);
+	repl_conn = establish_replication_connection_from_conninfo(node_record.conninfo,
-	parse_conninfo_string(node_record.conninfo, &remote_conninfo, NULL, false);
+															   node_record.repluser);
-
-	if (strcmp(param_get(&remote_conninfo, "user"), node_record.repluser) != 0)
-	{
-		param_set(&remote_conninfo, "user", node_record.repluser);
-		param_set(&remote_conninfo, "dbname", "replication");
-	}
-	param_set(&remote_conninfo, "replication", "1");
-
-	repl_conn = establish_db_connection_by_params(&remote_conninfo, false);
 
 	if (PQstatus(repl_conn) != CONNECTION_OK)
 	{
@@ -1298,6 +1349,98 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, CheckStatusList *list_ou
 }
 
 
+static CheckStatus
+do_node_check_upstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
+{
+	PGconn	   *upstream_conn = NULL;
+	t_node_info upstream_node_info = T_NODE_INFO_INITIALIZER;
+	PQExpBufferData details;
+
+	CheckStatus status = CHECK_STATUS_OK;
+
+	if (mode == OM_CSV && list_output == NULL)
+	{
+		log_error(_("--csv output not provided with --upstream option"));
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	initPQExpBuffer(&details);
+
+	if (get_node_record(conn, node_info->upstream_node_id, &upstream_node_info) != RECORD_FOUND)
+	{
+		if (get_recovery_type(conn) == RECTYPE_STANDBY)
+		{
+			appendPQExpBuffer(&details,
+							  _("node \"%s\" (ID: %i) is a standby but no upstream record found"),
+							  node_info->node_name,
+							  node_info->node_id);
+			status = CHECK_STATUS_CRITICAL;
+		}
+		else
+		{
+			appendPQExpBufferStr(&details,
+								 _("N/A - node is primary"));
+		}
+	}
+	else
+	{
+		upstream_conn = establish_db_connection(upstream_node_info.conninfo, true);
+
+		/* check our node is connected */
+		if (is_downstream_node_attached(upstream_conn, config_file_options.node_name) != NODE_ATTACHED)
+		{
+			appendPQExpBuffer(&details,
+							  _("node \"%s\" (ID: %i) is not attached to expected upstream node \"%s\" (ID: %i)"),
+							  node_info->node_name,
+							  node_info->node_id,
+							  upstream_node_info.node_name,
+							  upstream_node_info.node_id);
+			status = CHECK_STATUS_CRITICAL;
+		}
+		else
+		{
+			appendPQExpBuffer(&details,
+							  _("node \"%s\" (ID: %i) is attached to expected upstream node \"%s\" (ID: %i)"),
+							  node_info->node_name,
+							  node_info->node_id,
+							  upstream_node_info.node_name,
+							  upstream_node_info.node_id);
+		}
+	}
+
+	switch (mode)
+	{
+		case OM_NAGIOS:
+			{
+				printf("REPMGR_UPSTREAM_SERVER %s: %s | ",
+					   output_check_status(status),
+					   details.data);
+			}
+		case OM_TEXT:
+			if (list_output != NULL)
+			{
+				check_status_list_set(list_output,
+									  "Upstream connection",
+									  status,
+									  details.data);
+			}
+			else
+			{
+				printf("%s (%s)\n",
+					   output_check_status(status),
+					   details.data);
+			}
+		default:
+			break;
+	}
+
+	termPQExpBuffer(&details);
+
+	return status;
+}
+
+
 static CheckStatus
 do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
 {
@@ -1552,34 +1695,6 @@ do_node_check_role(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckS
 									 _("node is witness"));
 			}
 			break;
-		case BDR:
-			{
-				PQExpBufferData output;
-
-				initPQExpBuffer(&output);
-				if (is_bdr_db(conn, &output) == false)
-				{
-					status = CHECK_STATUS_CRITICAL;
-					appendPQExpBufferStr(&details,
-										 output.data);
-				}
-				termPQExpBuffer(&output);
-
-				if (status == CHECK_STATUS_OK)
-				{
-					if (is_active_bdr_node(conn, node_info->node_name) == false)
-					{
-						status = CHECK_STATUS_CRITICAL;
-						appendPQExpBufferStr(&details,
-											 _("node is not an active BDR node"));
-					}
-					else
-					{
-						appendPQExpBufferStr(&details,
-											 _("node is an active BDR node"));
-					}
-				}
-			}
 		default:
 			break;
 	}
@@ -1828,11 +1943,11 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	}
 
 	initPQExpBuffer(&details);
+
 	/*
 	 * Check actual data directory matches that in repmgr.conf; note this requires
 	 * a superuser connection
 	 */
-
 	if (connection_has_pg_settings(conn) == true)
 	{
 		/* we expect to have a database connection */
@@ -1875,10 +1990,9 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 		{
 			log_info(_("connection is not a superuser connection, falling back to simple check"));
 
-			/* XXX add -S/--superuser option */
 			if (PQserverVersion(conn) >= 100000)
 			{
-				log_hint(_("add the \"%s\" user to group \"pg_read_all_settings\" or \"pg_monitor\""),
+				log_hint(_("provide a superuser with -S/--superuser, or add the \"%s\" user to role \"pg_read_all_settings\" or \"pg_monitor\""),
 						   PQuser(conn));
 			}
 		}
@@ -1899,6 +2013,12 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 
 			status = CHECK_STATUS_CRITICAL;
 		}
+		else
+		{
+			appendPQExpBuffer(&details,
+							  _("configured \"data_directory\" is \"%s\""),
+							  config_file_options.data_directory);
+		}
 	}
 
 	switch (mode)
@@ -1942,6 +2062,40 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	return status;
 }
 
+/*
+ * This is not included in the general list output
+ */
+static
+CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
+{
+	CheckStatus status = CHECK_STATUS_OK;
+
+	PQExpBufferData errmsg;
+	PQExpBufferData details;
+
+	if (mode != OM_OPTFORMAT)
+	{
+		log_error(_("--replication-config-owner option can only be used with --optformat"));
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	initPQExpBuffer(&errmsg);
+	initPQExpBuffer(&details);
+
+	if (check_replication_config_owner(PQserverVersion(conn),
+									   config_file_options.data_directory,
+									   &errmsg, &details) == false)
+	{
+		status = CHECK_STATUS_CRITICAL;
+	}
+
+	printf("--replication-config-owner=%s\n",
+		   output_check_status(status));
+
+	return status;
+}
+
 
 void
 do_node_service(void)
@@ -1981,26 +2135,62 @@ do_node_service(void)
 
 	if ((action == ACTION_STOP || action == ACTION_RESTART) && runtime_options.checkpoint == true)
 	{
-		if (runtime_options.dry_run == true)
+		PGconn	   *conn = NULL;
+
+		if (config_file_options.conninfo[0] != '\0')
 		{
-			log_info(_("a CHECKPOINT would be issued here"));
+			/*
+			 * If --superuser option provided, attempt to connect as the specified user
+			 */
+			if (runtime_options.superuser[0] != '\0')
+			{
+				conn = establish_db_connection_with_replacement_param(
+					config_file_options.conninfo,
+					"user",
+					runtime_options.superuser,
+					true);
+			}
+			else
+			{
+				conn = establish_db_connection(config_file_options.conninfo, true);
+			}
 		}
 		else
 		{
-			PGconn	   *conn = NULL;
+			conn = establish_db_connection_by_params(&source_conninfo, true);
-
-			if (strlen(config_file_options.conninfo))
-				conn = establish_db_connection(config_file_options.conninfo, true);
-			else
-				conn = establish_db_connection_by_params(&source_conninfo, true);
-
-			log_notice(_("issuing CHECKPOINT"));
-
-			/* check superuser conn! */
-			checkpoint(conn);
-
-			PQfinish(conn);
 		}
+
+		if (is_superuser_connection(conn, NULL) == false)
+		{
+			if (runtime_options.dry_run == true)
+			{
+				log_warning(_("a CHECKPOINT would be issued here but no superuser connection is available"));
+			}
+			else
+			{
+				log_warning(_("a superuser connection is required to issue a CHECKPOINT"));
+			}
+
+			log_hint(_("provide a superuser with -S/--superuser"));
+		}
+		else
+		{
+			if (runtime_options.dry_run == true)
+			{
+				log_info(_("a CHECKPOINT would be issued here"));
+			}
+			else
+			{
+
+				log_notice(_("issuing CHECKPOINT on node \"%s\" (ID: %i) "),
+						   config_file_options.node_name,
+						   config_file_options.node_id);
+
+				checkpoint(conn);
+			}
+		}
+
+		PQfinish(conn);
 	}
 
 	get_server_action(action, command, data_dir);
@@ -2147,6 +2337,7 @@ do_node_rejoin(void)
 	PQExpBufferData follow_output;
 	struct stat statbuf;
 	t_node_info primary_node_record = T_NODE_INFO_INITIALIZER;
+	t_node_info local_node_record = T_NODE_INFO_INITIALIZER;
 
 	bool		success = true;
 	int			follow_error_code = SUCCESS;
@@ -2257,6 +2448,36 @@ do_node_rejoin(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	/*
+	 * Fetch the local node record - we'll need this later, and it acts as an
+	 * additional sanity-check that the node is known to the primary.
+	 */
+	if (get_node_record(primary_conn, config_file_options.node_id, &local_node_record) != RECORD_FOUND)
+	{
+		log_error(_("unable to retrieve node record for the local node"));
+		log_hint(_("check the local node is registered with the current primary \"%s\" (ID: %i)"),
+				 primary_node_record.node_name,
+				 primary_node_record.node_id);
+		PQfinish(upstream_conn);
+		PQfinish(primary_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/*
+	 * Sanity-check replication slot availability
+	 */
+	if (config_file_options.use_replication_slots)
+	{
+		bool slots_available = check_replication_slots_available(primary_node_record.node_id,
+																 primary_conn);
+		if (slots_available == false)
+		{
+			PQfinish(primary_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+
 	/*
 	 * sanity-check that it will actually be possible to stream from the new upstream
 	 */
@@ -2534,79 +2755,34 @@ do_node_rejoin(void)
 	 */
 	if (runtime_options.no_wait == false)
 	{
-		int i;
+		standy_join_status join_success = check_standby_join(primary_conn,
-
+															 &primary_node_record,
-		for (i = 0; i < config_file_options.standby_reconnect_timeout; i++)
+															 &local_node_record);
-		{
-			if (is_server_available(config_file_options.conninfo))
-			{
-				log_verbose(LOG_INFO, _("demoted primary is pingable"));
-				break;
-			}
-
-			if (i % 5 == 0)
-			{
-				log_verbose(LOG_INFO, _("waiting for node %i to respond to pings; %i of max %i attempts"),
-							config_file_options.node_id,
-							i + 1, config_file_options.node_rejoin_timeout);
-			}
-			else
-			{
-				log_debug("sleeping 1 second waiting for node %i to respond to pings; %i of max %i attempts",
-						  config_file_options.node_id,
-						  i + 1, config_file_options.node_rejoin_timeout);
-			}
-
-			sleep(1);
-		}
-
-		for (;  i < config_file_options.node_rejoin_timeout; i++)
-		{
-			NodeAttached node_attached = is_downstream_node_attached(primary_conn,
-														config_file_options.node_name);
-
-			if (node_attached == NODE_ATTACHED)
-			{
-				log_verbose(LOG_INFO, _("node %i has attached to its upstream node"),
-							config_file_options.node_id);
-				break;
-			}
-
-			if (i % 5 == 0)
-			{
-				log_info(_("waiting for node \"%s\" (ID: %i) to connect to new primary; %i of max %i attempts"),
-						 config_file_options.node_name,
-						 config_file_options.node_id,
-						 i + 1, config_file_options.node_rejoin_timeout);
-				log_detail(_("checking for record in node \"%s\"'s \"pg_stat_replication\" table where \"application_name\" is \"%s\""),
-						   primary_node_record.node_name,
-						   config_file_options.node_name);
-			}
-			else
-			{
-				log_debug("sleeping 1 second waiting for node %i to connect to new primary; %i of max %i attempts",
-						  config_file_options.node_id,
-						  i + 1, config_file_options.node_rejoin_timeout);
-			}
-
-			sleep(1);
-		}
 
 		create_event_notification(primary_conn,
 								  &config_file_options,
 								  config_file_options.node_id,
 								  "node_rejoin",
-								  success,
+								  join_success == JOIN_SUCCESS ? true : false,
 								  follow_output.data);
 
-		if (success == false)
+		if (join_success != JOIN_SUCCESS)
 		{
 			termPQExpBuffer(&follow_output);
 			log_error(_("NODE REJOIN failed"));
-			log_detail(_("no record for local node \"%s\" found in node \"%s\"'s \"pg_stat_replication\" table"),
+
-					   config_file_options.node_name,
+			if (join_success == JOIN_FAIL_NO_PING) {
-					   primary_node_record.node_name);
+				log_detail(_("local node \"%s\" did not become available start after %i seconds"),
+						   config_file_options.node_name,
+						   config_file_options.node_rejoin_timeout);
+			}
+			else {
+				log_detail(_("no record for local node \"%s\" found in node \"%s\"'s \"pg_stat_replication\" table"),
+						   config_file_options.node_name,
+						   primary_node_record.node_name);
+			}
 			log_hint(_("check the PostgreSQL log on the local node"));
+
 			exit(ERR_REJOIN_FAIL);
 		}
 	}
@@ -3173,17 +3349,22 @@ do_node_help(void)
 	puts("");
 	printf(_("  Configuration file required, runs on local node only.\n"));
 	puts("");
-	printf(_("    --csv                   emit output as CSV (not available for individual check output)\n"));
+	printf(_("  Connection options:\n"));
-	printf(_("    --nagios                emit output in Nagios format (individual check output only)\n"));
+	printf(_("    -S, --superuser=USERNAME  superuser to use, if repmgr user is not superuser\n"));
+	puts("");
+	printf(_("  Output options:\n"));
+	printf(_("    --csv                     emit output as CSV (not available for individual check output)\n"));
+	printf(_("    --nagios                  emit output in Nagios format (individual check output only)\n"));
 	puts("");
 	printf(_("  Following options check an individual status:\n"));
-	printf(_("    --archive-ready         number of WAL files ready for archiving\n"));
+	printf(_("    --archive-ready           number of WAL files ready for archiving\n"));
-	printf(_("    --downstream            whether all downstream nodes are connected\n"));
+	printf(_("    --downstream              whether all downstream nodes are connected\n"));
-	printf(_("    --replication-lag       replication lag in seconds (standbys only)\n"));
+	printf(_("    --uptream                 whether the node is connected to its upstream\n"));
-	printf(_("    --role                  check node has expected role\n"));
+	printf(_("    --replication-lag         replication lag in seconds (standbys only)\n"));
-	printf(_("    --slots                 check for inactive replication slots\n"));
+	printf(_("    --role                    check node has expected role\n"));
-	printf(_("    --missing-slots         check for missing replication slots\n"));
+	printf(_("    --slots                   check for inactive replication slots\n"));
-	printf(_("    --data-directory-config check repmgr's data directory configuration\n"));
+	printf(_("    --missing-slots           check for missing replication slots\n"));
+	printf(_("    --data-directory-config   check repmgr's data directory configuration\n"));
 
 	puts("");
 
@@ -3202,7 +3383,7 @@ do_node_help(void)
 			 "                            after executing \"pg_rewind\"\n"));
 	printf(_("    --config-archive-dir    directory to temporarily store retained configuration files\n" \
 			 "                              (default: /tmp)\n"));
-	printf(_("    -W/--no-wait            don't wait for the node to rejoin cluster\n"));
+	printf(_("    -W, --no-wait           don't wait for the node to rejoin cluster\n"));
 	puts("");
 
 	printf(_("NODE SERVICE\n"));
@@ -3212,10 +3393,11 @@ do_node_help(void)
 	puts("");
 	printf(_("  Configuration file required, runs on local node only.\n"));
 	puts("");
-	printf(_("    --dry-run             show what action would be performed, but don't execute it\n"));
+	printf(_("    --dry-run                 show what action would be performed, but don't execute it\n"));
-	printf(_("    --action              action to perform (one of \"start\", \"stop\", \"restart\" or \"reload\")\n"));
+	printf(_("    --action                  action to perform (one of \"start\", \"stop\", \"restart\" or \"reload\")\n"));
-	printf(_("    --list-actions        show what command would be performed for each action\n"));
+	printf(_("    --list-actions            show what command would be performed for each action\n"));
-	printf(_("    --checkpoint          issue a CHECKPOINT before stopping or restarting the node\n"));
+	printf(_("    --checkpoint              issue a CHECKPOINT before stopping or restarting the node\n"));
+	printf(_("    -S, --superuser=USERNAME  superuser to use, if repmgr user is not superuser\n"));
 	puts("");
 
 

repmgr-action-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -106,7 +106,7 @@ do_primary_register(void)
 	current_primary_id = get_primary_node_id(conn);
 	if (current_primary_id != NODE_NOT_FOUND && current_primary_id != config_file_options.node_id)
 	{
-		log_debug("XXX %i", current_primary_id);
+		log_debug("current active primary node ID is %i", current_primary_id);
 		primary_conn = establish_primary_db_connection(conn, false);
 
 		if (PQstatus(primary_conn) == CONNECTION_OK)

repmgr-action-primary.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-primary.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -357,11 +357,22 @@ do_service_status(void)
 	{
 		ItemListCell *cell = NULL;
 
-		printf(_("\nWARNING: following issues were detected\n"));
+		PQExpBufferData warning;
+
+		initPQExpBuffer(&warning);
+
+		appendPQExpBufferStr(&warning,
+							 _("following issues were detected\n"));
+
 		for (cell = warnings.head; cell; cell = cell->next)
 		{
-			printf(_("  - %s\n"), cell->string);
+			appendPQExpBuffer(&warning,
+							  _("  - %s\n"), cell->string);
 		}
+		puts("");
+		log_warning("%s", warning.data);
+
+		termPQExpBuffer(&warning);
 
 		if (runtime_options.verbose == false && connection_error_found == true)
 		{

repmgr-action-service.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-service.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-standby.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-standby.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -74,18 +74,6 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* check that witness node is not a BDR node */
-	if (is_bdr_db_quiet(witness_conn) == true)
-	{
-		log_error(_("witness node is a BDR node"));
-		log_hint(_("a witness node cannot be configured for a BDR cluster"));
-
-		PQfinish(witness_conn);
-
-		exit(ERR_BAD_CONFIG);
-	}
-
-
 	/* connect to primary with provided parameters */
 	log_info(_("connecting to primary node"));
 
@@ -194,19 +182,6 @@ do_witness_register(void)
 		}
 	}
 
-	/* check that primary node is not a BDR node */
-	if (is_bdr_db_quiet(primary_conn) == true)
-	{
-		log_error(_("primary node is a BDR node"));
-		log_hint(_("a witness node cannot be configured for a BDR cluster"));
-
-		PQfinish(witness_conn);
-		PQfinish(primary_conn);
-
-		exit(ERR_BAD_CONFIG);
-	}
-
-
 	/* create repmgr extension, if does not exist */
 	if (runtime_options.dry_run == false &&  !create_repmgr_extension(witness_conn))
 	{

repmgr-action-witness.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-witness.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-client-global.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client-global.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -28,6 +28,8 @@
 /* default value for "cluster event --limit"*/
 #define CLUSTER_EVENT_LIMIT 20
 
+
+
 typedef struct
 {
 	/* configuration metadata */
@@ -85,7 +87,7 @@ typedef struct
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
-	bool		recovery_conf_only;
+	bool		replication_conf_only;
 
 	/* "standby clone"/"standby follow" options */
 	int			upstream_node_id;
@@ -109,6 +111,7 @@ typedef struct
 	/* "node check" options */
 	bool		archive_ready;
 	bool		downstream;
+	bool		upstream;
 	bool		replication_lag;
 	bool		role;
 	bool		slots;
@@ -116,6 +119,7 @@ typedef struct
 	bool		has_passfile;
 	bool		replication_connection;
 	bool		data_directory_config;
+	bool		replication_config_owner;
 
 	/* "node rejoin" options */
 	char		config_files[MAXLEN];
@@ -168,7 +172,7 @@ 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, \
 		/* "node rejoin" options */ \
 		"", \
 		/* "node service" options */ \
@@ -201,6 +205,23 @@ typedef enum
 } t_server_action;
 
 
+typedef enum
+{
+	USER_TYPE_UNKNOWN = -1,
+	REPMGR_USER,
+	REPLICATION_USER_OPT,
+	REPLICATION_USER_NODE,
+	SUPERUSER
+} t_user_type;
+
+typedef enum
+{
+	JOIN_SUCCESS,
+	JOIN_FAIL_NO_PING,
+	JOIN_FAIL_NO_REPLICATION
+} standy_join_status;
+
+
 typedef struct ColHeader
 {
 	char		title[MAXLEN];
@@ -255,9 +276,15 @@ 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 drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);
 
+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);
+
+extern standy_join_status check_standby_join(PGconn *primary_conn, t_node_info *primary_node_record, t_node_info *standby_node_record);
+extern bool check_replication_slots_available(int node_id, PGconn* conn);
 extern bool check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_record, bool is_rejoin);
+extern bool check_replication_config_owner(int pg_version, const char *data_directory, PQExpBufferData *error_msg, PQExpBufferData *detail_msg);
+
 extern void check_shared_library(PGconn *conn);
 extern bool is_repmgrd_running(PGconn *conn);
 extern int parse_repmgr_version(const char *version_string);

repmgr-client.c

@@ -1,7 +1,7 @@
 /*
  * repmgr-client.c - Command interpreter for the repmgr package
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This module is a command-line utility to easily setup a cluster of
  * hot standby servers for an HA environment
@@ -18,9 +18,6 @@
  * STANDBY FOLLOW
  * STANDBY SWITCHOVER
  *
- * BDR REGISTER
- * BDR UNREGISTER
- *
  * CLUSTER SHOW
  * CLUSTER EVENT
  * CLUSTER CROSSCHECK
@@ -67,7 +64,6 @@
 #include "repmgr-action-primary.h"
 #include "repmgr-action-standby.h"
 #include "repmgr-action-witness.h"
-#include "repmgr-action-bdr.h"
 #include "repmgr-action-node.h"
 #include "repmgr-action-cluster.h"
 #include "repmgr-action-service.h"
@@ -95,11 +91,17 @@ char		path_buf[MAXLEN] = "";
  */
 t_node_info target_node_info = T_NODE_INFO_INITIALIZER;
 
+/* used by create_replication_slot() */
+static t_user_type ReplicationSlotUser = USER_TYPE_UNKNOWN;
 
 /* Collate command line errors and warnings here for friendlier reporting */
 static ItemList cli_errors = {NULL, NULL};
 static ItemList cli_warnings = {NULL, NULL};
 
+static void _determine_replication_slot_user(PGconn *conn,
+											 t_node_info *upstream_node_record,
+											 char **replication_user);
+
 int
 main(int argc, char **argv)
 {
@@ -174,9 +176,8 @@ main(int argc, char **argv)
 
 	/* set default user for -R/--remote-user */
 	{
-		struct passwd *pw = NULL;
+		struct passwd *pw = getpwuid(geteuid());
 
-		pw = getpwuid(geteuid());
 		if (pw == NULL)
 		{
 			fprintf(stderr, _("could not get current user name: %s\n"), strerror(errno));
@@ -287,8 +288,7 @@ main(int argc, char **argv)
 				 * These are the standard database connection options; with
 				 * the exception of -d/--dbname (which could be a conninfo
 				 * string) we'll also set these values in "source_conninfo"
-				 * (overwriting preset values from environment variables). XXX
+				 * (overwriting preset values from environment variables).
-				 * check this is same as psql
 				 */
 				/* -d/--dbname */
 			case 'd':
@@ -431,8 +431,8 @@ main(int argc, char **argv)
 				runtime_options.without_barman = true;
 				break;
 
-			case OPT_RECOVERY_CONF_ONLY:
+			case OPT_REPLICATION_CONF_ONLY:
-				runtime_options.recovery_conf_only = true;
+				runtime_options.replication_conf_only = true;
 				break;
 
 
@@ -505,6 +505,10 @@ main(int argc, char **argv)
 				runtime_options.downstream = true;
 				break;
 
+			case OPT_UPSTREAM:
+				runtime_options.upstream = true;
+				break;
+
 			case OPT_REPLICATION_LAG:
 				runtime_options.replication_lag = true;
 				break;
@@ -533,6 +537,10 @@ main(int argc, char **argv)
 				runtime_options.data_directory_config = true;
 				break;
 
+			case OPT_REPLICATION_CONFIG_OWNER:
+				runtime_options.replication_config_owner = true;
+				break;
+
 				/*--------------------
 				 * "node rejoin" options
 				 *--------------------
@@ -812,7 +820,6 @@ main(int argc, char **argv)
 	 *   { PRIMARY | MASTER } REGISTER |
 	 *   STANDBY { REGISTER | UNREGISTER | CLONE [node] | PROMOTE | FOLLOW [node] | SWITCHOVER } |
 	 *   WITNESS { CREATE | REGISTER | UNREGISTER }
-	 *   BDR { REGISTER | UNREGISTER } |
 	 *   NODE { STATUS | CHECK | REJOIN | SERVICE } |
 	 *   CLUSTER { CROSSCHECK | MATRIX | SHOW | EVENT | CLEANUP }
 	 *   SERVICE { STATUS | PAUSE | UNPAUSE | START | STOP }
@@ -882,6 +889,7 @@ main(int argc, char **argv)
 			else if (strcasecmp(repmgr_action, "STATUS") == 0)
 				action = NODE_STATUS;
 		}
+
 		else if (strcasecmp(repmgr_command, "WITNESS") == 0)
 		{
 			if (help_option == true)
@@ -894,23 +902,6 @@ main(int argc, char **argv)
 			else if (strcasecmp(repmgr_action, "UNREGISTER") == 0)
 				action = WITNESS_UNREGISTER;
 		}
-		else if (strcasecmp(repmgr_command, "BDR") == 0)
-		{
-			if (help_option == true)
-			{
-				do_bdr_help();
-				exit(SUCCESS);
-			}
-
-			if (strcasecmp(repmgr_action, "REGISTER") == 0)
-				action = BDR_REGISTER;
-			else if (strcasecmp(repmgr_action, "UNREGISTER") == 0)
-				action = BDR_UNREGISTER;
-			else if (strcasecmp(repmgr_action, "CHECK") == 0)
-				action = NODE_CHECK;
-			else if (strcasecmp(repmgr_action, "STATUS") == 0)
-				action = NODE_STATUS;
-		}
 
 		else if (strcasecmp(repmgr_command, "NODE") == 0)
 		{
@@ -1350,13 +1341,6 @@ main(int argc, char **argv)
 		case WITNESS_UNREGISTER:
 			do_witness_unregister();
 			break;
-			/* BDR */
-		case BDR_REGISTER:
-			do_bdr_register();
-			break;
-		case BDR_UNREGISTER:
-			do_bdr_unregister();
-			break;
 
 			/* NODE */
 		case NODE_STATUS:
@@ -1429,9 +1413,6 @@ main(int argc, char **argv)
  *
  * Messages will be added to the command line warning and error lists
  * as appropriate.
- *
- * XXX for each individual actions, check only required actions
- * for non-required actions check warn if provided
  */
 
 static void
@@ -1487,10 +1468,15 @@ check_cli_parameters(const int action)
 					}
 
 					/*
-					 * XXX if -D/--pgdata provided, and also
+					 * If -D/--pgdata was provided, but config_file_options.pgdata
-					 * config_file_options.pgdata, warn -D/--pgdata will be
+					 * is set, warn that -D/--pgdata will be ignored.
-					 * ignored
 					 */
+					if (runtime_options.data_dir[0] && config_file_options.data_directory[0])
+					{
+						item_list_append(&cli_warnings,
+										 _("-D/--pgdata will be ignored if a repmgr configuration file is provided"));
+
+					}
 
 					if (*runtime_options.upstream_conninfo)
 					{
@@ -1674,7 +1660,6 @@ check_cli_parameters(const int action)
 			case STANDBY_CLONE:
 			case STANDBY_REGISTER:
 			case STANDBY_FOLLOW:
-			case BDR_REGISTER:
 				break;
 			default:
 				item_list_append_format(&cli_warnings,
@@ -1705,7 +1690,24 @@ check_cli_parameters(const int action)
 		}
 	}
 
-	if (runtime_options.recovery_conf_only == true)
+	if (runtime_options.superuser[0])
+	{
+		switch (action)
+		{
+			case STANDBY_CLONE:
+			case STANDBY_SWITCHOVER:
+			case NODE_CHECK:
+			case NODE_SERVICE:
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--superuser ignored when executing %s"),
+										action_name(action));
+		}
+	}
+
+
+	if (runtime_options.replication_conf_only == true)
 	{
 		switch (action)
 		{
@@ -2213,7 +2215,6 @@ format_node_status(t_node_info *node_info, PQExpBufferData *node_status, PQExpBu
 
 		break;
 		case WITNESS:
-		case BDR:
 		{
 			/* node is reachable */
 			if (node_info->node_status == NODE_STATUS_UP)
@@ -2273,8 +2274,9 @@ format_node_status(t_node_info *node_info, PQExpBufferData *node_status, PQExpBu
 		 * Unable to retrieve the node's copy of its own record - copy the
 		 * name from our own copy of the record
 		 */
-		appendPQExpBufferStr(upstream,
+		appendPQExpBuffer(upstream,
-							 node_info->upstream_node_name);
+						  "? %s",
+						  node_info->upstream_node_name);
 	}
 	else if (remote_node_rec.type == WITNESS)
 	{
@@ -2456,17 +2458,14 @@ action_name(const int action)
 			return "STANDBY PROMOTE";
 		case STANDBY_FOLLOW:
 			return "STANDBY FOLLOW";
+		case STANDBY_SWITCHOVER:
+			return "STANDBY SWITCHOVER";
 
 		case WITNESS_REGISTER:
 			return "WITNESS REGISTER";
 		case WITNESS_UNREGISTER:
 			return "WITNESS UNREGISTER";
 
-		case BDR_REGISTER:
-			return "BDR REGISTER";
-		case BDR_UNREGISTER:
-			return "BDR UNREGISTER";
-
 		case NODE_STATUS:
 			return "NODE STATUS";
 		case NODE_CHECK:
@@ -2475,9 +2474,13 @@ action_name(const int action)
 			return "NODE REJOIN";
 		case NODE_SERVICE:
 			return "NODE SERVICE";
+		case NODE_CONTROL:
+			return "NODE CONTROL";
 
 		case CLUSTER_SHOW:
 			return "CLUSTER SHOW";
+		case CLUSTER_CLEANUP:
+			return "CLUSTER CLEANUP";
 		case CLUSTER_EVENT:
 			return "CLUSTER EVENT";
 		case CLUSTER_MATRIX:
@@ -2602,7 +2605,6 @@ do_help(void)
 	printf(_("Usage:\n"));
 	printf(_("    %s [OPTIONS] primary {register|unregister}\n"), progname());
 	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow|switchover}\n"), progname());
-	printf(_("    %s [OPTIONS] bdr     {register|unregister}\n"), progname());
 	printf(_("    %s [OPTIONS] node    {status|check|rejoin|service}\n"), progname());
 	printf(_("    %s [OPTIONS] cluster {show|event|matrix|crosscheck|cleanup}\n"), progname());
 	printf(_("    %s [OPTIONS] witness {register|unregister}\n"), progname());
@@ -2611,7 +2613,7 @@ do_help(void)
 
 	puts("");
 
-	printf(_("  Execute \"%s {primary|standby|bdr|node|cluster|witness|service} --help\" to see command-specific options\n"), progname());
+	printf(_("  Execute \"%s {primary|standby|node|cluster|witness|service} --help\" to see command-specific options\n"), progname());
 
 	puts("");
 
@@ -2641,7 +2643,6 @@ do_help(void)
 
 	printf(_("  -p, --port=PORT                     database server port (default: \"%s\")\n"), runtime_options.port);
 	printf(_("  -U, --username=USERNAME             database user name to connect as (default: \"%s\")\n"), runtime_options.username);
-	printf(_("  -S, --superuser=USERNAME            superuser to use, if repmgr user is not superuser\n"));
 
 	puts("");
 
@@ -2735,14 +2736,7 @@ create_repmgr_extension(PGconn *conn)
 
 	/* 4. Create extension */
 
-	initPQExpBuffer(&query);
+	res = PQexec(schema_create_conn, "CREATE EXTENSION repmgr");
-
-	wrap_ddl_query(&query, config_file_options.replication_type,
-				   "CREATE EXTENSION repmgr");
-
-	res = PQexec(schema_create_conn, query.data);
-
-	termPQExpBuffer(&query);
 
 	if ((PQresultStatus(res) != PGRES_COMMAND_OK && PQresultStatus(res) != PGRES_TUPLES_OK))
 	{
@@ -2763,13 +2757,13 @@ create_repmgr_extension(PGconn *conn)
 	{
 		initPQExpBuffer(&query);
 
-		wrap_ddl_query(&query, config_file_options.replication_type,
+		appendPQExpBuffer(&query,
-					   "GRANT USAGE ON SCHEMA repmgr TO %s",
+						  "GRANT USAGE ON SCHEMA repmgr TO %s",
-					   userinfo.username);
+						  userinfo.username);
 
 		res = PQexec(schema_create_conn, query.data);
-
 		termPQExpBuffer(&query);
+
 		if (PQresultStatus(res) != PGRES_COMMAND_OK)
 		{
 			log_error(_("unable to grant usage on \"repmgr\" extension to %s:\n  %s"),
@@ -2784,12 +2778,12 @@ create_repmgr_extension(PGconn *conn)
 		}
 
 		initPQExpBuffer(&query);
-		wrap_ddl_query(&query, config_file_options.replication_type,
+
-					   "GRANT ALL ON ALL TABLES IN SCHEMA repmgr TO %s",
+		appendPQExpBuffer(&query,
-					   userinfo.username);
+						  "GRANT ALL ON ALL TABLES IN SCHEMA repmgr TO %s",
+						  userinfo.username);
 
 		res = PQexec(schema_create_conn, query.data);
-
 		termPQExpBuffer(&query);
 
 		if (PQresultStatus(res) != PGRES_COMMAND_OK)
@@ -2844,15 +2838,25 @@ create_repmgr_extension(PGconn *conn)
 int
 check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *server_version_string)
 {
-	int			conn_server_version_num = get_server_version(conn, server_version_string);
+	char		version_string[MAXVERSIONSTR] = "";
+	int			conn_server_version_num = get_server_version(conn, version_string);
+
+	/* Copy the version string, if the caller wants it */
+	if (server_version_string != NULL)
+		strncpy(server_version_string, version_string, MAXVERSIONSTR);
 
 	if (conn_server_version_num < MIN_SUPPORTED_VERSION_NUM)
 	{
 		if (conn_server_version_num > 0)
+		{
 			log_error(_("%s requires %s to be PostgreSQL %s or later"),
 					  progname(),
 					  server_type,
 					  MIN_SUPPORTED_VERSION);
+			log_detail(_("%s server version is %s"),
+					   server_type,
+					   version_string);
+		}
 
 		if (exit_on_error == true)
 		{
@@ -2863,6 +2867,38 @@ check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *
 		return UNKNOWN_SERVER_VERSION_NUM;
 	}
 
+	/*
+	 * If it's clear a particular repmgr feature branch won't be able to support
+	 * 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.
+	 */
+#ifdef MAX_UNSUPPORTED_VERSION_NUM
+	if (conn_server_version_num >= MAX_UNSUPPORTED_VERSION_NUM)
+	{
+		if (conn_server_version_num > 0)
+		{
+			log_error(_("%s %s does not support PostgreSQL %s or later"),
+					  progname(),
+					  REPMGR_VERSION,
+					  MAX_UNSUPPORTED_VERSION);
+			log_detail(_("%s server version is %s"),
+					   server_type,
+					   version_string);
+			log_hint(_("For details of supported versions see: https://repmgr.org/docs/current/install-requirements.html#INSTALL-COMPATIBILITY-MATRIX"));
+		}
+
+		if (exit_on_error == true)
+		{
+			PQfinish(conn);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		return UNKNOWN_SERVER_VERSION_NUM;
+	}
+#endif
+
 	return conn_server_version_num;
 }
 
@@ -3602,45 +3638,389 @@ can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *rea
 }
 
 
-void
+// provided connection should be for the normal repmgr user
+// upstream_node_record may be NULL or initialised to default values
+bool
+create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_node_record, PQExpBufferData *error_msg)
+{
+	PGconn *slot_conn = NULL;
+	bool use_replication_protocol = false;
+	bool success = true;
+	char *replication_user = NULL;
+
+	_determine_replication_slot_user(conn, upstream_node_record, &replication_user);
+	/*
+	 * If called in --dry-run context, if the replication slot user is not the
+	 * repmgr user, attempt to validate the connection.
+	 */
+	if (runtime_options.dry_run == true)
+	{
+		switch (ReplicationSlotUser)
+		{
+			case USER_TYPE_UNKNOWN:
+				log_error("unable to determine user for replication slot creation");
+				return false;
+			case  REPMGR_USER:
+				log_info(_("replication slots will be created by user \"%s\""),
+						 PQuser(conn));
+				return true;
+
+			case REPLICATION_USER_NODE:
+			case REPLICATION_USER_OPT:
+			{
+				PGconn *repl_conn = duplicate_connection(conn,
+														 replication_user,
+														 true);
+				if (repl_conn == NULL || PQstatus(repl_conn) != CONNECTION_OK)
+				{
+					log_error(_("unable to create replication connection as user \"%s\""),
+							  replication_user);
+					log_detail("%s", PQerrorMessage(repl_conn));
+
+					PQfinish(repl_conn);
+					return false;
+				}
+				log_info(_("replication slots will be created by replication user \"%s\""),
+						 replication_user);
+				PQfinish(repl_conn);
+				return true;
+			}
+			case SUPERUSER:
+			{
+				PGconn *superuser_conn = duplicate_connection(conn,
+															  runtime_options.superuser,
+															  false);
+				if (superuser_conn == NULL || PQstatus(superuser_conn )!= CONNECTION_OK)
+				{
+					log_error(_("unable to create superuser connection as user \"%s\""),
+							  runtime_options.superuser);
+					log_detail("%s", PQerrorMessage(superuser_conn));
+
+					PQfinish(superuser_conn);
+
+					return false;
+				}
+
+				log_info(_("replication slots will be created by superuser \"%s\""),
+						 runtime_options.superuser);
+				PQfinish(superuser_conn);
+			}
+		}
+
+	}
+
+	/*
+	 * If we can't create a replication slot with the connection provided to
+	 * the function, create an connection with appropriate permissions.
+	 */
+	switch (ReplicationSlotUser)
+	{
+		case USER_TYPE_UNKNOWN:
+			log_error("unable to determine user for replication slot creation");
+			return false;
+		case  REPMGR_USER:
+			slot_conn = conn;
+			log_info(_("creating replication slot as user \"%s\""),
+					 PQuser(conn));
+			break;
+
+		case REPLICATION_USER_NODE:
+		case REPLICATION_USER_OPT:
+		{
+			slot_conn = duplicate_connection(conn,
+											 replication_user,
+											 true);
+			if (slot_conn == NULL || PQstatus(slot_conn) != CONNECTION_OK)
+			{
+				log_error(_("unable to create replication connection as user \"%s\""),
+						  runtime_options.replication_user);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+					return false;
+			}
+			use_replication_protocol = true;
+			log_info(_("creating replication slot as replication user \"%s\""),
+					 replication_user);
+		}
+			break;
+
+		case SUPERUSER:
+		{
+			slot_conn = duplicate_connection(conn,
+											 runtime_options.superuser,
+											 false);
+			if (slot_conn == NULL || PQstatus(slot_conn )!= CONNECTION_OK)
+			{
+				log_error(_("unable to create super connection as user \"%s\""),
+						  runtime_options.superuser);
+				log_detail("%s", PQerrorMessage(slot_conn));
+
+				PQfinish(slot_conn);
+
+				return false;
+			}
+			log_info(_("creating replication slot as superuser \"%s\""),
+					 runtime_options.superuser);
+		}
+			break;
+	}
+
+	if (use_replication_protocol == true)
+	{
+		success = create_replication_slot_replprot(conn, slot_conn, slot_name, error_msg);
+	}
+	else
+	{
+		success = create_replication_slot_sql(slot_conn, slot_name, error_msg);
+	}
+
+
+	if (slot_conn != conn)
+		PQfinish(slot_conn);
+
+	return success;
+}
+
+
+bool
 drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name)
 {
+	t_node_info node_record = T_NODE_INFO_INITIALIZER;
 	t_replication_slot slot_info = T_REPLICATION_SLOT_INITIALIZER;
-	RecordStatus record_status = get_slot_record(conn, slot_name, &slot_info);
+	RecordStatus record_status;
+
+	char *replication_user = NULL;
+	bool success = true;
+
+	if (node_id != UNKNOWN_NODE_ID)
+	{
+		record_status = get_node_record(conn, node_id, &node_record);
+	}
+
+	_determine_replication_slot_user(conn, &node_record, &replication_user);
+
+	record_status = get_slot_record(conn, slot_name, &slot_info);
 
 	log_verbose(LOG_DEBUG, "attempting to delete slot \"%s\" on node %i",
 				slot_name, node_id);
 
 	if (record_status != RECORD_FOUND)
 	{
-		/* this is a good thing */
+		/* this is not a bad good thing */
 		log_verbose(LOG_INFO,
 					_("slot \"%s\" does not exist on node %i, nothing to remove"),
 					slot_name, node_id);
+		return true;
 	}
-	else
-	{
-		if (slot_info.active == false)
-		{
-			if (drop_replication_slot(conn, slot_name) == true)
-			{
-				log_notice(_("replication slot \"%s\" deleted on node %i"), slot_name, node_id);
-			}
-			else
-			{
-				log_error(_("unable to delete replication slot \"%s\" on node %i"), slot_name, node_id);
-			}
-		}
 
-		/*
+	if (slot_info.active == false)
-		 * if active replication slot exists, call Houston as we have a
+	{
-		 * problem
+		if (drop_replication_slot_sql(conn, slot_name) == true)
-		 */
+		{
+			log_notice(_("replication slot \"%s\" deleted on node %i"), slot_name, node_id);
+		}
 		else
 		{
-			log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
+			log_error(_("unable to delete replication slot \"%s\" on node %i"), slot_name, node_id);
+			success = false;
 		}
 	}
+
+	/*
+	 * If an active replication slot exists, call Houston as we have a
+	 * problem.
+	 */
+	else
+	{
+		log_warning(_("replication slot \"%s\" is still active on node %i"), slot_name, node_id);
+		success = false;
+	}
+
+	return success;
+}
+
+
+static void
+_determine_replication_slot_user(PGconn *conn, t_node_info *upstream_node_record, char **replication_user)
+{
+	/*
+	 * If not previously done, work out which user will be responsible
+	 * for creating replication slots.
+	 */
+	if (ReplicationSlotUser == USER_TYPE_UNKNOWN)
+	{
+		/*
+		 * Is the repmgr user a superuser?
+		 */
+		if (is_superuser_connection(conn, NULL))
+		{
+			ReplicationSlotUser = REPMGR_USER;
+		}
+		/*
+		 * Does the repmgr user have the REPLICATION role?
+		 * Note we don't care here whether the repmgr user can actually
+		 * make a replication connection, we're just confirming that the
+		 * connection we have has the appropriate permissions.
+		 */
+		else if (is_replication_role(conn, NULL))
+		{
+			ReplicationSlotUser = REPMGR_USER;
+		}
+		/*
+		 * Is a superuser provided with --superuser?
+		 * We'll check later whether we can make a connection as that user.
+		 */
+		else if (runtime_options.superuser[0] != '\0')
+		{
+			ReplicationSlotUser = SUPERUSER;
+		}
+		/*
+		 * Is a replication user provided with --replication-user?
+		 * We'll check later whether we can make a replication connection as that user.
+		 * Overrides any replication user defined in the upstream node record.
+		 */
+		else if (runtime_options.replication_user[0] != '\0')
+		{
+			ReplicationSlotUser = REPLICATION_USER_OPT;
+			*replication_user = runtime_options.replication_user;
+		}
+		/*
+		 * Is the upstream's node record provided, and does it have a different
+		 * replication user?
+		 * We'll check later whether we can make a replication connection as that user.
+		 */
+		else if (upstream_node_record != NULL && upstream_node_record->node_id != UNKNOWN_NODE_ID
+			 && strncmp(upstream_node_record->repluser, PQuser(conn), NAMEDATALEN) != 0)
+		{
+			ReplicationSlotUser = REPLICATION_USER_NODE;
+			*replication_user = upstream_node_record->repluser;
+		}
+	}
+}
+
+
+bool
+check_replication_slots_available(int node_id, PGconn* conn)
+{
+	int max_replication_slots = UNKNOWN_VALUE;
+	int free_slots = get_free_replication_slot_count(conn, &max_replication_slots);
+
+	if (free_slots < 0)
+	{
+		log_error(_("unable to determine number of free replication slots on node %i"),
+				  node_id);
+		return false;
+	}
+
+	if (free_slots == 0)
+	{
+		log_error(_("no free replication slots available on node %i"),
+				  node_id);
+		log_hint(_("consider increasing \"max_replication_slots\" (current value: %i)"),
+				 max_replication_slots);
+		return false;
+	}
+	else if (runtime_options.dry_run == true)
+	{
+		log_info(_("replication slots in use, %i free slots on node %i"),
+				 node_id,
+				 free_slots);
+	}
+
+	return true;
+}
+
+
+/*
+ * Check whether the specified standby has joined to its upstream.
+ *
+ * This is used by "standby switchover" and "node rejoin" to check
+ * the success of a node rejoin operation.
+ *
+ * IMPORTANT: the timeout settings will be taken from the node where the check
+ * is performed, which might not be the standby itself.
+ */
+standy_join_status
+check_standby_join(PGconn *upstream_conn, t_node_info *upstream_node_record, t_node_info *standby_node_record)
+ {
+	 int i;
+	 bool available = false;
+
+	 for (i = 0; i < config_file_options.standby_reconnect_timeout; i++)
+	 {
+		 if (is_server_available(config_file_options.conninfo))
+		 {
+			 log_verbose(LOG_INFO, _("node \"%s\" (ID: %i) is pingable"),
+						 standby_node_record->node_name,
+						 standby_node_record->node_id);
+			 available = true;
+			 break;
+		 }
+
+		 if (i % 5 == 0)
+		 {
+			 log_verbose(LOG_INFO, _("waiting for node \"%s\" (ID: %i) to respond to pings; %i of max %i attempts (parameter \"node_rejoin_timeout\")"),
+						 standby_node_record->node_name,
+						 standby_node_record->node_id,
+						 i + 1,
+						 config_file_options.node_rejoin_timeout);
+		 }
+		 else
+		 {
+			 log_debug("sleeping 1 second waiting for node \"%s\" (ID: %i) to respond to pings; %i of max %i attempts",
+					   standby_node_record->node_name,
+					   standby_node_record->node_id,
+					   i + 1,
+					   config_file_options.node_rejoin_timeout);
+		 }
+
+		 sleep(1);
+	 }
+
+	 /* node did not become available */
+	 if (available == false)
+	 {
+		 return JOIN_FAIL_NO_PING;
+	 }
+
+	 for (; i < config_file_options.node_rejoin_timeout; i++)
+	 {
+		 NodeAttached node_attached = is_downstream_node_attached(upstream_conn,
+																  standby_node_record->node_name);
+		 if (node_attached == NODE_ATTACHED)
+		 {
+			 log_verbose(LOG_INFO, _("node \"%s\" (ID: %i) has attached to its upstream node"),
+						 standby_node_record->node_name,
+						 standby_node_record->node_id);
+			 return JOIN_SUCCESS;
+		 }
+
+		 if (i % 5 == 0)
+		 {
+			 log_info(_("waiting for node \"%s\" (ID: %i) to connect to new primary; %i of max %i attempts (parameter \"node_rejoin_timeout\")"),
+					  standby_node_record->node_name,
+					  standby_node_record->node_id,
+					  i + 1,
+					  config_file_options.node_rejoin_timeout);
+
+			 log_detail(_("checking for record in node \"%s\"'s \"pg_stat_replication\" table where \"application_name\" is \"%s\""),
+						upstream_node_record->node_name,
+						standby_node_record->node_name);
+		 }
+		 else
+		 {
+			 log_debug("sleeping 1 second waiting for node  \"%s\" (ID: %i) to connect to new primary; %i of max %i attempts",
+					   standby_node_record->node_name,
+					   standby_node_record->node_id,
+					   i + 1,
+					   config_file_options.node_rejoin_timeout);
+		 }
+
+		 sleep(1);
+	 }
+
+	 return JOIN_FAIL_NO_REPLICATION;
 }
 
 
@@ -3654,30 +4034,15 @@ bool
 check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_record, bool is_rejoin)
 {
 	uint64		local_system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
-	t_conninfo_param_list follow_target_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PGconn	   *follow_target_repl_conn = NULL;
 	t_system_identification follow_target_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
-	TimeLineHistoryEntry *follow_target_history = NULL;
 	bool success = true;
 
 	const char *action = is_rejoin == true ? "rejoin" : "follow";
 
 	/* check replication connection */
-	initialize_conninfo_params(&follow_target_repl_conninfo, false);
+	follow_target_repl_conn = establish_replication_connection_from_conn(follow_target_conn,
-
+																		 follow_target_node_record->repluser);
-	conn_to_param_list(follow_target_conn, &follow_target_repl_conninfo);
-
-	if (strcmp(param_get(&follow_target_repl_conninfo, "user"), follow_target_node_record->repluser) != 0)
-	{
-		param_set(&follow_target_repl_conninfo, "user", follow_target_node_record->repluser);
-		param_set(&follow_target_repl_conninfo, "dbname", "replication");
-	}
-
-	param_set(&follow_target_repl_conninfo, "replication", "1");
-
-	follow_target_repl_conn = establish_db_connection_by_params(&follow_target_repl_conninfo, false);
-
-	free_conninfo_params(&follow_target_repl_conninfo);
 
 	if (PQstatus(follow_target_repl_conn) != CONNECTION_OK)
 	{
@@ -3775,7 +4140,8 @@ check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *fo
 		/*
 		 * upstream has higher timeline - check where it forked off from this node's timeline
 		 */
-		follow_target_history = get_timeline_history(follow_target_repl_conn, local_tli + 1);
+		TimeLineHistoryEntry *follow_target_history = get_timeline_history(follow_target_repl_conn,
+																		   local_tli + 1);
 
 		if (follow_target_history == NULL)
 		{
@@ -3839,17 +4205,101 @@ check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *fo
 						   format_lsn(follow_target_history->end));
 			}
 		}
+
+		pfree(follow_target_history);
 	}
 
 	PQfinish(follow_target_repl_conn);
 
-	if (follow_target_history)
-		pfree(follow_target_history);
-
 	return success;
 }
 
 
+/*
+ * Check that the replication configuration file is owned by the user who
+ * owns the data directory.
+ */
+extern bool
+check_replication_config_owner(int pg_version, const char *data_directory, PQExpBufferData *error_msg, PQExpBufferData *detail_msg)
+{
+	PQExpBufferData replication_config_file;
+	struct stat     dirstat;
+	struct stat     confstat;
+
+	if (stat(data_directory, &dirstat))
+	{
+		if (error_msg != NULL)
+		{
+			appendPQExpBuffer(error_msg,
+							  "unable to check ownership of data directory \"%s\"",
+							  data_directory);
+			appendPQExpBufferStr(detail_msg,
+								 strerror(errno));
+		}
+		return false;
+	}
+
+	initPQExpBuffer(&replication_config_file);
+
+	appendPQExpBuffer(&replication_config_file,
+					  "%s/%s",
+					  config_file_options.data_directory,
+					  pg_version >= 120000 ? PG_AUTOCONF_FILENAME : RECOVERY_COMMAND_FILE);
+
+	stat(replication_config_file.data, &confstat);
+
+	if (confstat.st_uid == dirstat.st_uid)
+	{
+		termPQExpBuffer(&replication_config_file);
+		return true;
+	}
+
+	if (error_msg != NULL)
+	{
+		char conf_owner[MAXLEN];
+		char dir_owner[MAXLEN];
+		struct passwd *pw;
+
+		pw = getpwuid(confstat.st_uid);
+		if (!pw)
+		{
+			maxlen_snprintf(conf_owner,
+							"(unknown user %i)",
+							confstat.st_uid);
+		}
+		else
+		{
+			strncpy(conf_owner, pw->pw_name, MAXLEN);
+		}
+
+		pw = getpwuid(dirstat.st_uid);
+
+		if (!pw)
+		{
+			maxlen_snprintf(conf_owner,
+							"(unknown user %i)",
+							dirstat.st_uid);
+		}
+		else
+		{
+			strncpy(dir_owner, pw->pw_name, MAXLEN);
+		}
+
+		appendPQExpBuffer(error_msg,
+						  "ownership error for file \"%s\"",
+						  replication_config_file.data);
+		appendPQExpBuffer(detail_msg,
+						  "file owner is \"%s\", data directory owner is \"%s\"",
+						  conf_owner,
+						  dir_owner);
+	}
+
+	termPQExpBuffer(&replication_config_file);
+
+	return false;
+}
+
+
 /*
  * Simple check to see if "shared_preload_libraries" includes "repmgr".
  * Parsing "shared_preload_libraries" is non-trivial, as it's potentially

repmgr-client.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -34,23 +34,21 @@
 #define STANDBY_SWITCHOVER	   8
 #define WITNESS_REGISTER       9
 #define WITNESS_UNREGISTER     10
-#define BDR_REGISTER		   11
+#define NODE_STATUS			   11
-#define BDR_UNREGISTER		   12
+#define NODE_CHECK			   12
-#define NODE_STATUS			   13
+#define NODE_SERVICE		   13
-#define NODE_CHECK			   14
+#define NODE_REJOIN            14
-#define NODE_SERVICE		   15
+#define NODE_CONTROL           15
-#define NODE_REJOIN            16
+#define CLUSTER_SHOW		   16
-#define NODE_CONTROL           17
+#define CLUSTER_CLEANUP		   17
-#define CLUSTER_SHOW		   18
+#define CLUSTER_MATRIX		   18
-#define CLUSTER_CLEANUP		   19
+#define CLUSTER_CROSSCHECK	   19
-#define CLUSTER_MATRIX		   20
+#define CLUSTER_EVENT		   20
-#define CLUSTER_CROSSCHECK	   21
+#define SERVICE_STATUS		   21
-#define CLUSTER_EVENT		   22
+#define SERVICE_PAUSE		   22
-#define SERVICE_STATUS		   23
+#define SERVICE_UNPAUSE		   23
-#define SERVICE_PAUSE		   24
+#define DAEMON_START 		   24
-#define SERVICE_UNPAUSE		   25
+#define DAEMON_STOP 		   25
-#define DAEMON_START 		   26
-#define DAEMON_STOP 		   27
 
 /* command line options without short versions */
 #define OPT_HELP						   1001
@@ -83,23 +81,25 @@
 #define OPT_SIBLINGS_FOLLOW				   1028
 #define OPT_ROLE						   1029
 #define OPT_DOWNSTREAM					   1030
-#define OPT_SLOTS						   1031
+#define OPT_UPSTREAM					   1031
-#define OPT_CONFIG_ARCHIVE_DIR			   1032
+#define OPT_SLOTS						   1032
-#define OPT_HAS_PASSFILE				   1033
+#define OPT_CONFIG_ARCHIVE_DIR			   1033
-#define OPT_WAIT_START					   1034
+#define OPT_HAS_PASSFILE				   1034
-#define OPT_REPL_CONN					   1035
+#define OPT_WAIT_START					   1035
-#define OPT_REMOTE_NODE_ID				   1036
+#define OPT_REPL_CONN					   1036
-#define OPT_RECOVERY_CONF_ONLY			   1037
+#define OPT_REMOTE_NODE_ID				   1037
-#define OPT_NO_WAIT						   1038
+#define OPT_REPLICATION_CONF_ONLY		   1038
-#define OPT_MISSING_SLOTS				   1039
+#define OPT_NO_WAIT						   1039
-#define OPT_REPMGRD_NO_PAUSE			   1040
+#define OPT_MISSING_SLOTS				   1040
-#define OPT_VERSION_NUMBER				   1041
+#define OPT_REPMGRD_NO_PAUSE			   1041
-#define OPT_DATA_DIRECTORY_CONFIG		   1042
+#define OPT_VERSION_NUMBER				   1042
-#define OPT_COMPACT						   1043
+#define OPT_DATA_DIRECTORY_CONFIG		   1043
-#define OPT_DISABLE_WAL_RECEIVER		   1044
+#define OPT_COMPACT						   1044
-#define OPT_ENABLE_WAL_RECEIVER			   1045
+#define OPT_DISABLE_WAL_RECEIVER		   1045
-#define OPT_DETAIL						   1046
+#define OPT_ENABLE_WAL_RECEIVER			   1046
-#define OPT_REPMGRD_FORCE_UNPAUSE		   1047
+#define OPT_DETAIL						   1047
+#define OPT_REPMGRD_FORCE_UNPAUSE		   1048
+#define OPT_REPLICATION_CONFIG_OWNER	   1049
 
 /* deprecated since 4.0 */
 #define OPT_CHECK_UPSTREAM_CONFIG		    999
@@ -157,7 +157,9 @@ static struct option long_options[] =
 	{"upstream-conninfo", required_argument, NULL, OPT_UPSTREAM_CONNINFO},
 	{"upstream-node-id", required_argument, NULL, OPT_UPSTREAM_NODE_ID},
 	{"without-barman", no_argument, NULL, OPT_WITHOUT_BARMAN},
-	{"recovery-conf-only", no_argument, NULL, OPT_RECOVERY_CONF_ONLY},
+	{"replication-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
+	/* deprecate this once Pg11 and earlier are unsupported */
+	{"recovery-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
 
 /* "standby register" options */
 	{"wait-start", required_argument, NULL, OPT_WAIT_START},
@@ -178,6 +180,7 @@ static struct option long_options[] =
 /* "node check" options */
 	{"archive-ready", no_argument, NULL, OPT_ARCHIVE_READY},
 	{"downstream", no_argument, NULL, OPT_DOWNSTREAM},
+	{"upstream", no_argument, NULL, OPT_UPSTREAM},
 	{"replication-lag", no_argument, NULL, OPT_REPLICATION_LAG},
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
@@ -185,6 +188,7 @@ static struct option long_options[] =
 	{"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},
+	{"replication-config-owner", no_argument, NULL, OPT_REPLICATION_CONFIG_OWNER},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},

repmgr.c

@@ -1,7 +1,7 @@
 /*
  * repmgr.c - repmgr extension
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This is the actual extension code; see repmgr-client.c for the code which
  * generates the repmgr binary
@@ -84,8 +84,6 @@ typedef struct repmgrdSharedState
 	int			current_electoral_term;
 	int			candidate_node_id;
 	bool		follow_new_primary;
-	/* BDR failover */
-	int			bdr_failover_handler;
 } repmgrdSharedState;
 
 static repmgrdSharedState *shared_state = NULL;
@@ -131,12 +129,6 @@ PG_FUNCTION_INFO_V1(get_new_primary);
 Datum		reset_voting_status(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(reset_voting_status);
 
-Datum		am_bdr_failover_handler(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(am_bdr_failover_handler);
-
-Datum		unset_bdr_failover_handler(PG_FUNCTION_ARGS);
-PG_FUNCTION_INFO_V1(unset_bdr_failover_handler);
-
 Datum		set_repmgrd_pid(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(set_repmgrd_pid);
 
@@ -241,7 +233,6 @@ repmgr_shmem_startup(void)
 		shared_state->voting_status = VS_NO_VOTE;
 		shared_state->candidate_node_id = UNKNOWN_NODE_ID;
 		shared_state->follow_new_primary = false;
-		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
 	}
 
 	LWLockRelease(AddinShmemInitLock);
@@ -571,63 +562,6 @@ reset_voting_status(PG_FUNCTION_ARGS)
 }
 
 
-Datum
-am_bdr_failover_handler(PG_FUNCTION_ARGS)
-{
-	int			node_id = UNKNOWN_NODE_ID;
-	bool		am_handler = false;
-
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	if (PG_ARGISNULL(0))
-		PG_RETURN_NULL();
-
-	node_id = PG_GETARG_INT32(0);
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	if (shared_state->bdr_failover_handler == UNKNOWN_NODE_ID)
-	{
-		LWLockRelease(shared_state->lock);
-		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
-		shared_state->bdr_failover_handler = node_id;
-		am_handler = true;
-	}
-	else if (shared_state->bdr_failover_handler == node_id)
-	{
-		am_handler = true;
-	}
-
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_BOOL(am_handler);
-}
-
-
-Datum
-unset_bdr_failover_handler(PG_FUNCTION_ARGS)
-{
-	if (!shared_state)
-		PG_RETURN_NULL();
-
-	LWLockAcquire(shared_state->lock, LW_SHARED);
-
-	/* only do something if local_node_id is initialised */
-	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
-	{
-		LWLockRelease(shared_state->lock);
-		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
-
-		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
-	}
-
-	LWLockRelease(shared_state->lock);
-
-	PG_RETURN_VOID();
-}
-
-
 /*
  * Returns the repmgrd pid; or NULL if none set; or -1 if set but repmgrd
  * process not running (TODO!)

repmgr.conf.sample

@@ -21,7 +21,7 @@
 # repmgr and repmgrd require the following items to be explicitly configured.
 
 
-#node_id=    	     	     	 # A unique integer greater than zero
+#node_id=			 # A unique integer greater than zero
 #node_name=''			 # An arbitrary (but unique) string; we recommend
 				 # using the server's hostname or another identifier
 				 # unambiguously associated with the server to avoid
@@ -29,8 +29,8 @@
 				 # node's current role, e.g. 'primary' or 'standby1',
 				 # as roles can change and it will be confusing if
 				 # the current primary is called 'standby1'.
-                                 # The string's maximum length is 63 characters and it should
+				 # The string's maximum length is 63 characters and it should
-                                 # contain only printable ASCII characters.
+				 # contain only printable ASCII characters.
 
 #conninfo=''			 # Database connection information as a conninfo string.
 				 # All servers in the cluster must be able to connect to
@@ -71,13 +71,12 @@
 #replication_user='repmgr'	 # User to make replication connections with, if not set
 				 #  defaults to the user defined in "conninfo".
 
-#replication_type='physical'	 # Must be one of "physical" or "bdr".
+#replication_type='physical'	 # Must "physical" (the default).
-				 # NOTE: "bdr" can only be used with BDR 2.x
 
 #location='default'		 # An arbitrary string defining the location of the node; this
 				 # is used during failover to check visibility of the
 				 # current primary node. For further details see:
-                                 #   https://repmgr.org/docs/current/repmgrd-network-split.html
+				 #   https://repmgr.org/docs/current/repmgrd-network-split.html
 
 #use_replication_slots=no	 # whether to use physical replication slots
 				 # NOTE: when using replication slots,
@@ -160,12 +159,13 @@
 
 #repmgr_bindir=''			# Path to repmgr binary directory (location of the repmgr
 					# binary. Only needed if the repmgr executable is not in
-                                        # the system $PATH or the path defined in "pg_bindir".
+					# the system $PATH or the path defined in "pg_bindir".
 
-#use_primary_conninfo_password=false	# explicitly set "password" in recovery.conf's
+#use_primary_conninfo_password=false	# explicitly set "password" in "primary_conninfo"
-					# "primary_conninfo" parameter using the value contained
+					# using the value contained in the environment variable
-					# in the environment variable PGPASSWORD
+					# PGPASSWORD
 #passfile=''				# path to .pgpass file to include in "primary_conninfo"
+
 #------------------------------------------------------------------------------
 # external command options
 #------------------------------------------------------------------------------
@@ -179,7 +179,7 @@
 #   rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
 #   ssh_options=-o "StrictHostKeyChecking no"
 
-#pg_ctl_options='' 			# Options to append to "pg_ctl"
+#pg_ctl_options=''			# Options to append to "pg_ctl"
 #pg_basebackup_options=''		# Options to append to "pg_basebackup"
 #rsync_options=''			# Options to append to "rsync"
 ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
@@ -194,22 +194,22 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #
 # Examples:
 #
-#   tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
+#   tablespace_mapping='/path/to/original/tablespace=/path/to/new/tablespace'
 #   restore_command = 'cp /path/to/archived/wals/%f %p'
 
-#tablespace_mapping=''	  		# Tablespaces can be remapped from one
+#tablespace_mapping=''			# Tablespaces can be remapped from one
 					# file system location to another. This
 					# parameter can be provided multiple times.
 
-#restore_command=''			# This will be placed in the recovery.conf file generated
+#restore_command=''			# This will be included in the recovery configuration
-					# by repmgr.
+					# generated by repmgr.
 
-#archive_cleanup_command=''		# This will be placed in the recovery.conf file generated
+#archive_cleanup_command=''		# This will be included in the recovery configuration
-					# by repmgr. Note we recommend using Barman for managing
+					# generated by repmgr. Note we recommend using Barman for
-					# WAL archives (see: https://www.pgbarman.org )
+					# managing WAL archives (see: https://www.pgbarman.org )
 
-#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" in recovery.conf
+#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" will be set to
-					# will be set to this value (PostgreSQL 9.4 and later).
+					# this value (PostgreSQL 9.4 and later).
 
 
 #------------------------------------------------------------------------------
@@ -289,24 +289,23 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					#    node or follow the new upstream node
 					# 'manual': repmgrd will take no action and the node will require
 					#    manual attention to reattach it to replication
-					# (does not apply to BDR mode)
 
 #priority=100				# indicates a preferred priority for promoting nodes;
 					# a value of zero prevents the node being promoted to primary
 					# (default: 100)
 
 #connection_check_type=ping		# How to check availability of the upstream node; valid options:
-                                        #  'ping': use PQping() to check if the node is accepting connections
+					#  'ping': use PQping() to check if the node is accepting connections
-                                        #  'connection': execute a throwaway query on the current connection
+					#  'connection': execute a throwaway query on the current connection
 #reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
 #reconnect_interval=10			# Interval between attempts to reconnect to an unreachable
 					# primary (or other upstream node)
-#promote_command=			# command repmgrd executes when promoting a new primary; use something like:
+#promote_command=''			# command repmgrd executes when promoting a new primary; use something like:
 					#
 					#     repmgr standby promote -f /etc/repmgr.conf
 					#
-#follow_command=			# command repmgrd executes when instructing a standby to follow a new primary;
+#follow_command=''			# command repmgrd executes when instructing a standby to follow a new primary;
 					# use something like:
 					#
 					#     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
@@ -318,8 +317,8 @@ 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 "montoring_history" table
-#monitor_interval_secs=2                # Interval (in seconds) at which to write monitoring data
+#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)
 					# disables the timeout completely.
@@ -348,7 +347,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# an error, pause the specified amount of seconds before rerunning the election.
 					#
 					# The following items are relevant for repmgrd running on the primary,
-                                        # and will be ignored on non-primary nodes
+					# and will be ignored on non-primary nodes
 #child_nodes_check_interval=5		# Interval (in seconds) to check for attached child nodes (standbys)
 #child_nodes_connected_min_count=-1	# Minimum number of child nodes which must remain connected, otherwise
 					# disconnection command will be triggered
@@ -373,7 +372,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # NOTE: These commands must be runnable on remote nodes as well for switchover
 # to function correctly.
 #
-# If you use sudo, the user repmgr runs as (usually 'postgres')  must have
+# If you use sudo, the user repmgr runs as (usually 'postgres')	 must have
 # passwordless sudo access to execute the command.
 #
 # For example, to use systemd, you can set
@@ -386,8 +385,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #    # this is required when running sudo over ssh without -t:
 #    Defaults:postgres !requiretty
 #    postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.6, \
-#       /usr/bin/systemctl start postgresql-9.6, \
+#	/usr/bin/systemctl start postgresql-9.6, \
-#       /usr/bin/systemctl restart postgresql-9.6
+#	/usr/bin/systemctl restart postgresql-9.6
 #
 # Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
 #
@@ -414,7 +413,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 
 # Various warning/critical thresholds used by "repmgr node check".
 
-#archive_ready_warning=16  	      	# repmgr node check --archive-ready
+#archive_ready_warning=16		# repmgr node check --archive-ready
 #archive_ready_critical=128		#
 					# Numbers of files pending archiving via PostgreSQL's
 					# "archive_command" configuration parameter. If
@@ -435,12 +434,3 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# issues with shutting down the demotion candidate.
 
 
-#------------------------------------------------------------------------------
-# BDR monitoring options
-#------------------------------------------------------------------------------
-
-#bdr_local_monitoring_only=false         # Only monitor the local node; no checks will be
-					 # performed on the other node
-#bdr_recovery_timeout                    # If a BDR node was offline and has become available
-					 # maximum length of time in seconds to wait for the
-					 # node to reconnect to the cluster

repmgr.control

@@ -1,6 +1,6 @@
 # repmgr extension
 comment = 'Replication manager for PostgreSQL'
-default_version = '5.0'
+default_version = '5.1'
 module_pathname = '$libdir/repmgr'
 relocatable = false
 schema = repmgr

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -78,16 +78,15 @@
 #define MIN_SUPPORTED_VERSION_NUM	90300
 
 #define REPLICATION_TYPE_PHYSICAL 1
-#define REPLICATION_TYPE_BDR	  2
 
 #define UNKNOWN_SERVER_VERSION_NUM -1
-#define UNKNOWN_BDR_VERSION_NUM -1
 #define UNKNOWN_REPMGR_VERSION_NUM -1
 
 #define UNKNOWN_TIMELINE_ID -1
 #define UNKNOWN_SYSTEM_IDENTIFIER 0
 #define UNKNOWN_PID			-1
 #define UNKNOWN_REPLICATION_LAG	-1
+#define UNKNOWN_VALUE		-1
 
 #define NODE_NOT_FOUND		-1
 #define NO_UPSTREAM_NODE	-1
@@ -98,8 +97,6 @@
 #define ARCHIVE_STATUS_DIR_ERROR -1
 #define NO_DEGRADED_MONITORING_ELAPSED -1
 
-#define BDR2_REPLICATION_SET_NAME "repmgr"
-
 /*
  * various default values - ensure repmgr.conf.sample is update
  * if any of these are changed
@@ -113,7 +110,6 @@
 #define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
 #define DEFAULT_PRIMARY_FOLLOW_TIMEOUT       60  /* seconds */
 #define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
-#define DEFAULT_BDR_RECOVERY_TIMEOUT         30  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */
 #define	DEFAULT_REPLICATION_LAG_WARNING      300 /* seconds */

repmgr_version.h.in

@@ -1,5 +1,5 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "5.0"
+#define REPMGR_VERSION "5.1.0"
-#define REPMGR_VERSION_NUM 50000
+#define REPMGR_VERSION_NUM 50100
-#define REPMGR_RELEASE_DATE "2019-XX-XX"
+#define REPMGR_RELEASE_DATE "2020-04-13"
 #define PG_ACTUAL_VERSION_NUM 

repmgrd-bdr.c

@@ -1,678 +0,0 @@
-/*
- * repmgrd-bdr.c - BDR functionality for repmgrd
- *
- * Copyright (c) 2ndQuadrant, 2010-2019
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <signal.h>
-
-#include "repmgr.h"
-#include "repmgrd.h"
-#include "repmgrd-bdr.h"
-#include "configfile.h"
-
-
-static void do_bdr_failover(NodeInfoList *nodes, t_node_info *monitored_node);
-static void do_bdr_recovery(NodeInfoList *nodes, t_node_info *monitored_node);
-
-
-void
-do_bdr_node_check(void)
-{
-	/* nothing to do at the moment */
-}
-
-void
-handle_sigint_bdr(SIGNAL_ARGS)
-{
-	PQExpBufferData event_details;
-
-	initPQExpBuffer(&event_details);
-
-	appendPQExpBuffer(&event_details,
-					  _("%s signal received"),
-					  postgres_signal_arg == SIGTERM
-					  ? "TERM" : "INT");
-
-	log_notice("%s", event_details.data);
-
-	create_event_notification(local_conn,
-							  &config_file_options,
-							  config_file_options.node_id,
-							  "repmgrd_shutdown",
-							  true,
-							  event_details.data);
-	termPQExpBuffer(&event_details);
-
-	terminate(SUCCESS);
-}
-
-
-void
-monitor_bdr(void)
-{
-	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
-	t_bdr_node_info bdr_node_info = T_BDR_NODE_INFO_INITIALIZER;
-	RecordStatus record_status;
-	NodeInfoListCell *cell;
-	instr_time	log_status_interval_start;
-
-	/* sanity check local database */
-	log_info(_("connecting to local database \"%s\""),
-			 config_file_options.conninfo);
-
-	local_conn = establish_db_connection(config_file_options.conninfo, true);
-
-	/*
-	 * Local node must be running
-	 */
-	if (PQstatus(local_conn) != CONNECTION_OK)
-	{
-		log_error(_("unable connect to local node (ID: %i), terminating"),
-				  local_node_info.node_id);
-		log_hint(_("local node must be running before repmgrd can start"));
-		PQfinish(local_conn);
-		exit(ERR_DB_CONN);
-	}
-
-	/*
-	 * Verify that database is a BDR one TODO: check if supported BDR version?
-	 */
-	log_info(_("connected to database, checking for BDR"));
-
-	if (!is_bdr_db(local_conn, NULL))
-	{
-		log_error(_("database is not BDR-enabled"));
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/*
-	 * Check this is a supported BDR version (basically BDR 2.x)
-	 */
-	if (get_bdr_version_num() > 2)
-	{
-		log_error(_("\"bdr\" mode is for BDR 2.x only"));
-		log_hint(_("for BDR 3 and later, use \"replication_type=physical\""));
-		log_error(_("database is not BDR-enabled"));
-		exit(ERR_DB_CONN);
-	}
-
-	if (is_table_in_bdr_replication_set(local_conn, "nodes", "repmgr") == false)
-	{
-		log_error(_("repmgr metadata table 'repmgr.%s' is not in the 'repmgr' replication set"),
-				  "nodes");
-
-		/*
-		 * TODO: add `repmgr bdr sync` or similar for this situation, and hint
-		 * here
-		 */
-
-		exit(ERR_BAD_CONFIG);
-	}
-
-	record_status = get_bdr_node_record_by_name(local_conn, local_node_info.node_name, &bdr_node_info);
-
-	if (record_status != RECORD_FOUND)
-	{
-		log_error(_("unable to retrieve BDR record for node \"%s\", terminating"),
-				  local_node_info.node_name);
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (local_node_info.active == false)
-	{
-		log_error(_("local node (ID: %i) is marked as inactive in repmgr"),
-				  local_node_info.node_id);
-		log_hint(_("if the node has been reactivated, run \"repmgr bdr register --force\" and restart repmgrd"));
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (is_active_bdr_node(local_conn, local_node_info.node_name) == false)
-	{
-		log_error(_("BDR node \"%s\" is not active, terminating"),
-				  local_node_info.node_name);
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/* Log startup event */
-	create_event_record(local_conn,
-						&config_file_options,
-						config_file_options.node_id,
-						"repmgrd_start",
-						true,
-						NULL);
-
-	/*
-	 * retrieve list of all nodes - we'll need these if the DB connection goes
-	 * away
-	 */
-	if (get_all_node_records(local_conn, &nodes) == false)
-	{
-		/* get_all_node_records() will display the error */
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-
-	/* we're expecting all (both) nodes to be up */
-	for (cell = nodes.head; cell; cell = cell->next)
-	{
-		cell->node_info->node_status = NODE_STATUS_UP;
-	}
-
-	log_info(_("starting continuous BDR node monitoring on node %i"),
-			 config_file_options.node_id);
-
-	INSTR_TIME_SET_CURRENT(log_status_interval_start);
-
-	while (true)
-	{
-
-		/* monitoring loop */
-		log_verbose(LOG_DEBUG, "BDR check loop - checking %i nodes", nodes.node_count);
-
-		for (cell = nodes.head; cell; cell = cell->next)
-		{
-			if (config_file_options.bdr_local_monitoring_only == true
-				&& cell->node_info->node_id != local_node_info.node_id)
-			{
-				continue;
-			}
-
-			if (cell->node_info->node_id == local_node_info.node_id)
-			{
-				log_debug("checking local node %i in %s state",
-						  local_node_info.node_id,
-						  print_monitoring_state(cell->node_info->monitoring_state));
-			}
-			else
-			{
-				log_debug("checking other node %i in %s state",
-						  cell->node_info->node_id,
-						  print_monitoring_state(cell->node_info->monitoring_state));
-			}
-
-
-			switch (cell->node_info->monitoring_state)
-			{
-				case MS_NORMAL:
-					{
-						if (is_server_available(cell->node_info->conninfo) == false)
-						{
-							/* node is down, we were expecting it to be up */
-							if (cell->node_info->node_status == NODE_STATUS_UP)
-							{
-								instr_time	node_unreachable_start;
-
-								INSTR_TIME_SET_CURRENT(node_unreachable_start);
-
-								cell->node_info->node_status = NODE_STATUS_DOWN;
-
-								if (cell->node_info->conn != NULL)
-								{
-									PQfinish(cell->node_info->conn);
-									cell->node_info->conn = NULL;
-								}
-
-								log_warning(_("unable to connect to node \"%s\" (ID %i)"),
-											cell->node_info->node_name, cell->node_info->node_id);
-								try_reconnect(&cell->node_info->conn, cell->node_info);
-
-								/* node has recovered - log and continue */
-								if (cell->node_info->node_status == NODE_STATUS_UP)
-								{
-									int			node_unreachable_elapsed = calculate_elapsed(node_unreachable_start);
-									PQExpBufferData event_details;
-
-									initPQExpBuffer(&event_details);
-
-									appendPQExpBuffer(&event_details,
-													  _("reconnected to node %i after %i seconds"),
-													  cell->node_info->node_id,
-													  node_unreachable_elapsed);
-									log_notice("%s", event_details.data);
-
-									create_event_notification(cell->node_info->conn,
-															  &config_file_options,
-															  config_file_options.node_id,
-															  "bdr_reconnect",
-															  true,
-															  event_details.data);
-									termPQExpBuffer(&event_details);
-
-									goto loop;
-								}
-
-								/* still down after reconnect attempt(s) */
-								if (cell->node_info->node_status == NODE_STATUS_DOWN)
-								{
-									do_bdr_failover(&nodes, cell->node_info);
-									goto loop;
-								}
-							}
-						}
-					}
-					break;
-				case MS_DEGRADED:
-					{
-						/* degraded monitoring */
-						if (is_server_available(cell->node_info->conninfo) == true)
-						{
-							do_bdr_recovery(&nodes, cell->node_info);
-						}
-
-					}
-					break;
-			}
-		}
-
-loop:
-
-		/* emit "still alive" log message at regular intervals, if requested */
-		if (config_file_options.log_status_interval > 0)
-		{
-			int			log_status_interval_elapsed = calculate_elapsed(log_status_interval_start);
-			if (log_status_interval_elapsed >= config_file_options.log_status_interval)
-			{
-				log_info(_("monitoring BDR replication status on node \"%s\" (ID: %i)"),
-						 local_node_info.node_name,
-						 local_node_info.node_id);
-
-				for (cell = nodes.head; cell; cell = cell->next)
-				{
-					if (cell->node_info->monitoring_state == MS_DEGRADED)
-					{
-						log_detail(_("monitoring node \"%s\" (ID: %i) in degraded mode"),
-								   cell->node_info->node_name,
-								   cell->node_info->node_id);
-					}
-				}
-				INSTR_TIME_SET_CURRENT(log_status_interval_start);
-			}
-		}
-
-		if (got_SIGHUP)
-		{
-			/*
-			 * if we can reload, then could need to change local_conn
-			 */
-			if (reload_config(&config_file_options, BDR))
-			{
-				PQfinish(local_conn);
-				local_conn = establish_db_connection(config_file_options.conninfo, true);
-				update_registration(local_conn);
-			}
-
-			got_SIGHUP = false;
-		}
-
-		/* XXX this looks like it will never be called */
-		if (got_SIGHUP)
-		{
-			log_debug("SIGHUP received");
-
-			if (reload_config(&config_file_options, BDR))
-			{
-				PQfinish(local_conn);
-				local_conn = establish_db_connection(config_file_options.conninfo, true);
-
-				if (*config_file_options.log_file)
-				{
-					FILE	   *fd;
-
-					fd = freopen(config_file_options.log_file, "a", stderr);
-					if (fd == NULL)
-					{
-						fprintf(stderr, "error reopening stderr to \"%s\": %s",
-								config_file_options.log_file, strerror(errno));
-					}
-				}
-			}
-			got_SIGHUP = false;
-		}
-
-		log_verbose(LOG_DEBUG, "sleeping %i seconds (\"monitor_interval_secs\")",
-					config_file_options.monitor_interval_secs);
-		sleep(config_file_options.monitor_interval_secs);
-	}
-
-	return;
-}
-
-/*
- * do_bdr_failover()
- *
- * Here we attempt to perform a BDR "failover".
- *
- * As there's no equivalent of a physical replication failover,
- * we'll do the following:
- *
- *  - connect to active node
- *  - generate an event log record on that node
- *  - optionally execute `bdr_failover_command`, passing the conninfo string
- *    of that node to the command; this can be used for e.g. reconfiguring
- *    pgbouncer.
- *
- */
-
-void
-do_bdr_failover(NodeInfoList *nodes, t_node_info *monitored_node)
-{
-	PGconn	   *next_node_conn = NULL;
-	NodeInfoListCell *cell;
-	t_event_info event_info = T_EVENT_INFO_INITIALIZER;
-	t_node_info target_node = T_NODE_INFO_INITIALIZER;
-	t_node_info failed_node = T_NODE_INFO_INITIALIZER;
-	RecordStatus record_status;
-
-	/* if one of the two nodes is down, cluster will be in a degraded state */
-	monitored_node->monitoring_state = MS_DEGRADED;
-	INSTR_TIME_SET_CURRENT(degraded_monitoring_start);
-
-	/* terminate local connection if this is the failed node */
-	if (monitored_node->node_id == local_node_info.node_id)
-	{
-		PQfinish(local_conn);
-		local_conn = NULL;
-	}
-
-
-	/* get other node */
-
-	for (cell = nodes->head; cell; cell = cell->next)
-	{
-		log_debug("do_bdr_failover() %s", cell->node_info->node_name);
-
-		/*
-		 * don't attempt to connect to the current monitored node, as that's
-		 * the one which has failed
-		 */
-		if (cell->node_info->node_id == monitored_node->node_id)
-			continue;
-
-		/* TODO: reuse local conn if local node is up */
-		next_node_conn = establish_db_connection(cell->node_info->conninfo, false);
-
-		if (PQstatus(next_node_conn) == CONNECTION_OK)
-		{
-			record_status = get_node_record(next_node_conn,
-											cell->node_info->node_id,
-											&target_node);
-
-			if (record_status == RECORD_FOUND)
-			{
-				break;
-			}
-		}
-
-		next_node_conn = NULL;
-	}
-
-	/* shouldn't happen, and if it does, it means everything is down */
-	if (next_node_conn == NULL)
-	{
-		log_error(_("no other available node found"));
-
-		/* no other nodes found - continue degraded monitoring */
-		return;
-	}
-
-	/*
-	 * check if the node record for the failed node is still marked as active,
-	 * if not it means the other node has done the "failover" already
-	 */
-
-	record_status = get_node_record(next_node_conn,
-									monitored_node->node_id,
-									&failed_node);
-
-	if (record_status == RECORD_FOUND && failed_node.active == false)
-	{
-		PQfinish(next_node_conn);
-		log_notice(_("record for node %i has already been set inactive"),
-				   failed_node.node_id);
-		return;
-	}
-
-	if (am_bdr_failover_handler(next_node_conn, local_node_info.node_id) == false)
-	{
-		PQfinish(next_node_conn);
-		log_notice(_("other node's repmgrd is handling failover"));
-		return;
-	}
-
-
-	/* check here that the node hasn't come back up */
-	if (is_server_available(monitored_node->conninfo) == true)
-	{
-		log_notice(_("node %i has reappeared, aborting failover"),
-				   monitored_node->node_id);
-		monitored_node->monitoring_state = MS_NORMAL;
-		PQfinish(next_node_conn);
-	}
-
-	log_debug("this node is the failover handler");
-
-	{
-		PQExpBufferData event_details;
-
-		initPQExpBuffer(&event_details);
-
-		event_info.conninfo_str = target_node.conninfo;
-		event_info.node_name = target_node.node_name;
-
-		/* update node record on the active node */
-		update_node_record_set_active(next_node_conn, monitored_node->node_id, false);
-
-		log_notice(_("setting node record for node %i to inactive"), monitored_node->node_id);
-
-		appendPQExpBuffer(&event_details,
-						  _("node \"%s\" (ID: %i) detected as failed; next available node is \"%s\" (ID: %i)"),
-						  monitored_node->node_name,
-						  monitored_node->node_id,
-						  target_node.node_name,
-						  target_node.node_id);
-
-		/*
-		 * Create an event record
-		 *
-		 * If we were able to connect to another node, we'll update the event log
-		 * there.
-		 *
-		 * In any case the event notification command will be triggered with the
-		 * event "bdr_failover"
-		 */
-
-
-		create_event_notification_extended(next_node_conn,
-										   &config_file_options,
-										   monitored_node->node_id,
-										   "bdr_failover",
-										   true,
-										   event_details.data,
-										   &event_info);
-
-		log_info("%s", event_details.data);
-
-		termPQExpBuffer(&event_details);
-	}
-
-	unset_bdr_failover_handler(next_node_conn);
-
-	PQfinish(next_node_conn);
-
-
-	return;
-}
-
-static void
-do_bdr_recovery(NodeInfoList *nodes, t_node_info *monitored_node)
-{
-	PGconn	   *recovered_node_conn;
-
-	t_event_info event_info = T_EVENT_INFO_INITIALIZER;
-	int			i;
-	bool		slot_reactivated = false;
-	int			node_recovery_elapsed;
-
-	char		node_name[MAXLEN] = "";
-
-	log_debug("handling recovery for monitored node %i", monitored_node->node_id);
-
-	recovered_node_conn = establish_db_connection(monitored_node->conninfo, false);
-
-	if (PQstatus(recovered_node_conn) != CONNECTION_OK)
-	{
-		PQfinish(recovered_node_conn);
-		return;
-	}
-
-	if (PQstatus(local_conn) != CONNECTION_OK)
-	{
-		log_debug("no local connection - attempting to reconnect ");
-		local_conn = establish_db_connection(config_file_options.conninfo, false);
-	}
-
-	/*
-	 * still unable to connect - the local node is probably down, so we can't
-	 * check for reconnection
-	 */
-	if (PQstatus(local_conn) != CONNECTION_OK)
-	{
-		PQExpBufferData event_details;
-
-		local_conn = NULL;
-		log_warning(_("unable to reconnect to local node"));
-
-		initPQExpBuffer(&event_details);
-
-		node_recovery_elapsed = calculate_elapsed(degraded_monitoring_start);
-		monitored_node->monitoring_state = MS_NORMAL;
-		monitored_node->node_status = NODE_STATUS_UP;
-
-		appendPQExpBuffer(
-						  &event_details,
-						  _("node \"%s\" (ID: %i) has become available after %i seconds"),
-						  monitored_node->node_name,
-						  monitored_node->node_id,
-						  node_recovery_elapsed);
-
-		log_notice("%s", event_details.data);
-
-		termPQExpBuffer(&event_details);
-
-		PQfinish(recovered_node_conn);
-
-		return;
-	}
-
-	get_bdr_other_node_name(local_conn, local_node_info.node_id, node_name);
-
-	log_info(_("detected recovery on node \"%s\" (ID: %i), checking status"),
-			 monitored_node->node_name,
-			 monitored_node->node_id);
-
-	for (i = 0; i < config_file_options.bdr_recovery_timeout; i++)
-	{
-		ReplSlotStatus slot_status;
-
-		log_debug("checking for state of replication slot for node \"%s\"", node_name);
-
-		slot_status = get_bdr_node_replication_slot_status(
-														   local_conn,
-														   node_name);
-
-		if (slot_status == SLOT_ACTIVE)
-		{
-			slot_reactivated = true;
-			break;
-		}
-
-		sleep(1);
-	}
-
-	/* mark node as up */
-	monitored_node->node_status = NODE_STATUS_UP;
-
-	if (slot_reactivated == false)
-	{
-		log_warning(_("no active replication slot for node \"%s\" found after %i seconds"),
-					node_name,
-					config_file_options.bdr_recovery_timeout);
-		log_detail(_("this probably means inter-node BDR connections have not been re-established"));
-		PQfinish(recovered_node_conn);
-		return;
-	}
-
-	log_info(_("active replication slot for node \"%s\" found after %i seconds"),
-			 node_name,
-			 i);
-
-	node_recovery_elapsed = calculate_elapsed(degraded_monitoring_start);
-	monitored_node->monitoring_state = MS_NORMAL;
-
-	{
-		PQExpBufferData event_details;
-
-		initPQExpBuffer(&event_details);
-
-		appendPQExpBuffer(&event_details,
-						  _("node \"%s\" (ID: %i) has recovered after %i seconds"),
-						  monitored_node->node_name,
-						  monitored_node->node_id,
-						  node_recovery_elapsed);
-
-		log_notice("%s", event_details.data);
-
-
-		/* other node will generate the event */
-		if (monitored_node->node_id == local_node_info.node_id)
-		{
-			termPQExpBuffer(&event_details);
-			PQfinish(recovered_node_conn);
-
-			return;
-		}
-
-
-		/* generate the event on the currently active node only */
-		if (monitored_node->node_id != local_node_info.node_id)
-		{
-			event_info.conninfo_str = monitored_node->conninfo;
-			event_info.node_name = monitored_node->node_name;
-
-			create_event_notification_extended(local_conn,
-											   &config_file_options,
-											   config_file_options.node_id,
-											   "bdr_recovery",
-											   true,
-											   event_details.data,
-											   &event_info);
-		}
-
-		termPQExpBuffer(&event_details);
-	}
-
-	update_node_record_set_active(local_conn, monitored_node->node_id, true);
-
-	PQfinish(recovered_node_conn);
-
-	return;
-}

repmgrd-bdr.h

@@ -1,26 +0,0 @@
-/*
- * repmgrd-bdr.h
- * Copyright (c) 2ndQuadrant, 2010-2019
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _REPMGRD_BDR_H_
-#define _REPMGRD_BDR_H_
-
-extern void do_bdr_node_check(void);
-extern void monitor_bdr(void);
-
-extern void	handle_sigint_bdr(SIGNAL_ARGS);
-#endif							/* _REPMGRD_BDR_H_ */

repmgrd-physical.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd-physical.c - physical (streaming) replication functionality for repmgrd
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -125,6 +125,8 @@ static void clear_child_node_info_list(t_child_node_info_list *nodes);
 static void parse_child_nodes_disconnect_command(char *parsed_command, char *template, int reporting_node_id);
 static void execute_child_nodes_disconnect_command(NodeInfoList *db_child_node_records, t_child_node_info_list *local_child_nodes);
 
+static int try_primary_reconnect(PGconn **conn, PGconn *local_conn, t_node_info *node_info);
+
 void
 handle_sigint_physical(SIGNAL_ARGS)
 {
@@ -1497,7 +1499,34 @@ monitor_streaming_standby(void)
 					check_connection(&local_node_info, &local_conn);
 				}
 
-				try_reconnect(&upstream_conn, &upstream_node_info);
+
+				if (upstream_node_info.type == PRIMARY)
+				{
+					primary_node_id = try_primary_reconnect(&upstream_conn, local_conn, &upstream_node_info);
+
+					/*
+					 * We were notified by the the primary during our own reconnection
+					 * retry phase, in which case we can leave the failover process early
+					 * and connect to the new primary.
+					 */
+					if (primary_node_id == ELECTION_RERUN_NOTIFICATION)
+					{
+						if (do_primary_failover() == true)
+						{
+							primary_node_id = get_primary_node_id(local_conn);
+							return;
+						}
+					}
+					if (primary_node_id != UNKNOWN_NODE_ID && primary_node_id != ELECTION_RERUN_NOTIFICATION)
+					{
+						follow_new_primary(primary_node_id);
+						return;
+					}
+				}
+				else
+				{
+					try_reconnect(&upstream_conn, &upstream_node_info);
+				}
 
 				/* Upstream node has recovered - log and continue */
 				if (upstream_node_info.node_status == NODE_STATUS_UP)
@@ -2632,7 +2661,6 @@ loop:
 	}
 
 	return;
-
 }
 
 
@@ -3655,7 +3683,9 @@ follow_new_primary(int new_primary_id)
 		else
 		{
 			new_primary_ok = false;
-			log_warning(_("new primary is not in recovery"));
+			log_warning(_("new primary \"%s\" (node ID: %i) is in recovery"),
+						new_primary.node_name,
+						new_primary_id);
 			close_connection(&upstream_conn);
 		}
 	}
@@ -3848,7 +3878,9 @@ witness_follow_new_primary(int new_primary_id)
 				break;
 			case RECTYPE_STANDBY:
 				new_primary_ok = false;
-				log_warning(_("new primary is not in recovery"));
+				log_warning(_("new primary \"%s\" (node ID: %i) is in recovery"),
+							new_primary.node_name,
+							new_primary_id);
 				break;
 			case RECTYPE_UNKNOWN:
 				new_primary_ok = false;
@@ -4029,7 +4061,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 	}
 	else
 	{
-		log_info(_("primary and this node have the same location (\"%s\")"),
+		log_info(_("primary node  \"%s\" (ID: %i) and this node have the same location (\"%s\")"),
+				 upstream_node_info.node_name,
+				 upstream_node_info.node_id,
 				 local_node_info.location);
 	}
 
@@ -4269,7 +4303,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 			else
 			{
 				nodes_with_primary_still_visible++;
-				log_notice(_("node %i last saw primary node %i second(s) ago, considering primary still visible"),
+				log_notice(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago, considering primary still visible"),
+						   get_node_type_string(cell->node_info->type),
+						   cell->node_info->node_name,
 						   cell->node_info->node_id,
 						   sibling_replication_info.upstream_last_seen);
 				appendPQExpBuffer(&nodes_with_primary_visible,
@@ -4281,7 +4317,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		}
 		else
 		{
-			log_info(_("node %i last saw primary node %i second(s) ago"),
+			log_info(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago"),
+					 get_node_type_string(cell->node_info->type),
+					 cell->node_info->node_name,
 					 cell->node_info->node_id,
 					 sibling_replication_info.upstream_last_seen);
 		}
@@ -4773,11 +4811,9 @@ parse_failover_validation_command(const char *template, t_node_info *node_info,
 static bool
 check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_info)
 {
-	t_conninfo_param_list local_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PGconn	   *local_repl_conn = NULL;
 	t_system_identification local_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
 
-	t_conninfo_param_list follow_target_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PGconn	   *follow_target_repl_conn = NULL;
 	t_system_identification follow_target_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
 	TimeLineHistoryEntry *follow_target_history = NULL;
@@ -4785,23 +4821,7 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 	bool can_follow = true;
 	bool success;
 
-	/* Check local replication connection - we want to execute IDENTIFY_SYSTEM
+	local_repl_conn = establish_replication_connection_from_conn(local_conn, local_node_info.repluser);
-	 * to get the current timeline ID, which might not yet be written to
-	 * pg_control.
-	 *
-	 * TODO: from 9.6, query "pg_stat_wal_receiver" via the existing local connection
-	 */
-
-	initialize_conninfo_params(&local_repl_conninfo, false);
-
-	conn_to_param_list(local_conn, &local_repl_conninfo);
-
-	/* Set the replication user from the node record */
-	param_set(&local_repl_conninfo, "user", local_node_info.repluser);
-	param_set(&local_repl_conninfo, "replication", "1");
-
-	local_repl_conn = establish_db_connection_by_params(&local_repl_conninfo, false);
-	free_conninfo_params(&local_repl_conninfo);
 
 	if (PQstatus(local_repl_conn) != CONNECTION_OK)
 	{
@@ -4810,6 +4830,7 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 
 		return false;
 	}
+
 	success = identify_system(local_repl_conn, &local_identification);
 	PQfinish(local_repl_conn);
 
@@ -4821,22 +4842,8 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 	}
 
 	/* check replication connection */
-	initialize_conninfo_params(&follow_target_repl_conninfo, false);
+	follow_target_repl_conn = establish_replication_connection_from_conn(follow_target_conn,
-
+																		 follow_target_node_info->repluser);
-	conn_to_param_list(follow_target_conn, &follow_target_repl_conninfo);
-
-	if (strcmp(param_get(&follow_target_repl_conninfo, "user"), follow_target_node_info->repluser) != 0)
-	{
-		param_set(&follow_target_repl_conninfo, "user", follow_target_node_info->repluser);
-		param_set(&follow_target_repl_conninfo, "dbname", "replication");
-	}
-
-	param_set(&follow_target_repl_conninfo, "replication", "1");
-
-	follow_target_repl_conn = establish_db_connection_by_params(&follow_target_repl_conninfo, false);
-
-	free_conninfo_params(&follow_target_repl_conninfo);
-
 	if (PQstatus(follow_target_repl_conn) != CONNECTION_OK)
 	{
 		log_error(_("unable to establish a replication connection to the follow target node"));
@@ -5140,3 +5147,117 @@ parse_child_nodes_disconnect_command(char *parsed_command, char *template, int r
 
 	return;
 }
+
+
+int
+try_primary_reconnect(PGconn **conn, PGconn *local_conn, t_node_info *node_info)
+{
+	PGconn	   *our_conn;
+	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
+
+	int			i;
+
+	int			max_attempts = config_file_options.reconnect_attempts;
+
+	initialize_conninfo_params(&conninfo_params, false);
+
+	/* we assume by now the conninfo string is parseable */
+	(void) parse_conninfo_string(node_info->conninfo, &conninfo_params, NULL, false);
+
+	/* set some default values if not explicitly provided */
+	param_set_ine(&conninfo_params, "connect_timeout", "2");
+	param_set_ine(&conninfo_params, "fallback_application_name", "repmgr");
+
+	for (i = 0; i < max_attempts; i++)
+	{
+		log_info(_("checking state of node %i, %i of %i attempts"),
+				 node_info->node_id, i + 1, max_attempts);
+		if (is_server_available_params(&conninfo_params) == true)
+		{
+			log_notice(_("node %i has recovered, reconnecting"), node_info->node_id);
+
+			/*
+			 * Note: we could also handle the case where node is pingable but
+			 * connection denied due to connection exhaustion, by falling back to
+			 * degraded monitoring (make configurable)
+			 */
+			our_conn = establish_db_connection_by_params(&conninfo_params, false);
+
+			if (PQstatus(our_conn) == CONNECTION_OK)
+			{
+				free_conninfo_params(&conninfo_params);
+
+				log_info(_("connection to node %i succeeded"), node_info->node_id);
+
+				if (PQstatus(*conn) == CONNECTION_BAD)
+				{
+					log_verbose(LOG_INFO, _("original connection handle returned CONNECTION_BAD, using new connection"));
+					close_connection(conn);
+					*conn = our_conn;
+				}
+				else
+				{
+					ExecStatusType ping_result;
+
+					ping_result = connection_ping(*conn);
+
+					if (ping_result != PGRES_TUPLES_OK)
+					{
+						log_info(_("original connection no longer available, using new connection"));
+						close_connection(conn);
+						*conn = our_conn;
+					}
+					else
+					{
+						log_info(_("original connection is still available"));
+
+						PQfinish(our_conn);
+					}
+				}
+
+				node_info->node_status = NODE_STATUS_UP;
+
+				return UNKNOWN_NODE_ID;
+			}
+
+			close_connection(&our_conn);
+			log_notice(_("unable to reconnect to node \"%s\" (ID: %i)"),
+					   node_info->node_name,
+					   node_info->node_id);
+		}
+
+		if (i + 1 < max_attempts)
+		{
+			int j;
+			log_info(_("sleeping %i seconds until next reconnection attempt"),
+					 config_file_options.reconnect_interval);
+			for (j = 0; j < config_file_options.reconnect_interval; j++)
+			{
+				int new_primary_node_id;
+				if (get_new_primary(local_conn, &new_primary_node_id) == true && new_primary_node_id != UNKNOWN_NODE_ID)
+				{
+					if (new_primary_node_id == ELECTION_RERUN_NOTIFICATION)
+					{
+						log_notice(_("received rerun notification"));
+					}
+					else
+					{
+						log_notice(_("received notification that new primary is node %i"), new_primary_node_id);
+					}
+					return new_primary_node_id;
+				}
+				sleep(1);
+			}
+		}
+	}
+
+	log_warning(_("unable to reconnect to node %i after %i attempts"),
+				node_info->node_id,
+				max_attempts);
+
+	node_info->node_status = NODE_STATUS_DOWN;
+
+	free_conninfo_params(&conninfo_params);
+
+	return UNKNOWN_NODE_ID;
+}

repmgrd-physical.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd-physical.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgrd.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd.c - Replication manager daemon
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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
@@ -26,7 +26,6 @@
 #include "repmgr.h"
 #include "repmgrd.h"
 #include "repmgrd-physical.h"
-#include "repmgrd-bdr.h"
 #include "configfile.h"
 #include "voting.h"
 
@@ -484,9 +483,6 @@ main(int argc, char **argv)
 			case REPLICATION_TYPE_PHYSICAL:
 				log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
 				break;
-			case REPLICATION_TYPE_BDR:
-				log_hint(_("check that 'repmgr bdr register' was executed for this node"));
-				break;
 		}
 
 		close_connection(&local_conn);
@@ -513,12 +509,7 @@ main(int argc, char **argv)
 		}
 	}
 
-	if (config_file_options.replication_type == REPLICATION_TYPE_BDR)
+	if (config_file_options.replication_type == REPLICATION_TYPE_PHYSICAL)
-	{
-		log_debug("node id is %i", local_node_info.node_id);
-		do_bdr_node_check();
-	}
-	else
 	{
 		log_debug("node id is %i, upstream node id is %i",
 				  local_node_info.node_id,
@@ -526,8 +517,6 @@ main(int argc, char **argv)
 		do_physical_node_check();
 	}
 
-
-
 	if (daemonize == true)
 	{
 		daemonize_process();
@@ -576,9 +565,6 @@ start_monitoring(void)
 			case WITNESS:
 				monitor_streaming_witness();
 				break;
-			case BDR:
-				monitor_bdr();
-				return;
 			case UNKNOWN:
 				/* should never happen */
 				break;
@@ -771,10 +757,6 @@ setup_event_handlers(void)
 	 */
 	switch (config_file_options.replication_type)
 	{
-		case REPLICATION_TYPE_BDR:
-			pqsignal(SIGINT, handle_sigint_bdr);
-			pqsignal(SIGTERM, handle_sigint_bdr);
-			break;
 		case REPLICATION_TYPE_PHYSICAL:
 			pqsignal(SIGINT, handle_sigint_physical);
 			pqsignal(SIGTERM, handle_sigint_physical);

repmgrd.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  */
 
 

scripts/bdr-pgbouncer.sh

@@ -1,101 +0,0 @@
-#!/usr/bin/env bash
-set -u
-set -e
-
-# Process parameters passed to script
-# -----------------------------------
-#
-# This assumes the repmgr "event_notification_command" is defined like this:
-#
-#   event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&1'
-#
-# Adjust as appropriate.
-
-NODE_ID=$1
-EVENT_TYPE=$2
-SUCCESS=$3
-NEXT_CONNINFO=$4
-NEXT_NODE_NAME=$5
-
-if [ "$EVENT_TYPE" != "bdr_failover" ]; then
-    echo "unable to handle event type '$EVENT_TYPE'"
-    exit
-fi
-
-# Define database name here
-# -------------------------
-#
-# Note: this assumes the BDR-enabled database has the same name on
-# both hosts
-
-BDR_DBNAME=bdr_db
-
-# Define PgBouncer hosts here
-# ---------------------------
-
-PGBOUNCER_HOSTS="host1 host2"
-PGBOUNCER_PORTS=(6432 6432)
-PGBOUNCER_DATABASE_INI=(/path/to/pgbouncer.database.ini /path/to/pgbouncer.database.ini)
-
-
-# Define local host info here
-# ---------------------------
-
-THIS_HOST="host1"
-THIS_PGBOUNCER_PORT="6432"
-THIS_DB_PORT="5432"
-
-# Pause all pgbouncer nodes to minimize impact on clients
-# -------------------------------------------------------
-
-i=0
-for HOST in $PGBOUNCER_HOSTS
-do
-    PORT="${PGBOUNCER_PORTS[$i]}"
-
-    psql -tc "pause" -h $HOST -p $PORT -U postgres pgbouncer
-
-    i=$((i+1))
-done
-
-# Copy pgbouncer database ini file to all nodes and restart pgbouncer
-# -------------------------------------------------------------------
-
-i=0
-THIS_HOSTPORT="$THIS_HOST$THIS_PGBOUNCER_PORT"
-PGBOUNCER_DATABASE_INI_NEW="/tmp/pgbouncer.database.ini.new"
-
-for HOST in $PGBOUNCER_HOSTS
-do
-    PORT="${PGBOUNCER_PORTS[$i]}"
-
-    # Recreate the pgbouncer config file
-    # ----------------------------------
-    echo -e "[databases]\n" > $PGBOUNCER_DATABASE_INI_NEW
-
-    echo -e "$BDR_DBNAME= $NEXT_CONNINFO application_name=pgbouncer_$PORT" >> $PGBOUNCER_DATABASE_INI_NEW
-
-    # Copy file to host
-    # -----------------
-    CONFIG="${PGBOUNCER_DATABASE_INI[$i]}"
-
-    if [ "$HOST$PORT" != "$THIS_HOSTPORT" ]; then
-      rsync $PGBOUNCER_DATABASE_INI_NEW $HOST:$CONFIG
-    else
-      cp $PGBOUNCER_DATABASE_INI_NEW $CONFIG
-    fi
-
-    # Reload and resume PgBouncer
-    # ---------------------------
-
-    psql -tc "reload" -h $HOST -p $PORT -U postgres pgbouncer
-    psql -tc "resume" -h $HOST -p $PORT -U postgres pgbouncer
-
-    i=$((i+1))
-done
-
-
-# Clean up generated file
-rm $PGBOUNCER_DATABASE_INI_NEW
-
-echo "Reconfiguration of pgbouncer complete"

sql/repmgr_extension.sql

@@ -17,8 +17,6 @@ SELECT * FROM repmgr.replication_status;
 SELECT * FROM repmgr.show_nodes;
 
 -- functions
-SELECT repmgr.am_bdr_failover_handler(-1);
-SELECT repmgr.am_bdr_failover_handler(NULL);
 SELECT repmgr.get_new_primary();
 SELECT repmgr.notify_follow_primary(-1);
 SELECT repmgr.notify_follow_primary(NULL);
@@ -27,4 +25,3 @@ SELECT repmgr.set_local_node_id(-1);
 SELECT repmgr.set_local_node_id(NULL);
 SELECT repmgr.standby_get_last_updated();
 SELECT repmgr.standby_set_last_updated();
-SELECT repmgr.unset_bdr_failover_handler();

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

strutil.h

@@ -1,6 +1,6 @@
 /*
  * strutil.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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.h

@@ -1,6 +1,6 @@
 /*
  * sysutils.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  *
  * 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