4.4beta2

This ensures the provided path matches the path PostgreSQL reports as its
data directory.

.gitignore

@@ -53,6 +53,3 @@ 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 2010-2020, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+Copyright 2010-2019, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
 details.
 
 The development of repmgr has primarily been sponsored by 2ndQuadrant customers.

COPYRIGHT

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

HISTORY

@@ -1,38 +1,4 @@
-5.1.0   2020-04-13
-        repmgr: remove BDR 2.x support
-        repmgr: don't query upstream's data directory (Ian)
-        repmgr: rename --recovery-conf-only to --replication-conf-only (Ian)
-        repmgr: ensure postgresql.auto.conf is created with correct permissions (Ian)
-        repmgr: minimize requirement to check upstream data directory location
-          during "standby clone" (Ian)
-        repmgr: warn about missing pg_rewind prerequisites when excuting
-          "standby clone" (Ian)
-        repmgr: add --upstream option to "node check"
-        repmgr: report error code on follow/rejoin failure due to non-available
-          replication slot (Ian)
-        repmgr: ensure "node rejoin" checks for available replication slots (Ian)
-        repmgr: improve "standby switchover" completion checks (Ian)
-        repmgr: add replication configuration file ownership check to
-          "standby switchover" (Ian)
-        repmgr: check the demotion candidate's registered repmgr.conf file can
-          be found (laixiong; GitHub 615)
-        repmgr: consolidate replication connection code (Ian)
-        repmgr: check permissions for "pg_promote()" and fall back to pg_ctl
-          if necessary (Ian)
-        repmgr: in --dry-run mode, display promote command which will be used (Ian)
-        repmgr: enable "service_promote_command" in PostgreSQL 12 (Ian)
-        repmgr: accept option -S/--superuser for "node check"; GitHub #612 (Ian)
-
-5.0     2019-10-15
-        general: add PostgreSQL 12 support (Ian)
-        general: parse configuration file using flex (Ian)
-        repmgr: rename "repmgr daemon ..." commands to "repmgr service ..." (Ian)
-        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
+4.4     2019-??-??
         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)
@@ -58,7 +24,6 @@
         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

@@ -2,7 +2,6 @@
 # Makefile.global.in
 # @configure_input@
 
-
 # Can only be built using pgxs
 USE_PGXS=1
 
@@ -15,9 +14,6 @@ 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
@@ -28,13 +24,4 @@ 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

@@ -11,7 +11,6 @@ EXTENSION = repmgr
 
 DATA = \
   repmgr--unpackaged--4.0.sql \
-  repmgr--unpackaged--5.1.sql \
   repmgr--4.0.sql \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \
@@ -20,11 +19,7 @@ DATA = \
   repmgr--4.2--4.3.sql \
   repmgr--4.3.sql \
   repmgr--4.3--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--4.4.sql
 
 REGRESS = repmgr_extension
 
@@ -56,16 +51,13 @@ $(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-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
-	configfile.o configfile-scan.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
-REPMGRD_OBJS = repmgrd.o repmgrd-physical.o configfile.o configfile-scan.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.o
+	repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.o repmgr-action-daemon.o \
+	configfile.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
+REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o 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
-	$(SED) -E 's/REPMGR_VERSION_DATE.*""/REPMGR_VERSION_DATE "$(DATE)"/' $< >$@; \
-	$(SED) -i -E 's/PG_ACTUAL_VERSION_NUM/PG_ACTUAL_VERSION_NUM $(VERSION_NUM)/' $@
-
-configfile-scan.c: configfile-scan.l
+	sed '0,/REPMGR_VERSION_DATE/s,\(REPMGR_VERSION_DATE\).*,\1 "$(DATE)",' $< >$@
 
 $(REPMGR_CLIENT_OBJS): repmgr-client.h repmgr_version.h
 
@@ -106,7 +98,6 @@ 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

@@ -7,30 +7,32 @@ replication capabilities with utilities to set up standby servers, monitor
 replication, and perform administrative tasks such as failover or switchover
 operations.
 
-PostgreSQL 12, 11, 10, 9.6 and 9.5 are fully supported.
+`repmgr 4` is a complete rewrite of the existing `repmgr` codebase, allowing
+the use of all of the latest features in PostgreSQL replication.
+
+PostgreSQL 11, 10, 9.6 and 9.5 are fully supported.
 PostgreSQL 9.4 and 9.3 are supported, with some restrictions.
 
 `repmgr` is distributed under the GNU GPL 3 and maintained by 2ndQuadrant.
 
+### BDR support
+
+`repmgr 4` supports monitoring of a two-node BDR 2.0 cluster on PostgreSQL 9.6
+only. Note that BDR 2.0 is not publicly available; please contact 2ndQuadrant
+for details.
+
+
 Documentation
 -------------
 
-The full `repmgr` documentation is available here:
+The main `repmgr` documentation is available here:
 
 > [repmgr documentation](https://repmgr.org/docs/current/index.html)
 
-The old `README` file for `repmgr` 3.x is available here:
+The `README` file for `repmgr` 3.x is available here:
 
 > https://github.com/2ndQuadrant/repmgr/blob/REL3_3_STABLE/README.md
 
-Note that the `repmgr` 3.x series is no longer supported and contains known bugs;
-please upgrade to the current `repmgr` version as soon as possible.
-
-Versions
---------
-
-For an overview of `repmgr` versions and PostgreSQL compatibility, see the
-[repmgr compatibility matrix](https://repmgr.org/docs/current/install-requirements.html#INSTALL-COMPATIBILITY-MATRIX).
 
 Files
 ------
@@ -70,8 +72,6 @@ Please report bugs and other issues to:
 
 * https://github.com/2ndQuadrant/repmgr
 
-See 
-
 Further information is available at https://repmgr.org/
 
 We'd love to hear from you about how you use repmgr. Case studies and
@@ -98,8 +98,6 @@ Further reading
 ---------------
 
 * [repmgr documentation](https://repmgr.org/docs/current/index.html)
-* [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 1](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-1/)
-* [How to Automate PostgreSQL 12 Replication and Failover with repmgr - Part 2](https://www.2ndquadrant.com/en/blog/how-to-automate-postgresql-12-replication-and-failover-with-repmgr-part-2/)
 * https://blog.2ndquadrant.com/repmgr-3-2-is-here-barman-support-brand-new-high-availability-features/
 * https://blog.2ndquadrant.com/improvements-in-repmgr-3-1-4/
 * https://blog.2ndquadrant.com/managing-useful-clusters-repmgr/

compat.c

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

compat.h

@@ -1,6 +1,6 @@
 /*
  * compat.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California

configfile-scan.l

@@ -1,366 +0,0 @@
-/*
- * Scanner for the configuration file
- */
-
-%{
-
-#include <setjmp.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(FILE *fp, const char *config_file, KeyValueList *contents, t_configuration_options *options, ItemList *error_list, ItemList *warning_list);
-
-%}
-
-%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(FILE *fp, const char *config_file, t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
-{
-	return ProcessConfigFile(fp, config_file, NULL, options, error_list, warning_list);
-}
-
-extern bool
-ProcessPostgresConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, ItemList *error_list, ItemList *warning_list)
-{
-	return ProcessConfigFile(fp, config_file, contents, NULL, error_list, warning_list);
-}
-
-static bool
-ProcessConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
-{
-	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++;
-		}
-
-		/* OK, process the option name and value */
-		if (contents != NULL)
-		{
-			key_value_list_replace_or_set(contents,
-										  opt_name,
-										  opt_value);
-		}
-
-		if (options != NULL)
-		{
-			parse_configuration_item(options,
-									 error_list,
-									 warning_list,
-									 opt_name,
-									 opt_value);
-		}
-
-		/* break out of loop if read EOF, else loop for next line */
-		if (token == 0)
-			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;
-}
-
-
-/*
- *		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;
-}
-
-
-/*
- * 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.c

@@ -1,7 +1,7 @@
 /*
  * config.c - parse repmgr.conf and other configuration-related functionality
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -23,12 +23,6 @@
 #include "configfile.h"
 #include "log.h"
 
-#include <utils/elog.h>
-
-#if (PG_ACTUAL_VERSION_NUM >= 100000)
-#include <storage/fd.h>			/* for durable_rename() */
-#endif
-
 const static char *_progname = NULL;
 char		config_file_path[MAXPGPATH] = "";
 static bool config_file_provided = false;
@@ -272,6 +266,12 @@ static void
 _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *warning_list)
 {
 	FILE	   *fp;
+	char	   *s = NULL,
+				buf[MAXLINELENGTH] = "";
+	char		name[MAXLEN] = "";
+	char		value[MAXLEN] = "";
+
+	bool		node_id_found = false;
 
 	/* Initialize configuration options with sensible defaults */
 
@@ -378,6 +378,13 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	 */
 	options->witness_sync_interval = DEFAULT_WITNESS_SYNC_INTERVAL;
 
+	/*-------------
+	 * BDR settings
+	 *-------------
+	 */
+	options->bdr_local_monitoring_only = false;
+	options->bdr_recovery_timeout = DEFAULT_BDR_RECOVERY_TIMEOUT;
+
 	/*-------------------------
 	 * service command settings
 	 *-------------------------
@@ -461,12 +468,365 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		exit(ERR_BAD_CONFIG);
 	}
 
-	(void) ProcessRepmgrConfigFile(fp, config_file_path, options, error_list, warning_list);
+	/* Read file */
+	while ((s = fgets(buf, sizeof buf, fp)) != NULL)
+	{
+		bool		known_parameter = true;
+
+		/* Parse name/value pair from line */
+		_parse_line(buf, name, value);
+
+		/* Skip blank lines */
+		if (!strlen(name))
+			continue;
+
+		/* Skip comments */
+		if (name[0] == '#')
+			continue;
+
+		/* Copy into correct entry in parameters struct */
+		if (strcmp(name, "node_id") == 0)
+		{
+			options->node_id = repmgr_atoi(value, name, error_list, MIN_NODE_ID);
+			node_id_found = true;
+		}
+		else if (strcmp(name, "node_name") == 0)
+		{
+			if (strlen(value) < sizeof(options->node_name))
+				strncpy(options->node_name, value, sizeof(options->node_name));
+			else
+				item_list_append_format(error_list,
+										_("value for \"node_name\" must contain fewer than %lu characters"),
+										sizeof(options->node_name));
+		}
+		else if (strcmp(name, "conninfo") == 0)
+			strncpy(options->conninfo, value, MAXLEN);
+		else if (strcmp(name, "data_directory") == 0)
+		{
+			strncpy(options->data_directory, value, MAXPGPATH);
+			canonicalize_path(options->data_directory);
+		}
+		else if (strcmp(name, "config_directory") == 0)
+		{
+			strncpy(options->config_directory, value, MAXPGPATH);
+			canonicalize_path(options->config_directory);
+		}
+		else if (strcmp(name, "replication_user") == 0)
+		{
+			if (strlen(value) < sizeof(options->replication_user))
+				strncpy(options->replication_user, value, sizeof(options->replication_user));
+			else
+				item_list_append_format(error_list,
+										_("value for \"replication_user\" must contain fewer than %lu characters"),
+										sizeof(options->replication_user));
+		}
+		else if (strcmp(name, "pg_bindir") == 0)
+			strncpy(options->pg_bindir, value, MAXPGPATH);
+		else if (strcmp(name, "repmgr_bindir") == 0)
+			strncpy(options->repmgr_bindir, value, MAXPGPATH);
+
+		else if (strcmp(name, "replication_type") == 0)
+		{
+			if (strcmp(value, "physical") == 0)
+				options->replication_type = REPLICATION_TYPE_PHYSICAL;
+			else if (strcmp(value, "bdr") == 0)
+				options->replication_type = REPLICATION_TYPE_BDR;
+			else
+				item_list_append(error_list, _("value for \"replication_type\" must be \"physical\" or \"bdr\""));
+		}
+
+		/* log settings */
+		else if (strcmp(name, "log_file") == 0)
+			strncpy(options->log_file, value, MAXLEN);
+		else if (strcmp(name, "log_level") == 0)
+			strncpy(options->log_level, value, MAXLEN);
+		else if (strcmp(name, "log_facility") == 0)
+			strncpy(options->log_facility, value, MAXLEN);
+		else if (strcmp(name, "log_status_interval") == 0)
+			options->log_status_interval = repmgr_atoi(value, name, error_list, 0);
+
+		/* standby clone settings */
+		else if (strcmp(name, "use_replication_slots") == 0)
+			options->use_replication_slots = parse_bool(value, name, error_list);
+		else if (strcmp(name, "pg_basebackup_options") == 0)
+			strncpy(options->pg_basebackup_options, value, MAXLEN);
+		else if (strcmp(name, "tablespace_mapping") == 0)
+			tablespace_list_append(options, value);
+		else if (strcmp(name, "restore_command") == 0)
+			strncpy(options->restore_command, value, MAXLEN);
+		else if (strcmp(name, "recovery_min_apply_delay") == 0)
+		{
+			parse_time_unit_parameter(name, value, options->recovery_min_apply_delay, error_list);
+			options->recovery_min_apply_delay_provided = true;
+		}
+		else if (strcmp(name, "archive_cleanup_command") == 0)
+			strncpy(options->archive_cleanup_command, value, MAXLEN);
+		else if (strcmp(name, "use_primary_conninfo_password") == 0)
+			options->use_primary_conninfo_password = parse_bool(value, name, error_list);
+		else if (strcmp(name, "passfile") == 0)
+			strncpy(options->passfile, value, sizeof(options->passfile));
+
+		/* standby promote settings */
+		else if (strcmp(name, "promote_check_timeout") == 0)
+			options->promote_check_timeout = repmgr_atoi(value, name, error_list, 1);
+
+		else if (strcmp(name, "promote_check_interval") == 0)
+			options->promote_check_interval = repmgr_atoi(value, name, error_list, 1);
+
+		/* standby follow settings */
+		else if (strcmp(name, "primary_follow_timeout") == 0)
+			options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "standby_follow_timeout") == 0)
+			options->standby_follow_timeout = repmgr_atoi(value, name, error_list, 0);
+
+		/* standby switchover settings */
+		else if (strcmp(name, "shutdown_check_timeout") == 0)
+			options->shutdown_check_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "standby_reconnect_timeout") == 0)
+			options->standby_reconnect_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "wal_receive_check_timeout") == 0)
+			options->wal_receive_check_timeout = repmgr_atoi(value, name, error_list, 0);
+
+		/* node rejoin settings */
+		else if (strcmp(name, "node_rejoin_timeout") == 0)
+			options->node_rejoin_timeout = repmgr_atoi(value, name, error_list, 0);
+
+		/* node check settings */
+		else if (strcmp(name, "archive_ready_warning") == 0)
+			options->archive_ready_warning = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "archive_ready_critical") == 0)
+			options->archive_ready_critical = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "replication_lag_warning") == 0)
+			options->replication_lag_warning = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "replication_lag_critical") == 0)
+			options->replication_lag_critical = repmgr_atoi(value, name, error_list, 1);
+
+		/* repmgrd settings */
+		else if (strcmp(name, "failover") == 0)
+		{
+			if (strcmp(value, "manual") == 0)
+			{
+				options->failover = FAILOVER_MANUAL;
+			}
+			else if (strcmp(value, "automatic") == 0)
+			{
+				options->failover = FAILOVER_AUTOMATIC;
+			}
+			else
+			{
+				item_list_append(error_list,
+								 _("value for \"failover\" must be \"automatic\" or \"manual\"\n"));
+			}
+		}
+		else if (strcmp(name, "priority") == 0)
+			options->priority = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "location") == 0)
+			strncpy(options->location, value, sizeof(options->location));
+		else if (strcmp(name, "promote_command") == 0)
+			strncpy(options->promote_command, value, sizeof(options->promote_command));
+		else if (strcmp(name, "follow_command") == 0)
+			strncpy(options->follow_command, value, sizeof(options->follow_command));
+		else if (strcmp(name, "reconnect_attempts") == 0)
+			options->reconnect_attempts = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "reconnect_interval") == 0)
+			options->reconnect_interval = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "monitor_interval_secs") == 0)
+			options->monitor_interval_secs = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "monitoring_history") == 0)
+			options->monitoring_history = parse_bool(value, name, error_list);
+		else if (strcmp(name, "degraded_monitoring_timeout") == 0)
+			options->degraded_monitoring_timeout = repmgr_atoi(value, name, error_list, -1);
+		else if (strcmp(name, "async_query_timeout") == 0)
+			options->async_query_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "primary_notification_timeout") == 0)
+			options->primary_notification_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "repmgrd_standby_startup_timeout") == 0)
+			options->repmgrd_standby_startup_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "repmgrd_pid_file") == 0)
+			strncpy(options->repmgrd_pid_file, value, MAXPGPATH);
+		else if (strcmp(name, "standby_disconnect_on_failover") == 0)
+			options->standby_disconnect_on_failover = parse_bool(value, name, error_list);
+		else if (strcmp(name, "sibling_nodes_disconnect_timeout") == 0)
+			options->sibling_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "connection_check_type") == 0)
+		{
+			if (strcasecmp(value, "ping") == 0)
+			{
+				options->connection_check_type = CHECK_PING;
+			}
+			else if (strcasecmp(value, "connection") == 0)
+			{
+				options->connection_check_type = CHECK_CONNECTION;
+			}
+			else if (strcasecmp(value, "query") == 0)
+			{
+				options->connection_check_type = CHECK_QUERY;
+			}
+			else
+			{
+				item_list_append(error_list,
+								 _("value for \"connection_check_type\" must be \"ping\", \"connection\" or \"query\"\n"));
+			}
+		}
+		else if (strcmp(name, "primary_visibility_consensus") == 0)
+			options->primary_visibility_consensus = parse_bool(value, name, error_list);
+		else if (strcmp(name, "failover_validation_command") == 0)
+			strncpy(options->failover_validation_command, value, sizeof(options->failover_validation_command));
+		else if (strcmp(name, "election_rerun_interval") == 0)
+			options->election_rerun_interval = repmgr_atoi(value, name, error_list, 0);
+		else if (strcmp(name, "child_nodes_check_interval") == 0)
+			options->child_nodes_check_interval = repmgr_atoi(value, name, error_list, 1);
+		else if (strcmp(name, "child_nodes_disconnect_command") == 0)
+			snprintf(options->child_nodes_disconnect_command, sizeof(options->child_nodes_disconnect_command), "%s", value);
+		else if (strcmp(name, "child_nodes_disconnect_min_count") == 0)
+			options->child_nodes_disconnect_min_count = repmgr_atoi(value, name, error_list, -1);
+		else if (strcmp(name, "child_nodes_connected_min_count") == 0)
+			options->child_nodes_connected_min_count = repmgr_atoi(value, name, error_list, -1);
+		else if (strcmp(name, "child_nodes_connected_include_witness") == 0)
+			options->child_nodes_connected_include_witness = parse_bool(value, name, error_list);
+		else if (strcmp(name, "child_nodes_disconnect_timeout") == 0)
+			options->child_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
+
+		/* witness settings */
+		else if (strcmp(name, "witness_sync_interval") == 0)
+			options->witness_sync_interval = repmgr_atoi(value, name, error_list, 1);
+
+		/* BDR settings */
+		else if (strcmp(name, "bdr_local_monitoring_only") == 0)
+			options->bdr_local_monitoring_only = parse_bool(value, name, error_list);
+		else if (strcmp(name, "bdr_recovery_timeout") == 0)
+			options->bdr_recovery_timeout = repmgr_atoi(value, name, error_list, 0);
+
+		/* service settings */
+		else if (strcmp(name, "pg_ctl_options") == 0)
+			strncpy(options->pg_ctl_options, value, sizeof(options->pg_ctl_options));
+		else if (strcmp(name, "service_start_command") == 0)
+			strncpy(options->service_start_command, value, sizeof(options->service_start_command));
+		else if (strcmp(name, "service_stop_command") == 0)
+			strncpy(options->service_stop_command, value, sizeof(options->service_stop_command));
+		else if (strcmp(name, "service_restart_command") == 0)
+			strncpy(options->service_restart_command, value, sizeof(options->service_restart_command));
+		else if (strcmp(name, "service_reload_command") == 0)
+			strncpy(options->service_reload_command, value, sizeof(options->service_reload_command));
+		else if (strcmp(name, "service_promote_command") == 0)
+			strncpy(options->service_promote_command, value, sizeof(options->service_promote_command));
+
+		/* repmgrd service settings */
+		else if (strcmp(name, "repmgrd_service_start_command") == 0)
+			strncpy(options->repmgrd_service_start_command, value, sizeof(options->repmgrd_service_start_command));
+		else if (strcmp(name, "repmgrd_service_stop_command") == 0)
+			strncpy(options->repmgrd_service_stop_command, value, sizeof(options->repmgrd_service_stop_command));
+
+
+		/* event notification settings */
+		else if (strcmp(name, "event_notification_command") == 0)
+			strncpy(options->event_notification_command, value, sizeof(options->event_notification_command));
+		else if (strcmp(name, "event_notifications") == 0)
+		{
+			/* store unparsed value for comparison when reloading config */
+			strncpy(options->event_notifications_orig, value, sizeof(options->event_notifications_orig));
+			parse_event_notifications_list(options, value);
+		}
+
+		/* barman settings */
+		else if (strcmp(name, "barman_host") == 0)
+			strncpy(options->barman_host, value, sizeof(options->barman_host));
+		else if (strcmp(name, "barman_server") == 0)
+			strncpy(options->barman_server, value, sizeof(options->barman_server));
+		else if (strcmp(name, "barman_config") == 0)
+			strncpy(options->barman_config, value, sizeof(options->barman_config));
+
+		/* rsync/ssh settings */
+		else if (strcmp(name, "rsync_options") == 0)
+			strncpy(options->rsync_options, value, sizeof(options->rsync_options));
+		else if (strcmp(name, "ssh_options") == 0)
+			strncpy(options->ssh_options, value, sizeof(options->ssh_options));
+
+		/* undocumented settings for testing */
+		else if (strcmp(name, "promote_delay") == 0)
+			options->promote_delay = repmgr_atoi(value, name, error_list, 1);
+
+		/*
+		 * Following parameters have been deprecated or renamed from 3.x -
+		 * issue a warning
+		 */
+		else if (strcmp(name, "cluster") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"cluster\" is deprecated and will be ignored"));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "node") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"node\" has been renamed to \"node_id\""));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "upstream_node") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"upstream_node\" has been removed; use \"--upstream-node-id\" when cloning a standby"));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "loglevel") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"loglevel\" has been renamed to \"log_level\""));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "logfacility") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"logfacility\" has been renamed to \"log_facility\""));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "logfile") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"logfile\" has been renamed to \"log_file\""));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "master_reponse_timeout") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"master_reponse_timeout\" has been removed; use \"async_query_timeout\" instead"));
+			known_parameter = false;
+		}
+		else if (strcmp(name, "retry_promote_interval_secs") == 0)
+		{
+			item_list_append(warning_list,
+							 _("parameter \"retry_promote_interval_secs\" has been removed; use \"primary_notification_timeout\" instead"));
+			known_parameter = false;
+		}
+		else
+		{
+			known_parameter = false;
+			log_warning(_("%s/%s: unknown name/value pair provided; ignoring"), name, value);
+		}
+
+		/*
+		 * Raise an error if a known parameter is provided with an empty
+		 * value. Currently there's no reason why empty parameters are needed;
+		 * if we want to accept those, we'd need to add stricter default
+		 * checking, as currently e.g. an empty `node_id` value will be converted
+		 * to '0'.
+		 */
+		if (known_parameter == true && !strlen(value))
+		{
+			char		error_message_buf[MAXLEN] = "";
+
+			maxlen_snprintf(error_message_buf,
+							_("\"%s\": no value provided"),
+							name);
+
+			item_list_append(error_list, error_message_buf);
+		}
+	}
 
 	fclose(fp);
 
 	/* check required parameters */
-	if (options->node_id == UNKNOWN_NODE_ID)
+	if (node_id_found == false)
 	{
 		item_list_append(error_list, _("\"node_id\": required parameter was not found"));
 	}
@@ -559,313 +919,6 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 }
 
 
-void
-parse_configuration_item(t_configuration_options *options, ItemList *error_list, ItemList *warning_list, const char *name, const char *value)
-{
-	if (strcmp(name, "node_id") == 0)
-	{
-		options->node_id = repmgr_atoi(value, name, error_list, MIN_NODE_ID);
-	}
-	else if (strcmp(name, "node_name") == 0)
-	{
-		if (strlen(value) < sizeof(options->node_name))
-			strncpy(options->node_name, value, sizeof(options->node_name));
-		else
-			item_list_append_format(error_list,
-									_("value for \"node_name\" must contain fewer than %lu characters"),
-									sizeof(options->node_name));
-	}
-	else if (strcmp(name, "conninfo") == 0)
-	{
-		strncpy(options->conninfo, value, MAXLEN);
-	}
-	else if (strcmp(name, "data_directory") == 0)
-	{
-		strncpy(options->data_directory, value, MAXPGPATH);
-		canonicalize_path(options->data_directory);
-	}
-	else if (strcmp(name, "config_directory") == 0)
-	{
-		strncpy(options->config_directory, value, MAXPGPATH);
-		canonicalize_path(options->config_directory);
-	}
-	else if (strcmp(name, "replication_user") == 0)
-	{
-		if (strlen(value) < sizeof(options->replication_user))
-			strncpy(options->replication_user, value, sizeof(options->replication_user));
-		else
-			item_list_append_format(error_list,
-									_("value for \"replication_user\" must contain fewer than %lu characters"),
-									sizeof(options->replication_user));
-	}
-	else if (strcmp(name, "pg_bindir") == 0)
-		strncpy(options->pg_bindir, value, MAXPGPATH);
-	else if (strcmp(name, "repmgr_bindir") == 0)
-		strncpy(options->repmgr_bindir, value, MAXPGPATH);
-
-	else if (strcmp(name, "replication_type") == 0)
-	{
-		if (strcmp(value, "physical") == 0)
-			options->replication_type = REPLICATION_TYPE_PHYSICAL;
-		else
-			item_list_append(error_list, _("value for \"replication_type\" must be \"physical\""));
-	}
-
-	/* log settings */
-	else if (strcmp(name, "log_file") == 0)
-		strncpy(options->log_file, value, MAXLEN);
-	else if (strcmp(name, "log_level") == 0)
-		strncpy(options->log_level, value, MAXLEN);
-	else if (strcmp(name, "log_facility") == 0)
-		strncpy(options->log_facility, value, MAXLEN);
-	else if (strcmp(name, "log_status_interval") == 0)
-		options->log_status_interval = repmgr_atoi(value, name, error_list, 0);
-
-	/* standby clone settings */
-	else if (strcmp(name, "use_replication_slots") == 0)
-		options->use_replication_slots = parse_bool(value, name, error_list);
-	else if (strcmp(name, "pg_basebackup_options") == 0)
-		strncpy(options->pg_basebackup_options, value, MAXLEN);
-	else if (strcmp(name, "tablespace_mapping") == 0)
-		tablespace_list_append(options, value);
-	else if (strcmp(name, "restore_command") == 0)
-		strncpy(options->restore_command, value, MAXLEN);
-	else if (strcmp(name, "recovery_min_apply_delay") == 0)
-	{
-		parse_time_unit_parameter(name, value, options->recovery_min_apply_delay, error_list);
-		options->recovery_min_apply_delay_provided = true;
-	}
-	else if (strcmp(name, "archive_cleanup_command") == 0)
-		strncpy(options->archive_cleanup_command, value, MAXLEN);
-	else if (strcmp(name, "use_primary_conninfo_password") == 0)
-		options->use_primary_conninfo_password = parse_bool(value, name, error_list);
-	else if (strcmp(name, "passfile") == 0)
-		strncpy(options->passfile, value, sizeof(options->passfile));
-
-	/* standby promote settings */
-	else if (strcmp(name, "promote_check_timeout") == 0)
-		options->promote_check_timeout = repmgr_atoi(value, name, error_list, 1);
-
-	else if (strcmp(name, "promote_check_interval") == 0)
-		options->promote_check_interval = repmgr_atoi(value, name, error_list, 1);
-
-	/* standby follow settings */
-	else if (strcmp(name, "primary_follow_timeout") == 0)
-		options->primary_follow_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "standby_follow_timeout") == 0)
-		options->standby_follow_timeout = repmgr_atoi(value, name, error_list, 0);
-
-	/* standby switchover settings */
-	else if (strcmp(name, "shutdown_check_timeout") == 0)
-		options->shutdown_check_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "standby_reconnect_timeout") == 0)
-		options->standby_reconnect_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "wal_receive_check_timeout") == 0)
-		options->wal_receive_check_timeout = repmgr_atoi(value, name, error_list, 0);
-
-	/* node rejoin settings */
-	else if (strcmp(name, "node_rejoin_timeout") == 0)
-		options->node_rejoin_timeout = repmgr_atoi(value, name, error_list, 0);
-
-	/* node check settings */
-	else if (strcmp(name, "archive_ready_warning") == 0)
-		options->archive_ready_warning = repmgr_atoi(value, name, error_list, 1);
-	else if (strcmp(name, "archive_ready_critical") == 0)
-		options->archive_ready_critical = repmgr_atoi(value, name, error_list, 1);
-	else if (strcmp(name, "replication_lag_warning") == 0)
-		options->replication_lag_warning = repmgr_atoi(value, name, error_list, 1);
-	else if (strcmp(name, "replication_lag_critical") == 0)
-		options->replication_lag_critical = repmgr_atoi(value, name, error_list, 1);
-
-	/* repmgrd settings */
-	else if (strcmp(name, "failover") == 0)
-	{
-		if (strcmp(value, "manual") == 0)
-		{
-			options->failover = FAILOVER_MANUAL;
-		}
-		else if (strcmp(value, "automatic") == 0)
-		{
-			options->failover = FAILOVER_AUTOMATIC;
-		}
-		else
-		{
-			item_list_append(error_list,
-							 _("value for \"failover\" must be \"automatic\" or \"manual\"\n"));
-		}
-	}
-	else if (strcmp(name, "priority") == 0)
-		options->priority = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "location") == 0)
-		strncpy(options->location, value, sizeof(options->location));
-	else if (strcmp(name, "promote_command") == 0)
-		strncpy(options->promote_command, value, sizeof(options->promote_command));
-	else if (strcmp(name, "follow_command") == 0)
-		strncpy(options->follow_command, value, sizeof(options->follow_command));
-	else if (strcmp(name, "reconnect_attempts") == 0)
-		options->reconnect_attempts = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "reconnect_interval") == 0)
-		options->reconnect_interval = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "monitor_interval_secs") == 0)
-		options->monitor_interval_secs = repmgr_atoi(value, name, error_list, 1);
-	else if (strcmp(name, "monitoring_history") == 0)
-		options->monitoring_history = parse_bool(value, name, error_list);
-	else if (strcmp(name, "degraded_monitoring_timeout") == 0)
-		options->degraded_monitoring_timeout = repmgr_atoi(value, name, error_list, -1);
-	else if (strcmp(name, "async_query_timeout") == 0)
-		options->async_query_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "primary_notification_timeout") == 0)
-		options->primary_notification_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "repmgrd_standby_startup_timeout") == 0)
-		options->repmgrd_standby_startup_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "repmgrd_pid_file") == 0)
-		strncpy(options->repmgrd_pid_file, value, MAXPGPATH);
-	else if (strcmp(name, "standby_disconnect_on_failover") == 0)
-		options->standby_disconnect_on_failover = parse_bool(value, name, error_list);
-	else if (strcmp(name, "sibling_nodes_disconnect_timeout") == 0)
-		options->sibling_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "connection_check_type") == 0)
-	{
-		if (strcasecmp(value, "ping") == 0)
-		{
-			options->connection_check_type = CHECK_PING;
-		}
-		else if (strcasecmp(value, "connection") == 0)
-		{
-			options->connection_check_type = CHECK_CONNECTION;
-		}
-		else if (strcasecmp(value, "query") == 0)
-		{
-			options->connection_check_type = CHECK_QUERY;
-		}
-		else
-		{
-			item_list_append(error_list,
-							 _("value for \"connection_check_type\" must be \"ping\", \"connection\" or \"query\"\n"));
-		}
-	}
-	else if (strcmp(name, "primary_visibility_consensus") == 0)
-		options->primary_visibility_consensus = parse_bool(value, name, error_list);
-	else if (strcmp(name, "failover_validation_command") == 0)
-		strncpy(options->failover_validation_command, value, sizeof(options->failover_validation_command));
-	else if (strcmp(name, "election_rerun_interval") == 0)
-		options->election_rerun_interval = repmgr_atoi(value, name, error_list, 0);
-	else if (strcmp(name, "child_nodes_check_interval") == 0)
-		options->child_nodes_check_interval = repmgr_atoi(value, name, error_list, 1);
-	else if (strcmp(name, "child_nodes_disconnect_command") == 0)
-		snprintf(options->child_nodes_disconnect_command, sizeof(options->child_nodes_disconnect_command), "%s", value);
-	else if (strcmp(name, "child_nodes_disconnect_min_count") == 0)
-		options->child_nodes_disconnect_min_count = repmgr_atoi(value, name, error_list, -1);
-	else if (strcmp(name, "child_nodes_connected_min_count") == 0)
-		options->child_nodes_connected_min_count = repmgr_atoi(value, name, error_list, -1);
-	else if (strcmp(name, "child_nodes_connected_include_witness") == 0)
-		options->child_nodes_connected_include_witness = parse_bool(value, name, error_list);
-	else if (strcmp(name, "child_nodes_disconnect_timeout") == 0)
-		options->child_nodes_disconnect_timeout = repmgr_atoi(value, name, error_list, 0);
-
-	/* witness settings */
-	else if (strcmp(name, "witness_sync_interval") == 0)
-		options->witness_sync_interval = repmgr_atoi(value, name, error_list, 1);
-
-	/* service settings */
-	else if (strcmp(name, "pg_ctl_options") == 0)
-		strncpy(options->pg_ctl_options, value, sizeof(options->pg_ctl_options));
-	else if (strcmp(name, "service_start_command") == 0)
-		strncpy(options->service_start_command, value, sizeof(options->service_start_command));
-	else if (strcmp(name, "service_stop_command") == 0)
-		strncpy(options->service_stop_command, value, sizeof(options->service_stop_command));
-	else if (strcmp(name, "service_restart_command") == 0)
-		strncpy(options->service_restart_command, value, sizeof(options->service_restart_command));
-	else if (strcmp(name, "service_reload_command") == 0)
-		strncpy(options->service_reload_command, value, sizeof(options->service_reload_command));
-	else if (strcmp(name, "service_promote_command") == 0)
-		strncpy(options->service_promote_command, value, sizeof(options->service_promote_command));
-
-	/* repmgrd service settings */
-	else if (strcmp(name, "repmgrd_service_start_command") == 0)
-		strncpy(options->repmgrd_service_start_command, value, sizeof(options->repmgrd_service_start_command));
-	else if (strcmp(name, "repmgrd_service_stop_command") == 0)
-		strncpy(options->repmgrd_service_stop_command, value, sizeof(options->repmgrd_service_stop_command));
-
-
-	/* event notification settings */
-	else if (strcmp(name, "event_notification_command") == 0)
-		strncpy(options->event_notification_command, value, sizeof(options->event_notification_command));
-	else if (strcmp(name, "event_notifications") == 0)
-	{
-		/* store unparsed value for comparison when reloading config */
-		strncpy(options->event_notifications_orig, value, sizeof(options->event_notifications_orig));
-		parse_event_notifications_list(options, value);
-	}
-
-	/* barman settings */
-	else if (strcmp(name, "barman_host") == 0)
-		strncpy(options->barman_host, value, sizeof(options->barman_host));
-	else if (strcmp(name, "barman_server") == 0)
-		strncpy(options->barman_server, value, sizeof(options->barman_server));
-	else if (strcmp(name, "barman_config") == 0)
-		strncpy(options->barman_config, value, sizeof(options->barman_config));
-
-	/* rsync/ssh settings */
-	else if (strcmp(name, "rsync_options") == 0)
-		strncpy(options->rsync_options, value, sizeof(options->rsync_options));
-	else if (strcmp(name, "ssh_options") == 0)
-		strncpy(options->ssh_options, value, sizeof(options->ssh_options));
-
-	/* undocumented settings for testing */
-	else if (strcmp(name, "promote_delay") == 0)
-		options->promote_delay = repmgr_atoi(value, name, error_list, 1);
-
-	/*
-	 * Following parameters have been deprecated or renamed from 3.x -
-	 * issue a warning
-	 */
-	else if (strcmp(name, "cluster") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"cluster\" is deprecated and will be ignored"));
-	}
-	else if (strcmp(name, "node") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"node\" has been renamed to \"node_id\""));
-	}
-	else if (strcmp(name, "upstream_node") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"upstream_node\" has been removed; use \"--upstream-node-id\" when cloning a standby"));
-	}
-	else if (strcmp(name, "loglevel") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"loglevel\" has been renamed to \"log_level\""));
-	}
-	else if (strcmp(name, "logfacility") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"logfacility\" has been renamed to \"log_facility\""));
-	}
-	else if (strcmp(name, "logfile") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"logfile\" has been renamed to \"log_file\""));
-	}
-	else if (strcmp(name, "master_reponse_timeout") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"master_reponse_timeout\" has been removed; use \"async_query_timeout\" instead"));
-	}
-	else if (strcmp(name, "retry_promote_interval_secs") == 0)
-	{
-		item_list_append(warning_list,
-						 _("parameter \"retry_promote_interval_secs\" has been removed; use \"primary_notification_timeout\" instead"));
-	}
-	else
-	{
-		log_warning(_("%s/%s: unknown name/value pair provided; ignoring"), name, value);
-	}
-
-}
 
 
 bool
@@ -1069,6 +1122,8 @@ parse_time_unit_parameter(const char *name, const char *value, char *dest, ItemL
  * with these):
  *
  * - async_query_timeout
+ * - bdr_local_monitoring_only
+ * - bdr_recovery_timeout
  * - child_nodes_check_interval
  * - child_nodes_connected_min_count
  * - child_nodes_connected_include_witness
@@ -1135,8 +1190,7 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	_parse_config(&new_options, &config_errors, &config_warnings);
 
 
-	if (new_options.failover == FAILOVER_AUTOMATIC
-		&& (server_type == PRIMARY || server_type == STANDBY))
+	if (server_type == PRIMARY || server_type == STANDBY)
 	{
 		if (new_options.promote_command[0] == '\0')
 		{
@@ -1205,6 +1259,24 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 		config_changed = true;
 	}
 
+	/* bdr_local_monitoring_only */
+	if (orig_options->bdr_local_monitoring_only != new_options.bdr_local_monitoring_only)
+	{
+		orig_options->bdr_local_monitoring_only = new_options.bdr_local_monitoring_only;
+		log_info(_("\"bdr_local_monitoring_only\" is now \"%s\""), new_options.bdr_local_monitoring_only == true ? "TRUE" : "FALSE");
+
+		config_changed = true;
+	}
+
+	/* bdr_recovery_timeout */
+	if (orig_options->bdr_recovery_timeout != new_options.bdr_recovery_timeout)
+	{
+		orig_options->bdr_recovery_timeout = new_options.bdr_recovery_timeout;
+		log_info(_("\"bdr_recovery_timeout\" is now \"%i\""), new_options.bdr_recovery_timeout);
+
+		config_changed = true;
+	}
+
 	/* child_nodes_check_interval */
 	if (orig_options->child_nodes_check_interval != new_options.child_nodes_check_interval)
 	{
@@ -1744,7 +1816,6 @@ parse_bool(const char *s, const char *config_item, ItemList *error_list)
 	return false;
 }
 
-
 /*
  * Split argument into old_dir and new_dir and append to tablespace mapping
  * list.
@@ -1812,126 +1883,6 @@ tablespace_list_append(t_configuration_options *options, const char *arg)
 }
 
 
-bool
-modify_auto_conf(const char *data_dir, KeyValueList *items)
-{
-	PQExpBufferData auto_conf;
-	PQExpBufferData auto_conf_tmp;
-	PQExpBufferData auto_conf_contents;
-
-	FILE	   *fp;
-	mode_t		um;
-	struct stat auto_conf_st;
-
-	KeyValueList config = {NULL, NULL};
-	KeyValueListCell *cell = NULL;
-
-	bool	   success = true;
-
-	initPQExpBuffer(&auto_conf);
-	appendPQExpBuffer(&auto_conf, "%s/%s",
-					  data_dir, PG_AUTOCONF_FILENAME);
-
-	fp = fopen(auto_conf.data, "r");
-
-	if (fp == NULL)
-	{
-		fprintf(stderr, "unable to open \"%s\": %s\n",
-				auto_conf.data,
-				strerror(errno));
-		termPQExpBuffer(&auto_conf);
-		return false;
-	}
-
-	// XXX check return value
-	(void) ProcessPostgresConfigFile(fp, auto_conf.data, &config, NULL, NULL);
-	fclose(fp);
-
-	/*
-	 * Append requested items to items extracted from the existing file.
-	 */
-	for (cell = items->head; cell; cell = cell->next)
-	{
-		key_value_list_replace_or_set(&config,
-									  cell->key,
-									  cell->value);
-
-	}
-
-	initPQExpBuffer(&auto_conf_tmp);
-	appendPQExpBuffer(&auto_conf_tmp, "%s.tmp",
-					  auto_conf.data);
-
-	initPQExpBuffer(&auto_conf_contents);
-
-	/*
-	 * Keep this in sync with src/backend/utils/misc/guc.c:write_auto_conf_file()
-	 */
-	appendPQExpBufferStr(&auto_conf_contents,
-						 "# Do not edit this file manually!\n"
-						 "# It will be overwritten by the ALTER SYSTEM command.\n");
-
-	for (cell = config.head; cell; cell = cell->next)
-	{
-		appendPQExpBuffer(&auto_conf_contents,
-						  "%s = '%s'\n",
-						  cell->key, cell->value);
-	}
-
-	stat(auto_conf.data, &auto_conf_st);
-
-	/*
-	 * Set umask so the temporary file is created in the same mode as the original
-	 * postgresql.auto.conf file.
-	 */
-	um = umask(~(auto_conf_st.st_mode));
-	fp = fopen(auto_conf_tmp.data, "w");
-	umask(um);
-
-	if (fp == NULL)
-	{
-		fprintf(stderr, "unable to open \"%s\": %s\n",
-				auto_conf_tmp.data,
-				strerror(errno));
-	}
-	else
-	{
-		if (fwrite(auto_conf_contents.data, strlen(auto_conf_contents.data), 1, fp) != 1)
-		{
-			fclose(fp);
-		}
-		else
-		{
-			fclose(fp);
-
-			/*
-			 * Note: durable_rename() is not exposed to frontend code before Pg 10.
-			 * We only really need to be modifying postgresql.auto.conf from Pg 12,
-			 * but provide backwards compatibitilty for Pg 9.6 and earlier for the
-			 * (unlikely) event that a repmgr built against one of those versions
-			 * is being used against Pg 12 and later.
-			 */
-			// XXX check return values
-#if (PG_ACTUAL_VERSION_NUM >= 100000)
-			(void) durable_rename(auto_conf_tmp.data, auto_conf.data, LOG);
-#else
-			if (rename(auto_conf_tmp.data, auto_conf.data) < 0)
-			{
-				success = false;
-			}
-#endif
-		}
-	}
-
-	termPQExpBuffer(&auto_conf);
-	termPQExpBuffer(&auto_conf_tmp);
-	termPQExpBuffer(&auto_conf_contents);
-
-	key_value_list_free(&config);
-
-	return success;
-}
-
 
 /*
  * parse_event_notifications_list()
@@ -2108,6 +2059,9 @@ free_parsed_argv(char ***argv_array)
 }
 
 
+
+
+
 bool
 parse_pg_basebackup_options(const char *pg_basebackup_options, t_basebackup_options *backup_options, int server_version_num, ItemList *error_list)
 {

configfile.h

@@ -1,7 +1,7 @@
 /*
  * configfile.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -28,12 +28,6 @@
 /* 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];
 
@@ -161,6 +155,10 @@ 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];
@@ -189,7 +187,6 @@ typedef struct
 
 	/* undocumented test settings */
 	int			promote_delay;
-	int			failover_delay;
 } t_configuration_options;
 
 /*
@@ -235,6 +232,8 @@ typedef struct
 		DEFAULT_CHILD_NODES_CONNECTED_MIN_COUNT, \
 		DEFAULT_CHILD_NODES_CONNECTED_INCLUDE_WITNESS, \
 		DEFAULT_CHILD_NODES_DISCONNECT_TIMEOUT, "", \
+		/* BDR settings */ \
+		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
 		"", "", "", "", "", "", \
 		/* repmgrd service settings */ \
@@ -244,9 +243,8 @@ typedef struct
 		/* barman settings */ \
 		"", "", "",	 \
 		/* rsync/ssh settings */ \
-		"", "", \
+		 "", "", \
 		/* undocumented test settings */ \
-		0, \
 		0 \
  }
 
@@ -319,8 +317,6 @@ const char *progname(void);
 void		load_config(const char *config_file, bool verbose, bool terse, t_configuration_options *options, char *argv0);
 bool		reload_config(t_configuration_options *orig_options, t_server_type server_type);
 
-void		parse_configuration_item(t_configuration_options *options, ItemList *error_list, ItemList *warning_list, const char *name, const char *value);
-
 bool		parse_recovery_conf(const char *data_dir, t_recovery_conf *conf);
 
 bool		parse_bool(const char *s,
@@ -346,10 +342,4 @@ void		exit_with_cli_errors(ItemList *error_list, const char *repmgr_command);
 void		print_item_list(ItemList *item_list);
 const char *print_connection_check_type(ConnectionCheckType type);
 
-extern bool modify_auto_conf(const char *data_dir, KeyValueList *items);
-
-extern bool ProcessRepmgrConfigFile(FILE *fp, const char *config_file, t_configuration_options *options, ItemList *error_list, ItemList *warning_list);
-
-extern bool ProcessPostgresConfigFile(FILE *fp, const char *config_file, KeyValueList *contents, ItemList *error_list, ItemList *warning_list);
-
 #endif							/* _REPMGR_CONFIGFILE_H_ */

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 5.1.0.
+# Generated by GNU Autoconf 2.69 for repmgr 4.4.
 #
 # Report bugs to <repmgr@googlegroups.com>.
 #
@@ -11,7 +11,7 @@
 # This configure script is free software; the Free Software Foundation
 # gives unlimited permission to copy, distribute and modify it.
 #
-# Copyright (c) 2010-2020, 2ndQuadrant Ltd.
+# Copyright (c) 2010-2019, 2ndQuadrant Ltd.
 ## -------------------- ##
 ## M4sh Initialization. ##
 ## -------------------- ##
@@ -582,16 +582,13 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='5.1.0'
-PACKAGE_STRING='repmgr 5.1.0'
+PACKAGE_VERSION='4.4'
+PACKAGE_STRING='repmgr 4.4'
 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
@@ -1181,7 +1178,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures repmgr 5.1.0 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.4 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1242,7 +1239,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 5.1.0:";;
+     short | recursive ) echo "Configuration of repmgr 4.4:";;
    esac
   cat <<\_ACEOF
 
@@ -1316,14 +1313,14 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 5.1.0
+repmgr configure 4.4
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
 This configure script is free software; the Free Software Foundation
 gives unlimited permission to copy, distribute and modify it.
 
-Copyright (c) 2010-2020, 2ndQuadrant Ltd.
+Copyright (c) 2010-2019, 2ndQuadrant Ltd.
 _ACEOF
   exit
 fi
@@ -1335,7 +1332,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by repmgr $as_me 5.1.0, which was
+It was created by repmgr $as_me 4.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1850,133 +1847,6 @@ 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="$ac_config_files Makefile.global"
@@ -2487,7 +2357,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by repmgr $as_me 5.1.0, which was
+This file was extended by repmgr $as_me 4.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2550,7 +2420,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-repmgr config.status 5.1.0
+repmgr config.status 4.4
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,6 +1,6 @@
-AC_INIT([repmgr], [5.1.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [4.4], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
-AC_COPYRIGHT([Copyright (c) 2010-2020, 2ndQuadrant Ltd.])
+AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
 
 AC_CONFIG_HEADER(config.h)
 
@@ -57,22 +57,6 @@ 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

@@ -73,16 +73,7 @@ while(<$fh>) {
         if ($param eq 'data_directory') {
             $data_directory_found = 1;
         }
-
-        # Don't quote numbers
-        if ($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);
-        }
+        push @outp, $line;
     }
 }
 
@@ -92,6 +83,6 @@ print join("\n", @outp);
 print "\n";
 
 if ($data_directory_found == 0) {
-    print "data_directory=''\n";
+    print "data_directory=\n";
 }
 

controldata.c

@@ -6,7 +6,7 @@
  * running. For that reason we can't use on the pg_control_*() functions
  * provided in PostgreSQL 9.6 and later.
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -312,7 +312,6 @@ 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;
@@ -321,10 +320,6 @@ 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\n");
-		exit(ERR_BAD_CONFIG);
-#endif
 	}
 	else if (version_num >= 110000)
 	{

controldata.h

@@ -1,6 +1,6 @@
 /*
  * controldata.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
@@ -12,7 +12,6 @@
 #include "postgres_fe.h"
 #include "catalog/pg_control.h"
 
-
 #define MAX_VERSION_STRING 24
 /*
  * A simplified representation of pg_control containing only those fields
@@ -56,7 +55,7 @@ typedef struct CheckPoint93
 } CheckPoint93;
 
 
-/* Same for 9.5, 9.6, 10, 11 */
+/* Same for 9.5, 9.6, 10, HEAD */
 typedef struct CheckPoint95
 {
 	XLogRecPtr	redo;			/* next RecPtr available when we began to
@@ -84,50 +83,6 @@ typedef struct CheckPoint95
 } CheckPoint95;
 
 
-#if PG_ACTUAL_VERSION_NUM >= 120000
-/*
- * Following fields removed in PostgreSQL 12;
- *
- *   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 ControlFileData93
 {
 	uint64		system_identifier;
@@ -378,11 +333,19 @@ 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
@@ -396,7 +359,7 @@ typedef struct ControlFileData12
 	pg_time_t	time;			/* time stamp of last pg_control update */
 	XLogRecPtr	checkPoint;		/* last check point record ptr */
 
-	CheckPoint12	checkPointCopy; /* copy of last check point record */
+	CheckPoint	checkPointCopy; /* copy of last check point record */
 
 	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
 
@@ -435,7 +398,6 @@ 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);

dbutils.h

@@ -1,7 +1,7 @@
 /*
  * dbutils.h
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -60,6 +60,11 @@
 	"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
@@ -67,7 +72,8 @@ typedef enum
 	UNKNOWN = 0,
 	PRIMARY,
 	STANDBY,
-	WITNESS
+	WITNESS,
+	BDR
 } t_server_type;
 
 typedef enum
@@ -119,21 +125,14 @@ typedef enum
 
 typedef enum
 {
-	/* unable to query "pg_stat_replication" or other error */
 	NODE_ATTACHED_UNKNOWN = -1,
-	/* node has record in "pg_stat_replication" and state is not "streaming" */
-	NODE_ATTACHED,
-	/* node has record in "pg_stat_replication" but state is not "streaming" */
-	NODE_NOT_ATTACHED,
-	/* node has no record in "pg_stat_replication" */
-	NODE_DETACHED
+	NODE_DETACHED,
+	NODE_ATTACHED
 } NodeAttached;
 
 typedef enum
 {
 	SLOT_UNKNOWN = -1,
-	SLOT_NOT_FOUND,
-	SLOT_NOT_PHYSICAL,
 	SLOT_INACTIVE,
 	SLOT_ACTIVE
 } ReplSlotStatus;
@@ -171,7 +170,6 @@ 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];
@@ -326,6 +324,45 @@ 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];
@@ -335,7 +372,6 @@ typedef struct
 
 #define T_CONFIGFILE_INFO_INITIALIZER { "", "", false }
 
-
 typedef struct
 {
 	int			size;
@@ -345,7 +381,6 @@ typedef struct
 
 #define T_CONFIGFILE_LIST_INITIALIZER { 0, 0, NULL }
 
-
 typedef struct
 {
 	uint64		system_identifier;
@@ -385,6 +420,10 @@ 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 */
@@ -393,19 +432,12 @@ 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 */
@@ -434,7 +466,6 @@ 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);
@@ -450,12 +481,6 @@ bool		identify_system(PGconn *repl_conn, t_system_identification *identification
 uint64		system_identifier(PGconn *conn);
 TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
 
-/* user/role information functions */
-bool		can_execute_pg_promote(PGconn *conn);
-bool		connection_has_pg_settings(PGconn *conn);
-bool		is_replication_role(PGconn *conn, char *rolname);
-bool		is_superuser_connection(PGconn *conn, t_connection_user *userinfo);
-
 /* repmgrd shared memory functions */
 bool		repmgrd_set_local_node_id(PGconn *conn, int local_node_id);
 int			repmgrd_get_local_node_id(PGconn *conn);
@@ -533,14 +558,10 @@ 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_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);
-
+bool		create_replication_slot(PGconn *conn, char *slot_name, PQExpBufferData *error_msg);
+bool		drop_replication_slot(PGconn *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 *max_replication_slots);
+int			get_free_replication_slot_count(PGconn *conn);
 int			get_inactive_replication_slots(PGconn *conn, KeyValueList *list);
 
 /* tablespace functions */
@@ -592,14 +613,35 @@ 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, char *timeline_id_str);
+TimeLineID	get_node_timeline(PGconn *conn);
 void		get_node_replication_stats(PGconn *conn, t_node_info *node_info);
-NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name, char **node_state);
+NodeAttached is_downstream_node_attached(PGconn *conn, char *node_name);
 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, 2010-2020
+ * 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

dirutil.h

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

doc/Makefile

@@ -31,7 +31,6 @@ 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)\">"; \
 	} > $@
 
 ##
@@ -95,7 +94,6 @@ clean:
 	rm -f repmgr.html
 	rm -f repmgr-A4.pdf
 	rm -f repmgr-US.pdf
-	rm -f html/*
 
 maintainer-clean:
 	rm -rf html

doc/appendix-faq.xml

@@ -3,464 +3,437 @@
   <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">
-    <title>General</title>
+ <sect1 id="faq-general" xreflabel="General">
+  <title>General</title>
 
-    <sect2 id="faq-xrepmgr-version-diff" xreflabel="Version differences">
-      <title>What's the difference between the repmgr versions?</title>
-      <para>
-        &repmgr; 4 is a complete rewrite of the previous &repmgr; code base
-        and implements &repmgr; as a PostgreSQL extension. It
-        supports all PostgreSQL versions from 9.3 (although some &repmgr;
-        features are not available for PostgreSQL 9.3 and 9.4).
-      </para>
-      <note>
-        <para>
-          &repmgr; 5 is fundamentally the same code base as &repmgr; 4, but provides
-          support for the revised replication configuration mechanism in PostgreSQL 12.
-        </para>
-      </note>
-      <para>
-        &repmgr; 3.x builds on the improved replication facilities added
-        in PostgreSQL 9.3, as well as improved automated failover support
-        via &repmgrd;, and is not compatible with PostgreSQL 9.2
-        and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
-        series is no longer maintained.
-      </para>
-      <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-xrepmgr-version-diff" xreflabel="Version differences">
+    <title>What's the difference between the repmgr versions?</title>
+    <para>
+      &repmgr; 4 is a complete rewrite of the existing &repmgr; code base
+      and implements &repmgr; as a PostgreSQL extension. It
+      supports all PostgreSQL versions from 9.3 (although some &repmgr;
+      features are not available for PostgreSQL 9.3 and 9.4).
+     </para>
+     <para>
+      &repmgr; 3.x builds on the improved replication facilities added
+      in PostgreSQL 9.3, as well as improved automated failover support
+      via &repmgrd;, and is not compatible with PostgreSQL 9.2
+      and earlier. We recommend upgrading to &repmgr; 4, as the &repmgr; 3.x
+      series is no longer maintained.
+     </para>
+     <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">
-      <title>What's the advantage of using replication slots?</title>
-      <para>
-        Replication slots, introduced in PostgreSQL 9.4, ensure that the
-        primary server will retain WAL files until they have been consumed
-        by all standby servers. This means standby servers should never
-        fail due to not being able to retrieve required WAL files from the
-        primary.
-      </para>
-      <para>
-        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
-        to be retained indefinitely, and eventually lead to disk space
-        exhaustion.
-      </para>
+  <sect2 id="faq-replication-slots-advantage" xreflabel="Advantages of replication slots">
+   <title>What's the advantage of using replication slots?</title>
+   <para>
+    Replication slots, introduced in PostgreSQL 9.4, ensure that the
+    primary server will retain WAL files until they have been consumed
+    by all standby servers. This means standby servers should never
+    fail due to not being able to retrieve required WAL files from the
+    primary.
+   </para>
+   <para>
+    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
+    to be retained indefinitely, and eventually lead to disk space
+    exhaustion.
+   </para>
 
-      <tip>
-        <para>
-          2ndQuadrant's recommended configuration is to configure
-          <ulink url="https://www.pgbarman.org/">Barman</ulink> as a fallback
-          source of WAL files, rather than maintain replication slots for
-          each standby. See also: <link linkend="cloning-from-barman-restore-command">Using Barman as a WAL file source</link>.
-        </para>
-      </tip>
-    </sect2>
+   <tip>
+     <para>
+       2ndQuadrant's recommended configuration is to configure
+       <ulink url="https://www.pgbarman.org/">Barman</ulink> as a fallback
+       source of WAL files, rather than maintain replication slots for
+       each standby. See also: <link linkend="cloning-from-barman-restore-command">Using Barman as a WAL file source</link>.
+     </para>
+   </tip>
+  </sect2>
 
-    <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>
-      <para>
-        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
-        restart to take effect, and as there is no particular penalty for unused
-        replication slots, setting a higher figure will make adding new nodes
-        easier.
-      </para>
-    </sect2>
+  <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>
+   <para>
+    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
+    restart to take effect, and as there is no particular penalty for unused
+    replication slots, setting a higher figure will make adding new nodes
+    easier.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-hash-index" xreflabel="Hash indexes">
-      <title>Does &repmgr; support hash indexes?</title>
-      <para>
-        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
-        <ulink url="https://www.postgresql.org/docs/9.6/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
-        for details.
-      </para>
-      <para>
-        From PostgreSQL 10, this restriction has been lifted and hash indexes can be used
-        in a streaming replication cluster.
-      </para>
-    </sect2>
+  <sect2 id="faq-hash-index" xreflabel="Hash indexes">
+   <title>Does &repmgr; support hash indexes?</title>
+   <para>
+    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
+    <ulink url="https://www.postgresql.org/docs/9.6/sql-createindex.html#AEN80279">PostgreSQL documentation</ulink>
+    for details.
+   </para>
+   <para>
+    From PostgreSQL 10, this restriction has been lifted and hash indexes can be used
+    in a streaming replication cluster.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-upgrades" xreflabel="Upgrading PostgreSQL with repmgr">
-      <title>Can &repmgr; assist with upgrading a PostgreSQL cluster?</title>
-      <para>
-        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
-        <link linkend="performing-switchover">switchover</link> promoting it to a primary,
-        then upgrade the former primary.
-      </para>
-      <para>
-        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
-        node with <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade</ulink>
-        and recloning standbys from this.
-      </para>
-      <para>
-        To minimize downtime during major upgrades from PostgreSQL 9.4 and later,
-        <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,
-        which can be kept in sync with the existing production cluster until the
-        new cluster is ready to be put into production.
-      </para>
-    </sect2>
+  <sect2 id="faq-upgrades" xreflabel="Upgrading PostgreSQL with repmgr">
+   <title>Can &repmgr; assist with upgrading a PostgreSQL cluster?</title>
+   <para>
+     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
+     <link linkend="performing-switchover">switchover</link> promoting it to a primary,
+     then upgrade the former primary.
+   </para>
+   <para>
+     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
+     node with <ulink url="https://www.postgresql.org/docs/current/pgupgrade.html">pg_upgrade</ulink>
+     and recloning standbys from this.
+   </para>
+   <para>
+     To minimize downtime during major upgrades from PostgreSQL 9.4 and later,
+     <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,
+     which can be kept in sync with the existing production cluster until the
+     new cluster is ready to be put into production.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-libdir-repmgr-error">
-      <title>What does this error mean: <literal>ERROR: could not access file "$libdir/repmgr"</literal>?</title>
-      <para>
-        It means the &repmgr; extension code is not installed in the
-        PostgreSQL application directory. This typically happens when using PostgreSQL
-        packages provided by a third-party vendor, which often have different
-        filesystem layouts.
-      </para>
-      <para>
-        Either use PostgreSQL packages provided by the community or 2ndQuadrant; if this
-        is not possible, contact your vendor for assistance.
-      </para>
-    </sect2>
+  <sect2 id="faq-libdir-repmgr-error">
+   <title>What does this error mean: <literal>ERROR: could not access file "$libdir/repmgr"</literal>?</title>
+   <para>
+     It means the &repmgr; extension code is not installed in the
+     PostgreSQL application directory. This typically happens when using PostgreSQL
+     packages provided by a third-party vendor, which often have different
+     filesystem layouts.
+   </para>
+   <para>
+     Either use PostgreSQL packages provided by the community or 2ndQuadrant; if this
+     is not possible, contact your vendor for assistance.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-old-packages">
-      <title>How can I obtain old versions of &repmgr; packages?</title>
-      <para>
-        See appendix <xref linkend="packages-old-versions"/> for details.
-      </para>
-    </sect2>
+  <sect2 id="faq-old-packages">
+   <title>How can I obtain old versions of &repmgr; packages?</title>
+   <para>
+     See appendix <xref linkend="packages-old-versions"/> for details.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-required-for-replication">
-      <title>Is &repmgr; required for streaming replication?</title>
-      <para>
-        No.
-      </para>
-      <para>
-        &repmgr; (together with &repmgrd;) assists with
-        <emphasis>managing</emphasis> replication. It does not actually perform replication, which
-        is part of the core PostgreSQL functionality.
-      </para>
-    </sect2>
+  <sect2 id="faq-repmgr-required-for-replication">
+    <title>Is &repmgr; required for streaming replication?</title>
+    <para>
+      No.
+    </para>
+    <para>
+     &repmgr; (together with &repmgrd;) assists with
+     <emphasis>managing</emphasis> replication. It does not actually perform replication, which
+     is part of the core PostgreSQL functionality.
+    </para>
+  </sect2>
 
-    <sect2 id="faq-what-if-repmgr-uninstalled">
-      <title>Will replication stop working if &repmgr; is uninstalled?</title>
-      <para>
-        No. See preceding question.
-      </para>
-    </sect2>
+  <sect2 id="faq-what-if-repmgr-uninstalled">
+   <title>Will replication stop working if &repmgr; is uninstalled?</title>
+   <para>
+     No. See preceding question.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-version-mix">
-      <title>Does it matter if different &repmgr; versions are present in the replication cluster?</title>
-      <para>
-        Yes. If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x) are present,
-        &repmgr; (in particular &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
-        your replication cluster.
-      </para>
-      <para>
-        If different &quot;minor&quot; &repmgr; versions (e.g. 4.1.1 and 4.1.6) are installed,
-        &repmgr; will function, but we strongly recommend always running the same version
-        to ensure there are no unexpected suprises, e.g. a newer version behaving slightly
-        differently to the older version.
-      </para>
-      <para>
-        See also <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
-      </para>
-    </sect2>
+  <sect2 id="faq-version-mix">
+   <title>Does it matter if different &repmgr; versions are present in the replication cluster?</title>
+   <para>
+     Yes. If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.x) are present,
+     &repmgr; (in particular &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
+     your replication cluster.
+   </para>
+   <para>
+     If different &quot;minor&quot; &repmgr; versions (e.g. 4.1.1 and 4.1.6) are installed,
+     &repmgr; will function, but we strongly recommend always running the same version
+     to ensure there are no unexpected suprises, e.g. a newer version behaving slightly
+     differently to the older version.
+   </para>
+   <para>
+     See also <link linkend="faq-upgrade-repmgr">Should I upgrade &repmgr;?</link>.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-upgrade-repmgr">
-      <title>Should I upgrade &repmgr;?</title>
-      <para>
-        Yes.
-      </para>
-      <para>
-        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
-        costing you more effort. The same applies to PostgreSQL itself.
-      </para>
-    </sect2>
+  <sect2 id="faq-upgrade-repmgr">
+    <title>Should I upgrade &repmgr;?</title>
+    <para>
+      Yes.
+    </para>
+    <para>
+      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
+      costing you more effort. The same applies to PostgreSQL itself.
+    </para>
 
-    <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>
 
-    <sect2 id="faq-third-party-packages" xreflabel="Compatability with third party vendor packages">
-      <title>Are &repmgr; packages compatible with <literal>$third_party_vendor</literal>'s packages?</title>
-      <para>
-        &repmgr; packages provided by 2ndQuadrant are compatible with the community-provided PostgreSQL
-        packages and any software provided by 2ndQuadrant.
-      </para>
-      <para>
-        A number of other vendors provide their own versions of PostgreSQL packages, often with different
-        package naming schemes and/or file locations.
-      </para>
-      <para>
-        We cannot guarantee that &repmgr; packages will be compatible with these packages.
-        It may be possible to override package dependencies (e.g. <literal>rpm --nodeps</literal>
-        for CentOS-based systems or <literal>dpkg --force-depends</literal> for Debian-based systems).
-      </para>
-    </sect2>
-  </sect1>
+  <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. (In PostgreSQL 10 and later, non-superusers can be added to the
+      group <option>pg_read_all_settings</option> which will enable them to read this setting).
+    </para>
+  </sect2>
+ </sect1>
 
-  <sect1 id="faq-repmgr" xreflabel="repmgr">
-    <title><command>repmgr</command></title>
+ <sect1 id="faq-repmgr" xreflabel="repmgr">
+  <title><command>repmgr</command></title>
 
-    <sect2 id="faq-register-existing-node" xreflabel="registering an existing node">
-      <title>Can I register an existing PostgreSQL server with repmgr?</title>
-      <para>
-        Yes, any existing PostgreSQL server which is part of the same replication
-        cluster can be registered with &repmgr;. There's no requirement for a
-        standby to have been cloned using &repmgr;.
-      </para>
-    </sect2>
+  <sect2 id="faq-register-existing-node" xreflabel="registering an existing node">
+   <title>Can I register an existing PostgreSQL server with repmgr?</title>
+   <para>
+    Yes, any existing PostgreSQL server which is part of the same replication
+    cluster can be registered with &repmgr;. There's no requirement for a
+    standby to have been cloned using &repmgr;.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-clone-other-source" >
-      <title>Can I use a standby not cloned by &repmgr; as a &repmgr; node?</title>
+  <sect2 id="faq-repmgr-clone-other-source" >
+   <title>Can I use a standby not cloned by &repmgr; as a &repmgr; node?</title>
 
-      <para>
-        For a standby which has been manually cloned or recovered from an external
-        backup manager such as Barman, the command
-        <command><link linkend="repmgr-standby-clone">repmgr standby clone --replication-conf-only</link></command>
-        can be used to create the correct <filename>recovery.conf</filename> file for
-        use with &repmgr; (and will create a replication slot if required). Once this has been done,
-        <link linkend="repmgr-standby-register">register the node</link> as usual.
-      </para>
-    </sect2>
+   <para>
+     For a standby which has been manually cloned or recovered from an external
+     backup manager such as Barman, the command
+     <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>
+     can be used to create the correct <filename>recovery.conf</filename> file for
+     use with &repmgr; (and will create a replication slot if required). Once this has been done,
+     <link linkend="repmgr-standby-register">register the node</link> as usual.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-recovery-conf" >
-      <title>What does &repmgr; write in <filename>recovery.conf</filename>, and what options can be set there?</title>
-      <para>
-        See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
-      </para>
-    </sect2>
+  <sect2 id="faq-repmgr-recovery-conf" >
+    <title>What does &repmgr; write in <filename>recovery.conf</filename>, and what options can be set there?</title>
+   <para>
+     See section <link linkend="repmgr-standby-clone-recovery-conf">Customising recovery.conf</link>.
+   </para>
+  </sect2>
 
-    <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>
-      <para>
-        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
-        needs to be re-registered as a standby.
-      </para>
-      <para>
-        It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
-        directory, which will usually be much
-        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
-        data checksums were enabled when the cluster was initialized.
-      </para>
-      <para>
-        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.
-      </para>
-      <para>
-        &repmgr; provides the command <command>repmgr node rejoin</command> which can
-        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"/>.
-      </para>
-      <para>
-        If <command>pg_rewind</command> cannot be used, then the data directory will need
-        to be re-cloned from scratch.
-      </para>
+  <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>
+   <para>
+    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
+    needs to be re-registered as a standby.
+   </para>
+   <para>
+    It's possible to use <command>pg_rewind</command> to re-synchronise the existing data
+    directory, which will usually be much
+    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
+    data checksums were enabled when the cluster was initialized.
+   </para>
+   <para>
+     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.
+   </para>
+   <para>
+    &repmgr; provides the command <command>repmgr node rejoin</command> which can
+    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"/>.
+   </para>
+   <para>
+    If <command>pg_rewind</command> cannot be used, then the data directory will need
+    to be re-cloned from scratch.
+   </para>
 
-    </sect2>
+  </sect2>
 
-    <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>
-      <para>
-        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
-        which need to be rectified.
-      </para>
-    </sect2>
+  <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>
+   <para>
+    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
+    which need to be rectified.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-clone-skip-config-files" xreflabel="">
-      <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
-        directory in <filename>/etc</filename>?</title>
-      <para>
-        Use the command line option <literal>--copy-external-config-files</literal>. For more details
-        see <xref linkend="repmgr-standby-clone-config-file-copying"/>.
-      </para>
-    </sect2>
+  <sect2 id="faq-repmgr-clone-skip-config-files" xreflabel="">
+   <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
+     directory in <filename>/etc</filename>?</title>
+   <para>
+    Use the command line option <literal>--copy-external-config-files</literal>. For more details
+    see <xref linkend="repmgr-standby-clone-config-file-copying"/>.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
-      <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
-        in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
-      <para>
-        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
-        <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
-      </para>
-    </sect2>
+  <sect2 id="faq-repmgr-shared-preload-libaries-no-repmgrd" xreflabel="shared_preload_libraries without repmgrd">
+    <title>Do I need to include <literal>shared_preload_libraries = 'repmgr'</literal>
+      in <filename>postgresql.conf</filename> if I'm not using &repmgrd;?</title>
+   <para>
+    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
+    <literal>shared_preload_libraries = 'repmgr'</literal> and restart PostgreSQL.
+   </para>
+  </sect2>
 
-    <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>
-        but <command>repmgr</command>/&repmgrd; complains it can't connect to the server... Why?</title>
-      <para>
-        <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
-        permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
-      </para>
-    </sect2>
+  <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>
+     but <command>repmgr</command>/&repmgrd; complains it can't connect to the server... Why?</title>
+   <para>
+    <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
+    permission is for PostgreSQL's streaming replication (and doesn't  necessarily need to be the <literal>repmgr</literal> user).
+   </para>
+  </sect2>
 
-    <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
-        for the primary server on the command line, not in the configuration file?</title>
-      <para>
-        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
-        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
-        node, and if necessary scan the replication cluster until it locates the active primary.
-      </para>
-    </sect2>
+  <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
+     for the primary server on the command line, not in the configuration file?</title>
+   <para>
+    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
+    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
+    node, and if necessary scan the replication cluster until it locates the active primary.
+   </para>
+  </sect2>
 
-    <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>
-      <para>
-        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>.
-        For more details see <xref linkend="cloning-advanced-pg-basebackup-options"/>.
-      </para>
-    </sect2>
+  <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>
+   <para>
+     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>.
+     For more details see <xref linkend="cloning-advanced-pg-basebackup-options"/>.
+   </para>
+  </sect2>
 
-    <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>
-        table?</title>
-      <para>
-        Under some circumstances event notifications can be generated for servers
-        which have not yet been registered; it's also useful to retain a record
-        of events which includes servers removed from the replication cluster
-        which no longer have an entry in the <literal>repmgr.nodes</literal> table.
-      </para>
-    </sect2>
+  <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>
+     table?</title>
+   <para>
+     Under some circumstances event notifications can be generated for servers
+     which have not yet been registered; it's also useful to retain a record
+     of events which includes servers removed from the replication cluster
+     which no longer have an entry in the <literal>repmgr.nodes</literal> table.
+   </para>
+  </sect2>
 
-    <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in recovery.conf">
-      <title>Why are some values in <filename>recovery.conf</filename> surrounded by pairs of single quotes?</title>
-      <para>
-        This is to ensure that user-supplied values which are written as parameter values in <filename>recovery.conf</filename>
-        are escaped correctly and do not cause errors when <filename>recovery.conf</filename> is parsed.
-      </para>
-      <para>
-        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,
-        even if the string does not contain any characters which need escaping.
-      </para>
-    </sect2>
+  <sect2 id="faq-repmgr-recovery-conf-quoted-values" xreflabel="Quoted values in recovery.conf">
+    <title>Why are some values in <filename>recovery.conf</filename> surrounded by pairs of single quotes?</title>
+    <para>
+      This is to ensure that user-supplied values which are written as parameter values in <filename>recovery.conf</filename>
+      are escaped correctly and do not cause errors when <filename>recovery.conf</filename> is parsed.
+    </para>
+    <para>
+      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,
+      even if the string does not contain any characters which need escaping.
+    </para>
+  </sect2>
 
 
-  </sect1>
+ </sect1>
 
-  <sect1 id="faq-repmgrd" xreflabel="repmgrd">
-    <title>&repmgrd;</title>
+ <sect1 id="faq-repmgrd" xreflabel="repmgrd">
+  <title>&repmgrd;</title>
 
 
-    <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>
+  <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>
 
-    <sect2 id="faq-repmgrd-delayed-standby" xreflabel="Delayed standby support">
-      <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-delayed-standby" xreflabel="Delayed standby support">
+   <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-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>
+  </sect2>
 
-    <sect2 id="faq-repmgrd-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
-      <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-recloned-no-start" xreflabel="repmgrd not restarting after node cloned">
+   <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-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>
+  <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>
+ </sect1>
 </appendix>

doc/appendix-packages.xml

@@ -122,7 +122,7 @@
 
      <row>
       <entry>Package name example:</entry>
-      <entry><filename>repmgr11-4.4.0-1.rhel7.x86_64</filename></entry>
+      <entry><filename>repmgr10-4.0.4-1.rhel7.x86_64</filename></entry>
      </row>
 
      <row>
@@ -132,12 +132,12 @@
 
      <row>
       <entry>Installation command:</entry>
-      <entry><literal>yum install repmgr11</literal></entry>
+      <entry><literal>yum install repmgr10</literal></entry>
      </row>
 
      <row>
       <entry>Binary location:</entry>
-      <entry><filename>/usr/pgsql-11/bin</filename></entry>
+      <entry><filename>/usr/pgsql-10/bin</filename></entry>
      </row>
 
      <row>
@@ -147,22 +147,22 @@
 
      <row>
       <entry>Configuration file location:</entry>
-      <entry><filename>/etc/repmgr/11/repmgr.conf</filename></entry>
+      <entry><filename>/etc/repmgr/10/repmgr.conf</filename></entry>
      </row>
 
      <row>
       <entry>Data directory:</entry>
-      <entry><filename>/var/lib/pgsql/11/data</filename></entry>
+      <entry><filename>/var/lib/pgsql/10/data</filename></entry>
      </row>
 
      <row>
       <entry>repmgrd service command:</entry>
-      <entry><command>systemctl [start|stop|restart|reload] repmgr11</command></entry>
+      <entry><command>systemctl [start|stop|restart|reload] repmgr10</command></entry>
      </row>
 
      <row>
       <entry>repmgrd service file location:</entry>
-      <entry><filename>/usr/lib/systemd/system/repmgr11.service</filename></entry>
+      <entry><filename>/usr/lib/systemd/system/repmgr10.service</filename></entry>
      </row>
 
      <row>
@@ -253,14 +253,20 @@
     </indexterm>
 
     <para>
-      &repmgr; <literal>.deb</literal> packages are provided by 2ndQuadrant as well as the
+      &repmgr; <literal>.deb</literal> packages are provided via 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 repositories</title>
+      <title>APT repository</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>
@@ -285,7 +291,7 @@
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink></entry>
+              <entry><ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -317,7 +323,7 @@
 
             <row>
               <entry>Package name example:</entry>
-              <entry><filename>postgresql-11-repmgr</filename></entry>
+              <entry><filename>postgresql-10-repmgr</filename></entry>
             </row>
 
             <row>
@@ -327,12 +333,12 @@
 
             <row>
               <entry>Installation command:</entry>
-              <entry><literal>apt-get install postgresql-11-repmgr</literal></entry>
+              <entry><literal>apt-get install postgresql-10-repmgr</literal></entry>
             </row>
 
             <row>
               <entry>Binary location:</entry>
-              <entry><filename>/usr/lib/postgresql/11/bin</filename></entry>
+              <entry><filename>/usr/lib/postgresql/10/bin</filename></entry>
             </row>
 
             <row>
@@ -347,12 +353,12 @@
 
             <row>
               <entry>Data directory:</entry>
-              <entry><filename>/var/lib/postgresql/11/main</filename></entry>
+              <entry><filename>/var/lib/postgresql/10/main</filename></entry>
             </row>
 
             <row>
               <entry>PostgreSQL service command:</entry>
-              <entry><command>systemctl [start|stop|restart|reload] postgresql@11-main</command></entry>
+              <entry><command>systemctl [start|stop|restart|reload] postgresql@10-main</command></entry>
 
             </row>
 
@@ -376,11 +382,11 @@
       </table>
       <note>
         <para>
-          When using Debian packages, instead of using the <application>systemd</application> service
-          command directly,  it's recommended to execute <command>pg_ctlcluster</command>
-          (as <literal>root</literal>, either directly or via <command>sudo</command>), e.g.:
+          Instead of using the <application>systemd</application> service command directly,
+          it's recommended to execute <command>pg_ctlcluster</command> (as <literal>root</literal>,
+          either directly or via <command>sudo</command>), e.g.:
           <programlisting>
-            <command>pg_ctlcluster 11 main [start|stop|restart|reload]</command></programlisting>
+            <command>pg_ctlcluster 10 main [start|stop|restart|reload]</command></programlisting>
         </para>
         <para>
           For pre-<application>systemd</application> systems, <command>pg_ctlcluster</command>
@@ -471,7 +477,7 @@ 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="https://apt-archive.postgresql.org/">https://apt-archive.postgresql.org/</ulink>
+        <ulink url="http://atalia.postgresql.org/morgue/r/repmgr/">http://atalia.postgresql.org/morgue/r/repmgr/</ulink>
       </para>
     </sect2>
 

doc/appendix-support.xml

@@ -43,12 +43,6 @@
 
     <itemizedlist spacing="compact" mark="bullet">
 
-     <listitem>
-      <simpara>
-        PostgreSQL version
-      </simpara>
-     </listitem>
-
      <listitem>
       <simpara>
         &repmgr; version
@@ -74,18 +68,9 @@
       </simpara>
      </listitem>
 
-
      <listitem>
       <simpara>
-        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>.
+        PostgreSQL version
       </simpara>
      </listitem>
 
@@ -105,8 +90,8 @@
     </para>
     <para>
       In all cases it is <emphasis>extremely</emphasis> useful to receive
-      as much detail as possible on how to reliably reproduce
-      an issue.
+      information on how to reliably reproduce an issue with as much detail as
+      possible.
     </para>
 
   </sect1>

doc/bdr-failover.md

@@ -0,0 +1,8 @@
+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

@@ -52,25 +52,6 @@
    </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>
@@ -79,7 +60,8 @@
    <itemizedlist spacing="compact" mark="bullet">
      <listitem>
       <para>
-        the Barman catalogue must include at least one valid backup for this server;
+        the <varname>barman_server</varname> setting in <filename>repmgr.conf</filename> is the same as the
+        server configured in Barman;
       </para>
      </listitem>
      <listitem>
@@ -90,81 +72,19 @@
      </listitem>
      <listitem>
       <para>
-        the <varname>barman_server</varname> setting in <filename>repmgr.conf</filename> is the same as the
-        server configured in Barman.
+        the <varname>restore_command</varname> setting in <filename>repmgr.conf</filename> is configured to
+        use a copy of the <command>barman-wal-restore</command> script shipped with the
+        <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>
-    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>
@@ -174,7 +94,37 @@ description = "Main cluster"
      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>
@@ -192,28 +142,35 @@ description = "Main cluster"
    </para>
    <para>
      <command>barman-wal-restore</command> is a Python script provided as part of the <literal>barman-cli</literal>
-     package (Barman 2.0 ~ 2.7) or as part of the core Barman distribution (Barman 2.8 and later).
+     package (Barman 2.0 and later; for Barman 1.x the script is provided separately as
+     <command>barman-wal-restore.py</command>) which performs this function for Barman.
    </para>
    <para>
-    To use <command>barman-wal-restore</command> with &repmgr;,
-    assuming Barman is located on the host &quot;<literal>barmansrv</literal>&quot;
-    under the &quot;<literal>barman</literal>&quot; user account,
+    To use <command>barman-wal-restore</command> with &repmgr;
+    and assuming Barman is located on the <literal>barmansrv</literal> host
     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='barman@barmansrv'
-    barman_server='pg'
-    restore_command='/usr/bin/barman-wal-restore barmansrv pg %f %p'</programlisting>
+    barman_host=barmansrv
+    barman_server=somedb
+    restore_command=/usr/bin/barman-wal-restore barmansrv somedb %f %p</programlisting>
    </para>
    <note>
     <simpara>
       <command>barman-wal-restore</command> supports command line switches to
-      control parallelism (<literal>--parallel=N</literal>) and compression
-      (<literal>--bzip2</literal>, <literal>--gzip</literal>).
+      control parallelism (<literal>--parallel=N</literal>) and compression (
+      <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>
 
@@ -458,8 +415,10 @@ description = "Main cluster"
 
     <para>
      The recommended way to do this is to store the password in the <literal>postgres</literal> system
-     user's <filename>~/.pgpass</filename> file.  For more information on using the password file, see
-     the documentation section <xref linkend="configuration-password-file"/>.
+     user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
+     environment variable <varname>PGPASSWORD</varname>, however this is not recommended for
+     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>
@@ -481,6 +440,19 @@ description = "Main cluster"
      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">
@@ -496,34 +468,6 @@ description = "Main cluster"
      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

@@ -1,136 +0,0 @@
-<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>
-
-  <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>
-
-  </variablelist>
-</sect1>

doc/configuration-file.xml

@@ -31,8 +31,6 @@
       <secondary>format</secondary>
     </indexterm>
 
-
-
     <para>
       <filename>repmgr.conf</filename> is a plain text file with one parameter/value
       combination per line.
@@ -41,10 +39,14 @@
       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>
-    <para>
-      To embed a single quote in a parameter value, write either two quotes (preferred) or backslash-quote.
-    </para>
+    <important>
+      <para>
+        &repmgr; will interpret double-quotes as being part of a string value; only use single quotes
+        to quote parameter values.
+      </para>
+    </important>
 
     <para>
       Example of a valid <filename>repmgr.conf</filename> file:
@@ -54,32 +56,9 @@
 node_id=1
 node_name= node1
 conninfo ='host=node1 dbname=repmgr user=repmgr connect_timeout=2'
-data_directory = '/var/lib/pgsql/12/data'</programlisting>
+data_directory = /var/lib/pgsql/11/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>
-
   </sect2>
 
 
@@ -182,14 +161,6 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
    </itemizedlist>
   </para>
 
-  <para>
-    In examples provided in this documentation, it is assumed the configuration file is located
-    at <filename>/etc/repmgr.conf</filename>. If &repmgr; is installed from a package, the
-    configuration file will probably be located at another location specified by the packager;
-    see appendix <xref linkend="appendix-packages"/> for configuration file locations in
-    different packaging systems.
-  </para>
-
   <para>
    Note that if a file is explicitly specified with <literal>-f/--config-file</literal>,
    an error will be raised if it is not found or not readable, and no attempt will be made to
@@ -210,61 +181,6 @@ conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlistin
       <filename>/path/to/repmgr.conf</filename>).
     </para>
    </note>
-  </sect2>
-
-  <sect2 id="configuration-file-postgresql-major-upgrades" xreflabel="configuration file and PostgreSQL major version upgrades">
-    <title>Configuration file and PostgreSQL major version upgrades</title>
-
-    <indexterm>
-      <primary>repmgr.conf</primary>
-      <secondary>ostgreSQL major version upgrades</secondary>
-    </indexterm>
-
-    <para>
-      When upgrading the PostgreSQL cluster to a new major version, <filename>repmgr.conf</filename>
-      will probably needed to be updated.
-    </para>
-    <para>
-      Usually <option>pg_bindir</option> and <option>data_directory</option> will need to be modified,
-      particularly if the default package locations are used, as these usually change.
-    </para>
-
-     <para>
-       It's also possible the location of <filename>repmgr.conf</filename> itself will change
-       (e.g. from <filename>/etc/repmgr/11/repmgr.conf</filename> to <filename>/etc/repmgr/12/repmgr.conf</filename>).
-       This is stored as part of the &repmgr; metadata and is used by &repmgr; to execute &repmgr; remotely
-       (e.g. during a <link linkend="performing-switchover">switchover operation</link>).
-     </para>
-     <para>
-       If the content and/or location of <filename>repmgr.conf</filename> has changed, the &repmgr; metadata
-       needs to be updated to reflect this. The &repmgr; metadata can be updated on each node with:
-       <itemizedlist spacing="compact" mark="bullet">
-         <listitem>
-           <simpara>
-             <link linkend="repmgr-primary-register">
-               <command>repmgr primary register --force -f /path/to/repmgr.conf</command>
-             </link>
-           </simpara>
-         </listitem>
-
-         <listitem>
-           <simpara>
-             <link linkend="repmgr-standby-register">
-               <command>repmgr standby register --force -f /path/to/repmgr.conf</command>
-             </link>
-           </simpara>
-         </listitem>
-
-
-         <listitem>
-           <simpara>
-             <link linkend="repmgr-witness-register">
-               <command>repmgr witness register --force -f /path/to/repmgr.conf -h primary_host</command>
-             </link>
-           </simpara>
-         </listitem>
-       </itemizedlist>
-     </para>
 
    </sect2>
  </sect1>

doc/configuration-password-management.xml

@@ -1,175 +0,0 @@
-<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

@@ -1,25 +0,0 @@
-<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

@@ -148,19 +148,9 @@
             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>
 
@@ -318,7 +308,23 @@
   &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

@@ -117,6 +117,10 @@
      <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>
 
@@ -126,6 +130,9 @@
     <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>
 
@@ -141,7 +148,7 @@
   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>
 
@@ -266,6 +273,28 @@
    </itemizedlist>
  </para>
 
+  <para>
+   Events generated by &repmgrd; (BDR mode):
+   <itemizedlist spacing="compact" mark="bullet">
+   <listitem>
+    <simpara><literal>bdr_failover</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>bdr_reconnect</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>bdr_recovery</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>bdr_register</literal></simpara>
+   </listitem>
+   <listitem>
+    <simpara><literal>bdr_unregister</literal></simpara>
+   </listitem>
+
+  </itemizedlist>
+ </para>
+
  <para>
   Note that under some circumstances (e.g. when no replication cluster primary
   could be located), it will not be possible to write an entry into the

doc/filelist.xml

@@ -21,8 +21,6 @@
 <!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">
@@ -35,6 +33,7 @@
 <!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">
@@ -55,11 +54,11 @@
 <!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-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-status SYSTEM "repmgr-daemon-status.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

@@ -26,18 +26,10 @@
 	<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 (PGDG) RPM repository
-   (<ulink url="https://yum.postgresql.org/">https://yum.postgresql.org/</ulink>).
+   the PostgreSQL Global Development Group RPM repository
+   (<ulink url="https://yum.postgresql.org/">http://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.
@@ -50,10 +42,6 @@
       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>
@@ -93,9 +81,9 @@
 	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages).
 	  </para>
 	  <para>
-	    For example, for PostgreSQL 11 on CentOS, execute:
+	    For example, for PostgreSQL 10 on CentOS, execute:
 	    <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/11/rpm | sudo bash</programlisting>
+curl https://dl.2ndquadrant.com/default/release/get/10/rpm | sudo bash</programlisting>
 	  </para>
 
 	  <para>
@@ -111,8 +99,8 @@ 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-pg11/7/x86_64         2ndQuadrant packages (PG11) for 7 - x86_64               18
-2ndquadrant-dl-default-release-pg11-debug/7/x86_64   2ndQuadrant packages (PG11) for 7 - x86_64 - Debug        8</programlisting>
+2ndquadrant-dl-default-release-pg10/7/x86_64        2ndQuadrant packages (PG10) for 7 - x86_64          4
+2ndquadrant-dl-default-release-pg10-debug/7/x86_64  2ndQuadrant packages (PG10) for 7 - x86_64 - Debug  3</programlisting>
 	  </para>
 	</listitem>
 
@@ -120,7 +108,7 @@ sudo yum repolist</programlisting>
           <para>
             Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
-sudo yum install repmgr11</programlisting>
+sudo yum install repmgr10</programlisting>
           </para>
           <note>
             <para>
@@ -165,23 +153,19 @@ 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 repmgr11
-Loaded plugins: fastestmirror
-Loading mirror speeds from cached hostfile
- * base: ftp.tsukuba.wide.ad.jp
- * epel: nrt.edge.kernel.org
- * extras: ftp.tsukuba.wide.ad.jp
- * updates: ftp.tsukuba.wide.ad.jp
-Installed Packages
-repmgr11.x86_64                        4.4.0-1.rhel7                         @pgdg11
-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>
+        [root@localhost ~]# yum --showduplicates list repmgr10
+        Loaded plugins: fastestmirror
+        Loading mirror speeds from cached hostfile
+         * base: ftp.iij.ad.jp
+         * extras: ftp.iij.ad.jp
+         * updates: ftp.iij.ad.jp
+        Available Packages
+		repmgr10.x86_64                       4.0.3-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.4-1.rhel7                        pgdg10
+		repmgr10.x86_64                       4.0.5-1.el7                          2ndquadrant-repo-10</programlisting>
       then append the appropriate version number to the package name with a hyphen, e.g.:
       <programlisting>
-[root@localhost ~]# yum install repmgr11-4.3-1.el7</programlisting>
+        [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
     </para>
 
     <para>
@@ -206,7 +190,7 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
   </indexterm>
 
   <para>.deb packages for &repmgr; are available from the
-  PostgreSQL Community APT repository (<ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink>).
+  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://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>
@@ -236,13 +220,13 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
 
       <itemizedlist>
 
-	    <listitem>
-	      <para>
+	<listitem>
+	  <para>
             Install the repository definition for your distribution and PostgreSQL version
-	        (this enables the 2ndQuadrant repository as a source of &repmgr; packages) by executing:
+	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages) by executing:
             <programlisting>
-              curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlisting>
-	      </para>
+curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlisting>
+	  </para>
           <note>
             <para>
               This will automatically install the following additional packages, if not already present:
@@ -258,20 +242,20 @@ repmgr11.x86_64                        4.4-1.el7                             2nd
           </note>
         </listitem>
 
-	    <listitem>
-	      <para>
-            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr11</literal>):
+	<listitem>
+	  <para>
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
-              sudo apt-get install postgresql-11-repmgr</programlisting>
-	      </para>
+sudo apt-get install postgresql-10-repmgr</programlisting>
+	  </para>
           <note>
             <para>
-              For packages for PostgreSQL 9.6 and earlier, the package name includes
-              a period between major and minor version numbers, e.g.
-              <literal>postgresql-9.6-repmgr</literal>.
+            For packages for PostgreSQL 9.6 and earlier, the package name includes
+            a period between major and minor version numbers, e.g.
+            <literal>postgresql-9.6-repmgr</literal>.
             </para>
           </note>
-	    </listitem>
+	</listitem>
 
       </itemizedlist>
 

doc/install-requirements.xml

@@ -14,7 +14,7 @@
   </para>
 
   <para>
-   &repmgr; &repmgrversion; is compatible with all PostgreSQL versions from 9.3. See
+   &repmgr; 4.x is compatible with all PostgreSQL versions from 9.3. 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>&repmgrversion;.x</literal>) <emphasis>must</emphasis>
+     The same &quot;major&quot; &repmgr; version (e.g. <literal>4.2.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. 4.1.x and &repmgrversion;.x)
+     If different &quot;major&quot; &repmgr; versions (e.g. 3.3.x and 4.1.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>
@@ -99,9 +99,6 @@
             <entry>
               &repmgr; version
             </entry>
-            <entry>
-              Supported?
-            </entry>
             <entry>
               Latest release
             </entry>
@@ -112,31 +109,12 @@
         </thead>
 
         <tbody>
-
-          <row>
-            <entry>
-              &repmgr; 5.x
-            </entry>
-            <entry>
-              YES
-            </entry>
-            <entry>
-              <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
-            </entry>
-            <entry>
-              9.3, 9.4, 9.5, 9.6, 10, 11, 12
-            </entry>
-          </row>
-
           <row>
             <entry>
               &repmgr; 4.x
             </entry>
             <entry>
-              NO
-            </entry>
-            <entry>
-              <link linkend="release-4.4">4.4</link> (2019-06-27)
+              <link linkend="release-4.2">4.2</link> (2018-10-24)
             </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
@@ -147,9 +125,6 @@
             <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>
@@ -162,9 +137,6 @@
             <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>
@@ -182,26 +154,11 @@
         The &repmgr; 2.x and 3.x series are no longer maintained or supported.
         We strongly recommend  upgrading to the latest &repmgr; version.
       </para>
-      <para>
-        Following the release of &repmgr; 5.0, there will be no further releases of
-        the &repmgr; 4.x series. Note that &repmgr; 5.x is an incremental development
-        of the 4.x series and &repmgr; 4.x users should upgrade to this as soon as possible.
-      </para>
     </important>
 
-  </sect2>
-
-  <sect2 id="install-postgresql-93-94">
-
-    <title>PostgreSQL 9.3 and 9.4 support</title>
-
-    <indexterm>
-      <primary>PostgreSQL 9.3</primary>
-      <secondary>repmgr support</secondary>
-    </indexterm>
 
     <para>
-      Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4:
+      Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4.
     </para>
     <itemizedlist spacing="compact" mark="bullet">
 
@@ -220,26 +177,5 @@
       </listitem>
     </itemizedlist>
 
-    <important>
-      <para>
-        PostgreSQL 9.3 has reached the end of its community support period (final release was
-        <ulink url="https://www.postgresql.org/docs/9.3/release-9-3-25.html">9.3.25</ulink>
-        in November 2018) and will no longer be updated with security or bugfixes.
-      </para>
-      <para>
-        PostgreSQL 9.4 has reached the end of its community support period (final release was
-        <ulink url="https://www.postgresql.org/docs/9.4/release-9-4-26.html">9.4.26</ulink>
-        in February 2020) and will no longer be updated with security or bugfixes.
-      </para>
-      <para>
-        We recommend that users of these versions migrate to a recent PostgreSQL version
-        as soon as possible.
-      </para>
-      <para>
-        For further details, see the  <ulink url="https://www.postgresql.org/support/versioning/">PostgreSQL Versioning Policy</ulink>.
-      </para>
-    </important>
-
   </sect2>
-
  </sect1>

doc/install-source.xml

@@ -24,7 +24,8 @@
     <listitem>
      <para>
       <literal>Debian</literal> and <literal>Ubuntu</literal>: First
-      add the <ulink url="https://apt.postgresql.org/">apt.postgresql.org</ulink>
+      add the <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>
@@ -35,8 +36,8 @@
          line in the repository file, which is usually
          <filename>/etc/apt/sources.list.d/pgdg.list</filename>, e.g.:
          <programlisting>
-deb https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
-deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
+deb http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
+deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisting>
        </para>
      </tip>
      <para>
@@ -60,9 +61,6 @@ deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlist
 
          <itemizedlist spacing="compact" mark="bullet">
 
-           <listitem>
-             <simpara><literal>flex</literal></simpara>
-           </listitem>
            <listitem>
              <simpara><literal>libedit-dev</literal></simpara>
            </listitem>
@@ -117,9 +115,6 @@ deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlist
 
          <itemizedlist spacing="compact" mark="bullet">
 
-           <listitem>
-             <simpara><literal>flex</literal></simpara>
-           </listitem>
            <listitem>
              <simpara><literal>libselinux-devel</literal></simpara>
            </listitem>
@@ -182,8 +177,7 @@ deb-src https://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlist
    </para>
 
    <para>
-    There are also tags for each <ulink url="https://github.com/2ndQuadrant/repmgr/releases">&repmgr; release</ulink>, e.g.
-    <literal><ulink url="https://github.com/2ndQuadrant/repmgr/releases/tag/v4.4.0">v4.4.0</ulink></literal>.
+    There are also tags for each &repmgr; release, e.g. <literal>v4.2.0</literal>.
    </para>
 
    <para>

doc/legal.xml

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

doc/quickstart.xml

@@ -167,7 +167,7 @@
     For the sake of simplicity, the <literal>repmgr</literal> user is created
     as a superuser. If desired, it's possible to create the <literal>repmgr</literal>
     user as a normal user. However for certain operations superuser permissions
-    are required; in this case the command line option <command>--superuser</command>
+    are requiredl; 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>
@@ -265,6 +265,7 @@
    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
@@ -367,7 +368,7 @@
   </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>
@@ -477,8 +478,6 @@
     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>
@@ -498,12 +497,11 @@
   <para>
     Check the node is registered by executing <command>repmgr cluster show</command> on the standby:
     <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=node1 dbname=repmgr user=repmgr
-     2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=node2 dbname=repmgr user=repmgr</programlisting>
+    $ repmgr -f /etc/repmgr.conf cluster show
+     ID | Name  | Role    | Status    | Upstream | Location | 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>
   </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>) and status. It polls each server
+      <literal>standby</literal> / <literal>bdr</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>
@@ -53,13 +53,12 @@
     <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
-     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>
+     3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr</programlisting>
   </para>
   </refsect1>
   <refsect1>
@@ -83,22 +82,18 @@
 	  (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 | Timeline | Connection string
-    ----+-------+---------+----------------------+----------+----------+----------+----------+----------------------------------------------------
-     1  | node1 | primary | ? unreachable        |          | default  | 100      |          | host=db_node1 dbname=repmgr user=repmgr
-     2  | node2 | standby | ! running as primary | ? node1  | default  | 100      | 2        | host=db_node2 dbname=repmgr user=repmgr
-     3  | node3 | standby |   running            | ? node1  | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr
-     4  | node4 | standby | ? running            | ? node1  | default  | 100      |          | host=db_node4 dbname=repmgr user=repmgr
+	 ID | Name  | Role    | Status               | Upstream | Location | Priority | Connection string
+	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
+	 1  | node1 | primary | ? unreachable        |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
+	 2  | node2 | standby | ! running as primary | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
+	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
+	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
 
-    WARNING: following issues were detected
-      - unable to connect to node "node1" (ID: 1)
-      - node "node1" (ID: 1) is registered as an active primary but is unreachable
-      - node "node2" (ID: 2) is registered as standby but running as primary
-      - unable to connect to node "node2" (ID: 2)'s upstream node "node1" (ID: 1)
-      - unable to determine if node "node2" (ID: 2) is attached to its upstream node "node1" (ID: 1)
-      - unable to connect to node "node3" (ID: 3)'s upstream node "node1" (ID: 1)
-      - unable to determine if node "node3" (ID: 3) is attached to its upstream node "node1" (ID: 1)
-      - unable to connect to node "node4" (ID: 4)
+	WARNING: following issues were detected
+	  - unable to connect to node "node1" (ID: 1)
+	  - node "node1" (ID: 1) is registered as an active primary but is unreachable
+	  - node "node2" (ID: 2) is registered as standby but running as primary
+	  - unable to connect to node "node4" (ID: 4)
     HINT: execute with --verbose option to see connection error messages</programlisting>
     </para>
 	<para>
@@ -238,7 +233,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-service-status"/>
+     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-pause.xml

@@ -1,6 +1,6 @@
-<refentry id="repmgr-service-pause">
+<refentry id="repmgr-daemon-pause">
   <indexterm>
-    <primary>repmgr service pause</primary>
+    <primary>repmgr daemon pause</primary>
   </indexterm>
 
   <indexterm>
@@ -9,11 +9,11 @@
   </indexterm>
 
   <refmeta>
-    <refentrytitle>repmgr service pause</refentrytitle>
+    <refentrytitle>repmgr daemon pause</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr service pause</refname>
+    <refname>repmgr daemon pause</refname>
     <refpurpose>Instruct all &repmgrd; instances in the replication cluster to pause failover operations</refpurpose>
   </refnamediv>
 
@@ -32,29 +32,20 @@
     <note>
       <para>
         It's important to wait a few seconds after restarting PostgreSQL on any node before running
-        <command>repmgr service pause</command>, as the &repmgrd; instance
+        <command>repmgr daemon 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-service-unpause"/> will instruct all previously paused &repmgrd;
+      <xref linkend="repmgr-daemon-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 service pause</command> can be executed on any active node in the
+      <command>repmgr daemon 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>
@@ -64,7 +55,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-$ repmgr -f /etc/repmgr.conf service pause
+$ repmgr -f /etc/repmgr.conf daemon pause
 NOTICE: node 1 (node1) paused
 NOTICE: node 2 (node2) paused
 NOTICE: node 3 (node3) paused</programlisting>
@@ -88,7 +79,7 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr service unpause</command>:
+      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
     </para>
     <variablelist>
 
@@ -116,11 +107,7 @@ NOTICE: node 3 (node3) paused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-service-unpause"/>,
-      <xref linkend="repmgr-service-status"/>,
-      <xref linkend="repmgrd-pausing"/>,
-      <xref linkend="repmgr-daemon-start"/>,
-      <xref linkend="repmgr-daemon-stop"/>
+      <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-daemon-start.xml

@@ -14,13 +14,13 @@
 
   <refnamediv>
     <refname>repmgr daemon start</refname>
-    <refpurpose>Start the &repmgrd; daemon on the local node</refpurpose>
+    <refpurpose>Start the &repmgrd; daemon</refpurpose>
   </refnamediv>
 
   <refsect1>
     <title>Description</title>
     <para>
-      This command starts the &repmgrd; service on the
+      This command starts the &repmgrd; daemon on the
       local node.
     </para>
     <para>
@@ -197,11 +197,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-stop"/>,
-      <xref linkend="repmgrd-daemon"/>,
-      <xref linkend="repmgr-service-status"/>,
-      <xref linkend="repmgr-service-pause"/>,
-      <xref linkend="repmgr-service-unpause"/>
+      <xref linkend="repmgr-daemon-stop"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-status.xml

@@ -1,19 +1,19 @@
-<refentry id="repmgr-service-status">
+<refentry id="repmgr-daemon-status">
   <indexterm>
-    <primary>repmgr service status</primary>
+    <primary>repmgr daemon status</primary>
   </indexterm>
 
   <indexterm>
     <primary>repmgrd</primary>
-    <secondary>displaying service status</secondary>
+    <secondary>displaying daemon status</secondary>
   </indexterm>
 
   <refmeta>
-    <refentrytitle>repmgr service status</refentrytitle>
+    <refentrytitle>repmgr daemon status</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr service status</refname>
+    <refname>repmgr daemon status</refname>
     <refpurpose>display information about the status of &repmgrd; on each node in the cluster</refpurpose>
   </refnamediv>
 
@@ -22,33 +22,21 @@
     <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-service-pause"/> and <xref linkend="repmgr-service-unpause"/>
+      the result of <xref linkend="repmgr-daemon-pause"/> and <xref linkend="repmgr-daemon-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 service status</command> can be executed on any active node in the
+      <command>repmgr daemon 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 a node is not accessible, or PostgreSQL itself is not running on the node,
-      &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.
+      If PostgreSQL is not running on a node, &repmgr; will not be able to determine the
+      status of that node's &repmgrd; instance.
     </para>
-
     <note>
       <para>
         After restarting PostgreSQL on any node, the &repmgrd; instance
@@ -63,7 +51,7 @@
     <title>Examples</title>
     <para>
       &repmgrd; running normally on all nodes:
-    <programlisting>$ repmgr -f /etc/repmgr.conf service status
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running | 96563 | no      | n/a
@@ -72,8 +60,8 @@
     </para>
 
     <para>
-      &repmgrd; paused on all nodes (using <xref linkend="repmgr-service-pause"/>):
-    <programlisting>$ repmgr -f /etc/repmgr.conf service status
+      &repmgrd; paused on all nodes (using <xref linkend="repmgr-daemon-pause"/>):
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running | 96563 | yes     | n/a
@@ -83,7 +71,7 @@
 
     <para>
       &repmgrd; not running on one node:
-    <programlisting>$ repmgr -f /etc/repmgr.conf service status
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status    | Upstream | repmgrd     | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+-------------+-------+---------+--------------------
  1  | node1 | primary | * running |          | running     | 96563 | yes     | n/a
@@ -101,11 +89,11 @@
         <term><option>--csv</option></term>
         <listitem>
           <para>
-            <command>repmgr service status</command> accepts an optional parameter <literal>--csv</literal>, which
+            <command>repmgr daemon 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 service status --csv
+    $ repmgr -f /etc/repmgr.conf daemon 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>
@@ -183,7 +171,7 @@
         <listitem>
           <para>
             Display additional information (<literal>location</literal>, <literal>priority</literal>)
-	    about the &repmgr; configuration.
+			about the &repmgr; configuration.
           </para>
         </listitem>
       </varlistentry>
@@ -192,7 +180,7 @@
         <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>
@@ -204,12 +192,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <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"/>
+      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-unpause"/>, <xref linkend="repmgr-cluster-show"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-daemon-stop.xml

@@ -14,7 +14,7 @@
 
   <refnamediv>
     <refname>repmgr daemon stop</refname>
-    <refpurpose>Stop the &repmgrd; daemon on the local node</refpurpose>
+    <refpurpose>Stop the &repmgrd; daemon</refpurpose>
   </refnamediv>
 
   <refsect1>
@@ -194,11 +194,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-daemon-start"/>,
-      <xref linkend="repmgrd-daemon"/>,
-      <xref linkend="repmgr-service-status"/>,
-      <xref linkend="repmgr-service-pause"/>,
-      <xref linkend="repmgr-service-unpause"/>
+      <xref linkend="repmgr-daemon-start"/>, <xref linkend="repmgr-daemon-status"/>, <xref linkend="repmgrd-daemon"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-unpause.xml

@@ -1,6 +1,6 @@
-<refentry id="repmgr-service-unpause">
+<refentry id="repmgr-daemon-unpause">
   <indexterm>
-    <primary>repmgr service unpause</primary>
+    <primary>repmgr daemon unpause</primary>
   </indexterm>
 
   <indexterm>
@@ -8,12 +8,13 @@
     <secondary>unpausing</secondary>
   </indexterm>
 
+
   <refmeta>
-    <refentrytitle>repmgr service unpause</refentrytitle>
+    <refentrytitle>repmgr daemon unpause</refentrytitle>
   </refmeta>
 
   <refnamediv>
-    <refname>repmgr service unpause</refname>
+    <refname>repmgr daemon unpause</refname>
     <refpurpose>Instruct all &repmgrd; instances in the replication cluster to resume failover operations</refpurpose>
   </refnamediv>
 
@@ -22,33 +23,24 @@
     <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-service-pause"/>)
+      (following a previous execution of <xref linkend="repmgr-daemon-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 service pause</command>, as the &repmgrd; instance
+        <command>repmgr daemon 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 service unpause</command> can be executed on any active node in the
+     <command>repmgr daemon 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>
@@ -58,7 +50,7 @@
     <title>Example</title>
     <para>
     <programlisting>
-$ repmgr -f /etc/repmgr.conf service unpause
+$ repmgr -f /etc/repmgr.conf daemon unpause
 NOTICE: node 1 (node1) unpaused
 NOTICE: node 2 (node2) unpaused
 NOTICE: node 3 (node3) unpaused</programlisting>
@@ -82,7 +74,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>Exit codes</title>
     <para>
-      One of the following exit codes will be emitted by <command>repmgr service unpause</command>:
+      One of the following exit codes will be emitted by <command>repmgr daemon unpause</command>:
     </para>
     <variablelist>
 
@@ -110,11 +102,7 @@ NOTICE: node 3 (node3) unpaused</programlisting>
   <refsect1>
     <title>See also</title>
     <para>
-      <xref linkend="repmgr-service-pause"/>,
-      <xref linkend="repmgr-service-status"/>,
-      <xref linkend="repmgrd-pausing"/>,
-      <xref linkend="repmgr-daemon-start"/>,
-      <xref linkend="repmgr-daemon-stop"/>
+      <xref linkend="repmgr-daemon-pause"/>, <xref linkend="repmgr-daemon-status"/>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-node-check.xml

@@ -31,32 +31,15 @@
   <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)
-            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>
+            Missing replication slots: OK (node has no missing physical replication slots)</programlisting>
     </para>
   </refsect1>
   <refsect1>
@@ -74,20 +57,20 @@
 
      <listitem>
       <simpara>
-        <option>--role</option>: checks if the node has the expected role
+        <literal>--role</literal>: checks if the node has the expected role
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <option>--replication-lag</option>: checks if the node is lagging by more than
+        <literal>--replication-lag</literal>: checks if the node is lagging by more than
         <varname>replication_lag_warning</varname> or <varname>replication_lag_critical</varname>
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <option>--archive-ready</option>: checks for WAL files which have not yet been archived,
+        <literal>--archive-ready</literal>: 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>
@@ -95,31 +78,25 @@
 
      <listitem>
       <simpara>
-        <option>--downstream</option>: checks that the expected downstream nodes are attached
+        <literal>--downstream</literal>: checks that the expected downstream nodes are attached
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <option>--upstream</option>: checks that the node is attached to its expected upstream
+        <literal>--slots</literal>: checks there are no inactive physical replication slots
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <option>--slots</option>: checks there are no inactive physical replication slots
+        <literal>--missing-slots</literal>: checks there are no missing physical replication slots
       </simpara>
      </listitem>
 
      <listitem>
       <simpara>
-        <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
+        <literal>--data-directory-config</literal>: 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.
@@ -131,22 +108,6 @@
   </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>
@@ -154,14 +115,14 @@
 
         <listitem>
           <simpara>
-            <option>--csv</option>: generate output in CSV format (not available
+            <literal>--csv</literal>: generate output in CSV format (not available
             for individual checks)
           </simpara>
         </listitem>
 
         <listitem>
           <simpara>
-            <option>--nagios</option>: generate output in a Nagios-compatible format
+            <literal>--nagios</literal>: generate output in a Nagios-compatible format
             (for individual checks only)
           </simpara>
         </listitem>
@@ -169,15 +130,13 @@
     </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 <option>--nagios</option> is not supplied):
+      (even if <literal>--nagios</literal> is not supplied):
 
       <itemizedlist spacing="compact" mark="bullet">
 

doc/repmgr-node-rejoin.xml

@@ -43,12 +43,7 @@
       <programlisting>
       repmgr node rejoin -d '$conninfo'</programlisting>
 
-      where <literal>$conninfo</literal> is the PostgreSQL <literal>conninfo</literal> string of the
-      <emphasis>current</emphasis> primary node (or that of any reachable node in the cluster, but
-      <emphasis>not</emphasis> the local node). This is so that &repmgr; can fetch up-to-date information
-      about the current state of the cluster.
-    </para>
-    <para>
+      where <literal>$conninfo</literal> is the conninfo string of any reachable node in the cluster.
       <filename>repmgr.conf</filename> for the stopped node *must* be supplied explicitly if not
       otherwise available.
     </para>
@@ -288,15 +283,7 @@
       to execute <command>pg_rewind</command> to ensure the node can be rejoined successfully.
     </para>
 
-    <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>
-
+    <important>
       <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
@@ -304,27 +291,17 @@
       </para>
       <para>
         To prevent this happening, provide a comma-separated list of files to retain
-        using the <option>--config-file</option> command line option; the specified files
+        using the <literal>--config-file</literal> command line option; the specified files
         will be archived in a temporary directory (whose parent directory can be specified with
-        <option>--config-archive-dir</option>, default: <filename>/tmp</filename>)
-        and restored once the rewind operation is complete.
+        <literal>--config-archive-dir</literal>) and restored once the rewind operation is
+        complete.
       </para>
-    </refsect2>
+    </important>
 
-    <refsect2 id="repmgr-node-rejoin-pg-rewind-example" xreflabel="example using repmgr node rejoin and pg_rewind">
-
-      <title>Example using <command>repmgr node rejoin</command> and <command>pg_rewind</command></title>
-
-      <indexterm>
-        <primary>pg_rewind</primary>
-        <secondary>configuration file retention</secondary>
-      </indexterm>
-
-
-      <para>
-        Example, first using <option>--dry-run</option>, then actually executing the
-        <literal>node rejoin command</literal>.
-        <programlisting>
+    <para>
+      Example, first using <literal>--dry-run</literal>, then actually executing the
+      <literal>node rejoin command</literal>.
+    <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind --dry-run
     INFO: replication connection to the rejoin target node was successful
@@ -340,17 +317,17 @@
       pg_rewind -D '/var/lib/postgresql/data' --source-server='host=node3 dbname=repmgr user=repmgr'
     INFO: prerequisites for executing NODE REJOIN are met</programlisting>
 
-        <note>
-          <para>
-            If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
-            this checks the prerequisites for using <application>pg_rewind</application>, but is
-            not an absolute guarantee that actually executing <application>pg_rewind</application>
-            will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
-          </para>
+    <note>
+      <para>
+        If <option>--force-rewind</option> is used with the <option>--dry-run</option> option,
+        this checks the prerequisites for using <application>pg_rewind</application>, but is
+        not an absolute guarantee that actually executing <application>pg_rewind</application>
+        will succeed. See also section <xref linkend="repmgr-node-rejoin-caveats"/> below.
+      </para>
 
-        </note>
+    </note>
 
-        <programlisting>
+    <programlisting>
     $ repmgr node rejoin -f /etc/repmgr.conf -d 'host=node3 dbname=repmgr user=repmgr' \
         --config-files=postgresql.local.conf,postgresql.conf --verbose --force-rewind
     NOTICE: pg_rewind execution required for this node to attach to rejoin target node 3
@@ -362,8 +339,8 @@
     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>
-    </refsect2>
+    </para>
+
   </refsect1>
 
   <refsect1 id="repmgr-node-rejoin-caveats" xreflabel="Caveats">
@@ -379,7 +356,7 @@
      <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 12) may appear to succeed (or indicate there is no action
+     which currently (as of PostgreSQL 11) 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>
@@ -401,51 +378,6 @@
      is running in <option>--dry-run</option> mode.
    </para>
 
-   <warning>
-     <para>
-       In all current PostgreSQL versions (as of September 2020), <application>pg_rewind</application>
-       contains a corner-case bug which affects standbys in a very specific situation.
-     </para>
-     <para>
-       This situation occurs when a standby was shut down <emphasis>before</emphasis> its
-       primary node, and an attempt is made to attach this standby to another primary
-       in the same cluster (following a &quot;split brain&quot; situation where the standby
-       was connected to the wrong primary). In this case, &repmgr; will correctly determine
-       that <application>pg_rewind</application> should be executed, however
-       <application>pg_rewind</application> incorrectly decides that no action is necessary.
-     </para>
-     <para>
-       In this situation, &repmgr; will report something like:
-<programlisting>
-    NOTICE: pg_rewind execution required for this node to attach to rejoin target node 1
-    DETAIL: rejoin target server's timeline 3 forked off current database system timeline 2 before current recovery point 0/7019C10</programlisting>
-       but when executed, <application>pg_rewind</application> will report:
-<programlisting>
-    pg_rewind: servers diverged at WAL location 0/7015540 on timeline 2
-    pg_rewind: no rewind required</programlisting>
-       and if an attempt is made to attach the standby to the new primary, PostgreSQL logs on the standby
-       will contain errors like:
-<programlisting>
-    [2020-09-07 15:01:41 UTC]    LOG:  00000: replication terminated by primary server
-    [2020-09-07 15:01:41 UTC]    DETAIL:  End of WAL reached on timeline 2 at 0/7015540.
-    [2020-09-07 15:01:41 UTC]    LOG:  00000: new timeline 3 forked off current database system timeline 2 before current recovery point 0/7019C10</programlisting>
-     </para>
-     <para>
-       Currently it is not possible to resolve this situation using <application>pg_rewind</application>.
-       A <ulink url="https://www.postgresql.org/message-id/flat/CABvVfJU-LDWvoz4-Yow3Ay5LZYTuPD7eSjjE4kGyNZpXC6FrVQ@mail.gmail.com">patch</ulink>
-       has been submitted and will hopefully be included in a forthcoming PostgreSQL minor release.
-     </para>
-     <para>
-       As a workaround, start the primary server the standby was previously attached to,
-       and ensure the standby can be attached to it. If <application>pg_rewind</application> was actually executed,
-       it will have copied in the <filename>.history</filename> file from the target primary server; this must
-       be removed. <command>repmgr node rejoin</command> can then be used to attach the standby to the original
-       primary. Ensure any changes pending on the primary have propogated to the standby. Then shut down the primary
-       server <emphasis>first</emphasis>, before shutting down the standby. It should then be possible to
-       use <command>repmgr node rejoin</command> to attach the standby to the new primary.
-     </para>
-   </warning>
-
   </refsect1>
 
   <refsect1>

doc/repmgr-node-service.xml

@@ -75,22 +75,8 @@
           <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>
@@ -128,38 +114,38 @@
     <para>
       See what action would be taken for a restart:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --action=restart --checkpoint --dry-run
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --action=restart --checkpoint --dry-run
 INFO: a CHECKPOINT would be issued here
-INFO: would execute server command "sudo service postgresql-12 restart"</programlisting>
+INFO: would execute server command "sudo service postgresql-11 restart"</programlisting>
     </para>
 
     <para>
       Restart the PostgreSQL instance:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --action=restart --checkpoint
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --action=restart --checkpoint
 NOTICE: issuing CHECKPOINT
-DETAIL: executing server command "sudo service postgresql-12 restart"
-Redirecting to /bin/systemctl restart postgresql-12.service</programlisting>
+DETAIL: executing server command "sudo service postgresql-11 restart"
+Redirecting to /bin/systemctl restart postgresql-11.service</programlisting>
     </para>
 
     <para>
       List all commands:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --list-actions
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --list-actions
 Following commands would be executed for each action:
 
-    start: "sudo service postgresql-12 start"
-     stop: "sudo service postgresql-12 stop"
-  restart: "sudo service postgresql-12 restart"
-   reload: "sudo service postgresql-12 reload"
-  promote: "/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote"</programlisting>
+    start: "sudo service postgresql-11 start"
+     stop: "sudo service postgresql-11 stop"
+  restart: "sudo service postgresql-11 restart"
+   reload: "sudo service postgresql-11 reload"
+  promote: "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote"</programlisting>
     </para>
 
     <para>
       List a single command:
       <programlisting>
-[postgres@node1 ~]$ repmgr -f /etc/repmgr/12/repmgr.conf node service --list-actions --action=promote
-/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote      </programlisting>
+[postgres@node1 ~]$ repmgr -f /etc/repmgr/11/repmgr.conf node service --list-actions --action=promote
+/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote      </programlisting>
     </para>
   </refsect1>
 </refentry>

doc/repmgr-primary-register.xml

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

doc/repmgr-standby-clone.xml

@@ -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 replication configuration required
+      the cluster or from Barman. It creates the <filename>recovery.conf</filename> file required
       to attach the cloned node to the primary node (or another standby, if cascading replication
       is in use).
     </para>
@@ -85,20 +85,15 @@
   </refsect1>
 
   <refsect1 id="repmgr-standby-clone-recovery-conf">
-    <title>Customising replication configuration</title>
+    <title>Customising recovery.conf</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 replication configuration
+     By default, &repmgr; will create a minimal <filename>recovery.conf</filename>
      containing following parameters:
    </para>
 
@@ -124,7 +119,7 @@
 
    <para>
      The following additional parameters can be specified in <filename>repmgr.conf</filename>
-     for inclusion in the replication configuration:
+     for inclusion in <filename>recovery.conf</filename>:
    </para>
 
    <itemizedlist spacing="compact" mark="bullet">
@@ -188,16 +183,11 @@
    </note>
   </refsect1>
 
-<!-- don't rename this id as it may be used in external links -->
+
   <refsect1 id="repmgr-standby-create-recovery-conf">
 
    <title>Using a standby cloned by another method</title>
 
-   <indexterm>
-     <primary>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>
@@ -205,43 +195,35 @@
 
    <para>
      &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
-     <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command> command).
+     <command><ulink url="http://docs.pgbarman.org/release/2.5/#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>.
-   </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>.
+     Then execute the command <command>repmgr standby clone --recovery-conf-only</command>.
      This will create the <filename>recovery.conf</filename> file needed to attach
-     the node to its upstream (in PostgreSQL 12 and later: append replication configuration
-     to <filename>postgresql.auto.conf</filename>), and will also create a replication slot on the
+     the node to its upstream, and will also create a replication slot on the
      upstream node if required.
    </para>
    <para>
-     Note that the upstream node must be running. In PostgreSQL 11 and earlier, an existing
+     Note that the upstream node must be running. An existing
      <filename>recovery.conf</filename> will not be overwritten unless the
      <option>-F/--force</option> option is provided.
    </para>
    <para>
-     Execute <command>repmgr standby clone --replication-conf-only --dry-run</command>
-     to check the prerequisites for creating the recovery configuration,
-     and display the contents of the configuration which would be added without actually
-	 making any changes.
+     Execute <command>repmgr standby clone --recovery-conf-only --dry-run</command>
+     to check the prerequisites for creating the <filename>recovery.conf</filename> file,
+     and display the contents of the file without actually creating it.
    </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>
 
   <refsect1>
@@ -266,9 +248,9 @@
             Check prerequisites but don't actually clone the standby.
           </para>
           <para>
-            If <option>--replication-conf-only</option> specified, the contents of
-            the generated recovery configuration will be displayed
-            but not written.
+            If <option>--recovery-conf-only</option> specified, the contents of
+            the generated <filename>recovery.conf</filename> file will be displayed
+            but the file itself not written.
           </para>
         </listitem>
       </varlistentry>
@@ -312,19 +294,11 @@
       </varlistentry>
 
       <varlistentry>
-        <term><option>--replication-conf-only</option></term>
+        <term><option> --recovery-conf-only</option></term>
         <listitem>
           <para>
-            Create recovery configuration for a previously cloned instance.
+            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr; 4.0.4 and later.
           </para>
-		  <para>
-			In PostgreSQL 11 and earlier, the replication configuration will be
-			written to <filename>recovery.conf</filename>.
-		  </para>
-		  <para>
-			In PostgreSQL 12 and later, the replication configuration will be
-			written to <filename>postgresql.auto.conf</filename>.
-		  </para>
         </listitem>
       </varlistentry>
 
@@ -352,7 +326,7 @@
         <term><option>--upstream-conninfo</option></term>
         <listitem>
           <para>
-            <literal>primary_conninfo</literal> value to include in the recovery configuration
+            <literal>primary_conninfo</literal> value to write in <filename>recovery.conf</filename>
             when the intended upstream server does not yet exist.
           </para>
           <para>

doc/repmgr-standby-follow.xml

@@ -20,54 +20,49 @@
       ("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 <filename>repmgr.conf</filename> file for the standby,
-      either specified explicitly with <literal>-f/--config-file</literal> or located in a
+      This command requires a valid
+      <filename>repmgr.conf</filename> file for the standby, either specified
+      explicitly with <literal>-f/--config-file</literal> or located in a
       default location; no additional arguments are required.
     </para>
 
-    <para>The standby node (&quot;follow candidate&quot;) <emphasis>must</emphasis>
-      be running. If the new upstream (&quot;follow target&quot;) is not the primary,
-      the cluster primary <emphasis>must</emphasis> be running and accessible from the
-      standby node.
-    </para>
-
-    <tip>
-      <para>
-        To re-add an inactive node to the replication cluster, use
-        <xref linkend="repmgr-node-rejoin"/>.
-      </para>
-    </tip>
+	<para>
+	  By default &repmgr; will attempt to attach the standby to the current primary.
+	  If <option>--upstream-node-id</option> is provided, &repmgr; will attempt
+	  to attach the standby to the specified node, which can be another standby.
+	</para>
 
     <para>
-      By default &repmgr; will attempt to attach the standby to the current primary.
-      If <option>--upstream-node-id</option> is provided, &repmgr; will attempt
-      to attach the standby to the specified node, which can be another standby.
+      This command will force a restart of the standby server, which must be
+      running.
     </para>
 
-    <para>
-      This command will force a restart of PostgreSQL on the standby node.
-    </para>
-
-    <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>
+	<tip>
       <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.
+		To re-add an inactive node to the replication cluster, use
+		<xref linkend="repmgr-node-rejoin"/>.
       </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>
+	</tip>
+
+	<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>
 
@@ -129,7 +124,7 @@
           <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>
@@ -171,7 +166,7 @@
       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 &quot;node3&quot; (ID 3)
+ERROR: this node cannot attach to follow target node 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

@@ -23,8 +23,7 @@
     <important>
       <para>
         If &repmgrd; is active, you must execute
-        <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>)
+        <command><link linkend="repmgr-daemon-pause">repmgr daemon pause</link></command>
         to temporarily disable &repmgrd; while making any changes
         to the replication cluster.
       </para>
@@ -86,7 +85,6 @@
   </refsect1>
 
 
-
   <refsect1>
     <title>Example</title>
     <para>
@@ -95,46 +93,13 @@
       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>
@@ -169,42 +134,6 @@
         </listitem>
       </varlistentry>
 
-      <varlistentry>
-        <term><option>-F</option></term>
-        <term><option>--force</option></term>
-        <listitem>
-          <para>
-            Ignore warnings and continue anyway.
-          </para>
-          <para>
-            This option is relevant in the following situations if <option>--siblings-follow</option> was specified:
-            <itemizedlist spacing="compact" mark="bullet">
-              <listitem>
-                <simpara>
-                  If one or more sibling nodes was not reachable via SSH, the standby will be promoted anyway.
-                </simpara>
-              </listitem>
-              <listitem>
-                <simpara>
-                  If the promotion candidate has insufficient free walsenders to accomodate the standbys which will
-                  be attached to it, the standby will be promoted anyway.
-                </simpara>
-              </listitem>
-              <listitem>
-                <simpara>
-                  If replication slots are in use but the promotion candidate has insufficient free replication slots
-                  to accomodate the standbys which will be attached to it, the standby will be promoted anyway.
-                </simpara>
-              </listitem>
-            </itemizedlist>
-          </para>
-          <para>
-            Note that if the <option>-F</option>/<option>--force</option> option is used when any of the above
-            situations is encountered, the onus is on the user to manually resolve any resulting issues.
-          </para>
-        </listitem>
-      </varlistentry>
-
     </variablelist>
   </refsect1>
 
@@ -242,23 +171,6 @@
 		 </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

@@ -75,22 +75,10 @@
    <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, or if the node was not cloned by &repmgr;.
-   </para>
-   <para>
-    In this case, by using the <option>-F/--force</option>
+    a complex replication cluster. 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.
+    the standby can be registered.
    </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,
@@ -108,11 +96,9 @@
     <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><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command>
-     command), register the node as detailed in section
-     <xref linkend="repmgr-standby-register-inactive-node"/> then execute
-     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --replication-conf-only</link>
-     to generate the appropriate replication configuration.
+     <command>barman recover</command> command), first execute
+     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
+     to add the <filename>recovery.conf</filename> file, then register the standby as usual.
     </para>
   </refsect1>
 
@@ -133,7 +119,7 @@
 
 
       <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

@@ -63,38 +63,6 @@
   </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>
 
@@ -216,17 +184,6 @@
           </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

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

doc/repmgr.xml

@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.3 - PostgreSQL 12.
+   use with PostgreSQL 9.3 - PostgreSQL 11.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -91,6 +91,7 @@
   &repmgrd-automatic-failover;
   &repmgrd-configuration;
   &repmgrd-operation;
+  &repmgrd-bdr;
  </part>
 
  <part id="repmgr-command-reference">
@@ -115,11 +116,11 @@
   &repmgr-cluster-crosscheck;
   &repmgr-cluster-event;
   &repmgr-cluster-cleanup;
-  &repmgr-service-status;
-  &repmgr-service-pause;
-  &repmgr-service-unpause;
+  &repmgr-daemon-status;
   &repmgr-daemon-start;
   &repmgr-daemon-stop;
+  &repmgr-daemon-pause;
+  &repmgr-daemon-unpause;
  </part>
 
  &appendix-release-notes;

doc/repmgrd-automatic-failover.xml

@@ -192,23 +192,21 @@
     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 (and the witness, if present) for the time it last saw the
-    primary; if any have seen the primary very recently, it's reasonable
+    This is done by polling each standby for the time it last saw the 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-service-status"><command>repmgr service status</command></link>
-    (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>)
+    <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>,
     which includes this in its output, e.g.:
-    <programlisting>$ repmgr -f /etc/repmgr.conf service status
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
- 1  | node1 | primary | * running |          | running | 27259 | no      | n/a
- 2  | node2 | standby |   running | node1    | running | 27272 | no      | 1 second(s) ago
- 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>
+ 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
+ 2  | node2 | standby |   running | node1    | running | 96572 | no      | 1 second(s) ago
+ 3  | node3 | standby |   running | node1    | running | 96584 | no      | 0 second(s) ago</programlisting>
 
   </para>
 
@@ -269,12 +267,11 @@
   <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, and wait for the WAL receiver on all sibling nodes to be
-	disconnected, before making a failover decision.
+    the local node's WAL receiver before making a failover decision.
   </para>
   <note>
     <para>
-      <option>standby_disconnect_on_failover</option> is available with PostgreSQL 9.5 and later.
+      <option>standby_disconnect_on_failover</option> is available from PostgreSQL 9.5 and later.
       Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
     </para>
   </note>
@@ -293,12 +290,6 @@
     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>

doc/repmgrd-bdr.xml

@@ -0,0 +1,429 @@
+<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

@@ -8,20 +8,16 @@
   </indexterm>
 
   <para>
-    &repmgrd; is a daemon process which runs on each PostgreSQL node,
+    &repmgrd; is a daemon 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 or upstream node becomes unreachable, and/or
+    capability in case the primary 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>
@@ -81,7 +77,7 @@
               <listitem>
                 <simpara>
                   <literal>connection</literal> - determines server availability
-                  by attempting to make a new connection to the upstream node
+                  by attempt ingto make a new connection to the upstream node
                 </simpara>
               </listitem>
               <listitem>
@@ -226,17 +222,6 @@
               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>
@@ -398,8 +383,8 @@
             </indexterm>
 
             <para>
-              If <literal>true</literal>, only continue with failover if no standbys
-              (or the witness server, if present) have seen the primary node recently.
+              If <literal>true</literal>, only continue with failover if no standbys have seen
+			  the primary node recently.
             </para>
             <note>
               <para>
@@ -490,23 +475,6 @@
 
     </sect2>
 
-
-    <sect2 id="repmgrd-automatic-failover-configuration-pgbouncer-fencing">
-      <title>Configuring &repmgrd; and pgbouncer to fence a failed primary node</title>
-      <indexterm>
-        <primary>fencing</primary>
-        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
-      </indexterm>
-      <indexterm>
-        <primary>PgBouncer</primary>
-        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
-      </indexterm>
-      <para>
-        For further details and a reference implementation, see the separate document
-        <ulink url="https://github.com/2ndQuadrant/repmgr/blob/master/doc/repmgrd-node-fencing.md">Fencing a failed master node with repmgrd and PgBouncer</ulink>.
-      </para>
-    </sect2>
-
     <sect2 id="postgresql-service-configuration">
       <title>PostgreSQL service configuration</title>
 
@@ -540,8 +508,7 @@
       </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">
 
@@ -557,10 +524,10 @@
 
       </para>
       <para>
-        Example (for &repmgr; with PostgreSQL 12 on CentOS 7):
+        Example (for &repmgr; with PostgreSQL 11 on CentOS 7):
         <programlisting>
-repmgrd_service_start_command='sudo systemctl repmgr12 start'
-repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
+repmgrd_service_start_command='sudo systemctl repmgr11 start'
+repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
 </programlisting>
       </para>
       <para>
@@ -587,8 +554,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
         the option <option>monitor_interval_secs</option> (see above).
       </para>
       <para>
-        For more details on monitoring, see <xref linkend="repmgrd-monitoring"/>. For information on
-        monitoring standby disconnections, see <xref linkend="repmgrd-primary-child-disconnection"/>.
+        For more details on monitoring, see <xref linkend="repmgrd-monitoring"/>.
       </para>
     </sect2>
 
@@ -624,6 +590,18 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
           </simpara>
         </listitem>
 
+        <listitem>
+          <simpara>
+            <varname>bdr_local_monitoring_only</varname>
+          </simpara>
+        </listitem>
+
+        <listitem>
+          <simpara>
+            <varname>bdr_recovery_timeout</varname>
+          </simpara>
+        </listitem>
+
          <listitem>
           <simpara>
             <varname>child_nodes_check_interval</varname>
@@ -871,7 +849,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr12 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; on the local node.
+      as convenience wrappers to start and stop &repmgrd;.
     </para>
     <important>
       <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 --log-to-file
+    repmgr standby promote -f /etc/repmgr.conf
 
     # 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" xreflabel="pausing the repmgrd service">
+  <sect1 id="repmgrd-pausing">
 
-    <title>Pausing the repmgrd service</title>
+    <title>Pausing repmgrd</title>
 
   <indexterm>
     <primary>repmgrd</primary>
@@ -47,7 +47,7 @@
 
   <note>
     <para>
-      For major PostgreSQL upgrades, e.g. from PostgreSQL 11 to PostgreSQL 12,
+      For major PostgreSQL upgrades, e.g. from PostgreSQL 10 to PostgreSQL 11,
       &repmgrd; should be shut down completely and only started up
       once the &repmgr; packages for the new PostgreSQL major version have been installed.
     </para>
@@ -88,21 +88,17 @@
   <sect2 id="repmgrd-pausing-execution">
     <title>Pausing/unpausing &repmgrd;</title>
     <para>
-      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.:
+      To pause &repmgrd;, execute <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link>, e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf service pause
+$ repmgr -f /etc/repmgr.conf daemon 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-service-status"><command>repmgr service status</command></link>
-      (&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
+      <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>, e.g.:
+    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
  ID | Name  | Role    | Status  | repmgrd | PID  | Paused?
 ----+-------+---------+---------+---------+------+---------
  1  | node1 | primary | running | running | 7851 | yes
@@ -112,8 +108,8 @@ NOTICE: node 3 (node3) paused</programlisting>
 
     <note>
       <para>
-        If executing a switchover with <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-	&repmgr; will automatically pause/unpause the &repmgrd; service as part of the switchover process.
+        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.
       </para>
     </note>
 
@@ -121,32 +117,29 @@ 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>
-[2019-08-28 12:22:21] [WARNING] unable to connect to upstream node "node1" (node ID: 1)
-[2019-08-28 12:22:21] [INFO] checking state of node 1, 1 of 5 attempts
-[2019-08-28 12:22:21] [INFO] sleeping 1 seconds until next reconnection attempt
+[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (ID: 1)
+[2018-09-20 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 12:22:24] [INFO] sleeping 1 seconds until next reconnection attempt
-[2019-08-28 12:22:25] [INFO] checking state of node 1, 5 of 5 attempts
-[2019-08-28 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
-[2019-08-28 12:22:25] [NOTICE] node is paused
-[2019-08-28 12:22:33] [INFO] node "node2" (ID: 2) monitoring upstream node "node1" (node ID: 1) in degraded state
-[2019-08-28 12:22:33] [DETAIL] repmgrd paused by administrator
-[2019-08-28 12:22:33] [HINT] execute "repmgr service unpause" to resume normal failover mode</programlisting>
+[2018-09-20 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
+[2018-09-20 12:22:25] [WARNING] unable to reconnect to node 1 after 5 attempts
+[2018-09-20 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
+[2018-09-20 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>
     </para>
     <para>
       If the primary becomes available again (e.g. following a software upgrade), &repmgrd;
       will automatically reconnect, e.g.:
       <programlisting>
-[2019-08-28 12:25:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
+[2018-09-20 13:12:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
     </para>
 
     <para>
-      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.:
+      To unpause &repmgrd;, execute <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>, e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf service unpause
+$ repmgr -f /etc/repmgr.conf daemon unpause
 NOTICE: node 1 (node1) unpaused
 NOTICE: node 2 (node2) unpaused
 NOTICE: node 3 (node3) unpaused</programlisting>
@@ -157,11 +150,11 @@ 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
-	<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
+		and any standbys attached to the new primary with
+		<link linkend="repmgr-standby-follow"><command>repmgr standby follow</command></link>.
       </para>
       <para>
-        This is to prevent execution of <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
+        This is to prevent <link linkend="repmgr-daemon-unpause"><command>repmgr daemon 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.
@@ -175,23 +168,17 @@ NOTICE: node 3 (node3) unpaused</programlisting>
       The pause state of each node will be stored over a PostgreSQL restart.
     </para>
 
-    <para>
-      <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link> and
-      <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link> can be
-      executed even if &repmgrd; is not running; in this case,
-      &repmgrd; will start up in whichever pause state has been set.
-    </para>
+	<para>
+	  <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
+	  <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link> can be
+	  executed even if &repmgrd; is not running; in this case,
+	  &repmgrd; will start up in whichever pause state has been set.
+	</para>
     <note>
       <para>
-	    <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link> and
-	    <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
-	    <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.
+		<link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link> and
+		<link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
+		<emphasis>do not</emphasis> stop/start &repmgrd;.
       </para>
     </note>
   </sect2>

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-service-pause"><command>single command</command></link>
+           <link linkend="repmgr-daemon-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>
-    [2019-08-15 07:14:42] [NOTICE] repmgrd (repmgrd 5.0) starting up
-    [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-12.pid
-    [2019-08-15 07:14:42] [NOTICE] starting monitoring of node "node2" (ID: 2)
-    [2019-08-15 07:14:42] [INFO] monitoring connection to upstream node "node1" (ID: 1)</programlisting>
+    [2019-03-15 06:32:05] [NOTICE] repmgrd (repmgrd 4.3) starting up
+    [2019-03-15 06:32:05] [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
+    [2019-03-15 06:32:05] [NOTICE] starting monitoring of node "node2" (ID: 2)
+    [2019-03-15 06:32:05] [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  | 2019-08-15 07:14:42 | 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  | 2019-08-15 07:14:39 | monitoring cluster primary "node1" (ID: 1)</programlisting>
+     3       | node3 | repmgrd_start | t  | 2019-03-14 04:17:30 | 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)
+     1       | node1 | repmgrd_start | t  | 2019-03-14 04:04:31 | 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>
-    [2019-08-15 07:27:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
-    [2019-08-15 07:27:50] [INFO] checking state of node 1, 1 of 3 attempts
-    [2019-08-15 07:27:50] [INFO] sleeping 5 seconds until next reconnection attempt
-    [2019-08-15 07:27:55] [INFO] checking state of node 1, 2 of 3 attempts
-    [2019-08-15 07:27:55] [INFO] sleeping 5 seconds until next reconnection attempt
-    [2019-08-15 07:28:00] [INFO] checking state of node 1, 3 of 3 attempts
-    [2019-08-15 07:28:00] [WARNING] unable to reconnect to node 1 after 3 attempts
-    [2019-08-15 07:28:00] [INFO] primary and this node have the same location ("default")
-    [2019-08-15 07:28:00] [INFO] local node's last receive lsn: 0/900CBF8
-    [2019-08-15 07:28:00] [INFO] node 3 last saw primary node 12 second(s) ago
-    [2019-08-15 07:28:00] [INFO] last receive LSN for sibling node "node3" (ID: 3) is: 0/900CBF8
-    [2019-08-15 07:28:00] [INFO] node "node3" (ID: 3) has same LSN as current candidate "node2" (ID: 2)
-    [2019-08-15 07:28:00] [INFO] visible nodes: 2; total nodes: 2; no nodes have seen the primary within the last 4 seconds
-    [2019-08-15 07:28:00] [NOTICE] promotion candidate is "node2" (ID: 2)
-    [2019-08-15 07:28:00] [NOTICE] this node is the winner, will now promote itself and inform other nodes
-    [2019-08-15 07:28:00] [INFO] promote_command is:
-      "/usr/pgsql-12/bin/repmgr -f /etc/repmgr/12/repmgr.conf standby promote"
+    [2019-03-15 06:37:50] [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
+    [2019-03-15 06:37:50] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-03-15 06:37:55] [INFO] checking state of node 1, 2 of 3 attempts
+    [2019-03-15 06:37:55] [INFO] sleeping 5 seconds until next reconnection attempt
+    [2019-03-15 06:38:00] [INFO] checking state of node 1, 3 of 3 attempts
+    [2019-03-15 06:38:00] [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")
+    [2019-03-15 06:38:00] [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
+    [2019-03-15 06:38:00] [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)
+    [2019-03-15 06:38:00] [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)
+    [2019-03-15 06:38:00] [NOTICE] this node is the winner, will now promote itself and inform other nodes
+    [2019-03-15 06:38:00] [INFO] promote_command is:
+      "/usr/pgsql-11/bin/repmgr -f /etc/repmgr/11/repmgr.conf standby promote"
     NOTICE: promoting standby to primary
-    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote"
+    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/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
-    [2019-08-15 07:28:01] [INFO] 3 followers to notify
-    [2019-08-15 07:28:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
+    [2019-03-15 06:38:01] [INFO] 3 followers to notify
+    [2019-03-15 06:38:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
     INFO:  node 3 received notification to follow node 2
-    [2019-08-15 07:28:01] [INFO] switching to primary monitoring mode
-    [2019-08-15 07:28:01] [NOTICE] monitoring cluster primary "node2" (ID: 2)</programlisting>
+    [2019-03-15 06:38:01] [INFO] switching to primary monitoring mode
+    [2019-03-15 06:38:01] [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  | 2019-08-15 07:38:03 | node 3 now following new upstream node 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  | 2019-08-15 07:38:01 | monitoring cluster primary "node2" (ID: 2)
-     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  | 2019-08-15 07:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
+     3       | node3 | repmgrd_failover_follow    | t  | 2019-03-15 06:38:03 | 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)
+     2       | node2 | repmgrd_reload             | t  | 2019-03-15 06:38:01 | 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 | standby_promote            | t  | 2019-03-15 06:38:01 | server "node2" (ID: 2) was successfully promoted to primary</programlisting>
  </para>
 
   </sect1>

doc/switchover.xml

@@ -186,7 +186,6 @@
       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>
 
@@ -318,9 +317,7 @@
   </para>
   <para>
     If &repmgrd; is in use, it's worth double-checking that
-    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>).
+    all nodes are unpaused by executing <command><link linkend="repmgr-daemon-status">repmgr-daemon-status</link></command>.
   </para>
 
    <note>

doc/upgrading-repmgr.xml

@@ -201,13 +201,9 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 	</para>
 	<tip>
 	  <para>
-        If the &repmgr; upgrade requires a PostgreSQL restart, combine the &repmgr; upgrade
-        with a PostgreSQL minor version upgrade, which will require a restart in any case.
-      </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.
+		If the &repmgr; upgrade requires a PostgreSQL restart, combine the &repmgr; upgrade
+		with a PostgreSQL minor version upgrade, which will require a restart in any case.
+		New PostgreSQL minor version are usually released every couple of months.
 	  </para>
 	</tip>
   </sect2>
@@ -220,9 +216,7 @@ 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-service-status">repmgr service status</link></command>
-      (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-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-daemon-status">repmgr daemon status</link></command>
       command (on any node) to show an overview of the status of &repmgrd; on all nodes.
     </para>
   </sect2>
@@ -269,33 +263,10 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
   <tip>
 	<para>
 	  Use <command><link linkend="repmgr-node-check">repmgr node check</link></command>
-	  to determine which replication slots need to be recreated.
+	  to determine which replacation 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>
 
 
@@ -446,13 +417,13 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
      <programlisting>
     $ ./convert-config.pl /etc/repmgr.conf
     node_id=2
-    node_name='node2'
-    conninfo='host=node2 dbname=repmgr user=repmgr connect_timeout=2'
+    node_name=node2
+    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'
-    log_level='INFO'
-    pg_basebackup_options='--no-slot'
-    data_directory=''</programlisting>
+    rsync_options=--exclude=postgresql.local.conf --archive
+    log_level=INFO
+    pg_basebackup_options=--no-slot
+    data_directory=</programlisting>
     </para>
     <para>
       The converted file is printed to <literal>STDOUT</literal> and the original file is not
@@ -461,7 +432,8 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     <para>
       Please note that the the conversion script will add an empty
       placeholder parameter for <varname>data_directory</varname>, which
-      is a required parameter from &repmgr; 4.
+      is a required parameter in repmgr4 and which <emphasis>must</emphasis>
+      be provided.
     </para>
    </sect3>
   </sect2>

errcode.h

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

expected/repmgr_extension.out

@@ -32,6 +32,18 @@ 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 
 -----------------
@@ -80,3 +92,9 @@ 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, 2010-2020
+ * 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

log.h

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

repmgr--4.4--5.0.sql

@@ -1,5 +0,0 @@
--- 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--5.0--5.1.sql

@@ -1,5 +0,0 @@
--- 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

@@ -1,214 +0,0 @@
--- 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.sql

@@ -1,214 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
-
-CREATE TABLE repmgr.nodes (
-  node_id          INTEGER     PRIMARY KEY,
-  upstream_node_id INTEGER     NULL REFERENCES nodes (node_id) DEFERRABLE,
-  active           BOOLEAN     NOT NULL DEFAULT TRUE,
-  node_name        TEXT        NOT NULL,
-  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
-  location         TEXT        NOT NULL DEFAULT 'default',
-  priority         INT         NOT NULL DEFAULT 100,
-  conninfo         TEXT        NOT NULL,
-  repluser         VARCHAR(63) NOT NULL,
-  slot_name        TEXT        NULL,
-  config_file      TEXT        NOT NULL
-);
-
-CREATE TABLE repmgr.events (
-  node_id          INTEGER NOT NULL,
-  event            TEXT NOT NULL,
-  successful       BOOLEAN NOT NULL DEFAULT TRUE,
-  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
-  details          TEXT NULL
-);
-
-DO $repmgr$
-DECLARE
-  DECLARE server_version_num INT;
-BEGIN
-  SELECT setting
-    FROM pg_catalog.pg_settings
-   WHERE name = 'server_version_num'
-    INTO server_version_num;
-  IF server_version_num >= 90400 THEN
-    EXECUTE $repmgr_func$
-CREATE TABLE repmgr.monitoring_history (
-  primary_node_id                INTEGER NOT NULL,
-  standby_node_id                INTEGER NOT NULL,
-  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
-  last_apply_time                TIMESTAMP WITH TIME ZONE,
-  last_wal_primary_location      PG_LSN NOT NULL,
-  last_wal_standby_location      PG_LSN,
-  replication_lag                BIGINT NOT NULL,
-  apply_lag                      BIGINT NOT NULL
-)
-    $repmgr_func$;
-  ELSE
-    EXECUTE $repmgr_func$
-CREATE TABLE repmgr.monitoring_history (
-  primary_node_id                INTEGER NOT NULL,
-  standby_node_id                INTEGER NOT NULL,
-  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
-  last_apply_time                TIMESTAMP WITH TIME ZONE,
-  last_wal_primary_location      TEXT NOT NULL,
-  last_wal_standby_location      TEXT,
-  replication_lag                BIGINT NOT NULL,
-  apply_lag                      BIGINT NOT NULL
-)
-    $repmgr_func$;
-  END IF;
-END$repmgr$;
-
-
-
-CREATE INDEX idx_monitoring_history_time
-          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
-
-CREATE VIEW repmgr.show_nodes AS
-   SELECT n.node_id,
-          n.node_name,
-          n.active,
-          n.upstream_node_id,
-          un.node_name AS upstream_node_name,
-          n.type,
-          n.priority,
-          n.conninfo
-     FROM repmgr.nodes n
-LEFT JOIN repmgr.nodes un
-       ON un.node_id = n.upstream_node_id;
-
-CREATE TABLE repmgr.voting_term (
-  term INT NOT NULL
-);
-
-CREATE UNIQUE INDEX voting_term_restrict
-ON repmgr.voting_term ((TRUE));
-
-CREATE RULE voting_term_delete AS
-   ON DELETE TO repmgr.voting_term
-   DO INSTEAD NOTHING;
-
-
-/* ================= */
-/* repmgrd functions */
-/* ================= */
-
-/* monitoring functions */
-
-CREATE FUNCTION set_local_node_id(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_local_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_local_node_id()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_local_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION standby_set_last_updated()
-  RETURNS TIMESTAMP WITH TIME ZONE
-  AS 'MODULE_PATHNAME', 'standby_set_last_updated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION standby_get_last_updated()
-  RETURNS TIMESTAMP WITH TIME ZONE
-  AS 'MODULE_PATHNAME', 'standby_get_last_updated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_upstream_last_seen(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_upstream_last_seen()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_upstream_node_id()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_upstream_node_id(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
-  LANGUAGE C STRICT;
-
-/* failover functions */
-
-CREATE FUNCTION notify_follow_primary(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'notify_follow_primary'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_new_primary()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_new_primary'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION reset_voting_status()
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'reset_voting_status'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_repmgrd_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_repmgrd_pidfile()
-  RETURNS TEXT
-  AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
-  LANGUAGE C CALLED ON NULL INPUT;
-
-CREATE FUNCTION repmgrd_is_running()
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'repmgrd_is_running'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION repmgrd_pause(BOOL)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'repmgrd_pause'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION repmgrd_is_paused()
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_wal_receiver_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_wal_receiver_pid'
-  LANGUAGE C STRICT;
-
-
-
-
-/* views */
-
-CREATE VIEW repmgr.replication_status AS
-  SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
- 	     n.type AS node_type, n.active, last_monitor_time,
-         CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
-         m.last_wal_standby_location,
-         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
-         CASE WHEN n.type='standby' THEN
-           CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
-           ELSE NULL
-         END AS replication_time_lag,
-         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
-         AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
-    FROM repmgr.monitoring_history m
-    JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
-   WHERE (m.standby_node_id, m.last_monitor_time) IN (
-	          SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
-			    FROM repmgr.monitoring_history m1 GROUP BY 1
-         );
-

repmgr--unpackaged--5.1.sql

@@ -1,265 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
-
--- extract the current schema name
--- NOTE: this assumes there will be only one schema matching 'repmgr_%';
--- user is responsible for ensuring this is the case
-
-CREATE TEMPORARY TABLE repmgr_old_schema (schema_name TEXT);
-INSERT INTO repmgr_old_schema (schema_name)
-SELECT nspname AS schema_name
-  FROM pg_catalog.pg_namespace
- WHERE nspname LIKE 'repmgr_%'
- LIMIT 1;
-
--- move old objects into new schema
-DO $repmgr$
-DECLARE
-  old_schema TEXT;
-BEGIN
-  SELECT schema_name FROM repmgr_old_schema
-    INTO old_schema;
-  EXECUTE format('ALTER TABLE %I.repl_nodes SET SCHEMA repmgr', old_schema);
-  EXECUTE format('ALTER TABLE %I.repl_events SET SCHEMA repmgr', old_schema);
-  EXECUTE format('ALTER TABLE %I.repl_monitor SET SCHEMA repmgr', old_schema);
-  EXECUTE format('DROP VIEW IF EXISTS %I.repl_show_nodes', old_schema);
-  EXECUTE format('DROP VIEW IF EXISTS %I.repl_status', old_schema);
-END$repmgr$;
-
--- convert "repmgr_$cluster.repl_nodes" to "repmgr.nodes"
-CREATE TABLE repmgr.nodes (
-  node_id          INTEGER     PRIMARY KEY,
-  upstream_node_id INTEGER     NULL REFERENCES repmgr.nodes (node_id) DEFERRABLE,
-  active           BOOLEAN     NOT NULL DEFAULT TRUE,
-  node_name        TEXT        NOT NULL,
-  type             TEXT        NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
-  location         TEXT        NOT NULL DEFAULT 'default',
-  priority         INT         NOT NULL DEFAULT 100,
-  conninfo         TEXT        NOT NULL,
-  repluser         VARCHAR(63) NOT NULL,
-  slot_name        TEXT        NULL,
-  config_file      TEXT        NOT NULL
-);
-
-INSERT INTO repmgr.nodes
-  (node_id, upstream_node_id, active, node_name, type, location, priority, conninfo, repluser, slot_name, config_file)
-SELECT id, upstream_node_id, active, name,
-       CASE WHEN type = 'master' THEN 'primary' ELSE type END,
-       'default', priority, conninfo, 'unknown', slot_name, 'unknown'
-  FROM repmgr.repl_nodes
- ORDER BY id;
-
-
--- convert "repmgr_$cluster.repl_event" to "event"
-
-ALTER TABLE repmgr.repl_events RENAME TO events;
-
--- create new table "repmgr.voting_term"
-CREATE TABLE repmgr.voting_term (
-  term INT NOT NULL
-);
-
-CREATE UNIQUE INDEX voting_term_restrict
-ON repmgr.voting_term ((TRUE));
-
-CREATE RULE voting_term_delete AS
-   ON DELETE TO repmgr.voting_term
-   DO INSTEAD NOTHING;
-
-INSERT INTO repmgr.voting_term (term) VALUES (1);
-
-
--- convert "repmgr_$cluster.repl_monitor" to "monitoring_history"
-
-
-DO $repmgr$
-DECLARE
-  DECLARE server_version_num INT;
-BEGIN
-  SELECT setting
-    FROM pg_catalog.pg_settings
-   WHERE name = 'server_version_num'
-    INTO server_version_num;
-  IF server_version_num >= 90400 THEN
-    EXECUTE $repmgr_func$
-CREATE TABLE repmgr.monitoring_history (
-  primary_node_id                INTEGER NOT NULL,
-  standby_node_id                INTEGER NOT NULL,
-  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
-  last_apply_time                TIMESTAMP WITH TIME ZONE,
-  last_wal_primary_location      PG_LSN NOT NULL,
-  last_wal_standby_location      PG_LSN,
-  replication_lag                BIGINT NOT NULL,
-  apply_lag                      BIGINT NOT NULL
-)
-    $repmgr_func$;
-    INSERT INTO repmgr.monitoring_history
-      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
-    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location::pg_lsn, last_wal_standby_location::pg_lsn, replication_lag, apply_lag
-      FROM repmgr.repl_monitor;
-  ELSE
-    EXECUTE $repmgr_func$
-CREATE TABLE repmgr.monitoring_history (
-  primary_node_id                INTEGER NOT NULL,
-  standby_node_id                INTEGER NOT NULL,
-  last_monitor_time              TIMESTAMP WITH TIME ZONE NOT NULL,
-  last_apply_time                TIMESTAMP WITH TIME ZONE,
-  last_wal_primary_location      TEXT NOT NULL,
-  last_wal_standby_location      TEXT,
-  replication_lag                BIGINT NOT NULL,
-  apply_lag                      BIGINT NOT NULL
-)
-    $repmgr_func$;
-    INSERT INTO repmgr.monitoring_history
-      (primary_node_id, standby_node_id, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag)
-    SELECT primary_node, standby_node, last_monitor_time,  last_apply_time, last_wal_primary_location, last_wal_standby_location, replication_lag, apply_lag
-      FROM repmgr.repl_monitor;
-
-  END IF;
-END$repmgr$;
-
-CREATE INDEX idx_monitoring_history_time
-          ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
-
-CREATE VIEW repmgr.show_nodes AS
-   SELECT n.node_id,
-          n.node_name,
-          n.active,
-          n.upstream_node_id,
-          un.node_name AS upstream_node_name,
-          n.type,
-          n.priority,
-          n.conninfo
-     FROM repmgr.nodes n
-LEFT JOIN repmgr.nodes un
-       ON un.node_id = n.upstream_node_id;
-
-
-/* ================= */
-/* repmgrd functions */
-/* ================= */
-
-/* monitoring functions */
-
-CREATE FUNCTION set_local_node_id(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_local_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_local_node_id()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_local_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION standby_set_last_updated()
-  RETURNS TIMESTAMP WITH TIME ZONE
-  AS 'MODULE_PATHNAME', 'standby_set_last_updated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION standby_get_last_updated()
-  RETURNS TIMESTAMP WITH TIME ZONE
-  AS 'MODULE_PATHNAME', 'standby_get_last_updated'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_upstream_last_seen(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_upstream_last_seen()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_last_seen'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_upstream_node_id()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_upstream_node_id'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_upstream_node_id(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_upstream_node_id'
-  LANGUAGE C STRICT;
-
-/* failover functions */
-
-CREATE FUNCTION notify_follow_primary(INT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'notify_follow_primary'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_new_primary()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_new_primary'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION reset_voting_status()
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'reset_voting_status'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_repmgrd_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_repmgrd_pidfile()
-  RETURNS TEXT
-  AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
-  LANGUAGE C CALLED ON NULL INPUT;
-
-CREATE FUNCTION repmgrd_is_running()
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'repmgrd_is_running'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION repmgrd_pause(BOOL)
-  RETURNS VOID
-  AS 'MODULE_PATHNAME', 'repmgrd_pause'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION repmgrd_is_paused()
-  RETURNS BOOL
-  AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
-  LANGUAGE C STRICT;
-
-CREATE FUNCTION get_wal_receiver_pid()
-  RETURNS INT
-  AS 'MODULE_PATHNAME', 'get_wal_receiver_pid'
-  LANGUAGE C STRICT;
-
-
-/* views */
-
-CREATE VIEW repmgr.replication_status AS
-  SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
- 	     n.type AS node_type, n.active, last_monitor_time,
-         CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
-         m.last_wal_standby_location,
-         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
-         CASE WHEN n.type='standby' THEN
-           CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
-           ELSE NULL
-         END AS replication_time_lag,
-         CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
-         AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
-    FROM repmgr.monitoring_history m
-    JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
-   WHERE (m.standby_node_id, m.last_monitor_time) IN (
-	          SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
-			    FROM repmgr.monitoring_history m1 GROUP BY 1
-         );
-
-
-
-/* drop old tables */
-DROP TABLE repmgr.repl_nodes;
-DROP TABLE repmgr.repl_monitor;
-
--- remove temporary table
-DROP TABLE repmgr_old_schema;

repmgr-action-bdr.c

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

repmgr-action-bdr.h

@@ -1,6 +1,6 @@
 /*
- * repmgr-action-service.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * repmgr-action-bdr.h
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -16,13 +16,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef _REPMGR_ACTION_SERVICE_H_
-#define _REPMGR_ACTION_SERVICE_H_
+#ifndef _REPMGR_ACTION_BDR_H_
+#define _REPMGR_ACTION_BDR_H_
+
+extern void do_bdr_register(void);
+extern void do_bdr_unregister(void);
+
+extern void do_bdr_help(void);
 
 
-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
+#endif							/* _REPMGR_ACTION_BDR_H_ */

repmgr-action-cluster.c

@@ -3,7 +3,7 @@
  *
  * Implements cluster information actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -55,8 +55,10 @@ 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);
 
 /*
@@ -65,8 +67,6 @@ 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)
@@ -206,8 +206,7 @@ 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_str);
+			cell->node_info->replication_info->timeline_id = get_node_timeline(cell->node_info->conn);
 		}
 
 		initPQExpBuffer(&node_status);
@@ -245,13 +244,18 @@ do_cluster_show(void)
 
 		headers_show[SHOW_LOCATION].cur_length = strlen(cell->node_info->location);
 
-		/* Format timeline ID */
-		if (cell->node_info->type == WITNESS)
+		if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
 		{
-			/* The witness node's timeline ID is irrelevant */
-			strncpy(cell->node_info->replication_info->timeline_id_str, _("n/a"), MAXLEN);
+			/* display "?" */
+			headers_show[SHOW_PRIORITY].cur_length = 1;
+		}
+		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);
 
@@ -318,7 +322,10 @@ do_cluster_show(void)
 
 			if (headers_show[SHOW_TIMELINE_ID].display == true)
 			{
-				printf("| %-*s ", headers_show[SHOW_TIMELINE_ID].max_length, cell->node_info->replication_info->timeline_id_str);
+				if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
+					printf("| %-*c ", headers_show[SHOW_TIMELINE_ID].max_length, '?');
+				else
+					printf("| %-*i ", headers_show[SHOW_TIMELINE_ID].max_length, (int)cell->node_info->replication_info->timeline_id);
 			}
 
 			if (headers_show[SHOW_CONNINFO].display == true)
@@ -336,25 +343,14 @@ do_cluster_show(void)
 	/* 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"));
+		printf(_("\nWARNING: following issues were detected\n"));
 		for (cell = warnings.head; cell; cell = cell->next)
 		{
-			appendPQExpBuffer(&warning,
-							  _("  - %s\n"), cell->string);
+			printf(_("  - %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"));
@@ -536,6 +532,9 @@ 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;
 
@@ -543,7 +542,7 @@ do_cluster_crosscheck(void)
 	int			error_code = SUCCESS;
 	ItemList	warnings = {NULL, NULL};
 
-	n = build_cluster_crosscheck(&cube, &warnings, &error_code);
+	n = build_cluster_crosscheck(&cube, &name_length, &warnings, &error_code);
 
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -577,56 +576,24 @@ do_cluster_crosscheck(void)
 	}
 	else
 	{
-		/* output header contains node name, node ID and one column for each node in the cluster */
-		struct ColHeader *headers_crosscheck = NULL;
-
-		int header_count = n + 2;
-		int header_id = 2;
-
-		headers_crosscheck = palloc0(sizeof(ColHeader) * header_count);
-
-		/* Initialize column headers  */
-		strncpy(headers_crosscheck[0].title, _("Name"), MAXLEN);
-		strncpy(headers_crosscheck[1].title, _("ID"), MAXLEN);
-
+		printf("%*s | Id ", name_length, node_header);
 		for (i = 0; i < n; i++)
-		{
-			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;
-		}
+			printf("| %2d ", cube[i]->node_id);
+		printf("\n");
 
+		for (i = 0; i < name_length; i++)
+			printf("-");
+		printf("-+----");
 		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);
+			printf("+----");
+		printf("\n");
 
 		for (i = 0; i < n; i++)
 		{
 			int			column_node_ix;
 
-			printf(" %-*s | %-*i ",
-				   headers_crosscheck[0].max_length,
+			printf("%*s | %2d ", name_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++)
@@ -634,8 +601,6 @@ 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:
@@ -675,7 +640,7 @@ do_cluster_crosscheck(void)
 						exit(ERR_INTERNAL);
 				}
 
-				printf("| %-*c ", headers_crosscheck[column_node_ix + 2].max_length, c);
+				printf("|  %c ", c);
 			}
 
 			printf("\n");
@@ -737,13 +702,16 @@ 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, &warnings, &error_code);
+	n = build_cluster_matrix(&matrix_rec_list, &name_length, &warnings, &error_code);
 
 	if (runtime_options.output_mode == OM_CSV)
 	{
@@ -766,60 +734,27 @@ do_cluster_matrix()
 	}
 	else
 	{
-		/* output header contains node name, node ID and one column for each node in the cluster */
-		struct ColHeader *headers_matrix = NULL;
+		char		c;
 
-		int header_count = n + 2;
-		int header_id = 2;
+		printf("%*s | Id ", name_length, node_header);
+		for (i = 0; i < n; i++)
+			printf("| %2d ", matrix_rec_list[i]->node_id);
+		printf("\n");
 
-		headers_matrix = palloc0(sizeof(ColHeader) * header_count);
-
-		/* Initialize column headers  */
-		strncpy(headers_matrix[0].title, _("Name"), MAXLEN);
-		strncpy(headers_matrix[1].title, _("ID"), MAXLEN);
+		for (i = 0; i < name_length; i++)
+			printf("-");
+		printf("-+----");
+		for (i = 0; i < n; i++)
+			printf("+----");
+		printf("\n");
 
 		for (i = 0; i < n; i++)
 		{
-			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,
+			printf("%*s | %2d ", name_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:
@@ -837,7 +772,7 @@ do_cluster_matrix()
 						exit(ERR_INTERNAL);
 				}
 
-				printf("| %-*c ", headers_matrix[j + 2].max_length, c);
+				printf("|  %c ", c);
 			}
 			printf("\n");
 		}
@@ -897,7 +832,7 @@ 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, ItemList *warnings, int *error_code)
+build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, ItemList *warnings, int *error_code)
 {
 	PGconn	   *conn = NULL;
 	int			i = 0,
@@ -955,6 +890,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, i
 	/* 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));
@@ -964,6 +900,13 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, i
 				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;
@@ -1044,19 +987,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, i
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " 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, '"');
+							 " cluster show --csv -L NOTICE --terse\"");
 
 		log_verbose(LOG_DEBUG, "build_cluster_matrix(): executing:\n  %s", command.data);
 
@@ -1128,7 +1059,7 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, ItemList *warnings, i
 
 
 static int
-build_cluster_crosscheck(t_node_status_cube ***dest_cube, ItemList *warnings, int *error_code)
+build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, ItemList *warnings, int *error_code)
 {
 	PGconn	   *conn = NULL;
 	int			h,
@@ -1177,12 +1108,20 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, ItemList *warnings, in
 
 	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;
@@ -1236,18 +1175,7 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, ItemList *warnings, in
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " 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");
-		}
+							 " cluster matrix --csv -L NOTICE --terse");
 
 		initPQExpBuffer(&command_output);
 
@@ -1445,10 +1373,6 @@ do_cluster_cleanup(void)
 		log_warning(_("unable to vacuum table \"repmgr.monitoring_history\""));
 		log_detail("%s", PQerrorMessage(primary_conn));
 	}
-	else
-	{
-		log_info(_("vacuum of table \"repmgr.monitoring_history\" completed"));
-	}
 
 	if (runtime_options.keep_history == 0)
 	{

repmgr-action-cluster.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-cluster.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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

repmgr-action-daemon.c

@@ -2,7 +2,7 @@
  * repmgr-action-daemon.c
  *
  * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 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
@@ -26,9 +26,478 @@
 #include "repmgr-client-global.h"
 #include "repmgr-action-daemon.h"
 
-#define REPMGR_SERVICE_STOP_START_WAIT 15
-#define REPMGR_SERVICE_STATUS_START_HINT _("use \"repmgr service status\" to confirm that repmgrd was successfully started")
-#define REPMGR_SERVICE_STATUS_STOP_HINT _("use \"repmgr service status\" to confirm that repmgrd was successfully stopped")
+#define REPMGR_DAEMON_STOP_START_WAIT 15
+#define REPMGR_DAEMON_STATUS_START_HINT _("use \"repmgr daemon 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")
+
+/*
+ * 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)
@@ -114,12 +583,12 @@ do_daemon_start(void)
 
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
-		log_hint(REPMGR_SERVICE_STATUS_START_HINT);
+		log_hint(REPMGR_DAEMON_STATUS_START_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
+		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
 
 		if (runtime_options.wait_provided)
 			timeout = runtime_options.wait;
@@ -129,7 +598,7 @@ do_daemon_start(void)
 		if (PQstatus(conn) != CONNECTION_OK)
 		{
 			log_notice(_("unable to connect to local node"));
-			log_hint(REPMGR_SERVICE_STATUS_START_HINT);
+			log_hint(REPMGR_DAEMON_STATUS_START_HINT);
 			exit(ERR_DB_CONN);
 		}
 
@@ -147,7 +616,7 @@ do_daemon_start(void)
 				PQfinish(conn);
 				log_error(_("repmgrd does not appear to have started after %i seconds"),
 						  timeout);
-				log_hint(REPMGR_SERVICE_STATUS_START_HINT);
+				log_hint(REPMGR_DAEMON_STATUS_START_HINT);
 				exit(ERR_REPMGRD_SERVICE);
 			}
 
@@ -243,12 +712,12 @@ void do_daemon_stop(void)
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
 		if (have_db_connection == true)
-			log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
+			log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
+		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
 		/*
 		 *
 		 */
@@ -263,7 +732,7 @@ void do_daemon_stop(void)
 			log_warning(_("unable to determine repmgrd PID"));
 
 			if (have_db_connection == true)
-				log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
+				log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
 
 			exit(ERR_REPMGRD_SERVICE);
 		}
@@ -295,7 +764,7 @@ void do_daemon_stop(void)
 						  timeout);
 
 				if (have_db_connection == true)
-					log_hint(REPMGR_SERVICE_STATUS_START_HINT);
+					log_hint(REPMGR_DAEMON_STATUS_START_HINT);
 
 				exit(ERR_REPMGRD_SERVICE);
 			}
@@ -314,29 +783,53 @@ 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 on the local node\n"));
+	printf(_("  \"daemon start\" attempts to start repmgrd\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_SERVICE_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_DAEMON_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 on the local node\n"));
+	printf(_("  \"daemon stop\" attempts to stop repmgrd\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_SERVICE_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_DAEMON_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"));
+	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, 2010-2020
+ * 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
@@ -19,6 +19,10 @@
 #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.c

@@ -3,7 +3,7 @@
  *
  * Implements actions available for any kind of node
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -43,14 +43,13 @@ static void _do_node_restore_config(void);
 
 static void do_node_check_replication_connection(void);
 static CheckStatus do_node_check_archive_ready(PGconn *conn, OutputMode mode, CheckStatusList *list_output);
-static CheckStatus do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
-static CheckStatus do_node_check_upstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
+static CheckStatus do_node_check_downstream(PGconn *conn, OutputMode mode, CheckStatusList *list_output);
 static CheckStatus do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_role(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
-static CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
+
 /*
  * NODE STATUS
  *
@@ -160,6 +159,7 @@ do_node_status(void)
 								 _("- node is registered as standby but running as primary"));
 			}
 			break;
+		case BDR:
 		default:
 			break;
 	}
@@ -204,16 +204,7 @@ do_node_status(void)
 
 		if (enabled == false && recovery_type == RECTYPE_STANDBY)
 		{
-			if (PQserverVersion(conn) >= 90500)
-			{
-				appendPQExpBufferStr(&archiving_status,
-									 " (on standbys \"archive_mode\" must be set to \"always\" to be effective)");
-			}
-			else
-			{
-				appendPQExpBufferStr(&archiving_status,
-									 " (\"archive_mode\" has no effect on standbys)");
-			}
+			appendPQExpBufferStr(&archiving_status, " (on standbys \"archive_mode\" must be set to \"always\" to be effective)");
 		}
 
 		key_value_list_set(&node_status,
@@ -303,7 +294,7 @@ do_node_status(void)
 				continue;
 			}
 
-			if (is_downstream_node_attached(conn, node_cell->node_info->node_name, NULL) != NODE_ATTACHED)
+			if (is_downstream_node_attached(conn, node_cell->node_info->node_name) != NODE_ATTACHED)
 			{
 				missing_nodes_count++;
 				item_list_append_format(&missing_nodes,
@@ -726,49 +717,10 @@ do_node_check(void)
 		exit(SUCCESS);
 	}
 
-
-	if (config_file_options.conninfo[0] != '\0')
-	{
-		t_conninfo_param_list node_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
-		char	   *errmsg = NULL;
-		bool		parse_success = false;
-
-		initialize_conninfo_params(&node_conninfo, false);
-
-		parse_success = parse_conninfo_string(config_file_options.conninfo,
-											  &node_conninfo,
-											  &errmsg, false);
-
-		if (parse_success == false)
-		{
-			log_error(_("unable to parse conninfo string \"%s\" for local node"),
-					  config_file_options.conninfo);
-			log_detail("%s", errmsg);
-
-			exit(ERR_BAD_CONFIG);
-		}
-
-		/*
-		 * If --superuser option provided, attempt to connect as the specified user
-		 */
-
-		if (runtime_options.superuser[0] != '\0')
-		{
-			conn = establish_db_connection_with_replacement_param(
-				config_file_options.conninfo,
-				"user",
-				runtime_options.superuser,
-				true);
-		}
-		else
-		{
-			conn = establish_db_connection_by_params(&node_conninfo, true);
-		}
-	}
+	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);
-	}
 
 	if (get_node_record(conn, config_file_options.node_id, &node_info) != RECORD_FOUND)
 	{
@@ -792,26 +744,16 @@ do_node_check(void)
 		exit(return_code);
 	}
 
-	if (runtime_options.upstream == true)
-	{
-		return_code = do_node_check_upstream(conn,
-											 runtime_options.output_mode,
-											 &node_info,
-											 NULL);
-		PQfinish(conn);
-		exit(return_code);
-	}
-
 	if (runtime_options.downstream == true)
 	{
 		return_code = do_node_check_downstream(conn,
 											   runtime_options.output_mode,
-											   &node_info,
 											   NULL);
 		PQfinish(conn);
 		exit(return_code);
 	}
 
+
 	if (runtime_options.replication_lag == true)
 	{
 		return_code = do_node_check_replication_lag(conn,
@@ -862,16 +804,6 @@ do_node_check(void)
 		exit(return_code);
 	}
 
-	if (runtime_options.replication_config_owner == true)
-	{
-		return_code = do_node_check_replication_config_owner(conn,
-													   runtime_options.output_mode,
-													   &node_info,
-													   NULL);
-		PQfinish(conn);
-		exit(return_code);
-	}
-
 
 	if (runtime_options.output_mode == OM_NAGIOS)
 	{
@@ -895,10 +827,7 @@ do_node_check(void)
 	if (do_node_check_archive_ready(conn, runtime_options.output_mode, &status_list) != CHECK_STATUS_OK)
 		issue_detected = true;
 
-	if (do_node_check_upstream(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
-		issue_detected = true;
-
-	if (do_node_check_downstream(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
+	if (do_node_check_downstream(conn, runtime_options.output_mode, &status_list) != CHECK_STATUS_OK)
 		issue_detected = true;
 
 	if (do_node_check_slots(conn, runtime_options.output_mode, &node_info, &status_list) != CHECK_STATUS_OK)
@@ -980,6 +909,7 @@ do_node_check_replication_connection(void)
 	PGconn *repl_conn = NULL;
 	t_node_info node_record = T_NODE_INFO_INITIALIZER;
 	RecordStatus record_status = RECORD_NOT_FOUND;
+	t_conninfo_param_list remote_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PQExpBufferData output;
 
 
@@ -1009,8 +939,17 @@ do_node_check_replication_connection(void)
 		return;
 	}
 
-	repl_conn = establish_replication_connection_from_conninfo(node_record.conninfo,
-															   node_record.repluser);
+	initialize_conninfo_params(&remote_conninfo, false);
+	parse_conninfo_string(node_record.conninfo, &remote_conninfo, NULL, false);
+
+	if (strcmp(param_get(&remote_conninfo, "user"), node_record.repluser) != 0)
+	{
+		param_set(&remote_conninfo, "user", node_record.repluser);
+		param_set(&remote_conninfo, "dbname", "replication");
+	}
+	param_set(&remote_conninfo, "replication", "1");
+
+	repl_conn = establish_db_connection_by_params(&remote_conninfo, false);
 
 	if (PQstatus(repl_conn) != CONNECTION_OK)
 	{
@@ -1193,7 +1132,7 @@ do_node_check_archive_ready(PGconn *conn, OutputMode mode, CheckStatusList *list
 
 
 static CheckStatus
-do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
+do_node_check_downstream(PGconn *conn, OutputMode mode, CheckStatusList *list_output)
 {
 	NodeInfoList downstream_nodes = T_NODE_INFO_LIST_INITIALIZER;
 	NodeInfoListCell *cell = NULL;
@@ -1227,7 +1166,7 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info,
 			continue;
 		}
 
-		if (is_downstream_node_attached(conn, cell->node_info->node_name, NULL) != NODE_ATTACHED)
+		if (is_downstream_node_attached(conn, cell->node_info->node_name) != NODE_ATTACHED)
 		{
 			missing_nodes_count++;
 			item_list_append_format(&missing_nodes,
@@ -1244,13 +1183,7 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info,
 		}
 	}
 
-	if (node_info->type == WITNESS)
-	{
-		/* witness is not connecting to any upstream */
-		appendPQExpBufferStr(&details,
-							 _("N/A - node is a witness"));
-	}
-	else if (missing_nodes_count == 0)
+	if (missing_nodes_count == 0)
 	{
 		if (expected_nodes_count == 0)
 			appendPQExpBufferStr(&details,
@@ -1365,104 +1298,6 @@ do_node_check_downstream(PGconn *conn, OutputMode mode, t_node_info *node_info,
 }
 
 
-static CheckStatus
-do_node_check_upstream(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
-{
-	PGconn	   *upstream_conn = NULL;
-	t_node_info upstream_node_info = T_NODE_INFO_INITIALIZER;
-	PQExpBufferData details;
-
-	CheckStatus status = CHECK_STATUS_OK;
-
-	if (mode == OM_CSV && list_output == NULL)
-	{
-		log_error(_("--csv output not provided with --upstream option"));
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	initPQExpBuffer(&details);
-
-	if (node_info->type == WITNESS)
-	{
-		/* witness is not connecting to any upstream */
-		appendPQExpBufferStr(&details,
-							 _("N/A - node is a witness"));
-	}
-	else if (get_node_record(conn, node_info->upstream_node_id, &upstream_node_info) != RECORD_FOUND)
-	{
-		if (get_recovery_type(conn) == RECTYPE_STANDBY)
-		{
-			appendPQExpBuffer(&details,
-							  _("node \"%s\" (ID: %i) is a standby but no upstream record found"),
-							  node_info->node_name,
-							  node_info->node_id);
-			status = CHECK_STATUS_CRITICAL;
-		}
-		else
-		{
-			appendPQExpBufferStr(&details,
-								 _("N/A - node is primary"));
-		}
-	}
-	else
-	{
-		upstream_conn = establish_db_connection(upstream_node_info.conninfo, true);
-
-		/* check our node is connected */
-		if (is_downstream_node_attached(upstream_conn, config_file_options.node_name, NULL) != NODE_ATTACHED)
-		{
-			appendPQExpBuffer(&details,
-							  _("node \"%s\" (ID: %i) is not attached to expected upstream node \"%s\" (ID: %i)"),
-							  node_info->node_name,
-							  node_info->node_id,
-							  upstream_node_info.node_name,
-							  upstream_node_info.node_id);
-			status = CHECK_STATUS_CRITICAL;
-		}
-		else
-		{
-			appendPQExpBuffer(&details,
-							  _("node \"%s\" (ID: %i) is attached to expected upstream node \"%s\" (ID: %i)"),
-							  node_info->node_name,
-							  node_info->node_id,
-							  upstream_node_info.node_name,
-							  upstream_node_info.node_id);
-		}
-	}
-
-	switch (mode)
-	{
-		case OM_NAGIOS:
-			{
-				printf("REPMGR_UPSTREAM_SERVER %s: %s | ",
-					   output_check_status(status),
-					   details.data);
-			}
-		case OM_TEXT:
-			if (list_output != NULL)
-			{
-				check_status_list_set(list_output,
-									  "Upstream connection",
-									  status,
-									  details.data);
-			}
-			else
-			{
-				printf("%s (%s)\n",
-					   output_check_status(status),
-					   details.data);
-			}
-		default:
-			break;
-	}
-
-	termPQExpBuffer(&details);
-
-	return status;
-}
-
-
 static CheckStatus
 do_node_check_replication_lag(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
 {
@@ -1717,6 +1552,34 @@ do_node_check_role(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckS
 									 _("node is witness"));
 			}
 			break;
+		case BDR:
+			{
+				PQExpBufferData output;
+
+				initPQExpBuffer(&output);
+				if (is_bdr_db(conn, &output) == false)
+				{
+					status = CHECK_STATUS_CRITICAL;
+					appendPQExpBufferStr(&details,
+										 output.data);
+				}
+				termPQExpBuffer(&output);
+
+				if (status == CHECK_STATUS_OK)
+				{
+					if (is_active_bdr_node(conn, node_info->node_name) == false)
+					{
+						status = CHECK_STATUS_CRITICAL;
+						appendPQExpBufferStr(&details,
+											 _("node is not an active BDR node"));
+					}
+					else
+					{
+						appendPQExpBufferStr(&details,
+											 _("node is an active BDR node"));
+					}
+				}
+			}
 		default:
 			break;
 	}
@@ -1965,12 +1828,12 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	}
 
 	initPQExpBuffer(&details);
-
 	/*
 	 * Check actual data directory matches that in repmgr.conf; note this requires
 	 * a superuser connection
 	 */
-	if (connection_has_pg_settings(conn) == true)
+
+	if (is_superuser_connection(conn, NULL) == true)
 	{
 		/* we expect to have a database connection */
 		if (get_pg_setting(conn, "data_directory", actual_data_directory) == false)
@@ -2012,9 +1875,10 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 		{
 			log_info(_("connection is not a superuser connection, falling back to simple check"));
 
+			/* XXX add -S/--superuser option */
 			if (PQserverVersion(conn) >= 100000)
 			{
-				log_hint(_("provide a superuser with -S/--superuser, or add the \"%s\" user to role \"pg_read_all_settings\" or \"pg_monitor\""),
+				log_hint(_("add the \"%s\" user to group \"pg_read_all_settings\""),
 						   PQuser(conn));
 			}
 		}
@@ -2035,12 +1899,6 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 
 			status = CHECK_STATUS_CRITICAL;
 		}
-		else
-		{
-			appendPQExpBuffer(&details,
-							  _("configured \"data_directory\" is \"%s\""),
-							  config_file_options.data_directory);
-		}
 	}
 
 	switch (mode)
@@ -2084,40 +1942,6 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	return status;
 }
 
-/*
- * This is not included in the general list output
- */
-static
-CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
-{
-	CheckStatus status = CHECK_STATUS_OK;
-
-	PQExpBufferData errmsg;
-	PQExpBufferData details;
-
-	if (mode != OM_OPTFORMAT)
-	{
-		log_error(_("--replication-config-owner option can only be used with --optformat"));
-		PQfinish(conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	initPQExpBuffer(&errmsg);
-	initPQExpBuffer(&details);
-
-	if (check_replication_config_owner(PQserverVersion(conn),
-									   config_file_options.data_directory,
-									   &errmsg, &details) == false)
-	{
-		status = CHECK_STATUS_CRITICAL;
-	}
-
-	printf("--replication-config-owner=%s\n",
-		   output_check_status(status));
-
-	return status;
-}
-
 
 void
 do_node_service(void)
@@ -2157,62 +1981,26 @@ do_node_service(void)
 
 	if ((action == ACTION_STOP || action == ACTION_RESTART) && runtime_options.checkpoint == true)
 	{
-		PGconn	   *conn = NULL;
-
-		if (config_file_options.conninfo[0] != '\0')
+		if (runtime_options.dry_run == true)
 		{
-			/*
-			 * If --superuser option provided, attempt to connect as the specified user
-			 */
-			if (runtime_options.superuser[0] != '\0')
-			{
-				conn = establish_db_connection_with_replacement_param(
-					config_file_options.conninfo,
-					"user",
-					runtime_options.superuser,
-					true);
-			}
-			else
-			{
+			log_info(_("a CHECKPOINT would be issued here"));
+		}
+		else
+		{
+			PGconn	   *conn = NULL;
+
+			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);
-		}
-
-		if (is_superuser_connection(conn, NULL) == false)
-		{
-			if (runtime_options.dry_run == true)
-			{
-				log_warning(_("a CHECKPOINT would be issued here but no superuser connection is available"));
-			}
 			else
-			{
-				log_warning(_("a superuser connection is required to issue a CHECKPOINT"));
-			}
+				conn = establish_db_connection_by_params(&source_conninfo, true);
 
-			log_hint(_("provide a superuser with -S/--superuser"));
+			log_notice(_("issuing CHECKPOINT"));
+
+			/* check superuser conn! */
+			checkpoint(conn);
+
+			PQfinish(conn);
 		}
-		else
-		{
-			if (runtime_options.dry_run == true)
-			{
-				log_info(_("a CHECKPOINT would be issued here"));
-			}
-			else
-			{
-
-				log_notice(_("issuing CHECKPOINT on node \"%s\" (ID: %i) "),
-						   config_file_options.node_name,
-						   config_file_options.node_id);
-
-				checkpoint(conn);
-			}
-		}
-
-		PQfinish(conn);
 	}
 
 	get_server_action(action, command, data_dir);
@@ -2359,7 +2147,6 @@ do_node_rejoin(void)
 	PQExpBufferData follow_output;
 	struct stat statbuf;
 	t_node_info primary_node_record = T_NODE_INFO_INITIALIZER;
-	t_node_info local_node_record = T_NODE_INFO_INITIALIZER;
 
 	bool		success = true;
 	int			follow_error_code = SUCCESS;
@@ -2470,36 +2257,6 @@ do_node_rejoin(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/*
-	 * Fetch the local node record - we'll need this later, and it acts as an
-	 * additional sanity-check that the node is known to the primary.
-	 */
-	if (get_node_record(primary_conn, config_file_options.node_id, &local_node_record) != RECORD_FOUND)
-	{
-		log_error(_("unable to retrieve node record for the local node"));
-		log_hint(_("check the local node is registered with the current primary \"%s\" (ID: %i)"),
-				 primary_node_record.node_name,
-				 primary_node_record.node_id);
-
-		PQfinish(primary_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-	/*
-	 * Sanity-check replication slot availability
-	 */
-	if (config_file_options.use_replication_slots)
-	{
-		bool slots_available = check_replication_slots_available(primary_node_record.node_id,
-																 primary_conn);
-		if (slots_available == false)
-		{
-			PQfinish(primary_conn);
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-
-
 	/*
 	 * sanity-check that it will actually be possible to stream from the new upstream
 	 */
@@ -2777,41 +2534,86 @@ do_node_rejoin(void)
 	 */
 	if (runtime_options.no_wait == false)
 	{
-		standy_join_status join_success = check_standby_join(primary_conn,
-															 &primary_node_record,
-															 &local_node_record);
+		int i;
+
+		for (i = 0; i < config_file_options.standby_reconnect_timeout; i++)
+		{
+			if (is_server_available(config_file_options.conninfo))
+			{
+				log_verbose(LOG_INFO, _("demoted primary is pingable"));
+				break;
+			}
+
+			if (i % 5 == 0)
+			{
+				log_verbose(LOG_INFO, _("waiting for node %i to respond to pings; %i of max %i attempts"),
+							config_file_options.node_id,
+							i + 1, config_file_options.node_rejoin_timeout);
+			}
+			else
+			{
+				log_debug("sleeping 1 second waiting for node %i to respond to pings; %i of max %i attempts",
+						  config_file_options.node_id,
+						  i + 1, config_file_options.node_rejoin_timeout);
+			}
+
+			sleep(1);
+		}
+
+		for (;  i < config_file_options.node_rejoin_timeout; i++)
+		{
+			NodeAttached node_attached = is_downstream_node_attached(primary_conn,
+														config_file_options.node_name);
+
+			if (node_attached == NODE_ATTACHED)
+			{
+				log_verbose(LOG_INFO, _("node %i has attached to its upstream node"),
+							config_file_options.node_id);
+				break;
+			}
+
+			if (i % 5 == 0)
+			{
+				log_info(_("waiting for node \"%s\" (ID: %i) to connect to new primary; %i of max %i attempts"),
+						 config_file_options.node_name,
+						 config_file_options.node_id,
+						 i + 1, config_file_options.node_rejoin_timeout);
+				log_detail(_("checking for record in node \"%s\"'s \"pg_stat_replication\" table where \"application_name\" is \"%s\""),
+						   primary_node_record.node_name,
+						   config_file_options.node_name);
+			}
+			else
+			{
+				log_debug("sleeping 1 second waiting for node %i to connect to new primary; %i of max %i attempts",
+						  config_file_options.node_id,
+						  i + 1, config_file_options.node_rejoin_timeout);
+			}
+
+			sleep(1);
+		}
 
 		create_event_notification(primary_conn,
 								  &config_file_options,
 								  config_file_options.node_id,
 								  "node_rejoin",
-								  join_success == JOIN_SUCCESS ? true : false,
+								  success,
 								  follow_output.data);
 
-		if (join_success != JOIN_SUCCESS)
+		if (success == false)
 		{
 			termPQExpBuffer(&follow_output);
 			log_error(_("NODE REJOIN failed"));
-
-			if (join_success == JOIN_FAIL_NO_PING) {
-				log_detail(_("local node \"%s\" did not become available start after %i seconds"),
-						   config_file_options.node_name,
-						   config_file_options.node_rejoin_timeout);
-			}
-			else {
-				log_detail(_("no active record for local node \"%s\" found in node \"%s\"'s \"pg_stat_replication\" table"),
-						   config_file_options.node_name,
-						   primary_node_record.node_name);
-			}
+			log_detail(_("no record for local node \"%s\" found in node \"%s\"'s \"pg_stat_replication\" table"),
+					   config_file_options.node_name,
+					   primary_node_record.node_name);
 			log_hint(_("check the PostgreSQL log on the local node"));
-
 			exit(ERR_REJOIN_FAIL);
 		}
 	}
 	else
 	{
 		/* -W/--no-wait provided - check once */
-		NodeAttached node_attached = is_downstream_node_attached(primary_conn, config_file_options.node_name, NULL);
+		NodeAttached node_attached = is_downstream_node_attached(primary_conn, config_file_options.node_name);
 		if (node_attached == NODE_ATTACHED)
 			success = true;
 	}
@@ -3371,22 +3173,17 @@ do_node_help(void)
 	puts("");
 	printf(_("  Configuration file required, runs on local node only.\n"));
 	puts("");
-	printf(_("  Connection options:\n"));
-	printf(_("    -S, --superuser=USERNAME  superuser to use, if repmgr user is not superuser\n"));
-	puts("");
-	printf(_("  Output options:\n"));
-	printf(_("    --csv                     emit output as CSV (not available for individual check output)\n"));
-	printf(_("    --nagios                  emit output in Nagios format (individual check output only)\n"));
+	printf(_("    --csv                   emit output as CSV (not available for individual check output)\n"));
+	printf(_("    --nagios                emit output in Nagios format (individual check output only)\n"));
 	puts("");
 	printf(_("  Following options check an individual status:\n"));
-	printf(_("    --archive-ready           number of WAL files ready for archiving\n"));
-	printf(_("    --downstream              whether all downstream nodes are connected\n"));
-	printf(_("    --uptream                 whether the node is connected to its upstream\n"));
-	printf(_("    --replication-lag         replication lag in seconds (standbys only)\n"));
-	printf(_("    --role                    check node has expected role\n"));
-	printf(_("    --slots                   check for inactive replication slots\n"));
-	printf(_("    --missing-slots           check for missing replication slots\n"));
-	printf(_("    --data-directory-config   check repmgr's data directory configuration\n"));
+	printf(_("    --archive-ready         number of WAL files ready for archiving\n"));
+	printf(_("    --downstream            whether all downstream nodes are connected\n"));
+	printf(_("    --replication-lag       replication lag in seconds (standbys only)\n"));
+	printf(_("    --role                  check node has expected role\n"));
+	printf(_("    --slots                 check for inactive replication slots\n"));
+	printf(_("    --missing-slots         check for missing replication slots\n"));
+	printf(_("    --data-directory-config check repmgr's data directory configuration\n"));
 
 	puts("");
 
@@ -3405,7 +3202,7 @@ do_node_help(void)
 			 "                            after executing \"pg_rewind\"\n"));
 	printf(_("    --config-archive-dir    directory to temporarily store retained configuration files\n" \
 			 "                              (default: /tmp)\n"));
-	printf(_("    -W, --no-wait           don't wait for the node to rejoin cluster\n"));
+	printf(_("    -W/--no-wait            don't wait for the node to rejoin cluster\n"));
 	puts("");
 
 	printf(_("NODE SERVICE\n"));
@@ -3415,11 +3212,10 @@ do_node_help(void)
 	puts("");
 	printf(_("  Configuration file required, runs on local node only.\n"));
 	puts("");
-	printf(_("    --dry-run                 show what action would be performed, but don't execute it\n"));
-	printf(_("    --action                  action to perform (one of \"start\", \"stop\", \"restart\" or \"reload\")\n"));
-	printf(_("    --list-actions            show what command would be performed for each action\n"));
-	printf(_("    --checkpoint              issue a CHECKPOINT before stopping or restarting the node\n"));
-	printf(_("    -S, --superuser=USERNAME  superuser to use, if repmgr user is not superuser\n"));
+	printf(_("    --dry-run             show what action would be performed, but don't execute it\n"));
+	printf(_("    --action              action to perform (one of \"start\", \"stop\", \"restart\" or \"reload\")\n"));
+	printf(_("    --list-actions        show what command would be performed for each action\n"));
+	printf(_("    --checkpoint          issue a CHECKPOINT before stopping or restarting the node\n"));
 	puts("");
 
 

repmgr-action-node.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-node.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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

repmgr-action-primary.c

@@ -3,7 +3,7 @@
  *
  * Implements primary actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -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("current active primary node ID is %i", current_primary_id);
+		log_debug("XXX %i", current_primary_id);
 		primary_conn = establish_primary_db_connection(conn, false);
 
 		if (PQstatus(primary_conn) == CONNECTION_OK)

repmgr-action-primary.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-primary.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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

repmgr-action-service.c

@@ -1,546 +0,0 @@
-/*
- * repmgr-action-service.c
- *
- * Implements repmgrd actions for the repmgr command line utility
- * Copyright (c) 2ndQuadrant, 2010-2020
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <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("");
-}

repmgr-action-standby.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-standby.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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

repmgr-action-witness.c

@@ -3,7 +3,7 @@
  *
  * Implements witness actions for the repmgr command line utility
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -74,6 +74,18 @@ do_witness_register(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+	/* check that witness node is not a BDR node */
+	if (is_bdr_db_quiet(witness_conn) == true)
+	{
+		log_error(_("witness node is a BDR node"));
+		log_hint(_("a witness node cannot be configured for a BDR cluster"));
+
+		PQfinish(witness_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+
 	/* connect to primary with provided parameters */
 	log_info(_("connecting to primary node"));
 
@@ -182,6 +194,19 @@ do_witness_register(void)
 		}
 	}
 
+	/* check that primary node is not a BDR node */
+	if (is_bdr_db_quiet(primary_conn) == true)
+	{
+		log_error(_("primary node is a BDR node"));
+		log_hint(_("a witness node cannot be configured for a BDR cluster"));
+
+		PQfinish(witness_conn);
+		PQfinish(primary_conn);
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+
 	/* create repmgr extension, if does not exist */
 	if (runtime_options.dry_run == false &&  !create_repmgr_extension(witness_conn))
 	{

repmgr-action-witness.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-action-witness.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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

repmgr-client-global.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client-global.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -28,8 +28,6 @@
 /* default value for "cluster event --limit"*/
 #define CLUSTER_EVENT_LIMIT 20
 
-
-
 typedef struct
 {
 	/* configuration metadata */
@@ -87,7 +85,7 @@ typedef struct
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
-	bool		replication_conf_only;
+	bool		recovery_conf_only;
 
 	/* "standby clone"/"standby follow" options */
 	int			upstream_node_id;
@@ -111,7 +109,6 @@ typedef struct
 	/* "node check" options */
 	bool		archive_ready;
 	bool		downstream;
-	bool		upstream;
 	bool		replication_lag;
 	bool		role;
 	bool		slots;
@@ -119,7 +116,6 @@ typedef struct
 	bool		has_passfile;
 	bool		replication_connection;
 	bool		data_directory_config;
-	bool		replication_config_owner;
 
 	/* "node rejoin" options */
 	char		config_files[MAXLEN];
@@ -172,7 +168,7 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, false, false, false,	false, false, false, \
+		false, false, false, false, false, false, false, false,	false, \
 		/* "node rejoin" options */ \
 		"", \
 		/* "node service" options */ \
@@ -205,23 +201,6 @@ typedef enum
 } t_server_action;
 
 
-typedef enum
-{
-	USER_TYPE_UNKNOWN = -1,
-	REPMGR_USER,
-	REPLICATION_USER_OPT,
-	REPLICATION_USER_NODE,
-	SUPERUSER
-} t_user_type;
-
-typedef enum
-{
-	JOIN_SUCCESS,
-	JOIN_FAIL_NO_PING,
-	JOIN_FAIL_NO_REPLICATION
-} standy_join_status;
-
-
 typedef struct ColHeader
 {
 	char		title[MAXLEN];
@@ -276,17 +255,10 @@ extern void get_node_config_directory(char *config_dir_buf);
 extern void get_node_data_directory(char *data_dir_buf);
 extern void init_node_record(t_node_info *node_record);
 extern bool can_use_pg_rewind(PGconn *conn, const char *data_directory, PQExpBufferData *reason);
+extern void drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);
 
-extern bool create_replication_slot(PGconn *conn, char *slot_name, t_node_info *upstream_node_record, PQExpBufferData *error_msg);
-extern bool drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name);
-
-extern standy_join_status check_standby_join(PGconn *primary_conn, t_node_info *primary_node_record, t_node_info *standby_node_record);
-extern bool check_replication_slots_available(int node_id, PGconn* conn);
 extern bool check_node_can_attach(TimeLineID local_tli, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_record, bool is_rejoin);
-extern bool check_replication_config_owner(int pg_version, const char *data_directory, PQExpBufferData *error_msg, PQExpBufferData *detail_msg);
-
 extern void check_shared_library(PGconn *conn);
 extern bool is_repmgrd_running(PGconn *conn);
-extern int parse_repmgr_version(const char *version_string);
 
 #endif							/* _REPMGR_CLIENT_GLOBAL_H_ */

repmgr-client.h

@@ -1,6 +1,6 @@
 /*
  * repmgr-client.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -34,21 +34,23 @@
 #define STANDBY_SWITCHOVER	   8
 #define WITNESS_REGISTER       9
 #define WITNESS_UNREGISTER     10
-#define NODE_STATUS			   11
-#define NODE_CHECK			   12
-#define NODE_SERVICE		   13
-#define NODE_REJOIN            14
-#define NODE_CONTROL           15
-#define CLUSTER_SHOW		   16
-#define CLUSTER_CLEANUP		   17
-#define CLUSTER_MATRIX		   18
-#define CLUSTER_CROSSCHECK	   19
-#define CLUSTER_EVENT		   20
-#define SERVICE_STATUS		   21
-#define SERVICE_PAUSE		   22
-#define SERVICE_UNPAUSE		   23
-#define DAEMON_START 		   24
-#define DAEMON_STOP 		   25
+#define BDR_REGISTER		   11
+#define BDR_UNREGISTER		   12
+#define NODE_STATUS			   13
+#define NODE_CHECK			   14
+#define NODE_SERVICE		   15
+#define NODE_REJOIN            16
+#define NODE_CONTROL           17
+#define CLUSTER_SHOW		   18
+#define CLUSTER_CLEANUP		   19
+#define CLUSTER_MATRIX		   20
+#define CLUSTER_CROSSCHECK	   21
+#define CLUSTER_EVENT		   22
+#define DAEMON_STATUS		   23
+#define DAEMON_PAUSE		   24
+#define DAEMON_UNPAUSE		   25
+#define DAEMON_START 		   26
+#define DAEMON_STOP 		   27
 
 /* command line options without short versions */
 #define OPT_HELP						   1001
@@ -81,29 +83,31 @@
 #define OPT_SIBLINGS_FOLLOW				   1028
 #define OPT_ROLE						   1029
 #define OPT_DOWNSTREAM					   1030
-#define OPT_UPSTREAM					   1031
-#define OPT_SLOTS						   1032
-#define OPT_CONFIG_ARCHIVE_DIR			   1033
-#define OPT_HAS_PASSFILE				   1034
-#define OPT_WAIT_START					   1035
-#define OPT_REPL_CONN					   1036
-#define OPT_REMOTE_NODE_ID				   1037
-#define OPT_REPLICATION_CONF_ONLY		   1038
-#define OPT_NO_WAIT						   1039
-#define OPT_MISSING_SLOTS				   1040
-#define OPT_REPMGRD_NO_PAUSE			   1041
-#define OPT_VERSION_NUMBER				   1042
-#define OPT_DATA_DIRECTORY_CONFIG		   1043
-#define OPT_COMPACT						   1044
-#define OPT_DISABLE_WAL_RECEIVER		   1045
-#define OPT_ENABLE_WAL_RECEIVER			   1046
-#define OPT_DETAIL						   1047
-#define OPT_REPMGRD_FORCE_UNPAUSE		   1048
-#define OPT_REPLICATION_CONFIG_OWNER	   1049
+#define OPT_SLOTS						   1031
+#define OPT_CONFIG_ARCHIVE_DIR			   1032
+#define OPT_HAS_PASSFILE				   1033
+#define OPT_WAIT_START					   1034
+#define OPT_REPL_CONN					   1035
+#define OPT_REMOTE_NODE_ID				   1036
+#define OPT_RECOVERY_CONF_ONLY			   1037
+#define OPT_NO_WAIT						   1038
+#define OPT_MISSING_SLOTS				   1039
+#define OPT_REPMGRD_NO_PAUSE			   1040
+#define OPT_VERSION_NUMBER				   1041
+#define OPT_DATA_DIRECTORY_CONFIG		   1042
+#define OPT_COMPACT						   1043
+#define OPT_DISABLE_WAL_RECEIVER		   1044
+#define OPT_ENABLE_WAL_RECEIVER			   1045
+#define OPT_DETAIL						   1046
+#define OPT_REPMGRD_FORCE_UNPAUSE		   1047
 
+/* deprecated since 3.3 */
+#define OPT_DATA_DIR						999
+#define OPT_NO_CONNINFO_PASSWORD			998
+#define OPT_RECOVERY_MIN_APPLY_DELAY		997
 /* deprecated since 4.0 */
-#define OPT_CHECK_UPSTREAM_CONFIG		    999
-#define OPT_NODE						    998
+#define OPT_CHECK_UPSTREAM_CONFIG		    996
+#define OPT_NODE						    995
 
 
 static struct option long_options[] =
@@ -153,13 +157,12 @@ static struct option long_options[] =
 	{"copy-external-config-files", optional_argument, NULL, OPT_COPY_EXTERNAL_CONFIG_FILES},
 	{"fast-checkpoint", no_argument, NULL, 'c'},
 	{"no-upstream-connection", no_argument, NULL, OPT_NO_UPSTREAM_CONNECTION},
+	{"recovery-min-apply-delay", required_argument, NULL, OPT_RECOVERY_MIN_APPLY_DELAY},
 	{"replication-user", required_argument, NULL, OPT_REPLICATION_USER},
 	{"upstream-conninfo", required_argument, NULL, OPT_UPSTREAM_CONNINFO},
 	{"upstream-node-id", required_argument, NULL, OPT_UPSTREAM_NODE_ID},
 	{"without-barman", no_argument, NULL, OPT_WITHOUT_BARMAN},
-	{"replication-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
-	/* deprecate this once Pg11 and earlier are unsupported */
-	{"recovery-conf-only", no_argument, NULL, OPT_REPLICATION_CONF_ONLY},
+	{"recovery-conf-only", no_argument, NULL, OPT_RECOVERY_CONF_ONLY},
 
 /* "standby register" options */
 	{"wait-start", required_argument, NULL, OPT_WAIT_START},
@@ -180,7 +183,6 @@ static struct option long_options[] =
 /* "node check" options */
 	{"archive-ready", no_argument, NULL, OPT_ARCHIVE_READY},
 	{"downstream", no_argument, NULL, OPT_DOWNSTREAM},
-	{"upstream", no_argument, NULL, OPT_UPSTREAM},
 	{"replication-lag", no_argument, NULL, OPT_REPLICATION_LAG},
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
@@ -188,7 +190,6 @@ static struct option long_options[] =
 	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
 	{"replication-connection", no_argument, NULL, OPT_REPL_CONN},
 	{"data-directory-config", no_argument, NULL, OPT_DATA_DIRECTORY_CONFIG},
-	{"replication-config-owner", no_argument, NULL, OPT_REPLICATION_CONFIG_OWNER},
 
 /* "node rejoin" options */
 	{"config-files", required_argument, NULL, OPT_CONFIG_FILES},
@@ -214,8 +215,11 @@ static struct option long_options[] =
 
 /* deprecated */
 	{"check-upstream-config", no_argument, NULL, OPT_CHECK_UPSTREAM_CONFIG},
+	{"no-conninfo-password", no_argument, NULL, OPT_NO_CONNINFO_PASSWORD},
 	/* previously used by "standby switchover" */
 	{"remote-config-file", required_argument, NULL, 'C'},
+	/* legacy alias for -D/--pgdata */
+	{"data-dir", required_argument, NULL, OPT_DATA_DIR},
 	/* replaced by --node-id */
 	{"node", required_argument, NULL, OPT_NODE},
 

repmgr.c

@@ -1,7 +1,7 @@
 /*
  * repmgr.c - repmgr extension
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * This is the actual extension code; see repmgr-client.c for the code which
  * generates the repmgr binary
@@ -84,6 +84,8 @@ typedef struct repmgrdSharedState
 	int			current_electoral_term;
 	int			candidate_node_id;
 	bool		follow_new_primary;
+	/* BDR failover */
+	int			bdr_failover_handler;
 } repmgrdSharedState;
 
 static repmgrdSharedState *shared_state = NULL;
@@ -129,6 +131,12 @@ PG_FUNCTION_INFO_V1(get_new_primary);
 Datum		reset_voting_status(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(reset_voting_status);
 
+Datum		am_bdr_failover_handler(PG_FUNCTION_ARGS);
+PG_FUNCTION_INFO_V1(am_bdr_failover_handler);
+
+Datum		unset_bdr_failover_handler(PG_FUNCTION_ARGS);
+PG_FUNCTION_INFO_V1(unset_bdr_failover_handler);
+
 Datum		set_repmgrd_pid(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(set_repmgrd_pid);
 
@@ -233,6 +241,7 @@ repmgr_shmem_startup(void)
 		shared_state->voting_status = VS_NO_VOTE;
 		shared_state->candidate_node_id = UNKNOWN_NODE_ID;
 		shared_state->follow_new_primary = false;
+		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
 	}
 
 	LWLockRelease(AddinShmemInitLock);
@@ -562,6 +571,63 @@ reset_voting_status(PG_FUNCTION_ARGS)
 }
 
 
+Datum
+am_bdr_failover_handler(PG_FUNCTION_ARGS)
+{
+	int			node_id = UNKNOWN_NODE_ID;
+	bool		am_handler = false;
+
+	if (!shared_state)
+		PG_RETURN_NULL();
+
+	if (PG_ARGISNULL(0))
+		PG_RETURN_NULL();
+
+	node_id = PG_GETARG_INT32(0);
+
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+
+	if (shared_state->bdr_failover_handler == UNKNOWN_NODE_ID)
+	{
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+		shared_state->bdr_failover_handler = node_id;
+		am_handler = true;
+	}
+	else if (shared_state->bdr_failover_handler == node_id)
+	{
+		am_handler = true;
+	}
+
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_BOOL(am_handler);
+}
+
+
+Datum
+unset_bdr_failover_handler(PG_FUNCTION_ARGS)
+{
+	if (!shared_state)
+		PG_RETURN_NULL();
+
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+
+	/* only do something if local_node_id is initialised */
+	if (shared_state->local_node_id != UNKNOWN_NODE_ID)
+	{
+		LWLockRelease(shared_state->lock);
+		LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+
+		shared_state->bdr_failover_handler = UNKNOWN_NODE_ID;
+	}
+
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_VOID();
+}
+
+
 /*
  * Returns the repmgrd pid; or NULL if none set; or -1 if set but repmgrd
  * process not running (TODO!)
@@ -636,7 +702,7 @@ set_repmgrd_pid(PG_FUNCTION_ARGS)
 	shared_state->repmgrd_pid = repmgrd_pid;
 	memset(shared_state->repmgrd_pidfile, 0, MAXPGPATH);
 
-	if (repmgrd_pidfile != NULL)
+	if(repmgrd_pidfile != NULL)
 	{
 		strncpy(shared_state->repmgrd_pidfile, repmgrd_pidfile, MAXPGPATH);
 	}

repmgr.conf.sample

@@ -6,13 +6,12 @@
 # is noted for each item. Where no default value is shown, the
 # parameter will be treated as empty or false.
 #
-# repmgr parses its configuration file in the same way as PostgreSQL itself
-# does. In particular, strings must be enclosed in single quotes (although
-# simple identifiers may be provided as-is).
+# IMPORTANT: string values can be provided as-is, or enclosed in single quotes
+# (but not double-quotes, which will be interpreted as part of the string),
+# e.g.:
 #
-# For details on the configuration file format see the documentation at:
-#
-#   https://repmgr.org/docs/current/configuration-file.html#CONFIGURATION-FILE-FORMAT
+#  node_name=foo
+#  node_name = 'foo'
 #
 # =============================================================================
 # Required configuration items
@@ -21,7 +20,7 @@
 # repmgr and repmgrd require the following items to be explicitly configured.
 
 
-#node_id=			 # A unique integer greater than zero
+#node_id=    	     	     	 # A unique integer greater than zero
 #node_name=''			 # An arbitrary (but unique) string; we recommend
 				 # using the server's hostname or another identifier
 				 # unambiguously associated with the server to avoid
@@ -29,8 +28,8 @@
 				 # node's current role, e.g. 'primary' or 'standby1',
 				 # as roles can change and it will be confusing if
 				 # the current primary is called 'standby1'.
-				 # The string's maximum length is 63 characters and it should
-				 # contain only printable ASCII characters.
+                                 # The string's maximum length is 63 characters and it should
+                                 # contain only printable ASCII characters.
 
 #conninfo=''			 # Database connection information as a conninfo string.
 				 # All servers in the cluster must be able to connect to
@@ -71,12 +70,13 @@
 #replication_user='repmgr'	 # User to make replication connections with, if not set
 				 #  defaults to the user defined in "conninfo".
 
-#replication_type='physical'	 # Must "physical" (the default).
+#replication_type=physical	 # Must be one of "physical" or "bdr".
+				 # NOTE: "bdr" can only be used with BDR 2.x
 
-#location='default'		 # An arbitrary string defining the location of the node; this
+#location=default		 # An arbitrary string defining the location of the node; this
 				 # is used during failover to check visibility of the
 				 # current primary node. For further details see:
-				 #   https://repmgr.org/docs/current/repmgrd-network-split.html
+                                 #   https://repmgr.org/docs/current/repmgrd-network-split.html
 
 #use_replication_slots=no	 # whether to use physical replication slots
 				 # NOTE: when using replication slots,
@@ -101,10 +101,10 @@
 # This is mainly intended for those cases when `repmgr` is executed directly
 # by `repmgrd`.
 
-#log_level='INFO'		 # Log level: possible values are DEBUG, INFO, NOTICE,
+#log_level=INFO			 # Log level: possible values are DEBUG, INFO, NOTICE,
 				 # WARNING, ERROR, ALERT, CRIT or EMERG
 
-#log_facility='STDERR'		 # Logging facility: possible values are STDERR, or for
+#log_facility=STDERR		 # Logging facility: possible values are STDERR, or for
 				 # syslog integration, one of LOCAL0, LOCAL1, ..., LOCAL7, USER
 
 #log_file=''			 # STDERR can be redirected to an arbitrary file
@@ -159,13 +159,12 @@
 
 #repmgr_bindir=''			# Path to repmgr binary directory (location of the repmgr
 					# binary. Only needed if the repmgr executable is not in
-					# the system $PATH or the path defined in "pg_bindir".
+                                        # the system $PATH or the path defined in "pg_bindir".
 
-#use_primary_conninfo_password=false	# explicitly set "password" in "primary_conninfo"
-					# using the value contained in the environment variable
-					# PGPASSWORD
+#use_primary_conninfo_password=false	# explicitly set "password" in recovery.conf's
+					# "primary_conninfo" parameter using the value contained
+					# in the environment variable PGPASSWORD
 #passfile=''				# path to .pgpass file to include in "primary_conninfo"
-
 #------------------------------------------------------------------------------
 # external command options
 #------------------------------------------------------------------------------
@@ -179,7 +178,7 @@
 #   rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
 #   ssh_options=-o "StrictHostKeyChecking no"
 
-#pg_ctl_options=''			# Options to append to "pg_ctl"
+#pg_ctl_options='' 			# Options to append to "pg_ctl"
 #pg_basebackup_options=''		# Options to append to "pg_basebackup"
 #rsync_options=''			# Options to append to "rsync"
 ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
@@ -194,22 +193,22 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #
 # Examples:
 #
-#   tablespace_mapping='/path/to/original/tablespace=/path/to/new/tablespace'
+#   tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
 #   restore_command = 'cp /path/to/archived/wals/%f %p'
 
-#tablespace_mapping=''			# Tablespaces can be remapped from one
+#tablespace_mapping=''	  		# Tablespaces can be remapped from one
 					# file system location to another. This
 					# parameter can be provided multiple times.
 
-#restore_command=''			# This will be included in the recovery configuration
-					# generated by repmgr.
+#restore_command=''			# This will be placed in the recovery.conf file generated
+					# by repmgr.
 
-#archive_cleanup_command=''		# This will be included in the recovery configuration
-					# generated by repmgr. Note we recommend using Barman for
-					# managing WAL archives (see: https://www.pgbarman.org )
+#archive_cleanup_command=''		# This will be placed in the recovery.conf file generated
+					# by repmgr. Note we recommend using Barman for managing
+					# WAL archives (see: https://www.pgbarman.org )
 
-#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" will be set to
-					# this value (PostgreSQL 9.4 and later).
+#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" in recovery.conf
+					# will be set to this value (PostgreSQL 9.4 and later).
 
 
 #------------------------------------------------------------------------------
@@ -282,31 +281,31 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # These settings are only applied when repmgrd is running. Values shown
 # are defaults.
 
-#failover='manual'			# one of 'automatic', 'manual'.
+#failover=manual			# one of 'automatic', 'manual'.
 					# determines what action to take in the event of upstream failure
 					#
 					# 'automatic': repmgrd will automatically attempt to promote the
 					#    node or follow the new upstream node
 					# 'manual': repmgrd will take no action and the node will require
 					#    manual attention to reattach it to replication
+					# (does not apply to BDR mode)
 
 #priority=100				# indicates a preferred priority for promoting nodes;
 					# a value of zero prevents the node being promoted to primary
 					# (default: 100)
 
 #connection_check_type=ping		# How to check availability of the upstream node; valid options:
-					#  'ping': use PQping() to check if the node is accepting connections
-					#  'connection': execute a throwaway query on the current connection
-					#  'query': execute an SQL statement on the node via the existing connection
+                                        #  'ping': use PQping() to check if the node is accepting connections
+                                        #  'connection': execute a throwaway query on the current connection
 #reconnect_attempts=6			# Number of attempts which will be made to reconnect to an unreachable
 					# primary (or other upstream node)
 #reconnect_interval=10			# Interval between attempts to reconnect to an unreachable
 					# primary (or other upstream node)
-#promote_command=''			# command repmgrd executes when promoting a new primary; use something like:
+#promote_command=			# command repmgrd executes when promoting a new primary; use something like:
 					#
 					#     repmgr standby promote -f /etc/repmgr.conf
 					#
-#follow_command=''			# command repmgrd executes when instructing a standby to follow a new primary;
+#follow_command=			# command repmgrd executes when instructing a standby to follow a new primary;
 					# use something like:
 					#
 					#     repmgr standby follow -f /etc/repmgr.conf -W --upstream-node-id=%n
@@ -318,8 +317,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for the the local node to restart and become ready to accept connections after
 					# executing "follow_command" (defaults to the value set in "standby_reconnect_timeout")
 
-#monitoring_history=no			# Whether to write monitoring data to the "montoring_history" table
-#monitor_interval_secs=2		# Interval (in seconds) at which to write monitoring data
+#monitoring_history=no                  # Whether to write monitoring data to the "montoring_history" table
+#monitor_interval_secs=2                # Interval (in seconds) at which to write monitoring data
 #degraded_monitoring_timeout=-1		# Interval (in seconds) after which repmgrd will terminate if the
 					# server(s) being monitored are no longer available. -1 (default)
 					# disables the timeout completely.
@@ -340,7 +339,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# WAL receivers
 #primary_visibility_consensus=false	# If "true", only continue with failover if no standbys have seen
 					# the primary node recently. *Must* be the same on all nodes.
-#failover_validation_command=''		# Script to execute for an external mechanism to validate the failover
+#failover_validation_command=		# Script to execute for an external mechanism to validate the failover
 					# decision made by repmgrd. One or both of the following parameter placeholders
 					# should be provided, which will be replaced by repmgrd with the appropriate
 					# value: %n (node_id), %a (node_name). *Must* be the same on all nodes.
@@ -348,14 +347,14 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# an error, pause the specified amount of seconds before rerunning the election.
 					#
 					# The following items are relevant for repmgrd running on the primary,
-					# and will be ignored on non-primary nodes
+                                        # and will be ignored on non-primary nodes
 #child_nodes_check_interval=5		# Interval (in seconds) to check for attached child nodes (standbys)
 #child_nodes_connected_min_count=-1	# Minimum number of child nodes which must remain connected, otherwise
 					# disconnection command will be triggered
 #child_nodes_disconnect_min_count=-1	# Minimum number of disconnected child nodes required to execute disconnection command
 					# (ignored if "child_nodes_connected_min_count" set)
 #child_nodes_disconnect_timeout=30	# Interval between child node disconnection and disconnection command execution
-#child_nodes_disconnect_command=''	# Command to execute if child node disconnection detected
+#child_nodes_disconnect_command=	# Command to execute if child node disconnection detected
 
 #------------------------------------------------------------------------------
 # service control commands
@@ -373,7 +372,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # NOTE: These commands must be runnable on remote nodes as well for switchover
 # to function correctly.
 #
-# If you use sudo, the user repmgr runs as (usually 'postgres')	 must have
+# If you use sudo, the user repmgr runs as (usually 'postgres')  must have
 # passwordless sudo access to execute the command.
 #
 # For example, to use systemd, you can set
@@ -386,8 +385,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #    # this is required when running sudo over ssh without -t:
 #    Defaults:postgres !requiretty
 #    postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.6, \
-#	/usr/bin/systemctl start postgresql-9.6, \
-#	/usr/bin/systemctl restart postgresql-9.6
+#       /usr/bin/systemctl start postgresql-9.6, \
+#       /usr/bin/systemctl restart postgresql-9.6
 #
 # Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
 #
@@ -403,7 +402,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# for "promote_command"; do not use "repmgr standby promote"
 					# (or a script which executes "repmgr standby promote") here.
 
-# Used by "repmgr service (start|stop)" to control repmgrd
+# Used by "repmgr daemon (start|stop)" to control repmgrd
 #
 #repmgrd_service_start_command = ''
 #repmgrd_service_stop_command = ''
@@ -414,7 +413,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 
 # Various warning/critical thresholds used by "repmgr node check".
 
-#archive_ready_warning=16		# repmgr node check --archive-ready
+#archive_ready_warning=16  	      	# repmgr node check --archive-ready
 #archive_ready_critical=128		#
 					# Numbers of files pending archiving via PostgreSQL's
 					# "archive_command" configuration parameter. If
@@ -435,3 +434,12 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# issues with shutting down the demotion candidate.
 
 
+#------------------------------------------------------------------------------
+# BDR monitoring options
+#------------------------------------------------------------------------------
+
+#bdr_local_monitoring_only=false         # Only monitor the local node; no checks will be
+					 # performed on the other node
+#bdr_recovery_timeout                    # If a BDR node was offline and has become available
+					 # maximum length of time in seconds to wait for the
+					 # node to reconnect to the cluster

repmgr.control

@@ -1,6 +1,6 @@
 # repmgr extension
 comment = 'Replication manager for PostgreSQL'
-default_version = '5.1'
+default_version = '4.4'
 module_pathname = '$libdir/repmgr'
 relocatable = false
 schema = repmgr

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -21,37 +21,6 @@
 #include <config.h>
 #endif
 
-#ifdef vsnprintf
-#undef vsnprintf
-#endif
-#ifdef snprintf
-#undef snprintf
-#endif
-#ifdef vsprintf
-#undef vsprintf
-#endif
-#ifdef sprintf
-#undef sprintf
-#endif
-#ifdef vfprintf
-#undef vfprintf
-#endif
-#ifdef fprintf
-#undef fprintf
-#endif
-#ifdef vprintf
-#undef vprintf
-#endif
-#ifdef printf
-#undef printf
-#endif
-#ifdef strerror
-#undef strerror
-#endif
-#ifdef strerror_r
-#undef strerror_r
-#endif
-
 #ifndef _REPMGR_H_
 #define _REPMGR_H_
 
@@ -78,15 +47,15 @@
 #define MIN_SUPPORTED_VERSION_NUM	90300
 
 #define REPLICATION_TYPE_PHYSICAL 1
+#define REPLICATION_TYPE_BDR	  2
 
 #define UNKNOWN_SERVER_VERSION_NUM -1
-#define UNKNOWN_REPMGR_VERSION_NUM -1
+#define UNKNOWN_BDR_VERSION_NUM -1
 
 #define UNKNOWN_TIMELINE_ID -1
 #define UNKNOWN_SYSTEM_IDENTIFIER 0
 #define UNKNOWN_PID			-1
 #define UNKNOWN_REPLICATION_LAG	-1
-#define UNKNOWN_VALUE		-1
 
 #define NODE_NOT_FOUND		-1
 #define NO_UPSTREAM_NODE	-1
@@ -97,6 +66,8 @@
 #define ARCHIVE_STATUS_DIR_ERROR -1
 #define NO_DEGRADED_MONITORING_ELAPSED -1
 
+#define BDR2_REPLICATION_SET_NAME "repmgr"
+
 /*
  * various default values - ensure repmgr.conf.sample is update
  * if any of these are changed
@@ -110,6 +81,7 @@
 #define DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT 60  /* seconds */
 #define DEFAULT_PRIMARY_FOLLOW_TIMEOUT       60  /* seconds */
 #define DEFAULT_STANDBY_FOLLOW_TIMEOUT       30  /* seconds */
+#define DEFAULT_BDR_RECOVERY_TIMEOUT         30  /* seconds */
 #define DEFAULT_ARCHIVE_READY_WARNING        16  /* WAL files */
 #define DEFAULT_ARCHIVE_READY_CRITICAL       128 /* WAL files */
 #define	DEFAULT_REPLICATION_LAG_WARNING      300 /* seconds */
@@ -136,11 +108,6 @@
 #define RECOVERY_COMMAND_FILE "recovery.conf"
 #endif
 
-#ifndef STANDBY_SIGNAL_FILE
-#define STANDBY_SIGNAL_FILE "standby.signal"
-#define RECOVERY_SIGNAL_FILE "recovery.signal"
-#endif
-
 #ifndef TABLESPACE_MAP
 #define TABLESPACE_MAP "tablespace_map"
 #endif

repmgr_version.h.in

@@ -1,5 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "5.1.0"
-#define REPMGR_VERSION_NUM 50100
-#define REPMGR_RELEASE_DATE "2020-04-13"
-#define PG_ACTUAL_VERSION_NUM 
+#define REPMGR_VERSION "4.4beta2"
+#define REPMGR_VERSION_NUM 40400

repmgrd-bdr.c

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

repmgrd-bdr.h

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

repmgrd-physical.c

@@ -1,7 +1,7 @@
 /*
  * repmgrd-physical.c - physical (streaming) replication functionality for repmgrd
  *
- * Copyright (c) 2ndQuadrant, 2010-2020
+ * 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
@@ -125,8 +125,6 @@ static void clear_child_node_info_list(t_child_node_info_list *nodes);
 static void parse_child_nodes_disconnect_command(char *parsed_command, char *template, int reporting_node_id);
 static void execute_child_nodes_disconnect_command(NodeInfoList *db_child_node_records, t_child_node_info_list *local_child_nodes);
 
-static int try_primary_reconnect(PGconn **conn, PGconn *local_conn, t_node_info *node_info);
-
 void
 handle_sigint_physical(SIGNAL_ARGS)
 {
@@ -1328,7 +1326,6 @@ monitor_streaming_standby(void)
 	 */
 	if (PQstatus(upstream_conn) != CONNECTION_OK)
 	{
-		close_connection(&upstream_conn);
 		log_error(_("unable connect to upstream node (ID: %i), terminating"),
 				  local_node_info.upstream_node_id);
 		log_hint(_("upstream node must be running before repmgrd can start"));
@@ -1340,8 +1337,8 @@ monitor_streaming_standby(void)
 
 	if (upstream_node_info.node_id == local_node_info.node_id)
 	{
-		close_connection(&upstream_conn);
-
+		PQfinish(upstream_conn);
+		upstream_conn = NULL;
 		return;
 	}
 
@@ -1365,8 +1362,6 @@ monitor_streaming_standby(void)
 
 		if (PQstatus(primary_conn) != CONNECTION_OK)
 		{
-			close_connection(&primary_conn);
-
 			log_error(_("unable to connect to primary node"));
 			log_hint(_("ensure the primary node is reachable from this node"));
 
@@ -1443,7 +1438,6 @@ monitor_streaming_standby(void)
 	while (true)
 	{
 		log_verbose(LOG_DEBUG, "checking %s", upstream_node_info.conninfo);
-
 		if (check_upstream_connection(&upstream_conn, upstream_node_info.conninfo) == true)
 		{
 			set_upstream_last_seen(local_conn, upstream_node_info.node_id);
@@ -1503,34 +1497,7 @@ monitor_streaming_standby(void)
 					check_connection(&local_node_info, &local_conn);
 				}
 
-
-				if (upstream_node_info.type == PRIMARY)
-				{
-					primary_node_id = try_primary_reconnect(&upstream_conn, local_conn, &upstream_node_info);
-
-					/*
-					 * We were notified by the the primary during our own reconnection
-					 * retry phase, in which case we can leave the failover process early
-					 * and connect to the new primary.
-					 */
-					if (primary_node_id == ELECTION_RERUN_NOTIFICATION)
-					{
-						if (do_primary_failover() == true)
-						{
-							primary_node_id = get_primary_node_id(local_conn);
-							return;
-						}
-					}
-					if (primary_node_id != UNKNOWN_NODE_ID && primary_node_id != ELECTION_RERUN_NOTIFICATION)
-					{
-						follow_new_primary(primary_node_id);
-						return;
-					}
-				}
-				else
-				{
-					try_reconnect(&upstream_conn, &upstream_node_info);
-				}
+				try_reconnect(&upstream_conn, &upstream_node_info);
 
 				/* Upstream node has recovered - log and continue */
 				if (upstream_node_info.node_status == NODE_STATUS_UP)
@@ -1561,9 +1528,8 @@ monitor_streaming_standby(void)
 
 							log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
 									   upstream_node_info.node_name, upstream_node_info.node_id);
-
-							close_connection(&upstream_conn);
-
+							PQfinish(upstream_conn);
+							upstream_conn = NULL;
 							local_node_info.upstream_node_id = UNKNOWN_NODE_ID;
 
 							/* check local connection */
@@ -1573,7 +1539,7 @@ monitor_streaming_standby(void)
 							{
 								int i;
 
-								close_connection(&local_conn);
+								PQfinish(local_conn);
 
 								for (i = 0; i < config_file_options.repmgrd_standby_startup_timeout; i++)
 								{
@@ -1582,8 +1548,6 @@ monitor_streaming_standby(void)
 									if (PQstatus(local_conn) == CONNECTION_OK)
 										break;
 
-									close_connection(&local_conn);
-
 									log_debug("sleeping 1 second; %i of %i attempts to reconnect to local node",
 											  i + 1,
 											  config_file_options.repmgrd_standby_startup_timeout);
@@ -1616,7 +1580,7 @@ monitor_streaming_standby(void)
 					{
 						log_notice(_("repmgrd on this node is paused"));
 						log_detail(_("no failover will be carried out"));
-						log_hint(_("execute \"repmgr service unpause\" to resume normal failover mode"));
+						log_hint(_("execute \"repmgr daemon unpause\" to resume normal failover mode"));
 						monitoring_state = MS_DEGRADED;
 						INSTR_TIME_SET_CURRENT(degraded_monitoring_start);
 					}
@@ -1713,12 +1677,7 @@ monitor_streaming_standby(void)
 					}
 					else
 					{
-						if (primary_conn != NULL && PQstatus(primary_conn) != CONNECTION_OK)
-						{
-							close_connection(&primary_conn);
-						}
-
-						if (primary_conn == NULL)
+						if (primary_conn == NULL || PQstatus(primary_conn) != CONNECTION_OK)
 						{
 							primary_conn = establish_primary_db_connection(upstream_conn, false);
 						}
@@ -1727,8 +1686,7 @@ monitor_streaming_standby(void)
 					initPQExpBuffer(&event_details);
 
 					appendPQExpBuffer(&event_details,
-									  _("reconnected to upstream node \"%s\" (ID: %i) after %i seconds, resuming monitoring"),
-									  upstream_node_info.node_name,
+									  _("reconnected to upstream node %i after %i seconds, resuming monitoring"),
 									  upstream_node_info.node_id,
 									  degraded_monitoring_elapsed);
 
@@ -1752,6 +1710,9 @@ monitor_streaming_standby(void)
 				 * has been promoted
 				 */
 
+				NodeInfoListCell *cell;
+				int			follow_node_id = UNKNOWN_NODE_ID;
+
 				/* local node has been promoted */
 				if (get_recovery_type(local_conn) == RECTYPE_PRIMARY)
 				{
@@ -1841,9 +1802,6 @@ monitor_streaming_standby(void)
 
 					if (sibling_nodes.node_count > 0)
 					{
-						NodeInfoListCell *cell;
-						t_node_info *follow_node_info = NULL;
-
 						log_debug("scanning %i node records to detect new primary...", sibling_nodes.node_count);
 						for (cell = sibling_nodes.head; cell; cell = cell->next)
 						{
@@ -1864,27 +1822,22 @@ monitor_streaming_standby(void)
 
 							if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 							{
-								close_connection(&cell->node_info->conn);
 								log_debug("unable to connect to %i ... ", cell->node_info->node_id);
-								close_connection(&cell->node_info->conn);
 								continue;
 							}
 
 							if (get_recovery_type(cell->node_info->conn) == RECTYPE_PRIMARY)
 							{
-								follow_node_info = cell->node_info;
+								follow_node_id = cell->node_info->node_id;
 								close_connection(&cell->node_info->conn);
 								break;
 							}
 							close_connection(&cell->node_info->conn);
 						}
 
-						if (follow_node_info != NULL)
+						if (follow_node_id != UNKNOWN_NODE_ID)
 						{
-							log_info(_("node \"%s\" (node ID: %i) detected as primary"),
-									 follow_node_info->node_name,
-									 follow_node_info->node_id);
-							follow_new_primary(follow_node_info->node_id);
+							follow_new_primary(follow_node_id);
 						}
 					}
 
@@ -1928,7 +1881,7 @@ loop:
 					if (PQstatus(local_conn) == CONNECTION_OK && repmgrd_is_paused(local_conn))
 					{
 						log_detail(_("repmgrd paused by administrator"));
-						log_hint(_("execute \"repmgr service unpause\" to resume normal failover mode"));
+						log_hint(_("execute \"repmgr daemon unpause\" to resume normal failover mode"));
 					}
 					else
 					{
@@ -2051,8 +2004,7 @@ loop:
 
 				if (last_known_upstream_node_id != local_node_info.upstream_node_id)
 				{
-					log_notice(_("upstream for local node \"%s\" (ID: %i) appears to have changed, restarting monitoring"),
-							   local_node_info.node_name,
+					log_notice(_("local node %i upstream appears to have changed, restarting monitoring"),
 							   local_node_info.node_id);
 					log_detail(_("currently monitoring upstream %i; new upstream is %i"),
 							   last_known_upstream_node_id,
@@ -2066,8 +2018,7 @@ loop:
 				 */
 				if (local_node_info.type != STANDBY)
 				{
-					log_notice(_("local node \"%s\" (ID: %i) is no longer a standby, restarting monitoring"),
-							   local_node_info.node_name,
+					log_notice(_("local node %i is no longer a standby, restarting monitoring"),
 							   local_node_info.node_id);
 					close_connection(&upstream_conn);
 					return;
@@ -2092,8 +2043,8 @@ loop:
 				{
 					log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
 							   upstream_node_info.node_name, upstream_node_info.node_id);
-
-					close_connection(&primary_conn);
+					PQfinish(primary_conn);
+					primary_conn = NULL;
 
 					local_node_info.upstream_node_id = UNKNOWN_NODE_ID;
 					return;
@@ -2132,6 +2083,7 @@ loop:
 			}
 		}
 
+
 		if (got_SIGHUP)
 		{
 			handle_sighup(&local_conn, STANDBY);
@@ -2141,35 +2093,13 @@ loop:
 
 		if (local_monitoring_state == MS_NORMAL && last_known_upstream_node_id != local_node_info.upstream_node_id)
 		{
-			/*
-			 * It's possible that after a change of upstream, the local node record will not
-			 * yet have been updated with the new upstream node ID. Therefore we check the
-			 * node record on the upstream, and if that matches "last_known_upstream_node_id",
-			 * take that as the correct value.
-			 */
-
-			if (monitoring_state == MS_NORMAL)
-			{
-				t_node_info node_info_on_upstream = T_NODE_INFO_INITIALIZER;
-				record_status = get_node_record(primary_conn, config_file_options.node_id, &node_info_on_upstream);
-
-				if (last_known_upstream_node_id == node_info_on_upstream.upstream_node_id)
-				{
-					local_node_info.upstream_node_id = last_known_upstream_node_id;
-				}
-			}
-
-			if (last_known_upstream_node_id != local_node_info.upstream_node_id)
-			{
-				log_notice(_("local node \"%s\" (ID: %i)'s upstream appears to have changed, restarting monitoring"),
-						   local_node_info.node_name,
-						   local_node_info.node_id);
-				log_detail(_("currently monitoring upstream %i; new upstream is %i"),
-						   last_known_upstream_node_id,
-						   local_node_info.upstream_node_id);
-				close_connection(&upstream_conn);
-				return;
-			}
+			log_notice(_("local node %i's upstream appears to have changed, restarting monitoring"),
+					   local_node_info.node_id);
+			log_detail(_("currently monitoring upstream %i; new upstream is %i"),
+					   last_known_upstream_node_id,
+					   local_node_info.upstream_node_id);
+			close_connection(&upstream_conn);
+			return;
 		}
 
 		log_verbose(LOG_DEBUG, "sleeping %i seconds (parameter \"monitor_interval_secs\")",
@@ -2353,9 +2283,8 @@ monitor_streaming_witness(void)
 					{
 						log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
 								   upstream_node_info.node_name, upstream_node_info.node_id);
-
-						close_connection(&primary_conn);
-
+						PQfinish(primary_conn);
+						primary_conn = NULL;
 						termPQExpBuffer(&event_details);
 						return;
 					}
@@ -2416,8 +2345,7 @@ monitor_streaming_witness(void)
 					initPQExpBuffer(&event_details);
 
 					appendPQExpBuffer(&event_details,
-									  _("reconnected to upstream node \"%s\" (ID: %i) after %i seconds, resuming monitoring"),
-									  upstream_node_info.node_name,
+									  _("reconnected to upstream node %i after %i seconds, resuming monitoring"),
 									  upstream_node_info.node_id,
 									  degraded_monitoring_elapsed);
 
@@ -2427,11 +2355,9 @@ monitor_streaming_witness(void)
 					if (get_recovery_type(primary_conn) != RECTYPE_PRIMARY)
 					{
 						log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
-								   upstream_node_info.node_name,
-								   upstream_node_info.node_id);
-
-						close_connection(&primary_conn);
-
+								   upstream_node_info.node_name, upstream_node_info.node_id);
+						PQfinish(primary_conn);
+						primary_conn = NULL;
 						termPQExpBuffer(&event_details);
 						return;
 					}
@@ -2454,6 +2380,8 @@ monitor_streaming_witness(void)
 				 * has been promoted
 				 */
 
+				NodeInfoListCell *cell;
+				int			follow_node_id = UNKNOWN_NODE_ID;
 				NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 
 				get_active_sibling_node_records(local_conn,
@@ -2463,9 +2391,6 @@ monitor_streaming_witness(void)
 
 				if (sibling_nodes.node_count > 0)
 				{
-					NodeInfoListCell *cell;
-					t_node_info *follow_node_info = NULL;
-
 					log_debug("scanning %i node records to detect new primary...", sibling_nodes.node_count);
 					for (cell = sibling_nodes.head; cell; cell = cell->next)
 					{
@@ -2485,30 +2410,24 @@ monitor_streaming_witness(void)
 
 						if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 						{
-							close_connection(&cell->node_info->conn);
 							log_debug("unable to connect to %i ... ", cell->node_info->node_id);
-							close_connection(&cell->node_info->conn);
 							continue;
 						}
 
 						if (get_recovery_type(cell->node_info->conn) == RECTYPE_PRIMARY)
 						{
-							follow_node_info = cell->node_info;
+							follow_node_id = cell->node_info->node_id;
 							close_connection(&cell->node_info->conn);
 							break;
 						}
 						close_connection(&cell->node_info->conn);
 					}
 
-					if (follow_node_info != NULL)
+					if (follow_node_id != UNKNOWN_NODE_ID)
 					{
-						log_info(_("node \"%s\" (node ID: %i) detected as primary"),
-								 follow_node_info->node_name,
-								 follow_node_info->node_id);
-						witness_follow_new_primary(follow_node_info->node_id);
+						witness_follow_new_primary(follow_node_id);
 					}
 				}
-
 				clear_node_info_list(&sibling_nodes);
 			}
 		}
@@ -2629,9 +2548,8 @@ loop:
 				{
 					log_notice(_("current upstream node \"%s\" (ID: %i) is not primary, restarting monitoring"),
 							   upstream_node_info.node_name, upstream_node_info.node_id);
-
-					close_connection(&primary_conn);
-
+					PQfinish(primary_conn);
+					primary_conn = NULL;
 					return;
 				}
 
@@ -2686,6 +2604,7 @@ loop:
 	}
 
 	return;
+
 }
 
 
@@ -2741,32 +2660,24 @@ do_primary_failover(void)
 			{
 				for (cell = check_sibling_nodes.head; cell; cell = cell->next)
 				{
+					pid_t sibling_wal_receiver_pid;
+
 					if (cell->node_info->conn == NULL)
 						cell->node_info->conn = establish_db_connection(cell->node_info->conninfo, false);
 
-					if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
-					{
-						log_warning(_("unable to query WAL receiver PID on node \"%s\" (ID: %i)"),
-									cell->node_info->node_name,
-									cell->node_info->node_id);
-						close_connection(&cell->node_info->conn);
-					}
-					else
-					{
-						pid_t sibling_wal_receiver_pid = (pid_t)get_wal_receiver_pid(cell->node_info->conn);
+					sibling_wal_receiver_pid = (pid_t)get_wal_receiver_pid(cell->node_info->conn);
 
-						if (sibling_wal_receiver_pid == UNKNOWN_PID)
-						{
-							log_warning(_("unable to query WAL receiver PID on node %i"),
-										cell->node_info->node_id);
-						}
-						else if (sibling_wal_receiver_pid > 0)
-						{
-							log_info(_("WAL receiver PID on node %i is %i"),
-									 cell->node_info->node_id,
-									 sibling_wal_receiver_pid);
-							sibling_node_wal_receiver_connected = true;
-						}
+					if (sibling_wal_receiver_pid == UNKNOWN_PID)
+					{
+						log_warning(_("unable to query WAL receiver PID on node %i"),
+									cell->node_info->node_id);
+					}
+					else if (sibling_wal_receiver_pid > 0)
+					{
+						log_info(_("WAL receiver PID on node %i is %i"),
+								 cell->node_info->node_id,
+								 sibling_wal_receiver_pid);
+						sibling_node_wal_receiver_connected = true;
 					}
 				}
 
@@ -2928,8 +2839,7 @@ do_primary_failover(void)
 
 					initPQExpBuffer(&event_details);
 					appendPQExpBuffer(&event_details,
-									  _("node \"%s\" (ID: %i) is in manual failover mode and is now disconnected from streaming replication"),
-									  local_node_info.node_name,
+									  _("node %i is in manual failover mode and is now disconnected from streaming replication"),
 									  local_node_info.node_id);
 
 					new_primary_conn = establish_db_connection(new_primary.conninfo, false);
@@ -3089,6 +2999,8 @@ do_primary_failover(void)
 }
 
 
+
+
 static void
 update_monitoring_history(void)
 {
@@ -3323,8 +3235,6 @@ do_upstream_standby_failover(void)
 		if (PQstatus(local_conn) == CONNECTION_OK)
 			break;
 
-		close_connection(&local_conn);
-
 		log_debug("sleeping 1 second; %i of %i (\"repmgrd_standby_startup_timeout\") attempts to reconnect to local node",
 				  i + 1,
 				  config_file_options.repmgrd_standby_startup_timeout);
@@ -3333,8 +3243,7 @@ do_upstream_standby_failover(void)
 
 	if (PQstatus(local_conn) != CONNECTION_OK)
 	{
-		log_error(_("unable to reconnect to local node \"%s\" (ID: %i)"),
-				  local_node_info.node_name,
+		log_error(_("unable to reconnect to local node %i"),
 				  local_node_info.node_id);
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}
@@ -3369,8 +3278,7 @@ do_upstream_standby_failover(void)
 
 			initPQExpBuffer(&event_details);
 			appendPQExpBuffer(&event_details,
-							  _("unable to set node \"%s\" (ID: %i)'s new upstream ID to %i"),
-							  local_node_info.node_name,
+							  _("unable to set node %i's new upstream ID to %i"),
 							  local_node_info.node_id,
 							  primary_node_info.node_id);
 
@@ -3408,10 +3316,8 @@ do_upstream_standby_failover(void)
 		initPQExpBuffer(&event_details);
 
 		appendPQExpBuffer(&event_details,
-						  _("node \"%s\" (ID: %i) is now following primary node \"%s\" (ID: %i)"),
-						  local_node_info.node_name,
+						  _("node %i is now following primary node %i"),
 						  local_node_info.node_id,
-						  primary_node_info.node_name,
 						  primary_node_info.node_id);
 
 		log_notice("%s", event_details.data);
@@ -3476,16 +3382,12 @@ promote_self(void)
 
 	r = system(promote_command);
 
-	log_debug("result of promote_command: %i", WEXITSTATUS(r));
-
 	/* connection should stay up, but check just in case */
 	if (PQstatus(local_conn) != CONNECTION_OK)
 	{
 		log_warning(_("local database connection not available"));
 		log_detail("\n%s", PQerrorMessage(local_conn));
 
-		close_connection(&local_conn);
-
 		local_conn = establish_db_connection(local_node_info.conninfo, true);
 
 		/* assume node failed */
@@ -3493,37 +3395,24 @@ promote_self(void)
 		{
 			log_error(_("unable to reconnect to local node"));
 			log_detail("\n%s", PQerrorMessage(local_conn));
-
-			close_connection(&local_conn);
-
 			/* XXX handle this */
 			return FAILOVER_STATE_LOCAL_NODE_FAILURE;
 		}
 	}
 
-	if (WIFEXITED(r) && WEXITSTATUS(r))
+	if (r != 0)
 	{
-		int			primary_node_id = UNKNOWN_NODE_ID;
-
-		log_error(_("promote command failed"));
-		log_detail(_("promote command exited with error code %i"), WEXITSTATUS(r));
-
-		log_info(_("checking if original primary node has reappeared"));
+		int			primary_node_id;
 
 		upstream_conn = get_primary_connection(local_conn,
 											   &primary_node_id,
 											   NULL);
 
-		if (PQstatus(upstream_conn) != CONNECTION_OK)
-		{
-			close_connection(&upstream_conn);
-		}
-		else if (primary_node_id == failed_primary.node_id)
+		if (PQstatus(upstream_conn) == CONNECTION_OK && primary_node_id == failed_primary.node_id)
 		{
 			PQExpBufferData event_details;
 
-			log_notice(_("original primary \"%s\" (ID: %i) reappeared before this standby was promoted - no action taken"),
-					   failed_primary.node_name,
+			log_notice(_("original primary (ID: %i) reappeared before this standby was promoted - no action taken"),
 					   failed_primary.node_id);
 
 			initPQExpBuffer(&event_details);
@@ -3548,6 +3437,9 @@ promote_self(void)
 			return FAILOVER_STATE_PRIMARY_REAPPEARED;
 		}
 
+
+		log_error(_("promote command failed"));
+
 		create_event_notification(NULL,
 								  &config_file_options,
 								  local_node_info.node_id,
@@ -3558,11 +3450,6 @@ promote_self(void)
 		return FAILOVER_STATE_PROMOTION_FAILED;
 	}
 
-	/*
-	 * Promotion has succeeded - verify local connection is still available
-	 */
-	try_reconnect(&local_conn, &local_node_info);
-
 	/* bump the electoral term */
 	increment_current_term(local_conn);
 
@@ -3578,10 +3465,8 @@ promote_self(void)
 		initPQExpBuffer(&event_details);
 
 		appendPQExpBuffer(&event_details,
-						  _("node \"%s\" (ID: %i) promoted to primary; old primary \"%s\" (ID: %i) marked as failed"),
-						  local_node_info.node_name,
+						  _("node %i promoted to primary; old primary %i marked as failed"),
 						  local_node_info.node_id,
-						  failed_primary.node_name,
 						  failed_primary.node_id);
 
 		/* local_conn is now the primary connection */
@@ -3625,8 +3510,6 @@ notify_followers(NodeInfoList *standby_nodes, int follow_node_id)
 					 cell->node_info->node_name,
 					 cell->node_info->node_id);
 
-			close_connection(&cell->node_info->conn);
-
 			cell->node_info->conn = establish_db_connection(cell->node_info->conninfo, false);
 		}
 
@@ -3637,7 +3520,6 @@ notify_followers(NodeInfoList *standby_nodes, int follow_node_id)
 						cell->node_info->node_id);
 			log_detail("\n%s", PQerrorMessage(cell->node_info->conn));
 
-			close_connection(&cell->node_info->conn);
 			continue;
 		}
 
@@ -3712,10 +3594,6 @@ follow_new_primary(int new_primary_id)
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}
 
-	log_notice(_("attempting to follow new primary \"%s\" (node ID: %i)"),
-				 new_primary.node_name,
-				 new_primary_id);
-
 	record_status = get_node_record(local_conn, local_node_info.upstream_node_id, &failed_primary);
 
 	if (record_status != RECORD_FOUND)
@@ -3745,9 +3623,7 @@ follow_new_primary(int new_primary_id)
 		else
 		{
 			new_primary_ok = false;
-			log_warning(_("new primary \"%s\" (node ID: %i) is in recovery"),
-						new_primary.node_name,
-						new_primary_id);
+			log_warning(_("new primary is not in recovery"));
 			close_connection(&upstream_conn);
 		}
 	}
@@ -3862,18 +3738,15 @@ follow_new_primary(int new_primary_id)
 		if (PQstatus(local_conn) == CONNECTION_OK)
 			break;
 
-		close_connection(&local_conn);
-
 		log_debug("sleeping 1 second; %i of %i attempts to reconnect to local node",
 				  i + 1,
 				  config_file_options.repmgrd_standby_startup_timeout);
 		sleep(1);
 	}
 
-	if (local_conn == NULL || PQstatus(local_conn) != CONNECTION_OK)
+	if (PQstatus(local_conn) != CONNECTION_OK)
 	{
-		log_error(_("unable to reconnect to local node \"%s\" (ID: %i)"),
-				  local_node_info.node_name,
+		log_error(_("unable to reconnect to local node %i"),
 				  local_node_info.node_id);
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}
@@ -3887,10 +3760,8 @@ follow_new_primary(int new_primary_id)
 
 		initPQExpBuffer(&event_details);
 		appendPQExpBuffer(&event_details,
-						  _("node \"%s\" (ID: %i) now following new upstream node \"%s\" (ID: %i)"),
-						  local_node_info.node_name,
+						  _("node %i now following new upstream node %i"),
 						  local_node_info.node_id,
-						  upstream_node_info.node_name,
 						  upstream_node_info.node_id);
 
 		log_notice("%s", event_details.data);
@@ -3945,9 +3816,7 @@ witness_follow_new_primary(int new_primary_id)
 				break;
 			case RECTYPE_STANDBY:
 				new_primary_ok = false;
-				log_warning(_("new primary \"%s\" (node ID: %i) is in recovery"),
-							new_primary.node_name,
-							new_primary_id);
+				log_warning(_("new primary is not in recovery"));
 				break;
 			case RECTYPE_UNKNOWN:
 				new_primary_ok = false;
@@ -3985,7 +3854,7 @@ witness_follow_new_primary(int new_primary_id)
 	record_status = get_node_record(upstream_conn, local_node_info.node_id, &local_node_info);
 	if (record_status != RECORD_FOUND)
 	{
-		log_error(_("unable to retrieve metadata record for node %i"),
+		log_error(_("unable to retrieve metadata record found for node %i"),
 				  local_node_info.node_id);
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}
@@ -3995,10 +3864,8 @@ witness_follow_new_primary(int new_primary_id)
 
 		initPQExpBuffer(&event_details);
 		appendPQExpBuffer(&event_details,
-						  _("witness node \"%s\" (ID: %i) now following new primary node \"%s\" (ID: %i)"),
-						  local_node_info.node_name,
+						  _("witness node %i now following new primary node %i"),
 						  local_node_info.node_id,
-						  upstream_node_info.node_name,
 						  upstream_node_info.node_id);
 
 		log_notice("%s", event_details.data);
@@ -4100,12 +3967,6 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 
 		return ELECTION_NOT_CANDIDATE;
 	}
-	if (config_file_options.failover_delay > 0)
-	{
-		log_debug("sleeping %i seconds (\"failover_delay\") before initiating failover",
-				  config_file_options.failover_delay);
-		sleep(config_file_options.failover_delay);
-	}
 
 	/* node priority is set to zero - don't become a candidate, and lose by default */
 	if (local_node_info.priority <= 0)
@@ -4136,9 +3997,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 	}
 	else
 	{
-		log_info(_("primary node  \"%s\" (ID: %i) and this node have the same location (\"%s\")"),
-				 upstream_node_info.node_name,
-				 upstream_node_info.node_id,
+		log_info(_("primary and this node have the same location (\"%s\")"),
 				 local_node_info.location);
 	}
 
@@ -4240,8 +4099,6 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 
 		if (PQstatus(cell->node_info->conn) != CONNECTION_OK)
 		{
-			close_connection(&cell->node_info->conn);
-
 			continue;
 		}
 
@@ -4372,8 +4229,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		{
 			if (sibling_replication_info.upstream_node_id != upstream_node_info.node_id)
 			{
-				log_warning(_("assumed sibling node \"%s\" (ID: %i) monitoring different upstream node %i"),
-							cell->node_info->node_name,
+				log_warning(_("assumed sibling node %i monitoring different upstream node %i"),
 							cell->node_info->node_id,
 							sibling_replication_info.upstream_node_id);
 
@@ -4381,9 +4237,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 			else
 			{
 				nodes_with_primary_still_visible++;
-				log_notice(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago, considering primary still visible"),
-						   get_node_type_string(cell->node_info->type),
-						   cell->node_info->node_name,
+				log_notice(_("node %i last saw primary node %i second(s) ago, considering primary still visible"),
 						   cell->node_info->node_id,
 						   sibling_replication_info.upstream_last_seen);
 				appendPQExpBuffer(&nodes_with_primary_visible,
@@ -4395,9 +4249,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		}
 		else
 		{
-			log_info(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago"),
-					 get_node_type_string(cell->node_info->type),
-					 cell->node_info->node_name,
+			log_info(_("node %i last saw primary node %i second(s) ago"),
 					 cell->node_info->node_id,
 					 sibling_replication_info.upstream_last_seen);
 		}
@@ -4413,8 +4265,7 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		/* don't check 0-priority nodes */
 		if (cell->node_info->priority <= 0)
 		{
-			log_info(_("node \"%s\" (ID: %i) has priority of %i, skipping"),
-					   cell->node_info->node_name,
+			log_info(_("node %i has priority of %i, skipping"),
 					   cell->node_info->node_id,
 					   cell->node_info->priority);
 			continue;
@@ -4675,8 +4526,8 @@ check_connection(t_node_info *node_info, PGconn **conn)
 					node_info->node_name,
 					node_info->node_id);
 		log_detail("\n%s", PQerrorMessage(*conn));
-
-		close_connection(conn);
+		PQfinish(*conn);
+		*conn = NULL;
 	}
 
 	if (PQstatus(*conn) != CONNECTION_OK)
@@ -4685,14 +4536,13 @@ check_connection(t_node_info *node_info, PGconn **conn)
 				 node_info->node_name,
 				 node_info->node_id);
 
-		close_connection(conn);
-
+		PQfinish(*conn);
 		*conn = establish_db_connection(node_info->conninfo, false);
 
 		if (PQstatus(*conn) != CONNECTION_OK)
 		{
-			close_connection(conn);
-
+			PQfinish(*conn);
+			*conn = NULL;
 			log_warning(_("reconnection to node \"%s\" (ID: %i) failed"),
 						node_info->node_name,
 						node_info->node_id);
@@ -4766,8 +4616,7 @@ handle_sighup(PGconn **conn, t_server_type server_type)
 
 	if (reload_config(&config_file_options, server_type))
 	{
-		close_connection(conn);
-
+		PQfinish(*conn);
 		*conn = establish_db_connection(config_file_options.conninfo, true);
 	}
 
@@ -4892,9 +4741,11 @@ parse_failover_validation_command(const char *template, t_node_info *node_info,
 static bool
 check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *follow_target_conn, t_node_info *follow_target_node_info)
 {
+	t_conninfo_param_list local_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PGconn	   *local_repl_conn = NULL;
 	t_system_identification local_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
 
+	t_conninfo_param_list follow_target_repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	PGconn	   *follow_target_repl_conn = NULL;
 	t_system_identification follow_target_identification = T_SYSTEM_IDENTIFICATION_INITIALIZER;
 	TimeLineHistoryEntry *follow_target_history = NULL;
@@ -4902,7 +4753,23 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 	bool can_follow = true;
 	bool success;
 
-	local_repl_conn = establish_replication_connection_from_conn(local_conn, local_node_info.repluser);
+	/* Check local replication connection - we want to execute IDENTIFY_SYSTEM
+	 * to get the current timeline ID, which might not yet be written to
+	 * pg_control.
+	 *
+	 * TODO: from 9.6, query "pg_stat_wal_receiver" via the existing local connection
+	 */
+
+	initialize_conninfo_params(&local_repl_conninfo, false);
+
+	conn_to_param_list(local_conn, &local_repl_conninfo);
+
+	/* Set the replication user from the node record */
+	param_set(&local_repl_conninfo, "user", local_node_info.repluser);
+	param_set(&local_repl_conninfo, "replication", "1");
+
+	local_repl_conn = establish_db_connection_by_params(&local_repl_conninfo, false);
+	free_conninfo_params(&local_repl_conninfo);
 
 	if (PQstatus(local_repl_conn) != CONNECTION_OK)
 	{
@@ -4911,7 +4778,6 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 
 		return false;
 	}
-
 	success = identify_system(local_repl_conn, &local_identification);
 	PQfinish(local_repl_conn);
 
@@ -4923,13 +4789,25 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 	}
 
 	/* check replication connection */
-	follow_target_repl_conn = establish_replication_connection_from_conn(follow_target_conn,
-																		 follow_target_node_info->repluser);
+	initialize_conninfo_params(&follow_target_repl_conninfo, false);
+
+	conn_to_param_list(follow_target_conn, &follow_target_repl_conninfo);
+
+	if (strcmp(param_get(&follow_target_repl_conninfo, "user"), follow_target_node_info->repluser) != 0)
+	{
+		param_set(&follow_target_repl_conninfo, "user", follow_target_node_info->repluser);
+		param_set(&follow_target_repl_conninfo, "dbname", "replication");
+	}
+
+	param_set(&follow_target_repl_conninfo, "replication", "1");
+
+	follow_target_repl_conn = establish_db_connection_by_params(&follow_target_repl_conninfo, false);
+
+	free_conninfo_params(&follow_target_repl_conninfo);
+
 	if (PQstatus(follow_target_repl_conn) != CONNECTION_OK)
 	{
 		log_error(_("unable to establish a replication connection to the follow target node"));
-
-		PQfinish(follow_target_repl_conn);
 		return false;
 	}
 
@@ -5031,8 +4909,7 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 		 */
 		if (local_xlogpos > follow_target_history->end)
 		{
-			log_error(_("this node cannot attach to follow target node \"%s\" (ID: %i)"),
-					  follow_target_node_info->node_name,
+			log_error(_("this node cannot attach to follow target node %i"),
 					  follow_target_node_info->node_id);
 			can_follow = false;
 
@@ -5044,10 +4921,8 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 
 		if (can_follow == true)
 		{
-			log_info(_("local node \"%s\" (ID: %i) can attach to follow target node \"%s\" (ID: %i)"),
-					 config_file_options.node_name,
+			log_info(_("local node %i can attach to follow target node %i"),
 					 config_file_options.node_id,
-					 follow_target_node_info->node_name,
 					 follow_target_node_info->node_id);
 
 			log_detail(_("local node's recovery point: %X/%X; follow target node's fork point: %X/%X"),
@@ -5061,6 +4936,7 @@ check_node_can_follow(PGconn *local_conn, XLogRecPtr local_xlogpos, PGconn *foll
 	if (follow_target_history)
 		pfree(follow_target_history);
 
+
 	return can_follow;
 }
 
@@ -5229,126 +5105,3 @@ parse_child_nodes_disconnect_command(char *parsed_command, char *template, int r
 
 	return;
 }
-
-
-int
-try_primary_reconnect(PGconn **conn, PGconn *local_conn, t_node_info *node_info)
-{
-	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
-	int			i;
-	int			max_attempts = config_file_options.reconnect_attempts;
-
-	initialize_conninfo_params(&conninfo_params, false);
-
-	/* we assume by now the conninfo string is parseable */
-	(void) parse_conninfo_string(node_info->conninfo, &conninfo_params, NULL, false);
-
-	/* set some default values if not explicitly provided */
-	param_set_ine(&conninfo_params, "connect_timeout", "2");
-	param_set_ine(&conninfo_params, "fallback_application_name", "repmgr");
-
-	for (i = 0; i < max_attempts; i++)
-	{
-		log_info(_("checking state of node \"%s\" (ID: %i), %i of %i attempts"),
-				 node_info->node_name,
-				 node_info->node_id,
-				 i + 1, max_attempts);
-
-		if (is_server_available_params(&conninfo_params) == true)
-		{
-			PGconn	   *our_conn;
-
-			log_notice(_("node \"%s\" (ID: %i) has recovered, reconnecting"),
-					   node_info->node_name,
-					   node_info->node_id);
-
-			/*
-			 * Note: we could also handle the case where node is pingable but
-			 * connection denied due to connection exhaustion, by falling back to
-			 * degraded monitoring (make configurable)
-			 */
-			our_conn = establish_db_connection_by_params(&conninfo_params, false);
-
-			if (PQstatus(our_conn) == CONNECTION_OK)
-			{
-				free_conninfo_params(&conninfo_params);
-
-				log_info(_("connection to node \"%s\" (ID: %i) succeeded"),
-						 node_info->node_name,
-						 node_info->node_id);
-
-				if (PQstatus(*conn) == CONNECTION_BAD)
-				{
-					log_verbose(LOG_INFO, _("original connection handle returned CONNECTION_BAD, using new connection"));
-					close_connection(conn);
-					*conn = our_conn;
-				}
-				else
-				{
-					ExecStatusType ping_result;
-
-					ping_result = connection_ping(*conn);
-
-					if (ping_result != PGRES_TUPLES_OK)
-					{
-						log_info(_("original connection no longer available, using new connection"));
-						close_connection(conn);
-						*conn = our_conn;
-					}
-					else
-					{
-						log_info(_("original connection is still available"));
-
-						PQfinish(our_conn);
-					}
-				}
-
-				node_info->node_status = NODE_STATUS_UP;
-
-				return UNKNOWN_NODE_ID;
-			}
-
-			close_connection(&our_conn);
-			log_notice(_("unable to reconnect to node \"%s\" (ID: %i)"),
-					   node_info->node_name,
-					   node_info->node_id);
-		}
-
-		if (i + 1 < max_attempts)
-		{
-			int j;
-			log_info(_("sleeping %i seconds until next reconnection attempt"),
-					 config_file_options.reconnect_interval);
-			for (j = 0; j < config_file_options.reconnect_interval; j++)
-			{
-				int new_primary_node_id;
-				if (get_new_primary(local_conn, &new_primary_node_id) == true && new_primary_node_id != UNKNOWN_NODE_ID)
-				{
-					if (new_primary_node_id == ELECTION_RERUN_NOTIFICATION)
-					{
-						log_notice(_("received rerun notification"));
-					}
-					else
-					{
-						log_notice(_("received notification that new primary is node %i"), new_primary_node_id);
-					}
-
-					free_conninfo_params(&conninfo_params);
-					return new_primary_node_id;
-				}
-				sleep(1);
-			}
-		}
-	}
-
-	log_warning(_("unable to reconnect to node \"%s\" (ID: %i) after %i attempts"),
-				node_info->node_name,
-				node_info->node_id,
-				max_attempts);
-
-	node_info->node_status = NODE_STATUS_DOWN;
-
-	free_conninfo_params(&conninfo_params);
-
-	return UNKNOWN_NODE_ID;
-}