doc: link to main documentation section about RemoveIPC

Per suggestion in GitHub #705.

.gitignore

@@ -53,3 +53,6 @@ repmgr
 repmgrd
 repmgr4
 repmgrd4
+
+# generated files
+configfile-scan.c

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

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2019, 2ndQuadrant Limited
+Copyright (c) 2010-2021, EnterpriseDB Corporation
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

FAQ.md

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

HISTORY

@@ -1,4 +1,81 @@
-4.4     2019-??-??
+5.2.2.  2021-??-??
+        standby clone: set "slot_name" in node record if required (Ian)
+        node rejoin: emit rejoin target note information as NOTICE (Ian)
+        repmgrd: ensure short option "-s" is accepted (Ian)
+
+5.2.1   2020-12-07
+        config: fix parsing of "replication_type"; GitHub #672 (Ian)
+        standby clone: handle missing "postgresql.auto.conf" (Ian)
+        standby clone: add option --recovery-min-apply-delay (Ian)
+        standby clone: fix data directory permissions handling for
+          PostgreSQL 11 and later (Ian)
+        repmgrd: prevent termination when local node not available and
+          standby_disconnect_on_failover; GitHub #675 (Ian)
+        repmgrd: ensure reconnect_interval" is correctly handled;
+          GitHub #673 (Ian)
+
+5.2.0   2020-10-22
+        general: add support for PostgreSQL 13 (Ian)
+        general: remove support for PostgreSQL 9.3 (Ian)
+        config: add support for file inclusion directives (Ian)
+        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 executing
+          "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)
+        general: parse configuration file using flex (Ian)
+        repmgr: rename "repmgr daemon ..." commands to "repmgr service ..." (Ian)
+        repmgr: improve data directory check (Ian)
+        repmgr: improve extension check during "standby clone" (Ian)
+		repmgr: pass provided log level when executing repmgr remotely (Ian)
+        repmgrd: fix handling of upstream node change check (Ian)
+
+4.4     2019-06-27
         repmgr: improve "daemon status" output (Ian)
         repmgr: add "--siblings-follow" option to "standby promote" (Ian)
         repmgr: add "--repmgrd-force-unpause" option to "standby switchover" (Ian)
@@ -6,6 +83,8 @@
           an existing directory is being overwritten (Ian)
         repmgr: improve "--dry-run" behaviour for "standby promote" and
           "standby switchover" (Ian)
+        repmgr: when running "standby clone" with the "--upstream-conninfo" option
+          ensure that "application_name" is set correctly in "primary_conninfo" (Ian)
         repmgr: ensure "--dry-run" together with --force when running "standby clone"
           in barman mode does not modify an existing data directory (Ian)
         repmgr: improve "--dry-run" output when running "standby clone" in
@@ -21,6 +100,8 @@
         repmgr: prevent a witness server being registered on the cluster primary (John)
         repmgr: ensure BDR2-specific functionality cannot be used on
           BDR3 and later (Ian)
+        repmgr: canonicalize the data directory path (Ian)
+        repmgr: note that "standby follow" requires a primary to be available (Ian)
         repmgrd: monitor standbys attached to primary (Ian)
         repmgrd: add "primary visibility consensus" functionality (Ian)
         repmgrd: fix memory leak which occurs while the monitored PostgreSQL

Makefile.global.in

@@ -2,6 +2,7 @@
 # Makefile.global.in
 # @configure_input@
 
+
 # Can only be built using pgxs
 USE_PGXS=1
 
@@ -14,6 +15,9 @@ ifeq ($(vpath_build),yes)
 	VPATH := $(repmgr_abs_srcdir)/$(repmgr_subdir)
 	USE_VPATH :=$(VPATH)
 endif
+
+SED=@SED@
+
 GIT_WORK_TREE=${repmgr_abs_srcdir}
 GIT_DIR=${repmgr_abs_srcdir}/.git
 export GIT_DIR
@@ -24,4 +28,13 @@ include $(PGXS)
 -include ${repmgr_abs_srcdir}/Makefile.custom
 
 REPMGR_VERSION=$(shell awk '/^\#define REPMGR_VERSION / { print $3; }' ${repmgr_abs_srcdir}/repmgr_version.h.in | cut -d '"' -f 2)
+REPMGR_RELEASE_DATE=$(shell awk '/^\#define REPMGR_RELEASE_DATE / { print $3; }' ${repmgr_abs_srcdir}/repmgr_version.h.in | cut -d '"' -f 2)
 
+FLEX = flex
+
+##########################################################################
+#
+# Global targets and rules
+
+%.c: %.l
+	$(FLEX) $(FLEXFLAGS) -o'$@' $<

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 \
@@ -19,7 +21,13 @@ DATA = \
   repmgr--4.2--4.3.sql \
   repmgr--4.3.sql \
   repmgr--4.3--4.4.sql \
-  repmgr--4.4.sql
+  repmgr--4.4.sql \
+  repmgr--4.4--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
 
@@ -51,21 +59,27 @@ $(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-daemon.o \
+	repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
-	configfile.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
+	configdata.o configfile.o configfile-scan.o log.o strutil.o controldata.o dirutil.o compat.o \
-REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.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
-	sed '0,/REPMGR_VERSION_DATE/s,\(REPMGR_VERSION_DATE\).*,\1 "$(DATE)",' $< >$@
+	$(SED) -E 's/REPMGR_VERSION_DATE.*""/REPMGR_VERSION_DATE "$(DATE)"/' $< >$@; \
+	$(SED) -i -E 's/PG_ACTUAL_VERSION_NUM/PG_ACTUAL_VERSION_NUM $(VERSION_NUM)/' $@
+
+configfile-scan.c: configfile-scan.l
 
 $(REPMGR_CLIENT_OBJS): repmgr-client.h repmgr_version.h
 
 repmgr: $(REPMGR_CLIENT_OBJS)
-	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGR_CLIENT_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
 
 repmgrd: $(REPMGRD_OBJS)
-	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o $@$(X)
+	$(CC) $(CFLAGS) $(REPMGRD_OBJS) $(libpq_pgport) $(LDFLAGS) $(LDFLAGS_EX) -o $@$(X)
 
 $(REPMGR_CLIENT_OBJS): $(HEADERS)
 $(REPMGRD_OBJS): $(HEADERS)
@@ -98,6 +112,7 @@ maintainer-clean: additional-maintainer-clean
 
 additional-clean:
 	rm -f *.o
+	rm -f repmgr_version.h
 	$(MAKE) -C doc clean
 
 additional-maintainer-clean: clean

README.md

@@ -7,32 +7,31 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-`repmgr 4` is a complete rewrite of the existing `repmgr` codebase, allowing
+The most recent `repmgr` version (5.2.1) supports all PostgreSQL versions from
-the use of all of the latest features in PostgreSQL replication.
+9.5 to 13. PostgreSQL 9.4 is also supported, with some restrictions.
-
-PostgreSQL 11, 10, 9.6 and 9.5 are fully supported.
-PostgreSQL 9.4 and 9.3 are supported, with some restrictions.
-
-`repmgr` is distributed under the GNU GPL 3 and maintained by 2ndQuadrant.
-
-### BDR support
-
-`repmgr 4` supports monitoring of a two-node BDR 2.0 cluster on PostgreSQL 9.6
-only. Note that BDR 2.0 is not publicly available; please contact 2ndQuadrant
-for details.
 
+`repmgr` is distributed under the GNU GPL 3 and maintained by EnterpriseDB.
 
 Documentation
 -------------
 
-The main `repmgr` documentation is available here:
+The full `repmgr` documentation is available here:
 
 > [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
-The `README` file for `repmgr` 3.x is available here:
+The old `README` file for `repmgr` 3.x is available here:
 
-> https://github.com/2ndQuadrant/repmgr/blob/REL3_3_STABLE/README.md
+> https://github.com/EnterpriseDB/repmgr/blob/REL3_3_STABLE/README.md
 
+Note that the `repmgr` 3.x series is no longer supported and contains known bugs;
+please upgrade to the [current repmgr version](https://repmgr.org/docs/current/appendix-release-notes.html)
+as soon as possible.
+
+Versions
+--------
+
+For an overview of `repmgr` versions and PostgreSQL compatibility, see the
+[repmgr compatibility matrix](https://repmgr.org/docs/current/install-requirements.html#INSTALL-COMPATIBILITY-MATRIX).
 
 Files
 ------
@@ -56,11 +55,11 @@ Directories
 Support and Assistance
 ----------------------
 
-2ndQuadrant provides 24x7 production support for `repmgr`, including
+EnterpriseDB provides 24x7 production support for `repmgr`, including
 configuration assistance, installation verification and training for
 running a robust replication cluster. For further details see:
 
-* https://2ndquadrant.com/en/support/
+* [EDB Support Services](https://www.enterprisedb.com/support/postgresql-support-overview-get-the-most-out-of-postgresql)
 
 There is a mailing list/forum to discuss contributions or issues:
 
@@ -70,21 +69,12 @@ The IRC channel #repmgr is registered with freenode.
 
 Please report bugs and other issues to:
 
-* https://github.com/2ndQuadrant/repmgr
+* https://github.com/EnterpriseDB/repmgr
 
 Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
-news are always welcome. Send us an email at info@2ndQuadrant.com, or
+news are always welcome.
-send a postcard to
-
-    repmgr
-    c/o 2ndQuadrant
-    7200 The Quorum
-    Oxford Business Park North
-    Oxford
-    OX4 2JZ
-    United Kingdom
 
 Thanks from the repmgr core team.
 
@@ -98,7 +88,5 @@ Further reading
 ---------------
 
 * [repmgr documentation](https://repmgr.org/docs/current/index.html)
-* https://blog.2ndquadrant.com/repmgr-3-2-is-here-barman-support-brand-new-high-availability-features/
+* [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 1](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-1/)
-* https://blog.2ndquadrant.com/improvements-in-repmgr-3-1-4/
+* [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 2](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-2/)
-* https://blog.2ndquadrant.com/managing-useful-clusters-repmgr/
-* https://blog.2ndquadrant.com/easier_postgresql_90_clusters/

TODO.md

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

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) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

compat.h

@@ -1,6 +1,6 @@
 /*
  * compat.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

configdata.c

@@ -0,0 +1,936 @@
+/*
+ * configdata.c - contains structs with parsed configuration data
+ *
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * 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_REPLICATION_TYPE,
+		{ .replicationtypeptr = &config_file_options.replication_type },
+		{ .replicationtypedefault = DEFAULT_REPLICATION_TYPE },
+		{},
+		{},
+		{}
+	},
+
+	/* ================
+	 * 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

@@ -0,0 +1,644 @@
+/*
+ * Scanner for the configuration file
+ */
+
+%{
+
+#include <setjmp.h>
+#include <sys/stat.h>
+#include <dirent.h>
+
+#include "repmgr.h"
+#include "configfile.h"
+
+/*
+ * flex emits a yy_fatal_error() function that it calls in response to
+ * critical errors like malloc failure, file I/O errors, and detection of
+ * internal inconsistency.  That function prints a message and calls exit().
+ * Mutate it to instead call our handler, which jumps out of the parser.
+ */
+#undef fprintf
+#define fprintf(file, fmt, msg) CONF_flex_fatal(msg)
+
+enum
+{
+	CONF_ID = 1,
+	CONF_STRING = 2,
+	CONF_INTEGER = 3,
+	CONF_REAL = 4,
+	CONF_EQUALS = 5,
+	CONF_UNQUOTED_STRING = 6,
+	CONF_QUALIFIED_ID = 7,
+	CONF_EOL = 99,
+	CONF_ERROR = 100
+};
+
+static unsigned int ConfigFileLineno;
+static const char *CONF_flex_fatal_errmsg;
+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(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);
+
+%}
+
+%option 8bit
+%option never-interactive
+%option nodefault
+%option noinput
+%option nounput
+%option noyywrap
+%option warn
+%option prefix="CONF_yy"
+
+
+SIGN			("-"|"+")
+DIGIT			[0-9]
+HEXDIGIT		[0-9a-fA-F]
+
+UNIT_LETTER		[a-zA-Z]
+
+INTEGER			{SIGN}?({DIGIT}+|0x{HEXDIGIT}+){UNIT_LETTER}*
+
+EXPONENT		[Ee]{SIGN}?{DIGIT}+
+REAL			{SIGN}?{DIGIT}*"."{DIGIT}*{EXPONENT}?
+
+LETTER			[A-Za-z_\200-\377]
+LETTER_OR_DIGIT [A-Za-z_0-9\200-\377]
+
+ID				{LETTER}{LETTER_OR_DIGIT}*
+QUALIFIED_ID	{ID}"."{ID}
+
+UNQUOTED_STRING {LETTER}({LETTER_OR_DIGIT}|[-._:/])*
+STRING			\'([^'\\\n]|\\.|\'\')*\'
+
+%%
+
+\n				ConfigFileLineno++; return CONF_EOL;
+[ \t\r]+		/* eat whitespace */
+#.*				/* eat comment (.* matches anything until newline) */
+
+{ID}			return CONF_ID;
+{QUALIFIED_ID}	return CONF_QUALIFIED_ID;
+{STRING}		return CONF_STRING;
+{UNQUOTED_STRING} return CONF_UNQUOTED_STRING;
+{INTEGER}		return CONF_INTEGER;
+{REAL}			return CONF_REAL;
+=				return CONF_EQUALS;
+
+.				return CONF_ERROR;
+
+%%
+
+
+extern bool
+ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList *error_list, ItemList *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, bool strict, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
+{
+	return ProcessConfigFile(base_dir, config_file, NULL, strict, 0, contents, error_list, 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)
+{
+	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;
+	sigjmp_buf	flex_fatal_jmp;
+	int			errorcount;
+	int			token;
+
+	if (sigsetjmp(flex_fatal_jmp, 1) == 0)
+	{
+		CONF_flex_fatal_jmp = &flex_fatal_jmp;
+	}
+	else
+	{
+		/*
+		 * Regain control after a fatal, internal flex error.  It may have
+		 * corrupted parser state.  Consequently, abandon the file, but trust
+		 * that the state remains sane enough for yy_delete_buffer().
+		 */
+		item_list_append_format(error_list,
+								"%s at file \"%s\" line %u",
+								CONF_flex_fatal_errmsg, config_file, ConfigFileLineno);
+		OK = false;
+		goto cleanup;
+	}
+
+	/*
+	 * Parse
+	 */
+	ConfigFileLineno = 1;
+	errorcount = 0;
+
+	lex_buffer = yy_create_buffer(fp, YY_BUF_SIZE);
+	yy_switch_to_buffer(lex_buffer);
+
+	/* This loop iterates once per logical line */
+	while ((token = yylex()))
+	{
+		char	   *opt_name = NULL;
+		char	   *opt_value = NULL;
+
+		if (token == CONF_EOL)	/* empty or comment line */
+			continue;
+
+		/* first token on line is option name */
+		if (token != CONF_ID && token != CONF_QUALIFIED_ID)
+			goto parse_error;
+		opt_name = pstrdup(yytext);
+
+		/* next we have an optional equal sign; discard if present */
+		token = yylex();
+		if (token == CONF_EQUALS)
+			token = yylex();
+
+		/* now we must have the option value */
+		if (token != CONF_ID &&
+			token != CONF_STRING &&
+			token != CONF_INTEGER &&
+			token != CONF_REAL &&
+			token != CONF_UNQUOTED_STRING)
+			goto parse_error;
+		if (token == CONF_STRING)	/* strip quotes and escapes */
+			opt_value = CONF_scanstr(yytext);
+		else
+			opt_value = pstrdup(yytext);
+
+		/* now we'd like an end of line, or possibly EOF */
+		token = yylex();
+		if (token != CONF_EOL)
+		{
+			if (token != 0)
+				goto parse_error;
+			/* treat EOF like \n for line numbering purposes, cf bug 4752 */
+			ConfigFileLineno++;
+		}
+
+		/* Handle include files */
+		if (base_dir != NULL && strcasecmp(opt_name, "include_dir") == 0)
+		{
+			/*
+			 * 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);
+			}
+
+		}
+
+
+		/* break out of loop if read EOF, else loop for next line */
+		if (token == 0)
+			break;
+		continue;
+
+parse_error:
+		/* release storage if we allocated any on this line */
+		if (opt_name)
+			pfree(opt_name);
+		if (opt_value)
+			pfree(opt_value);
+
+		/* report the error */
+		if (token == CONF_EOL || token == 0)
+		{
+			item_list_append_format(error_list,
+									_("syntax error in file \"%s\" line %u, near end of line"),
+								    config_file, ConfigFileLineno - 1);
+		}
+		else
+		{
+			item_list_append_format(error_list,
+									_("syntax error in file \"%s\" line %u, near token \"%s\""),
+									config_file, ConfigFileLineno, yytext);
+		}
+		OK = false;
+		errorcount++;
+
+		/*
+		 * To avoid producing too much noise when fed a totally bogus file,
+		 * give up after 100 syntax errors per file (an arbitrary number).
+		 * Also, if we're only logging the errors at DEBUG level anyway, might
+		 * as well give up immediately.  (This prevents postmaster children
+		 * from bloating the logs with duplicate complaints.)
+		 */
+		if (errorcount >= 100)
+		{
+			fprintf(stderr,
+ 				   _("too many syntax errors found, abandoning file \"%s\"\n"),
+				   config_file);
+			break;
+		}
+
+		/* resync to next end-of-line or EOF */
+		while (token != CONF_EOL && token != 0)
+			token = yylex();
+		/* break out of loop on EOF */
+		if (token == 0)
+			break;
+	}
+
+cleanup:
+	yy_delete_buffer(lex_buffer);
+
+	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
+ *
+ * Strip the quotes surrounding the given string, and collapse any embedded
+ * '' sequences and backslash escapes.
+ *
+ * the string returned is palloc'd and should eventually be pfree'd by the
+ * caller.
+ */
+static char *
+CONF_scanstr(const char *s)
+{
+	char	   *newStr;
+	int			len,
+				i,
+				j;
+
+	Assert(s != NULL && s[0] == '\'');
+	len = strlen(s);
+	Assert(s != NULL);
+
+	Assert(len >= 2);
+	Assert(s[len - 1] == '\'');
+
+	/* Skip the leading quote; we'll handle the trailing quote below */
+	s++, len--;
+
+	/* Since len still includes trailing quote, this is enough space */
+	newStr = palloc(len);
+
+	for (i = 0, j = 0; i < len; i++)
+	{
+		if (s[i] == '\\')
+		{
+			i++;
+			switch (s[i])
+			{
+				case 'b':
+					newStr[j] = '\b';
+					break;
+				case 'f':
+					newStr[j] = '\f';
+					break;
+				case 'n':
+					newStr[j] = '\n';
+					break;
+				case 'r':
+					newStr[j] = '\r';
+					break;
+				case 't':
+					newStr[j] = '\t';
+					break;
+				case '0':
+				case '1':
+				case '2':
+				case '3':
+				case '4':
+				case '5':
+				case '6':
+				case '7':
+					{
+						int			k;
+						long		octVal = 0;
+
+						for (k = 0;
+							 s[i + k] >= '0' && s[i + k] <= '7' && k < 3;
+							 k++)
+							octVal = (octVal << 3) + (s[i + k] - '0');
+						i += k - 1;
+						newStr[j] = ((char) octVal);
+					}
+					break;
+				default:
+					newStr[j] = s[i];
+					break;
+			}					/* switch */
+		}
+		else if (s[i] == '\'' && s[i + 1] == '\'')
+		{
+			/* doubled quote becomes just one quote */
+			newStr[j] = s[++i];
+		}
+		else
+			newStr[j] = s[i];
+		j++;
+	}
+
+	/* We copied the ending quote to newStr, so replace with \0 */
+	Assert(j > 0 && j <= len);
+	newStr[--j] = '\0';
+
+	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
+ * ParseConfigFp().  Assume all msg arguments point to string constants; this
+ * holds for flex 2.5.31 (earliest we support) and flex 2.5.35 (latest as of
+ * this writing).  Otherwise, we would need to copy the message.
+ *
+ * We return "int" since this takes the place of calls to fprintf().
+*/
+static int
+CONF_flex_fatal(const char *msg)
+{
+	CONF_flex_fatal_errmsg = msg;
+	siglongjmp(*CONF_flex_fatal_jmp, 1);
+	return 0;					/* keep compiler quiet */
+}

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -28,6 +28,12 @@
 /* magic number for use in t_recovery_conf */
 #define TARGET_TIMELINE_LATEST 0
 
+/*
+ * 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"
+
 extern bool config_file_found;
 extern char config_file_path[MAXPGPATH];
 
@@ -44,6 +50,11 @@ typedef enum
 	CHECK_CONNECTION
 } ConnectionCheckType;
 
+typedef enum
+{
+	REPLICATION_TYPE_PHYSICAL
+} ReplicationType;
+
 typedef struct EventNotificationListCell
 {
 	struct EventNotificationListCell *next;
@@ -72,6 +83,58 @@ 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,
+    CONFIG_REPLICATION_TYPE
+} 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;
+		ReplicationType *replicationtypeptr;
+	} val;
+	union {
+		int			intdefault;
+		const char *strdefault;
+		bool		booldefault;
+		failover_mode_opt failovermodedefault;
+		ConnectionCheckType checktypedefault;
+		ReplicationType replicationtypedefault;
+	} 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 */
@@ -83,7 +146,7 @@ typedef struct
 	char		config_directory[MAXPGPATH];
 	char		pg_bindir[MAXPGPATH];
 	char		repmgr_bindir[MAXPGPATH];
-	int			replication_type;
+	ReplicationType	replication_type;
 
 	/* log settings */
 	char		log_level[MAXLEN];
@@ -109,6 +172,7 @@ typedef struct
 	/* standby follow settings */
 	int			primary_follow_timeout;
 	int			standby_follow_timeout;
+	bool		standby_follow_restart;
 
 	/* standby switchover settings */
 	int			shutdown_check_timeout;
@@ -146,6 +210,7 @@ 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;
@@ -155,10 +220,6 @@ 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];
@@ -185,79 +246,35 @@ typedef struct
 	char		rsync_options[MAXLEN];
 	char		ssh_options[MAXLEN];
 
-	/* undocumented test settings */
+	/*
+	 * undocumented settings
+	 *
+	 * These settings are for testing or experimental 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
@@ -314,8 +331,11 @@ 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);
+void		load_config(const char *config_file, bool verbose, bool terse, char *argv0);
-bool		reload_config(t_configuration_options *orig_options, t_server_type server_type);
+bool		reload_config(t_server_type server_type);
+void		dump_config(void);
+
+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);
 
@@ -328,6 +348,9 @@ 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,
@@ -335,11 +358,21 @@ 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_replication_type(ReplicationType type);
 const char *print_connection_check_type(ConnectionCheckType type);
+char 	   *print_event_notification_list(EventNotificationList *list);
+char 	   *print_tablespace_mapping(TablespaceList *tablespacemappingptr);
+
+extern bool modify_auto_conf(const char *data_dir, KeyValueList *items);
+
+extern bool ProcessRepmgrConfigFile(const char *config_file, const char *base_dir, ItemList *error_list, ItemList *warning_list);
+
+extern bool ProcessPostgresConfigFile(const char *config_file, const char *base_dir, bool strict, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
 
 #endif							/* _REPMGR_CONFIGFILE_H_ */

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.4.
+# Generated by GNU Autoconf 2.69 for repmgr 5.2.1.
 #
 # 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) 2010-2021, EnterpriseDB Corporation
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,13 +582,16 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.4'
+PACKAGE_VERSION='5.2.1'
-PACKAGE_STRING='repmgr 4.4'
+PACKAGE_STRING='repmgr 5.2.1'
 PACKAGE_BUGREPORT='repmgr@googlegroups.com'
 PACKAGE_URL='https://repmgr.org/'
 
 ac_subst_vars='LTLIBOBJS
 LIBOBJS
+HAVE_SED
+HAVE_GSED
+HAVE_GNUSED
 vpath_build
 SED
 PG_CONFIG
@@ -1178,7 +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 4.4 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.2.1 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1239,7 +1242,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.4:";;
+     short | recursive ) echo "Configuration of repmgr 5.2.1:";;
    esac
   cat <<\_ACEOF
 
@@ -1313,14 +1316,14 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.4
+repmgr configure 5.2.1
 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) 2010-2021, EnterpriseDB Corporation
 _ACEOF
   exit
 fi
@@ -1332,7 +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 4.4, which was
+It was created by repmgr $as_me 5.2.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1821,7 +1824,7 @@ if test "$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
@@ -1847,6 +1850,133 @@ else
 fi
 
 
+# Extract the first word of "gnused", so it can be a program name with args.
+set dummy gnused; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_GNUSED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_GNUSED"; then
+  ac_cv_prog_HAVE_GNUSED="$HAVE_GNUSED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_GNUSED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_GNUSED" && ac_cv_prog_HAVE_GNUSED="no"
+fi
+fi
+HAVE_GNUSED=$ac_cv_prog_HAVE_GNUSED
+if test -n "$HAVE_GNUSED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_GNUSED" >&5
+$as_echo "$HAVE_GNUSED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+# Extract the first word of "gsed", so it can be a program name with args.
+set dummy gsed; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_GSED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_GSED"; then
+  ac_cv_prog_HAVE_GSED="$HAVE_GSED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_GSED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_GSED" && ac_cv_prog_HAVE_GSED="no"
+fi
+fi
+HAVE_GSED=$ac_cv_prog_HAVE_GSED
+if test -n "$HAVE_GSED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_GSED" >&5
+$as_echo "$HAVE_GSED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+# Extract the first word of "sed", so it can be a program name with args.
+set dummy sed; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_SED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_SED"; then
+  ac_cv_prog_HAVE_SED="$HAVE_SED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_SED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_SED" && ac_cv_prog_HAVE_SED="no"
+fi
+fi
+HAVE_SED=$ac_cv_prog_HAVE_SED
+if test -n "$HAVE_SED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_SED" >&5
+$as_echo "$HAVE_SED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+
+if test "$HAVE_GNUSED" = yes; then
+ SED=gnused
+else
+ if test "$HAVE_GSED" = yes; then
+  SED=gsed
+ else
+  SED=sed
+ fi
+fi
+
+
+
 ac_config_files="$ac_config_files Makefile"
 
 ac_config_files="$ac_config_files Makefile.global"
@@ -2357,7 +2487,7 @@ cat >>$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 4.4, which was
+This file was extended by repmgr $as_me 5.2.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2420,7 +2550,7 @@ _ACEOF
 cat >>$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 4.4
+repmgr config.status 5.2.1
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [4.4], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.2.1], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2021, EnterpriseDB Corporation])
 
 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
@@ -57,6 +57,22 @@ else
 fi
 AC_SUBST(vpath_build)
 
+AC_CHECK_PROG(HAVE_GNUSED,gnused,yes,no)
+AC_CHECK_PROG(HAVE_GSED,gsed,yes,no)
+AC_CHECK_PROG(HAVE_SED,sed,yes,no)
+
+if test "$HAVE_GNUSED" = yes; then
+ SED=gnused
+else
+ if test "$HAVE_GSED" = yes; then
+  SED=gsed
+ else
+  SED=sed
+ fi
+fi
+AC_SUBST(SED)
+
+
 AC_CONFIG_FILES([Makefile])
 AC_CONFIG_FILES([Makefile.global])
 AC_OUTPUT

contrib/convert-config.pl

@@ -73,7 +73,16 @@ while(<$fh>) {
         if ($param eq 'data_directory') {
             $data_directory_found = 1;
         }
-        push @outp, $line;
+
+        # Don't quote numbers
+        if ($value =~ /^\d+$/) {
+            push @outp, sprintf(q|%s=%s|, $param, $value);
+        }
+        # Quote everything else
+        else {
+            $value =~ s/'/''/g;
+            push @outp, sprintf(q|%s='%s'|, $param, $value);
+        }
     }
 }
 
@@ -83,6 +92,6 @@ print join("\n", @outp);
 print "\n";
 
 if ($data_directory_found == 0) {
-    print "data_directory=\n";
+    print "data_directory=''\n";
 }
 

controldata.c

@@ -2,11 +2,11 @@
  * controldata.c - functions for reading the pg_control file
  *
  * The functions provided here enable repmgr to read a pg_control file
- * in a version-indepent way, even if the PostgreSQL instance is not
+ * in a version-independent way, even if the PostgreSQL instance is not
  * running. For that reason we can't use on the pg_control_*() functions
  * provided in PostgreSQL 9.6 and later.
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -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
+bool
-get_db_state(const char *data_directory)
+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 >= 120000)
-	if (version_num >= 90500)
+	{
+#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)
 	{
@@ -312,6 +323,7 @@ get_controlfile(const char *DataDir)
 
 	if (version_num >= 120000)
 	{
+#if PG_ACTUAL_VERSION_NUM >= 120000
 		ControlFileData12 *ptr = (struct ControlFileData12 *)ControlFileDataPtr;
 		control_file_info->system_identifier = ptr->system_identifier;
 		control_file_info->state = ptr->state;
@@ -320,6 +332,10 @@ get_controlfile(const char *DataDir)
 		control_file_info->timeline = ptr->checkPointCopy.ThisTimeLineID;
 		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
 		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
+#else
+		fprintf(stderr, "ERROR: please use a repmgr version built for PostgreSQL 12 or later\n");
+		exit(ERR_BAD_CONFIG);
+#endif
 	}
 	else if (version_num >= 110000)
 	{
@@ -354,17 +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) EnterpriseDB Corporation, 2010-2021
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -12,6 +12,7 @@
 #include "postgres_fe.h"
 #include "catalog/pg_control.h"
 
+
 #define MAX_VERSION_STRING 24
 /*
  * A simplified representation of pg_control containing only those fields
@@ -30,9 +31,7 @@ typedef struct
 } ControlFileInfo;
 
 
-
+typedef struct CheckPoint94
-/* Same for 9.3, 9.4 */
-typedef struct CheckPoint93
 {
 	XLogRecPtr	redo;			/* next RecPtr available when we began to
 								 * create CheckPoint (i.e. REDO start point) */
@@ -52,10 +51,10 @@ typedef struct CheckPoint93
 	pg_time_t	time;			/* time stamp of checkpoint */
 
 	TransactionId oldestActiveXid;
-} CheckPoint93;
+} CheckPoint94;
 
 
-/* Same for 9.5, 9.6, 10, HEAD */
+/* Same for 9.5, 9.6, 10, 11 */
 typedef struct CheckPoint95
 {
 	XLogRecPtr	redo;			/* next RecPtr available when we began to
@@ -83,66 +82,51 @@ typedef struct CheckPoint95
 } CheckPoint95;
 
 
-typedef struct ControlFileData93
+#if PG_ACTUAL_VERSION_NUM >= 120000
-{
-	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:
+ * Following fields removed in PostgreSQL 12;
  *
- * 	int			max_worker_processes;
+ *   uint32 nextXidEpoch;
+ *   TransactionId nextXid;
+ *
+ * and replaced by:
+ *
+ *   FullTransactionId nextFullXid;
  */
 
+typedef struct CheckPoint12
+{
+	XLogRecPtr	redo;			/* next RecPtr available when we began to
+								 * create CheckPoint (i.e. REDO start point) */
+	TimeLineID	ThisTimeLineID; /* current TLI */
+	TimeLineID	PrevTimeLineID; /* previous TLI, if this record begins a new
+								 * timeline (equals ThisTimeLineID otherwise) */
+	bool		fullPageWrites; /* current full_page_writes */
+	FullTransactionId nextFullXid;	/* next free full transaction ID */
+	Oid			nextOid;		/* next free OID */
+	MultiXactId nextMulti;		/* next free MultiXactId */
+	MultiXactOffset nextMultiOffset;	/* next free MultiXact offset */
+	TransactionId oldestXid;	/* cluster-wide minimum datfrozenxid */
+	Oid			oldestXidDB;	/* database with minimum datfrozenxid */
+	MultiXactId oldestMulti;	/* cluster-wide minimum datminmxid */
+	Oid			oldestMultiDB;	/* database with minimum datminmxid */
+	pg_time_t	time;			/* time stamp of checkpoint */
+	TransactionId oldestCommitTsXid;	/* oldest Xid with valid commit
+										 * timestamp */
+	TransactionId newestCommitTsXid;	/* newest Xid with valid commit
+										 * timestamp */
+
+	/*
+	 * Oldest XID still running. This is only needed to initialize hot standby
+	 * mode from an online checkpoint, so we only bother calculating this for
+	 * online checkpoints and only when wal_level is replica. Otherwise it's
+	 * set to InvalidTransactionId.
+	 */
+	TransactionId oldestActiveXid;
+} CheckPoint12;
+#endif
+
+
 typedef struct ControlFileData94
 {
 	uint64		system_identifier;
@@ -155,7 +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 */
 
@@ -333,19 +317,11 @@ typedef struct ControlFileData11
 } ControlFileData11;
 
 
+#if PG_ACTUAL_VERSION_NUM >= 120000
 /*
  * Following field added in Pg12:
  *
  *   int max_wal_senders;
- *
- * Following fields removed:
- *
- *   uint32 nextXidEpoch;
- *   TransactionId nextXid;
- *
- * and replaced by:
- *
- *   FullTransactionId nextFullXid;
  */
 
 typedef struct ControlFileData12
@@ -359,7 +335,7 @@ typedef struct ControlFileData12
 	pg_time_t	time;			/* time stamp of last pg_control update */
 	XLogRecPtr	checkPoint;		/* last check point record ptr */
 
-	CheckPoint	checkPointCopy; /* copy of last check point record */
+	CheckPoint12	checkPointCopy; /* copy of last check point record */
 
 	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
 
@@ -398,9 +374,10 @@ typedef struct ControlFileData12
 
 	uint32		data_checksum_version;
 } 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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -60,11 +60,6 @@
 	"NULL AS attached "
 
 
-
-#define BDR2_NODES_COLUMNS "node_sysid, node_timeline, node_dboid, node_name, node_local_dsn, ''"
-#define BDR3_NODES_COLUMNS "ns.node_id, 0, 0, ns.node_name, ns.interface_connstr, ns.peer_state_name"
-
-
 #define ERRBUFF_SIZE 512
 
 typedef enum
@@ -72,8 +67,7 @@ typedef enum
 	UNKNOWN = 0,
 	PRIMARY,
 	STANDBY,
-	WITNESS,
+	WITNESS
-	BDR
 } t_server_type;
 
 typedef enum
@@ -125,14 +119,21 @@ typedef enum
 
 typedef enum
 {
+	/* unable to query "pg_stat_replication" or other error */
 	NODE_ATTACHED_UNKNOWN = -1,
-	NODE_DETACHED,
+	/* node has record in "pg_stat_replication" and state is not "streaming" */
-	NODE_ATTACHED
+	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 */
@@ -432,12 +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);
 void		close_connection(PGconn **conn);
 
 /* conninfo manipulation functions */
@@ -450,6 +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);
@@ -466,6 +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);
@@ -481,6 +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);
@@ -520,6 +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);
@@ -558,10 +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 */
@@ -613,35 +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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -109,9 +109,56 @@ create_dir(const char *path)
 
 
 bool
-set_dir_permissions(const char *path)
+set_dir_permissions(const char *path, int server_version_num)
 {
-	return (chmod(path, 0700) != 0) ? false : true;
+	struct stat stat_buf;
+	bool no_group_access =
+		(server_version_num != UNKNOWN_SERVER_VERSION_NUM) &&
+		(server_version_num < 110000);
+	/*
+	 * At this point the path should exist, so this check is very
+	 * much just-in-case.
+	 */
+	if (stat(path, &stat_buf) != 0)
+	{
+		if (errno == ENOENT)
+		{
+			log_warning(_("directory \"%s\" does not exist"), path);
+		}
+		else
+		{
+			log_warning(_("could not read permissions of directory \"%s\""),
+						path);
+			log_detail("%s", strerror(errno));
+		}
+
+		return false;
+	}
+
+	/*
+	 * If mode is not 0700 or 0750, attempt to change.
+	 */
+	if ((no_group_access == true  && (stat_buf.st_mode & (S_IRWXG | S_IRWXO)))
+	 || (no_group_access == false && (stat_buf.st_mode & (S_IWGRP | S_IRWXO))))
+	{
+		/*
+		 * Currently we default to 0700.
+		 * There is no facility to override this directly,
+		 * but the user can manually create the directory with
+		 * the desired permissions.
+		 */
+
+		if (chmod(path, 0700) != 0) {
+			log_error(_("unable to change permissions of directory \"%s\""), path);
+			log_detail("%s", strerror(errno));
+			return false;
+		}
+
+		return true;
+	}
+
+	/* Leave as-is */
+	return true;
 }
 
 
@@ -158,7 +205,7 @@ mkdir_p(char *path, mode_t omode)
 			/*
 			 * POSIX 1003.2: For each dir operand that does not name an
 			 * existing directory, effects equivalent to those caused by the
-			 * following command shall occcur:
+			 * following command shall occur:
 			 *
 			 * mkdir -p -m $(umask -S),u+wx $(dirname dir) && mkdir [-m mode]
 			 * dir
@@ -242,7 +289,7 @@ is_pg_running(const char *path)
 	{
 		/*
 		 * No PID file - PostgreSQL shouldn't be running. From 9.3 (the
-		 * earliesty version we care about) removal of the PID file will
+		 * earliest version we care about) removal of the PID file will
 		 * cause the postmaster to shut down, so it's highly unlikely
 		 * that PostgreSQL will still be running.
 		 */
@@ -303,7 +350,7 @@ create_pg_dir(const char *path, bool force)
 	switch (check_dir(path))
 	{
 		case DIR_NOENT:
-			/* directory does not exist, attempt to create it */
+			/* Directory does not exist, attempt to create it. */
 			log_info(_("creating directory \"%s\"..."), path);
 
 			if (!create_dir(path))
@@ -314,14 +361,23 @@ create_pg_dir(const char *path, bool force)
 			}
 			break;
 		case DIR_EMPTY:
-			/* exists but empty, fix permissions and use it */
+			/*
+			 * Directory exists but empty, fix permissions and use it.
+			 *
+			 * Note that at this point the caller might not know the server
+			 * version number, so in this case "set_dir_permissions()" will
+			 * accept 0750 as a valid setting. As this is invalid in Pg10 and
+			 * earlier,  the caller should call "set_dir_permissions()" again
+			 * when it has the number.
+			 *
+			 * We need to do the permissions check here in any case to catch
+			 * fatal permissions early.
+			 */
 			log_info(_("checking and correcting permissions on existing directory \"%s\""),
 					 path);
 
-			if (!set_dir_permissions(path))
+			if (!set_dir_permissions(path, UNKNOWN_SERVER_VERSION_NUM))
 			{
-				log_error(_("unable to change permissions of directory \"%s\""), path);
-				log_detail("%s", strerror(errno));
 				return false;
 			}
 			break;

dirutil.h

@@ -1,6 +1,6 @@
 /*
  * dirutil.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -35,7 +35,7 @@ typedef enum
 } PgDirState;
 
 extern int	mkdir_p(char *path, mode_t omode);
-extern bool set_dir_permissions(const char *path);
+extern bool set_dir_permissions(const char *path, int server_version_num);
 
 extern DataDirState	check_dir(const char *path);
 extern bool create_dir(const char *path);

doc/Makefile

@@ -31,6 +31,7 @@ ALLXML := $(wildcard $(srcdir)/*.xml) $(GENERATED_XML)
 version.xml: $(repmgr_top_builddir)/repmgr_version.h
 	{ \
 	  echo "<!ENTITY repmgrversion \"$(REPMGR_VERSION)\">"; \
+	  echo "<!ENTITY releasedate \"$(REPMGR_RELEASE_DATE)\">"; \
 	} > $@
 
 ##
@@ -94,6 +95,8 @@ clean:
 	rm -f repmgr.html
 	rm -f repmgr-A4.pdf
 	rm -f repmgr-US.pdf
+	rm -f *.fo
+	rm -f html/*
 
 maintainer-clean:
 	rm -rf html

doc/appendix-faq.xml

@@ -3,437 +3,486 @@
   <title>FAQ (Frequently Asked Questions)</title>
 
   <indexterm>
-   <primary>FAQ (Frequently Asked Questions)</primary>
+    <primary>FAQ (Frequently Asked Questions)</primary>
   </indexterm>
 
- <sect1 id="faq-general" xreflabel="General">
+  <sect1 id="faq-general" xreflabel="General">
-  <title>General</title>
+    <title>General</title>
 
-  <sect2 id="faq-xrepmgr-version-diff" xreflabel="Version differences">
+    <sect2 id="faq-xrepmgr-version-diff" xreflabel="Version differences">
-    <title>What's the difference between the repmgr versions?</title>
+      <title>What's the difference between the repmgr versions?</title>
-    <para>
+      <para>
-      &repmgr; 4 is a complete rewrite of the existing &repmgr; code base
+        &repmgr; 4 is a complete rewrite of the previous &repmgr; code base
-      and implements &repmgr; as a PostgreSQL extension. It
+        and implements &repmgr; as a PostgreSQL extension. It
-      supports all PostgreSQL versions from 9.3 (although some &repmgr;
+        supports all PostgreSQL versions from 9.3 (although some &repmgr;
-      features are not available for PostgreSQL 9.3 and 9.4).
+        features are not available for PostgreSQL 9.3 and 9.4).
-     </para>
+      </para>
-     <para>
+      <note>
-      &repmgr; 3.x builds on the improved replication facilities added
+        <para>
-      in PostgreSQL 9.3, as well as improved automated failover support
+          &repmgr; 5 is fundamentally the same code base as &repmgr; 4, but provides
-      via &repmgrd;, and is not compatible with PostgreSQL 9.2
+          support for the revised replication configuration mechanism in PostgreSQL 12.
-      and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
+        </para>
-      series is no longer maintained.
+        <para>
-     </para>
+          Support for PostgreSQL 9.3 is no longer available from &repmgr; 5.2.
-     <para>
+        </para>
-      &repmgr; 2.x supports PostgreSQL 9.0 ~ 9.3. While it is compatible
+      </note>
-      with PostgreSQL 9.3, we recommend using repmgr 4.x. &repmgr; 2.x is
+      <para>
-      no longer maintained.
+        &repmgr; 3.x builds on the improved replication facilities added
-     </para>
+        in PostgreSQL 9.3, as well as improved automated failover support
-     <para>
+        via &repmgrd;, and is not compatible with PostgreSQL 9.2
-       See also <link linkend="install-compatibility-matrix">&repmgr; compatibility matrix</link>
+        and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
-       and <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
+        series is no longer maintained.
-     </para>
+      </para>
-  </sect2>
+      <para>
+        &repmgr; 2.x supports PostgreSQL 9.0 ~ 9.3. While it is compatible
+        with PostgreSQL 9.3, we recommend using repmgr 4.x. &repmgr; 2.x is
+        no longer maintained.
+      </para>
+      <para>
+        See also <link linkend="install-compatibility-matrix">&repmgr; compatibility matrix</link>
+        and <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
+      </para>
+    </sect2>
 
-  <sect2 id="faq-replication-slots-advantage" xreflabel="Advantages of replication slots">
+    <sect2 id="faq-replication-slots-advantage" xreflabel="Advantages of replication slots">
-   <title>What's the advantage of using replication slots?</title>
+      <title>What's the advantage of using replication slots?</title>
-   <para>
+      <para>
-    Replication slots, introduced in PostgreSQL 9.4, ensure that the
+        Replication slots, introduced in PostgreSQL 9.4, ensure that the
-    primary server will retain WAL files until they have been consumed
+        primary server will retain WAL files until they have been consumed
-    by all standby servers. This means standby servers should never
+        by all standby servers. This means standby servers should never
-    fail due to not being able to retrieve required WAL files from the
+        fail due to not being able to retrieve required WAL files from the
-    primary.
+        primary.
-   </para>
+      </para>
-   <para>
+      <para>
-    However this does mean that if a standby is no longer connected to the
+        However this does mean that if a standby is no longer connected to the
-    primary, the presence of the replication slot will cause WAL files
+        primary, the presence of the replication slot will cause WAL files
-    to be retained indefinitely, and eventually lead to disk space
+        to be retained indefinitely, and eventually lead to disk space
-    exhaustion.
+        exhaustion.
-   </para>
+      </para>
 
-   <tip>
+      <tip>
-     <para>
+        <para>
-       2ndQuadrant's recommended configuration is to configure
+          Our recommended configuration is to configure
-       <ulink url="https://www.pgbarman.org/">Barman</ulink> as a fallback
+          <ulink url="https://www.pgbarman.org/">Barman</ulink> as a fallback
-       source of WAL files, rather than maintain replication slots for
+          source of WAL files, rather than maintain replication slots for
-       each standby. See also: <link linkend="cloning-from-barman-restore-command">Using Barman as a WAL file source</link>.
+          each standby. See also: <link linkend="cloning-from-barman-restore-command">Using Barman as a WAL file source</link>.
-     </para>
+        </para>
-   </tip>
+      </tip>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-replication-slots-number" xreflabel="Number of replication slots">
+    <sect2 id="faq-replication-slots-number" xreflabel="Number of replication slots">
-   <title>How many replication slots should I define in <varname>max_replication_slots</varname>?</title>
+      <title>How many replication slots should I define in <varname>max_replication_slots</varname>?</title>
-   <para>
+      <para>
-    Normally at least same number as the number of standbys which will connect
+        Normally at least same number as the number of standbys which will connect
-    to the node. Note that changes to <varname>max_replication_slots</varname> require a server
+        to the node. Note that changes to <varname>max_replication_slots</varname> require a server
-    restart to take effect, and as there is no particular penalty for unused
+        restart to take effect, and as there is no particular penalty for unused
-    replication slots, setting a higher figure will make adding new nodes
+        replication slots, setting a higher figure will make adding new nodes
-    easier.
+        easier.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-hash-index" xreflabel="Hash indexes">
+    <sect2 id="faq-hash-index" xreflabel="Hash indexes">
-   <title>Does &repmgr; support hash indexes?</title>
+      <title>Does &repmgr; support hash indexes?</title>
-   <para>
+      <para>
-    Before PostgreSQL 10, hash indexes were not WAL logged and are therefore not suitable
+        Before PostgreSQL 10, hash indexes were not WAL logged and are therefore not suitable
-    for use in streaming replication in PostgreSQL 9.6 and earlier. See the
+        for use in streaming replication in PostgreSQL 9.6 and earlier. See the
-    <ulink url="https://www.postgresql.org/docs/9.6/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
+        <ulink url="https://www.postgresql.org/docs/9.6/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
-    for details.
+        for details.
-   </para>
+      </para>
-   <para>
+      <para>
-    From PostgreSQL 10, this restriction has been lifted and hash indexes can be used
+        From PostgreSQL 10, this restriction has been lifted and hash indexes can be used
-    in a streaming replication cluster.
+        in a streaming replication cluster.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-upgrades" xreflabel="Upgrading PostgreSQL with repmgr">
+    <sect2 id="faq-upgrades" xreflabel="Upgrading PostgreSQL with repmgr">
-   <title>Can &repmgr; assist with upgrading a PostgreSQL cluster?</title>
+      <title>Can &repmgr; assist with upgrading a PostgreSQL cluster?</title>
-   <para>
+      <para>
-     For <emphasis>minor</emphasis> version upgrades, e.g. from 9.6.7 to 9.6.8, a common
+        For <emphasis>minor</emphasis> version upgrades, e.g. from 9.6.7 to 9.6.8, a common
-     approach is to upgrade a standby to the latest version, perform a
+        approach is to upgrade a standby to the latest version, perform a
-     <link linkend="performing-switchover">switchover</link> promoting it to a primary,
+        <link linkend="performing-switchover">switchover</link> promoting it to a primary,
-     then upgrade the former primary.
+        then upgrade the former primary.
-   </para>
+      </para>
-   <para>
+      <para>
-     For <emphasis>major</emphasis> version upgrades (e.g. from PostgreSQL 9.6 to PostgreSQL 10),
+        For <emphasis>major</emphasis> version upgrades (e.g. from PostgreSQL 9.6 to PostgreSQL 10),
-     the traditional approach is to "reseed" a cluster by upgrading a single
+        the traditional approach is to "reseed" a cluster by upgrading a single
-     node with <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade</ulink>
+        node with <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade</ulink>
-     and recloning standbys from this.
+        and recloning standbys from this.
-   </para>
+      </para>
-   <para>
+      <para>
-     To minimize downtime during major upgrades from PostgreSQL 9.4 and later,
+        To minimize downtime during major upgrades from PostgreSQL 9.4 and later,
-     <ulink url="https://www.2ndquadrant.com/en/resources/pglogical/">pglogical</ulink>
+        <ulink url="https://www.2ndquadrant.com/en/resources/pglogical/">pglogical</ulink>
-     can be used to set up a parallel cluster using the newer PostgreSQL version,
+        can be used to set up a parallel cluster using the newer PostgreSQL version,
-     which can be kept in sync with the existing production cluster until the
+        which can be kept in sync with the existing production cluster until the
-     new cluster is ready to be put into production.
+        new cluster is ready to be put into production.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-libdir-repmgr-error">
+    <sect2 id="faq-libdir-repmgr-error">
-   <title>What does this error mean: <literal>ERROR: could not access file "$libdir/repmgr"</literal>?</title>
+      <title>What does this error mean: <literal>ERROR: could not access file "$libdir/repmgr"</literal>?</title>
-   <para>
+      <para>
-     It means the &repmgr; extension code is not installed in the
+        It means the &repmgr; extension code is not installed in the
-     PostgreSQL application directory. This typically happens when using PostgreSQL
+        PostgreSQL application directory. This typically happens when using PostgreSQL
-     packages provided by a third-party vendor, which often have different
+        packages provided by a third-party vendor, which often have different
-     filesystem layouts.
+        filesystem layouts.
-   </para>
+      </para>
-   <para>
+      <para>
-     Either use PostgreSQL packages provided by the community or 2ndQuadrant; if this
+        Either use PostgreSQL packages provided by the community or EnterpriseDB; if this
-     is not possible, contact your vendor for assistance.
+        is not possible, contact your vendor for assistance.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-old-packages">
+    <sect2 id="faq-old-packages">
-   <title>How can I obtain old versions of &repmgr; packages?</title>
+      <title>How can I obtain old versions of &repmgr; packages?</title>
-   <para>
+      <para>
-     See appendix <xref linkend="packages-old-versions"/> for details.
+        See appendix <xref linkend="packages-old-versions"/> for details.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-required-for-replication">
+    <sect2 id="faq-repmgr-required-for-replication">
-    <title>Is &repmgr; required for streaming replication?</title>
+      <title>Is &repmgr; required for streaming replication?</title>
-    <para>
+      <para>
-      No.
+        No.
-    </para>
+      </para>
-    <para>
+      <para>
-     &repmgr; (together with &repmgrd;) assists with
+        &repmgr; (together with &repmgrd;) assists with
-     <emphasis>managing</emphasis> replication. It does not actually perform replication, which
+        <emphasis>managing</emphasis> replication. It does not actually perform replication, which
-     is part of the core PostgreSQL functionality.
+        is part of the core PostgreSQL functionality.
-    </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-what-if-repmgr-uninstalled">
+    <sect2 id="faq-what-if-repmgr-uninstalled">
-   <title>Will replication stop working if &repmgr; is uninstalled?</title>
+      <title>Will replication stop working if &repmgr; is uninstalled?</title>
-   <para>
+      <para>
-     No. See preceding question.
+        No. See preceding question.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-version-mix">
+    <sect2 id="faq-version-mix">
-   <title>Does it matter if different &repmgr; versions are present in the replication cluster?</title>
+      <title>Does it matter if different &repmgr; versions are present in the replication cluster?</title>
-   <para>
+      <para>
-     Yes. If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x) are present,
+        Yes. If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x) are present,
-     &repmgr; (in particular &repmgrd;)
+        &repmgr; (in particular &repmgrd;)
-     may not run, or run properly, or in the worst case (if different &repmgrd;
+        may not run, or run properly, or in the worst case (if different &repmgrd;
-     versions are running and there are differences in the failover implementation) break
+        versions are running and there are differences in the failover implementation) break
-     your replication cluster.
+        your replication cluster.
-   </para>
+      </para>
-   <para>
+      <para>
-     If different &quot;minor&quot; &repmgr; versions (e.g. 4.1.1 and 4.1.6) are installed,
+        If different &quot;minor&quot; &repmgr; versions (e.g. 4.1.1 and 4.1.6) are installed,
-     &repmgr; will function, but we strongly recommend always running the same version
+        &repmgr; will function, but we strongly recommend always running the same version
-     to ensure there are no unexpected suprises, e.g. a newer version behaving slightly
+        to ensure there are no unexpected surprises, e.g. a newer version behaving slightly
-     differently to the older version.
+        differently to the older version.
-   </para>
+      </para>
-   <para>
+      <para>
-     See also <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
+        See also <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-upgrade-repmgr">
+    <sect2 id="faq-upgrade-repmgr">
-    <title>Should I upgrade &repmgr;?</title>
+      <title>Should I upgrade &repmgr;?</title>
-    <para>
+      <para>
-      Yes.
+        Yes.
-    </para>
+      </para>
-    <para>
+      <para>
-      We don't release new versions for fun, you know. Upgrading may require a little effort,
+        We don't release new versions for fun, you know. Upgrading may require a little effort,
-      but running an older &repmgr; version with bugs which have since been fixed may end up
+        but running an older &repmgr; version with bugs which have since been fixed may end up
-      costing you more effort. The same applies to PostgreSQL itself.
+        costing you more effort. The same applies to PostgreSQL itself.
-    </para>
+      </para>
+    </sect2>
 
-  </sect2>
+    <sect2 id="faq-repmgr-conf-data-directory">
+      <title>Why do I need to specify the data directory location in repmgr.conf?</title>
+      <para>
+        In some circumstances &repmgr; may need to access a PostgreSQL data
+        directory while the PostgreSQL server is not running, e.g. to confirm
+        it shut down cleanly during a <link linkend="performing-switchover">switchover</link>.
+      </para>
+      <para>
+        Additionally, this provides support when using &repmgr; on PostgreSQL 9.6 and
+        earlier, where the <literal>repmgr</literal> user is not a superuser; in that
+        case the <literal>repmgr</literal> user will not be able to access the
+        <literal>data_directory</literal> configuration setting, access to which is restricted
+        to superusers.
+      </para>
+      <para>
+        In PostgreSQL 10 and later, non-superusers can be added to the
+        <ulink url="https://www.postgresql.org/docs/current/default-roles.html">default role</ulink>
+        <option>pg_read_all_settings</option> (or the meta-role <option>pg_monitor</option>)
+        which will enable them to read this setting.
+      </para>
+    </sect2>
 
-  <sect2 id="faq-repmgr-conf-data-directory">
+    <sect2 id="faq-third-party-packages" xreflabel="Compatibility with third party vendor packages">
-    <title>Why do I need to specify the data directory location in repmgr.conf?</title>
+      <title>Are &repmgr; packages compatible with <literal>$third_party_vendor</literal>'s packages?</title>
-    <para>
+      <para>
-      In some circumstances &repmgr; may need to access a PostgreSQL data
+        &repmgr; packages provided by EnterpriseDB are compatible with the community-provided PostgreSQL
-      directory while the PostgreSQL server is not running, e.g. to confirm
+        packages and specified software provided by EnterpriseDB.
-      it shut down cleanly during a <link linkend="performing-switchover">switchover</link>.
+      </para>
-    </para>
+      <para>
-    <para>
+        A number of other vendors provide their own versions of PostgreSQL packages, often with different
-      Additionally, this provides support when using &repmgr; on PostgreSQL 9.6 and
+        package naming schemes and/or file locations.
-      earlier, where the <literal>repmgr</literal> user is not a superuser; in that
+      </para>
-      case the <literal>repmgr</literal> user will not be able to access the
+      <para>
-      <literal>data_directory</literal> configuration setting, access to which is restricted
+        We cannot guarantee that &repmgr; packages will be compatible with these packages.
-      to superusers. (In PostgreSQL 10 and later, non-superusers can be added to the
+        It may be possible to override package dependencies (e.g. <literal>rpm --nodeps</literal>
-      group <option>pg_read_all_settings</option> which will enable them to read this setting).
+        for CentOS-based systems or <literal>dpkg --force-depends</literal> for Debian-based systems).
-    </para>
+      </para>
-  </sect2>
+    </sect2>
- </sect1>
+  </sect1>
 
- <sect1 id="faq-repmgr" xreflabel="repmgr">
+  <sect1 id="faq-repmgr" xreflabel="repmgr">
-  <title><command>repmgr</command></title>
+    <title><command>repmgr</command></title>
 
-  <sect2 id="faq-register-existing-node" xreflabel="registering an existing node">
+    <sect2 id="faq-register-existing-node" xreflabel="registering an existing node">
-   <title>Can I register an existing PostgreSQL server with repmgr?</title>
+      <title>Can I register an existing PostgreSQL server with repmgr?</title>
-   <para>
+      <para>
-    Yes, any existing PostgreSQL server which is part of the same replication
+        Yes, any existing PostgreSQL server which is part of the same replication
-    cluster can be registered with &repmgr;. There's no requirement for a
+        cluster can be registered with &repmgr;. There's no requirement for a
-    standby to have been cloned using &repmgr;.
+        standby to have been cloned using &repmgr;.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-clone-other-source" >
+    <sect2 id="faq-repmgr-clone-other-source" >
-   <title>Can I use a standby not cloned by &repmgr; as a &repmgr; node?</title>
+      <title>Can I use a standby not cloned by &repmgr; as a &repmgr; node?</title>
 
-   <para>
+      <para>
-     For a standby which has been manually cloned or recovered from an external
+        For a standby which has been manually cloned or recovered from an external
-     backup manager such as Barman, the command
+        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
+        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,
+        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.
+        <link linkend="repmgr-standby-register">register the node</link> as usual.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-recovery-conf" >
+    <sect2 id="faq-repmgr-recovery-conf" >
-    <title>What does &repmgr; write in <filename>recovery.conf</filename>, and what options can be set there?</title>
+      <title>What does &repmgr; write in <filename>recovery.conf</filename>, and what options can be set there?</title>
-   <para>
+      <para>
-     See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
+        See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-failed-primary-standby" xreflabel="Reintegrate a failed primary as a standby">
+    <sect2 id="faq-repmgr-failed-primary-standby" xreflabel="Reintegrate a failed primary as a standby">
-   <title>How can a failed primary be re-added as a standby?</title>
+      <title>How can a failed primary be re-added as a standby?</title>
-   <para>
+      <para>
-    This is a two-stage process. First, the failed primary's data directory
+        This is a two-stage process. First, the failed primary's data directory
-    must be re-synced with the current primary; secondly the failed primary
+        must be re-synced with the current primary; secondly the failed primary
-    needs to be re-registered as a standby.
+        needs to be re-registered as a standby.
-   </para>
+      </para>
-   <para>
+      <para>
-    It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
+        It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
-    directory, which will usually be much
+        directory, which will usually be much
-    faster than re-cloning the server. However <command>pg_rewind</command> can only
+        faster than re-cloning the server. However <command>pg_rewind</command> can only
-    be used if PostgreSQL either has <varname>wal_log_hints</varname> enabled, or
+        be used if PostgreSQL either has <varname>wal_log_hints</varname> enabled, or
-    data checksums were enabled when the cluster was initialized.
+        data checksums were enabled when the cluster was initialized.
-   </para>
+      </para>
-   <para>
+      <para>
-     Note that <command>pg_rewind</command> is available as part of the core PostgreSQL
+        Note that <command>pg_rewind</command> is available as part of the core PostgreSQL
-     distribution from PostgreSQL 9.5, and as a third-party utility for PostgreSQL 9.3 and 9.4.
+        distribution from PostgreSQL 9.5, and as a third-party utility for PostgreSQL 9.3 and 9.4.
-   </para>
+      </para>
-   <para>
+      <para>
-    &repmgr; provides the command <command>repmgr node rejoin</command> which can
+        &repmgr; provides the command <command>repmgr node rejoin</command> which can
-    optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin"/>
+        optionally execute <command>pg_rewind</command>; see the <xref linkend="repmgr-node-rejoin"/>
-    documentation for details, in particular the section <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
+        documentation for details, in particular the section <xref linkend="repmgr-node-rejoin-pg-rewind"/>.
-   </para>
+      </para>
-   <para>
+      <para>
-    If <command>pg_rewind</command> cannot be used, then the data directory will need
+        If <command>pg_rewind</command> cannot be used, then the data directory will need
-    to be re-cloned from scratch.
+        to be re-cloned from scratch.
-   </para>
+      </para>
 
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-check-configuration" xreflabel="Check PostgreSQL configuration">
+    <sect2 id="faq-repmgr-check-configuration" xreflabel="Check PostgreSQL configuration">
-   <title>Is there an easy way to check my primary server is correctly configured for use with &repmgr;?</title>
+      <title>Is there an easy way to check my primary server is correctly configured for use with &repmgr;?</title>
-   <para>
+      <para>
-    Execute <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>
+        Execute <command><link linkend="repmgr-standby-clone">repmgr standby clone</link></command>
-    with the <literal>--dry-run</literal> option; this will report any configuration problems
+        with the <literal>--dry-run</literal> option; this will report any configuration problems
-    which need to be rectified.
+        which need to be rectified.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-clone-skip-config-files" xreflabel="">
+    <sect2 id="faq-repmgr-clone-skip-config-files" xreflabel="">
-   <title>When cloning a standby, how can I get &repmgr; to copy
+      <title>When cloning a standby, how can I get &repmgr; to copy
-     <filename>postgresql.conf</filename> and <filename>pg_hba.conf</filename> from the PostgreSQL configuration
+        <filename>postgresql.conf</filename> and <filename>pg_hba.conf</filename> from the PostgreSQL configuration
-     directory in <filename>/etc</filename>?</title>
+        directory in <filename>/etc</filename>?</title>
-   <para>
+      <para>
-    Use the command line option <literal>--copy-external-config-files</literal>. For more details
+        Use the command line option <literal>--copy-external-config-files</literal>. For more details
-    see <xref linkend="repmgr-standby-clone-config-file-copying"/>.
+        see <xref linkend="repmgr-standby-clone-config-file-copying"/>.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
+    <sect2 id="faq-repmgr-shared-preload-libraries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
-    <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
+      <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
-      in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
+        in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
-   <para>
+      <para>
-    No, the <literal>repmgr</literal> shared library is only needed when running &repmgrd;.
+        No, the <literal>repmgr</literal> shared library is only needed when running &repmgrd;.
-    If you later decide to run &repmgrd;, you just need to add
+        If you later decide to run &repmgrd;, you just need to add
-    <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
+        <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-permissions" xreflabel="Replication permission problems">
+    <sect2 id="faq-repmgr-permissions" xreflabel="Replication permission problems">
-   <title>I've provided replication permission for the <literal>repmgr</literal> user in <filename>pg_hba.conf</filename>
+      <title>I've provided replication permission for the <literal>repmgr</literal> user in <filename>pg_hba.conf</filename>
-     but <command>repmgr</command>/&repmgrd; complains it can't connect to the server... Why?</title>
+        but <command>repmgr</command>/&repmgrd; complains it can't connect to the server... Why?</title>
-   <para>
+      <para>
-    <command>repmgr</command> and &repmgrd; need to be able to connect to the repmgr database
+        <command>repmgr</command> and &repmgrd; need to be able to connect to the repmgr database
-    with a normal connection to query metadata. The <literal>replication</literal> connection
+        with a normal connection to query metadata. The <literal>replication</literal> connection
-    permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
+        permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-clone-provide-primary-conninfo" xreflabel="Providing primary connection parameters">
+    <sect2 id="faq-repmgr-clone-provide-primary-conninfo" xreflabel="Providing primary connection parameters">
-   <title>When cloning a standby, why do I need to provide the connection parameters
+      <title>When cloning a standby, why do I need to provide the connection parameters
-     for the primary server on the command line, not in the configuration file?</title>
+        for the primary server on the command line, not in the configuration file?</title>
-   <para>
+      <para>
-    Cloning a standby is a one-time action; the role of the server being cloned
+        Cloning a standby is a one-time action; the role of the server being cloned
-    from could change, so fixing it in the configuration file would create
+        from could change, so fixing it in the configuration file would create
-    confusion. If &repmgr; needs to establish a connection to the primary
+        confusion. If &repmgr; needs to establish a connection to the primary
-    server, it can retrieve this from the <literal>repmgr.nodes</literal> table on the local
+        server, it can retrieve this from the <literal>repmgr.nodes</literal> table on the local
-    node, and if necessary scan the replication cluster until it locates the active primary.
+        node, and if necessary scan the replication cluster until it locates the active primary.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-clone-waldir-xlogdir" xreflabel="Providing a custom WAL directory">
+    <sect2 id="faq-repmgr-clone-waldir-xlogdir" xreflabel="Providing a custom WAL directory">
-   <title>When cloning a standby, how do I ensure the WAL files are placed in a custom directory?</title>
+      <title>When cloning a standby, how do I ensure the WAL files are placed in a custom directory?</title>
-   <para>
+      <para>
-     Provide the option <literal>--waldir</literal>  (<literal>--xlogdir</literal> in PostgreSQL 9.6
+        Provide the option <literal>--waldir</literal>  (<literal>--xlogdir</literal> in PostgreSQL 9.6
-     and earlier) with the absolute path to the WAL directory in <varname>pg_basebackup_options</varname>.
+        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"/>.
+        For more details see <xref linkend="cloning-advanced-pg-basebackup-options"/>.
-   </para>
+      </para>
-  </sect2>
+      <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">
+    <sect2 id="faq-repmgr-events-no-fkey" xreflabel="No foreign key on node_id in repmgr.events">
-   <title>Why is there no foreign key on the <literal>node_id</literal> column in the <literal>repmgr.events</literal>
+      <title>Why is there no foreign key on the <literal>node_id</literal> column in the <literal>repmgr.events</literal>
-     table?</title>
+        table?</title>
-   <para>
+      <para>
-     Under some circumstances event notifications can be generated for servers
+        Under some circumstances event notifications can be generated for servers
-     which have not yet been registered; it's also useful to retain a record
+        which have not yet been registered; it's also useful to retain a record
-     of events which includes servers removed from the replication cluster
+        of events which includes servers removed from the replication cluster
-     which no longer have an entry in the <literal>repmgr.nodes</literal> table.
+        which no longer have an entry in the <literal>repmgr.nodes</literal> table.
-   </para>
+      </para>
-  </sect2>
+    </sect2>
 
-  <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in recovery.conf">
+    <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in recovery.conf">
-    <title>Why are some values in <filename>recovery.conf</filename> surrounded by pairs of single quotes?</title>
+      <title>Why are some values in <filename>recovery.conf</filename> surrounded by pairs of single quotes?</title>
-    <para>
+      <para>
-      This is to ensure that user-supplied values which are written as parameter values in <filename>recovery.conf</filename>
+        This is to ensure that user-supplied values which are written as parameter values in <filename>recovery.conf</filename>
-      are escaped correctly and do not cause errors when <filename>recovery.conf</filename> is parsed.
+        are escaped correctly and do not cause errors when <filename>recovery.conf</filename> is parsed.
-    </para>
+      </para>
-    <para>
+      <para>
-      The escaping is performed by an internal PostgreSQL routine, which leaves strings consisting
+        The escaping is performed by an internal PostgreSQL routine, which leaves strings consisting
-      of digits and alphabetical characters only as-is, but wraps everything else in pairs of single quotes,
+        of digits and alphabetical characters only as-is, but wraps everything else in pairs of single quotes,
-      even if the string does not contain any characters which need escaping.
+        even if the string does not contain any characters which need escaping.
-    </para>
+      </para>
-  </sect2>
+    </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>
+
+  <sect1 id="faq-repmgrd" xreflabel="repmgrd">
+    <title>&repmgrd;</title>
 
 
- </sect1>
+    <sect2 id="faq-repmgrd-prevent-promotion" xreflabel="Prevent standby from being promoted to primary">
+      <title>How can I prevent a node from ever being promoted to primary?</title>
+      <para>
+        In <filename>repmgr.conf</filename>, set its priority to a value of <literal>0</literal>; apply the changed setting with
+        <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>.
+      </para>
+      <para>
+        Additionally, if <varname>failover</varname> is set to <literal>manual</literal>, the node will never
+        be considered as a promotion candidate.
+      </para>
+    </sect2>
 
- <sect1 id="faq-repmgrd" xreflabel="repmgrd">
+    <sect2 id="faq-repmgrd-delayed-standby" xreflabel="Delayed standby support">
-  <title>&repmgrd;</title>
+      <title>Does &repmgrd; support delayed standbys?</title>
+      <para>
+        &repmgrd; can monitor delayed standbys - those set up with
+        <varname>recovery_min_apply_delay</varname> set to a non-zero value
+        in <filename>recovery.conf</filename> - but as it's not currently possible
+        to directly examine the value applied to the standby, &repmgrd;
+        may not be able to properly evaluate the node as a promotion candidate.
+      </para>
+      <para>
+        We recommend that delayed standbys are explicitly excluded from promotion
+        by setting <varname>priority</varname> to <literal>0</literal> in
+        <filename>repmgr.conf</filename>.
+      </para>
+      <para>
+        Note that after registering a delayed standby, &repmgrd; will only start
+        once the metadata added in the primary node has been replicated.
+      </para>
+    </sect2>
 
+    <sect2 id="faq-repmgrd-logfile-rotate" xreflabel="repmgrd logfile rotation">
+      <title>How can I get &repmgrd; to rotate its logfile?</title>
+      <para>
+        Configure your system's <literal>logrotate</literal> service to do this; see <xref linkend="repmgrd-log-rotation"/>.
+      </para>
 
-  <sect2 id="faq-repmgrd-prevent-promotion" xreflabel="Prevent standby from being promoted to primary">
+    </sect2>
-   <title>How can I prevent a node from ever being promoted to primary?</title>
-   <para>
-     In <filename>repmgr.conf</filename>, set its priority to a value of <literal>0</literal>; apply the changed setting with
-    <command><link linkend="repmgr-standby-register">repmgr standby register --force</link></command>.
-   </para>
-   <para>
-    Additionally, if <varname>failover</varname> is set to <literal>manual</literal>, the node will never
-    be considered as a promotion candidate.
-   </para>
-  </sect2>
 
-  <sect2 id="faq-repmgrd-delayed-standby" xreflabel="Delayed standby support">
+    <sect2 id="faq-repmgrd-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
-   <title>Does &repmgrd; support delayed standbys?</title>
+      <title>I've recloned a failed primary as a standby, but &repmgrd; refuses to start?</title>
-   <para>
+      <para>
-    &repmgrd; can monitor delayed standbys - those set up with
+        Check you registered the standby after recloning. If unregistered, the standby
-    <varname>recovery_min_apply_delay</varname> set to a non-zero value
+        cannot be considered as a promotion candidate even if <varname>failover</varname> is set to
-    in <filename>recovery.conf</filename> - but as it's not currently possible
+        <literal>automatic</literal>, which is probably not what you want. &repmgrd; will start if
-    to directly examine the value applied to the standby, &repmgrd;
+        <varname>failover</varname> is set to <literal>manual</literal> so the node's replication status can still
-    may not be able to properly evaluate the node as a promotion candidate.
+        be monitored, if desired.
-   </para>
+      </para>
-   <para>
+    </sect2>
-    We recommend that delayed standbys are explicitly excluded from promotion
-    by setting <varname>priority</varname> to <literal>0</literal> in
-    <filename>repmgr.conf</filename>.
-   </para>
-   <para>
-    Note that after registering a delayed standby, &repmgrd; will only start
-    once the metadata added in the primary node has been replicated.
-   </para>
-  </sect2>
 
-  <sect2 id="faq-repmgrd-logfile-rotate" xreflabel="repmgrd logfile rotation">
+    <sect2 id="faq-repmgrd-pg-bindir" xreflabel="repmgrd does not apply pg_bindir to promote_command or follow_command">
-   <title>How can I get &repmgrd; to rotate its logfile?</title>
+      <title>
-   <para>
+        &repmgrd; ignores pg_bindir when executing <varname>promote_command</varname> or <varname>follow_command</varname>
-     Configure your system's <literal>logrotate</literal> service to do this; see <xref linkend="repmgrd-log-rotation"/>.
+      </title>
-   </para>
+      <para>
+        <varname>promote_command</varname> or <varname>follow_command</varname> can be user-defined scripts,
+        so &repmgr; will not apply <option>pg_bindir</option> even if executing &repmgr;. Always provide the full
+        path; see <xref linkend="repmgrd-automatic-failover-configuration"/> for more details.
+      </para>
+    </sect2>
 
-  </sect2>
+    <sect2 id="faq-repmgrd-startup-no-upstream" xreflabel="repmgrd does not start if upstream node is not running">
+      <title>
+        &repmgrd; aborts startup with the error "<literal>upstream node must be running before repmgrd can start</literal>"
+      </title>
+      <para>
+        &repmgrd; does this to avoid starting up on a replication cluster
+        which is not in a healthy state. If the upstream is unavailable, &repmgrd;
+        may initiate a failover immediately after starting up, which could have unintended side-effects,
+        particularly if &repmgrd; is not running on other nodes.
+      </para>
+      <para>
+        In particular, it's possible that the node's local copy of the <literal>repmgr.nodes</literal> copy
+        is out-of-date, which may lead to incorrect failover behaviour.
+      </para>
+      <para>
+        The onus is therefore on the administrator to manually set the cluster to a stable, healthy state before
+        starting &repmgrd;.
+      </para>
+    </sect2>
 
-  <sect2 id="faq-repmgrd-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
+  </sect1>
-   <title>I've recloned a failed primary as a standby, but &repmgrd; refuses to start?</title>
-   <para>
-    Check you registered the standby after recloning. If unregistered, the standby
-    cannot be considered as a promotion candidate even if <varname>failover</varname> is set to
-    <literal>automatic</literal>, which is probably not what you want. &repmgrd; will start if
-    <varname>failover</varname> is set to <literal>manual</literal> so the node's replication status can still
-  be monitored, if desired.
-   </para>
-  </sect2>
-
-  <sect2 id="faq-repmgrd-pg-bindir" xreflabel="repmgrd does not apply pg_bindir to promote_command or follow_command">
-    <title>
-      &repmgrd; ignores pg_bindir when executing <varname>promote_command</varname> or <varname>follow_command</varname>
-    </title>
-    <para>
-      <varname>promote_command</varname> or <varname>follow_command</varname> can be user-defined scripts,
-      so &repmgr; will not apply <option>pg_bindir</option> even if excuting &repmgr;. Always provide the full
-      path; see <xref linkend="repmgrd-automatic-failover-configuration"/> for more details.
-    </para>
-  </sect2>
-
-  <sect2 id="faq-repmgrd-startup-no-upstream" xreflabel="repmgrd does not start if upstream node is not running">
-    <title>
-      &repmgrd; aborts startup with the error "<literal>upstream node must be running before repmgrd can start</literal>"
-    </title>
-    <para>
-      &repmgrd; does this to avoid starting up on a replication cluster
-      which is not in a healthy state. If the upstream is unavailable, &repmgrd;
-      may initiate a failover immediately after starting up, which could have unintended side-effects,
-      particularly if &repmgrd; is not running on other nodes.
-    </para>
-    <para>
-      In particular, it's possible that the node's local copy of the <literal>repmgr.nodes</literal> copy
-      is out-of-date, which may lead to incorrect failover behaviour.
-    </para>
-    <para>
-      The onus is therefore on the adminstrator to manually set the cluster to a stable, healthy state before
-      starting &repmgrd;.
-    </para>
-  </sect2>
-
- </sect1>
 </appendix>

doc/appendix-packages.xml

@@ -52,8 +52,7 @@
       <para>
         &repmgr; packages are available from the public 2ndQuadrant repository, and also the
         PostgreSQL community repository. The 2ndQuadrant repository is updated immediately
-        after each
+        after each &repmgr; release.
-        &repmgr; release.
       </para>
 
       <table id="centos-2ndquadrant-repository">
@@ -122,7 +121,7 @@
 
      <row>
       <entry>Package name example:</entry>
-      <entry><filename>repmgr10-4.0.4-1.rhel7.x86_64</filename></entry>
+      <entry><filename>repmgr11-4.4.0-1.rhel7.x86_64</filename></entry>
      </row>
 
      <row>
@@ -132,12 +131,12 @@
 
      <row>
       <entry>Installation command:</entry>
-      <entry><literal>yum install repmgr10</literal></entry>
+      <entry><literal>yum install repmgr11</literal></entry>
      </row>
 
      <row>
       <entry>Binary location:</entry>
-      <entry><filename>/usr/pgsql-10/bin</filename></entry>
+      <entry><filename>/usr/pgsql-11/bin</filename></entry>
      </row>
 
      <row>
@@ -147,22 +146,22 @@
 
      <row>
       <entry>Configuration file location:</entry>
-      <entry><filename>/etc/repmgr/10/repmgr.conf</filename></entry>
+      <entry><filename>/etc/repmgr/11/repmgr.conf</filename></entry>
      </row>
 
      <row>
       <entry>Data directory:</entry>
-      <entry><filename>/var/lib/pgsql/10/data</filename></entry>
+      <entry><filename>/var/lib/pgsql/11/data</filename></entry>
      </row>
 
      <row>
       <entry>repmgrd service command:</entry>
-      <entry><command>systemctl [start|stop|restart|reload] repmgr10</command></entry>
+      <entry><command>systemctl [start|stop|restart|reload] repmgr11</command></entry>
      </row>
 
      <row>
       <entry>repmgrd service file location:</entry>
-      <entry><filename>/usr/lib/systemd/system/repmgr10.service</filename></entry>
+      <entry><filename>/usr/lib/systemd/system/repmgr11.service</filename></entry>
      </row>
 
      <row>
@@ -253,20 +252,14 @@
     </indexterm>
 
     <para>
-      &repmgr; <literal>.deb</literal> packages are provided via the
+      &repmgr; <literal>.deb</literal> packages are provided by 2ndQuadrant as well as the
       PostgreSQL Community APT repository, and are available for each community-supported
       PostgreSQL version, currently supported Debian releases, and currently supported
       Ubuntu LTS releases.
     </para>
 
     <sect2 id="packages-apt-repository">
-      <title>APT repository</title>
+      <title>APT repositories</title>
-
-      <para>
-        &repmgr; packages are available from the  PostgreSQL Community APT repository,
-        which is updated immediately after each &repmgr; release.
-      </para>
-
 
       <table id="apt-2ndquadrant-repository">
         <title>2ndQuadrant public repository</title>
@@ -291,7 +284,7 @@
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink></entry>
+              <entry><ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -323,7 +316,7 @@
 
             <row>
               <entry>Package name example:</entry>
-              <entry><filename>postgresql-10-repmgr</filename></entry>
+              <entry><filename>postgresql-11-repmgr</filename></entry>
             </row>
 
             <row>
@@ -333,12 +326,12 @@
 
             <row>
               <entry>Installation command:</entry>
-              <entry><literal>apt-get install postgresql-10-repmgr</literal></entry>
+              <entry><literal>apt-get install postgresql-11-repmgr</literal></entry>
             </row>
 
             <row>
               <entry>Binary location:</entry>
-              <entry><filename>/usr/lib/postgresql/10/bin</filename></entry>
+              <entry><filename>/usr/lib/postgresql/11/bin</filename></entry>
             </row>
 
             <row>
@@ -353,12 +346,12 @@
 
             <row>
               <entry>Data directory:</entry>
-              <entry><filename>/var/lib/postgresql/10/main</filename></entry>
+              <entry><filename>/var/lib/postgresql/11/main</filename></entry>
             </row>
 
             <row>
               <entry>PostgreSQL service command:</entry>
-              <entry><command>systemctl [start|stop|restart|reload] postgresql@10-main</command></entry>
+              <entry><command>systemctl [start|stop|restart|reload] postgresql@11-main</command></entry>
 
             </row>
 
@@ -382,11 +375,11 @@
       </table>
       <note>
         <para>
-          Instead of using the <application>systemd</application> service command directly,
+          When using Debian packages, instead of using the <application>systemd</application> service
-          it's recommended to execute <command>pg_ctlcluster</command> (as <literal>root</literal>,
+          command directly,  it's recommended to execute <command>pg_ctlcluster</command>
-          either directly or via <command>sudo</command>), e.g.:
+          (as <literal>root</literal>, either directly or via <command>sudo</command>), e.g.:
           <programlisting>
-            <command>pg_ctlcluster 10 main [start|stop|restart|reload]</command></programlisting>
+            <command>pg_ctlcluster 11 main [start|stop|restart|reload]</command></programlisting>
         </para>
         <para>
           For pre-<application>systemd</application> systems, <command>pg_ctlcluster</command>
@@ -404,7 +397,7 @@
     </indexterm>
     <indexterm>
       <primary>packages</primary>
-      <secondary>snaphots</secondary>
+      <secondary>snapshots</secondary>
     </indexterm>
 
     <para>
@@ -445,7 +438,7 @@ curl https://dl.2ndquadrant.com/default/snapshot/get/9.6/rpm | sudo bash</progra
       The package name will be formatted like this:
       <programlisting>
 repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
-      containg the snapshot build number (here: <literal>320</literal>) and the hash
+      containing the snapshot build number (here: <literal>320</literal>) and the hash
       of the <application>git</application> commit it was built from (here: <literal>g5113ab0</literal>).
     </para>
 
@@ -477,7 +470,7 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
       <title>Debian/Ubuntu</title>
       <para>
         An archive of old packages (<literal>3.3.2</literal> and later) for Debian/Ubuntu-based systems is available here:
-        <ulink url="http://atalia.postgresql.org/morgue/r/repmgr/">http://atalia.postgresql.org/morgue/r/repmgr/</ulink>
+        <ulink url="https://apt-archive.postgresql.org/">https://apt-archive.postgresql.org/</ulink>
       </para>
     </sect2>
 

doc/appendix-support.xml

@@ -20,7 +20,7 @@
     A mailing list/forum is provided via Google groups to discuss contributions or issues: <ulink url="https://groups.google.com/group/repmgr">https://groups.google.com/group/repmgr</ulink>.
   </para>
   <para>
-    Please report bugs and other issues to: <ulink url="https://github.com/2ndQuadrant/repmgr">https://github.com/2ndQuadrant/repmgr</ulink>.
+    Please report bugs and other issues to: <ulink url="https://github.com/EnterpriseDB/repmgr">https://github.com/EnterpriseDB/repmgr</ulink>.
   </para>
 
   <important>
@@ -43,6 +43,12 @@
 
     <itemizedlist spacing="compact" mark="bullet">
 
+     <listitem>
+      <simpara>
+        PostgreSQL version
+      </simpara>
+     </listitem>
+
      <listitem>
       <simpara>
         &repmgr; version
@@ -58,7 +64,7 @@
 
      <listitem>
       <simpara>
-        <filename>repmpgr.conf</filename> files (suitably anonymized if necessary)
+        <filename>repmgr.conf</filename> files (suitably anonymized if necessary)
       </simpara>
      </listitem>
 
@@ -68,9 +74,18 @@
       </simpara>
      </listitem>
 
+
      <listitem>
       <simpara>
-        PostgreSQL version
+        PostgreSQL 11 and earlier: contents of the <filename>recovery.conf</filename> file
+        (suitably anonymized if necessary).
+      </simpara>
+     </listitem>
+     <listitem>
+      <simpara>
+        PostgreSQL 12 and later: contents of the <filename>postgresql.auto.conf</filename> file
+        (suitably anonymized if necessary), and whether or not the PostgreSQL data directory
+        contains the files <filename>standby.signal</filename> and/or <filename>recovery.signal</filename>.
       </simpara>
      </listitem>
 
@@ -90,8 +105,8 @@
     </para>
     <para>
       In all cases it is <emphasis>extremely</emphasis> useful to receive
-      information on how to reliably reproduce an issue with as much detail as
+      as much detail as possible on how to reliably reproduce
-      possible.
+      an issue.
     </para>
 
   </sect1>

doc/bdr-failover.md

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

doc/cloning-standbys.xml

@@ -46,12 +46,32 @@
       <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>
    </itemizedlist>
    </para>
 
+
+   <note>
+    <para>
+      Currently &repmgr;'s support for cloning from Barman is implemented by using
+      <productname>rsync</productname> to clone from the Barman server.
+    </para>
+    <para>
+      It is therefore not able to make use of Barman's parallel restore facility, which
+      is executed on the Barman server and clones to the target server.
+    </para>
+    <para>
+      Barman's parallel restore facility can be used by executing it manually on
+      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>
+
+
   <sect2 id="cloning-from-barman-prerequisites">
    <title>Prerequisites for cloning from Barman</title>
    <para>
@@ -60,8 +80,7 @@
    <itemizedlist spacing="compact" mark="bullet">
      <listitem>
       <para>
-        the <varname>barman_server</varname> setting in <filename>repmgr.conf</filename> is the same as the
+        the Barman catalogue must include at least one valid backup for this server;
-        server configured in Barman;
       </para>
      </listitem>
      <listitem>
@@ -72,19 +91,90 @@
      </listitem>
      <listitem>
       <para>
-        the <varname>restore_command</varname> setting in <filename>repmgr.conf</filename> is configured to
+        the <varname>barman_server</varname> setting in <filename>repmgr.conf</filename> is the same as the
-        use a copy of the <command>barman-wal-restore</command> script shipped with the
+        server configured in Barman.
-        <literal>barman-cli</literal> package (see section <xref linkend="cloning-from-barman-restore-command"/>
-        below).
-      </para>
-     </listitem>
-     <listitem>
-      <para>
-        the Barman catalogue includes at least one valid backup for this  server.
       </para>
      </listitem>
+
    </itemizedlist>
    </para>
+
+   <para>
+     For example, assuming Barman is located on the host &quot;<literal>barmansrv</literal>&quot;
+     under the &quot;<literal>barman</literal>&quot; user account,
+     <filename>repmgr.conf</filename> should contain the following entries:
+    <programlisting>
+    barman_host='barman@barmansrv'
+    barman_server='pg'</programlisting>
+   </para>
+   <para>
+     Here <literal>pg</literal> corresponds to a section in Barman's configuration file for a specific
+     server backup configuration, which would look something like:
+     <programlisting>
+[pg]
+description = "Main cluster"
+...
+     </programlisting>
+   </para>
+   <para>
+     More details on Barman configuration can be found in the
+     <ulink url="https://docs.pgbarman.org/">Barman documentation</ulink>'s
+     <ulink url="https://docs.pgbarman.org/#configuration">configuration section</ulink>.
+   </para>
+   <note>
+    <para>
+     To use a non-default Barman configuration file on the Barman server,
+     specify this in <filename>repmgr.conf</filename> with <filename>barman_config</filename>:
+     <programlisting>
+      barman_config='/path/to/barman.conf'</programlisting>
+    </para>
+   </note>
+
+
+   <para>
+     We also recommend configuring the <varname>restore_command</varname> setting in <filename>repmgr.conf</filename>
+     to use the <command>barman-wal-restore</command> script
+     (see section <xref linkend="cloning-from-barman-restore-command"/> below).
+   </para>
+
+
+   <tip>
+    <simpara>
+      If you have a non-default SSH configuration on the Barman
+      server, e.g. using a port other than 22, then you can set those
+      parameters in a dedicated Host section in <filename>~/.ssh/config</filename>
+      corresponding to the value of <varname>barman_host</varname> in
+      <filename>repmgr.conf</filename>. See the <literal>Host</literal>
+      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>
+    $ repmgr -f /etc/repmgr.conf -h node1 -U repmgr -d repmgr standby clone
+    NOTICE: destination directory "/var/lib/postgresql/data" provided
+    INFO: connecting to Barman server to verify backup for "test_cluster"
+    INFO: checking and correcting permissions on existing directory "/var/lib/postgresql/data"
+    INFO: creating directory "/var/lib/postgresql/data/repmgr"...
+    INFO: connecting to Barman server to fetch server parameters
+    INFO: connecting to source node
+    DETAIL: current installation size is 30 MB
+    NOTICE: retrieving backup from Barman...
+    (...)
+    NOTICE: standby clone (from Barman) complete
+    NOTICE: you can now start your PostgreSQL server
+    HINT: for example: pg_ctl -D /var/lib/postgresql/data start</programlisting>
+   </para>
+
    <note>
     <simpara>
      Barman support is automatically enabled if <varname>barman_server</varname>
@@ -94,37 +184,7 @@
      command line option.
     </simpara>
    </note>
-   <tip>
-    <simpara>
-      If you have a non-default SSH configuration on the Barman
-      server, e.g. using a port other than 22, then you can set those
-      parameters in a dedicated Host section in <filename>~/.ssh/config</filename>
-      corresponding to the value of<varname>barman_host</varname> in
-      <filename>repmgr.conf</filename>. See the <literal>Host</literal>
-      section in <command>man 5 ssh_config</command> for more details.
-    </simpara>
-   </tip>
-   <para>
-    It's now possible to clone a standby from Barman, e.g.:
-    <programlisting>
-    NOTICE: using configuration file "/etc/repmgr.conf"
-    NOTICE: destination directory "/var/lib/postgresql/data" provided
-    INFO: connecting to Barman server to verify backup for test_cluster
-    INFO: checking and correcting permissions on existing directory "/var/lib/postgresql/data"
-    INFO: creating directory "/var/lib/postgresql/data/repmgr"...
-    INFO: connecting to Barman server to fetch server parameters
-    INFO: connecting to upstream node
-    INFO: connected to source node, checking its state
-    INFO: successfully connected to source node
-    DETAIL: current installation size is 29 MB
-    NOTICE: retrieving backup from Barman...
-    receiving file list ...
-    (...)
-    NOTICE: standby clone (from Barman) complete
-    NOTICE: you can now start your PostgreSQL server
-    HINT: for example: pg_ctl -D /var/lib/postgresql/data start</programlisting>
 
-   </para>
   </sect2>
   <sect2 id="cloning-from-barman-restore-command" xreflabel="Using Barman as a WAL file source">
    <title>Using Barman as a WAL file source</title>
@@ -142,35 +202,28 @@
    </para>
    <para>
      <command>barman-wal-restore</command> is a Python script provided as part of the <literal>barman-cli</literal>
-     package (Barman 2.0 and later; for Barman 1.x the script is provided separately as
+     package (Barman 2.0 ~ 2.7) or as part of the core Barman distribution (Barman 2.8 and later).
-     <command>barman-wal-restore.py</command>) which performs this function for Barman.
    </para>
    <para>
-    To use <command>barman-wal-restore</command> with &repmgr;
+    To use <command>barman-wal-restore</command> with &repmgr;,
-    and assuming Barman is located on the <literal>barmansrv</literal> host
+    assuming Barman is located on the host &quot;<literal>barmansrv</literal>&quot;
+    under the &quot;<literal>barman</literal>&quot; user account,
     and that <command>barman-wal-restore</command> is located as an executable at
     <filename>/usr/bin/barman-wal-restore</filename>,
     <filename>repmgr.conf</filename> should include the following lines:
     <programlisting>
-    barman_host=barmansrv
+    barman_host='barman@barmansrv'
-    barman_server=somedb
+    barman_server='pg'
-    restore_command=/usr/bin/barman-wal-restore barmansrv somedb %f %p</programlisting>
+    restore_command='/usr/bin/barman-wal-restore barmansrv pg %f %p'</programlisting>
    </para>
    <note>
     <simpara>
       <command>barman-wal-restore</command> supports command line switches to
-      control parallelism (<literal>--parallel=N</literal>) and compression (
+      control parallelism (<literal>--parallel=N</literal>) and compression
-      <literal>--bzip2</literal>, <literal>--gzip</literal>).
+      (<literal>--bzip2</literal>, <literal>--gzip</literal>).
     </simpara>
    </note>
-   <note>
+
-    <para>
-     To use a non-default Barman configuration file on the Barman server,
-     specify this in <filename>repmgr.conf</filename> with <filename>barman_config</filename>:
-     <programlisting>
-      barman_config=/path/to/barman.conf</programlisting>
-    </para>
-   </note>
   </sect2>
  </sect1>
 
@@ -191,7 +244,8 @@
     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.
@@ -265,7 +319,7 @@
     Cascading replication, introduced with PostgreSQL 9.2, enables a standby server
     to replicate from another standby server rather than directly from the primary,
     meaning replication changes "cascade" down through a hierarchy of servers. This
-    can be used to reduce load on the primary and minimize bandwith usage between
+    can be used to reduce load on the primary and minimize bandwidth usage between
     sites. For more details, see the
     <ulink url="https://www.postgresql.org/docs/current/warm-standby.html#CASCADING-REPLICATION">
     PostgreSQL cascading replication documentation</ulink>.
@@ -337,7 +391,7 @@
      cluster, you may wish to clone a downstream standby whose upstream node
      does not yet exist. In this case you can clone from the primary (or
      another upstream node); provide the parameter <literal>--upstream-conninfo</literal>
-     to explictly set the upstream's <varname>primary_conninfo</varname> string
+     to explicitly set the upstream's <varname>primary_conninfo</varname> string
      in <filename>recovery.conf</filename>.
     </simpara>
    </tip>
@@ -395,6 +449,13 @@
       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.
@@ -415,10 +476,8 @@
 
     <para>
      The recommended way to do this is to store the password in the <literal>postgres</literal> system
-     user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
+     user's <filename>~/.pgpass</filename> file.  For more information on using the password file, see
-     environment variable <varname>PGPASSWORD</varname>, however this is not recommended for
+     the documentation section <xref linkend="configuration-password-file"/>.
-     security reasons. For more details see the
-     <ulink url="https://www.postgresql.org/docs/current/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
     </para>
 
     <note>
@@ -440,19 +499,6 @@
      will need to be set during any action which causes <filename>recovery.conf</filename> to be
      rewritten, e.g. <xref linkend="repmgr-standby-follow"/>.
     </para>
-    <para>
-     It is of course also possible to include the password value in the <varname>conninfo</varname>
-     string for each node, but this is obviously a security risk and should be avoided.
-    </para>
-    <para>
-      From PostgreSQL 9.6, <application>libpq</application> supports the <varname>passfile</varname>
-      parameter in connection strings, which can be used to specify a password file other than
-      the default <filename>~/.pgpass</filename>.
-    </para>
-    <para>
-      To have &repmgr; write a custom password file in <varname>primary_conninfo</varname>,
-      specify its location in <varname>passfile</varname> in <filename>repmgr.conf</filename>.
-    </para>
    </sect2>
 
    <sect2 id="cloning-advanced-replication-user" xreflabel="Separate replication user">
@@ -468,6 +514,34 @@
      cloning a node or executing <xref linkend="repmgr-standby-follow"/>.
     </para>
    </sect2>
+
+
+   <sect2 id="cloning-advanced-tablespace-mapping" xreflabel="Tablespace mapping">
+    <title>Tablespace mapping</title>
+    <indexterm>
+      <primary>tablespace mapping</primary>
+    </indexterm>
+    <para>
+      &repmgr; provides a <option>tablespace_mapping</option> configuration
+      file option, which will makes it possible to map the tablespace on the source node to
+      a different location on the local node.
+    </para>
+    <para>
+      To use this, add <option>tablespace_mapping</option> to <filename>repmgr.conf</filename>
+      like this:
+<programlisting>
+  tablespace_mapping='/var/lib/pgsql/tblspc1=/data/pgsql/tblspc1'
+</programlisting>
+    </para>
+    <para>
+      where the left-hand value represents the tablespace on the source node,
+      and the right-hand value represents  the tablespace on the standby to be cloned.
+    </para>
+    <para>
+      This parameter can be provided multiple times.
+    </para>
+   </sect2>
+
  </sect1>
 
 

doc/configuration-file-optional-settings.xml

@@ -0,0 +1,189 @@
+<sect1 id="configuration-file-optional-settings" xreflabel="optional configuration file settings">
+
+  <title>Optional configuration file settings</title>
+
+  <indexterm>
+    <primary>repmgr.conf</primary>
+    <secondary>optional settings</secondary>
+  </indexterm>
+
+  <note>
+    <simpara>
+      This section documents a subset of optional configuration settings; for a full
+      for a full and annotated view of all configuration options see the
+      see the <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">sample repmgr.conf file</ulink>
+    </simpara>
+  </note>
+
+  <variablelist>
+
+
+    <varlistentry id="repmgr-conf-config-directory" xreflabel="config_directory">
+      <term><varname>config_directory</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>config_directory</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          If PostgreSQL configuration files are located outside the data
+	  directory, specify the directory where the main
+	  <filename>postgresql.conf</filename> file is located.
+        </para>
+        <para>
+          This enables explicit provision of an external configuration file
+          directory, which if set will be passed to <command>pg_ctl</command> as the
+          <option>-D</option> parameter. Otherwise <command>pg_ctl</command> will
+          default to using the data directory, which will cause some operations
+          to fail if the configuration files are not present there.
+        </para>
+        <note>
+          <para>
+           This is implemented primarily for feature completeness and for
+           development/testing purposes. Users who have installed &repmgr; from
+           a package should <emphasis>not</emphasis> rely on  to stop/start/restart PostgreSQL,
+           instead they should set the appropriate <option>service_..._command</option>
+           for their operating system. For more details see
+           <xref linkend="configuration-file-service-commands"/>.
+          </para>
+        </note>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry id="repmgr-conf-replication-user" xreflabel="replication_user">
+      <term><varname>replication_user</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>replication_user</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          PostgreSQL user to make replication connections with.
+          If not set defaults, to the user defined in <xref linkend="repmgr-conf-conninfo"/>.
+        </para>
+      </listitem>
+    </varlistentry>
+
+
+
+    <varlistentry id="repmgr-conf-replication-type" xreflabel="replication_type">
+      <term><varname>replication_type</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>replication_type</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Must be <literal>physical</literal> (the default).
+        </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry id="repmgr-conf-location" xreflabel="location">
+      <term><varname>location</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>location</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          An arbitrary string defining the location of the node; this
+	  is used during failover to check visibility of the
+	  current primary node.
+        </para>
+        <para>
+          For more details see <xref linkend="repmgrd-network-split"/>.
+        </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry id="repmgr-conf-use-replication-slots" xreflabel="use_replication_slots">
+      <term><varname>use_replication_slots</varname> (<type>boolean</type>)
+        <indexterm>
+          <primary><varname>use_replication_slots</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Whether to use physical replication slots.
+        </para>
+        <note>
+          <para>
+	    When using replication slots,
+	    <varname>max_replication_slots</varname> should be configured for
+	    at least the number of standbys which will connect
+	    to the primary.
+          </para>
+        </note>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry id="repmgr-conf-ssh-options" xreflabel="ssh_options">
+      <term><varname>ssh_options</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>ssh_options</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Options to append to the <command>ssh</command> command when executed
+          by &repmgr;.
+        </para>
+        <para>
+          We recommend adding <literal>-q</literal> to suppress any superfluous
+          SSH chatter such as login banners, and also an explicit
+          <option>ConnectTimeout</option> value,
+          e.g.:
+<programlisting>
+ssh_options='-q -o ConnectTimeout=10'</programlisting>
+        </para>
+      </listitem>
+    </varlistentry>
+
+    <varlistentry id="repmgr-conf-pg-bindir" xreflabel="pg_bindir">
+      <term><varname>pg_bindir</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>pg_bindir</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Path to the PostgreSQL binary directory (location of <application>pg_ctl</application>,
+          <application>pg_basebackup</application> etc.). Only required
+	  if these are not in the system <varname>PATH</varname>.
+        </para>
+        <tip>
+          <para>
+            When &repmgr; is executed via <application>SSH</application> (e.g. when running
+            <command><link linkend="repmgr-standby-switchover">repmgr standby switchover</link></command>,
+            <command><link linkend="repmgr-cluster-matrix">repmgr cluster matrix</link></command> or
+            <command><link linkend="repmgr-cluster-crosscheck">repmgr cluster crosscheck</link></command>,
+            or if it is executed as cronjob), a login shell will not be used and only the
+            default system <varname>PATH</varname> will be set. Therefore it's recommended to set
+            <varname>pg_bindir</varname> so &repmgr; can correctly invoke binaries on a remote
+            system and avoid potential path issues.
+          </para>
+        </tip>
+
+        <para>
+          Debian/Ubuntu users: you will probably need to  set this to the directory where
+          <application>pg_ctl</application> is located, e.g. <filename>/usr/lib/postgresql/9.6/bin/</filename>.
+        </para>
+        <para>
+          <emphasis>NOTE</emphasis>: <varname>pg_bindir</varname> is only used when &repmgr; directly
+	  executes PostgreSQL binaries; any user-defined scripts
+	  <emphasis>must</emphasis> be specified with the full path.
+        </para>
+
+      </listitem>
+    </varlistentry>
+  </variablelist>
+
+  <tip>
+    <simpara>
+      See the <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">sample repmgr.conf file</ulink>
+      for a full and annotated view of all configuration options.
+    </simpara>
+  </tip>
+
+</sect1>

doc/configuration-file-required-settings.xml

@@ -96,33 +96,9 @@
   </variablelist>
  </para>
 
-  <para>
+ <para>
-    For a full list of annotated configuration items, see the file
+   See <xref linkend="configuration-file-optional-settings"/> for further configuration options.
-    <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
+ </para>
-  </para>
-  <para>
-    For &repmgrd;-specific settings, see <xref linkend="repmgrd-configuration"/>.
-  </para>
 
-  <note>
-    <para>
-    The following parameters in the configuration file can be overridden with
-    command line options:
-    <itemizedlist>
-     <listitem>
-       <simpara>
-         <literal>-L/--log-level</literal> overrides <literal>log_level</literal> in
-         <filename>repmgr.conf</filename>
-       </simpara>
-     </listitem>
-     <listitem>
-       <simpara>
-         <literal>-b/--pg_bindir</literal> overrides <literal>pg_bindir</literal> in
-         <filename>repmgr.conf</filename>
-       </simpara>
-     </listitem>
-    </itemizedlist>
-    </para>
-  </note>
 
 </sect1>

doc/configuration-file-service-commands.xml

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

doc/configuration-file.xml

@@ -31,6 +31,8 @@
       <secondary>format</secondary>
     </indexterm>
 
+
+
     <para>
       <filename>repmgr.conf</filename> is a plain text file with one parameter/value
       combination per line.
@@ -39,14 +41,10 @@
       Whitespace is insignificant (except within a quoted parameter value) and blank lines are ignored.
       Hash marks (<literal>#</literal>) designate the remainder of the line as a comment.
       Parameter values that are not simple identifiers or numbers should be single-quoted.
-      Note that single quote cannot be embedded in a parameter value.
     </para>
-    <important>
+    <para>
-      <para>
+      To embed a single quote in a parameter value, write either two quotes (preferred) or backslash-quote.
-        &repmgr; will interpret double-quotes as being part of a string value; only use single quotes
+    </para>
-        to quote parameter values.
-      </para>
-    </important>
 
     <para>
       Example of a valid <filename>repmgr.conf</filename> file:
@@ -56,12 +54,144 @@
 node_id=1
 node_name= node1
 conninfo ='host=node1 dbname=repmgr user=repmgr connect_timeout=2'
-data_directory = /var/lib/pgsql/11/data</programlisting>
+data_directory = '/var/lib/pgsql/12/data'</programlisting>
 
     </para>
+
+    <note>
+      <para>
+        Beginning with <link linkend="release-5.0">repmgr 5.0</link>, configuration
+        file parsing has been tightened up and now matches the way PostgreSQL
+        itself parses configuration files.
+      </para>
+      <para>
+        This means <filename>repmgr.conf</filename> files used with earlier &repmgr;
+        versions may need slight modification before they can be used with &repmgr; 5
+        and later.
+      </para>
+      <para>
+        The main change is that &repmgr; requires most string values to be
+        enclosed in single quotes. For example, this was previously valid:
+          <programlisting>
+conninfo=host=node1 user=repmgr dbname=repmgr connect_timeout=2</programlisting>
+          but must now be changed to:
+          <programlisting>
+conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlisting>
+      </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>
 
 
+  <sect2 id="configuration-file-items" xreflabel="configuration file items">
+
+    <title>Configuration file items</title>
+    <para>
+      The following sections document some sections of the configuration file:
+       <itemizedlist>
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-settings"/>
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-optional-settings"/>
+            </simpara>
+          </listitem>
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-log-settings"/>
+            </simpara>
+          </listitem>
+
+
+          <listitem>
+            <simpara>
+              <xref linkend="configuration-file-service-commands"/>
+            </simpara>
+          </listitem>
+
+       </itemizedlist>
+
+    </para>
+    <para>
+      For a full list of annotated configuration items, see the file
+      <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>.
+    </para>
+    <para>
+      For &repmgrd;-specific settings, see <xref linkend="repmgrd-configuration"/>.
+    </para>
+
+    <note>
+      <para>
+        The following parameters in the configuration file can be overridden with
+        command line options:
+        <itemizedlist>
+          <listitem>
+            <simpara>
+              <literal>-L/--log-level</literal> overrides <literal>log_level</literal> in
+              <filename>repmgr.conf</filename>
+            </simpara>
+          </listitem>
+          <listitem>
+            <simpara>
+              <literal>-b/--pg_bindir</literal> overrides <literal>pg_bindir</literal> in
+              <filename>repmgr.conf</filename>
+            </simpara>
+          </listitem>
+        </itemizedlist>
+      </para>
+    </note>
+
+  </sect2>
 
   <sect2 id="configuration-file-location" xreflabel="configuration file location">
   <title>Configuration file location</title>
@@ -97,6 +227,14 @@ data_directory = /var/lib/pgsql/11/data</programlisting>
    </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
@@ -117,6 +255,61 @@ data_directory = /var/lib/pgsql/11/data</programlisting>
       <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

@@ -0,0 +1,175 @@
+<sect1 id="configuration-password-management" xreflabel="password management">
+
+  <title>Password Management</title>
+  <indexterm>
+    <primary>passwords</primary>
+  </indexterm>
+
+  <sect2 id="configuration-password-management-options" xreflabel="password management options">
+  <title>Password Management Options</title>
+  <indexterm>
+    <primary>passwords</primary>
+    <secondary>options for managing</secondary>
+  </indexterm>
+
+  <para>
+    For security purposes it's desirable to protect database access using a password.
+  </para>
+  <para>
+    PostgreSQL has three ways of providing a password:
+    <itemizedlist spacing="compact" mark="bullet">
+
+       <listitem>
+         <simpara>
+           including the password in the <option>conninfo</option> string
+           (e.g. &quot;<literal>host=node1 dbname=repmgr user=repmgr password=foo</literal>&quot;)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           exporting the password as an environment variable (<envar>PGPASSWORD</envar>)
+         </simpara>
+       </listitem>
+
+       <listitem>
+         <simpara>
+           storing the password in a dedicated password file
+         </simpara>
+       </listitem>
+    </itemizedlist>
+  </para>
+  <para>
+    We strongly advise against including the password in the <option>conninfo</option> string, as
+    this will result in the database password being exposed in various places, including in the
+    <filename>repmgr.conf</filename> file, the <literal>repmgr.nodes</literal> table, any output
+    generated by &repmgr; which lists the node <option>conninfo</option> strings (e.g.
+    <link linkend="repmgr-cluster-show">repmgr cluster show</link>) and in the &repmgr; log file,
+    particularly at <option>log_level=DEBUG</option>.
+  </para>
+  <note>
+    <para>
+      Currently &repmgr; does not fully support use of the <option>password</option> option in the
+      <option>conninfo</option> string.
+    </para>
+  </note>
+  <para>
+    Exporting the password as an environment variable (<envar>PGPASSWORD</envar>) is considered
+    less insecure, but the PostgreSQL documentation explicitly recommends against doing this:
+   <blockquote>
+     <attribution><ulink url="https://www.postgresql.org/docs/current/libpq-envars.html">Environment Variables</ulink></attribution>
+     <para>
+       <envar>PGPASSWORD</envar> behaves the same as the <option>password</option>
+       connection parameter. Use of this environment variable
+       is not recommended for security reasons, as some operating systems
+       allow non-root users to see process environment variables via
+       <application>ps</application>; instead consider using a password file.
+     </para>
+    </blockquote>
+
+  </para>
+  <para>
+    The most secure option for managing passwords is to use a dedicated password file; see the following
+    section for more details.
+  </para>
+
+  </sect2>
+
+  <sect2 id="configuration-password-file" xreflabel="password file">
+    <title>Using a password file</title>
+    <indexterm>
+      <primary>pgpass</primary>
+    </indexterm>
+
+    <indexterm>
+      <primary>.pgpass</primary>
+    </indexterm>
+
+    <indexterm>
+      <primary>passwords</primary>
+      <secondary>using a password file</secondary>
+    </indexterm>
+
+    <para>
+      The most secure way of storing passwords is in a password file,
+      which by default is <filename>~/.pgpass</filename>. This file
+      can only be read by the system user who owns the file, and
+      PostgreSQL will refuse to use the file unless read/write
+      permissions are restricted to the file owner. The password(s)
+      contained in the file will not be directly accessed by
+      &repmgr; (or any other libpq-based client software such as <application>psql</application>).
+    </para>
+    <para>
+       For full details see the
+       <ulink url="https://www.postgresql.org/docs/current/libpq-pgpass.html">PostgreSQL password file documentation</ulink>.
+    </para>
+    <para>
+      For use with &repmgr;, the <filename>~/.pgpass</filename> must two entries for each
+      node in the replication cluster: one for the &repmgr; user who accesses the &repmgr; metadatabase,
+      and one for replication connections (regardless of whether a dedicated replication user is used).
+      The file must be present on each node in the replication cluster.
+    </para>
+    <para>
+      A <filename>~/.pgpass</filename> file for a 3-node cluster where the <literal>repmgr</literal> database user
+      is used for both for accessing the  &repmgr; metadatabase and for replication connections would look like this:
+      <programlisting>
+node1:5432:repmgr:repmgr:foo
+node1:5432:replication:repmgr:foo
+node2:5432:repmgr:repmgr:foo
+node2:5432:replication:repmgr:foo
+node3:5432:repmgr:repmgr:foo
+node3:5432:replication:repmgr:foo</programlisting>
+      If a dedicated replication user (here: <literal>repluser</literal>) is in use, the file would look like this:
+      <programlisting>
+node1:5432:repmgr:repmgr:foo
+node1:5432:replication:repluser:foo
+node2:5432:repmgr:repmgr:foo
+node2:5432:replication:repluser:foo
+node3:5432:repmgr:repmgr:foo
+node3:5432:replication:repluser:foo</programlisting>
+      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
+        the environment variable <envar>PGPASSFILE</envar>, or (from PostgreSQL 9.6) using the
+        <varname>passfile</varname> parameter in connection strings.
+      </para>
+      <para>
+        If using the <varname>passfile</varname> parameter, it's essential to ensure the file is in the same
+        location on all nodes, as when connecting to a remote node, the file referenced is the one on the
+        local node.
+      </para>
+      <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>
+
+</sect1>

doc/configuration-permissions.xml

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

doc/configuration.xml

@@ -148,9 +148,19 @@
             instances in the replication cluster which may potentially become a primary server or
             (in cascading replication) the upstream server of a standby.
           </para>
-          <para>
+         <para>
             PostgreSQL documentation: <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-WAL-SENDERS">max_wal_senders</ulink>.
           </para>
+          <note>
+            <para>
+              From <productname>PostgreSQL 12</productname>, <option>max_wal_senders</option>
+              <emphasis>must</emphasis> be set to the same or a higher value as the primary node
+              (at the time the node was cloned), otherwise the standby will refuse
+              to start (unless <option>hot_standby</option> is set to <literal>off</literal>, which
+              will prevent the node from accepting queries).
+            </para>
+          </note>
+
         </listitem>
       </varlistentry>
 
@@ -260,7 +270,7 @@
 
       <varlistentry>
 
-        <term><option>wal_keep_segments</option></term>
+        <term><option>wal_keep_segments</option> / <option>wal_keep_size</option></term>
 
         <listitem>
 
@@ -269,25 +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
+            Normally there is no need to set <option>wal_keep_segments</option>
-            is <emphasis>not</emphasis> a reliable way of ensuring that all required WAL segments are available to standbys.
+            (PostgreSQL 13 and later: <varname>wal_keep_size</varname>; default: <literal>0</literal>),
-            Replication slots and/or an archiving solution such as Barman are recommended to ensure standbys have a reliable
+            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
+            The only reason ever to set  <option>wal_keep_segments</option> / <option>wal_keep_size</option>
-            you have configured <option>pg_basebackup_options</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>
@@ -305,25 +326,10 @@
 
   &configuration-file;
   &configuration-file-required-settings;
+  &configuration-file-optional-settings;
   &configuration-file-log-settings;
   &configuration-file-service-commands;
+  &configuration-permissions;
+  &configuration-password-management;
 
-  <sect1 id="configuration-permissions" xreflabel="Database user permissions">
-    <title>repmgr database user permissions</title>
-
-    <indexterm>
-      <primary>configuration</primary>
-      <secondary>database user permissions</secondary>
-    </indexterm>
-
-    <para>
-      &repmgr; will create an extension database containing objects
-      for administering &repmgr; metadata. The user defined in the <varname>conninfo</varname>
-      setting must be able to access all objects. Additionally, superuser permissions
-      are required to install the &repmgr; extension. The easiest way to do this
-      is create the &repmgr; user as a superuser, however if this is not
-      desirable, the &repmgr; user can be created as a normal user and a
-      superuser specified with <literal>--superuser</literal> when registering a &repmgr; node.
-    </para>
-  </sect1>
 </chapter>

doc/event-notifications.xml

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

doc/filelist.xml

@@ -18,8 +18,11 @@
 <!ENTITY configuration      SYSTEM "configuration.xml">
 <!ENTITY configuration-file      SYSTEM "configuration-file.xml">
 <!ENTITY configuration-file-required-settings      SYSTEM "configuration-file-required-settings.xml">
+<!ENTITY configuration-file-optional-settings      SYSTEM "configuration-file-optional-settings.xml">
 <!ENTITY configuration-file-log-settings      SYSTEM "configuration-file-log-settings.xml">
 <!ENTITY configuration-file-service-commands   SYSTEM "configuration-file-service-commands.xml">
+<!ENTITY configuration-permissions   SYSTEM "configuration-permissions.xml">
+<!ENTITY configuration-password-management   SYSTEM "configuration-password-management.xml">
 <!ENTITY cloning-standbys  SYSTEM "cloning-standbys.xml">
 <!ENTITY promoting-standby  SYSTEM "promoting-standby.xml">
 <!ENTITY follow-new-primary  SYSTEM "follow-new-primary.xml">
@@ -32,7 +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">
@@ -53,11 +55,11 @@
 <!ENTITY repmgr-cluster-crosscheck SYSTEM "repmgr-cluster-crosscheck.xml">
 <!ENTITY repmgr-cluster-event SYSTEM "repmgr-cluster-event.xml">
 <!ENTITY repmgr-cluster-cleanup SYSTEM "repmgr-cluster-cleanup.xml">
-<!ENTITY repmgr-daemon-status SYSTEM "repmgr-daemon-status.xml">
+<!ENTITY repmgr-service-status SYSTEM "repmgr-service-status.xml">
+<!ENTITY repmgr-service-pause SYSTEM "repmgr-service-pause.xml">
+<!ENTITY repmgr-service-unpause SYSTEM "repmgr-service-unpause.xml">
 <!ENTITY repmgr-daemon-start SYSTEM "repmgr-daemon-start.xml">
 <!ENTITY repmgr-daemon-stop SYSTEM "repmgr-daemon-stop.xml">
-<!ENTITY repmgr-daemon-pause SYSTEM "repmgr-daemon-pause.xml">
-<!ENTITY repmgr-daemon-unpause SYSTEM "repmgr-daemon-unpause.xml">
 
 <!ENTITY appendix-release-notes  SYSTEM "appendix-release-notes.xml">
 <!ENTITY appendix-faq      SYSTEM "appendix-faq.xml">

doc/install-packages.xml

@@ -26,10 +26,18 @@
 	<ulink url="https://dl.2ndquadrant.com/">public repository</ulink>; see following
 	section for details.
   </para>
+  <note>
+    <para>
+      Currently the <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+	  <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> provides
+      support for RedHat/CentOS versions 5, 6 and 7. Support for version 8 is
+      available via the PGDG repository; see below for details.
+    </para>
+  </note>
   <para>
    RPM packages for &repmgr; are also available via Yum through
-   the PostgreSQL Global Development Group RPM repository
+   the PostgreSQL Global Development Group (PGDG) RPM repository
-   (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</ulink>).
+   (<ulink url="https://yum.postgresql.org/">https://yum.postgresql.org/</ulink>).
    Follow the instructions for your distribution (RedHat, CentOS,
    Fedora, etc.) and architecture as detailed there. Note that it can take some days
    for new &repmgr; packages to become available via the this repository.
@@ -42,6 +50,10 @@
       customers, as the PostgreSQL filesystem layout may be different to the community RPMs.
       Please contact your support vendor for assistance.
     </para>
+    <para>
+      See also <link linkend="appendix-faq">FAQ</link> entry
+      <xref linkend="faq-third-party-packages"/>.
+    </para>
   </note>
 
   <para>
@@ -81,9 +93,9 @@
 	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages).
 	  </para>
 	  <para>
-	    For example, for PostgreSQL 10 on CentOS, execute:
+	    For example, for PostgreSQL 11 on CentOS, execute:
 	    <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/10/rpm | sudo bash</programlisting>
+curl https://dl.2ndquadrant.com/default/release/get/11/rpm | sudo bash</programlisting>
 	  </para>
 
 	  <para>
@@ -99,8 +111,8 @@ curl https://dl.2ndquadrant.com/default/release/get/9.6/rpm | sudo bash</program
 sudo yum repolist</programlisting>
 	    The output should contain two entries like this:
 	    <programlisting>
-2ndquadrant-dl-default-release-pg10/7/x86_64        2ndQuadrant packages (PG10) for 7 - x86_64          4
+2ndquadrant-dl-default-release-pg11/7/x86_64         2ndQuadrant packages (PG11) for 7 - x86_64               18
-2ndquadrant-dl-default-release-pg10-debug/7/x86_64  2ndQuadrant packages (PG10) for 7 - x86_64 - Debug  3</programlisting>
+2ndquadrant-dl-default-release-pg11-debug/7/x86_64   2ndQuadrant packages (PG11) for 7 - x86_64 - Debug        8</programlisting>
 	  </para>
 	</listitem>
 
@@ -108,7 +120,7 @@ sudo yum repolist</programlisting>
           <para>
             Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
-sudo yum install repmgr10</programlisting>
+sudo yum install repmgr11</programlisting>
           </para>
           <note>
             <para>
@@ -153,19 +165,23 @@ yum search repmgr</programlisting>
       To install a specific package version, execute <command>yum --showduplicates list</command>
       for the package in question:
       <programlisting>
-        [root@localhost ~]# yum --showduplicates list repmgr10
+[root@localhost ~]# yum --showduplicates list repmgr11
-        Loaded plugins: fastestmirror
+Loaded plugins: fastestmirror
-        Loading mirror speeds from cached hostfile
+Loading mirror speeds from cached hostfile
-         * base: ftp.iij.ad.jp
+ * base: ftp.tsukuba.wide.ad.jp
-         * extras: ftp.iij.ad.jp
+ * epel: nrt.edge.kernel.org
-         * updates: ftp.iij.ad.jp
+ * extras: ftp.tsukuba.wide.ad.jp
-        Available Packages
+ * updates: ftp.tsukuba.wide.ad.jp
-		repmgr10.x86_64                       4.0.3-1.rhel7                        pgdg10
+Installed Packages
-		repmgr10.x86_64                       4.0.4-1.rhel7                        pgdg10
+repmgr11.x86_64                        4.4.0-1.rhel7                         @pgdg11
-		repmgr10.x86_64                       4.0.5-1.el7                          2ndquadrant-repo-10</programlisting>
+Available Packages
+repmgr11.x86_64                        4.2-1.el7                             2ndquadrant-dl-default-release-pg11
+repmgr11.x86_64                        4.2-2.el7                             2ndquadrant-dl-default-release-pg11
+repmgr11.x86_64                        4.3-1.el7                             2ndquadrant-dl-default-release-pg11
+repmgr11.x86_64                        4.4-1.el7                             2ndquadrant-dl-default-release-pg11</programlisting>
       then append the appropriate version number to the package name with a hyphen, e.g.:
       <programlisting>
-        [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
+[root@localhost ~]# yum install repmgr11-4.3-1.el7</programlisting>
     </para>
 
     <para>
@@ -190,7 +206,7 @@ yum search repmgr</programlisting>
   </indexterm>
 
   <para>.deb packages for &repmgr; are available from the
-  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
+  PostgreSQL Community APT repository (<ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink>).
   Instructions can be found in the APT section of the PostgreSQL Wiki
   (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink>).
   </para>
@@ -220,13 +236,13 @@ yum search repmgr</programlisting>
 
       <itemizedlist>
 
-	<listitem>
+	    <listitem>
-	  <para>
+	      <para>
             Install the repository definition for your distribution and PostgreSQL version
-	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages) by executing:
+	        (this enables the 2ndQuadrant repository as a source of &repmgr; packages) by executing:
             <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlisting>
+              curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlisting>
-	  </para>
+	      </para>
           <note>
             <para>
               This will automatically install the following additional packages, if not already present:
@@ -242,20 +258,20 @@ curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlist
           </note>
         </listitem>
 
-	<listitem>
+	    <listitem>
-	  <para>
+	      <para>
-            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr11</literal>):
             <programlisting>
-sudo apt-get install postgresql-10-repmgr</programlisting>
+              sudo apt-get install postgresql-11-repmgr</programlisting>
-	  </para>
+	      </para>
           <note>
             <para>
-            For packages for PostgreSQL 9.6 and earlier, the package name includes
+              For packages for PostgreSQL 9.6 and earlier, the package name includes
-            a period between major and minor version numbers, e.g.
+              a period between major and minor version numbers, e.g.
-            <literal>postgresql-9.6-repmgr</literal>.
+              <literal>postgresql-9.6-repmgr</literal>.
             </para>
           </note>
-	</listitem>
+	    </listitem>
 
       </itemizedlist>
 

doc/install-requirements.xml

@@ -14,7 +14,7 @@
   </para>
 
   <para>
-   &repmgr; 4.x 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>
@@ -39,13 +39,13 @@
 
   <note>
    <simpara>
-     The same &quot;major&quot; &repmgr; version (e.g. <literal>4.2.x</literal>) <emphasis>must</emphasis>
+     The same &quot;major&quot; &repmgr; version (e.g. <literal>&repmgrversion;.x</literal>) <emphasis>must</emphasis>
      be installed on all node in the replication cluster. We strongly recommend keeping all
      nodes on the same (preferably latest) &quot;minor&quot; &repmgr; version to minimize the risk
      of incompatibilities.
    </simpara>
    <simpara>
-     If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x)
+     If different &quot;major&quot; &repmgr; versions (e.g. 4.1.x and &repmgrversion;.x)
      are installed on different nodes, in the best case &repmgr; (in particular &repmgrd;)
      will not run. In the worst case, you will end up with a broken cluster.
    </simpara>
@@ -93,12 +93,15 @@
     <table id="repmgr-compatibility-matrix">
       <title>&repmgr; compatibility matrix</title>
 
-      <tgroup cols="3">
+      <tgroup cols="4">
         <thead>
           <row>
             <entry>
               &repmgr; version
             </entry>
+            <entry>
+              Supported?
+            </entry>
             <entry>
               Latest release
             </entry>
@@ -109,12 +112,62 @@
         </thead>
 
         <tbody>
+
+          <row>
+            <entry>
+              &repmgr; 5.2
+            </entry>
+            <entry>
+              YES
+            </entry>
+            <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
             </entry>
             <entry>
-              <link linkend="release-4.2">4.2</link> (2018-10-24)
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-4.4">4.4</link> (2019-06-27)
             </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
@@ -125,6 +178,9 @@
             <entry>
               &repmgr; 3.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-3.3.2.html">3.3.2</ulink> (2017-05-30)
             </entry>
@@ -137,6 +193,9 @@
             <entry>
               &repmgr; 2.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-2.0.3.html">2.0.3</ulink> (2015-04-16)
             </entry>
@@ -154,28 +213,61 @@
         The &repmgr; 2.x and 3.x series are no longer maintained or supported.
         We strongly recommend  upgrading to the latest &repmgr; version.
       </para>
+      <para>
+        Following the release of &repmgr; 5.0, there will be no further releases of
+        the &repmgr; 4.x series. Note that &repmgr; 5.x is an incremental development
+        of the 4.x series and &repmgr; 4.x users should upgrade to this as soon as possible.
+      </para>
     </important>
 
+  </sect2>
+
+  <sect2 id="install-postgresql-93-94">
+
+    <title>PostgreSQL 9.4 support</title>
+
+    <indexterm>
+      <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
+          In PostgreSQL 9.4, <command>pg_rewind</command> is not part of the core
-          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
           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>
 
+    <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 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>
+    </warning>
+
   </sect2>
+
  </sect1>

doc/install-source.xml

@@ -24,8 +24,7 @@
     <listitem>
      <para>
       <literal>Debian</literal> and <literal>Ubuntu</literal>: First
-      add the <ulink
+      add the <ulink url="https://apt.postgresql.org/">apt.postgresql.org</ulink>
-      url="http://apt.postgresql.org/">apt.postgresql.org</ulink>
       repository to your <filename>sources.list</filename> if you
       have not already done so, and ensure the source repository is enabled.
      </para>
@@ -36,8 +35,8 @@
          line in the repository file, which is usually
          <filename>/etc/apt/sources.list.d/pgdg.list</filename>, e.g.:
          <programlisting>
-deb http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
+deb https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
-deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
+deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
        </para>
      </tip>
      <para>
@@ -61,6 +60,9 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
          <itemizedlist spacing="compact" mark="bullet">
 
+           <listitem>
+             <simpara><literal>flex</literal></simpara>
+           </listitem>
            <listitem>
              <simpara><literal>libedit-dev</literal></simpara>
            </listitem>
@@ -115,6 +117,9 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
          <itemizedlist spacing="compact" mark="bullet">
 
+           <listitem>
+             <simpara><literal>flex</literal></simpara>
+           </listitem>
            <listitem>
              <simpara><literal>libselinux-devel</literal></simpara>
            </listitem>
@@ -173,17 +178,18 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
    <para>
     The source for &repmgr; is maintained at
-    <ulink url="https://github.com/2ndQuadrant/repmgr">https://github.com/2ndQuadrant/repmgr</ulink>.
+    <ulink url="https://github.com/EnterpriseDB/repmgr">https://github.com/EnterpriseDB/repmgr</ulink>.
    </para>
 
    <para>
-    There are also tags for each &repmgr; release, e.g. <literal>v4.2.0</literal>.
+    There are also tags for each <ulink url="https://github.com/EnterpriseDB/repmgr/releases">&repmgr; release</ulink>, e.g.
+    <literal><ulink url="https://github.com/EnterpriseDB/repmgr/releases/tag/v4.4.0">v4.4.0</ulink></literal>.
    </para>
 
    <para>
     Clone the source code using <application>git</application>:
     <programlisting>
-     git clone https://github.com/2ndQuadrant/repmgr</programlisting>
+     git clone https://github.com/EnterpriseDB/repmgr</programlisting>
    </para>
 
    <para>

doc/legal.xml

@@ -3,16 +3,16 @@
 <date>2017</date>
 
 <copyright>
- <year>2010-2019</year>
+ <year>2010-2021</year>
- <holder>2ndQuadrant, Ltd.</holder>
+ <holder>EnterpriseDB Corporation</holder>
 </copyright>
 
 <legalnotice id="legalnotice">
  <title>Legal Notice</title>
 
  <para>
-  <productname>repmgr</productname> is Copyright &copy; 2010-2019
+  <productname>repmgr</productname> is Copyright &copy; 2010-2021
-  by 2ndQuadrant, Ltd. All rights reserved.
+  by EnterpriseDB Corporation All rights reserved.
  </para>
 
  <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>
@@ -254,7 +254,7 @@
   </para>
   <programlisting>
     node_id=1
-    node_name=node1
+    node_name='node1'
     conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'
     data_directory='/var/lib/postgresql/data'
   </programlisting>
@@ -265,7 +265,6 @@
    server. See sections <xref linkend="configuration"/> and <xref linkend="configuration-file"/>
    for further details about <filename>repmgr.conf</filename>.
   </para>
-
   <note>
     <para>
       &repmgr; only uses <option>pg_bindir</option> when it executes
@@ -285,7 +284,7 @@
 
   <tip>
    <simpara>
-    For Debian-based distributions we recommend explictly setting
+    For Debian-based distributions we recommend explicitly setting
     <option>pg_bindir</option> to the directory where <command>pg_ctl</command> and other binaries
     not in the standard path are located. For PostgreSQL 9.6 this would be <filename>/usr/lib/postgresql/9.6/bin/</filename>.
    </simpara>
@@ -303,7 +302,7 @@
 
   <para>
    See the file
-   <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>
+   <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink>
     for details of all available configuration parameters.
   </para>
 
@@ -368,7 +367,7 @@
   </para>
   <programlisting>
     node_id=2
-    node_name=node2
+    node_name='node2'
     conninfo='host=node2 user=repmgr dbname=repmgr connect_timeout=2'
     data_directory='/var/lib/postgresql/data'</programlisting>
   <para>
@@ -478,6 +477,8 @@
     latest_end_lsn        | 0/7000538
     latest_end_time       | 2017-08-28 15:20:56.418735+09
     slot_name             |
+    sender_host           | node1
+    sender_port           | 5432
     conninfo              | user=repmgr dbname=replication host=node1 application_name=node2
    </programlisting>
    Note that the <varname>conninfo</varname> value is that generated in <filename>recovery.conf</filename>
@@ -497,11 +498,12 @@
   <para>
     Check the node is registered by executing <command>repmgr cluster show</command> on the standby:
     <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster show
+      $ repmgr -f /etc/repmgr.conf cluster show
-     ID | Name  | Role    | Status    | Upstream | Location | Connection string
+
-    ----+-------+---------+-----------+----------+----------+--------------------------------------
+     ID | Name  | Role    | Status    | Upstream | Location | Priority | Timeline | Connection string
-     1  | node1 | primary | * running |          | default  | host=node1 dbname=repmgr user=repmgr
+    ----+-------+---------+-----------+----------+----------+----------+----------+--------------------------------------
-     2  | node2 | standby |   running | node1    | default  | host=node2 dbname=repmgr user=repmgr</programlisting>
+     1  | node1 | primary | * running |          | default  | 100      | 1        | host=node1 dbname=repmgr user=repmgr
+     2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=node2 dbname=repmgr user=repmgr</programlisting>
   </para>
   <para>
    Both nodes are now registered with &repmgr; and the records have been copied to the standby server.

doc/repmgr-cluster-show.xml

@@ -18,7 +18,7 @@
     <para>
       Displays information about each registered node in the replication cluster. This
       command polls each registered server and shows its role (<literal>primary</literal> /
-      <literal>standby</literal> / <literal>bdr</literal>) and status. It polls each server
+      <literal>standby</literal>) and status. It polls each server
       directly and can be run on any node in the cluster; this is also useful when analyzing
       connectivity from a particular node.
     </para>
@@ -53,12 +53,13 @@
     <para>
     <programlisting>
     $ repmgr -f /etc/repmgr.conf cluster show
-
      ID | Name  | Role    | Status    | Upstream | Location | Priority | Timeline | Connection string
-    ----+-------+---------+-----------+----------+----------+----------+-----------------------------------------
+    ----+-------+---------+-----------+----------+----------+----------+----------+-----------------------------------------
      1  | node1 | primary | * running |          | default  | 100      | 1        | host=db_node1 dbname=repmgr user=repmgr
      2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=db_node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr</programlisting>
+     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr
+     4  | node4 | standby |   running | node1    | default  | 100      | 1        | host=db_node4 dbname=repmgr user=repmgr
+     5  | node5 | witness | * running | node1    | default  | 0        | n/a      | host=db_node5 dbname=repmgr user=repmgr</programlisting>
   </para>
   </refsect1>
   <refsect1>
@@ -82,18 +83,22 @@
 	  (but <literal>node3</literal> is not attached to it, and its metadata has not yet been updated);
 	  <literal>node4</literal> is running but rejecting connections (from <literal>node3</literal> at least).
       <programlisting>
-	 ID | Name  | Role    | Status               | Upstream | Location | Priority | Connection string
+     ID | Name  | Role    | Status               | Upstream | Location | Priority | Timeline | Connection string
-	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
+    ----+-------+---------+----------------------+----------+----------+----------+----------+----------------------------------------------------
-	 1  | node1 | primary | ? unreachable        |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
+     1  | node1 | primary | ? unreachable        |          | default  | 100      |          | host=db_node1 dbname=repmgr user=repmgr
-	 2  | node2 | standby | ! running as primary | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
+     2  | node2 | standby | ! running as primary | ? node1  | default  | 100      | 2        | host=db_node2 dbname=repmgr user=repmgr
-	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
+     3  | node3 | standby |   running            | ? node1  | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr
-	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
+     4  | node4 | standby | ? running            | ? node1  | default  | 100      |          | host=db_node4 dbname=repmgr user=repmgr
 
-	WARNING: following issues were detected
+    WARNING: following issues were detected
-	  - unable to connect to node "node1" (ID: 1)
+      - unable to connect to node "node1" (ID: 1)
-	  - node "node1" (ID: 1) is registered as an active primary but is unreachable
+      - node "node1" (ID: 1) is registered as an active primary but is unreachable
-	  - node "node2" (ID: 2) is registered as standby but running as primary
+      - node "node2" (ID: 2) is registered as standby but running as primary
-	  - unable to connect to node "node4" (ID: 4)
+      - unable to connect to node "node2" (ID: 2)'s upstream node "node1" (ID: 1)
+      - unable to determine if node "node2" (ID: 2) is attached to its upstream node "node1" (ID: 1)
+      - unable to connect to node "node3" (ID: 3)'s upstream node "node1" (ID: 1)
+      - unable to determine if node "node3" (ID: 3) is attached to its upstream node "node1" (ID: 1)
+      - unable to connect to node "node4" (ID: 4)
     HINT: execute with --verbose option to see connection error messages</programlisting>
     </para>
 	<para>
@@ -233,7 +238,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-daemon-status"/>
+     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-service-status"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-start.xml

@@ -14,18 +14,18 @@
 
   <refnamediv>
     <refname>repmgr daemon start</refname>
-    <refpurpose>Start the &repmgrd; daemon</refpurpose>
+    <refpurpose>Start the &repmgrd; daemon on the local node</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
-      This command starts the &repmgrd; daemon on the
+      This command starts the &repmgrd; service on the
       local node.
     </para>
     <para>
       By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
-      started. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
+      started. This behaviour can be overridden by specifying a different value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
 
@@ -197,7 +197,11 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-stop"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
+      <xref linkend="repmgr-daemon-stop"/>,
+      <xref linkend="repmgrd-daemon"/>,
+      <xref linkend="repmgr-service-status"/>,
+      <xref linkend="repmgr-service-pause"/>,
+      <xref linkend="repmgr-service-unpause"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-stop.xml

@@ -14,7 +14,7 @@
 
   <refnamediv>
     <refname>repmgr daemon stop</refname>
-    <refpurpose>Stop the &repmgrd; daemon</refpurpose>
+    <refpurpose>Stop the &repmgrd; daemon on the local node</refpurpose>
   </refnamediv>
 
   <refsect1>
@@ -26,7 +26,7 @@
 
     <para>
       By default, &repmgr; will wait for up to 15 seconds to confirm that &repmgrd;
-      stopped. This behaviour can be overridden by specifying a diffent value using the <option>--wait</option>
+      stopped. This behaviour can be overridden by specifying a different value using the <option>--wait</option>
       option, or disabled altogether with the <option>--no-wait</option> option.
     </para>
     <note>
@@ -194,7 +194,11 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-start"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
+      <xref linkend="repmgr-daemon-start"/>,
+      <xref linkend="repmgrd-daemon"/>,
+      <xref linkend="repmgr-service-status"/>,
+      <xref linkend="repmgr-service-pause"/>,
+      <xref linkend="repmgr-service-unpause"/>
     </para>
   </refsect1>
 

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

@@ -22,6 +22,10 @@
       This can optionally use <application>pg_rewind</application> to re-integrate
       a node which has diverged from the rest of the cluster, typically a failed primary.
     </para>
+    <para>
+      Note that <command>repmgr node rejoin</command> can only be used to attach
+      a standby to the current primary, not another standby.
+    </para>
 
     <tip>
       <para>
@@ -43,7 +47,12 @@
       <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 +80,7 @@
           </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 +216,18 @@
       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
+      The node's PostgreSQL instance  must have been shut down cleanly. If this was not the
-      need to be manually started (remove any existing <filename>recovery.conf</filename> file first)
+      case, it will need to be started up until it has reached a consistent recovery point,
-      until it has reached a consistent recovery point, then shut down cleanly.
+      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 +239,14 @@
           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 +262,7 @@
       <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>
@@ -264,6 +285,7 @@
       <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --force-rewind --config-files=postgresql.local.conf,postgresql.conf --verbose --dry-run
+    NOTICE: rejoin target is node "node3" (node ID: 3)
     INFO: replication connection to the rejoin target node was successful
     INFO: local and rejoin target system identifiers match
     DETAIL: system identifier is 6652184002263212600
@@ -283,7 +305,15 @@
       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
@@ -291,19 +321,30 @@
       </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
+        <option>--config-archive-dir</option>, default: <filename>/tmp</filename>)
-        complete.
+        and restored once the rewind operation is complete.
       </para>
-    </important>
+    </refsect2>
 
-    <para>
+    <refsect2 id="repmgr-node-rejoin-pg-rewind-example" xreflabel="example using repmgr node rejoin and pg_rewind">
-      Example, first using <literal>--dry-run</literal>, then actually executing the
+
-      <literal>node rejoin command</literal>.
+      <title>Example using <command>repmgr node rejoin</command> and <command>pg_rewind</command></title>
-    <programlisting>
+
+      <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
+    NOTICE: rejoin target is node "node3" (node ID: 3)
     INFO: replication connection to the rejoin target node was successful
     INFO: local and rejoin target system identifiers match
     DETAIL: system identifier is 6652460429293670710
@@ -317,17 +358,17 @@
       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>
+        <note>
-      <para>
+          <para>
-        If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
+            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
+            this checks the prerequisites for using <application>pg_rewind</application>, but is
-        not an absolute guarantee that actually executing <application>pg_rewind</application>
+            not an absolute guarantee that actually executing <application>pg_rewind</application>
-        will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
+            will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
-      </para>
+          </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 +380,8 @@
     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">
@@ -356,7 +397,7 @@
      <command>repmgr node rejoin</command> attempts to determine whether it will succeed by
      comparing the timelines and relative WAL positions of the local node (rejoin candidate) and primary
      (rejoin target). This is particularly important if planning to use <application>pg_rewind</application>,
-     which currently (as of PostgreSQL 11) may appear to succeed (or indicate there is no action
+     which currently (as of PostgreSQL 12) may appear to succeed (or indicate there is no action
      needed) but potentially allow an impossible action, such as trying to rejoin a standby to a
      primary which is behind the standby. &repmgr; will prevent this situation from occurring.
    </para>
@@ -369,6 +410,11 @@
      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 +424,52 @@
      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://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=2b4f3130382fe2f8705863e4d38589d4d69cd695">patch</ulink>
+       has been successfully submitted and will be included the next PostgreSQL minor release round, scheduled for
+       February 2021.
+     </para>
+     <para>
+       As a workaround, start the primary server the standby was previously attached to,
+       and ensure the standby can be attached to it. If <application>pg_rewind</application> was actually executed,
+       it will have copied in the <filename>.history</filename> file from the target primary server; this must
+       be removed. <command>repmgr node rejoin</command> can then be used to attach the standby to the original
+       primary. Ensure any changes pending on the primary have propagated to the standby. Then shut down the primary
+       server <emphasis>first</emphasis>, before shutting down the standby. It should then be possible to
+       use <command>repmgr node rejoin</command> to attach the standby to the new primary.
+     </para>
+   </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>
@@ -114,38 +128,38 @@
     <para>
       See what action would be taken for a restart:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --action=restart --checkpoint --dry-run
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --action=restart --checkpoint --dry-run
 INFO: a CHECKPOINT would be issued here
-INFO: would execute server command "sudo service postgresql-11 restart"</programlisting>
+INFO: would execute server command "sudo service postgresql-12 restart"</programlisting>
     </para>
 
     <para>
       Restart the PostgreSQL instance:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --action=restart --checkpoint
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --action=restart --checkpoint
 NOTICE: issuing CHECKPOINT
-DETAIL: executing server command "sudo service postgresql-11 restart"
+DETAIL: executing server command "sudo service postgresql-12 restart"
-Redirecting to /bin/systemctl restart postgresql-11.service</programlisting>
+Redirecting to /bin/systemctl restart postgresql-12.service</programlisting>
     </para>
 
     <para>
       List all commands:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --list-actions
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --list-actions
 Following commands would be executed for each action:
 
-    start: "sudo service postgresql-11 start"
+    start: "sudo service postgresql-12 start"
-     stop: "sudo service postgresql-11 stop"
+     stop: "sudo service postgresql-12 stop"
-  restart: "sudo service postgresql-11 restart"
+  restart: "sudo service postgresql-12 restart"
-   reload: "sudo service postgresql-11 reload"
+   reload: "sudo service postgresql-12 reload"
-  promote: "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote"</programlisting>
+  promote: "/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote"</programlisting>
     </para>
 
     <para>
       List a single command:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --list-actions --action=promote
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --list-actions --action=promote
-/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote      </programlisting>
+/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote      </programlisting>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-primary-register.xml

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

doc/repmgr-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-service-pause.xml

@@ -1,6 +1,6 @@
-<refentry id="repmgr-daemon-pause">
+<refentry id="repmgr-service-pause">
   <indexterm>
-    <primary>repmgr daemon pause</primary>
+    <primary>repmgr service pause</primary>
   </indexterm>
 
   <indexterm>
@@ -9,11 +9,11 @@
   </indexterm>
 
   <refmeta>
-    <refentrytitle>repmgr daemon pause</refentrytitle>
+    <refentrytitle>repmgr service pause</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr daemon pause</refname>
+    <refname>repmgr service pause</refname>
     <refpurpose>Instruct all &repmgrd; instances in the replication cluster to pause failover operations</refpurpose>
   </refnamediv>
 
@@ -32,20 +32,29 @@
     <note>
       <para>
         It's important to wait a few seconds after restarting PostgreSQL on any node before running
-        <command>repmgr daemon pause</command>, as the &repmgrd; instance
+        <command>repmgr service pause</command>, as the &repmgrd; instance
         on the restarted node will take a second or two before it has updated its status.
       </para>
     </note>
     <para>
-      <xref linkend="repmgr-daemon-unpause"/> will instruct all previously paused &repmgrd;
+      <xref linkend="repmgr-service-unpause"/> will instruct all previously paused &repmgrd;
       instances to resume normal failover operation.
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Prerequisites</title>
+    <para>
+      PostgreSQL must be accessible on all nodes (using the <varname>conninfo</varname> string shown by
+      <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>)
+      from the node where <command>repmgr service pause</command> is executed.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Execution</title>
     <para>
-      <command>repmgr daemon pause</command> can be executed on any active node in the
+      <command>repmgr service pause</command> can be executed on any active node in the
       replication cluster. A valid <filename>repmgr.conf</filename> file is required.
       It will have no effect on previously paused nodes.
     </para>
@@ -55,7 +64,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon pause
+$ repmgr -f /etc/repmgr.conf service pause
 NOTICE: node 1 (node1) paused
 NOTICE: node 2 (node2) paused
 NOTICE: node 3 (node3) paused</programlisting>
@@ -79,7 +88,7 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
+      One of the following exit codes will be emitted by <command>repmgr service unpause</command>:
     </para>
     <variablelist>
 
@@ -107,7 +116,11 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-daemon-status"/>
+      <xref linkend="repmgr-service-unpause"/>,
+      <xref linkend="repmgr-service-status"/>,
+      <xref linkend="repmgrd-pausing"/>,
+      <xref linkend="repmgr-daemon-start"/>,
+      <xref linkend="repmgr-daemon-stop"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-service-status.xml

@@ -1,19 +1,19 @@
-<refentry id="repmgr-daemon-status">
+<refentry id="repmgr-service-status">
   <indexterm>
-    <primary>repmgr daemon status</primary>
+    <primary>repmgr service status</primary>
   </indexterm>
 
   <indexterm>
     <primary>repmgrd</primary>
-    <secondary>displaying daemon status</secondary>
+    <secondary>displaying service status</secondary>
   </indexterm>
 
   <refmeta>
-    <refentrytitle>repmgr daemon status</refentrytitle>
+    <refentrytitle>repmgr service status</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr daemon status</refname>
+    <refname>repmgr service status</refname>
     <refpurpose>display information about the status of &repmgrd; on each node in the cluster</refpurpose>
   </refnamediv>
 
@@ -22,21 +22,33 @@
     <para>
       This command provides an overview over all active nodes in the cluster and the state
       of each node's &repmgrd; instance. It can be used to check
-      the result of <xref linkend="repmgr-daemon-pause"/> and <xref linkend="repmgr-daemon-unpause"/>
+      the result of <xref linkend="repmgr-service-pause"/> and <xref linkend="repmgr-service-unpause"/>
       operations.
     </para>
   </refsect1>
 
+  <refsect1>
+    <title>Prerequisites</title>
+    <para>
+      PostgreSQL should be accessible on all nodes (using the <varname>conninfo</varname> string shown by
+      <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>)
+      from the node where <command>repmgr service status</command> is executed.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Execution</title>
     <para>
-      <command>repmgr daemon status</command> can be executed on any active node in the
+      <command>repmgr service status</command> can be executed on any active node in the
       replication cluster. A valid <filename>repmgr.conf</filename> file is required.
     </para>
     <para>
-      If PostgreSQL is not running on a node, &repmgr; will not be able to determine the
+      If a node is not accessible, or PostgreSQL itself is not running on the node,
-      status of that node's &repmgrd; instance.
+      &repmgr; will not be able to determine the status of that node's &repmgrd; instance,
+      and &quot;<literal>n/a</literal>&quot; will be displayed in the node's <literal>repmgrd</literal>
+      column.
     </para>
+
     <note>
       <para>
         After restarting PostgreSQL on any node, the &repmgrd; instance
@@ -51,7 +63,7 @@
     <title>Examples</title>
     <para>
       &repmgrd; running normally on all nodes:
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running | 96563 | no      | n/a
@@ -60,8 +72,8 @@
     </para>
 
     <para>
-      &repmgrd; paused on all nodes (using <xref linkend="repmgr-daemon-pause"/>):
+      &repmgrd; paused on all nodes (using <xref linkend="repmgr-service-pause"/>):
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running | 96563 | yes     | n/a
@@ -71,7 +83,7 @@
 
     <para>
       &repmgrd; not running on one node:
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd     | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+-------------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running     | 96563 | yes     | n/a
@@ -89,11 +101,11 @@
         <term><option>--csv</option></term>
         <listitem>
           <para>
-            <command>repmgr daemon status</command> accepts an optional parameter <literal>--csv</literal>, which
+            <command>repmgr service status</command> accepts an optional parameter <literal>--csv</literal>, which
             outputs the replication cluster's status in a simple CSV format, suitable for
             parsing by scripts, e.g.:
             <programlisting>
-    $ repmgr -f /etc/repmgr.conf daemon status --csv
+    $ repmgr -f /etc/repmgr.conf service status --csv
     1,node1,primary,1,1,5722,1,100,-1,default
     2,node2,standby,1,0,-1,1,100,1,default
     3,node3,standby,1,1,5779,1,100,1,default</programlisting>
@@ -171,7 +183,7 @@
         <listitem>
           <para>
             Display additional information (<literal>location</literal>, <literal>priority</literal>)
-			about the &repmgr; configuration.
+	    about the &repmgr; configuration.
           </para>
         </listitem>
       </varlistentry>
@@ -180,7 +192,7 @@
         <term><option>--verbose</option></term>
         <listitem>
           <para>
-            Display the full text of any database connection error messages
+            Display the full text of any database connection error messages.
           </para>
         </listitem>
       </varlistentry>
@@ -192,7 +204,12 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-cluster-show"/>
+      <xref linkend="repmgr-service-pause"/>,
+      <xref linkend="repmgr-service-unpause"/>,
+      <xref linkend="repmgr-cluster-show"/>,
+      <xref linkend="repmgrd-pausing"/>,
+      <xref linkend="repmgr-daemon-start"/>,
+      <xref linkend="repmgr-daemon-stop"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-service-unpause.xml

@@ -1,6 +1,6 @@
-<refentry id="repmgr-daemon-unpause">
+<refentry id="repmgr-service-unpause">
   <indexterm>
-    <primary>repmgr daemon unpause</primary>
+    <primary>repmgr service unpause</primary>
   </indexterm>
 
   <indexterm>
@@ -8,13 +8,12 @@
     <secondary>unpausing</secondary>
   </indexterm>
 
-
   <refmeta>
-    <refentrytitle>repmgr daemon unpause</refentrytitle>
+    <refentrytitle>repmgr service unpause</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr daemon unpause</refname>
+    <refname>repmgr service unpause</refname>
     <refpurpose>Instruct all &repmgrd; instances in the replication cluster to resume failover operations</refpurpose>
   </refnamediv>
 
@@ -23,24 +22,33 @@
     <para>
       This command can be run on any active node in the replication cluster to instruct all
       running &repmgrd; instances to &quot;unpause&quot;
-      (following a previous execution of <xref linkend="repmgr-daemon-pause"/>)
+      (following a previous execution of <xref linkend="repmgr-service-pause"/>)
       and resume normal failover/monitoring operation.
     </para>
 
     <note>
       <para>
         It's important to wait a few seconds after restarting PostgreSQL on any node before running
-        <command>repmgr daemon pause</command>, as the &repmgrd; instance
+        <command>repmgr service pause</command>, as the &repmgrd; instance
         on the restarted node will take a second or two before it has updated its status.
       </para>
     </note>
 
   </refsect1>
 
+  <refsect1>
+    <title>Prerequisites</title>
+    <para>
+      PostgreSQL must be accessible on all nodes (using the <varname>conninfo</varname> string shown by
+      <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>)
+      from the node where <command>repmgr service pause</command> is executed.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Execution</title>
     <para>
-     <command>repmgr daemon unpause</command> can be executed on any active node in the
+     <command>repmgr service unpause</command> can be executed on any active node in the
       replication cluster. A valid <filename>repmgr.conf</filename> file is required.
       It will have no effect on nodes which are not already paused.
     </para>
@@ -50,7 +58,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon unpause
+$ repmgr -f /etc/repmgr.conf service unpause
 NOTICE: node 1 (node1) unpaused
 NOTICE: node 2 (node2) unpaused
 NOTICE: node 3 (node3) unpaused</programlisting>
@@ -74,7 +82,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
+      One of the following exit codes will be emitted by <command>repmgr service unpause</command>:
     </para>
     <variablelist>
 
@@ -102,7 +110,11 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-status"/>
+      <xref linkend="repmgr-service-pause"/>,
+      <xref linkend="repmgr-service-status"/>,
+      <xref linkend="repmgrd-pausing"/>,
+      <xref linkend="repmgr-daemon-start"/>,
+      <xref linkend="repmgr-daemon-stop"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-standby-clone.xml

@@ -18,7 +18,7 @@
     <para>
       <command>repmgr standby clone</command> clones a PostgreSQL node from another
       PostgreSQL node, typically the primary, but optionally from any other node in
-      the cluster or from Barman. It creates the <filename>recovery.conf</filename> file required
+      the cluster or from Barman. It creates the replication configuration required
       to attach the cloned node to the primary node (or another standby, if cascading replication
       is in use).
     </para>
@@ -85,28 +85,25 @@
   </refsect1>
 
   <refsect1 id="repmgr-standby-clone-recovery-conf">
-    <title>Customising recovery.conf</title>
+    <title>Customising replication configuration</title>
     <indexterm>
      <primary>recovery.conf</primary>
      <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
     </indexterm>
 
+	<indexterm>
+     <primary>replication configuration</primary>
+     <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
+    </indexterm>
+
 
    <para>
-     By default, &repmgr; will create a minimal <filename>recovery.conf</filename>
+     By default, &repmgr; will create a minimal replication configuration
      containing following parameters:
    </para>
 
    <itemizedlist spacing="compact" mark="bullet">
 
-     <listitem>
-       <simpara><varname>standby_mode</varname> (always <literal>'on'</literal>)</simpara>
-     </listitem>
-
-     <listitem>
-       <simpara><varname>recovery_target_timeline</varname> (always <literal>'latest'</literal>)</simpara>
-     </listitem>
-
      <listitem>
        <simpara><varname>primary_conninfo</varname></simpara>
      </listitem>
@@ -117,9 +114,24 @@
 
    </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 <filename>recovery.conf</filename>:
+     for inclusion in the replication configuration:
    </para>
 
    <itemizedlist spacing="compact" mark="bullet">
@@ -170,7 +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>
@@ -183,11 +198,35 @@
    </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>replication configuration</primary>
+     <secondary>generating for a standby cloned by another method</secondary>
+   </indexterm>
+
    <indexterm>
      <primary>recovery.conf</primary>
      <secondary>generating for a standby cloned by another method</secondary>
@@ -195,34 +234,55 @@
 
    <para>
      &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
-     <command><ulink url="http://docs.pgbarman.org/release/2.5/#recover">barman recover</ulink></command> command).
+     <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command> command).
    </para>
    <para>
      To integrate the standby as a &repmgr; node, once the standby has been cloned,
      ensure the <filename>repmgr.conf</filename>
      file is created for the node, and that it has been registered using
      <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>.
-     Then execute the command <command>repmgr standby clone --recovery-conf-only</command>.
+   </para>
+   <tip>
+     <para>
+       To register a standby which is not running, execute
+       <link linkend="repmgr-standby-register">repmgr standby register --force</link>
+       and provide the connection details for the primary.
+     </para>
+     <para>
+       See <xref linkend="repmgr-standby-register-inactive-node"/> for more details.
+     </para>
+   </tip>
+   <para>
+     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, and will also create a replication slot on the
+     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
      upstream node if required.
    </para>
    <para>
-     Note that the upstream node must be running. An existing
+     The upstream node must be running so the correct replication configuration can be obtained.
-     <filename>recovery.conf</filename> will not be overwritten unless the
-     <option>-F/--force</option> option is provided.
    </para>
    <para>
-     Execute <command>repmgr standby clone --recovery-conf-only --dry-run</command>
+     If the standby is running, the replication configuration will not be written unless the
-     to check the prerequisites for creating the <filename>recovery.conf</filename> file,
+     <option>-F/--force</option> option is provided.
-     and display the contents of the file without actually creating it.
+   </para>
+   <tip>
+     <para>
+       Execute <command>repmgr standby clone --replication-conf-only --dry-run</command>
+       to check the prerequisites for creating the recovery configuration,
+       and display the configuration changes which would be made without actually
+	   making any changes.
+     </para>
+   </tip>
+   <para>
+     In PostgreSQL 13 and later, the PostgreSQL configuration must be reloaded for replication
+     configuration changes to take effect.
+   </para>
+   <para>
+     In PostgreSQL 12 and earlier, the PostgreSQL instance must be restarted for replication
+     configuration changes to take effect.
    </para>
 
-   <note>
-     <para>
-       <option>--recovery-conf-only</option> was introduced in &repmgr; <link linkend="release-4.0.4">4.0.4</link>.
-     </para>
-   </note>
 
   </refsect1>
 
@@ -248,9 +308,9 @@
             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 <filename>recovery.conf</filename> file will be displayed
+            the generated recovery configuration will be displayed
-            but the file itself not written.
+            but not written.
           </para>
         </listitem>
       </varlistentry>
@@ -284,6 +344,25 @@
         </listitem>
       </varlistentry>
 
+
+      <varlistentry>
+        <term><option>--recovery-min-apply-delay</option></term>
+        <listitem>
+          <para>
+            Set PostgreSQL configuration <option>recovery_min_apply_delay</option> parameter
+            to the provided value.
+          </para>
+          <para>
+            This overrides any <option>recovery_min_apply_delay</option> provided via
+            <filename>repmgr.conf</filename>.
+          </para>
+          <para>
+            For more details on this parameter, see:
+            <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-RECOVERY-MIN-APPLY-DELAY">recovery_min_apply_delay</ulink>.
+          </para>
+        </listitem>
+      </varlistentry>
+
       <varlistentry>
         <term><option>-R, --remote-user=USERNAME</option></term>
         <listitem>
@@ -294,11 +373,19 @@
       </varlistentry>
 
       <varlistentry>
-        <term><option> --recovery-conf-only</option></term>
+        <term><option>--replication-conf-only</option></term>
         <listitem>
           <para>
-            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr; 4.0.4 and later.
+            Create recovery configuration for a previously cloned instance.
           </para>
+		  <para>
+			In PostgreSQL 12 and later, the replication configuration will be
+			written to <filename>postgresql.auto.conf</filename>.
+		  </para>
+		  <para>
+			In PostgreSQL 11 and earlier, the replication configuration will be
+			written to <filename>recovery.conf</filename>.
+		  </para>
         </listitem>
       </varlistentry>
 
@@ -326,9 +413,13 @@
         <term><option>--upstream-conninfo</option></term>
         <listitem>
           <para>
-            <literal>primary_conninfo</literal> value to write in recovery.conf
+            <literal>primary_conninfo</literal> value to include in the recovery configuration
             when the intended upstream server does not yet exist.
           </para>
+          <para>
+            Note that &repmgr; may modify the provided value, in particular to set the
+            correct <literal>application_name</literal>.
+          </para>
         </listitem>
       </varlistentry>
 
@@ -340,6 +431,23 @@
           </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

@@ -20,49 +20,62 @@
       ("follow target"). Typically this will be the primary, but this
       command can also be used to attach the standby to another standby.
     </para>
+
     <para>
-      This command requires a valid
+      This command requires a valid <filename>repmgr.conf</filename> file for the standby,
-      <filename>repmgr.conf</filename> file for the standby, either specified
+      either specified explicitly with <literal>-f/--config-file</literal> or located in a
-      explicitly with <literal>-f/--config-file</literal> or located in a
       default location; no additional arguments are required.
     </para>
 
-	<para>
+    <para>The standby node (&quot;follow candidate&quot;) <emphasis>must</emphasis>
-	  By default &repmgr; will attempt to attach the standby to the current primary.
+      be running. If the new upstream (&quot;follow target&quot;) is not the primary,
-	  If <option>--upstream-node-id</option> is provided, &repmgr; will attempt
+      the cluster primary <emphasis>must</emphasis> be running and accessible from the
-	  to attach the standby to the specified node, which can be another standby.
+      standby node.
-	</para>
-
-    <para>
-      This command will force a restart of the standby server, which must be
-      running.
     </para>
 
-	<tip>
+    <tip>
       <para>
-		To re-add an inactive node to the replication cluster, use
+        To re-add an inactive node to the replication cluster, use
-		<xref linkend="repmgr-node-rejoin"/>.
+        <xref linkend="repmgr-node-rejoin"/>.
       </para>
-	</tip>
+    </tip>
 
-	<para>
+    <para>
-	  <command>repmgr standby follow</command> will wait up to
+      By default &repmgr; will attempt to attach the standby to the current primary.
-	  <varname>standby_follow_timeout</varname> seconds (default: <literal>30</literal>)
+      If <option>--upstream-node-id</option> is provided, &repmgr; will attempt
-	  to verify the standby has actually connected to the new upstream node.
+      to attach the standby to the specified node, which can be another standby.
-	</para>
+    </para>
 
-	<note>
+    <para>
-	  <para>
+      In PostgreSQL 12 and earlier, this command will force a restart of PostgreSQL on the standby node.
-	    If <option>recovery_min_apply_delay</option> is set for the standby, it
+    </para>
-	    will not attach to the new upstream node until it has replayed available
+
-	    WAL.
+    <para>
-	  </para>
+      In PostgreSQL 13 and later, by default this command will signal PostgreSQL to reload its
-	  <para>
+      configuration, which will cause PostgreSQL to follow the new upstream without
-	    Conversely, if the standby is attached to an upstream standby
+      a restart. If this behaviour is not desired for whatever reason, the configuration
-	    which has <option>recovery_min_apply_delay</option> set, the upstream
+      file parameter <varname>standby_follow_restart</varname> can be set <literal>true</literal>
-            standby's replay state may actually be behind that of its new downstream node.
+      to always force a restart.
-	  </para>
+    </para>
-	</note>
+
+    <para>
+      <command>repmgr standby follow</command> will wait up to
+      <varname>standby_follow_timeout</varname> seconds (default: <literal>30</literal>)
+      to verify the standby has actually connected to the new upstream node.
+    </para>
+
+    <note>
+      <para>
+        If <option>recovery_min_apply_delay</option> is set for the standby, it
+        will not attach to the new upstream node until it has replayed available
+        WAL.
+      </para>
+      <para>
+        Conversely, if the standby is attached to an upstream standby
+        which has <option>recovery_min_apply_delay</option> set, the upstream
+        standby's replay state may actually be behind that of its new downstream node.
+      </para>
+    </note>
 
   </refsect1>
 
@@ -124,7 +137,7 @@
           <para>
             Note that when using &repmgrd;, <option>--upstream-node-id</option>
             should always be configured;
-			see <link linkend="repmgrd-automatic-failover-configuration">Automatic failover configuration</link>
+            see <link linkend="repmgrd-automatic-failover-configuration">Automatic failover configuration</link>
             for details.
           </para>
         </listitem>
@@ -166,7 +179,7 @@
       be possible to follow the new upstream node, and &repmgr; will emit an error
       message like this:
       <programlisting>
-ERROR: this node cannot attach to follow target node 3
+ERROR: this node cannot attach to follow target node &quot;node3&quot; (ID 3)
 DETAIL: follow target server's timeline 2 forked off current database system timeline 1 before current recovery point 0/6108880</programlisting>
     </para>
     <para>

doc/repmgr-standby-promote.xml

@@ -23,7 +23,8 @@
     <important>
       <para>
         If &repmgrd; is active, you must execute
-        <command><link linkend="repmgr-daemon-pause">repmgr daemon pause</link></command>
+        <command><link linkend="repmgr-service-pause">repmgr service pause</link></command>
+        (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-pause">repmgr service pause</link></command>)
         to temporarily disable &repmgrd; while making any changes
         to the replication cluster.
       </para>
@@ -65,10 +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
+        In PostgreSQL 12 and earlier, if WAL replay is paused on the standby, and not all
-        replayed, &repmgr; will not attempt to promote it.
+        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
@@ -80,11 +81,15 @@
         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>
 
 
+
   <refsect1>
     <title>Example</title>
     <para>
@@ -93,13 +98,46 @@
       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>
   </refsect1>
 
 
+  <refsect1>
+    <title>User permission requirements</title>
+    <para><emphasis>pg_promote() (PostgreSQL 12 and later)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; will attempt to use the built-in <function>pg_promote()</function>
+      function to promote a standby to primary.
+    </para>
+    <para>
+      By default, execution of <function>pg_promote()</function> is restricted to superusers.
+      If the <literal>repmgr</literal> user does not have permission to execute
+      <function>pg_promote()</function>, &repmgr; will fall back to using &quot;<command>pg_ctl promote</command>&quot;.
+    </para>
+    <tip>
+      <para>
+        Execute <command>repmgr standby promote</command> with the <option>--dry-run</option>
+        to check whether the &repmgr; user has permission to execute <function>pg_promote()</function>.
+      </para>
+      <para>
+        If the <literal>repmgr</literal> user is not a superuser, execution permission for this
+        function can be granted with e.g.:
+        <programlisting>
+    GRANT EXECUTE ON FUNCTION pg_catalog.pg_promote TO repmgr</programlisting>
+      </para>
+      <para>
+        Note that permissions are only effective for the database they are granted in, so
+        this <emphasis>must</emphasis> be executed in the &repmgr; database to be effective.
+      </para>
+    </tip>
+    <para>
+      For more details on <function>pg_promote()</function>, see the
+      <ulink url="https://www.postgresql.org/docs/current/functions-admin.html#FUNCTIONS-RECOVERY-CONTROL-TABLE">PostgreSQL documentation</ulink>.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Options</title>
     <variablelist>
@@ -134,6 +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 accommodate the standbys which will
+                  be attached to it, the standby will be promoted anyway.
+                </simpara>
+              </listitem>
+              <listitem>
+                <simpara>
+                  If replication slots are in use but the promotion candidate has insufficient free replication slots
+                  to accommodate 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>
 
@@ -171,6 +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

@@ -75,10 +75,22 @@
    <para>
     Under some circumstances you may wish to register a standby which is not
     yet running; this can be the case when using provisioning tools to create
-    a complex replication cluster. In this case, by using the <option>-F/--force</option>
+    a complex replication cluster, or if the node was not cloned by &repmgr;.
-    option and providing the connection parameters to the primary server,
-    the standby can be registered.
    </para>
+   <para>
+    In this case, by using the <option>-F/--force</option>
+    option and providing the connection parameters to the primary server,
+    the standby can be registered even if it has not yet been started.
+   </para>
+   <tip>
+     <para>
+       Connection parameters can either be provided either as a <literal>conninfo</literal> string
+       (e.g. <option>-d 'host=node1 user=repmgr'</option> or as individual connection parameters
+        (<option>-h/--host</option>, <option>-d/--dbname</option>,
+       <option>-U/--user</option>, <option>-p/--port</option> etc.).
+     </para>
+   </tip>
+
    <para>
     Similarly, with cascading replication it may be necessary to register
     a standby whose upstream node has not yet been registered - in this case,
@@ -96,9 +108,11 @@
     <title>Registering a node not cloned by repmgr</title>
     <para>
       If you've cloned a standby using another method (e.g. <application>barman</application>'s
-     <command>barman recover</command> command), first execute
+     <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command>
-     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
+     command), register the node as detailed in section
-     to add the <filename>recovery.conf</filename> file, then register the standby as usual.
+     <xref linkend="repmgr-standby-register-inactive-node"/> then execute
+     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --replication-conf-only</link>
+     to generate the appropriate replication configuration.
     </para>
   </refsect1>
 
@@ -119,7 +133,7 @@
 
 
       <varlistentry>
-       <term><option>-F</option><option>--force</option></term>
+       <term><option>-F</option>/<option>--force</option></term>
         <listitem>
           <para>
             Overwrite an existing node record

doc/repmgr-standby-switchover.xml

@@ -63,6 +63,38 @@
   </refsect1>
 
   <refsect1>
+    <title>User permission requirements</title>
+    <para><emphasis>CHECKPOINT</emphasis></para>
+    <para>
+      &repmgr; executes <command>CHECKPOINT</command> on the demotion candidate as part of the shutdown
+      process to ensure it shuts down as smoothly as possible.
+    </para>
+    <para>
+      Note that <command>CHECKPOINT</command> requires database superuser permissions to execute.
+      If the <literal>repmgr</literal> user is not a superuser, the name of a superuser should be
+      provided with the <option>-S</option>/<option>--superuser</option>.
+    </para>
+    <para>
+      If &repmgr; is unable to execute the <command>CHECKPOINT</command> command, the switchover
+      can still be carried out, albeit at a greater risk that the demotion candidate may not
+      be able to shut down as smoothly as might otherwise have been the case.
+    </para>
+    <para><emphasis>pg_promote() (PostgreSQL 12 and later)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; defaults to using the built-in <command>pg_promote()</command> function to
+      promote a standby to primary.
+    </para>
+    <para>
+      Note that execution of <function>pg_promote()</function> is restricted to superusers or to
+      any user who has been granted execution permission for this function. If the &repmgr; user
+      is not permitted to execute <function>pg_promote()</function>, &repmgr; will fall back to using
+      &quot;<command>pg_ctl promote</command>&quot;. For more details see
+      <link linkend="repmgr-standby-promote">repmgr standby promote</link>.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
     <title>Options</title>
     <variablelist>
 
@@ -115,7 +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>
@@ -184,6 +216,17 @@
           </note>
         </listitem>
       </varlistentry>
+
+     <varlistentry>
+        <term><option>-S</option>/<option>--superuser</option></term>
+        <listitem>
+          <para>
+            Use the named superuser instead of the normal &repmgr; user to perform
+            actions requiring superuser permissions.
+          </para>
+        </listitem>
+     </varlistentry>
+
     </variablelist>
 
   </refsect1>

doc/repmgr-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

@@ -18,7 +18,7 @@
  <title>repmgr &repmgrversion; Documentation</title>
 
  <bookinfo>
-  <corpauthor>2ndQuadrant Ltd</corpauthor>
+  <corpauthor>EnterpriseDB Corporation</corpauthor>
   <productname>repmgr</productname>
   <productnumber>&repmgrversion;</productnumber>
   &legal;
@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.3 - PostgreSQL 11.
+   use with PostgreSQL 9.4 - PostgreSQL 13.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -38,20 +38,20 @@
 
    <para>
     &repmgr; is developed by
-    <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+    <ulink url="https://2ndquadrant.com">2ndQuadrant (EDB)</ulink>
     along with contributions from other individuals and organisations.
     Contributions from the community are appreciated and welcome - get
-    in touch via <ulink url="https://github.com/2ndQuadrant/repmgr">github</ulink>
+    in touch via <ulink url="https://github.com/EnterpriseDB/repmgr">github</ulink>
     or <ulink url="https://groups.google.com/group/repmgr">the mailing list/forum</ulink>.
-    Multiple 2ndQuadrant customers contribute funding
+    Multiple 2ndQuadrant (EDB) customers contribute funding
     to make repmgr development possible.
    </para>
 
    <para>
-     &repmgr; is fully supported by 2ndQuadrant's
+     &repmgr; is fully supported by 2ndQuadrant (EDB)'s
      <ulink url="https://www.2ndquadrant.com/en/support/support-postgresql/">24/7 Production Support</ulink>.
-     2ndQuadrant, a Major Sponsor of the PostgreSQL project, continues to develop and maintain &repmgr;.
+     EnterpriseDB Corporation, a Major Sponsor of the PostgreSQL project, continues to maintain &repmgr;.
-     Other organisations as well as individual developers are welcome to participate in the efforts.
+     We welcome participation from other organisations and individual developers.
    </para>
   </abstract>
 
@@ -91,7 +91,6 @@
   &repmgrd-automatic-failover;
   &repmgrd-configuration;
   &repmgrd-operation;
-  &repmgrd-bdr;
  </part>
 
  <part id="repmgr-command-reference">
@@ -116,11 +115,11 @@
   &repmgr-cluster-crosscheck;
   &repmgr-cluster-event;
   &repmgr-cluster-cleanup;
-  &repmgr-daemon-status;
+  &repmgr-service-status;
+  &repmgr-service-pause;
+  &repmgr-service-unpause;
   &repmgr-daemon-start;
   &repmgr-daemon-stop;
-  &repmgr-daemon-pause;
-  &repmgr-daemon-unpause;
  </part>
 
  &appendix-release-notes;

doc/repmgrd-automatic-failover.xml

@@ -55,7 +55,7 @@
    </para>
  </note>
  <para>
-   For more complex replication scenarios,e.g. with multiple datacentres, it may
+   For more complex replication scenarios, e.g. with multiple datacentres, it may
    be preferable to use location-based failover, which ensures that only nodes
    in the same location as the primary will ever be promotion candidates;
    see <xref linkend="repmgrd-network-split"/> for more details.
@@ -192,21 +192,23 @@
     connected. Beginning with <link linkend="release-4.4">&repmgr; 4.4</link>
     it is now possible for the affected standbys to build a consensus about whether
     the primary is still available to some standbys (&quot;primary visibility consensus&quot;).
-    This is done by polling each standby for the time it last saw the primary;
+    This is done by polling each standby (and the witness, if present) for the time it last saw the
-    if any have seen the primary very recently, it's reasonable
+    primary; if any have seen the primary very recently, it's reasonable
     to infer that the primary is still available and a failover should not be started.
   </para>
 
   <para>
     The time the primary was last seen by each node can be checked by executing
-    <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>,
+    <link linkend="repmgr-service-status"><command>repmgr service status</command></link>
+    (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>)
     which includes this in its output, e.g.:
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
- 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
+ 1  | node1 | primary | * running |          | running | 27259 | no      | n/a
- 2  | node2 | standby |   running | node1    | running | 96572 | no      | 1 second(s) ago
+ 2  | node2 | standby |   running | node1    | running | 27272 | no      | 1 second(s) ago
- 3  | node3 | standby |   running | node1    | running | 96584 | no      | 0 second(s) ago</programlisting>
+ 3  | node3 | standby |   running | node1    | running | 27282 | no      | 0 second(s) ago
+ 4  | node4 | witness | * running | node1    | running | 27298 | no      | 1 second(s) ago</programlisting>
 
   </para>
 
@@ -267,11 +269,12 @@
   <para>
     If <option>standby_disconnect_on_failover</option> is set to <literal>true</literal> in
     <filename>repmgr.conf</filename>, in a failover situation &repmgrd; will forcibly disconnect
-    the local node's WAL receiver before making a failover decision.
+    the local node's WAL receiver, and wait for the WAL receiver on all sibling nodes to be
+	disconnected, before making a failover decision.
   </para>
   <note>
     <para>
-      <option>standby_disconnect_on_failover</option> is available from PostgreSQL 9.5 and later.
+      <option>standby_disconnect_on_failover</option> is available with PostgreSQL 9.5 and later.
       Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
     </para>
   </note>
@@ -290,6 +293,12 @@
     plus however many seconds it takes to confirm the WAL receiver is disconnected before
     &repmgrd; proceeds with the failover decision.
   </para>
+  <para>
+	&repmgrd; will wait up to <option>sibling_nodes_disconnect_timeout</option> seconds (default:
+	<literal>30</literal>) to confirm that the WAL receiver on all sibling nodes hase been
+	disconnected before proceding with the failover operation. If the timeout is reached, the
+	failover operation will go ahead anyway.
+  </para>
   <para>
     Following the failover operation, no matter what the outcome, each node will reconnect its WAL receiver.
   </para>
@@ -322,11 +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
+    The <literal>%n</literal> parameter will be replaced with the node ID when the script is
-    <literal>%a</literal> parameter will be replaced by the node name when the script is executed.
+    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.
@@ -576,7 +586,7 @@ INFO:  node 3 received notification to rerun promotion candidate election
   <sect2 id="repmgrd-primary-child-disconnection-caveats">
 	<title>Standby disconnections monitoring caveats</title>
 	<para>
-	  The follwing caveats should be considered if you are intending to use this functionality.
+	  The following caveats should be considered if you are intending to use this functionality.
 	</para>
 	<para>
 	  <itemizedlist mark="bullet">

doc/repmgrd-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

@@ -8,16 +8,20 @@
   </indexterm>
 
   <para>
-    &repmgrd; is a daemon which runs on each PostgreSQL node,
+    &repmgrd; is a daemon process which runs on each PostgreSQL node,
     monitoring the local node, and (unless it's the primary node) the upstream server
     (the primary server or with cascading replication, another standby) which it's
     connected to.
   </para>
   <para>
     &repmgrd; can be configured to provide failover
-    capability in case the primary upstream node becomes unreachable, and/or
+    capability in case the primary or upstream node becomes unreachable, and/or
     provide monitoring data to the &repmgr; metadatabase.
   </para>
+  <para>
+    From &repmgr; 4.4, when running on the primary node, &repmgrd; can also monitor
+    standby disconnections/reconnections (see <xref linkend="repmgrd-primary-child-disconnection"/>).
+  </para>
 
   <sect1 id="repmgrd-basic-configuration">
     <title>repmgrd configuration</title>
@@ -77,7 +81,7 @@
               <listitem>
                 <simpara>
                   <literal>connection</literal> - determines server availability
-                  by attempt ingto make a new connection to the upstream node
+                  by attempting to make a new connection to the upstream node
                 </simpara>
               </listitem>
               <listitem>
@@ -85,6 +89,10 @@
                   <literal>query</literal> - determines server availability
                   by executing an SQL statement on the node via the existing connection
                 </simpara>
+                <simpara>
+                  The query is a minimal throwaway query - <command>SELECT 1</command> -
+                  which is used to determine that the server can accept queries.
+                </simpara>
               </listitem>
 
             </itemizedlist>
@@ -148,7 +156,7 @@
     </variablelist>
 
       <para>
-        See also <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file.
+        See also <filename><ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file.
       </para>
 
     <sect2 id="repmgrd-automatic-failover-configuration">
@@ -222,6 +230,17 @@
               Normally <option>promote_command</option> is set as &repmgr;'s
               <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command> command.
             </para>
+
+            <note>
+              <para>
+                When invoking <command>repmgr standby promote</command> (either directly via
+                the <option>promote_command</option>, or in a script called
+                via <option>promote_command</option>), <option>--siblings-follow</option>
+                <emphasis>must not</emphasis> be included as a
+                command line option for <command>repmgr standby promote</command>.
+              </para>
+            </note>
+
             <para>
               It is also possible to provide a shell script to e.g. perform user-defined tasks
               before promoting the current node. In this case the script <emphasis>must</emphasis>
@@ -310,11 +329,11 @@
 
     </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>
-        The following configuraton options can be use to fine-tune automatic failover:
+        The following configuraton options can be used to fine-tune automatic failover:
       </para>
       <variablelist>
 
@@ -355,8 +374,8 @@
               </para>
             </note>
             <para>
-              One or both of the following parameter placeholders
+              One or more of the following parameter placeholders
-			  should be provided, which will be replaced by repmgrd with the appropriate
+			  may be provided, which will be replaced by repmgrd with the appropriate
 	          value:
               <itemizedlist spacing="compact" mark="bullet">
                 <listitem>
@@ -365,6 +384,15 @@
                 <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>
@@ -383,8 +411,8 @@
             </indexterm>
 
             <para>
-              If <literal>true</literal>, only continue with failover if no standbys have seen
+              If <literal>true</literal>, only continue with failover if no standbys
-			  the primary node recently.
+              (or the witness server, if present) have seen the primary node recently.
             </para>
             <note>
               <para>
@@ -395,6 +423,33 @@
           </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>
@@ -475,6 +530,23 @@
 
     </sect2>
 
+
+    <sect2 id="repmgrd-automatic-failover-configuration-pgbouncer-fencing">
+      <title>Configuring &repmgrd; and pgbouncer to fence a failed primary node</title>
+      <indexterm>
+        <primary>fencing</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>PgBouncer</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </indexterm>
+      <para>
+        For further details and a reference implementation, see the separate document
+        <ulink url="https://github.com/EnterpriseDB/repmgr/blob/master/doc/repmgrd-node-fencing.md">Fencing a failed master node with repmgrd and PgBouncer</ulink>.
+      </para>
+    </sect2>
+
     <sect2 id="postgresql-service-configuration">
       <title>PostgreSQL service configuration</title>
 
@@ -508,7 +580,8 @@
       </indexterm>
       <para>
         If you are intending to use the <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link>
-        and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> commands, the following
+        and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link>
+        commands, the following
         parameters <emphasis>must</emphasis> be set in <filename>repmgr.conf</filename>:
         <itemizedlist spacing="compact" mark="bullet">
 
@@ -524,10 +597,10 @@
 
       </para>
       <para>
-        Example (for &repmgr; with PostgreSQL 11 on CentOS 7):
+        Example (for &repmgr; with PostgreSQL 12 on CentOS 7):
         <programlisting>
-repmgrd_service_start_command='sudo systemctl repmgr11 start'
+repmgrd_service_start_command='sudo systemctl repmgr12 start'
-repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
+repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
 </programlisting>
       </para>
       <para>
@@ -554,7 +627,8 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
         the option <option>monitor_interval_secs</option> (see above).
       </para>
       <para>
-        For more details on monitoring, see <xref linkend="repmgrd-monitoring"/>.
+        For more details on monitoring, see <xref linkend="repmgrd-monitoring"/>. For information on
+        monitoring standby disconnections, see <xref linkend="repmgrd-primary-child-disconnection"/>.
       </para>
     </sect2>
 
@@ -590,18 +664,6 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 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>
@@ -734,6 +796,12 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
           </simpara>
         </listitem>
 
+        <listitem>
+          <simpara>
+            <varname>always_promote</varname>
+          </simpara>
+        </listitem>
+
         <listitem>
           <simpara>
             <varname>promote_command</varname>
@@ -849,7 +917,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
     <para>
       The commands <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link> and
       <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> can be used
-      as convenience wrappers to start and stop &repmgrd;.
+      as convenience wrappers to start and stop &repmgrd; on the local node.
     </para>
     <important>
       <para>
@@ -905,7 +973,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
       </para>
       <para>
         If none of the above apply, &repmgrd; will create a PID file
-        in the operating system's temporary directory (as setermined by the environment variable
+        in the operating system's temporary directory (as determined by the environment variable
         <varname>TMPDIR</varname>, or if that is not set, will use <filename>/tmp</filename>).
       </para>
       <para>

doc/repmgrd-node-fencing.md

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

doc/repmgrd-operation.xml

@@ -6,9 +6,9 @@
     <secondary>operation</secondary>
   </indexterm>
 
-  <sect1 id="repmgrd-pausing">
+  <sect1 id="repmgrd-pausing" xreflabel="pausing the repmgrd service">
 
-    <title>Pausing repmgrd</title>
+    <title>Pausing the repmgrd service</title>
 
   <indexterm>
     <primary>repmgrd</primary>
@@ -47,7 +47,7 @@
 
   <note>
     <para>
-      For major PostgreSQL upgrades, e.g. from PostgreSQL 10 to PostgreSQL 11,
+      For major PostgreSQL upgrades, e.g. from PostgreSQL 11 to PostgreSQL 12,
       &repmgrd; should be shut down completely and only started up
       once the &repmgr; packages for the new PostgreSQL major version have been installed.
     </para>
@@ -88,17 +88,21 @@
   <sect2 id="repmgrd-pausing-execution">
     <title>Pausing/unpausing &repmgrd;</title>
     <para>
-      To pause &repmgrd;, execute <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link>, e.g.:
+      To pause &repmgrd;, execute <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link>
+      (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-pause"><command>repmgr daemon pause</command></link>),
+      e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon pause
+$ repmgr -f /etc/repmgr.conf service pause
 NOTICE: node 1 (node1) paused
 NOTICE: node 2 (node2) paused
 NOTICE: node 3 (node3) paused</programlisting>
     </para>
     <para>
       The state of &repmgrd; on each node can be checked with
-      <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>, e.g.:
+      <link linkend="repmgr-service-status"><command>repmgr service status</command></link>
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+      (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>),
+      e.g.:
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status  | repmgrd | PID  | Paused?
 ----+-------+---------+---------+---------+------+---------
  1  | node1 | primary | running | running | 7851 | yes
@@ -108,8 +112,8 @@ NOTICE: node 3 (node3) paused</programlisting>
 
     <note>
       <para>
-        If executing a switchover with  <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
+        If executing a switchover with <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-		&repmgr; will automatically pause/unpause &repmgrd; as part of the switchover process.
+	&repmgr; will automatically pause/unpause the &repmgrd; service as part of the switchover process.
       </para>
     </note>
 
@@ -117,29 +121,32 @@ NOTICE: node 3 (node3) paused</programlisting>
       If the primary (in this example, <literal>node1</literal>) is stopped, &repmgrd;
       running on one of the standbys (here: <literal>node2</literal>) will react like this:
       <programlisting>
-[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (ID: 1)
+[2019-08-28 12:22:21] [WARNING] unable to connect to upstream node "node1" (node ID: 1)
-[2018-09-20 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts
+[2019-08-28 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts
-[2018-09-20 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
+[2019-08-28 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
 ...
-[2018-09-20 12:22:24] [INFO] sleeping 1 seconds until next reconnection attempt
+[2019-08-28 12:22:24] [INFO] sleeping 1 seconds until next reconnection attempt
-[2018-09-20 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts
+[2019-08-28 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts
-[2018-09-20 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
+[2019-08-28 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
-[2018-09-20 12:22:25] [NOTICE] node is paused
+[2019-08-28 12:22:25] [NOTICE] node is paused
-[2018-09-20 12:22:33] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (ID: 1) in degraded state
+[2019-08-28 12:22:33] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state
-[2018-09-20 12:22:33] [DETAIL] repmgrd paused by administrator
+[2019-08-28 12:22:33] [DETAIL] repmgrd paused by administrator
-[2018-09-20 12:22:33] [HINT] execute "repmgr daemon unpause" to resume normal failover mode</programlisting>
+[2019-08-28 12:22:33] [HINT] execute "repmgr service unpause" to resume normal failover mode</programlisting>
     </para>
     <para>
       If the primary becomes available again (e.g. following a software upgrade), &repmgrd;
       will automatically reconnect, e.g.:
       <programlisting>
-[2018-09-20 13:12:41] [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>
-      To unpause &repmgrd;, execute <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>, e.g.:
+      To unpause the &repmgrd; service, execute
+      <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
+      ((&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-unpause"><command>repmgr daemon unpause</command></link>),
+      e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon unpause
+$ repmgr -f /etc/repmgr.conf service unpause
 NOTICE: node 1 (node1) unpaused
 NOTICE: node 2 (node2) unpaused
 NOTICE: node 3 (node3) unpaused</programlisting>
@@ -150,11 +157,11 @@ NOTICE: node 3 (node3) unpaused</programlisting>
         If the previous primary is no longer accessible when &repmgrd;
         is unpaused, no failover action will be taken. Instead, a new primary must be manually promoted using
         <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>,
-		and any standbys attached to the new primary with
+	and any standbys attached to the new primary with
-		<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
+	<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
       </para>
       <para>
-        This is to prevent <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
+        This is to prevent execution of <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
         resulting in the automatic promotion of a new primary, which may be a problem particularly
         in larger clusters, where &repmgrd; could select a different promotion
         candidate to the one intended by the administrator.
@@ -168,17 +175,23 @@ NOTICE: node 3 (node3) unpaused</programlisting>
       The pause state of each node will be stored over a PostgreSQL restart.
     </para>
 
-	<para>
+    <para>
-	  <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
+      <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link> and
-	  <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link> can be
+      <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link> can be
-	  executed even if &repmgrd; is not running; in this case,
+      executed even if &repmgrd; is not running; in this case,
-	  &repmgrd; will start up in whichever pause state has been set.
+      &repmgrd; will start up in whichever pause state has been set.
-	</para>
+    </para>
     <note>
       <para>
-		<link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
+	    <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link> and
-		<link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
+	    <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
-		<emphasis>do not</emphasis> stop/start &repmgrd;.
+	    <emphasis>do not</emphasis> start/stop &repmgrd;.
+      </para>
+      <para>
+        The commands <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link>
+        and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link>
+        (<link linkend="repmgrd-service-configuration">if correctly configured</link>) can be used to start/stop
+        &repmgrd; on individual nodes.
       </para>
     </note>
   </sect2>
@@ -282,7 +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/repmgrd-overview.xml

@@ -38,7 +38,7 @@
          <simpara>
            ability to <link linkend="repmgrd-pausing">pause repmgrd</link>
            operation on all nodes with a
-           <link linkend="repmgr-daemon-pause"><command>single command</command></link>
+           <link linkend="repmgr-service-pause"><command>single command</command></link>
          </simpara>
        </listitem>
 
@@ -100,11 +100,11 @@
   Start &repmgrd; on each standby and verify that it's running by examining the
   log output, which at log level <literal>INFO</literal> will look like this:
   <programlisting>
-    [2019-03-15 06:32:05] [NOTICE] repmgrd (repmgrd 4.3) starting up
+    [2019-08-15 07:14:42] [NOTICE] repmgrd (repmgrd 5.0) starting up
-    [2019-03-15 06:32:05] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr connect_timeout=2"
+    [2019-08-15 07:14:42] [INFO] connecting to database "host=node2 dbname=repmgr user=repmgr connect_timeout=2"
-    INFO:  set_repmgrd_pid(): provided pidfile is /var/run/repmgr/repmgrd-11.pid
+    INFO:  set_repmgrd_pid(): provided pidfile is /var/run/repmgr/repmgrd-12.pid
-    [2019-03-15 06:32:05] [NOTICE] starting monitoring of node "node2" (ID: 2)
+    [2019-08-15 07:14:42] [NOTICE] starting monitoring of node "node2" (ID: 2)
-    [2019-03-15 06:32:05] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
+    [2019-08-15 07:14:42] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
  </para>
  <para>
   Each &repmgrd; should also have recorded its successful startup as an event:
@@ -112,9 +112,9 @@
     $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
      Node ID | Name  | Event         | OK | Timestamp           | Details
     ---------+-------+---------------+----+---------------------+--------------------------------------------------------
-     3       | node3 | repmgrd_start | t  | 2019-03-14 04:17:30 | monitoring connection to upstream node "node1" (ID: 1)
+     3       | node3 | repmgrd_start | t  | 2019-08-15 07:14:42 | monitoring connection to upstream node "node1" (ID: 1)
-     2       | node2 | repmgrd_start | t  | 2019-03-14 04:11:47 | monitoring connection to upstream node "node1" (ID: 1)
+     2       | node2 | repmgrd_start | t  | 2019-08-15 07:14:41 | monitoring connection to upstream node "node1" (ID: 1)
-     1       | node1 | repmgrd_start | t  | 2019-03-14 04:04:31 | monitoring cluster primary "node1" (ID: 1)</programlisting>
+     1       | node1 | repmgrd_start | t  | 2019-08-15 07:14:39 | monitoring cluster primary "node1" (ID: 1)</programlisting>
  </para>
  <para>
   Now stop the current primary server with e.g.:
@@ -128,33 +128,33 @@
   decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
   which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
   <programlisting>
-    [2019-03-15 06:37:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
+    [2019-08-15 07:27:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
-    [2019-03-15 06:37:50] [INFO] checking state of node 1, 1 of 3 attempts
+    [2019-08-15 07:27:50] [INFO] checking state of node 1, 1 of 3 attempts
-    [2019-03-15 06:37:50] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-08-15 07:27:50] [INFO] sleeping 5 seconds until next reconnection attempt
-    [2019-03-15 06:37:55] [INFO] checking state of node 1, 2 of 3 attempts
+    [2019-08-15 07:27:55] [INFO] checking state of node 1, 2 of 3 attempts
-    [2019-03-15 06:37:55] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-08-15 07:27:55] [INFO] sleeping 5 seconds until next reconnection attempt
-    [2019-03-15 06:38:00] [INFO] checking state of node 1, 3 of 3 attempts
+    [2019-08-15 07:28:00] [INFO] checking state of node 1, 3 of 3 attempts
-    [2019-03-15 06:38:00] [WARNING] unable to reconnect to node 1 after 3 attempts
+    [2019-08-15 07:28:00] [WARNING] unable to reconnect to node 1 after 3 attempts
-    [2019-03-15 06:38:00] [INFO] primary and this node have the same location ("default")
+    [2019-08-15 07:28:00] [INFO] primary and this node have the same location ("default")
-    [2019-03-15 06:38:00] [INFO] local node's last receive lsn: 0/900CBF8
+    [2019-08-15 07:28:00] [INFO] local node's last receive lsn: 0/900CBF8
-    [2019-03-15 06:38:00] [INFO] node 3 last saw primary node 12 second(s) ago
+    [2019-08-15 07:28:00] [INFO] node 3 last saw primary node 12 second(s) ago
-    [2019-03-15 06:38:00] [INFO] last receive LSN for sibling node "node3" (ID: 3) is: 0/900CBF8
+    [2019-08-15 07:28:00] [INFO] last receive LSN for sibling node "node3" (ID: 3) is: 0/900CBF8
-    [2019-03-15 06:38:00] [INFO] node "node3" (ID: 3) has same LSN as current candidate "node2" (ID: 2)
+    [2019-08-15 07:28:00] [INFO] node "node3" (ID: 3) has same LSN as current candidate "node2" (ID: 2)
-    [2019-03-15 06:38:00] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
+    [2019-08-15 07:28:00] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
-    [2019-03-15 06:38:00] [NOTICE] promotion candidate is "node2" (ID: 2)
+    [2019-08-15 07:28:00] [NOTICE] promotion candidate is "node2" (ID: 2)
-    [2019-03-15 06:38:00] [NOTICE] this node is the winner, will now promote itself and inform other nodes
+    [2019-08-15 07:28:00] [NOTICE] this node is the winner, will now promote itself and inform other nodes
-    [2019-03-15 06:38:00] [INFO] promote_command is:
+    [2019-08-15 07:28:00] [INFO] promote_command is:
-      "/usr/pgsql-11/bin/repmgr -f /etc/repmgr/11/repmgr.conf standby promote"
+      "/usr/pgsql-12/bin/repmgr -f /etc/repmgr/12/repmgr.conf standby promote"
     NOTICE: promoting standby to primary
-    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote"
+    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote"
     NOTICE: waiting up to 60 seconds (parameter "promote_check_timeout") for promotion to complete
     NOTICE: STANDBY PROMOTE successful
     DETAIL: server "node2" (ID: 2) was successfully promoted to primary
-    [2019-03-15 06:38:01] [INFO] 3 followers to notify
+    [2019-08-15 07:28:01] [INFO] 3 followers to notify
-    [2019-03-15 06:38:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
+    [2019-08-15 07:28:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
     INFO:  node 3 received notification to follow node 2
-    [2019-03-15 06:38:01] [INFO] switching to primary monitoring mode
+    [2019-08-15 07:28:01] [INFO] switching to primary monitoring mode
-    [2019-03-15 06:38:01] [NOTICE] monitoring cluster primary "node2" (ID: 2)</programlisting>
+    [2019-08-15 07:28:01] [NOTICE] monitoring cluster primary "node2" (ID: 2)</programlisting>
  </para>
  <para>
   The cluster status will now look like this, with the original primary (<literal>node1</literal>)
@@ -176,11 +176,11 @@
     $ repmgr -f /etc/repmgr.conf cluster event
      Node ID | Name  | Event                      | OK | Timestamp           | Details
     ---------+-------+----------------------------+----+---------------------+-------------------------------------------------------------
-     3       | node3 | repmgrd_failover_follow    | t  | 2019-03-15 06:38:03 | node 3 now following new upstream node 2
+     3       | node3 | repmgrd_failover_follow    | t  | 2019-08-15 07:38:03 | node 3 now following new upstream node 2
-     3       | node3 | standby_follow             | t  | 2019-03-15 06:38:02 | standby attached to upstream node "node2" (ID: 2)
+     3       | node3 | standby_follow             | t  | 2019-08-15 07:38:02 | standby attached to upstream node "node2" (ID: 2)
-     2       | node2 | repmgrd_reload             | t  | 2019-03-15 06:38:01 | monitoring cluster primary "node2" (ID: 2)
+     2       | node2 | repmgrd_reload             | t  | 2019-08-15 07:38:01 | monitoring cluster primary "node2" (ID: 2)
-     2       | node2 | repmgrd_failover_promote   | t  | 2019-03-15 06:38:01 | node 2 promoted to primary; old primary 1 marked as failed
+     2       | node2 | repmgrd_failover_promote   | t  | 2019-08-15 07:38:01 | node 2 promoted to primary; old primary 1 marked as failed
-     2       | node2 | standby_promote            | t  | 2019-03-15 06:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
+     2       | node2 | standby_promote            | t  | 2019-08-15 07:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
  </para>
 
   </sect1>

doc/switchover.xml

@@ -120,16 +120,19 @@
    </important>
 
    <note>
-    <simpara>
+    <para>
      On <literal>systemd</literal> systems we strongly recommend using the appropriate
      <command>systemctl</command> commands (typically run via <command>sudo</command>) to ensure
      <literal>systemd</literal> is informed about the status of the PostgreSQL service.
-    </simpara>
+    </para>
-    <simpara>
+    <para>
      If using <command>sudo</command> for the <command>systemctl</command> calls, make sure the
      <command>sudo</command> specification doesn't require a real tty for the user. If not set
      this way, <command>repmgr</command> will fail to stop the primary.
-    </simpara>
+    </para>
+    <para>
+      See the <xref linkend="configuration-file-service-commands"/> documentation section for further details.
+    </para>
    </note>
 
    <para>
@@ -186,6 +189,7 @@
       NOTICE: local node "node2" (ID: 2) will be promoted to primary; current primary "node1" (ID: 1) will be demoted to standby
       INFO: following shutdown command would be run on node "node1":
         "pg_ctl -l /var/log/postgresql/startup.log -D '/var/lib/postgresql/data' -m fast -W stop"
+      INFO: parameter "shutdown_check_timeout" is set to 60 seconds
     </programlisting>
    </para>
 
@@ -243,16 +247,15 @@
     </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
+      Note that building the 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>,
+      source code.
-      meaning data checksums must have been enabled when the database was initialized.
     </para>
   </sect2>
 
@@ -317,7 +320,9 @@
   </para>
   <para>
     If &repmgrd; is in use, it's worth double-checking that
-    all nodes are unpaused by executing <command><link linkend="repmgr-daemon-status">repmgr-daemon-status</link></command>.
+    all nodes are unpaused by executing
+    <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+    (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-status">repmgr daemon status</link></command>).
   </para>
 
    <note>
@@ -340,7 +345,7 @@
    <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
+        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.
+        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.
+      </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>
@@ -216,7 +220,9 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 	  <secondary>checking repmgrd status</secondary>
 	</indexterm>
 	<para>
-      From <link linkend="release-4.2">repmgr 4.2</link>, once the upgrade is complete, execute the <command><link linkend="repmgr-daemon-status">repmgr daemon status</link></command>
+      From <link linkend="release-4.2">repmgr 4.2</link>, once the upgrade is complete, execute the
+      <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+      (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-status">repmgr daemon status</link></command>)
       command (on any node) to show an overview of the status of &repmgrd; on all nodes.
     </para>
   </sect2>
@@ -263,10 +269,33 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   <tip>
 	<para>
 	  Use <command><link linkend="repmgr-node-check">repmgr node check</link></command>
-	  to determine which replacation slots need to be recreated.
+	  to determine which replication slots need to be recreated.
 	</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>
 
 
@@ -283,12 +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>
@@ -417,13 +446,13 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
      <programlisting>
     $ ./convert-config.pl /etc/repmgr.conf
     node_id=2
-    node_name=node2
+    node_name='node2'
-    conninfo=host=node2 dbname=repmgr user=repmgr connect_timeout=2
+    conninfo='host=node2 dbname=repmgr user=repmgr connect_timeout=2'
     pg_ctl_options='-l /var/log/postgres/startup.log'
-    rsync_options=--exclude=postgresql.local.conf --archive
+    rsync_options='--exclude=postgresql.local.conf --archive'
-    log_level=INFO
+    log_level='INFO'
-    pg_basebackup_options=--no-slot
+    pg_basebackup_options='--no-slot'
-    data_directory=</programlisting>
+    data_directory=''</programlisting>
     </para>
     <para>
       The converted file is printed to <literal>STDOUT</literal> and the original file is not
@@ -432,23 +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 in repmgr4 and which <emphasis>must</emphasis>
+      is a required parameter from &repmgr; 4. This must be manually modified to contain
-      be provided.
+      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 following 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
@@ -460,10 +497,10 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
       <itemizedlist spacing="compact" mark="bullet">
       <listitem>
         <simpara>
-          <ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/REL3_3_STABLE/sql/repmgr3.0_repmgr3.1.sql">repmgr3.0_repmgr3.1.sql</ulink></simpara>
+          <ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/REL3_3_STABLE/sql/repmgr3.0_repmgr3.1.sql">repmgr3.0_repmgr3.1.sql</ulink></simpara>
       </listitem>
       <listitem>
-        <simpara><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/REL3_3_STABLE/sql/repmgr3.1.1_repmgr3.1.2.sql">repmgr3.1.1_repmgr3.1.2.sql</ulink></simpara>
+        <simpara><ulink url="https://raw.githubusercontent.com/EnterpriseDB/repmgr/REL3_3_STABLE/sql/repmgr3.1.1_repmgr3.1.2.sql">repmgr3.1.1_repmgr3.1.2.sql</ulink></simpara>
       </listitem>
       </itemizedlist>
     </para>
@@ -477,19 +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.
@@ -499,6 +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>
@@ -511,18 +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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr--4.0.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.1.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.2.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.3.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

repmgr--4.4--5.0.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
+
+ALTER FUNCTION set_repmgrd_pid(INT, TEXT) RETURNS NULL ON NULL INPUT;
+

repmgr--4.4.sql

@@ -78,8 +78,6 @@ CREATE VIEW repmgr.show_nodes AS
 LEFT JOIN repmgr.nodes un
        ON un.node_id = n.upstream_node_id;
 
-
-/* XXX update upgrade scripts! */
 CREATE TABLE repmgr.voting_term (
   term INT NOT NULL
 );

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

@@ -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--5.1--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-cluster.c

@@ -3,7 +3,7 @@
  *
  * Implements cluster information actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -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, ItemList *warnings, int *error_code);
-
+static int	build_cluster_crosscheck(t_node_status_cube ***cube_dest, ItemList *warnings, int *error_code);
-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 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 "?" */
+			/* The witness node's timeline ID is irrelevant */
-			headers_show[SHOW_PRIORITY].cur_length = 1;
+			strncpy(cell->node_info->replication_info->timeline_id_str, _("n/a"), MAXLEN);
-		}
-		else
-		{
-			initPQExpBuffer(&buf);
-			appendPQExpBuffer(&buf, "%i", cell->node_info->replication_info->timeline_id);
-			headers_show[SHOW_PRIORITY].cur_length = strlen(buf.data);
-			termPQExpBuffer(&buf);
 		}
+		headers_show[SHOW_TIMELINE_ID].cur_length = strlen(cell->node_info->replication_info->timeline_id_str);
 
 		headers_show[SHOW_CONNINFO].cur_length = strlen(cell->node_info->conninfo);
 
@@ -322,10 +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("| %-*s ", headers_show[SHOW_TIMELINE_ID].max_length, cell->node_info->replication_info->timeline_id_str);
-					printf("| %-*c ", headers_show[SHOW_TIMELINE_ID].max_length, '?');
-				else
-					printf("| %-*i ", headers_show[SHOW_TIMELINE_ID].max_length, (int)cell->node_info->replication_info->timeline_id);
 			}
 
 			if (headers_show[SHOW_CONNINFO].display == true)
@@ -343,14 +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);
+		/* output header contains node name, node ID and one column for each node in the cluster */
-		for (i = 0; i < n; i++)
+		struct ColHeader *headers_crosscheck = NULL;
-			printf("| %2d ", cube[i]->node_id);
+
-		printf("\n");
+		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);
+		int header_count = n + 2;
-		for (i = 0; i < n; i++)
+		int header_id = 2;
-			printf("| %2d ", matrix_rec_list[i]->node_id);
-		printf("\n");
 
-		for (i = 0; i < name_length; i++)
+		headers_matrix = palloc0(sizeof(ColHeader) * header_count);
-			printf("-");
+
-		printf("-+----");
+		/* Initialize column headers  */
-		for (i = 0; i < n; i++)
+		strncpy(headers_matrix[0].title, _("Name"), MAXLEN);
-			printf("+----");
+		strncpy(headers_matrix[1].title, _("ID"), MAXLEN);
-		printf("\n");
 
 		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;
@@ -987,7 +1048,19 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " cluster show --csv -L NOTICE --terse\"");
+							 " cluster show --csv --terse");
+
+		/*
+		 * Usually we'll want NOTICE as the log level, but if the user
+		 * explicitly provided one with --log-level, that will be passed
+		 * in the remote repmgr invocation.
+		 */
+		if (runtime_options.log_level[0] == '\0')
+		{
+			appendPQExpBufferStr(&command,
+								 " -L NOTICE");
+		}
+		appendPQExpBufferChar(&command, '"');
 
 		log_verbose(LOG_DEBUG, "build_cluster_matrix(): executing:\n  %s", command.data);
 
@@ -1059,7 +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,
@@ -1108,20 +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;
@@ -1175,7 +1240,18 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " cluster matrix --csv -L NOTICE --terse");
+							 " cluster matrix --csv --terse");
+
+		/*
+		 * Usually we'll want NOTICE as the log level, but if the user
+		 * explicitly provided one with --log-level, that will be passed
+		 * in the remote repmgr invocation.
+		 */
+		if (runtime_options.log_level[0] == '\0')
+		{
+			appendPQExpBufferStr(&command,
+								 " -L NOTICE");
+		}
 
 		initPQExpBuffer(&command_output);
 
@@ -1373,6 +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)
 	{
@@ -1474,4 +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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-daemon.c

@@ -2,7 +2,7 @@
  * repmgr-action-daemon.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -26,478 +26,9 @@
 #include "repmgr-client-global.h"
 #include "repmgr-action-daemon.h"
 
-#define REPMGR_DAEMON_STOP_START_WAIT 15
+#define REPMGR_SERVICE_STOP_START_WAIT 15
-#define REPMGR_DAEMON_STATUS_START_HINT _("use \"repmgr daemon status\" to confirm that repmgrd was successfully started")
+#define REPMGR_SERVICE_STATUS_START_HINT _("use \"repmgr service status\" to confirm that repmgrd was successfully started")
-#define REPMGR_DAEMON_STATUS_STOP_HINT _("use \"repmgr daemon status\" to confirm that repmgrd was successfully stopped")
+#define REPMGR_SERVICE_STATUS_STOP_HINT _("use \"repmgr service status\" to confirm that repmgrd was successfully stopped")
-
-/*
- * Possibly also show:
- *  - repmgrd start time?
- *  - repmgrd mode
- *  - priority
- *  - whether promotion candidate (due to zero priority/different location)
- */
-
-typedef enum
-{
-	STATUS_ID = 0,
-	STATUS_NAME,
-	STATUS_ROLE,
-	STATUS_PG,
-	STATUS_UPSTREAM_NAME,
-	STATUS_LOCATION,
-	STATUS_PRIORITY,
-	STATUS_REPMGRD,
-	STATUS_PID,
-	STATUS_PAUSED,
-	STATUS_UPSTREAM_LAST_SEEN
-} StatusHeader;
-
-#define STATUS_HEADER_COUNT 11
-
-struct ColHeader headers_status[STATUS_HEADER_COUNT];
-
-static void fetch_node_records(PGconn *conn, NodeInfoList *node_list);
-static void _do_repmgr_pause(bool pause);
-
-
-void
-do_daemon_status(void)
-{
-	PGconn	   *conn = NULL;
-	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
-	NodeInfoListCell *cell = NULL;
-	int i;
-	RepmgrdInfo **repmgrd_info;
-	ItemList	warnings = {NULL, NULL};
-	bool		connection_error_found = false;
-
-	/* Connect to local database to obtain cluster connection data */
-	log_verbose(LOG_INFO, _("connecting to database"));
-
-	if (strlen(config_file_options.conninfo))
-		conn = establish_db_connection(config_file_options.conninfo, true);
-	else
-		conn = establish_db_connection_by_params(&source_conninfo, true);
-
-	fetch_node_records(conn, &nodes);
-
-	repmgrd_info = (RepmgrdInfo **) pg_malloc0(sizeof(RepmgrdInfo *) * nodes.node_count);
-
-	if (repmgrd_info == NULL)
-	{
-		log_error(_("unable to allocate memory"));
-		exit(ERR_OUT_OF_MEMORY);
-	}
-
-	strncpy(headers_status[STATUS_ID].title, _("ID"), MAXLEN);
-	strncpy(headers_status[STATUS_NAME].title, _("Name"), MAXLEN);
-	strncpy(headers_status[STATUS_ROLE].title, _("Role"), MAXLEN);
-	strncpy(headers_status[STATUS_PG].title, _("Status"), MAXLEN);
-	strncpy(headers_status[STATUS_UPSTREAM_NAME].title, _("Upstream"), MAXLEN);
-
-	/* following only displayed with the --detail option */
-	strncpy(headers_status[STATUS_LOCATION].title, _("Location"), MAXLEN);
-	if (runtime_options.compact == true)
-		strncpy(headers_status[STATUS_PRIORITY].title, _("Prio."), MAXLEN);
-	else
-		strncpy(headers_status[STATUS_PRIORITY].title, _("Priority"), MAXLEN);
-
-	strncpy(headers_status[STATUS_REPMGRD].title, _("repmgrd"), MAXLEN);
-	strncpy(headers_status[STATUS_PID].title, _("PID"), MAXLEN);
-	strncpy(headers_status[STATUS_PAUSED].title, _("Paused?"), MAXLEN);
-
-	if (runtime_options.compact == true)
-		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstr. last"), MAXLEN);
-	else
-		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstream last seen"), MAXLEN);
-
-	for (i = 0; i < STATUS_HEADER_COUNT; i++)
-	{
-		headers_status[i].max_length = strlen(headers_status[i].title);
-		headers_status[i].display = true;
-	}
-
-	if (runtime_options.detail == false)
-	{
-		headers_status[STATUS_LOCATION].display = false;
-		headers_status[STATUS_PRIORITY].display = false;
-	}
-
-	i = 0;
-
-	for (cell = nodes.head; cell; cell = cell->next)
-	{
-		int j;
-		PQExpBufferData node_status;
-		PQExpBufferData upstream;
-
-		repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
-		repmgrd_info[i]->node_id = cell->node_info->node_id;
-		repmgrd_info[i]->pid = UNKNOWN_PID;
-		repmgrd_info[i]->recovery_type = RECTYPE_UNKNOWN;
-		repmgrd_info[i]->paused = false;
-		repmgrd_info[i]->running = false;
-		repmgrd_info[i]->pg_running = true;
-		repmgrd_info[i]->wal_paused_pending_wal = false;
-		repmgrd_info[i]->upstream_last_seen = -1;
-
-		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
-
-		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
-		{
-
-			connection_error_found = true;
-
-			if (runtime_options.verbose)
-			{
-				char		error[MAXLEN];
-
-				strncpy(error, PQerrorMessage(cell->node_info->conn), MAXLEN);
-
-				item_list_append_format(&warnings,
-										"when attempting to connect to node \"%s\" (ID: %i), following error encountered :\n\"%s\"",
-										cell->node_info->node_name, cell->node_info->node_id, trim(error));
-			}
-			else
-			{
-				item_list_append_format(&warnings,
-										"unable to  connect to node \"%s\" (ID: %i)",
-										cell->node_info->node_name, cell->node_info->node_id);
-			}
-
-			repmgrd_info[i]->pg_running = false;
-			maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("n/a"));
-			maxlen_snprintf(repmgrd_info[i]->pid_text, "%s", _("n/a"));
-		}
-		else
-		{
-			cell->node_info->node_status = NODE_STATUS_UP;
-			cell->node_info->recovery_type = get_recovery_type(cell->node_info->conn);
-
-			repmgrd_info[i]->pid = repmgrd_get_pid(cell->node_info->conn);
-
-			repmgrd_info[i]->running = repmgrd_is_running(cell->node_info->conn);
-
-			if (repmgrd_info[i]->running == true)
-			{
-				maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("running"));
-			}
-			else
-			{
-				maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("not running"));
-			}
-
-			if (repmgrd_info[i]->pid == UNKNOWN_PID)
-			{
-				maxlen_snprintf(repmgrd_info[i]->pid_text, "%s", _("n/a"));
-			}
-			else
-			{
-				maxlen_snprintf(repmgrd_info[i]->pid_text, "%i", repmgrd_info[i]->pid);
-			}
-
-			repmgrd_info[i]->paused = repmgrd_is_paused(cell->node_info->conn);
-
-			repmgrd_info[i]->recovery_type = get_recovery_type(cell->node_info->conn);
-
-			if (repmgrd_info[i]->recovery_type == RECTYPE_STANDBY)
-			{
-				repmgrd_info[i]->wal_paused_pending_wal = is_wal_replay_paused(cell->node_info->conn, true);
-
-				if (repmgrd_info[i]->wal_paused_pending_wal == true)
-				{
-					item_list_append_format(&warnings,
-											_("WAL replay is paused on node \"%s\" (ID: %i) with WAL replay pending; this node cannot be manually promoted  until WAL replay is resumed"),
-											cell->node_info->node_name, cell->node_info->node_id);
-				}
-			}
-
-			repmgrd_info[i]->upstream_last_seen = get_upstream_last_seen(cell->node_info->conn, cell->node_info->type);
-			if (repmgrd_info[i]->upstream_last_seen < 0)
-			{
-				maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, "%s", _("n/a"));
-			}
-			else
-			{
-				if (runtime_options.compact == true)
-				{
-					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i sec(s) ago"), repmgrd_info[i]->upstream_last_seen);
-				}
-				else
-				{
-					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i second(s) ago"), repmgrd_info[i]->upstream_last_seen);
-				}
-			}
-		}
-
-		initPQExpBuffer(&node_status);
-		initPQExpBuffer(&upstream);
-
-		(void)format_node_status(cell->node_info, &node_status, &upstream, &warnings);
-		snprintf(repmgrd_info[i]->pg_running_text, sizeof(cell->node_info->details),
-				 "%s", node_status.data);
-
-		snprintf(cell->node_info->upstream_node_name, sizeof(cell->node_info->upstream_node_name),
-				 "%s", upstream.data);
-
-		termPQExpBuffer(&node_status);
-		termPQExpBuffer(&upstream);
-
-		PQfinish(cell->node_info->conn);
-
-		headers_status[STATUS_NAME].cur_length = strlen(cell->node_info->node_name);
-		headers_status[STATUS_ROLE].cur_length = strlen(get_node_type_string(cell->node_info->type));
-		headers_status[STATUS_PG].cur_length = strlen(repmgrd_info[i]->pg_running_text);
-		headers_status[STATUS_UPSTREAM_NAME].cur_length = strlen(cell->node_info->upstream_node_name);
-
-		if (runtime_options.detail == true)
-		{
-			PQExpBufferData buf;
-
-			headers_status[STATUS_LOCATION].cur_length = strlen(cell->node_info->location);
-
-			initPQExpBuffer(&buf);
-			appendPQExpBuffer(&buf, "%i", cell->node_info->priority);
-			headers_status[STATUS_PRIORITY].cur_length = strlen(buf.data);
-			termPQExpBuffer(&buf);
-		}
-
-		headers_status[STATUS_PID].cur_length = strlen(repmgrd_info[i]->pid_text);
-		headers_status[STATUS_REPMGRD].cur_length = strlen(repmgrd_info[i]->repmgrd_running);
-
-		headers_status[STATUS_UPSTREAM_LAST_SEEN].cur_length = strlen(repmgrd_info[i]->upstream_last_seen_text);
-
-		for (j = 0; j < STATUS_HEADER_COUNT; j++)
-		{
-			if (headers_status[j].cur_length > headers_status[j].max_length)
-			{
-				headers_status[j].max_length = headers_status[j].cur_length;
-			}
-		}
-
-		i++;
-	}
-
-	/* Print column header row (text mode only) */
-	if (runtime_options.output_mode == OM_TEXT)
-	{
-		print_status_header(STATUS_HEADER_COUNT, headers_status);
-	}
-
-	i = 0;
-
-	for (cell = nodes.head; cell; cell = cell->next)
-	{
-		if (runtime_options.output_mode == OM_CSV)
-		{
-			int running = repmgrd_info[i]->running ? 1 : 0;
-			int paused = repmgrd_info[i]->paused ? 1 : 0;
-
-			/* If PostgreSQL is not running, repmgrd status is unknown */
-			if (repmgrd_info[i]->pg_running == false)
-			{
-				running = -1;
-				paused = -1;
-			}
-
-			printf("%i,%s,%s,%i,%i,%i,%i,%i,%i,%s\n",
-				   cell->node_info->node_id,
-				   cell->node_info->node_name,
-				   get_node_type_string(cell->node_info->type),
-				   repmgrd_info[i]->pg_running ? 1 : 0,
-				   running,
-				   repmgrd_info[i]->pid,
-				   paused,
-				   cell->node_info->priority,
-				   repmgrd_info[i]->pid == UNKNOWN_PID
-				     ? -1
- 				     : repmgrd_info[i]->upstream_last_seen,
-				   cell->node_info->location);
-		}
-		else
-		{
-			printf(" %-*i ",  headers_status[STATUS_ID].max_length, cell->node_info->node_id);
-			printf("| %-*s ", headers_status[STATUS_NAME].max_length, cell->node_info->node_name);
-			printf("| %-*s ", headers_status[STATUS_ROLE].max_length, get_node_type_string(cell->node_info->type));
-			printf("| %-*s ", headers_status[STATUS_PG].max_length, repmgrd_info[i]->pg_running_text);
-			printf("| %-*s ", headers_status[STATUS_UPSTREAM_NAME].max_length, cell->node_info->upstream_node_name);
-
-			if (runtime_options.detail == true)
-			{
-				printf("| %-*s ", headers_status[STATUS_LOCATION].max_length, cell->node_info->location);
-				printf("| %-*i ", headers_status[STATUS_PRIORITY].max_length, cell->node_info->priority);
-			}
-
-			printf("| %-*s ", headers_status[STATUS_REPMGRD].max_length, repmgrd_info[i]->repmgrd_running);
-			printf("| %-*s ", headers_status[STATUS_PID].max_length, repmgrd_info[i]->pid_text);
-
-			if (repmgrd_info[i]->pid == UNKNOWN_PID)
-			{
-				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, _("n/a"));
-				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, _("n/a"));
-
-			}
-			else
-			{
-				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, repmgrd_info[i]->paused ? _("yes") : _("no"));
-
-				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, repmgrd_info[i]->upstream_last_seen_text);
-			}
-
-			printf("\n");
-		}
-
-		pfree(repmgrd_info[i]);
-		i++;
-	}
-
-	pfree(repmgrd_info);
-
-	/* 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"));
-		for (cell = warnings.head; cell; cell = cell->next)
-		{
-			printf(_("  - %s\n"), cell->string);
-		}
-
-		if (runtime_options.verbose == false && connection_error_found == true)
-		{
-			log_hint(_("execute with --verbose option to see connection error messages"));
-		}
-	}
-}
-
-void
-do_daemon_pause(void)
-{
-	_do_repmgr_pause(true);
-}
-
-void
-do_daemon_unpause(void)
-{
-	_do_repmgr_pause(false);
-}
-
-
-static void
-_do_repmgr_pause(bool pause)
-{
-	PGconn	   *conn = NULL;
-	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
-	NodeInfoListCell *cell = NULL;
-	int i;
-	int error_nodes = 0;
-
-	/* Connect to local database to obtain cluster connection data */
-	log_verbose(LOG_INFO, _("connecting to database"));
-
-	if (strlen(config_file_options.conninfo))
-		conn = establish_db_connection(config_file_options.conninfo, true);
-	else
-		conn = establish_db_connection_by_params(&source_conninfo, true);
-
-	fetch_node_records(conn, &nodes);
-
-	i = 0;
-
-	for (cell = nodes.head; cell; cell = cell->next)
-	{
-		log_verbose(LOG_DEBUG, "pausing node %i (%s)",
-					cell->node_info->node_id,
-					cell->node_info->node_name);
-		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
-
-		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
-		{
-			log_warning(_("unable to connect to node %i"),
-						cell->node_info->node_id);
-			error_nodes++;
-		}
-		else
-		{
-			if (runtime_options.dry_run == true)
-			{
-				if (pause == true)
-				{
-					log_info(_("would pause node %i (%s) "),
-							 cell->node_info->node_id,
-							 cell->node_info->node_name);
-				}
-				else
-				{
-					log_info(_("would unpause node %i (%s) "),
-							 cell->node_info->node_id,
-							 cell->node_info->node_name);
-				}
-			}
-			else
-			{
-				bool success = repmgrd_pause(cell->node_info->conn, pause);
-
-				if (success == false)
-					error_nodes++;
-
-				log_notice(_("node %i (%s) %s"),
-						   cell->node_info->node_id,
-						   cell->node_info->node_name,
-						   success == true
-								? pause == true ? "paused" : "unpaused"
-		   						: pause == true ? "not paused" : "not unpaused");
-			}
-			PQfinish(cell->node_info->conn);
-		}
-		i++;
-	}
-
-	if (error_nodes > 0)
-	{
-		if (pause == true)
-		{
-			log_error(_("unable to pause %i node(s)"), error_nodes);
-		}
-		else
-		{
-			log_error(_("unable to unpause %i node(s)"), error_nodes);
-		}
-
-		log_hint(_("execute \"repmgr daemon status\" to view current status"));
-
-		exit(ERR_REPMGRD_PAUSE);
-	}
-
-	exit(SUCCESS);
-}
-
-
-
-void
-fetch_node_records(PGconn *conn, NodeInfoList *node_list)
-{
-	bool success = get_all_node_records_with_upstream(conn, node_list);
-
-	if (success == false)
-	{
-		/* get_all_node_records() will display any error message */
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	if (node_list->node_count == 0)
-	{
-		log_error(_("no node records were found"));
-		log_hint(_("ensure at least one node is registered"));
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-}
-
 
 void
 do_daemon_start(void)
@@ -583,12 +114,12 @@ do_daemon_start(void)
 
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
-		log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+		log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
+		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
 
 		if (runtime_options.wait_provided)
 			timeout = runtime_options.wait;
@@ -598,7 +129,7 @@ do_daemon_start(void)
 		if (PQstatus(conn) != CONNECTION_OK)
 		{
 			log_notice(_("unable to connect to local node"));
-			log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+			log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 			exit(ERR_DB_CONN);
 		}
 
@@ -616,7 +147,7 @@ do_daemon_start(void)
 				PQfinish(conn);
 				log_error(_("repmgrd does not appear to have started after %i seconds"),
 						  timeout);
-				log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+				log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 				exit(ERR_REPMGRD_SERVICE);
 			}
 
@@ -712,12 +243,12 @@ void do_daemon_stop(void)
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
 		if (have_db_connection == true)
-			log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
+			log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
+		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
 		/*
 		 *
 		 */
@@ -732,7 +263,7 @@ void do_daemon_stop(void)
 			log_warning(_("unable to determine repmgrd PID"));
 
 			if (have_db_connection == true)
-				log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
+				log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
 
 			exit(ERR_REPMGRD_SERVICE);
 		}
@@ -764,7 +295,7 @@ void do_daemon_stop(void)
 						  timeout);
 
 				if (have_db_connection == true)
-					log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+					log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 
 				exit(ERR_REPMGRD_SERVICE);
 			}
@@ -783,53 +314,30 @@ void do_daemon_help(void)
 	print_help_header();
 
 	printf(_("Usage:\n"));
-	printf(_("    %s [OPTIONS] daemon status\n"),  progname());
-	printf(_("    %s [OPTIONS] daemon pause\n"),   progname());
-	printf(_("    %s [OPTIONS] daemon unpause\n"), progname());
 	printf(_("    %s [OPTIONS] daemon start\n"),   progname());
 	printf(_("    %s [OPTIONS] daemon stop\n"),    progname());
-	puts("");
 
-	printf(_("DAEMON STATUS\n"));
-	puts("");
-	printf(_("  \"daemon status\" shows the status of repmgrd on each node in the cluster\n"));
-	puts("");
-	printf(_("    --csv                     emit output as CSV\n"));
-	printf(_("    --detail                  show additional detail\n"));
-	printf(_("    --verbose                 show text of database connection error messages\n"));
 	puts("");
 
 	printf(_("DAEMON START\n"));
 	puts("");
-	printf(_("  \"daemon start\" attempts to start repmgrd\n"));
+	printf(_("  \"daemon start\" attempts to start repmgrd on the local node\n"));
 	puts("");
 	printf(_("    --dry-run               check prerequisites but don't start repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_SERVICE_STOP_START_WAIT);
 	printf(_("    --no-wait               don't wait for repmgrd to start\n"));
 	puts("");
 
 	printf(_("DAEMON STOP\n"));
 	puts("");
-	printf(_("  \"daemon stop\" attempts to stop repmgrd\n"));
+	printf(_("  \"daemon stop\" attempts to stop repmgrd on the local node\n"));
 	puts("");
 	printf(_("    --dry-run               check prerequisites but don't stop repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_SERVICE_STOP_START_WAIT);
 	printf(_("    --no-wait               don't wait for repmgrd to stop\n"));
 	puts("");
 
-	printf(_("DAEMON PAUSE\n"));
-	puts("");
-	printf(_("  \"daemon pause\" instructs repmgrd on each node to pause failover detection\n"));
-	puts("");
-	printf(_("    --dry-run               check if nodes are reachable but don't pause repmgrd\n"));
 	puts("");
 
-	printf(_("DAEMON UNPAUSE\n"));
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
-	puts("");
-	printf(_("  \"daemon unpause\"  instructs repmgrd on each node to resume failover detection\n"));
-	puts("");
-	printf(_("    --dry-run               check if nodes are reachable but don't unpause repmgrd\n"));
-	puts("");
-
-	puts("");
 }

repmgr-action-daemon.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-daemon.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -19,10 +19,6 @@
 #ifndef _REPMGR_ACTION_DAEMON_H_
 #define _REPMGR_ACTION_DAEMON_H_
 
-
-extern void do_daemon_status(void);
-extern void do_daemon_pause(void);
-extern void do_daemon_unpause(void);
 extern void do_daemon_start(void);
 extern void do_daemon_stop(void);
 

repmgr-action-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-primary.c

@@ -3,7 +3,7 @@
  *
  * Implements primary actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -106,7 +106,7 @@ do_primary_register(void)
 	current_primary_id = get_primary_node_id(conn);
 	if (current_primary_id != NODE_NOT_FOUND && current_primary_id != config_file_options.node_id)
 	{
-		log_debug("XXX %i", current_primary_id);
+		log_debug("current active primary node ID is %i", current_primary_id);
 		primary_conn = establish_primary_db_connection(conn, false);
 
 		if (PQstatus(primary_conn) == CONNECTION_OK)
@@ -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) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

repmgr-action-service.c

@@ -0,0 +1,548 @@
+/*
+ * repmgr-action-service.c
+ *
+ * Implements repmgrd actions for the repmgr command line utility
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * 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 <sys/stat.h>			/* for stat() */
+
+#include "repmgr.h"
+
+#include "repmgr-client-global.h"
+#include "repmgr-action-service.h"
+
+
+/*
+ * Possibly also show:
+ *  - repmgrd start time?
+ *  - repmgrd mode
+ *  - priority
+ *  - whether promotion candidate (due to zero priority/different location)
+ */
+
+typedef enum
+{
+	STATUS_ID = 0,
+	STATUS_NAME,
+	STATUS_ROLE,
+	STATUS_PG,
+	STATUS_UPSTREAM_NAME,
+	STATUS_LOCATION,
+	STATUS_PRIORITY,
+	STATUS_REPMGRD,
+	STATUS_PID,
+	STATUS_PAUSED,
+	STATUS_UPSTREAM_LAST_SEEN
+} StatusHeader;
+
+#define STATUS_HEADER_COUNT 11
+
+struct ColHeader headers_status[STATUS_HEADER_COUNT];
+
+static void fetch_node_records(PGconn *conn, NodeInfoList *node_list);
+static void _do_repmgr_pause(bool pause);
+
+
+void
+do_service_status(void)
+{
+	PGconn	   *conn = NULL;
+	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
+	NodeInfoListCell *cell = NULL;
+	int i;
+	RepmgrdInfo **repmgrd_info;
+	ItemList	warnings = {NULL, NULL};
+	bool		connection_error_found = false;
+
+	/* Connect to local database to obtain cluster connection data */
+	log_verbose(LOG_INFO, _("connecting to database"));
+
+	if (strlen(config_file_options.conninfo))
+		conn = establish_db_connection(config_file_options.conninfo, true);
+	else
+		conn = establish_db_connection_by_params(&source_conninfo, true);
+
+	fetch_node_records(conn, &nodes);
+
+	repmgrd_info = (RepmgrdInfo **) pg_malloc0(sizeof(RepmgrdInfo *) * nodes.node_count);
+
+	if (repmgrd_info == NULL)
+	{
+		log_error(_("unable to allocate memory"));
+		exit(ERR_OUT_OF_MEMORY);
+	}
+
+	strncpy(headers_status[STATUS_ID].title, _("ID"), MAXLEN);
+	strncpy(headers_status[STATUS_NAME].title, _("Name"), MAXLEN);
+	strncpy(headers_status[STATUS_ROLE].title, _("Role"), MAXLEN);
+	strncpy(headers_status[STATUS_PG].title, _("Status"), MAXLEN);
+	strncpy(headers_status[STATUS_UPSTREAM_NAME].title, _("Upstream"), MAXLEN);
+
+	/* following only displayed with the --detail option */
+	strncpy(headers_status[STATUS_LOCATION].title, _("Location"), MAXLEN);
+	if (runtime_options.compact == true)
+		strncpy(headers_status[STATUS_PRIORITY].title, _("Prio."), MAXLEN);
+	else
+		strncpy(headers_status[STATUS_PRIORITY].title, _("Priority"), MAXLEN);
+
+	strncpy(headers_status[STATUS_REPMGRD].title, _("repmgrd"), MAXLEN);
+	strncpy(headers_status[STATUS_PID].title, _("PID"), MAXLEN);
+	strncpy(headers_status[STATUS_PAUSED].title, _("Paused?"), MAXLEN);
+
+	if (runtime_options.compact == true)
+		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstr. last"), MAXLEN);
+	else
+		strncpy(headers_status[STATUS_UPSTREAM_LAST_SEEN].title, _("Upstream last seen"), MAXLEN);
+
+	for (i = 0; i < STATUS_HEADER_COUNT; i++)
+	{
+		headers_status[i].max_length = strlen(headers_status[i].title);
+		headers_status[i].display = true;
+	}
+
+	if (runtime_options.detail == false)
+	{
+		headers_status[STATUS_LOCATION].display = false;
+		headers_status[STATUS_PRIORITY].display = false;
+	}
+
+	i = 0;
+
+	for (cell = nodes.head; cell; cell = cell->next)
+	{
+		int j;
+		PQExpBufferData node_status;
+		PQExpBufferData upstream;
+
+		repmgrd_info[i] = pg_malloc0(sizeof(RepmgrdInfo));
+		repmgrd_info[i]->node_id = cell->node_info->node_id;
+		repmgrd_info[i]->pid = UNKNOWN_PID;
+		repmgrd_info[i]->recovery_type = RECTYPE_UNKNOWN;
+		repmgrd_info[i]->paused = false;
+		repmgrd_info[i]->running = false;
+		repmgrd_info[i]->pg_running = true;
+		repmgrd_info[i]->wal_paused_pending_wal = false;
+		repmgrd_info[i]->upstream_last_seen = -1;
+
+		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
+
+		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
+		{
+
+			connection_error_found = true;
+
+			if (runtime_options.verbose)
+			{
+				char		error[MAXLEN];
+
+				strncpy(error, PQerrorMessage(cell->node_info->conn), MAXLEN);
+
+				item_list_append_format(&warnings,
+										"when attempting to connect to node \"%s\" (ID: %i), following error encountered :\n\"%s\"",
+										cell->node_info->node_name, cell->node_info->node_id, trim(error));
+			}
+			else
+			{
+				item_list_append_format(&warnings,
+										"unable to  connect to node \"%s\" (ID: %i)",
+										cell->node_info->node_name, cell->node_info->node_id);
+			}
+
+			repmgrd_info[i]->pg_running = false;
+			maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("n/a"));
+			maxlen_snprintf(repmgrd_info[i]->pid_text, "%s", _("n/a"));
+		}
+		else
+		{
+			cell->node_info->node_status = NODE_STATUS_UP;
+			cell->node_info->recovery_type = get_recovery_type(cell->node_info->conn);
+
+			repmgrd_info[i]->pid = repmgrd_get_pid(cell->node_info->conn);
+
+			repmgrd_info[i]->running = repmgrd_is_running(cell->node_info->conn);
+
+			if (repmgrd_info[i]->running == true)
+			{
+				maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("running"));
+			}
+			else
+			{
+				maxlen_snprintf(repmgrd_info[i]->repmgrd_running, "%s", _("not running"));
+			}
+
+			if (repmgrd_info[i]->pid == UNKNOWN_PID)
+			{
+				maxlen_snprintf(repmgrd_info[i]->pid_text, "%s", _("n/a"));
+			}
+			else
+			{
+				maxlen_snprintf(repmgrd_info[i]->pid_text, "%i", repmgrd_info[i]->pid);
+			}
+
+			repmgrd_info[i]->paused = repmgrd_is_paused(cell->node_info->conn);
+
+			repmgrd_info[i]->recovery_type = get_recovery_type(cell->node_info->conn);
+
+			if (repmgrd_info[i]->recovery_type == RECTYPE_STANDBY)
+			{
+				repmgrd_info[i]->wal_paused_pending_wal = is_wal_replay_paused(cell->node_info->conn, true);
+
+				if (repmgrd_info[i]->wal_paused_pending_wal == true)
+				{
+					item_list_append_format(&warnings,
+											_("WAL replay is paused on node \"%s\" (ID: %i) with WAL replay pending; this node cannot be manually promoted  until WAL replay is resumed"),
+											cell->node_info->node_name, cell->node_info->node_id);
+				}
+			}
+
+			repmgrd_info[i]->upstream_last_seen = get_upstream_last_seen(cell->node_info->conn, cell->node_info->type);
+			if (repmgrd_info[i]->upstream_last_seen < 0)
+			{
+				maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, "%s", _("n/a"));
+			}
+			else
+			{
+				if (runtime_options.compact == true)
+				{
+					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i sec(s) ago"), repmgrd_info[i]->upstream_last_seen);
+				}
+				else
+				{
+					maxlen_snprintf(repmgrd_info[i]->upstream_last_seen_text, _("%i second(s) ago"), repmgrd_info[i]->upstream_last_seen);
+				}
+			}
+		}
+
+		initPQExpBuffer(&node_status);
+		initPQExpBuffer(&upstream);
+
+		(void)format_node_status(cell->node_info, &node_status, &upstream, &warnings);
+		snprintf(repmgrd_info[i]->pg_running_text, sizeof(cell->node_info->details),
+				 "%s", node_status.data);
+
+		snprintf(cell->node_info->upstream_node_name, sizeof(cell->node_info->upstream_node_name),
+				 "%s", upstream.data);
+
+		termPQExpBuffer(&node_status);
+		termPQExpBuffer(&upstream);
+
+		PQfinish(cell->node_info->conn);
+
+		headers_status[STATUS_NAME].cur_length = strlen(cell->node_info->node_name);
+		headers_status[STATUS_ROLE].cur_length = strlen(get_node_type_string(cell->node_info->type));
+		headers_status[STATUS_PG].cur_length = strlen(repmgrd_info[i]->pg_running_text);
+		headers_status[STATUS_UPSTREAM_NAME].cur_length = strlen(cell->node_info->upstream_node_name);
+
+		if (runtime_options.detail == true)
+		{
+			PQExpBufferData buf;
+
+			headers_status[STATUS_LOCATION].cur_length = strlen(cell->node_info->location);
+
+			initPQExpBuffer(&buf);
+			appendPQExpBuffer(&buf, "%i", cell->node_info->priority);
+			headers_status[STATUS_PRIORITY].cur_length = strlen(buf.data);
+			termPQExpBuffer(&buf);
+		}
+
+		headers_status[STATUS_PID].cur_length = strlen(repmgrd_info[i]->pid_text);
+		headers_status[STATUS_REPMGRD].cur_length = strlen(repmgrd_info[i]->repmgrd_running);
+
+		headers_status[STATUS_UPSTREAM_LAST_SEEN].cur_length = strlen(repmgrd_info[i]->upstream_last_seen_text);
+
+		for (j = 0; j < STATUS_HEADER_COUNT; j++)
+		{
+			if (headers_status[j].cur_length > headers_status[j].max_length)
+			{
+				headers_status[j].max_length = headers_status[j].cur_length;
+			}
+		}
+
+		i++;
+	}
+
+	/* Print column header row (text mode only) */
+	if (runtime_options.output_mode == OM_TEXT)
+	{
+		print_status_header(STATUS_HEADER_COUNT, headers_status);
+	}
+
+	i = 0;
+
+	for (cell = nodes.head; cell; cell = cell->next)
+	{
+		if (runtime_options.output_mode == OM_CSV)
+		{
+			int running = repmgrd_info[i]->running ? 1 : 0;
+			int paused = repmgrd_info[i]->paused ? 1 : 0;
+
+			/* If PostgreSQL is not running, repmgrd status is unknown */
+			if (repmgrd_info[i]->pg_running == false)
+			{
+				running = -1;
+				paused = -1;
+			}
+
+			printf("%i,%s,%s,%i,%i,%i,%i,%i,%i,%s\n",
+				   cell->node_info->node_id,
+				   cell->node_info->node_name,
+				   get_node_type_string(cell->node_info->type),
+				   repmgrd_info[i]->pg_running ? 1 : 0,
+				   running,
+				   repmgrd_info[i]->pid,
+				   paused,
+				   cell->node_info->priority,
+				   repmgrd_info[i]->pid == UNKNOWN_PID
+				     ? -1
+ 				     : repmgrd_info[i]->upstream_last_seen,
+				   cell->node_info->location);
+		}
+		else
+		{
+			printf(" %-*i ",  headers_status[STATUS_ID].max_length, cell->node_info->node_id);
+			printf("| %-*s ", headers_status[STATUS_NAME].max_length, cell->node_info->node_name);
+			printf("| %-*s ", headers_status[STATUS_ROLE].max_length, get_node_type_string(cell->node_info->type));
+			printf("| %-*s ", headers_status[STATUS_PG].max_length, repmgrd_info[i]->pg_running_text);
+			printf("| %-*s ", headers_status[STATUS_UPSTREAM_NAME].max_length, cell->node_info->upstream_node_name);
+
+			if (runtime_options.detail == true)
+			{
+				printf("| %-*s ", headers_status[STATUS_LOCATION].max_length, cell->node_info->location);
+				printf("| %-*i ", headers_status[STATUS_PRIORITY].max_length, cell->node_info->priority);
+			}
+
+			printf("| %-*s ", headers_status[STATUS_REPMGRD].max_length, repmgrd_info[i]->repmgrd_running);
+			printf("| %-*s ", headers_status[STATUS_PID].max_length, repmgrd_info[i]->pid_text);
+
+			if (repmgrd_info[i]->pid == UNKNOWN_PID)
+			{
+				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, _("n/a"));
+				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, _("n/a"));
+
+			}
+			else
+			{
+				printf("| %-*s ", headers_status[STATUS_PAUSED].max_length, repmgrd_info[i]->paused ? _("yes") : _("no"));
+
+				printf("| %-*s ", headers_status[STATUS_UPSTREAM_LAST_SEEN].max_length, repmgrd_info[i]->upstream_last_seen_text);
+			}
+
+			printf("\n");
+		}
+
+		pfree(repmgrd_info[i]);
+		i++;
+	}
+
+	pfree(repmgrd_info);
+
+	/* emit any warnings */
+
+	if (warnings.head != NULL && runtime_options.terse == false && runtime_options.output_mode != OM_CSV)
+	{
+		ItemListCell *cell = NULL;
+
+		PQExpBufferData warning;
+
+		initPQExpBuffer(&warning);
+
+		appendPQExpBufferStr(&warning,
+							 _("following issues were detected\n"));
+
+		for (cell = warnings.head; cell; cell = cell->next)
+		{
+			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"));
+		}
+	}
+}
+
+void
+do_service_pause(void)
+{
+	_do_repmgr_pause(true);
+}
+
+void
+do_service_unpause(void)
+{
+	_do_repmgr_pause(false);
+}
+
+
+static void
+_do_repmgr_pause(bool pause)
+{
+	PGconn	   *conn = NULL;
+	NodeInfoList nodes = T_NODE_INFO_LIST_INITIALIZER;
+	NodeInfoListCell *cell = NULL;
+	int i;
+	int error_nodes = 0;
+
+	/* Connect to local database to obtain cluster connection data */
+	log_verbose(LOG_INFO, _("connecting to database"));
+
+	if (strlen(config_file_options.conninfo))
+		conn = establish_db_connection(config_file_options.conninfo, true);
+	else
+		conn = establish_db_connection_by_params(&source_conninfo, true);
+
+	fetch_node_records(conn, &nodes);
+
+	i = 0;
+
+	for (cell = nodes.head; cell; cell = cell->next)
+	{
+		log_verbose(LOG_DEBUG, "pausing node %i (%s)",
+					cell->node_info->node_id,
+					cell->node_info->node_name);
+		cell->node_info->conn = establish_db_connection_quiet(cell->node_info->conninfo);
+
+		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
+		{
+			log_warning(_("unable to connect to node %i"),
+						cell->node_info->node_id);
+			error_nodes++;
+		}
+		else
+		{
+			if (runtime_options.dry_run == true)
+			{
+				if (pause == true)
+				{
+					log_info(_("would pause node %i (%s) "),
+							 cell->node_info->node_id,
+							 cell->node_info->node_name);
+				}
+				else
+				{
+					log_info(_("would unpause node %i (%s) "),
+							 cell->node_info->node_id,
+							 cell->node_info->node_name);
+				}
+			}
+			else
+			{
+				bool success = repmgrd_pause(cell->node_info->conn, pause);
+
+				if (success == false)
+					error_nodes++;
+
+				log_notice(_("node %i (%s) %s"),
+						   cell->node_info->node_id,
+						   cell->node_info->node_name,
+						   success == true
+								? pause == true ? "paused" : "unpaused"
+		   						: pause == true ? "not paused" : "not unpaused");
+			}
+			PQfinish(cell->node_info->conn);
+		}
+		i++;
+	}
+
+	if (error_nodes > 0)
+	{
+		if (pause == true)
+		{
+			log_error(_("unable to pause %i node(s)"), error_nodes);
+		}
+		else
+		{
+			log_error(_("unable to unpause %i node(s)"), error_nodes);
+		}
+
+		log_hint(_("execute \"repmgr service status\" to view current status"));
+
+		exit(ERR_REPMGRD_PAUSE);
+	}
+
+	exit(SUCCESS);
+}
+
+
+
+void
+fetch_node_records(PGconn *conn, NodeInfoList *node_list)
+{
+	bool success = get_all_node_records_with_upstream(conn, node_list);
+
+	if (success == false)
+	{
+		/* get_all_node_records() will display any error message */
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	if (node_list->node_count == 0)
+	{
+		log_error(_("no node records were found"));
+		log_hint(_("ensure at least one node is registered"));
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+}
+
+
+
+void do_service_help(void)
+{
+	print_help_header();
+
+	printf(_("Usage:\n"));
+	printf(_("    %s [OPTIONS] service status\n"),  progname());
+	printf(_("    %s [OPTIONS] service pause\n"),   progname());
+	printf(_("    %s [OPTIONS] service unpause\n"), progname());
+
+	puts("");
+
+	printf(_("SERVICE STATUS\n"));
+	puts("");
+	printf(_("  \"service status\" shows the status of repmgrd on each node in the cluster\n"));
+	puts("");
+	printf(_("    --csv                     emit output as CSV\n"));
+	printf(_("    --detail                  show additional detail\n"));
+	printf(_("    --verbose                 show text of database connection error messages\n"));
+	puts("");
+
+	printf(_("SERVICE PAUSE\n"));
+	puts("");
+	printf(_("  \"service pause\" instructs repmgrd on each node to pause failover detection\n"));
+	puts("");
+	printf(_("    --dry-run               check if nodes are reachable but don't pause repmgrd\n"));
+	puts("");
+
+	printf(_("SERVICE UNPAUSE\n"));
+	puts("");
+	printf(_("  \"service unpause\"  instructs repmgrd on each node to resume failover detection\n"));
+	puts("");
+	printf(_("    --dry-run               check if nodes are reachable but don't unpause repmgrd\n"));
+	puts("");
+
+	puts("");
+
+	printf(_("%s home page: <%s>\n"), "repmgr", REPMGR_URL);
+}

repmgr-action-service.h

@@ -1,6 +1,6 @@
 /*
- * repmgr-action-bdr.h
+ * repmgr-action-service.h
- * Copyright (c) 2ndQuadrant, 2010-2019
+ * Copyright (c) EnterpriseDB Corporation, 2010-2021
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -16,13 +16,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef _REPMGR_ACTION_BDR_H_
+#ifndef _REPMGR_ACTION_SERVICE_H_
-#define _REPMGR_ACTION_BDR_H_
+#define _REPMGR_ACTION_SERVICE_H_
-
-extern void do_bdr_register(void);
-extern void do_bdr_unregister(void);
-
-extern void do_bdr_help(void);
 
 
-#endif							/* _REPMGR_ACTION_BDR_H_ */
+extern void do_service_status(void);
+extern void do_service_pause(void);
+extern void do_service_unpause(void);
+
+extern void do_service_help(void);
+#endif