Finalize release date

Drop old "repl_events" table.

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

@@ -1,6 +1,54 @@
-5.0.1   20??-??-??
-        repmgr: ensure an existing replication slot is not deleted if the
-          follow target is the node's current upstream (Ian)
+5.2.0   2020-10-22
+        general: add support for PostgreSQL 13 (Ian)
+        general: remove support for PostgreSQL 9.3 (Ian)
+        config: add support for file inclusion directives (Ian)
+        repmgr: "primary unregister --force" will unregister an active primary
+          with no registered standby nodes (Ian)
+        repmgr: add option --verify-backup to "standby clone" (Ian)
+        repmgr: "standby clone" honours --waldir option if set in
+          "pg_basebackup_options" (Ian)
+        repmgr: add option --db-connection to "node check" (Ian)
+        repmgr: report database connection error if the --optformat option was
+          provided to "node check" (Ian)
+        repmgr: improve "node rejoin" checks (Ian)
+        repmgr: enable "node rejoin" to join a target with a lower timeline (Ian)
+        repmgr: support pg_rewind's automatic crash recovery in Pg13 and later (Ian)
+        repmgr: improve output formatting for cluster matrix/crosscheck (Ian)
+        repmgr: improve database connection failure error checking on the
+          demotion candidate during "standby switchover" (Ian)
+        repmgr: make repmgr metadata tables dumpable (Ian)
+        repmgr: fix issue with tablespace mapping when cloning from Barman;
+          GitHub #650 (Ian)
+        repmgr: improve handling of pg_control read errors (Ian)
+        repmgrd: add additional optional parameters to "failover_validation command"
+          (spaskalev; GitHub #651)
+        repmgrd: ensure primary connection is reset if same as upstream;
+          GitHub #633 (Ian)
+
+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
+0          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)

Makefile.in

@@ -11,6 +11,8 @@ EXTENSION = repmgr
 
 DATA = \
   repmgr--unpackaged--4.0.sql \
+  repmgr--unpackaged--5.1.sql \
+  repmgr--unpackaged--5.2.sql \
   repmgr--4.0.sql \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \
@@ -21,7 +23,11 @@ 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 \
+  repmgr--5.1--5.2.sql \
+  repmgr--5.2.sql
 
 REGRESS = repmgr_extension
 
@@ -53,9 +59,12 @@ $(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 \
-	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
+	repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
+	configdata.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 configdata.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

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

configdata.c

@@ -0,0 +1,936 @@
+/*
+ * configdata.c - contains structs with parsed configuration data
+ *
+ * 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
+ * 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 "configfile.h"
+
+/*
+ * Parsed configuration settings are stored here
+ */
+t_configuration_options config_file_options;
+
+
+/*
+ * Configuration settings are defined here
+ */
+
+struct ConfigFileSetting config_file_settings[] =
+{
+
+	/* ================
+	 * node information
+	 * ================
+	 */
+	/* node_id */
+	{
+		"node_id",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.node_id },
+		{ .intdefault = UNKNOWN_NODE_ID },
+		{ .intminval = MIN_NODE_ID },
+		{},
+		{}
+	},
+	/* node_name */
+	{
+		"node_name",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.node_name },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.node_name) },
+		{}
+	},
+	/* conninfo */
+	{
+		"conninfo",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.conninfo },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.conninfo) },
+		{}
+	},
+	/* replication_user */
+	{
+		"replication_user",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.replication_user },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.replication_user) },
+		{}
+	},
+	/* data_directory */
+	{
+		"data_directory",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.data_directory },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.data_directory) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* config_directory */
+	{
+		"config_directory",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.config_directory },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.config_directory) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* pg_bindir */
+	{
+		"pg_bindir",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_bindir },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_bindir) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* repmgr_bindir */
+	{
+		"repmgr_bindir",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.repmgr_bindir },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.repmgr_bindir) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* replication_type */
+	{
+		"replication_type",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.replication_type },
+		{ .intdefault = REPLICATION_TYPE_PHYSICAL },
+		{ .intminval = -1 },
+		{},
+		{}
+	},
+
+	/* ================
+	 * logging settings
+	 * ================
+	 */
+
+	/*
+	 * log_level
+	 * NOTE: the default for "log_level" is set in log.c and does not need
+	 * to be initialised here
+	 */
+	{
+		"log_level",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.log_level },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.log_level) },
+		{}
+	},
+	/* log_facility */
+	{
+		"log_facility",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.log_facility },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.log_facility) },
+		{}
+	},
+	/* log_file */
+	{
+		"log_file",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.log_file },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.log_file) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* log_status_interval */
+	{
+		"log_status_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.log_status_interval },
+		{ .intdefault = DEFAULT_LOG_STATUS_INTERVAL, },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* ======================
+	 * standby clone settings
+	 * ======================
+	 */
+	/* use_replication_slots */
+	{
+		"use_replication_slots",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.use_replication_slots },
+		{ .booldefault = DEFAULT_USE_REPLICATION_SLOTS },
+		{},
+		{},
+		{}
+	},
+	/* pg_basebackup_options */
+	{
+		"pg_basebackup_options",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_basebackup_options },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_basebackup_options) },
+		{}
+	},
+	/* restore_command */
+	{
+		"restore_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.restore_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.restore_command) },
+		{}
+	},
+	/* tablespace_mapping */
+	{
+		"tablespace_mapping",
+		CONFIG_TABLESPACE_MAPPING,
+		{ .tablespacemappingptr = &config_file_options.tablespace_mapping },
+		{},
+		{},
+		{},
+		{}
+	},
+	/* recovery_min_apply_delay */
+	{
+		"recovery_min_apply_delay",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.recovery_min_apply_delay },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.recovery_min_apply_delay) },
+        {
+			.process_func = &parse_time_unit_parameter,
+			.providedptr = &config_file_options.recovery_min_apply_delay_provided
+		}
+	},
+
+	/* archive_cleanup_command */
+	{
+		"archive_cleanup_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.archive_cleanup_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.archive_cleanup_command) },
+		{}
+	},
+
+	/* use_primary_conninfo_password */
+	{
+		"use_primary_conninfo_password",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.use_primary_conninfo_password },
+		{ .booldefault = DEFAULT_USE_PRIMARY_CONNINFO_PASSWORD },
+		{},
+		{},
+		{}
+	},
+	/* passfile */
+	{
+		"passfile",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.passfile },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.passfile) },
+		{}
+	},
+
+	/* ======================
+	 * standby clone settings
+	 * ======================
+	 */
+	/* promote_check_timeout */
+	{
+		"promote_check_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.promote_check_timeout },
+		{ .intdefault = DEFAULT_PROMOTE_CHECK_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* promote_check_interval */
+	{
+		"promote_check_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.promote_check_interval },
+		{ .intdefault = DEFAULT_PROMOTE_CHECK_INTERVAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+
+	/* =======================
+	 * standby follow settings
+	 * =======================
+	 */
+	/* primary_follow_timeout */
+	{
+		"primary_follow_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.primary_follow_timeout },
+		{ .intdefault = DEFAULT_PRIMARY_FOLLOW_TIMEOUT, },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* standby_follow_timeout */
+	{
+		"standby_follow_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.standby_follow_timeout },
+		{ .intdefault = DEFAULT_STANDBY_FOLLOW_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* standby_follow_restart */
+	{
+		"standby_follow_restart",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.standby_follow_restart },
+		{ .booldefault = DEFAULT_STANDBY_FOLLOW_RESTART },
+		{},
+		{},
+		{}
+	},
+
+	/* ===========================
+	 * standby switchover settings
+	 * ===========================
+	 */
+	/* shutdown_check_timeout */
+	{
+		"shutdown_check_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.shutdown_check_timeout },
+		{ .intdefault = DEFAULT_SHUTDOWN_CHECK_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* standby_reconnect_timeout */
+	{
+		"standby_reconnect_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.standby_reconnect_timeout },
+		{ .intdefault = DEFAULT_STANDBY_RECONNECT_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* wal_receive_check_timeout */
+	{
+		"wal_receive_check_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.wal_receive_check_timeout },
+		{ .intdefault = DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+
+	/* ====================
+	 * node rejoin settings
+	 * ====================
+	 */
+	/* node_rejoin_timeout */
+	{
+		"node_rejoin_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.node_rejoin_timeout },
+		{ .intdefault = DEFAULT_NODE_REJOIN_TIMEOUT },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* ===================
+	 * node check settings
+	 * ===================
+	 */
+	/* archive_ready_warning */
+	{
+		"archive_ready_warning",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.archive_ready_warning },
+		{ .intdefault = DEFAULT_ARCHIVE_READY_WARNING },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* archive_ready_critical */
+	{
+		"archive_ready_critical",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.archive_ready_critical },
+		{ .intdefault = DEFAULT_ARCHIVE_READY_CRITICAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* replication_lag_warning */
+	{
+		"replication_lag_warning",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.replication_lag_warning },
+		{ .intdefault = DEFAULT_REPLICATION_LAG_WARNING },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* replication_lag_critical */
+	{
+		"replication_lag_critical",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.replication_lag_critical },
+		{ .intdefault = DEFAULT_REPLICATION_LAG_CRITICAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+
+	/* ================
+	 * witness settings
+	 * ================
+	 */
+	/* witness_sync_interval */
+	{
+		"witness_sync_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.witness_sync_interval },
+		{ .intdefault = DEFAULT_WITNESS_SYNC_INTERVAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+
+	/* ================
+	 * repmgrd settings
+	 * ================
+	 */
+	/* failover */
+	{
+		"failover",
+		CONFIG_FAILOVER_MODE,
+		{ .failovermodeptr = &config_file_options.failover },
+		{ .failovermodedefault = FAILOVER_MANUAL },
+		{},
+		{},
+		{}
+	},
+	/* location */
+	{
+		"location",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.location },
+		{ .strdefault = DEFAULT_LOCATION },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.location) },
+		{}
+	},
+	/* priority */
+	{
+		"priority",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.priority },
+		{ .intdefault = DEFAULT_PRIORITY, },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* promote_command */
+	{
+		"promote_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.promote_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.promote_command) },
+		{}
+	},
+	/* follow_command */
+	{
+		"follow_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.follow_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.follow_command) },
+		{}
+	},
+	/* monitor_interval_secs */
+	{
+		"monitor_interval_secs",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.monitor_interval_secs },
+		{ .intdefault = DEFAULT_MONITORING_INTERVAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* reconnect_attempts */
+	{
+		"reconnect_attempts",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.reconnect_attempts },
+		{ .intdefault = DEFAULT_RECONNECTION_ATTEMPTS },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* reconnect_interval */
+	{
+		"reconnect_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.reconnect_interval },
+		{ .intdefault = DEFAULT_RECONNECTION_INTERVAL },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+
+	/* monitoring_history */
+	{
+		"monitoring_history",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.monitoring_history },
+		{ .booldefault = DEFAULT_MONITORING_HISTORY },
+		{},
+		{},
+		{}
+	},
+	/* degraded_monitoring_timeout */
+	{
+		"degraded_monitoring_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.degraded_monitoring_timeout },
+		{ .intdefault = DEFAULT_DEGRADED_MONITORING_TIMEOUT },
+		{ .intminval = -1 },
+		{},
+		{}
+	},
+	/* async_query_timeout */
+	{
+		"async_query_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.async_query_timeout },
+		{ .intdefault = DEFAULT_ASYNC_QUERY_TIMEOUT },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* primary_notification_timeout */
+	{
+		"primary_notification_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.primary_notification_timeout },
+		{ .intdefault = DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* repmgrd_standby_startup_timeout */
+	{
+		"repmgrd_standby_startup_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.repmgrd_standby_startup_timeout },
+		{ .intdefault = DEFAULT_REPMGRD_STANDBY_STARTUP_TIMEOUT },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* repmgrd_pid_file */
+	{
+		"repmgrd_pid_file",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.repmgrd_pid_file },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.repmgrd_pid_file) },
+		{ .postprocess_func = &repmgr_canonicalize_path }
+	},
+	/* standby_disconnect_on_failover */
+	{
+		"standby_disconnect_on_failover",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.standby_disconnect_on_failover },
+		{ .booldefault = DEFAULT_STANDBY_DISCONNECT_ON_FAILOVER },
+		{},
+		{},
+		{}
+	},
+	/* sibling_nodes_disconnect_timeout */
+	{
+		"sibling_nodes_disconnect_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.sibling_nodes_disconnect_timeout },
+		{ .intdefault = DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* connection_check_type */
+	{
+		"connection_check_type",
+		CONFIG_CONNECTION_CHECK_TYPE,
+		{ .checktypeptr = &config_file_options.connection_check_type },
+		{ .checktypedefault = DEFAULT_CONNECTION_CHECK_TYPE },
+		{},
+		{},
+		{}
+	},
+	/* primary_visibility_consensus */
+	{
+		"primary_visibility_consensus",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.primary_visibility_consensus },
+		{ .booldefault = DEFAULT_PRIMARY_VISIBILITY_CONSENSUS },
+		{},
+		{},
+		{}
+	},
+	/* always_promote */
+	{
+		"always_promote",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.always_promote },
+		{ .booldefault = DEFAULT_ALWAYS_PROMOTE },
+		{},
+		{},
+		{}
+	},
+	/* failover_validation_command */
+	{
+		"failover_validation_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.failover_validation_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.failover_validation_command) },
+		{}
+	},
+	/* election_rerun_interval */
+	{
+		"election_rerun_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.election_rerun_interval },
+		{ .intdefault = DEFAULT_ELECTION_RERUN_INTERVAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* child_nodes_check_interval */
+	{
+		"child_nodes_check_interval",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.child_nodes_check_interval },
+		{ .intdefault = DEFAULT_CHILD_NODES_CHECK_INTERVAL },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* child_nodes_disconnect_min_count */
+	{
+		"child_nodes_disconnect_min_count",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.child_nodes_disconnect_min_count },
+		{ .intdefault = DEFAULT_CHILD_NODES_DISCONNECT_MIN_COUNT },
+		{ .intminval = -1 },
+		{},
+		{}
+	},
+	/* child_nodes_connected_min_count */
+	{
+		"child_nodes_connected_min_count",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.child_nodes_connected_min_count },
+		{ .intdefault = DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT},
+		{ .intminval = -1 },
+		{},
+		{}
+	},
+	/* child_nodes_connected_include_witness */
+	{
+		"child_nodes_connected_include_witness",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.child_nodes_connected_include_witness },
+		{ .booldefault = DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS },
+		{},
+		{},
+		{}
+	},
+	/* child_nodes_disconnect_timeout */
+	{
+		"child_nodes_disconnect_timeout",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.child_nodes_disconnect_timeout },
+		{ .intdefault = DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT },
+		{ .intminval = 0 },
+		{},
+		{}
+	},
+	/* child_nodes_disconnect_command */
+	{
+		"child_nodes_disconnect_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.child_nodes_disconnect_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.child_nodes_disconnect_command) },
+		{}
+	},
+	/* ================
+	 * service settings
+	 * ================
+	 */
+	/* pg_ctl_options */
+	{
+		"pg_ctl_options",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.pg_ctl_options },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.pg_ctl_options) },
+		{}
+	},
+	/* service_start_command */
+	{
+		"service_start_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.service_start_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.service_start_command) },
+		{}
+	},
+	/* service_stop_command */
+	{
+		"service_stop_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.service_stop_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.service_stop_command) },
+		{}
+	},
+	/* service_restart_command */
+	{
+		"service_restart_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.service_restart_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.service_restart_command) },
+		{}
+	},
+	/* service_reload_command */
+	{
+		"service_reload_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.service_reload_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.service_reload_command) },
+		{}
+	},
+	/* service_promote_command */
+	{
+		"service_promote_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.service_promote_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.service_promote_command) },
+		{}
+	},
+
+	/* ========================
+	 * repmgrd service settings
+	 * ========================
+	 */
+	/* repmgrd_service_start_command */
+	{
+		"repmgrd_service_start_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.repmgrd_service_start_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.repmgrd_service_start_command) },
+		{}
+	},
+	/* repmgrd_service_stop_command */
+	{
+		"repmgrd_service_stop_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.repmgrd_service_stop_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.repmgrd_service_stop_command) },
+		{}
+	},
+	/* ===========================
+	 * event notification settings
+	 * ===========================
+	 */
+	/* event_notification_command */
+	{
+		"event_notification_command",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.event_notification_command },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.event_notification_command) },
+		{}
+	},
+	{
+		"event_notifications",
+		CONFIG_EVENT_NOTIFICATION_LIST,
+		{ .notificationlistptr = &config_file_options.event_notifications },
+		{},
+		{},
+		{},
+		{}
+	},
+	/* ===============
+	 * barman settings
+	 * ===============
+	 */
+	/* barman_host */
+	{
+		"barman_host",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.barman_host },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.barman_host) },
+		{}
+	},
+	/* barman_server */
+	{
+		"barman_server",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.barman_server },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.barman_server) },
+		{}
+	},
+	/* barman_config */
+	{
+		"barman_config",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.barman_config },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.barman_config) },
+		{}
+	},
+	/* ==================
+	 * rsync/ssh settings
+	 * ==================
+	 */
+	/* rsync_options */
+	{
+		"rsync_options",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.rsync_options },
+		{ .strdefault = "" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.rsync_options) },
+		{}
+	},
+	/* ssh_options */
+	{
+		"ssh_options",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.ssh_options },
+		{ .strdefault = DEFAULT_SSH_OPTIONS },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.ssh_options) },
+		{}
+	},
+	/* ==================================
+	 * undocumented experimental settings
+	 * ==================================
+	 */
+	/* reconnect_loop_sync */
+	{
+		"reconnect_loop_sync",
+		CONFIG_BOOL,
+		{ .boolptr = &config_file_options.reconnect_loop_sync },
+		{ .booldefault = false },
+		{},
+		{},
+		{}
+	},
+	/* ==========================
+	 * undocumented test settings
+	 * ==========================
+	 */
+	/* promote_delay */
+	{
+		"promote_delay",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.promote_delay },
+		{ .intdefault = 0 },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	/* failover_delay */
+	{
+		"failover_delay",
+		CONFIG_INT,
+		{ .intptr = &config_file_options.failover_delay },
+		{ .intdefault = 0 },
+		{ .intminval = 1 },
+		{},
+		{}
+	},
+	{
+		"connection_check_query",
+		CONFIG_STRING,
+		{ .strptr = config_file_options.connection_check_query },
+		{ .strdefault = "SELECT 1" },
+		{},
+		{ .strmaxlen = sizeof(config_file_options.connection_check_query) },
+		{}
+	},
+	/* End-of-list marker */
+	{
+		NULL, CONFIG_INT, {}, {}, {}, {}, {}
+	}
+};
+

configfile-scan.l

@@ -5,6 +5,8 @@
 %{
 
 #include <setjmp.h>
+#include <sys/stat.h>
+#include <dirent.h>
 
 #include "repmgr.h"
 #include "configfile.h"
@@ -38,7 +40,13 @@ static sigjmp_buf *CONF_flex_fatal_jmp;
 static char *CONF_scanstr(const char *s);
 static int	CONF_flex_fatal(const char *msg);
 
-static bool ProcessConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, t_configuration_options *options, ItemList *error_list, ItemList *warning_list);
+static bool ProcessConfigFile(const char *base_dir, const char *config_file, const char *calling_file, bool strict, int depth, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
+
+static bool ProcessConfigFp(FILE *fp, const char *config_file, const char *calling_file, int depth, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
+
+static bool ProcessConfigDirectory(const char *base_dir, const char *includedir, const char *calling_file, int depth, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
+
+static char *AbsoluteConfigLocation(const char *base_dir, const char *location, const char *calling_file);
 
 %}
 
@@ -90,20 +98,91 @@ STRING			\'([^'\\\n]|\\.|\'\')*\'
 
 %%
 
-extern bool
-ProcessRepmgrConfigFile(FILE *fp, const char *config_file, t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
-{
-	return ProcessConfigFile(fp, config_file, NULL, options, error_list, warning_list);
-}
 
 extern bool
-ProcessPostgresConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList *error_list, ItemList *warning_list)
 {
-	return ProcessConfigFile(fp, config_file, contents, NULL, error_list, warning_list);
+	return ProcessConfigFile(base_dir, config_file, NULL, true, 0, NULL, error_list, warning_list);
+}
+
+
+extern bool
+ProcessPostgresConfigFile(const char *config_file, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+{
+	return ProcessConfigFile(base_dir, config_file, NULL, true, 0, contents, error_list, warning_list);
 }
 
 static bool
-ProcessConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
+ProcessConfigFile(const char *base_dir, const char *config_file, const char *calling_file, bool strict, int depth, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+{
+	char	   *abs_path;
+	bool		success = true;
+	FILE	   *fp;
+
+	/*
+	 * Reject file name that is all-blank (including empty), as that leads to
+	 * confusion --- we'd try to read the containing directory as a file.
+	 */
+	if (strspn(config_file, " \t\r\n") == strlen(config_file))
+	{
+		return false;
+	}
+
+	/*
+	 * Reject too-deep include nesting depth.  This is just a safety check to
+	 * avoid dumping core due to stack overflow if an include file loops back
+	 * to itself.  The maximum nesting depth is pretty arbitrary.
+	 */
+	if (depth > 10)
+	{
+		item_list_append_format(error_list,
+								_("could not open configuration file \"%s\": maximum nesting depth exceeded"),
+								config_file);
+		return false;
+	}
+
+	abs_path = AbsoluteConfigLocation(base_dir, config_file, calling_file);
+
+	/* Reject direct recursion */
+	if (calling_file && strcmp(abs_path, calling_file) == 0)
+	{
+		item_list_append_format(error_list,
+								_("configuration file recursion in \"%s\""),
+								calling_file);
+		pfree(abs_path);
+		return false;
+	}
+
+	fp = fopen(abs_path, "r");
+	if (!fp)
+	{
+		if (strict == false)
+		{
+			item_list_append_format(error_list,
+									"skipping configuration file \"%s\"",
+									abs_path);
+		}
+		else
+		{
+			item_list_append_format(error_list,
+									"could not open configuration file \"%s\": %s",
+									abs_path,
+									strerror(errno));
+			success = false;
+		}
+	}
+	else
+	{
+		success = ProcessConfigFp(fp, abs_path, calling_file, depth + 1, base_dir, contents, error_list, warning_list);
+	}
+
+	free(abs_path);
+
+	return success;
+}
+
+static bool
+ProcessConfigFp(FILE *fp, const char *config_file, const char *calling_file, int depth, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
 {
 	volatile bool OK = true;
 	volatile YY_BUFFER_STATE lex_buffer = NULL;
@@ -179,22 +258,62 @@ ProcessConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, t_c
 			ConfigFileLineno++;
 		}
 
-		/* OK, process the option name and value */
-		if (contents != NULL)
+		/* Handle include files */
+		if (base_dir != NULL && strcasecmp(opt_name, "include_dir") == 0)
 		{
-			key_value_list_replace_or_set(contents,
-										  opt_name,
-										  opt_value);
+			/*
+			 * An include_dir directive isn't a variable and should be
+			 * processed immediately.
+			 */
+			if (!ProcessConfigDirectory(base_dir, opt_value, config_file,
+										depth + 1, contents,
+									    error_list, warning_list))
+				OK = false;
+			yy_switch_to_buffer(lex_buffer);
+			pfree(opt_name);
+			pfree(opt_value);
+		}
+		else if (base_dir != NULL && strcasecmp(opt_name, "include_if_exists") == 0)
+		{
+			if (!ProcessConfigFile(base_dir, opt_value, config_file,
+								   false, depth + 1, contents,
+								   error_list, warning_list))
+				OK = false;
+
+			yy_switch_to_buffer(lex_buffer);
+			pfree(opt_name);
+			pfree(opt_value);
+		}
+		else if (base_dir != NULL && strcasecmp(opt_name, "include") == 0)
+		{
+			if (!ProcessConfigFile(base_dir, opt_value, config_file,
+								   true, depth + 1, contents,
+								   error_list, warning_list))
+				OK = false;
+
+			yy_switch_to_buffer(lex_buffer);
+			pfree(opt_name);
+			pfree(opt_value);
+		}
+		else
+		{
+			/* OK, process the option name and value */
+			if (contents != NULL)
+			{
+				key_value_list_replace_or_set(contents,
+											  opt_name,
+											  opt_value);
+			}
+			else
+			{
+				parse_configuration_item(error_list,
+										 warning_list,
+										 opt_name,
+										 opt_value);
+			}
+
 		}
 
-		if (options != NULL)
-		{
-			parse_configuration_item(options,
-									 error_list,
-									 warning_list,
-									 opt_name,
-									 opt_value);
-		}
 
 		/* break out of loop if read EOF, else loop for next line */
 		if (token == 0)
@@ -253,6 +372,132 @@ cleanup:
 	return OK;
 }
 
+/*
+ * Read and parse all config files in a subdirectory in alphabetical order
+ *
+ * includedir is the absolute or relative path to the subdirectory to scan.
+ *
+ * See ProcessConfigFp for further details.
+ */
+static bool
+ProcessConfigDirectory(const char *base_dir, const char *includedir, const char *calling_file, int depth, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+{
+	char	   *directory;
+	DIR		   *d;
+	struct dirent *de;
+	char	  **filenames;
+	int			num_filenames;
+	int			size_filenames;
+	bool		status;
+
+	/*
+	 * Reject directory name that is all-blank (including empty), as that
+	 * leads to confusion --- we'd read the containing directory, typically
+	 * resulting in recursive inclusion of the same file(s).
+	 */
+	if (strspn(includedir, " \t\r\n") == strlen(includedir))
+	{
+		item_list_append_format(error_list,
+								_("empty configuration directory name: \"%s\""),
+								includedir);
+
+		return false;
+	}
+
+	directory = AbsoluteConfigLocation(base_dir, includedir, calling_file);
+	d = opendir(directory);
+	if (d == NULL)
+	{
+		item_list_append_format(error_list,
+								_("could not open configuration directory \"%s\": %s"),
+								directory,
+								strerror(errno));
+		status = false;
+		goto cleanup;
+	}
+
+	/*
+	 * Read the directory and put the filenames in an array, so we can sort
+	 * them prior to processing the contents.
+	 */
+	size_filenames = 32;
+	filenames = (char **) palloc(size_filenames * sizeof(char *));
+	num_filenames = 0;
+
+	while ((de = readdir(d)) != NULL)
+	{
+		struct stat st;
+		char		filename[MAXPGPATH];
+
+		/*
+		 * Only parse files with names ending in ".conf".  Explicitly reject
+		 * files starting with ".".  This excludes things like "." and "..",
+		 * as well as typical hidden files, backup files, and editor debris.
+		 */
+		if (strlen(de->d_name) < 6)
+			continue;
+		if (de->d_name[0] == '.')
+			continue;
+		if (strcmp(de->d_name + strlen(de->d_name) - 5, ".conf") != 0)
+			continue;
+
+		join_path_components(filename, directory, de->d_name);
+		canonicalize_path(filename);
+		if (stat(filename, &st) == 0)
+		{
+			if (!S_ISDIR(st.st_mode))
+			{
+				/* Add file to array, increasing its size in blocks of 32 */
+				if (num_filenames >= size_filenames)
+				{
+					size_filenames += 32;
+					filenames = (char **) repalloc(filenames,
+											size_filenames * sizeof(char *));
+				}
+				filenames[num_filenames] = pstrdup(filename);
+				num_filenames++;
+			}
+		}
+		else
+		{
+			/*
+			 * stat does not care about permissions, so the most likely reason
+			 * a file can't be accessed now is if it was removed between the
+			 * directory listing and now.
+			 */
+			item_list_append_format(error_list,
+									_("could not stat file \"%s\": %s"),
+									filename, strerror(errno));
+			status = false;
+			goto cleanup;
+		}
+	}
+
+	if (num_filenames > 0)
+	{
+		int			i;
+
+		qsort(filenames, num_filenames, sizeof(char *), pg_qsort_strcmp);
+		for (i = 0; i < num_filenames; i++)
+		{
+			if (!ProcessConfigFile(base_dir, filenames[i], calling_file,
+								   true, depth, contents,
+								   error_list, warning_list))
+			{
+				status = false;
+				goto cleanup;
+			}
+		}
+	}
+	status = true;
+
+
+cleanup:
+	if (d)
+		closedir(d);
+	pfree(directory);
+	return status;
+}
 
 /*
  *		scanstr
@@ -348,6 +593,39 @@ CONF_scanstr(const char *s)
 	return newStr;
 }
 
+/*
+ * Given a configuration file or directory location that may be a relative
+ * path, return an absolute one.  We consider the location to be relative to
+ * the directory holding the calling file, or to DataDir if no calling file.
+ */
+static char *
+AbsoluteConfigLocation(const char *base_dir, const char *location, const char *calling_file)
+{
+	char		abs_path[MAXPGPATH];
+
+	if (is_absolute_path(location))
+		return strdup(location);
+
+    if (calling_file != NULL)
+	{
+		strlcpy(abs_path, calling_file, sizeof(abs_path));
+		get_parent_directory(abs_path);
+		join_path_components(abs_path, abs_path, location);
+		canonicalize_path(abs_path);
+	}
+	else if (base_dir != NULL)
+	{
+		join_path_components(abs_path, base_dir, location);
+		canonicalize_path(abs_path);
+	}
+	else
+	{
+		strlcpy(abs_path, location, sizeof(abs_path));
+	}
+
+	return strdup(abs_path);
+}
+
 
 /*
  * Flex fatal errors bring us here.  Stash the error message and jump back to

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
@@ -29,7 +29,7 @@
 #define TARGET_TIMELINE_LATEST 0
 
 /*
- * This is defined src/include/utils.h, however it's not practical
+ * This is defined in src/include/utils.h, however it's not practical
  * to include that from a frontend application.
  */
 #define PG_AUTOCONF_FILENAME "postgresql.auto.conf"
@@ -78,6 +78,55 @@ typedef struct TablespaceList
 } TablespaceList;
 
 
+typedef enum
+{
+	CONFIG_BOOL,
+	CONFIG_INT,
+	CONFIG_STRING,
+	CONFIG_FAILOVER_MODE,
+	CONFIG_CONNECTION_CHECK_TYPE,
+	CONFIG_EVENT_NOTIFICATION_LIST,
+	CONFIG_TABLESPACE_MAPPING
+} ConfigItemType;
+
+
+typedef struct ConfigFileSetting
+{
+	const char	   *name;
+	ConfigItemType  type;
+    union
+    {
+        int		   *intptr;
+        char	   *strptr;
+		bool	   *boolptr;
+		failover_mode_opt *failovermodeptr;
+		ConnectionCheckType *checktypeptr;
+		EventNotificationList *notificationlistptr;
+		TablespaceList *tablespacemappingptr;
+	} val;
+	union {
+		int			intdefault;
+		const char *strdefault;
+		bool		booldefault;
+		failover_mode_opt failovermodedefault;
+		ConnectionCheckType checktypedefault;
+	} defval;
+	union {
+		int				intminval;
+	} minval;
+	union {
+		int				strmaxlen;
+	} maxval;
+	struct {
+		void (*process_func)(const char *, const char *, char *, ItemList *errors);
+		void (*postprocess_func)(const char *, const char *, char *, ItemList *errors);
+		bool	   *providedptr;
+	} process;
+} ConfigFileSetting;
+
+/* Declare the main configfile structure for client applications */
+extern ConfigFileSetting config_file_settings[];
+
 typedef struct
 {
 	/* node information */
@@ -115,6 +164,7 @@ typedef struct
 	/* standby follow settings */
 	int			primary_follow_timeout;
 	int			standby_follow_timeout;
+	bool		standby_follow_restart;
 
 	/* standby switchover settings */
 	int			shutdown_check_timeout;
@@ -152,6 +202,7 @@ typedef struct
 	int			sibling_nodes_disconnect_timeout;
 	ConnectionCheckType connection_check_type;
 	bool		primary_visibility_consensus;
+	bool		always_promote;
 	char		failover_validation_command[MAXPGPATH];
 	int			election_rerun_interval;
 	int			child_nodes_check_interval;
@@ -161,10 +212,6 @@ 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];
@@ -191,79 +238,35 @@ typedef struct
 	char		rsync_options[MAXLEN];
 	char		ssh_options[MAXLEN];
 
-	/* undocumented test settings */
+	/*
+	 * undocumented settings
+	 *
+	 * These settings are for testing or experimential features
+	 * and may be changed without notice.
+	 */
+
+	/* experimental settings */
+	bool		reconnect_loop_sync;
+
+	/* test settings */
 	int			promote_delay;
+	int			failover_delay;
+	char		connection_check_query[MAXLEN];
 } t_configuration_options;
 
-/*
- * The following will initialize the structure with a minimal set of options;
- * actual defaults are set in parse_config() before parsing the configuration file
- */
-
-#define T_CONFIGURATION_OPTIONS_INITIALIZER { \
-		/* node information */ \
-		UNKNOWN_NODE_ID, "", "", "", "", "", "", "", REPLICATION_TYPE_PHYSICAL,	\
-		/* log settings */ \
-		"", "", "", DEFAULT_LOG_STATUS_INTERVAL, \
-		/* standby clone settings */ \
-		false, "", "", { NULL, NULL }, "", false, "", false, "", \
-		/* standby promote settings */ \
-		DEFAULT_PROMOTE_CHECK_TIMEOUT, DEFAULT_PROMOTE_CHECK_INTERVAL, \
-		/* standby follow settings */ \
-		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
-		DEFAULT_STANDBY_FOLLOW_TIMEOUT,	\
-		/* standby switchover settings */ \
-		DEFAULT_SHUTDOWN_CHECK_TIMEOUT, \
-		DEFAULT_STANDBY_RECONNECT_TIMEOUT, \
-		DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT, \
-		/* node rejoin settings */ \
-		DEFAULT_NODE_REJOIN_TIMEOUT, \
-		/* node check settings */ \
-		DEFAULT_ARCHIVE_READY_WARNING, DEFAULT_ARCHIVE_READY_CRITICAL, \
-		DEFAULT_REPLICATION_LAG_WARNING, DEFAULT_REPLICATION_LAG_CRITICAL, \
-		/* witness settings */ \
-		DEFAULT_WITNESS_SYNC_INTERVAL, \
-		/* repmgrd settings */ \
-		FAILOVER_MANUAL, DEFAULT_LOCATION, DEFAULT_PRIORITY, "", "", \
-		DEFAULT_MONITORING_INTERVAL, \
-		DEFAULT_RECONNECTION_ATTEMPTS, \
-        DEFAULT_RECONNECTION_INTERVAL, \
-        false, -1, \
-		DEFAULT_ASYNC_QUERY_TIMEOUT, \
-		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT, \
-		-1, "", false, DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT, \
-		CHECK_PING, true, "", DEFAULT_ELECTION_RERUN_INTERVAL, \
-		DEFAULT_CHILD_NODES_CHECK_INTERVAL, \
-		DEFAULT_CHILD_NODES_DISCONNECT_MIN_COUNT, \
-		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 */ \
-		"", "",  \
-		/* event notification settings */ \
-		"", "", { NULL, NULL }, \
-		/* barman settings */ \
-		"", "", "",	 \
-		/* rsync/ssh settings */ \
-		 "", "", \
-		/* undocumented test settings */ \
-		0 \
- }
-
 
+/* Declare the main configfile structure for client applications */
+extern t_configuration_options config_file_options;
 
 typedef struct
 {
 	char		slot[MAXLEN];
 	char		wal_method[MAXLEN];
+	char		waldir[MAXPGPATH];
 	bool		no_slot;		/* from PostgreSQL 10 */
 } t_basebackup_options;
 
-#define T_BASEBACKUP_OPTIONS_INITIALIZER { "", "", false }
+#define T_BASEBACKUP_OPTIONS_INITIALIZER { "", "", "", false }
 
 
 typedef enum
@@ -320,10 +323,11 @@ typedef struct
 void		set_progname(const char *argv0);
 const char *progname(void);
 
-void		load_config(const char *config_file, bool verbose, bool terse, t_configuration_options *options, char *argv0);
-bool		reload_config(t_configuration_options *orig_options, t_server_type server_type);
+void		load_config(const char *config_file, bool verbose, bool terse, char *argv0);
+bool		reload_config(t_server_type server_type);
+void		dump_config(void);
 
-void		parse_configuration_item(t_configuration_options *options, ItemList *error_list, ItemList *warning_list, const char *name, const char *value);
+void		parse_configuration_item(ItemList *error_list, ItemList *warning_list, const char *name, const char *value);
 
 bool		parse_recovery_conf(const char *data_dir, t_recovery_conf *conf);
 
@@ -336,6 +340,9 @@ int repmgr_atoi(const char *s,
 			ItemList *error_list,
 			int minval);
 
+void parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemList *errors);
+void repmgr_canonicalize_path(const char *name, const char *value, char *config_item, ItemList *errors);
+
 bool parse_pg_basebackup_options(const char *pg_basebackup_options,
 							t_basebackup_options *backup_options,
 							int server_version_num,
@@ -343,17 +350,20 @@ bool parse_pg_basebackup_options(const char *pg_basebackup_options,
 
 int parse_output_to_argv(const char *string, char ***argv_array);
 void free_parsed_argv(char ***argv_array);
-
+const char *format_failover_mode(failover_mode_opt failover);
 
 /* called by repmgr-client and repmgrd */
 void		exit_with_cli_errors(ItemList *error_list, const char *repmgr_command);
+
 void		print_item_list(ItemList *item_list);
 const char *print_connection_check_type(ConnectionCheckType type);
+char 	   *print_event_notification_list(EventNotificationList *list);
+char 	   *print_tablespace_mapping(TablespaceList *tablespacemappingptr);
 
 extern bool modify_auto_conf(const char *data_dir, KeyValueList *items);
 
-extern bool ProcessRepmgrConfigFile(FILE *fp, const char *config_file, t_configuration_options *options, ItemList *error_list, ItemList *warning_list);
+extern bool ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList *error_list, ItemList *warning_list);
 
-extern bool ProcessPostgresConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
+extern bool ProcessPostgresConfigFile(const char *config_file, const char *base_dir, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
 
 #endif							/* _REPMGR_CONFIGFILE_H_ */

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 5.0.0.
+# Generated by GNU Autoconf 2.69 for repmgr 5.2.0.
 #
 # 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='5.0.0'
-PACKAGE_STRING='repmgr 5.0.0'
+PACKAGE_VERSION='5.2.0'
+PACKAGE_STRING='repmgr 5.2.0'
 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 5.0.0 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.2.0 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 5.0.0:";;
+     short | recursive ) echo "Configuration of repmgr 5.2.0:";;
    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 5.0.0
+repmgr configure 5.2.0
 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 5.0.0, which was
+It was created by repmgr $as_me 5.2.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1824,7 +1824,7 @@ if test "$major_version_num" -lt '10'; then
     version_num_int=$(echo "$version_num"|
                     $SED -e 's/^\([0-9]*\)\.\([0-9]*\)$/\1\2/')
 
-    if test "$version_num_int" -lt '93'; then
+    if test "$version_num_int" -lt '94'; then
         as_fn_error $? "repmgr is not compatible with detected PostgreSQL version: $version_num" "$LINENO" 5
     fi
 else
@@ -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 5.0.0, which was
+This file was extended by repmgr $as_me 5.2.0, 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 5.0.0
+repmgr config.status 5.2.0
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [5.0.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.2.0], [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)
 
@@ -32,7 +32,7 @@ if test "$major_version_num" -lt '10'; then
     version_num_int=$(echo "$version_num"|
                     $SED -e 's/^\([[0-9]]*\)\.\([[0-9]]*\)$/\1\2/')
 
-    if test "$version_num_int" -lt '93'; then
+    if test "$version_num_int" -lt '94'; then
         AC_MSG_ERROR([repmgr is not compatible with detected PostgreSQL version: $version_num])
     fi
 else

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
@@ -90,7 +90,9 @@ get_system_identifier(const char *data_directory)
 	uint64		system_identifier = UNKNOWN_SYSTEM_IDENTIFIER;
 
 	control_file_info = get_controlfile(data_directory);
-	system_identifier = control_file_info->system_identifier;
+
+	if (control_file_info->control_file_processed == true)
+		system_identifier = control_file_info->system_identifier;
 
 	pfree(control_file_info);
 
@@ -98,19 +100,21 @@ get_system_identifier(const char *data_directory)
 }
 
 
-DBState
-get_db_state(const char *data_directory)
+bool
+get_db_state(const char *data_directory, DBState *state)
 {
 	ControlFileInfo *control_file_info = NULL;
-	DBState		state;
+	bool control_file_processed;
 
 	control_file_info = get_controlfile(data_directory);
+	control_file_processed = control_file_info->control_file_processed;
 
-	state = control_file_info->state;
+	if (control_file_processed == true)
+		*state = control_file_info->state;
 
 	pfree(control_file_info);
 
-	return state;
+	return control_file_processed;
 }
 
 
@@ -122,7 +126,8 @@ get_latest_checkpoint_location(const char *data_directory)
 
 	control_file_info = get_controlfile(data_directory);
 
-	checkPoint = control_file_info->checkPoint;
+	if (control_file_info->control_file_processed == true)
+		checkPoint = control_file_info->checkPoint;
 
 	pfree(control_file_info);
 
@@ -134,11 +139,12 @@ int
 get_data_checksum_version(const char *data_directory)
 {
 	ControlFileInfo *control_file_info = NULL;
-	int			data_checksum_version = -1;
+	int			data_checksum_version = UNKNOWN_DATA_CHECKSUM_VERSION;
 
 	control_file_info = get_controlfile(data_directory);
 
-	data_checksum_version = (int) control_file_info->data_checksum_version;
+	if (control_file_info->control_file_processed == true)
+		data_checksum_version = (int) control_file_info->data_checksum_version;
 
 	pfree(control_file_info);
 
@@ -277,8 +283,19 @@ get_controlfile(const char *DataDir)
 		return control_file_info;
 	}
 
-
-	if (version_num >= 90500)
+	if (version_num >= 120000)
+	{
+#if PG_ACTUAL_VERSION_NUM >= 120000
+		expected_size = sizeof(ControlFileData12);
+		ControlFileDataPtr = palloc0(expected_size);
+#endif
+	}
+	else if (version_num >= 110000)
+	{
+		expected_size = sizeof(ControlFileData11);
+		ControlFileDataPtr = palloc0(expected_size);
+	}
+	else if (version_num >= 90500)
 	{
 		expected_size = sizeof(ControlFileData95);
 		ControlFileDataPtr = palloc0(expected_size);
@@ -288,12 +305,6 @@ get_controlfile(const char *DataDir)
 		expected_size = sizeof(ControlFileData94);
 		ControlFileDataPtr = palloc0(expected_size);
 	}
-	else if (version_num >= 90300)
-	{
-		expected_size = sizeof(ControlFileData93);
-		ControlFileDataPtr = palloc0(expected_size);
-	}
-
 
 	if (read(fd, ControlFileDataPtr, expected_size) != expected_size)
 	{
@@ -359,17 +370,6 @@ get_controlfile(const char *DataDir)
 		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
 		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
 	}
-	else if (version_num >= 90300)
-	{
-		ControlFileData93 *ptr = (struct ControlFileData93 *)ControlFileDataPtr;
-		control_file_info->system_identifier = ptr->system_identifier;
-		control_file_info->state = ptr->state;
-		control_file_info->checkPoint = ptr->checkPoint;
-		control_file_info->data_checksum_version = ptr->data_checksum_version;
-		control_file_info->timeline = ptr->checkPointCopy.ThisTimeLineID;
-		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
-		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
-	}
 
 	pfree(ControlFileDataPtr);
 

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
@@ -31,9 +31,7 @@ typedef struct
 } ControlFileInfo;
 
 
-
-/* Same for 9.3, 9.4 */
-typedef struct CheckPoint93
+typedef struct CheckPoint94
 {
 	XLogRecPtr	redo;			/* next RecPtr available when we began to
 								 * create CheckPoint (i.e. REDO start point) */
@@ -53,7 +51,7 @@ typedef struct CheckPoint93
 	pg_time_t	time;			/* time stamp of checkpoint */
 
 	TransactionId oldestActiveXid;
-} CheckPoint93;
+} CheckPoint94;
 
 
 /* Same for 9.5, 9.6, 10, 11 */
@@ -128,65 +126,6 @@ typedef struct CheckPoint12
 } CheckPoint12;
 #endif
 
-typedef struct ControlFileData93
-{
-	uint64		system_identifier;
-
-	uint32		pg_control_version;		/* PG_CONTROL_VERSION */
-	uint32		catalog_version_no;		/* see catversion.h */
-
-	DBState		state;			/* see enum above */
-	pg_time_t	time;			/* time stamp of last pg_control update */
-	XLogRecPtr	checkPoint;		/* last check point record ptr */
-	XLogRecPtr	prevCheckPoint; /* previous check point record ptr */
-
-	CheckPoint93	checkPointCopy; /* copy of last check point record */
-
-	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
-
-	XLogRecPtr	minRecoveryPoint;
-	TimeLineID	minRecoveryPointTLI;
-	XLogRecPtr	backupStartPoint;
-	XLogRecPtr	backupEndPoint;
-	bool		backupEndRequired;
-
-	int			wal_level;
-	int			MaxConnections;
-	int			max_prepared_xacts;
-	int			max_locks_per_xact;
-
-	uint32		maxAlign;		/* alignment requirement for tuples */
-	double		floatFormat;	/* constant 1234567.0 */
-
-	uint32		blcksz;			/* data block size for this DB */
-	uint32		relseg_size;	/* blocks per segment of large relation */
-
-	uint32		xlog_blcksz;	/* block size within WAL files */
-	uint32		xlog_seg_size;	/* size of each WAL segment */
-
-	uint32		nameDataLen;	/* catalog name field width */
-	uint32		indexMaxKeys;	/* max number of columns in an index */
-
-	uint32		toast_max_chunk_size;	/* chunk size in TOAST tables */
-
-	/* flag indicating internal format of timestamp, interval, time */
-	bool		enableIntTimes; /* int64 storage enabled? */
-
-	/* flags indicating pass-by-value status of various types */
-	bool		float4ByVal;	/* float4 pass-by-value? */
-	bool		float8ByVal;	/* float8, int8, etc pass-by-value? */
-
-	/* Are data pages protected by checksums? Zero if no checksum version */
-	uint32		data_checksum_version;
-
-} ControlFileData93;
-
-
-/*
- * Following field added since 9.3:
- *
- * 	int			max_worker_processes;
- */
 
 typedef struct ControlFileData94
 {
@@ -200,7 +139,7 @@ typedef struct ControlFileData94
 	XLogRecPtr	checkPoint;		/* last check point record ptr */
 	XLogRecPtr	prevCheckPoint; /* previous check point record ptr */
 
-	CheckPoint93	checkPointCopy; /* copy of last check point record */
+	CheckPoint94	checkPointCopy; /* copy of last check point record */
 
 	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
 
@@ -438,7 +377,7 @@ typedef struct ControlFileData12
 #endif
 
 extern int get_pg_version(const char *data_directory, char *version_string);
-extern DBState get_db_state(const char *data_directory);
+extern bool get_db_state(const char *data_directory, DBState *state);
 extern const char *describe_db_state(DBState state);
 extern int	get_data_checksum_version(const char *data_directory);
 extern uint64 get_system_identifier(const char *data_directory);

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,
-	BDR
+	WITNESS
 } t_server_type;
 
 typedef enum
@@ -125,14 +119,21 @@ typedef enum
 
 typedef enum
 {
+	/* unable to query "pg_stat_replication" or other error */
 	NODE_ATTACHED_UNKNOWN = -1,
-	NODE_DETACHED,
-	NODE_ATTACHED
+	/* node has record in "pg_stat_replication" and state is not "streaming" */
+	NODE_ATTACHED,
+	/* node has record in "pg_stat_replication" but state is not "streaming" */
+	NODE_NOT_ATTACHED,
+	/* node has no record in "pg_stat_replication" */
+	NODE_DETACHED
 } NodeAttached;
 
 typedef enum
 {
 	SLOT_UNKNOWN = -1,
+	SLOT_NOT_FOUND,
+	SLOT_NOT_PHYSICAL,
 	SLOT_INACTIVE,
 	SLOT_ACTIVE
 } ReplSlotStatus;
@@ -170,6 +171,7 @@ 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 +326,6 @@ 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 +335,7 @@ typedef struct
 
 #define T_CONFIGFILE_INFO_INITIALIZER { "", "", false }
 
+
 typedef struct
 {
 	int			size;
@@ -381,6 +345,7 @@ typedef struct
 
 #define T_CONFIGFILE_LIST_INITIALIZER { 0, 0, NULL }
 
+
 typedef struct
 {
 	uint64		system_identifier;
@@ -420,10 +385,6 @@ 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 +393,19 @@ 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 */
@@ -451,6 +418,7 @@ void		conn_to_param_list(PGconn *conn, t_conninfo_param_list *param_list);
 void		param_set(t_conninfo_param_list *param_list, const char *param, const char *value);
 void		param_set_ine(t_conninfo_param_list *param_list, const char *param, const char *value);
 char	   *param_get(t_conninfo_param_list *param_list, const char *param);
+bool		validate_conninfo_string(const char *conninfo_str, char **errmsg);
 bool		parse_conninfo_string(const char *conninfo_str, t_conninfo_param_list *param_list, char **errmsg, bool ignore_local_params);
 char	   *param_list_to_string(t_conninfo_param_list *param_list);
 char	   *normalize_conninfo_string(const char *conninfo_str);
@@ -467,6 +435,7 @@ 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 +451,12 @@ 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_monitor_role(PGconn *conn, const char *subrole);
+bool		is_replication_role(PGconn *conn, char *rolname);
+bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
+
 /* repmgrd shared memory functions */
 bool		repmgrd_set_local_node_id(PGconn *conn, int local_node_id);
 int			repmgrd_get_local_node_id(PGconn *conn);
@@ -521,6 +496,7 @@ bool		get_local_node_record(PGconn *conn, int node_id, t_node_info *node_info);
 bool		get_primary_node_record(PGconn *conn, t_node_info *node_info);
 
 bool		get_all_node_records(PGconn *conn, NodeInfoList *node_list);
+bool		get_all_nodes_count(PGconn *conn, int *count);
 void		get_downstream_node_records(PGconn *conn, int node_id, NodeInfoList *nodes);
 void		get_active_sibling_node_records(PGconn *conn, int node_id, int upstream_node_id, NodeInfoList *node_list);
 bool		get_child_nodes(PGconn *conn, int node_id, NodeInfoList *node_list);
@@ -559,10 +535,14 @@ 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 */
@@ -614,35 +594,14 @@ 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);
+NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state);
 void		set_upstream_last_seen(PGconn *conn, int upstream_node_id);
 int			get_upstream_last_seen(PGconn *conn, t_server_type node_type);
 
 bool		is_wal_replay_paused(PGconn *conn, bool check_pending_wal);
 
-/* 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/Makefile

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

doc/appendix-faq.xml

@@ -22,6 +22,9 @@
           &repmgr; 5 is fundamentally the same code base as &repmgr; 4, but provides
           support for the revised replication configuration mechanism in PostgreSQL 12.
         </para>
+        <para>
+          Support for PostgreSQL 9.3 is no longer available from &repmgr; 5.2.
+        </para>
       </note>
       <para>
         &repmgr; 3.x builds on the improved replication facilities added
@@ -245,7 +248,7 @@
       <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.
@@ -347,6 +350,9 @@
         and earlier) with the absolute path to the WAL directory in <varname>pg_basebackup_options</varname>.
         For more details see <xref linkend="cloning-advanced-pg-basebackup-options"/>.
       </para>
+      <para>
+        In &repmgr; 5.2 and later, this setting will also be honoured when cloning from Barman.
+      </para>
     </sect2>
 
     <sect2 id="faq-repmgr-events-no-fkey" xreflabel="No foreign key on node_id in repmgr.events">
@@ -373,6 +379,22 @@
       </para>
     </sect2>
 
+    <sect2 id="faq-repmgr-exclude-metadata-from-dump" xreflabel="Excluding repmgr metadata from pg_dump output">
+      <title>How can I exclude &repmgr; metadata from <application>pg_dump</application> output?</title>
+      <para>
+        Beginning with &repmgr; 5.2, the metadata tables associated with the &repmgr; extension
+        (<literal>repmgr.nodes</literal>, <literal>repmgr.events</literal> and <literal>repmgr.monitoring_history</literal>)
+        have been marked as dumpable as they contain configuration and user-generated data.
+      </para>
+      <para>
+        To exclude these from <application>pg_dump</application> output, add the flag <option>--exclude-schema=repmgr</option>.
+      </para>
+      <para>
+        To exclude individual &repmgr; metadata tables from <application>pg_dump</application> output, add the flag
+        e.g. <option>--exclude-table=repmgr.monitoring_history</option>. This flag can be provided multiple times
+        to exclude individual tables,
+      </para>
+    </sect2>
 
   </sect1>
 

doc/appendix-release-notes.xml

@@ -16,24 +16,395 @@
   </para>
 
 <!-- remember to update the release date in ../repmgr_version.h.in -->
-  <sect1 id="release-5.0.1">
-    <title>Release 5.0.1</title>
-    <para><emphasis>???</emphasis></para>
+
+  <sect1 id="release-5.2.0">
+    <title id="release-current">Release 5.2.0</title>
+    <para><emphasis>Thu 22 October, 2020</emphasis></para>
+
     <para>
-      &repmgr; 5.0.1 is a minor release.
+      &repmgr; 5.2.0 is a major release.
     </para>
+    <para>
+      This release provides support for <ulink url="https://www.postgresql.org/docs/13/release-13.html">PostgreSQL 13</ulink>, released in September 2020.
+    </para>
+    <para>
+      This release removes support for PostgreSQL 9.3, which was
+      <ulink url="https://www.postgresql.org/docs/9.3/release-9-3-25.html">designated EOL in November 2018</ulink>.
+    </para>
+
+    <sect2>
+      <title>General improvements</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Configuration: support <command>include</command>, <command>include_dir</command> and
+              <command>include_if_exists</command> directives (see <xref linkend="configuration-file-include-directives"/>).
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>:
+              Improve sanity check failure log output from the demotion candidate.
+            </para>
+            <para>
+              If database connection configuration is not consistent across all nodes, it's
+              possible remote &repmgr; invocations (e.g. during switchover, from the promotion candidate
+              to the demotion candidate) will not be able to connect to the database. This will
+              now be explicitly reported as a database connection failure, rather than as a failure
+              of the respective sanity check.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              <link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link> /
+              <link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link>:
+              improve text mode output format, in particular so that node identifiers of arbitrary length are
+              displayed correctly.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-primary-unregister">repmgr primary unregister</link>:
+              the <option>--force</option> can be provided to unregister an active primary node, provided
+              it has no registered standby nodes.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>: new option
+              <option>--verify-backup</option> to run PostgreSQL's
+              <ulink url="https://www.postgresql.org/docs/13/app-pgverifybackup.html">pg_verifybackup</ulink>
+              utility after cloning a standby to verify the integrity of the copied data
+              (PostgreSQL 13 and later).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>:
+              when cloning from Barman, setting <option>--waldir</option>
+              (PostgreSQL 9.6 and earlier: <option>--xlogdir</option>) in
+              <option>pg_basebackup_options</option> will cause &repmgr; to create
+              a WAL directory outside of the main data directory and symlink
+              it from there, in the same way as would happen when cloning
+              using <application>pg_basebackup</application>.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-follow">repmgr standby follow</link>:
+              In PostgreSQL 13 and later, a standby no longer requires a restart to
+              follow a new upstream node.
+            </para>
+            <para>
+              The old behaviour (always restarting the standby to follow a new node)
+              can be restored by setting the configuration file parameter
+              <varname>standby_follow_restart</varname> to <literal>true</literal>.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-rejoin">repmgr node rejoin</link>:
+              enable a node to attach to a target node even the target node
+              has a lower timeline (PostgreSQL 9.6 and later).
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-rejoin">repmgr node rejoin</link>:
+              in PostgreSQL 13 and later, support <application>pg_rewind</application>'s
+              ability to automatically run crash recovery on a PostgreSQL instance
+              which was not shut down cleanly.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check">repmgr node check</link>:
+              option <option>--db-connection</option> added to check if &repmgr;
+              can connect to the database on the local node.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check">repmgr node check</link>:
+              report database connection error if the <option>--optformat</option> was provided.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              Improve handling of pg_control read errors.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              It is now possible to dump the contents of &repmgr; metadata tables with
+              <application>pg_dump</application>.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+    <sect2>
+      <title>repmgrd enhancements</title>
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              Following additional parameters can be provided to <varname>failover_validation_command</varname>:
+              <itemizedlist spacing="compact" mark="bullet">
+                <listitem>
+                  <simpara><literal>%n</literal>: node ID</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%a</literal>: node name</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%v</literal>: number of visible nodes</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%u</literal>: number of shared upstream nodes</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%t</literal>: total number of nodes</simpara>
+                </listitem>
+              </itemizedlist>
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Configuration option <varname>always_promote</varname> (default: <literal>false</literal>)
+              to control whether a node should be promoted if the &repmgr; metadata is not up-to-date
+              on that node.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
 
     <sect2>
       <title>Bug fixes</title>
       <para>
-        <itemizedlist>
-         <listitem>
+       <itemizedlist>
+          <listitem>
             <para>
-              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>:
-	          ensure an existing replication slot is not deleted if the
-              follow target is the node's current upstream.
+              <link linkend="repmgr-standby-clone">repmgr standby clone</link>:
+              fix issue with cloning from Barman where the tablespace mapping file was
+              not flushed to disk before attempting to retrieve files from Barman. GitHub #650.
             </para>
-	      </listitem>
+          </listitem>
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-rejoin">repmgr node rejoin</link>:
+              ensure that when verifying a standby node has attached to its upstream, the
+              node has started streaming before confirming the success of the rejoin operation.
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              &repmgrd;: ensure primary connection is reset if same as upstream. GitHub #633.
+            </para>
+          </listitem>
+       </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
+  <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>
@@ -41,9 +412,8 @@
 
   </sect1>
 
-
   <sect1 id="release-5.0">
-    <title id="release-current">Release 5.0</title>
+    <title>Release 5.0</title>
     <para><emphasis>Tue 15 October, 2019</emphasis></para>
 
     <para>

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

@@ -46,6 +46,7 @@
       <para>
        WAL management on the primary becomes much easier as there's no need
        to use replication slots, and <varname>wal_keep_segments</varname>
+       (PostgreSQL 13 and later: <varname>wal_keep_size</varname>)
        does not need to be set.
      </para>
     </listitem>
@@ -64,8 +65,9 @@
     </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
-      <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>.
+      the Barman server and configuring replication on the resulting cloned
+      standby using
+      <command><link linkend="repmgr-standby-clone">repmgr standby clone --replication-conf-only</link></command>.
     </para>
    </note>
 
@@ -146,6 +148,15 @@ description = "Main cluster"
       section in <command>man 5 ssh_config</command> for more details.
     </simpara>
    </tip>
+   <para>
+     If you wish to place WAL files in a location outside the main
+     PostgreSQL data directory, set <option>--waldir</option>
+     (PostgreSQL 9.6 and earlier: <option>--xlogdir</option>) in
+     <option>pg_basebackup_options</option> to the target directory
+     (must be an absolute filepath). &repmgr; will create and
+     symlink to this directory in exactly the same way
+     <application>pg_basebackup</application> would.
+   </para>
    <para>
     It's now possible to clone a standby from Barman, e.g.:
     <programlisting>
@@ -233,7 +244,8 @@ description = "Main cluster"
     that any standby connected to the primary using a replication slot will always
     be able to retrieve the required WAL files. This removes the need to manually
     manage WAL file retention by estimating the number of WAL files that need to
-    be maintained on the primary using <varname>wal_keep_segments</varname>.
+    be maintained on the primary using <varname>wal_keep_segments</varname>
+    (PostgreSQL 13 and later: <varname>wal_keep_size</varname>).
     Do however be aware that if a standby is disconnected, WAL will continue to
     accumulate on the primary until either the standby reconnects or the replication
     slot is dropped.
@@ -437,6 +449,13 @@ description = "Main cluster"
       WAL directory. Any WALs generated during the cloning process will be copied here, and
       a symlink will automatically be created from the main data directory.
     </para>
+    <tip>
+      <para>
+        The <literal>--waldir</literal> (<literal>--xlogdir</literal>) option,
+        if present in <varname>pg_basebackup_options</varname>, will be honoured by &repmgr;
+        when cloning from Barman (&repmgr; 5.2 and later).
+      </para>
+    </tip>
     <para>
      See the <ulink url="https://www.postgresql.org/docs/current/app-pgbasebackup.html">PostgreSQL pg_basebackup documentation</ulink>
      for more details of available options.

doc/configuration-file-optional-settings.xml

@@ -66,17 +66,8 @@
       </term>
       <listitem>
         <para>
-          Must be one of <literal>physical</literal> (for standard streaming replication)
-          or <literal>bdr</literal>.
+          Must be <literal>physical</literal> (the default).
         </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>
 

doc/configuration-file.xml

@@ -80,6 +80,51 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
       </para>
     </note>
 
+
+    <sect3 id="configuration-file-include-directives" xreflabel="configuration file include directives">
+
+      <title>Configuration file include directives</title>
+
+      <indexterm>
+        <primary>repmgr.conf</primary>
+        <secondary>include directives</secondary>
+      </indexterm>
+      <para>
+        From &repmgr; 5.2, the configuration file can contain the following include directives:
+        <itemizedlist spacing="compact" mark="bullet">
+          <listitem>
+            <simpara>
+              <option>include</option>: include the specified file,
+              either as an absolute path or path relative to the current file
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <option>include_if_exists</option>: include the specified file.
+              The file is specified as an absolute path or path relative to the current file.
+              However, if it does not exist, an error will not be raised.
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <option>include_dir</option>: include files in the specified directory
+              which have the <filename>.conf</filename> suffix.
+              The directory is specified either as an absolute path or path
+              relative to the current file
+            </simpara>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+      <para>
+        These behave in exactly the same way as the PostgreSQL configuration file processing;
+        see the <ulink url="https://www.postgresql.org/docs/current/config-setting.html#CONFIG-INCLUDES">PostgreSQL documentation</ulink>
+        for additional details.
+      </para>
+    </sect3>
+
   </sect2>
 
 
@@ -182,6 +227,14 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
    </itemizedlist>
   </para>
 
+  <para>
+    In examples provided in this documentation, it is assumed the configuration file is located
+    at <filename>/etc/repmgr.conf</filename>. If &repmgr; is installed from a package, the
+    configuration file will probably be located at another location specified by the packager;
+    see appendix <xref linkend="appendix-packages"/> for configuration file locations in
+    different packaging systems.
+  </para>
+
   <para>
    Note that if a file is explicitly specified with <literal>-f/--config-file</literal>,
    an error will be raised if it is not found or not readable, and no attempt will be made to
@@ -202,6 +255,61 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
       <filename>/path/to/repmgr.conf</filename>).
     </para>
    </note>
+  </sect2>
+
+  <sect2 id="configuration-file-postgresql-major-upgrades" xreflabel="configuration file and PostgreSQL major version upgrades">
+    <title>Configuration file and PostgreSQL major version upgrades</title>
+
+    <indexterm>
+      <primary>repmgr.conf</primary>
+      <secondary>ostgreSQL major version upgrades</secondary>
+    </indexterm>
+
+    <para>
+      When upgrading the PostgreSQL cluster to a new major version, <filename>repmgr.conf</filename>
+      will probably needed to be updated.
+    </para>
+    <para>
+      Usually <option>pg_bindir</option> and <option>data_directory</option> will need to be modified,
+      particularly if the default package locations are used, as these usually change.
+    </para>
+
+     <para>
+       It's also possible the location of <filename>repmgr.conf</filename> itself will change
+       (e.g. from <filename>/etc/repmgr/11/repmgr.conf</filename> to <filename>/etc/repmgr/12/repmgr.conf</filename>).
+       This is stored as part of the &repmgr; metadata and is used by &repmgr; to execute &repmgr; remotely
+       (e.g. during a <link linkend="performing-switchover">switchover operation</link>).
+     </para>
+     <para>
+       If the content and/or location of <filename>repmgr.conf</filename> has changed, the &repmgr; metadata
+       needs to be updated to reflect this. The &repmgr; metadata can be updated on each node with:
+       <itemizedlist spacing="compact" mark="bullet">
+         <listitem>
+           <simpara>
+             <link linkend="repmgr-primary-register">
+               <command>repmgr primary register --force -f /path/to/repmgr.conf</command>
+             </link>
+           </simpara>
+         </listitem>
+
+         <listitem>
+           <simpara>
+             <link linkend="repmgr-standby-register">
+               <command>repmgr standby register --force -f /path/to/repmgr.conf</command>
+             </link>
+           </simpara>
+         </listitem>
+
+
+         <listitem>
+           <simpara>
+             <link linkend="repmgr-witness-register">
+               <command>repmgr witness register --force -f /path/to/repmgr.conf -h primary_host</command>
+             </link>
+           </simpara>
+         </listitem>
+       </itemizedlist>
+     </para>
 
    </sect2>
  </sect1>

doc/configuration-password-management.xml

@@ -127,8 +127,31 @@ node2:5432:repmgr:repmgr:foo
 node2:5432:replication:repluser:foo
 node3:5432:repmgr:repmgr:foo
 node3:5432:replication:repluser:foo</programlisting>
-
+      If you are planning to use the <option>-S</option>/<option>--superuser</option> option,
+      there must also be an entry enabling the superuser to connect to the &repmgr; database.
+      Assuming the superuser is <literal>postgres</literal>, the file would look like this:
+        <programlisting>
+node1:5432:repmgr:repmgr:foo
+node1:5432:repmgr:postgres:foo
+node1:5432:replication:repluser:foo
+node2:5432:repmgr:repmgr:foo
+node2:5432:repmgr:postgres:foo
+node2:5432:replication:repluser:foo
+node3:5432:repmgr:repmgr:foo
+node3:5432:repmgr:postgres:foo
+node3:5432:replication:repluser:foo</programlisting>
     </para>
+
+    <para>
+      The <filename>~/.pgpass</filename> file can be simplified with the use of wildcards if
+      there is no requirement to restrict provision of passwords to particular hosts, ports
+      or databases. The preceding file could then be formatted like this:
+        <programlisting>
+*:*:*:repmgr:foo
+*:*:*:postgres:foo
+</programlisting>
+    </para>
+
     <note>
       <para>
         It's possible to specify an alternative location for the <filename>~/.pgpass</filename> file, either via
@@ -140,6 +163,11 @@ node3:5432:replication:repluser:foo</programlisting>
         location on all nodes, as when connecting to a remote node, the file referenced is the one on the
         local node.
       </para>
+      <para>
+        Additionally, you <emphasis>must</emphasis> specify the passfile location in <filename>repmgr.conf</filename>
+        with the <option>passfile</option> option so &repmgr; can write the correct path when creating the
+        <option>primary_conninfo</option> parameter for replication configuration on standbys.
+      </para>
     </note>
 
   </sect2>

doc/configuration.xml

@@ -270,7 +270,7 @@
 
       <varlistentry>
 
-        <term><option>wal_keep_segments</option></term>
+        <term><option>wal_keep_segments</option> / <option>wal_keep_size</option></term>
 
         <listitem>
 
@@ -279,25 +279,36 @@
             <secondary>PostgreSQL configuration</secondary>
           </indexterm>
 
+
+          <indexterm>
+            <primary>wal_keep_size</primary>
+            <secondary>PostgreSQL configuration</secondary>
+          </indexterm>
+
           <para>
-            Normally there is no need to set <option>wal_keep_segments</option> (default: <literal>0</literal>), as it
-            is <emphasis>not</emphasis> a reliable way of ensuring that all required WAL segments are available to standbys.
-            Replication slots and/or an archiving solution such as Barman are recommended to ensure standbys have a reliable
+            Normally there is no need to set <option>wal_keep_segments</option>
+            (PostgreSQL 13 and later: <varname>wal_keep_size</varname>; default: <literal>0</literal>),
+            as it is <emphasis>not</emphasis> a reliable way of ensuring that all required WAL
+            segments are available to standbys. Replication slots and/or an archiving solution
+            such as Barman are recommended to ensure standbys have a reliable
             source of WAL segments at all times.
           </para>
           <para>
-            The only reason ever to set  <option>wal_keep_segments</option> is you have
-            you have configured <option>pg_basebackup_options</option>
+            The only reason ever to set  <option>wal_keep_segments</option> / <option>wal_keep_size</option>
+            is you have you have configured <option>pg_basebackup_options</option>
             in <filename>repmgr.conf</filename> to include the setting <literal>--wal-method=fetch</literal>
             (PostgreSQL 9.6 and earlier: <literal>--xlog-method=fetch</literal>)
             <emphasis>and</emphasis> you have <emphasis>not</emphasis> set <option>restore_command</option>
             in <filename>repmgr.conf</filename> to fetch WAL files from a reliable source such as Barman,
             in which case you'll need to set <option>wal_keep_segments</option>
             to a sufficiently high number to ensure that all WAL files required by the standby
-            are retained. However we do not recommend managing replication in this way.
+            are retained. However we do not recommend WAL retention in this way.
           </para>
           <para>
             PostgreSQL documentation: <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-WAL-KEEP-SEGMENTS">wal_keep_segments</ulink>.
+            <!--
+             PostgreSQL documentation: <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-WAL-KEEP-SIZE">wal_keep_size</ulink>.
+              -->
           </para>
         </listitem>
       </varlistentry>

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>
 
@@ -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

@@ -35,7 +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-requirements.xml

@@ -14,7 +14,7 @@
   </para>
 
   <para>
-   &repmgr; &repmgrversion; is compatible with all PostgreSQL versions from 9.3. See
+   &repmgr; &repmgrversion; is compatible with all PostgreSQL versions from 9.4. See
    section <link linkend="install-compatibility-matrix">&repmgr; compatibility matrix</link>
    for an overview of version compatibility.
   </para>
@@ -115,7 +115,7 @@
 
           <row>
             <entry>
-              &repmgr; 5.x
+              &repmgr; 5.2
             </entry>
             <entry>
               YES
@@ -123,11 +123,42 @@
             <entry>
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
+            <entry>
+              9.4, 9.5, 9.6, 10, 11, 12, 13
+            </entry>
+          </row>
+
+          <row>
+            <entry>
+              &repmgr; 5.1
+            </entry>
+            <entry>
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-5.1.0">5.1.0</link> (2020-04-13)
+            </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11, 12
             </entry>
           </row>
 
+          <row>
+            <entry>
+              &repmgr; 5.0
+            </entry>
+            <entry>
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-5.0">5.0</link> (2019-10-15)
+            </entry>
+            <entry>
+              9.3, 9.4, 9.5, 9.6, 10, 11, 12
+            </entry>
+          </row>
+
+
           <row>
             <entry>
               &repmgr; 4.x
@@ -193,52 +224,49 @@
 
   <sect2 id="install-postgresql-93-94">
 
-    <title>PostgreSQL 9.3 and 9.4 support</title>
+    <title>PostgreSQL 9.4 support</title>
 
     <indexterm>
-      <primary>PostgreSQL 9.3</primary>
+      <primary>PostgreSQL 9.4</primary>
       <secondary>repmgr support</secondary>
     </indexterm>
 
     <para>
-      Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4:
+      Note that some &repmgr; functionality is not available in PostgreSQL 9.4:
     </para>
     <itemizedlist spacing="compact" mark="bullet">
 
       <listitem>
         <para>
-          PostgreSQL 9.3 does not support replication slots, so corresponding &repmgr; functionality
-          is not available.
-        </para>
-      </listitem>
-      <listitem>
-        <para>
-          In PostgreSQL 9.3 and PostgreSQL 9.4, <command>pg_rewind</command> is not part of the core
+          In PostgreSQL 9.4, <command>pg_rewind</command> is not part of the core
           distribution. <command>pg_rewind</command> will need to be compiled separately to be able
           to use any &repmgr; functionality which takes advantage of it.
         </para>
       </listitem>
     </itemizedlist>
 
-    <important>
+    <warning>
       <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>
+        Beginning with &repmgr; 5.2, &repmgr; no longer supports PostgreSQL 9.3.
+      </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
+        We recommend that users of these versions migrate to a supported 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>
+    </warning>
 
   </sect2>
 

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
-	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
-	 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
-	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
-	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
+     ID | Name  | Role    | Status               | Upstream | Location | Priority | Timeline | Connection string
+    ----+-------+---------+----------------------+----------+----------+----------+----------+----------------------------------------------------
+     1  | node1 | primary | ? unreachable        |          | default  | 100      |          | host=db_node1 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      | 1        | host=db_node3 dbname=repmgr user=repmgr
+     4  | node4 | standby | ? running            | ? node1  | default  | 100      |          | host=db_node4 dbname=repmgr user=repmgr
 
-	WARNING: following issues were detected
-	  - unable to connect to node "node1" (ID: 1)
-	  - 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
-	  - unable to connect to node "node4" (ID: 4)
+    WARNING: following issues were detected
+      - unable to connect to node "node1" (ID: 1)
+      - 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
+      - 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 +131,62 @@
   </para>
   </refsect1>
 
+  <refsect1>
+    <title>Additional checks</title>
+    <para>
+      Several checks are provided for diagnostic purposes and are not
+      included in the general output:
+      <itemizedlist spacing="compact" mark="bullet">
+
+        <listitem>
+          <simpara>
+            <option>--db-connection</option>: checks if &repmgr; can connect to the
+            database on the local node.
+          </simpara>
+          <simpara>
+            This option is particularly useful in combination with <command>SSH</command>, as
+            it can be used to troubleshoot connection issues encountered when &repmgr; is
+            executed remotely (e.g. during a switchover operation).
+          </simpara>
+
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <option>--replication-config-owner</option>: checks if the file containing replication
+            configuration (PostgreSQL 12 and later: <filename>postgresql.auto.conf</filename>;
+            PostgreSQL 11 and earlier: <filename>recovery.conf</filename>) is
+            owned by the same user who owns the data directory.
+          </simpara>
+          <simpara>
+            Incorrect ownership of these files (e.g. if they are owned by <literal>root</literal>)
+            will cause operations which need to update the replication configuration
+            (e.g. <link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>
+            or <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>)
+            to fail.
+          </simpara>
+        </listitem>
+
+      </itemizedlist>
+    </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 +194,14 @@
 
         <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 +209,15 @@
     </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-rejoin.xml

@@ -43,7 +43,12 @@
       <programlisting>
       repmgr node rejoin -d '$conninfo'</programlisting>
 
-      where <literal>$conninfo</literal> is the conninfo string of any reachable node in the cluster.
+      where <literal>$conninfo</literal> is the PostgreSQL <literal>conninfo</literal> string of the
+      <emphasis>current</emphasis> primary node (or that of any reachable node in the cluster, but
+      <emphasis>not</emphasis> the local node). This is so that &repmgr; can fetch up-to-date information
+      about the current state of the cluster.
+    </para>
+    <para>
       <filename>repmgr.conf</filename> for the stopped node *must* be supplied explicitly if not
       otherwise available.
     </para>
@@ -71,7 +76,7 @@
           </para>
           <para>
             It is only necessary to provide the <application>pg_rewind</application> path
-            if using PostgreSQL 9.3 or 9.4, and <application>pg_rewind</application>
+            if using PostgreSQL 9.4, and <application>pg_rewind</application>
             is not installed in the PostgreSQL <filename>bin</filename> directory.
           </para>
         </listitem>
@@ -207,9 +212,18 @@
       a standby to the current primary, not another standby.
     </para>
     <para>
-      The node must have been shut down cleanly; if this was not the case, it will
-      need to be manually started (remove any existing <filename>recovery.conf</filename> file first)
-      until it has reached a consistent recovery point, then shut down cleanly.
+      The node's PostgreSQL instance  must have been shut down cleanly. If this was not the
+      case, it will need to be started up until it has reached a consistent recovery point,
+      then shut down cleanly.
+    </para>
+    <para>
+      In PostgreSQL 13 and later, this will be done automatically
+      if the <option>--force-rewind</option> is provided (even if an actual rewind
+      is not necessary).
+    </para>
+    <para>
+      With PostgreSQL 12 and earlier, PostgreSQL will need to
+      be started and shut down manually; see below for the best way to do this.
     </para>
     <tip>
       <para>
@@ -221,11 +235,14 @@
           rm -f /var/lib/pgsql/data/recovery.conf
           postgres --single -D /var/lib/pgsql/data/ &lt; /dev/null</programlisting>
       </para>
+      <para>
+        Note that  <filename>standby.signal</filename> (PostgreSQL 11 and earlier:
+        <filename>recovery.conf</filename>) <emphasis>must</emphasis> be removed
+        from the data directory for PostgreSQL to be able to start in single
+        user mode.
+      </para>
     </tip>
-    <para>
-      &repmgr; will attempt to verify whether the node can rejoin as-is, or whether
-      <command>pg_rewind</command> must be used (see following section).
-    </para>
+
   </refsect1>
 
   <refsect1 id="repmgr-node-rejoin-pg-rewind" xreflabel="Using pg_rewind">
@@ -241,7 +258,7 @@
       <command>repmgr node rejoin</command> can optionally use <command>pg_rewind</command> to re-integrate a
       node which has diverged from the rest of the cluster, typically a failed primary.
       <command>pg_rewind</command> is available in PostgreSQL 9.5 and later as part of the core distribution,
-      and can be installed from external sources for PostgreSQL 9.3 and 9.4.
+      and can be installed from external sources for PostgreSQL 9.4.
     </para>
     <note>
       <para>
@@ -283,7 +300,15 @@
       to execute <command>pg_rewind</command> to ensure the node can be rejoined successfully.
     </para>
 
-    <important>
+    <refsect2 id="repmgr-node-rejoin-pg-rewind-config-files" xreflabel="pg_rewind and configuration files">
+
+      <title><command>pg_rewind</command> and configuration file retention</title>
+
+      <indexterm>
+        <primary>pg_rewind</primary>
+        <secondary>configuration file retention</secondary>
+      </indexterm>
+
       <para>
         Be aware that if <command>pg_rewind</command> is executed and actually performs a
         rewind operation, any configuration files in the PostgreSQL data directory will be
@@ -291,17 +316,27 @@
       </para>
       <para>
         To prevent this happening, provide a comma-separated list of files to retain
-        using the <literal>--config-file</literal> command line option; the specified files
+        using the <option>--config-file</option> command line option; the specified files
         will be archived in a temporary directory (whose parent directory can be specified with
-        <literal>--config-archive-dir</literal>) and restored once the rewind operation is
-        complete.
+        <option>--config-archive-dir</option>, default: <filename>/tmp</filename>)
+        and restored once the rewind operation is complete.
       </para>
-    </important>
+    </refsect2>
 
-    <para>
-      Example, first using <literal>--dry-run</literal>, then actually executing the
-      <literal>node rejoin command</literal>.
-    <programlisting>
+    <refsect2 id="repmgr-node-rejoin-pg-rewind-example" xreflabel="example using repmgr node rejoin and pg_rewind">
+
+      <title>Example using <command>repmgr node rejoin</command> and <command>pg_rewind</command></title>
+
+      <indexterm>
+        <primary>pg_rewind</primary>
+        <secondary>configuration file retention</secondary>
+      </indexterm>
+
+
+      <para>
+        Example, first using <option>--dry-run</option>, then actually executing the
+        <literal>node rejoin command</literal>.
+        <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind --dry-run
     INFO: replication connection to the rejoin target node was successful
@@ -317,17 +352,17 @@
       pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node3 dbname=repmgr user=repmgr'
     INFO: prerequisites for executing NODE REJOIN are met</programlisting>
 
-    <note>
-      <para>
-        If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
-        this checks the prerequisites for using <application>pg_rewind</application>, but is
-        not an absolute guarantee that actually executing <application>pg_rewind</application>
-        will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
-      </para>
+        <note>
+          <para>
+            If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
+            this checks the prerequisites for using <application>pg_rewind</application>, but is
+            not an absolute guarantee that actually executing <application>pg_rewind</application>
+            will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
+          </para>
 
-    </note>
+        </note>
 
-    <programlisting>
+        <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind
     NOTICE: pg_rewind execution required for this node to attach to rejoin target node 3
@@ -339,8 +374,8 @@
     NOTICE: starting server using "pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/pgsql/data' start"
     NOTICE: NODE REJOIN successful
     DETAIL: node 2 is now attached to node 3</programlisting>
-    </para>
-
+      </para>
+    </refsect2>
   </refsect1>
 
   <refsect1 id="repmgr-node-rejoin-caveats" xreflabel="Caveats">
@@ -369,6 +404,11 @@
      the current standby's PostgreSQL log will contain entries with the text
      &quot;<literal>record with incorrect prev-link</literal>&quot;.
    </para>
+   <para>
+     In PostgreSQL 9.5 and earlier, it is <emphasis>not</emphasis> possible to use
+     <application>pg_rewind</application> to attach to a target node with a lower
+     timeline than the local node.
+   </para>
    <para>
      We strongly recommend running <command>repmgr node rejoin</command> with the
      <option>--dry-run</option> option first. Additionally it might be a good idea
@@ -378,6 +418,51 @@
      is running in <option>--dry-run</option> mode.
    </para>
 
+   <warning>
+     <para>
+       In all current PostgreSQL versions (as of September 2020), <application>pg_rewind</application>
+       contains a corner-case bug which affects standbys in a very specific situation.
+     </para>
+     <para>
+       This situation occurs when a standby was shut down <emphasis>before</emphasis> its
+       primary node, and an attempt is made to attach this standby to another primary
+       in the same cluster (following a &quot;split brain&quot; situation where the standby
+       was connected to the wrong primary). In this case, &repmgr; will correctly determine
+       that <application>pg_rewind</application> should be executed, however
+       <application>pg_rewind</application> incorrectly decides that no action is necessary.
+     </para>
+     <para>
+       In this situation, &repmgr; will report something like:
+<programlisting>
+    NOTICE: pg_rewind execution required for this node to attach to rejoin target node 1
+    DETAIL: rejoin target server's timeline 3 forked off current database system timeline 2 before current recovery point 0/7019C10</programlisting>
+       but when executed, <application>pg_rewind</application> will report:
+<programlisting>
+    pg_rewind: servers diverged at WAL location 0/7015540 on timeline 2
+    pg_rewind: no rewind required</programlisting>
+       and if an attempt is made to attach the standby to the new primary, PostgreSQL logs on the standby
+       will contain errors like:
+<programlisting>
+    [2020-09-07 15:01:41 UTC]    LOG:  00000: replication terminated by primary server
+    [2020-09-07 15:01:41 UTC]    DETAIL:  End of WAL reached on timeline 2 at 0/7015540.
+    [2020-09-07 15:01:41 UTC]    LOG:  00000: new timeline 3 forked off current database system timeline 2 before current recovery point 0/7019C10</programlisting>
+     </para>
+     <para>
+       Currently it is not possible to resolve this situation using <application>pg_rewind</application>.
+       A <ulink url="https://www.postgresql.org/message-id/flat/CABvVfJU-LDWvoz4-Yow3Ay5LZYTuPD7eSjjE4kGyNZpXC6FrVQ@mail.gmail.com">patch</ulink>
+       has been submitted and will hopefully be included in a forthcoming PostgreSQL minor release.
+     </para>
+     <para>
+       As a workaround, start the primary server the standby was previously attached to,
+       and ensure the standby can be attached to it. If <application>pg_rewind</application> was actually executed,
+       it will have copied in the <filename>.history</filename> file from the target primary server; this must
+       be removed. <command>repmgr node rejoin</command> can then be used to attach the standby to the original
+       primary. Ensure any changes pending on the primary have propogated to the standby. Then shut down the primary
+       server <emphasis>first</emphasis>, before shutting down the standby. It should then be possible to
+       use <command>repmgr node rejoin</command> to attach the standby to the new primary.
+     </para>
+   </warning>
+
   </refsect1>
 
   <refsect1>

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-unregister.xml

@@ -60,6 +60,17 @@
         </listitem>
       </varlistentry>
 
+     <varlistentry>
+        <term><option>--force</option></term>
+        <listitem>
+          <para>
+            Forcibly unregister the node if it is registered as an active primary,
+            as long as it has no registered standbys; or if it is registered as
+            a primary but running as a standby.
+          </para>
+        </listitem>
+      </varlistentry>
+
     </variablelist>
 
   </refsect1>

doc/repmgr-standby-clone.xml

@@ -104,14 +104,6 @@
 
    <itemizedlist spacing="compact" mark="bullet">
 
-     <listitem>
-       <simpara><varname>standby_mode</varname> (always <literal>'on'</literal>)</simpara>
-     </listitem>
-
-     <listitem>
-       <simpara><varname>recovery_target_timeline</varname> (always <literal>'latest'</literal>)</simpara>
-     </listitem>
-
      <listitem>
        <simpara><varname>primary_conninfo</varname></simpara>
      </listitem>
@@ -122,6 +114,21 @@
 
    </itemizedlist>
 
+   <para>
+     For PostgreSQL 11 and earlier, these parameters will also be set:
+   </para>
+
+   <itemizedlist spacing="compact" mark="bullet">
+     <listitem>
+       <simpara><varname>standby_mode</varname> (always <literal>'on'</literal>)</simpara>
+     </listitem>
+
+     <listitem>
+       <simpara><varname>recovery_target_timeline</varname> (always <literal>'latest'</literal>)</simpara>
+     </listitem>
+   </itemizedlist>
+
+
    <para>
      The following additional parameters can be specified in <filename>repmgr.conf</filename>
      for inclusion in the replication configuration:
@@ -175,7 +182,10 @@
     <programlisting>
       pg_basebackup_options='--wal-method=fetch'</programlisting>
 
-    and ensure that <literal>wal_keep_segments</literal> is set to an appropriately high value.
+    and ensure that <literal>wal_keep_segments</literal> (PostgreSQL 13 and later:
+    <literal>wal_keep_size</literal>) is set to an appropriately high value. Note
+    however that this is not a particularly reliable way of ensuring sufficient
+    WAL is retained and is not recommended.
     See the <ulink url="https://www.postgresql.org/docs/current/app-pgbasebackup.html">
     pg_basebackup</ulink> documentation for details.
    </para>
@@ -188,18 +198,37 @@
    </note>
   </refsect1>
 
+  <refsect1 id="repmgr-standby-clone-wal-directory">
 
+   <title>Placing WAL files into a different directory</title>
+
+   <para>
+     To ensure that WAL files are placed in a directory outside of the main data
+     directory (e.g. to keep them on a separate disk for performance reasons),
+     specify the location with  <option>--waldir</option>
+     (PostgreSQL 9.6 and earlier: <option>--xlogdir</option>) in
+     the <filename>repmgr.conf</filename> parameter <option>pg_basebackup_options</option>,
+     e.g.:
+     <programlisting>
+pg_basebackup_options='--waldir=/path/to/wal-directory'</programlisting>
+     This setting will also be honored by &repmgr; when cloning from Barman
+     (&repmgr; 5.2 and later).
+   </para>
+
+  </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 +253,7 @@
      </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 +265,7 @@
      <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 +295,7 @@
             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 +341,7 @@
       </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.
@@ -370,6 +399,23 @@
           </para>
         </listitem>
       </varlistentry>
+
+      <varlistentry>
+        <term><option>--verify-backup</option></term>
+        <listitem>
+          <para>
+            <!-- update link after Pg13 release -->
+            Verify a cloned node using the
+            <ulink url="https://www.postgresql.org/docs/13/app-pgverifybackup.html">pg_verifybackup</ulink>
+            utility (PostgreSQL 13 and later).
+          </para>
+          <para>
+            This option can currently only be used when cloning directly from an upstream
+            node.
+          </para>
+        </listitem>
+      </varlistentry>
+
       <varlistentry>
         <term><option>--without-barman </option></term>
         <listitem>

doc/repmgr-standby-follow.xml

@@ -47,7 +47,15 @@
     </para>
 
     <para>
-      This command will force a restart of PostgreSQL on the standby node.
+      In PostgreSQL 12 and earlier, this command will force a restart of PostgreSQL on the standby node.
+    </para>
+
+    <para>
+      In PostgreSQL 13 and later, by default this command will signal PostgreSQL to reload its
+      configuration, which will cause PostgreSQL to follow the new upstream without
+      a restart. If this behaviour is not desired for whatever reason, the configuration
+      file parameter <varname>standby_follow_restart</varname> can be set <literal>true</literal>
+      to always force a restart.
     </para>
 
     <para>

doc/repmgr-standby-promote.xml

@@ -66,10 +66,10 @@
       Both values can be defined in <filename>repmgr.conf</filename>.
     </para>
 
-    <note>
+    <warning>
       <para>
-        If WAL replay is paused on the standby, and not all WAL files on the standby have been
-        replayed, &repmgr; will not attempt to promote it.
+        In PostgreSQL 12 and earlier, if WAL replay is paused on the standby, and not all
+        WAL files on the standby have been replayed, &repmgr; will not attempt to promote it.
       </para>
       <para>
         This is because if WAL replay is paused, PostgreSQL itself will not react to a promote command
@@ -81,7 +81,10 @@
         Note that if the standby is in archive recovery, &repmgr; will not be able to determine
         if more WAL is pending replay, and will abort the promotion attempt if WAL replay is paused.
       </para>
-    </note>
+      <para>
+        This restriction does <emphasis>not</emphasis> apply to PostgreSQL 13 and later.
+      </para>
+    </warning>
 
   </refsect1>
 
@@ -95,7 +98,6 @@
       NOTICE: promoting standby to primary
       DETAIL: promoting server "node2" (ID: 2) using "pg_ctl -l /var/log/postgres/startup.log -w -D '/var/lib/postgres/data' promote"
       server promoting
-      DEBUG: setting node 2 as primary and marking existing primary as failed
       NOTICE: STANDBY PROMOTE successful
       DETAIL: server "node2" (ID: 2) was successfully promoted to primary</programlisting>
     </para>
@@ -104,26 +106,35 @@
 
   <refsect1>
     <title>User permission requirements</title>
-    <para><emphasis>pg_promote() (PostgreSQL 12)</emphasis></para>
+    <para><emphasis>pg_promote() (PostgreSQL 12 and later)</emphasis></para>
     <para>
-      From PostgreSQL 12, &repmgr; uses the <command>pg_promote()</command> function to promote a standby
-      to primary.
+      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 <command>pg_promote()</command> is restricted to superusers.
-      If the <literal>repmgr</literal> use is not a superuser, execution permission for this
-      function must be granted with e.g.:
-      <programlisting>
+      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>
-      A future &repmgr; release will relax this restriction by falling back to
-      <command>pg_ctl promote</command>, as used for pre-PostgreSQL 12 versions.
+      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>
 
@@ -161,6 +172,42 @@
         </listitem>
       </varlistentry>
 
+      <varlistentry>
+        <term><option>-F</option></term>
+        <term><option>--force</option></term>
+        <listitem>
+          <para>
+            Ignore warnings and continue anyway.
+          </para>
+          <para>
+            This option is relevant in the following situations if <option>--siblings-follow</option> was specified:
+            <itemizedlist spacing="compact" mark="bullet">
+              <listitem>
+                <simpara>
+                  If one or more sibling nodes was not reachable via SSH, the standby will be promoted anyway.
+                </simpara>
+              </listitem>
+              <listitem>
+                <simpara>
+                  If the promotion candidate has insufficient free walsenders to accomodate the standbys which will
+                  be attached to it, the standby will be promoted anyway.
+                </simpara>
+              </listitem>
+              <listitem>
+                <simpara>
+                  If replication slots are in use but the promotion candidate has insufficient free replication slots
+                  to accomodate the standbys which will be attached to it, the standby will be promoted anyway.
+                </simpara>
+              </listitem>
+            </itemizedlist>
+          </para>
+          <para>
+            Note that if the <option>-F</option>/<option>--force</option> option is used when any of the above
+            situations is encountered, the onus is on the user to manually resolve any resulting issues.
+          </para>
+        </listitem>
+      </varlistentry>
+
     </variablelist>
   </refsect1>
 
@@ -198,6 +245,23 @@
 		 </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

@@ -67,28 +67,29 @@
     <para><emphasis>CHECKPOINT</emphasis></para>
     <para>
       &repmgr; executes <command>CHECKPOINT</command> on the demotion candidate as part of the shutdown
-      process.
+      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 checkpoint operation will
-      fail, though this is not a fatal error &repmgr; will continue the switchover process.
-    </para>
-    <para><emphasis>pg_promote() (PostgreSQL 12)</emphasis></para>
-    <para>
-      From PostgreSQL 12, &repmgr; uses the <command>pg_promote()</command> function to promote a standby
-      to primary.
+      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>
-      By default, execution of <command>pg_promote()</command> is restricted to superusers.
-      If the <literal>repmgr</literal> use is not a superuser, execution permission for this
-      function must be granted with e.g.:
-      <programlisting>
-    GRANT EXECUTE ON FUNCTION pg_catalog.pg_promote TO repmgr</programlisting>
+      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>
-      A future &repmgr; release will relax this restriction by falling back to
-      <command>pg_ctl promote</command>, as used for pre-PostgreSQL 12 versions.
+      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>
 
@@ -146,7 +147,7 @@
           <para>
             Use <application>pg_rewind</application> to reintegrate the old primary if necessary
             (and the prerequisites for using <application>pg_rewind</application> are met).
-            If using PostgreSQL 9.3 or 9.4, and the <application>pg_rewind</application>
+            If using PostgreSQL 9.4, and the <application>pg_rewind</application>
             binary is not installed in the PostgreSQL <filename>bin</filename> directory,
             provide its full path. For more details see also <xref linkend="switchover-pg-rewind"/>.
           </para>
@@ -215,6 +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-witness-register.xml

@@ -63,6 +63,34 @@
   </refsect1>
 
 
+
+  <refsect1>
+
+    <title>Options</title>
+   <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually register the witness
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+       <term><option>-F</option>/<option>--force</option></term>
+        <listitem>
+          <para>
+            Overwrite an existing node record
+          </para>
+        </listitem>
+      </varlistentry>
+
+   </variablelist>
+  </refsect1>
+
   <refsect1 id="repmgr-witness-register-events">
     <title>Event notifications</title>
     <para>

doc/repmgr.xml

@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.3 - PostgreSQL 12.
+   use with PostgreSQL 9.4 - PostgreSQL 13.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -91,7 +91,6 @@
   &repmgrd-automatic-failover;
   &repmgrd-configuration;
   &repmgrd-operation;
-  &repmgrd-bdr;
  </part>
 
  <part id="repmgr-command-reference">

doc/repmgrd-automatic-failover.xml

@@ -331,11 +331,12 @@
     To use this, <option>failover_validation_command</option> in <filename>repmgr.conf</filename>
     to a script executable by the <literal>postgres</literal> system user, e.g.:
     <programlisting>
-      failover_validation_command=/path/to/script.sh %n %a</programlisting>
+      failover_validation_command=/path/to/script.sh %n</programlisting>
   </para>
   <para>
-    The <literal>%n</literal> parameter will be replaced with the node ID, and the
-    <literal>%a</literal> parameter will be replaced by the node name when the script is executed.
+    The <literal>%n</literal> parameter will be replaced with the node ID when the script is
+    executed. A number of other parameters are also available, see section
+    &quot;<xref linkend="repmgrd-automatic-failover-configuration-optional"/>&quot; for details.
   </para>
   <para>
     This script must return an exit code of <literal>0</literal> to indicate the node should promote itself.

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

@@ -325,7 +325,7 @@
 
     </sect2>
 
-    <sect2 id="repmgrd-automatic-failover-configuration-optional">
+    <sect2 id="repmgrd-automatic-failover-configuration-optional" xreflabel="Optional configuration for automatic failover">
       <title>Optional configuration for automatic failover</title>
 
       <para>
@@ -370,8 +370,8 @@
               </para>
             </note>
             <para>
-              One or both of the following parameter placeholders
-			  should be provided, which will be replaced by repmgrd with the appropriate
+              One or more of the following parameter placeholders
+			  may be provided, which will be replaced by repmgrd with the appropriate
 	          value:
               <itemizedlist spacing="compact" mark="bullet">
                 <listitem>
@@ -380,6 +380,15 @@
                 <listitem>
                   <simpara><literal>%a</literal>: node name</simpara>
                 </listitem>
+                <listitem>
+                  <simpara><literal>%v</literal>: number of visible nodes</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%u</literal>: number of shared upstream nodes</simpara>
+                </listitem>
+                <listitem>
+                  <simpara><literal>%t</literal>: total number of nodes</simpara>
+                </listitem>
               </itemizedlist>
             </para>
             <para>
@@ -410,6 +419,33 @@
           </listitem>
         </varlistentry>
 
+        <varlistentry>
+          <term><option>always_promote</option></term>
+
+          <listitem>
+            <indexterm>
+              <primary>always_promote</primary>
+            </indexterm>
+
+            <para>
+              Default: <literal>false</literal>.
+            </para>
+            <para>
+              If <literal>true</literal>, promote the local node even if its
+              &repmgr; metadata is not up-to-date.
+            </para>
+            <para>
+              Normally &repmgr; expects its metadata (stored in the <varname>repmgr.nodes</varname>
+              table) to be up-to-date so &repmgrd; can take the correct action during a failover.
+              However it's possible that updates made on the primary may not
+              have propagated to the standby (promotion candidate). In this case &repmgrd; will
+              default to not promoting the standby. This behaviour can be overridden by setting
+              <option>always_promote</option> to <literal>true</literal>.
+            </para>
+          </listitem>
+        </varlistentry>
+
+
         <varlistentry>
 
           <term><option>standby_disconnect_on_failover</option></term>
@@ -624,18 +660,6 @@ 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>
@@ -768,6 +792,12 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
           </simpara>
         </listitem>
 
+        <listitem>
+          <simpara>
+            <varname>always_promote</varname>
+          </simpara>
+        </listitem>
+
         <listitem>
           <simpara>
             <varname>promote_command</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
 

doc/repmgrd-operation.xml

@@ -137,7 +137,7 @@ NOTICE: node 3 (node3) paused</programlisting>
       If the primary becomes available again (e.g. following a software upgrade), &repmgrd;
       will automatically reconnect, e.g.:
       <programlisting>
-[2019-08-28 12:25:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
+[2019-08-28 12:25:41] [NOTICE] reconnected to upstream node "node1" (ID: 1) after 8 seconds, resuming monitoring</programlisting>
     </para>
 
     <para>
@@ -295,7 +295,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
     [2017-08-29 10:59:37] [HINT] use "repmgr standby promote" to manually promote this node
     [2017-08-29 10:59:37] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
     [2017-08-29 10:59:53] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state (automatic failover disabled)
-    [2017-08-29 11:00:45] [NOTICE] reconnected to upstream node 1 after 68 seconds, resuming monitoring
+    [2017-08-29 11:00:45] [NOTICE] reconnected to upstream node "node1" (ID: 1) after 68 seconds, resuming monitoring
     [2017-08-29 11:00:57] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in normal state (automatic failover disabled)</programlisting>
 
  </para>

doc/switchover.xml

@@ -244,16 +244,15 @@
     </para>
     <para>
       <application>pg_rewind</application> has been part of the core PostgreSQL distribution since
-      version 9.5. Users of versions 9.3 and 9.4 will need to manually install it; the source code is available here:
+      version 9.5. Users of PostgreSQL 9.4 will need to manually install it; the source code is available here:
       <ulink url="https://github.com/vmware/pg_rewind">https://github.com/vmware/pg_rewind</ulink>.
       If the <application>pg_rewind</application>
       binary is not installed in the PostgreSQL <filename>bin</filename> directory, provide
       its full path  on the demotion candidate  with <option>--force-rewind</option>.
     </para>
     <para>
-      Note that building the 9.3/9.4 version of <application>pg_rewind</application> requires the PostgreSQL
-      source code. Also, PostgreSQL 9.3 does not provide <varname>wal_log_hints</varname>,
-      meaning data checksums must have been enabled when the database was initialized.
+      Note that building the 9.4 version of <application>pg_rewind</application> requires the PostgreSQL
+      source code.
     </para>
   </sect2>
 
@@ -343,7 +342,7 @@
    <itemizedlist spacing="compact" mark="bullet">
     <listitem>
      <simpara>
-      If using PostgreSQL 9.3 or 9.4, you should ensure that the shutdown command
+      If using PostgreSQL 9.4, you should ensure that the shutdown command
       is configured to use PostgreSQL's <varname>fast</varname> shutdown mode (the default in 9.5
       and later). If relying on <command>pg_ctl</command> to perform database server operations,
       you should include <literal>-m fast</literal> in <varname>pg_ctl_options</varname>

doc/upgrading-repmgr.xml

@@ -201,9 +201,13 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 	</para>
 	<tip>
 	  <para>
-		If the &repmgr; upgrade requires a PostgreSQL restart, combine the &repmgr; upgrade
-		with a PostgreSQL minor version upgrade, which will require a restart in any case.
-		New PostgreSQL minor version are usually released every couple of months.
+        If the &repmgr; upgrade requires a PostgreSQL restart, combine the &repmgr; upgrade
+        with a PostgreSQL minor version upgrade, which will require a restart in any case.
+      </para>
+      <para>
+		New PostgreSQL minor versions are usually released every couple of months;
+        see the <ulink url="https://www.postgresql.org/developer/roadmap/">Roadmap</ulink>
+        for the current schedule.
 	  </para>
 	</tip>
   </sect2>
@@ -269,6 +273,29 @@ 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>
 
 
@@ -285,12 +312,12 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
    <orderedlist>
     <listitem>
      <simpara>
-       converting the repmgr.conf configuration files
+       converting the <filename>repmgr.conf</filename> configuration files
      </simpara>
     </listitem>
     <listitem>
      <simpara>
-       upgrading the repmgr schema using <command>CREATE EXTENSION</command>
+       upgrading the repmgr schema using <command>CREATE EXTENSION</command> (PostgreSQL 12 and earlier)
      </simpara>
     </listitem>
    </orderedlist>
@@ -434,22 +461,31 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     <para>
       Please note that the the conversion script will add an empty
       placeholder parameter for <varname>data_directory</varname>, which
-      is a required parameter from &repmgr; 4.
+      is a required parameter from &repmgr; 4. This must be manually modified to contain
+      the correct data directory.
     </para>
    </sect3>
   </sect2>
   <sect2>
-   <title>Upgrading the repmgr schema</title>
+   <title>Upgrading the repmgr schema (PostgreSQL 12 and earlier)</title>
    <para>
     Ensure &repmgrd; is not running, or any cron jobs which execute the
     <command>repmgr</command> binary.
    </para>
    <para>
-    Install <literal>repmgr 4</literal> packages; any <literal>repmgr 3.x</literal> packages
+    Install the latest &repmgr; package; any <literal>repmgr 3.x</literal> packages
     should be uninstalled (if not automatically uninstalled already by your packaging system).
    </para>
    <sect3>
     <title>Upgrading from repmgr 3.1.1 or earlier</title>
+    <tip>
+     <simpara>
+      If you don't care about any data from the existing &repmgr; installation,
+      (e.g. the contents of the <structname>events</structname> and <structname>monitoring</structname>
+      tables), the follwing steps can be skipped; proceed to <xref linkend="upgrade-reregister-nodes"/>.
+     </simpara>
+    </tip>
+
     <para>
      If your repmgr version is 3.1.1 or earlier, you will need to update
      the schema to the latest version in the 3.x series (3.3.2) before
@@ -478,19 +514,37 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     <para>
      In the database used by the existing &repmgr; installation, execute:
      <programlisting>
-      CREATE EXTENSION repmgr FROM unpackaged;</programlisting>
+      CREATE EXTENSION repmgr FROM unpackaged</programlisting>
     </para>
+
     <para>
      This will move and convert all objects from the existing schema
      into the new, standard <literal>repmgr</literal> schema.
     </para>
     <note>
-      <simpara>there must be only one schema matching <literal>repmgr_%</literal> in the
+      <simpara>There must be only one schema matching <literal>repmgr_%</literal> in the
         database, otherwise this step may not work.
       </simpara>
     </note>
    </sect3>
-   <sect3>
+  </sect2>
+
+  <sect2>
+   <title>Upgrading the repmgr schema (PostgreSQL 13 and later)</title>
+   <para>
+     Beginning with PostgreSQL 13, the <command>CREATE EXTENSION ... FROM unpackaged</command>
+     syntax is no longer available. In the unlikely event you have ended up with an
+     installation running PostgreSQL 13 or later and containing the legacy &repmgr;
+     schema, there is no convenient way of upgrading this; instead you'll just need
+     to re-register the nodes as detailed in <link linkend="upgrade-reregister-nodes">the following section</link>,
+     which will create the &repmgr; extension automatically.
+   </para>
+   <para>
+     Any historical data you wish to retain (e.g. the contents of the <structname>events</structname>
+     and <structname>monitoring</structname> tables) will need to be exported manually.
+   </para>
+  </sect2>
+  <sect2 id="upgrade-reregister-nodes">
     <title>Re-register each node</title>
     <para>
      This is necessary to update the <literal>repmgr</literal> metadata with some additional items.
@@ -500,6 +554,10 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
      <programlisting>
       repmgr primary register -f /etc/repmgr.conf --force</programlisting>
     </para>
+    <para>
+      If not already present (e.g. after executing <command>CREATE EXTENSION repmgr FROM unpackaged</command>),
+      the &repmgr; extension will be automatically created by <command>repmgr primary register</command>.
+    </para>
     <para>
      On each standby node, execute e.g.
      <programlisting>
@@ -512,18 +570,20 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     <para>
      The original <literal>repmgr_$cluster</literal> schema can be dropped at any time.
     </para>
-    <tip>
-     <simpara>
-      If you don't care about any data from the existing &repmgr; installation,
-      (e.g. the contents of the <structname>events</structname> and <structname>monitoring</structname>
-      tables), the manual <command>CREATE EXTENSION</command> step can be skipped; just re-register
-      each node, starting with the primary node, and the <literal>repmgr</literal> extension will be
-      automatically created.
-     </simpara>
-    </tip>
-   </sect3>
+
   </sect2>
 
+  <sect2 id="upgrade-drop-repmgr-cluster-schema">
+    <title>Drop the legacy repmgr schema</title>
+    <para>
+      Once the cluster has been registered with the current &repmgr; version, the legacy
+      <literal>repmgr_$cluster</literal> schema can be dropped at any time with:
+<programlisting>
+    DROP SCHEMA repmgr_$cluster CASCADE</programlisting>
+      (substitute <literal>$cluster</literal> with the value of the <varname>clustername</varname>
+      variable used in &repmgr; 3.x).
+    </para>
+  </sect2>
  </sect1>
 
 </chapter>

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--5.2.sql

@@ -0,0 +1,7 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.nodes', '');
+SELECT pg_catalog.pg_extension_config_dump('repmgr.events', '');
+SELECT pg_catalog.pg_extension_config_dump('repmgr.monitoring_history', '');
+

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--5.2.sql

@@ -0,0 +1,192 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+CREATE TABLE repmgr.nodes (
+  node_id          INTEGER     PRIMARY KEY,
+  upstream_node_id INTEGER     NULL REFERENCES nodes (node_id) DEFERRABLE,
+  active           BOOLEAN     NOT NULL DEFAULT TRUE,
+  node_name        TEXT        NOT NULL,
+  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
+  location         TEXT        NOT NULL DEFAULT 'default',
+  priority         INT         NOT NULL DEFAULT 100,
+  conninfo         TEXT        NOT NULL,
+  repluser         VARCHAR(63) NOT NULL,
+  slot_name        TEXT        NULL,
+  config_file      TEXT        NOT NULL
+);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.nodes', '');
+
+CREATE TABLE repmgr.events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.events', '');
+
+CREATE TABLE repmgr.monitoring_history (
+  primary_node_id                INTEGER NOT NULL,
+  standby_node_id                INTEGER NOT NULL,
+  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
+  last_apply_time                TIMESTAMP WITH TIME ZONE,
+  last_wal_primary_location      PG_LSN NOT NULL,
+  last_wal_standby_location      PG_LSN,
+  replication_lag                BIGINT NOT NULL,
+  apply_lag                      BIGINT NOT NULL
+);
+
+CREATE INDEX idx_monitoring_history_time
+          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
+
+SELECT pg_catalog.pg_extension_config_dump('repmgr.monitoring_history', '');
+
+CREATE VIEW repmgr.show_nodes AS
+   SELECT n.node_id,
+          n.node_name,
+          n.active,
+          n.upstream_node_id,
+          un.node_name AS upstream_node_name,
+          n.type,
+          n.priority,
+          n.conninfo
+     FROM repmgr.nodes n
+LEFT JOIN repmgr.nodes un
+       ON un.node_id = n.upstream_node_id;
+
+CREATE TABLE repmgr.voting_term (
+  term INT NOT NULL
+);
+
+CREATE UNIQUE INDEX voting_term_restrict
+ON repmgr.voting_term ((TRUE));
+
+CREATE RULE voting_term_delete AS
+   ON DELETE TO repmgr.voting_term
+   DO INSTEAD NOTHING;
+
+
+/* ================= */
+/* repmgrd functions */
+/* ================= */
+
+/* monitoring functions */
+
+CREATE FUNCTION set_local_node_id(INT)
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', '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--unpackaged--5.2.sql

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

repmgr-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
@@ -55,10 +55,8 @@ typedef enum
 struct ColHeader headers_show[SHOW_HEADER_COUNT];
 struct ColHeader headers_event[EVENT_HEADER_COUNT];
 
-
-
-static int	build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, ItemList *warnings, int *error_code);
-static int	build_cluster_crosscheck(t_node_status_cube ***cube_dest, int *name_length, ItemList *warnings, int *error_code);
+static int	build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, int *error_code);
+static int	build_cluster_crosscheck(t_node_status_cube ***cube_dest, ItemList *warnings, int *error_code);
 static void cube_set_node_status(t_node_status_cube **cube, int n, int node_id, int matrix_node_id, int connection_node_id, int connection_status);
 
 /*
@@ -67,6 +65,8 @@ 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 +206,8 @@ 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 +245,13 @@ 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 "?" */
-			headers_show[SHOW_TIMELINE_ID].cur_length = 1;
-		}
-		else
-		{
-			initPQExpBuffer(&buf);
-			appendPQExpBuffer(&buf, "%i", cell->node_info->replication_info->timeline_id);
-			headers_show[SHOW_TIMELINE_ID].cur_length = strlen(buf.data);
-			termPQExpBuffer(&buf);
+			/* The witness node's timeline ID is irrelevant */
+			strncpy(cell->node_info->replication_info->timeline_id_str, _("n/a"), MAXLEN);
 		}
+		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 +318,7 @@ do_cluster_show(void)
 
 			if (headers_show[SHOW_TIMELINE_ID].display == true)
 			{
-				if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
-					printf("| %-*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);
+				printf("| %-*s ", headers_show[SHOW_TIMELINE_ID].max_length, cell->node_info->replication_info->timeline_id_str);
 			}
 
 			if (headers_show[SHOW_CONNINFO].display == true)
@@ -343,14 +336,25 @@ 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"));
@@ -532,9 +536,6 @@ do_cluster_crosscheck(void)
 {
 	int			i = 0,
 				n = 0;
-	char		c;
-	const char *node_header = "Name";
-	int			name_length = strlen(node_header);
 
 	t_node_status_cube **cube;
 
@@ -542,7 +543,7 @@ do_cluster_crosscheck(void)
 	int			error_code = SUCCESS;
 	ItemList	warnings = {NULL, NULL};
 
-	n = build_cluster_crosscheck(&cube, &name_length, &warnings, &error_code);
+	n = build_cluster_crosscheck(&cube, &warnings, &error_code);
 
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -576,24 +577,56 @@ do_cluster_crosscheck(void)
 	}
 	else
 	{
-		printf("%*s | Id ", name_length, node_header);
-		for (i = 0; i < n; i++)
-			printf("| %2d ", cube[i]->node_id);
-		printf("\n");
+		/* output header contains node name, node ID and one column for each node in the cluster */
+		struct ColHeader *headers_crosscheck = NULL;
+
+		int header_count = n + 2;
+		int header_id = 2;
+
+		headers_crosscheck = palloc0(sizeof(ColHeader) * header_count);
+
+		/* Initialize column headers  */
+		strncpy(headers_crosscheck[0].title, _("Name"), MAXLEN);
+		strncpy(headers_crosscheck[1].title, _("ID"), MAXLEN);
 
-		for (i = 0; i < name_length; i++)
-			printf("-");
-		printf("-+----");
 		for (i = 0; i < n; i++)
-			printf("+----");
-		printf("\n");
+		{
+			maxlen_snprintf(headers_crosscheck[header_id].title, "%i", cube[i]->node_id);
+			header_id++;
+		}
+
+		/* Initialize column max values */
+		for (i = 0; i < header_count; i++)
+		{
+			headers_crosscheck[i].display = true;
+			headers_crosscheck[i].max_length = strlen(headers_crosscheck[i].title);
+			headers_crosscheck[i].cur_length = headers_crosscheck[i].max_length;
+
+			/* We can derive the maximum node ID length for the ID column from
+			 * the generated matrix node ID headers
+			 */
+			if (i >= 2 && headers_crosscheck[i].max_length > headers_crosscheck[1].max_length)
+				headers_crosscheck[1].max_length = headers_crosscheck[i].max_length;
+		}
+
+		for (i = 0; i < n; i++)
+		{
+			if (strlen(cube[i]->node_name) > headers_crosscheck[0].max_length)
+			{
+				headers_crosscheck[0].max_length = strlen(cube[i]->node_name);
+			}
+		}
+
+		print_status_header(header_count, headers_crosscheck);
 
 		for (i = 0; i < n; i++)
 		{
 			int			column_node_ix;
 
-			printf("%*s | %2d ", name_length,
+			printf(" %-*s | %-*i ",
+				   headers_crosscheck[0].max_length,
 				   cube[i]->node_name,
+				   headers_crosscheck[1].max_length,
 				   cube[i]->node_id);
 
 			for (column_node_ix = 0; column_node_ix < n; column_node_ix++)
@@ -601,6 +634,8 @@ do_cluster_crosscheck(void)
 				int			max_node_status = -2;
 				int			node_ix = 0;
 
+				char		c;
+
 				/*
 				 * The value of entry (i,j) is equal to the maximum value of all
 				 * the (i,j,k). Indeed:
@@ -640,12 +675,14 @@ do_cluster_crosscheck(void)
 						exit(ERR_INTERNAL);
 				}
 
-				printf("|  %c ", c);
+				printf("| %-*c ", headers_crosscheck[column_node_ix + 2].max_length, c);
 			}
 
 			printf("\n");
 		}
 
+		pfree(headers_crosscheck);
+
 		if (warnings.head != NULL && runtime_options.terse == false)
 		{
 			log_warning(_("following problems detected:"));
@@ -702,16 +739,13 @@ do_cluster_matrix()
 				j = 0,
 				n = 0;
 
-	const char *node_header = "Name";
-	int			name_length = strlen(node_header);
-
 	t_node_matrix_rec **matrix_rec_list;
 
 	bool		connection_error_found = false;
 	int			error_code = SUCCESS;
 	ItemList	warnings = {NULL, NULL};
 
-	n = build_cluster_matrix(&matrix_rec_list, &name_length, &warnings, &error_code);
+	n = build_cluster_matrix(&matrix_rec_list, &warnings, &error_code);
 
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -734,27 +768,60 @@ do_cluster_matrix()
 	}
 	else
 	{
-		char		c;
+		/* output header contains node name, node ID and one column for each node in the cluster */
+		struct ColHeader *headers_matrix = NULL;
 
-		printf("%*s | Id ", name_length, node_header);
-		for (i = 0; i < n; i++)
-			printf("| %2d ", matrix_rec_list[i]->node_id);
-		printf("\n");
+		int header_count = n + 2;
+		int header_id = 2;
 
-		for (i = 0; i < name_length; i++)
-			printf("-");
-		printf("-+----");
-		for (i = 0; i < n; i++)
-			printf("+----");
-		printf("\n");
+		headers_matrix = palloc0(sizeof(ColHeader) * header_count);
+
+		/* Initialize column headers  */
+		strncpy(headers_matrix[0].title, _("Name"), MAXLEN);
+		strncpy(headers_matrix[1].title, _("ID"), MAXLEN);
 
 		for (i = 0; i < n; i++)
 		{
-			printf("%*s | %2d ", name_length,
+			maxlen_snprintf(headers_matrix[header_id].title, "%i", matrix_rec_list[i]->node_id);
+			header_id++;
+		}
+
+		/* Initialize column max values */
+		for (i = 0; i < header_count; i++)
+		{
+			headers_matrix[i].display = true;
+			headers_matrix[i].max_length = strlen(headers_matrix[i].title);
+			headers_matrix[i].cur_length = headers_matrix[i].max_length;
+
+			/* We can derive the maximum node ID length for the ID column from
+			 * the generated matrix node ID headers
+			 */
+			if (i >= 2 && headers_matrix[i].max_length > headers_matrix[1].max_length)
+				headers_matrix[1].max_length = headers_matrix[i].max_length;
+		}
+
+
+		for (i = 0; i < n; i++)
+		{
+			if (strlen(matrix_rec_list[i]->node_name) > headers_matrix[0].max_length)
+			{
+				headers_matrix[0].max_length = strlen(matrix_rec_list[i]->node_name);
+			}
+		}
+
+		print_status_header(header_count, headers_matrix);
+
+		for (i = 0; i < n; i++)
+		{
+			printf(" %-*s | %-*i ",
+				   headers_matrix[0].max_length,
 				   matrix_rec_list[i]->node_name,
+				   headers_matrix[1].max_length,
 				   matrix_rec_list[i]->node_id);
 			for (j = 0; j < n; j++)
 			{
+				char		c;
+
 				switch (matrix_rec_list[i]->node_status_list[j]->node_status)
 				{
 					case -2:
@@ -772,11 +839,13 @@ do_cluster_matrix()
 						exit(ERR_INTERNAL);
 				}
 
-				printf("|  %c ", c);
+				printf("| %-*c ", headers_matrix[j + 2].max_length, c);
 			}
 			printf("\n");
 		}
 
+		pfree(headers_matrix);
+
 		if (warnings.head != NULL && runtime_options.terse == false)
 		{
 			log_warning(_("following problems detected:"));
@@ -832,7 +901,7 @@ matrix_set_node_status(t_node_matrix_rec **matrix_rec_list, int n, int node_id,
 
 
 static int
-build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, ItemList *warnings, int *error_code)
+build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, int *error_code)
 {
 	PGconn	   *conn = NULL;
 	int			i = 0,
@@ -890,7 +959,6 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 	/* Initialise matrix structure for each node */
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
-		int			name_length_cur;
 		NodeInfoListCell *cell_j;
 
 		matrix_rec_list[i] = (t_node_matrix_rec *) pg_malloc0(sizeof(t_node_matrix_rec));
@@ -900,13 +968,6 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 				cell->node_info->node_name,
 				sizeof(matrix_rec_list[i]->node_name));
 
-		/*
-		 * Find the maximum length of a node name
-		 */
-		name_length_cur = strlen(matrix_rec_list[i]->node_name);
-		if (name_length_cur > *name_length)
-			*name_length = name_length_cur;
-
 		matrix_rec_list[i]->node_status_list = (t_node_status_rec **) pg_malloc0(sizeof(t_node_status_rec) * nodes.node_count);
 
 		j = 0;
@@ -1071,7 +1132,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 
 
 static int
-build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, ItemList *warnings, int *error_code)
+build_cluster_crosscheck(t_node_status_cube ***dest_cube, ItemList *warnings, int *error_code)
 {
 	PGconn	   *conn = NULL;
 	int			h,
@@ -1120,20 +1181,12 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 
 	for (cell = nodes.head; cell; cell = cell->next)
 	{
-		int			name_length_cur = 0;
 		NodeInfoListCell *cell_i = NULL;
 
 		cube[h] = (t_node_status_cube *) pg_malloc(sizeof(t_node_status_cube));
 		cube[h]->node_id = cell->node_info->node_id;
 		strncpy(cube[h]->node_name, cell->node_info->node_name, sizeof(cube[h]->node_name));
 
-		/*
-		 * Find the maximum length of a node name
-		 */
-		name_length_cur = strlen(cube[h]->node_name);
-		if (name_length_cur > *name_length)
-			*name_length = name_length_cur;
-
 		cube[h]->matrix_list_rec = (t_node_matrix_rec **) pg_malloc(sizeof(t_node_matrix_rec) * nodes.node_count);
 
 		i = 0;
@@ -1396,6 +1449,10 @@ 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)
 	{
@@ -1497,4 +1554,5 @@ do_cluster_help(void)
 	printf(_("    -k, --keep-history=VALUE  retain indicated number of days of history (default: 0)\n"));
 	puts("");
 
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
 }

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
@@ -339,4 +339,5 @@ void do_daemon_help(void)
 
 	puts("");
 
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
 }

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.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
@@ -454,9 +454,9 @@ do_primary_unregister(void)
 
 			/*
 			 * This appears to be the cluster primary - cowardly refuse to
-			 * delete the record
+			 * delete the record, unless --force is supplied.
 			 */
-			if (primary_node_info.node_id == target_node_info_ptr->node_id)
+			if (primary_node_info.node_id == target_node_info_ptr->node_id && !runtime_options.force)
 			{
 				log_error(_("node \"%s\" (ID: %i) is the current primary node, unable to unregister"),
 						  target_node_info_ptr->node_name,
@@ -575,4 +575,5 @@ do_primary_help(void)
 
 	puts("");
 
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
 }

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)
 		{
@@ -532,4 +543,6 @@ void do_service_help(void)
 	puts("");
 
 	puts("");
+
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
 }

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))
 	{
@@ -594,5 +569,5 @@ void do_witness_help(void)
 
 	puts("");
 
-	return;
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
 }

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 */
@@ -46,6 +48,7 @@ typedef struct
 	bool		no_wait;
 	bool		compact;
 	bool		detail;
+	bool		dump_config;
 
 	/* logging options */
 	char		log_level[MAXLEN];	/* overrides setting in repmgr.conf */
@@ -85,7 +88,8 @@ typedef struct
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
-	bool		recovery_conf_only;
+	bool		replication_conf_only;
+	bool		verify_backup;
 
 	/* "standby clone"/"standby follow" options */
 	int			upstream_node_id;
@@ -109,6 +113,7 @@ typedef struct
 	/* "node check" options */
 	bool		archive_ready;
 	bool		downstream;
+	bool		upstream;
 	bool		replication_lag;
 	bool		role;
 	bool		slots;
@@ -116,6 +121,8 @@ typedef struct
 	bool		has_passfile;
 	bool		replication_connection;
 	bool		data_directory_config;
+	bool		replication_config_owner;
+	bool		db_connection;
 
 	/* "node rejoin" options */
 	char		config_files[MAXLEN];
@@ -136,7 +143,7 @@ typedef struct
 
 	/* following options for internal use */
 	char		config_archive_dir[MAXPGPATH];
-	OutputMode	output_mode;
+	OutputMode	output_mode; /* set through provision of --csv, --nagios or --optformat */
 	bool		disable_wal_receiver;
 	bool		enable_wal_receiver;
 } t_runtime_options;
@@ -145,7 +152,7 @@ typedef struct
 		/* configuration metadata */ \
 		false, false, false, false, false,	\
 		/* general configuration options */	\
-		"", false, false, "", -1, false, false, false, \
+		"", false, false, "", -1, false, false, false, false, \
 		/* logging options */ \
 		"", false, false, false, false,	\
 		/* output options */ \
@@ -158,7 +165,7 @@ typedef struct
 		UNKNOWN_NODE_ID, "", "", UNKNOWN_NODE_ID, \
 		/* "standby clone" options */ \
 		false, CONFIG_FILE_SAMEPATH, false, false, false, "", "", "", \
-		false, false, \
+		false, false, false, \
 		/* "standby clone"/"standby follow" options */ \
 		NO_UPSTREAM_NODE, \
 		/* "standby register" options */ \
@@ -168,7 +175,7 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, false, false, false,	false, \
+		false, false, false, false, false, false, false, false,	false, false, false, false, \
 		/* "node rejoin" options */ \
 		"", \
 		/* "node service" options */ \
@@ -201,6 +208,30 @@ 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 enum
+{
+	REMOTE_ERROR_UNKNOWN = -1,
+	REMOTE_ERROR_NONE,
+	REMOTE_ERROR_DB_CONNECTION,
+	REMOTE_ERROR_CONNINFO_PARSE
+} t_remote_error_type;
+
 typedef struct ColHeader
 {
 	char		title[MAXLEN];
@@ -211,21 +242,17 @@ typedef struct ColHeader
 
 
 
-/* global configuration structures */
+/* globally available configuration structures */
 extern t_runtime_options runtime_options;
-extern t_configuration_options config_file_options;
-
-t_conninfo_param_list source_conninfo;
-
+extern t_conninfo_param_list source_conninfo;
+extern t_node_info target_node_info;
 
+/* global variables */
 extern bool config_file_required;
 extern char pg_bindir[MAXLEN];
 
-extern t_node_info target_node_info;
-
-
+/* global functions */
 extern int	check_server_version(PGconn *conn, char *server_type, bool exit_on_error, char *server_version_string);
-extern void check_93_config(void);
 extern bool create_repmgr_extension(PGconn *conn);
 extern int	test_ssh_connection(char *host, char *remote_user);
 
@@ -236,7 +263,7 @@ extern int copy_remote_files(char *host, char *remote_user, char *remote_path,
 
 extern void print_error_list(ItemList *error_list, int log_level);
 
-extern char *make_pg_path(const char *file);
+extern void make_pg_path(PQExpBufferData *buf, const char *file);
 
 extern void get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privileged_conn);
 
@@ -255,9 +282,17 @@ 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 void make_standby_signal_path(char *buf);
+extern bool write_standby_signal(void);
 
+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.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 BDR_UNREGISTER		   12
-#define NODE_STATUS			   13
-#define NODE_CHECK			   14
-#define NODE_SERVICE		   15
-#define NODE_REJOIN            16
-#define NODE_CONTROL           17
-#define CLUSTER_SHOW		   18
-#define CLUSTER_CLEANUP		   19
-#define CLUSTER_MATRIX		   20
-#define CLUSTER_CROSSCHECK	   21
-#define CLUSTER_EVENT		   22
-#define SERVICE_STATUS		   23
-#define SERVICE_PAUSE		   24
-#define SERVICE_UNPAUSE		   25
-#define DAEMON_START 		   26
-#define DAEMON_STOP 		   27
+#define NODE_STATUS			   11
+#define NODE_CHECK			   12
+#define NODE_SERVICE		   13
+#define NODE_REJOIN            14
+#define NODE_CONTROL           15
+#define CLUSTER_SHOW		   16
+#define CLUSTER_CLEANUP		   17
+#define CLUSTER_MATRIX		   18
+#define CLUSTER_CROSSCHECK	   19
+#define CLUSTER_EVENT		   20
+#define SERVICE_STATUS		   21
+#define SERVICE_PAUSE		   22
+#define SERVICE_UNPAUSE		   23
+#define DAEMON_START 		   24
+#define DAEMON_STOP 		   25
 
 /* command line options without short versions */
 #define OPT_HELP						   1001
@@ -83,27 +81,33 @@
 #define OPT_SIBLINGS_FOLLOW				   1028
 #define OPT_ROLE						   1029
 #define OPT_DOWNSTREAM					   1030
-#define OPT_SLOTS						   1031
-#define OPT_CONFIG_ARCHIVE_DIR			   1032
+#define OPT_UPSTREAM					   1031
+#define OPT_SLOTS						   1032
 #define OPT_HAS_PASSFILE				   1033
 #define OPT_WAIT_START					   1034
 #define OPT_REPL_CONN					   1035
 #define OPT_REMOTE_NODE_ID				   1036
-#define OPT_RECOVERY_CONF_ONLY			   1037
+#define OPT_REPLICATION_CONF_ONLY		   1037
 #define OPT_NO_WAIT						   1038
 #define OPT_MISSING_SLOTS				   1039
 #define OPT_REPMGRD_NO_PAUSE			   1040
 #define OPT_VERSION_NUMBER				   1041
 #define OPT_DATA_DIRECTORY_CONFIG		   1042
 #define OPT_COMPACT						   1043
-#define OPT_DISABLE_WAL_RECEIVER		   1044
-#define OPT_ENABLE_WAL_RECEIVER			   1045
-#define OPT_DETAIL						   1046
-#define OPT_REPMGRD_FORCE_UNPAUSE		   1047
+#define OPT_DETAIL						   1044
+#define OPT_REPMGRD_FORCE_UNPAUSE		   1045
+#define OPT_REPLICATION_CONFIG_OWNER	   1046
+#define OPT_DB_CONNECTION				   1047
+#define OPT_VERIFY_BACKUP				   1048
+
+/* These options are for internal use only */
+#define OPT_CONFIG_ARCHIVE_DIR			   2001
+#define OPT_DISABLE_WAL_RECEIVER		   2002
+#define OPT_ENABLE_WAL_RECEIVER			   2003
+#define OPT_DUMP_CONFIG					   2004
 
 /* deprecated since 4.0 */
 #define OPT_CHECK_UPSTREAM_CONFIG		    999
-#define OPT_NODE						    998
 
 
 static struct option long_options[] =
@@ -122,6 +126,7 @@ static struct option long_options[] =
 	{"no-wait", no_argument, NULL, 'W'},
 	{"compact", no_argument, NULL, OPT_COMPACT},
 	{"detail", no_argument, NULL, OPT_DETAIL},
+	{"dump-config", no_argument, NULL, OPT_DUMP_CONFIG},
 
 /* connection options */
 	{"dbname", required_argument, NULL, 'd'},
@@ -157,7 +162,10 @@ 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},
+	{"verify-backup", no_argument, NULL, OPT_VERIFY_BACKUP },
+	/* 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 +186,7 @@ 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 +194,8 @@ 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},
+	{"db-connection", no_argument, NULL, OPT_DB_CONNECTION},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},
@@ -212,9 +223,6 @@ static struct option long_options[] =
 	{"check-upstream-config", no_argument, NULL, OPT_CHECK_UPSTREAM_CONFIG},
 	/* previously used by "standby switchover" */
 	{"remote-config-file", required_argument, NULL, 'C'},
-	/* replaced by --node-id */
-	{"node", required_argument, NULL, OPT_NODE},
-
 	{NULL, 0, NULL, 0}
 };
 

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
@@ -33,22 +33,14 @@
 #include "storage/shmem.h"
 #include "storage/spin.h"
 #include "utils/builtins.h"
-
-#if (PG_VERSION_NUM >= 90400)
 #include "utils/pg_lsn.h"
-#endif
 
 #include "utils/timestamp.h"
 
 #include "lib/stringinfo.h"
 #include "access/xact.h"
 #include "utils/snapmgr.h"
-
-#if (PG_VERSION_NUM >= 90400)
 #include "pgstat.h"
-#else
-#define PGSTAT_STAT_PERMANENT_DIRECTORY             "pg_stat"
-#endif
 
 #include "voting.h"
 
@@ -84,8 +76,6 @@ 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 +121,6 @@ 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);
 
@@ -165,8 +149,6 @@ PG_FUNCTION_INFO_V1(get_wal_receiver_pid);
 void
 _PG_init(void)
 {
-	elog(DEBUG1, "repmgr init");
-
 	if (!process_shared_preload_libraries_in_progress)
 		return;
 
@@ -183,7 +165,6 @@ _PG_init(void)
 	 */
 	prev_shmem_startup_hook = shmem_startup_hook;
 	shmem_startup_hook = repmgr_shmem_startup;
-
 }
 
 
@@ -241,7 +222,6 @@ 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 +551,6 @@ 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

@@ -71,8 +71,7 @@
 #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".
-				 # NOTE: "bdr" can only be used with BDR 2.x
+#replication_type='physical'	 # Must "physical" (the default).
 
 #location='default'		 # An arbitrary string defining the location of the node; this
 				 # is used during failover to check visibility of the
@@ -182,6 +181,8 @@
 
 #pg_ctl_options=''			# Options to append to "pg_ctl"
 #pg_basebackup_options=''		# Options to append to "pg_basebackup"
+                                        # (Note: when cloning from Barman, repmgr will honour any
+                                        # --waldir/--xlogdir setting present in "pg_basebackup_options"
 #rsync_options=''			# Options to append to "rsync"
 ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 
@@ -195,7 +196,7 @@ 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
@@ -210,7 +211,9 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# managing WAL archives (see: https://www.pgbarman.org )
 
 #recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" will be set to
-					# this value (PostgreSQL 9.4 and later).
+					# this value (PostgreSQL 9.4 and later). Value can be
+                                        # an integer representing milliseconds, or a string
+                                        # representing a period of time (e.g. '5 min').
 
 
 #------------------------------------------------------------------------------
@@ -237,7 +240,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for the new primary to become available
 #standby_follow_timeout=15		# The max length of time (in seconds) to wait
 					# for the standby to connect to the primary
-
+#standby_follow_restart=false		# Restart the standby instead of sending a SIGHUP
+					# (only for PostgreSQL 13 and later)
 
 #------------------------------------------------------------------------------
 # "standby switchover" settings
@@ -290,7 +294,6 @@ 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
@@ -299,6 +302,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #connection_check_type=ping		# How to check availability of the upstream node; valid options:
 					#  'ping': use PQping() to check if the node is accepting connections
 					#  'connection': execute a throwaway query on the current connection
+					#  'query': execute an SQL statement on the node via the existing connection
 #reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
 #reconnect_interval=10			# Interval between attempts to reconnect to an unreachable
@@ -341,6 +345,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# WAL receivers
 #primary_visibility_consensus=false	# If "true", only continue with failover if no standbys have seen
 					# the primary node recently. *Must* be the same on all nodes.
+#always_promote=false			# Always promote a node, even if repmgr metadata is outdated
 #failover_validation_command=''		# Script to execute for an external mechanism to validate the failover
 					# decision made by repmgrd. One or both of the following parameter placeholders
 					# should be provided, which will be replaced by repmgrd with the appropriate
@@ -436,12 +441,3 @@ 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 = '5.2'
 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
@@ -74,20 +74,20 @@
 #include "log.h"
 #include "sysutils.h"
 
-#define MIN_SUPPORTED_VERSION		"9.3"
-#define MIN_SUPPORTED_VERSION_NUM	90300
+#define MIN_SUPPORTED_VERSION		"9.4"
+#define MIN_SUPPORTED_VERSION_NUM	90400
 
 #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_DATA_CHECKSUM_VERSION -1
 #define UNKNOWN_PID			-1
 #define UNKNOWN_REPLICATION_LAG	-1
+#define UNKNOWN_VALUE		-1
 
 #define NODE_NOT_FOUND		-1
 #define NO_UPSTREAM_NODE	-1
@@ -98,43 +98,57 @@
 #define ARCHIVE_STATUS_DIR_ERROR -1
 #define NO_DEGRADED_MONITORING_ELAPSED -1
 
-#define BDR2_REPLICATION_SET_NAME "repmgr"
+#define WALRECEIVER_DISABLE_TIMEOUT_VALUE    86400000 /* milliseconds */
 
 /*
- * various default values - ensure repmgr.conf.sample is update
- * if any of these are changed
+ * Default command line option parameter values
  */
-#define DEFAULT_LOCATION                     "default"
-#define DEFAULT_PRIORITY		             100
-#define DEFAULT_RECONNECTION_ATTEMPTS        6	 /* seconds */
-#define DEFAULT_RECONNECTION_INTERVAL        10  /* seconds */
-#define DEFAULT_MONITORING_INTERVAL          2	 /* seconds */
-#define DEFAULT_ASYNC_QUERY_TIMEOUT          60  /* seconds */
-#define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
+#define DEFAULT_WAIT_START                   30  /* seconds */
+
+/*
+ * Default configuration file parameter values - ensure repmgr.conf.sample
+ * is update if any of these are changed
+ */
+
+#define DEFAULT_USE_REPLICATION_SLOTS        false
+#define DEFAULT_USE_PRIMARY_CONNINFO_PASSWORD false
+#define DEFAULT_PROMOTE_CHECK_TIMEOUT        60  /* seconds */
+#define DEFAULT_PROMOTE_CHECK_INTERVAL       1   /* seconds */
 #define DEFAULT_PRIMARY_FOLLOW_TIMEOUT       60  /* seconds */
 #define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
-#define DEFAULT_BDR_RECOVERY_TIMEOUT         30  /* seconds */
+#define DEFAULT_STANDBY_FOLLOW_RESTART       false
+#define DEFAULT_SHUTDOWN_CHECK_TIMEOUT       60  /* seconds */
+#define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */
+#define DEFAULT_NODE_REJOIN_TIMEOUT          60  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */
 #define	DEFAULT_REPLICATION_LAG_WARNING      300 /* seconds */
 #define DEFAULT_REPLICATION_LAG_CRITICAL     600 /* seconds */
 #define DEFAULT_WITNESS_SYNC_INTERVAL        15  /* seconds */
-#define DEFAULT_WAIT_START                   30  /* seconds */
-#define DEFAULT_PROMOTE_CHECK_TIMEOUT        60  /* seconds */
-#define DEFAULT_PROMOTE_CHECK_INTERVAL       1   /* seconds */
-#define DEFAULT_SHUTDOWN_CHECK_TIMEOUT       60  /* seconds */
-#define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */
-#define DEFAULT_NODE_REJOIN_TIMEOUT          60  /* seconds */
 #define DEFAULT_WAL_RECEIVE_CHECK_TIMEOUT    30  /* seconds */
+#define DEFAULT_LOCATION                     "default"
+#define DEFAULT_PRIORITY                     100
+#define DEFAULT_MONITORING_INTERVAL          2	 /* seconds */
+#define DEFAULT_RECONNECTION_ATTEMPTS        6	 /* seconds */
+#define DEFAULT_RECONNECTION_INTERVAL        10  /* seconds */
+#define DEFAULT_MONITORING_HISTORY           false
+#define DEFAULT_DEGRADED_MONITORING_TIMEOUT  -1  /* seconds */
+#define DEFAULT_ASYNC_QUERY_TIMEOUT          60  /* seconds */
+#define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
+#define DEFAULT_REPMGRD_STANDBY_STARTUP_TIMEOUT -1 /*seconds */
+#define DEFAULT_STANDBY_DISCONNECT_ON_FAILOVER false
 #define DEFAULT_SIBLING_NODES_DISCONNECT_TIMEOUT 30 /* seconds */
+#define DEFAULT_CONNECTION_CHECK_TYPE        CHECK_PING
+#define DEFAULT_PRIMARY_VISIBILITY_CONSENSUS false
+#define DEFAULT_ALWAYS_PROMOTE               false
 #define DEFAULT_ELECTION_RERUN_INTERVAL      15  /* seconds */
 #define DEFAULT_CHILD_NODES_CHECK_INTERVAL   5   /* seconds */
 #define DEFAULT_CHILD_NODES_DISCONNECT_MIN_COUNT -1
 #define DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT -1
-#define DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT 30 /* seconds */
 #define DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS false
+#define DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT 30 /* seconds */
+#define DEFAULT_SSH_OPTIONS                  "-q -o ConnectTimeout=10"
 
-#define WALRECEIVER_DISABLE_TIMEOUT_VALUE    86400000 /* milliseconds */
 
 #ifndef RECOVERY_COMMAND_FILE
 #define RECOVERY_COMMAND_FILE "recovery.conf"
@@ -149,6 +163,6 @@
 #define TABLESPACE_MAP "tablespace_map"
 #endif
 
-
+#define REPMGR_URL "https://repmgr.org/"
 
 #endif							/* _REPMGR_H_ */

repmgr_version.h.in

@@ -1,5 +1,5 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "5.0.0"
-#define REPMGR_VERSION_NUM 50000
-#define REPMGR_RELEASE_DATE "2019-10-15"
+#define REPMGR_VERSION "5.2.0"
+#define REPMGR_VERSION_NUM 50200
+#define REPMGR_RELEASE_DATE "2020-10-22"
 #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.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"
 
@@ -40,13 +39,9 @@ static bool daemonize = true;
 static bool show_pid_file = false;
 static bool no_pid_file = false;
 
-t_configuration_options config_file_options = T_CONFIGURATION_OPTIONS_INITIALIZER;
-
 t_node_info local_node_info = T_NODE_INFO_INITIALIZER;
 PGconn	   *local_conn = NULL;
 
-
-
 /* Collate command line errors here for friendlier reporting */
 static ItemList cli_errors = {NULL, NULL};
 
@@ -257,7 +252,7 @@ main(int argc, char **argv)
 	 * locations). If no conifguration file is available, or it can't be parsed
 	 * parse_config() will abort anyway, with an appropriate message.
 	 */
-	load_config(config_file, verbose, false, &config_file_options, argv[0]);
+	load_config(config_file, verbose, false, argv[0]);
 
 	/* Determine pid file location, unless --no-pid-file supplied */
 
@@ -484,9 +479,6 @@ 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 +505,7 @@ main(int argc, char **argv)
 		}
 	}
 
-	if (config_file_options.replication_type == REPLICATION_TYPE_BDR)
-	{
-		log_debug("node id is %i", local_node_info.node_id);
-		do_bdr_node_check();
-	}
-	else
+	if (config_file_options.replication_type == REPLICATION_TYPE_PHYSICAL)
 	{
 		log_debug("node id is %i, upstream node id is %i",
 				  local_node_info.node_id,
@@ -526,8 +513,6 @@ main(int argc, char **argv)
 		do_physical_node_check();
 	}
 
-
-
 	if (daemonize == true)
 	{
 		daemonize_process();
@@ -576,9 +561,6 @@ start_monitoring(void)
 			case WITNESS:
 				monitor_streaming_witness();
 				break;
-			case BDR:
-				monitor_bdr();
-				return;
 			case UNKNOWN:
 				/* should never happen */
 				break;
@@ -771,10 +753,6 @@ 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);
@@ -830,42 +808,92 @@ show_help(void)
 
 
 bool
-check_upstream_connection(PGconn **conn, const char *conninfo)
+check_upstream_connection(PGconn **conn, const char *conninfo, PGconn **paired_conn)
 {
 	/* Check the connection status twice in case it changes after reset */
 	bool		twice = false;
 
-	if (config_file_options.connection_check_type == CHECK_PING)
-		return is_server_available(conninfo);
-
-	if (config_file_options.connection_check_type == CHECK_CONNECTION)
+	log_debug("connection check type is \"%s\"",
+			  print_connection_check_type(config_file_options.connection_check_type));
+	/*
+	 * For the check types which do not involve using the existing database
+	 * connection, we'll perform the actual check, then as an additional
+	 * safeguard verify that the connection is still valid (as it might have
+	 * gone away during a brief outage between checks).
+	 */
+	if (config_file_options.connection_check_type != CHECK_QUERY)
 	{
 		bool success = true;
-		PGconn *test_conn = PQconnectdb(conninfo);
 
-		log_debug("check_upstream_connection(): attempting to connect to \"%s\"", conninfo);
-
-		if (PQstatus(test_conn) != CONNECTION_OK)
+		if (config_file_options.connection_check_type == CHECK_PING)
 		{
-			log_warning(_("unable to connect to \"%s\""), conninfo);
-			log_detail("\n%s", PQerrorMessage(test_conn));
-			success = false;
+			success = is_server_available(conninfo);
 		}
-		PQfinish(test_conn);
+		else if (config_file_options.connection_check_type == CHECK_CONNECTION)
+		{
+			/*
+			 * This connection is thrown away, and we never execute a query on it.
+			 */
+			PGconn *test_conn = PQconnectdb(conninfo);
 
-		return success;
+			log_debug("check_upstream_connection(): attempting to connect to \"%s\"", conninfo);
+
+			if (PQstatus(test_conn) != CONNECTION_OK)
+			{
+				log_warning(_("unable to connect to \"%s\""), conninfo);
+				log_detail("\n%s", PQerrorMessage(test_conn));
+				success = false;
+			}
+			PQfinish(test_conn);
+		}
+
+		if (success == false)
+			return false;
+
+		if (PQstatus(*conn) == CONNECTION_OK)
+			return true;
+
+		/*
+		 * Checks have succeeded, but the open connection to the primary has gone away,
+		 * possibly due to a brief outage between monitoring intervals - attempt to
+		 * reset it.
+		 */
+		log_notice(_("upstream is available but upstream connection has gone away, resetting"));
+
+		PQfinish(*conn);
+		*conn = establish_db_connection_quiet(conninfo);
+
+		if (PQstatus(*conn) == CONNECTION_OK)
+		{
+			if (paired_conn != NULL)
+			{
+				log_debug("resetting paired connection");
+				*paired_conn = *conn;
+			}
+
+			return true;
+		}
+
+		return false;
 	}
 
 	for (;;)
 	{
 		if (PQstatus(*conn) != CONNECTION_OK)
 		{
-			log_debug("check_upstream_connection(): connection not OK");
+			log_debug("check_upstream_connection(): upstream connection has gone away, resetting");
 			if (twice)
 				return false;
+
 			/* reconnect */
 			PQfinish(*conn);
-			*conn = PQconnectdb(conninfo);
+			*conn = establish_db_connection_quiet(conninfo);
+
+			if (paired_conn != NULL)
+			{
+				log_debug("resetting paired connection");
+				*paired_conn = *conn;
+			}
 			twice = true;
 		}
 		else
@@ -877,7 +905,7 @@ check_upstream_connection(PGconn **conn, const char *conninfo)
 				goto failed;
 
 			/* execute a simple query to verify connection availability */
-			if (PQsendQuery(*conn, "SELECT 1") == 0)
+			if (PQsendQuery(*conn, config_file_options.connection_check_query) == 0)
 			{
 				log_warning(_("unable to send query to upstream"));
 				log_detail("%s", PQerrorMessage(*conn));
@@ -895,8 +923,16 @@ check_upstream_connection(PGconn **conn, const char *conninfo)
 				return false;
 
 			/* reconnect */
+			log_debug("check_upstream_connection(): upstream connection not available, resetting");
+
 			PQfinish(*conn);
-			*conn = PQconnectdb(conninfo);
+			*conn = establish_db_connection_quiet(conninfo);
+
+			if (paired_conn != NULL)
+			{
+				log_debug("resetting paired connection");
+				*paired_conn = *conn;
+			}
 			twice = true;
 		}
 	}

repmgrd.h

@@ -1,6 +1,6 @@
 /*
  * repmgrd.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) 2ndQuadrant, 2010-2020
  */
 
 
@@ -17,13 +17,12 @@ extern volatile sig_atomic_t got_SIGHUP;
 extern MonitoringState monitoring_state;
 extern instr_time degraded_monitoring_start;
 
-extern t_configuration_options config_file_options;
 extern t_node_info local_node_info;
 extern PGconn *local_conn;
 extern bool startup_event_logged;
 extern char pid_file[MAXPGPATH];
 
-bool		check_upstream_connection(PGconn **conn, const char *conninfo);
+bool		check_upstream_connection(PGconn **conn, const char *conninfo, PGconn **paired_conn);
 void		try_reconnect(PGconn **conn, t_node_info *node_info);
 
 int			calculate_elapsed(instr_time start_time);

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
@@ -386,12 +386,9 @@ output_check_status(CheckStatus status)
 	}
 
 	return "UNKNOWN";
-
 }
 
 
-
-
 /*
  * Escape a string for use as a parameter in recovery.conf
  * Caller must free returned value
@@ -433,7 +430,6 @@ escape_string(PGconn *conn, const char *string)
 /*
  * simple function to escape double quotes only
  */
-
 void
 escape_double_quotes(char *string, PQExpBufferData *out)
 {
@@ -564,3 +560,10 @@ parse_follow_command(char *parsed_command, char *template, int node_id)
 
 	return;
 }
+
+
+const char *
+format_bool(bool value)
+{
+	return value == true ? "true" : "false";
+}

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
@@ -166,4 +166,6 @@ extern char *trim(char *s);
 extern void
 			parse_follow_command(char *parsed_command, char *template, int node_id);
 
+extern const char *format_bool(bool value);
+
 #endif							/* _STRUTIL_H_ */

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
@@ -57,27 +57,56 @@ _local_command(const char *command, PQExpBufferData *outputbuf, bool simple, int
 	char		output[MAXLEN];
 	int			retval = 0;
 	bool		success;
+	char		tmpfile_path[MAXPGPATH];
+	const char *tmpdir = getenv("TMPDIR");
+	int			fd;
+	PQExpBufferData command_final;
 
-	log_verbose(LOG_DEBUG, "executing:\n  %s", command);
+	if (!tmpdir)
+		tmpdir = "/tmp";
+
+	maxpath_snprintf(tmpfile_path, "%s/repmgr_command.XXXXXX",
+					 tmpdir);
+
+	fd = mkstemp(tmpfile_path);
+
+	if (fd < 1)
+	{
+		log_error(_("unable to open temporary file"));
+		return false;
+	}
+
+	initPQExpBuffer(&command_final);
+	appendPQExpBufferStr(&command_final, command);
+
+	appendPQExpBuffer(&command_final, " 2>%s", tmpfile_path);
+
+	log_verbose(LOG_DEBUG, "executing:\n  %s", command_final.data);
 
 	if (outputbuf == NULL)
 	{
-		retval = system(command);
+		retval = system(command_final.data);
+		termPQExpBuffer(&command_final);
 
 		if (return_value != NULL)
 			*return_value = WEXITSTATUS(retval);
 
+		close(fd);
+
 		return (retval == 0) ? true : false;
 	}
 
-	fp = popen(command, "r");
+	fp = popen(command_final.data, "r");
 
 	if (fp == NULL)
 	{
-		log_error(_("unable to execute local command:\n%s"), command);
+		log_error(_("unable to execute local command:\n%s"), command_final.data);
+		termPQExpBuffer(&command_final);
+		close(fd);
 		return false;
 	}
 
+	termPQExpBuffer(&command_final);
 
 	while (fgets(output, MAXLEN, fp) != NULL)
 	{
@@ -91,11 +120,32 @@ _local_command(const char *command, PQExpBufferData *outputbuf, bool simple, int
 
 	retval = pclose(fp);
 
-	/*  */
+	/* 141 = SIGPIPE */
 	success = (WEXITSTATUS(retval) == 0 || WEXITSTATUS(retval) == 141) ? true : false;
 
 	log_verbose(LOG_DEBUG, "result of command was %i (%i)", WEXITSTATUS(retval), retval);
 
+	/*
+	 * Append any captured STDERR output
+	 */
+
+	fp = fopen(tmpfile_path, "r");
+
+	/*
+	 * Not critical if we can't open the file
+	 */
+	if (fp != NULL)
+	{
+		while (fgets(output, MAXLEN, fp) != NULL)
+		{
+			appendPQExpBufferStr(outputbuf, output);
+		}
+
+		fclose(fp);
+	}
+
+	unlink(tmpfile_path);
+
 	if (return_value != NULL)
 		*return_value = WEXITSTATUS(retval);
 
@@ -104,6 +154,7 @@ _local_command(const char *command, PQExpBufferData *outputbuf, bool simple, int
 	else
 		log_verbose(LOG_DEBUG, "local_command(): no output returned");
 
+
 	return success;
 }
 
@@ -118,28 +169,13 @@ remote_command(const char *host, const char *user, const char *command, const ch
 {
 	FILE	   *fp;
 	PQExpBufferData ssh_command;
-	PQExpBufferData ssh_host;
 
 	char		output[MAXLEN] = "";
 
-	initPQExpBuffer(&ssh_host);
-
-	if (*user != '\0')
-	{
-		appendPQExpBuffer(&ssh_host, "%s@", user);
-	}
-
-	appendPQExpBufferStr(&ssh_host, host);
 
 	initPQExpBuffer(&ssh_command);
 
-	appendPQExpBuffer(&ssh_command,
-					  "ssh -o Batchmode=yes %s %s %s",
-					  ssh_options,
-					  ssh_host.data,
-					  command);
-
-	termPQExpBuffer(&ssh_host);
+	make_remote_command(host, user, command, ssh_options, &ssh_command);
 
 	log_debug("remote_command():\n  %s", ssh_command.data);
 
@@ -187,6 +223,32 @@ remote_command(const char *host, const char *user, const char *command, const ch
 }
 
 
+void
+make_remote_command(const char *host, const char *user, const char *command, const char *ssh_options, PQExpBufferData *ssh_command)
+{
+	PQExpBufferData ssh_host;
+
+	initPQExpBuffer(&ssh_host);
+
+	if (*user != '\0')
+	{
+		appendPQExpBuffer(&ssh_host, "%s@", user);
+	}
+
+	appendPQExpBufferStr(&ssh_host, host);
+
+
+	appendPQExpBuffer(ssh_command,
+					  "ssh -o Batchmode=yes %s %s %s",
+					  ssh_options,
+					  ssh_host.data,
+					  command);
+
+	termPQExpBuffer(&ssh_host);
+
+}
+
+
 pid_t
 disable_wal_receiver(PGconn *conn)
 {

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
@@ -24,6 +24,7 @@ extern bool local_command_return_value(const char *command, PQExpBufferData *out
 extern bool local_command_simple(const char *command, PQExpBufferData *outputbuf);
 
 extern bool remote_command(const char *host, const char *user, const char *command, const char *ssh_options, PQExpBufferData *outputbuf);
+extern void make_remote_command(const char *host, const char *user, const char *command, const char *ssh_options, PQExpBufferData *ssh_command);
 
 extern pid_t disable_wal_receiver(PGconn *conn);
 extern pid_t enable_wal_receiver(PGconn *conn, bool wait_startup);

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