doc: note downstream node (dis)connection monitoring in more places

See also https://www.df7cb.de/blog/2020/apt-archive.postgresql.org.html

.gitignore

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

HISTORY

@@ -1,6 +1,15 @@
-4.4.1   2019-??-??
+5.0.1   20??-??-??
+        repmgr: ensure an existing replication slot is not deleted if the
+          follow target is the node's current upstream (Ian)
+
+5.0     2019-10-15
+        general: add PostgreSQL 12 support (Ian)
+        general: parse configuration file using flex (Ian)
+        repmgr: rename "repmgr daemon ..." commands to "repmgr service ..." (Ian)
         repmgr: improve data directory check (Ian)
         repmgr: improve extension check during "standby clone" (Ian)
+		repmgr: pass provided log level when executing repmgr remotely (Ian)
+        repmgrd: fix handling of upstream node change check (Ian)
 
 4.4     2019-06-27
         repmgr: improve "daemon status" output (Ian)

Makefile.global.in

@@ -2,6 +2,7 @@
 # Makefile.global.in
 # @configure_input@
 
+
 # Can only be built using pgxs
 USE_PGXS=1
 
@@ -14,6 +15,9 @@ ifeq ($(vpath_build),yes)
 	VPATH := $(repmgr_abs_srcdir)/$(repmgr_subdir)
 	USE_VPATH :=$(VPATH)
 endif
+
+SED=@SED@
+
 GIT_WORK_TREE=${repmgr_abs_srcdir}
 GIT_DIR=${repmgr_abs_srcdir}/.git
 export GIT_DIR
@@ -26,3 +30,11 @@ include $(PGXS)
 REPMGR_VERSION=$(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

@@ -19,7 +19,9 @@ DATA = \
   repmgr--4.2--4.3.sql \
   repmgr--4.3.sql \
   repmgr--4.3--4.4.sql \
-  repmgr--4.4.sql
+  repmgr--4.4.sql \
+  repmgr--4.4--5.0.sql \
+  repmgr--5.0.sql
 
 REGRESS = repmgr_extension
 
@@ -51,13 +53,16 @@ $(info Building against PostgreSQL $(MAJORVERSION))
 
 REPMGR_CLIENT_OBJS = repmgr-client.o \
 	repmgr-action-primary.o repmgr-action-standby.o repmgr-action-witness.o \
-	repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.o repmgr-action-daemon.o \
-	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
+	repmgr-action-bdr.o repmgr-action-cluster.o repmgr-action-node.o repmgr-action-service.o repmgr-action-daemon.o \
+	configfile.o configfile-scan.o log.o strutil.o controldata.o dirutil.o compat.o dbutils.o sysutils.o
+REPMGRD_OBJS = repmgrd.o repmgrd-physical.o repmgrd-bdr.o configfile.o configfile-scan.o log.o dbutils.o strutil.o controldata.o compat.o sysutils.o
 DATE=$(shell date "+%Y-%m-%d")
 
 repmgr_version.h: repmgr_version.h.in
-	sed '0,/REPMGR_VERSION_DATE/s,\(REPMGR_VERSION_DATE\).*,\1 "$(DATE)",' $< >$@
+	$(SED) -E 's/REPMGR_VERSION_DATE.*""/REPMGR_VERSION_DATE "$(DATE)"/' $< >$@; \
+	$(SED) -i -E 's/PG_ACTUAL_VERSION_NUM/PG_ACTUAL_VERSION_NUM $(VERSION_NUM)/' $@
+
+configfile-scan.c: configfile-scan.l
 
 $(REPMGR_CLIENT_OBJS): repmgr-client.h repmgr_version.h
 
@@ -98,6 +103,7 @@ maintainer-clean: additional-maintainer-clean
 
 additional-clean:
 	rm -f *.o
+	rm -f repmgr_version.h
 	$(MAKE) -C doc clean
 
 additional-maintainer-clean: clean

README.md

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

configfile-scan.l

@@ -0,0 +1,366 @@
+/*
+ * 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

@@ -23,6 +23,12 @@
 #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;
@@ -266,12 +272,6 @@ 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 */
 
@@ -468,365 +468,12 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* 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);
-		}
-	}
+	(void) ProcessRepmgrConfigFile(fp, config_file_path, options, error_list, warning_list);
 
 	fclose(fp);
 
 	/* check required parameters */
-	if (node_id_found == false)
+	if (options->node_id == UNKNOWN_NODE_ID)
 	{
 		item_list_append(error_list, _("\"node_id\": required parameter was not found"));
 	}
@@ -919,6 +566,349 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 }
 
 
+void
+parse_configuration_item(t_configuration_options *options, ItemList *error_list, ItemList *warning_list, const char *name, const char *value)
+{
+	bool		known_parameter = true;
+
+	if (strcmp(name, "node_id") == 0)
+	{
+		options->node_id = repmgr_atoi(value, name, error_list, MIN_NODE_ID);
+	}
+	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);
+	}
+}
 
 
 bool
@@ -1190,7 +1180,8 @@ reload_config(t_configuration_options *orig_options, t_server_type server_type)
 	_parse_config(&new_options, &config_errors, &config_warnings);
 
 
-	if (server_type == PRIMARY || server_type == STANDBY)
+	if (new_options.failover == FAILOVER_AUTOMATIC
+		&& (server_type == PRIMARY || server_type == STANDBY))
 	{
 		if (new_options.promote_command[0] == '\0')
 		{
@@ -1816,6 +1807,7 @@ 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.
@@ -1883,6 +1875,120 @@ 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;
+
+	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);
+	}
+
+	/* Set umask to 0600 */
+	um = umask((~(S_IRUSR | S_IWUSR)) & (S_IRWXG | S_IRWXO));
+	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()
@@ -2059,9 +2165,6 @@ 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

@@ -28,6 +28,12 @@
 /* magic number for use in t_recovery_conf */
 #define TARGET_TIMELINE_LATEST 0
 
+/*
+ * This is defined 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];
 
@@ -317,6 +323,8 @@ 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,
@@ -342,4 +350,10 @@ 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 4.4.
+# Generated by GNU Autoconf 2.69 for repmgr 5.0.0.
 #
 # Report bugs to <repmgr@googlegroups.com>.
 #
@@ -582,13 +582,16 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.4'
-PACKAGE_STRING='repmgr 4.4'
+PACKAGE_VERSION='5.0.0'
+PACKAGE_STRING='repmgr 5.0.0'
 PACKAGE_BUGREPORT='repmgr@googlegroups.com'
 PACKAGE_URL='https://repmgr.org/'
 
 ac_subst_vars='LTLIBOBJS
 LIBOBJS
+HAVE_SED
+HAVE_GSED
+HAVE_GNUSED
 vpath_build
 SED
 PG_CONFIG
@@ -1178,7 +1181,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures repmgr 4.4 to adapt to many kinds of systems.
+\`configure' configures repmgr 5.0.0 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1239,7 +1242,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.4:";;
+     short | recursive ) echo "Configuration of repmgr 5.0.0:";;
    esac
   cat <<\_ACEOF
 
@@ -1313,7 +1316,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-repmgr configure 4.4
+repmgr configure 5.0.0
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1332,7 +1335,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by repmgr $as_me 4.4, which was
+It was created by repmgr $as_me 5.0.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -1847,6 +1850,133 @@ else
 fi
 
 
+# Extract the first word of "gnused", so it can be a program name with args.
+set dummy gnused; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_GNUSED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_GNUSED"; then
+  ac_cv_prog_HAVE_GNUSED="$HAVE_GNUSED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_GNUSED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_GNUSED" && ac_cv_prog_HAVE_GNUSED="no"
+fi
+fi
+HAVE_GNUSED=$ac_cv_prog_HAVE_GNUSED
+if test -n "$HAVE_GNUSED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_GNUSED" >&5
+$as_echo "$HAVE_GNUSED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+# Extract the first word of "gsed", so it can be a program name with args.
+set dummy gsed; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_GSED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_GSED"; then
+  ac_cv_prog_HAVE_GSED="$HAVE_GSED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_GSED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_GSED" && ac_cv_prog_HAVE_GSED="no"
+fi
+fi
+HAVE_GSED=$ac_cv_prog_HAVE_GSED
+if test -n "$HAVE_GSED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_GSED" >&5
+$as_echo "$HAVE_GSED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+# Extract the first word of "sed", so it can be a program name with args.
+set dummy sed; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_HAVE_SED+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -n "$HAVE_SED"; then
+  ac_cv_prog_HAVE_SED="$HAVE_SED" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_exec_ext in '' $ac_executable_extensions; do
+  if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+    ac_cv_prog_HAVE_SED="yes"
+    $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+    break 2
+  fi
+done
+  done
+IFS=$as_save_IFS
+
+  test -z "$ac_cv_prog_HAVE_SED" && ac_cv_prog_HAVE_SED="no"
+fi
+fi
+HAVE_SED=$ac_cv_prog_HAVE_SED
+if test -n "$HAVE_SED"; then
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $HAVE_SED" >&5
+$as_echo "$HAVE_SED" >&6; }
+else
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+
+if test "$HAVE_GNUSED" = yes; then
+ SED=gnused
+else
+ if test "$HAVE_GSED" = yes; then
+  SED=gsed
+ else
+  SED=sed
+ fi
+fi
+
+
+
 ac_config_files="$ac_config_files Makefile"
 
 ac_config_files="$ac_config_files Makefile.global"
@@ -2357,7 +2487,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by repmgr $as_me 4.4, which was
+This file was extended by repmgr $as_me 5.0.0, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -2420,7 +2550,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-repmgr config.status 4.4
+repmgr config.status 5.0.0
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

configure.in

@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.4], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
+AC_INIT([repmgr], [5.0.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
 
 AC_COPYRIGHT([Copyright (c) 2010-2019, 2ndQuadrant Ltd.])
 
@@ -57,6 +57,22 @@ else
 fi
 AC_SUBST(vpath_build)
 
+AC_CHECK_PROG(HAVE_GNUSED,gnused,yes,no)
+AC_CHECK_PROG(HAVE_GSED,gsed,yes,no)
+AC_CHECK_PROG(HAVE_SED,sed,yes,no)
+
+if test "$HAVE_GNUSED" = yes; then
+ SED=gnused
+else
+ if test "$HAVE_GSED" = yes; then
+  SED=gsed
+ else
+  SED=sed
+ fi
+fi
+AC_SUBST(SED)
+
+
 AC_CONFIG_FILES([Makefile])
 AC_CONFIG_FILES([Makefile.global])
 AC_OUTPUT

contrib/convert-config.pl

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

controldata.c

@@ -312,6 +312,7 @@ get_controlfile(const char *DataDir)
 
 	if (version_num >= 120000)
 	{
+#if PG_ACTUAL_VERSION_NUM >= 120000
 		ControlFileData12 *ptr = (struct ControlFileData12 *)ControlFileDataPtr;
 		control_file_info->system_identifier = ptr->system_identifier;
 		control_file_info->state = ptr->state;
@@ -320,6 +321,10 @@ get_controlfile(const char *DataDir)
 		control_file_info->timeline = ptr->checkPointCopy.ThisTimeLineID;
 		control_file_info->minRecoveryPointTLI = ptr->minRecoveryPointTLI;
 		control_file_info->minRecoveryPoint = ptr->minRecoveryPoint;
+#else
+		fprintf(stderr, "ERROR: please use a repmgr version built for PostgreSQL 12\n");
+		exit(ERR_BAD_CONFIG);
+#endif
 	}
 	else if (version_num >= 110000)
 	{

controldata.h

@@ -12,6 +12,7 @@
 #include "postgres_fe.h"
 #include "catalog/pg_control.h"
 
+
 #define MAX_VERSION_STRING 24
 /*
  * A simplified representation of pg_control containing only those fields
@@ -55,7 +56,7 @@ typedef struct CheckPoint93
 } CheckPoint93;
 
 
-/* Same for 9.5, 9.6, 10, HEAD */
+/* Same for 9.5, 9.6, 10, 11 */
 typedef struct CheckPoint95
 {
 	XLogRecPtr	redo;			/* next RecPtr available when we began to
@@ -83,6 +84,50 @@ 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;
@@ -333,19 +378,11 @@ typedef struct ControlFileData11
 } ControlFileData11;
 
 
+#if PG_ACTUAL_VERSION_NUM >= 120000
 /*
  * Following field added in Pg12:
  *
  *   int max_wal_senders;
- *
- * Following fields removed:
- *
- *   uint32 nextXidEpoch;
- *   TransactionId nextXid;
- *
- * and replaced by:
- *
- *   FullTransactionId nextFullXid;
  */
 
 typedef struct ControlFileData12
@@ -359,7 +396,7 @@ typedef struct ControlFileData12
 	pg_time_t	time;			/* time stamp of last pg_control update */
 	XLogRecPtr	checkPoint;		/* last check point record ptr */
 
-	CheckPoint	checkPointCopy; /* copy of last check point record */
+	CheckPoint12	checkPointCopy; /* copy of last check point record */
 
 	XLogRecPtr	unloggedLSN;	/* current fake LSN value, for unlogged rels */
 
@@ -398,6 +435,7 @@ 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.c

@@ -67,6 +67,12 @@ static bool _is_bdr_db(PGconn *conn, PQExpBufferData *output, bool quiet);
 static void _populate_bdr_node_record(PGresult *res, t_bdr_node_info *node_info, int row);
 static void _populate_bdr_node_records(PGresult *res, BdrNodeInfoList *node_list);
 
+/*
+ * This provides a standardized way of logging database errors. Note
+ * that the provided PGconn can be a normal or a replication connection;
+ * no attempt is made to write to the database, only to report the output
+ * of PQerrorMessage().
+ */
 void
 log_db_error(PGconn *conn, const char *query_text, const char *fmt,...)
 {
@@ -1920,7 +1926,7 @@ repmgrd_set_pid(PGconn *conn, pid_t repmgrd_pid, const char *pidfile)
 	else
 	{
 		appendPQExpBufferStr(&query,
-							 " '')");
+							 " NULL)");
 	}
 
 	res = PQexec(conn, query.data);

doc/appendix-faq.xml

@@ -3,437 +3,464 @@
   <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 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-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-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 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>
+    <sect2 id="faq-repmgr-conf-data-directory">
+      <title>Why do I need to specify the data directory location in repmgr.conf?</title>
+      <para>
+        In some circumstances &repmgr; may need to access a PostgreSQL data
+        directory while the PostgreSQL server is not running, e.g. to confirm
+        it shut down cleanly during a <link linkend="performing-switchover">switchover</link>.
+      </para>
+      <para>
+        Additionally, this provides support when using &repmgr; on PostgreSQL 9.6 and
+        earlier, where the <literal>repmgr</literal> user is not a superuser; in that
+        case the <literal>repmgr</literal> user will not be able to access the
+        <literal>data_directory</literal> configuration setting, access to which is restricted
+        to superusers.
+      </para>
+      <para>
+        In PostgreSQL 10 and later, non-superusers can be added to the
+        <ulink url="https://www.postgresql.org/docs/current/default-roles.html">default role</ulink>
+        <option>pg_read_all_settings</option> (or the meta-role <option>pg_monitor</option>)
+        which will enable them to read this setting.
+      </para>
+    </sect2>
 
-  <sect2 id="faq-repmgr-conf-data-directory">
-    <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>
+    <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>
 
- <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 --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>
+      <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>repmgr10-4.0.4-1.rhel7.x86_64</filename></entry>
+      <entry><filename>repmgr11-4.4.0-1.rhel7.x86_64</filename></entry>
      </row>
 
      <row>
@@ -132,12 +132,12 @@
 
      <row>
       <entry>Installation command:</entry>
-      <entry><literal>yum install repmgr10</literal></entry>
+      <entry><literal>yum install repmgr11</literal></entry>
      </row>
 
      <row>
       <entry>Binary location:</entry>
-      <entry><filename>/usr/pgsql-10/bin</filename></entry>
+      <entry><filename>/usr/pgsql-11/bin</filename></entry>
      </row>
 
      <row>
@@ -147,22 +147,22 @@
 
      <row>
       <entry>Configuration file location:</entry>
-      <entry><filename>/etc/repmgr/10/repmgr.conf</filename></entry>
+      <entry><filename>/etc/repmgr/11/repmgr.conf</filename></entry>
      </row>
 
      <row>
       <entry>Data directory:</entry>
-      <entry><filename>/var/lib/pgsql/10/data</filename></entry>
+      <entry><filename>/var/lib/pgsql/11/data</filename></entry>
      </row>
 
      <row>
       <entry>repmgrd service command:</entry>
-      <entry><command>systemctl [start|stop|restart|reload] repmgr10</command></entry>
+      <entry><command>systemctl [start|stop|restart|reload] repmgr11</command></entry>
      </row>
 
      <row>
       <entry>repmgrd service file location:</entry>
-      <entry><filename>/usr/lib/systemd/system/repmgr10.service</filename></entry>
+      <entry><filename>/usr/lib/systemd/system/repmgr11.service</filename></entry>
      </row>
 
      <row>
@@ -253,20 +253,14 @@
     </indexterm>
 
     <para>
-      &repmgr; <literal>.deb</literal> packages are provided via the
+      &repmgr; <literal>.deb</literal> packages are provided by 2ndQuadrant as well as the
       PostgreSQL Community APT repository, and are available for each community-supported
       PostgreSQL version, currently supported Debian releases, and currently supported
       Ubuntu LTS releases.
     </para>
 
     <sect2 id="packages-apt-repository">
-      <title>APT repository</title>
-
-      <para>
-        &repmgr; packages are available from the  PostgreSQL Community APT repository,
-        which is updated immediately after each &repmgr; release.
-      </para>
-
+      <title>APT repositories</title>
 
       <table id="apt-2ndquadrant-repository">
         <title>2ndQuadrant public repository</title>
@@ -291,7 +285,7 @@
           <tbody>
             <row>
               <entry>Repository URL:</entry>
-              <entry><ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink></entry>
+              <entry><ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink></entry>
             </row>
             <row>
               <entry>Repository documentation:</entry>
@@ -323,7 +317,7 @@
 
             <row>
               <entry>Package name example:</entry>
-              <entry><filename>postgresql-10-repmgr</filename></entry>
+              <entry><filename>postgresql-11-repmgr</filename></entry>
             </row>
 
             <row>
@@ -333,12 +327,12 @@
 
             <row>
               <entry>Installation command:</entry>
-              <entry><literal>apt-get install postgresql-10-repmgr</literal></entry>
+              <entry><literal>apt-get install postgresql-11-repmgr</literal></entry>
             </row>
 
             <row>
               <entry>Binary location:</entry>
-              <entry><filename>/usr/lib/postgresql/10/bin</filename></entry>
+              <entry><filename>/usr/lib/postgresql/11/bin</filename></entry>
             </row>
 
             <row>
@@ -353,12 +347,12 @@
 
             <row>
               <entry>Data directory:</entry>
-              <entry><filename>/var/lib/postgresql/10/main</filename></entry>
+              <entry><filename>/var/lib/postgresql/11/main</filename></entry>
             </row>
 
             <row>
               <entry>PostgreSQL service command:</entry>
-              <entry><command>systemctl [start|stop|restart|reload] postgresql@10-main</command></entry>
+              <entry><command>systemctl [start|stop|restart|reload] postgresql@11-main</command></entry>
 
             </row>
 
@@ -382,11 +376,11 @@
       </table>
       <note>
         <para>
-          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.:
+          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.:
           <programlisting>
-            <command>pg_ctlcluster 10 main [start|stop|restart|reload]</command></programlisting>
+            <command>pg_ctlcluster 11 main [start|stop|restart|reload]</command></programlisting>
         </para>
         <para>
           For pre-<application>systemd</application> systems, <command>pg_ctlcluster</command>
@@ -477,7 +471,7 @@ repmgr96-4.1.1-0.0git320.g5113ab0.1.el7.x86_64.rpm</programlisting>
       <title>Debian/Ubuntu</title>
       <para>
         An archive of old packages (<literal>3.3.2</literal> and later) for Debian/Ubuntu-based systems is available here:
-        <ulink url="http://atalia.postgresql.org/morgue/r/repmgr/">http://atalia.postgresql.org/morgue/r/repmgr/</ulink>
+        <ulink url="https://apt-archive.postgresql.org/">https://apt-archive.postgresql.org/</ulink>
       </para>
     </sect2>
 

doc/appendix-release-notes.xml

@@ -15,15 +15,288 @@
     See also: <xref linkend="upgrading-repmgr"/>
   </para>
 
+<!-- remember to update the release date in ../repmgr_version.h.in -->
+  <sect1 id="release-5.0.1">
+    <title>Release 5.0.1</title>
+    <para><emphasis>???</emphasis></para>
+    <para>
+      &repmgr; 5.0.1 is a minor release.
+    </para>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+         <listitem>
+            <para>
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command>:
+	          ensure an existing replication slot is not deleted if the
+              follow target is the node's current upstream.
+            </para>
+	      </listitem>
+
+        </itemizedlist>
+      </para>
+    </sect2>
+
+  </sect1>
+
+
+  <sect1 id="release-5.0">
+    <title id="release-current">Release 5.0</title>
+    <para><emphasis>Tue 15 October, 2019</emphasis></para>
+
+    <para>
+      &repmgr; 5.0 is a major release.
+    </para>
+    <para>
+      For details on how to upgrade an existing &repmgr; installation, see
+      documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
+    </para>
+    <para>
+      If &repmgrd; is in use, a PostgreSQL restart <emphasis>is</emphasis> required;
+      in that case we suggest combining this &repmgr; upgrade with the next PostgreSQL
+      minor release, which will require a PostgreSQL restart in any case.
+    </para>
+
+
+    <sect2>
+      <title>Compatibility changes</title>
+
+      <sect3 id="repmgr-5-0-config-file-parsing">
+        <title>Configuration file parsing has been made stricter</title>
+        <para>
+          &repmgr; now parses <link linkend="configuration-file-format">configuration files</link>
+          in the same way that PostgreSQL itself does, which means some 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 string parameters should always be enclosed in single quotes.
+        </para>
+        <para>
+          For example, in &repmgr; 4.4 and earlier, the following <filename>repmgr.conf</filename>
+          entry was valid:
+          <programlisting>
+conninfo=host=node1 user=repmgr dbname=repmgr connect_timeout=2</programlisting>
+          This must now be changed to:
+          <programlisting>
+conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlisting>
+        </para>
+        <para>
+          Note that simple string identifiers (e.g. <literal>node_name=node1</literal>)
+          may remain unquoted, though we recommend always enclosing
+          strings in single quotes.
+        </para>
+        <para>
+          Additionally, leading/trailing white space between single quotes will no longer
+          be trimmed; the entire string between single quotes will be
+          taken literally.
+        </para>
+        <para>
+          Strings enclosed in double quotes (e.g. <literal>node_name=&quot;node1&quot;</literal>)
+          will now be rejected; previously they were accepted, but the double quotes were
+          interpreted as part of the string, which was a frequent cause of confusion.
+        </para>
+        <para>
+          This syntax matches that used by PostgreSQL itself.
+        </para>
+      </sect3>
+
+      <sect3>
+        <title>Some &quot;repmgr daemon ...&quot; commands renamed</title>
+
+        <para>
+          Some &quot;<command>repmgr daemon ...</command>&quot; commands have been renamed to
+          &quot;<command>repmgr service ...</command>&quot; as they have a cluster-wide effect
+          and to avoid giving the impression they affect only the local &repmgr; daemon.
+        </para>
+        <para>
+          The following commands are affected:
+
+          <itemizedlist spacing="compact" mark="bullet">
+
+            <listitem>
+              <simpara>
+                <command>repmgr daemon pause</command>
+                (now <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link>)
+              </simpara>
+            </listitem>
+
+            <listitem>
+              <simpara>
+                <command>repmgr daemon unpause</command>
+                (now <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>)
+              </simpara>
+            </listitem>
+
+            <listitem>
+              <simpara>
+                <command>repmgr daemon status</command>
+                (now <link linkend="repmgr-service-status"><command>repmgr service status</command></link>)
+              </simpara>
+            </listitem>
+
+          </itemizedlist>
+        </para>
+        <para>
+          The &quot;<command>repmgr daemon ...</command>&quot; form will still be accepted
+          for backwards compatibility.
+        </para>
+      </sect3>
+
+     <sect3>
+       <title>Some deprecated command line options removed</title>
+       <para>
+         The following command line options, which have been deprecated since &repmgr; 3.3
+         (and which no longer had any effect other than to generate a warning about their use)
+         have been removed:
+         <itemizedlist spacing="compact" mark="bullet">
+
+           <listitem>
+             <simpara><option>--data-dir</option></simpara>
+           </listitem>
+
+           <listitem>
+             <simpara><option>--no-conninfo-password</option></simpara>
+           </listitem>
+
+           <listitem>
+             <simpara><option>--recovery-min-apply-delay</option></simpara>
+           </listitem>
+
+         </itemizedlist>
+      </para>
+     </sect3>
+
+    </sect2>
+
+    <sect2>
+      <title>General enhancements</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Support for PostgreSQL 12 added.
+            </para>
+            <para>
+              Beginning with PostgreSQL 12, replication configuration has been integrated
+              into the main PostgreSQL configuraton system and the conventional
+              <filename>recovery.conf</filename> file is no longer valid.
+            </para>
+            <para>
+              &repmgr; has been modified to be compatible with this change.
+            </para>
+            <para>
+              &repmgr; additionally takes advantage of the new <command>pg_promote()</command>
+              function, which enables a standby to be promoted to primary using an SQL
+              command.
+            </para>
+            <para>
+              For an overview of general changes to replication configuration, see this blog entry:
+              <ulink url="https://www.2ndquadrant.com/en/blog/replication-configuration-changes-in-postgresql-12/">Replication configuration changes in PostgreSQL 12</ulink>
+            </para>
+          </listitem>
+
+
+          <listitem>
+            <para>
+              The &repmgr; configuration file is now parsed using
+              <command>flex</command>, meaning it will be parsed in
+              the same way as PostgreSQL parses its own configuration
+              files.
+            </para>
+            <para>
+              This makes configuration file parsing more robust
+              and consistent.
+            </para>
+            <para>
+              See item <link linkend="repmgr-5-0-config-file-parsing">Configuration file parsing has been made stricter</link>
+              for details.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-standby-clone"><command>repmgr standby clone</command></link>:
+              checks for availability of the &repmgr; extension on the upstream node have
+              been improved and error messages improved.
+            </para>
+          </listitem>
+
+		  <listitem>
+			<para>
+			  When executing &repmgr; remotely, if the &repmgr; log level was explicitly
+			  provided (with <option>-L</option>/<option>--log-level</option>), that log level
+			  will be passed to the remote &repmgr;.
+			</para>
+			<para>
+			  This makes it possible to return log output when executing repmgr
+			  remotely at a different level to the one defined in the remote
+			  &repmgr;'s <filename>repmgr.conf</filename>.
+			</para>
+			<para>
+			  This is particularly useful when <literal>DEBUG</literal> output is required.
+			</para>
+		  </listitem>
+        </itemizedlist>
+      </para>
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              Check role membership when trying to read <literal>pg_settings</literal>.
+            </para>
+            <para>
+              Previously &repmgr; assumed only superusers could read <literal>pg_settings</literal>,
+              but from PostgreSQL 10, all members of the roles <literal>pg_read_all_settings</literal>
+              or <literal>pg_monitor</literal> are permitted to do this as well.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              &repmgrd;: Fix handling of upstream node change check.
+            </para>
+            <para>
+              &repmgrd; has a check to see if the upstream node has unexpectedly
+              changed, e.g. if the repmgrd service is paused and the PostgreSQL
+              instance has been pointed to another node.
+            </para>
+            <para>
+              However this check was relying on the node record on the local node
+              being up-to-date, which may not be the case immediately after a
+              failover, when the node is still replaying records updated prior
+              to the node's own record being updated. In this case it will
+              mistakenly assume the node is following the original primary
+              and attempt to restart monitoring, which will fail as the original
+              primary is no longer available.
+            </para>
+            <para>
+              To prevent this, the node's record on the upstream node is checked
+              to see if the reported upstream <literal>node_id</literal> matches
+              the expected <literal>node_id</literal>. GitHub #587/#588.
+            </para>
+          </listitem>
+        </itemizedlist>
+      </para>
+
+    </sect2>
+  </sect1>
+
   <sect1 id="release-4.4">
-    <title id="release-current">Release 4.4</title>
-    <para><emphasis>27 June, 2019</emphasis></para>
+    <title>Release 4.4</title>
+    <para><emphasis>Thu 27 June, 2019</emphasis></para>
 
     <para>
       &repmgr; 4.4 is a major release.
     </para>
     <para>
-      For details on how to upgrade an existing &repmgr; instrallation, see
+      For details on how to upgrade an existing &repmgr; installation, see
       documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
     </para>
     <para>
@@ -140,7 +413,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+              <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>:
               make output similar to that of
               <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
               for consistency and to make it easier to identify nodes not in the expected
@@ -158,7 +431,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
           <listitem>
             <para>
               <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
-              and <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+              and <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>:
               show the upstream node name as reported by each individual node - this helps visualise
               situations where the cluster is in an unexpected state, and provide a better idea of the
               actual cluster state.
@@ -176,7 +449,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
           <listitem>
             <para>
               <link linkend="repmgr-cluster-show"><command>repmgr cluster show</command></link>
-              and <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>:
+              and <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>:
               check if a node is attached to its advertised upstream node, and issue a
               warning if the node is not attached.
             </para>
@@ -198,7 +471,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
               execute a custom script.
             </para>
             <para>
-              This provides an additional method for fencing an isolated primary node, and/or taking
+              This provided an additional method for fencing an isolated primary node, and/or taking
               other action if one or more standys become disconnected.
             </para>
             <para>
@@ -324,7 +597,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
       &repmgr; 4.3 is a major release.
     </para>
     <para>
-      For details on how to upgrade an existing &repmgr; instrallation, see
+      For details on how to upgrade an existing &repmgr; installation, see
       documentation section <link linkend="upgrading-major-version">Upgrading a major version release</link>.
     </para>
     <para>
@@ -393,7 +666,7 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
 
           <listitem>
             <para>
-              <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>
+              <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>
               additionally displays the node priority and the interval (in seconds) since the
               &repmgrd; instance last verified its upstream node was available.
             </para>

doc/appendix-support.xml

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

doc/cloning-standbys.xml

@@ -102,16 +102,29 @@
      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=somedb</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>
+      barman_config='/path/to/barman.conf'</programlisting>
     </para>
    </note>
 
@@ -188,9 +201,9 @@
     <filename>/usr/bin/barman-wal-restore</filename>,
     <filename>repmgr.conf</filename> should include the following lines:
     <programlisting>
-    barman_host=barman@barmansrv
-    barman_server=somedb
-    restore_command=/usr/bin/barman-wal-restore barmansrv somedb %f %p</programlisting>
+    barman_host='barman@barmansrv'
+    barman_server='pg'
+    restore_command='/usr/bin/barman-wal-restore barmansrv pg %f %p'</programlisting>
    </para>
    <note>
     <simpara>
@@ -444,10 +457,8 @@
 
     <para>
      The recommended way to do this is to store the password in the <literal>postgres</literal> system
-     user's <filename>~/.pgpass</filename> file. It's also possible to store the password in the
-     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>.
+     user's <filename>~/.pgpass</filename> file.  For more information on using the password file, see
+     the documentation section <xref linkend="configuration-password-file"/>.
     </para>
 
     <note>
@@ -469,19 +480,6 @@
      will need to be set during any action which causes <filename>recovery.conf</filename> to be
      rewritten, e.g. <xref linkend="repmgr-standby-follow"/>.
     </para>
-    <para>
-     It is of course also possible to include the password value in the <varname>conninfo</varname>
-     string for each node, but this is obviously a security risk and should be avoided.
-    </para>
-    <para>
-      From PostgreSQL 9.6, <application>libpq</application> supports the <varname>passfile</varname>
-      parameter in connection strings, which can be used to specify a password file other than
-      the default <filename>~/.pgpass</filename>.
-    </para>
-    <para>
-      To have &repmgr; write a custom password file in <varname>primary_conninfo</varname>,
-      specify its location in <varname>passfile</varname> in <filename>repmgr.conf</filename>.
-    </para>
    </sect2>
 
    <sect2 id="cloning-advanced-replication-user" xreflabel="Separate replication user">
@@ -497,6 +495,34 @@
      cloning a node or executing <xref linkend="repmgr-standby-follow"/>.
     </para>
    </sect2>
+
+
+   <sect2 id="cloning-advanced-tablespace-mapping" xreflabel="Tablespace mapping">
+    <title>Tablespace mapping</title>
+    <indexterm>
+      <primary>tablespace mapping</primary>
+    </indexterm>
+    <para>
+      &repmgr; provides a <option>tablespace_mapping</option> configuration
+      file option, which will makes it possible to map the tablespace on the source node to
+      a different location on the local node.
+    </para>
+    <para>
+      To use this, add <option>tablespace_mapping</option> to <filename>repmgr.conf</filename>
+      like this:
+<programlisting>
+  tablespace_mapping='/var/lib/pgsql/tblspc1=/data/pgsql/tblspc1'
+</programlisting>
+    </para>
+    <para>
+      where the left-hand value represents the tablespace on the source node,
+      and the right-hand value represents  the tablespace on the standby to be cloned.
+    </para>
+    <para>
+      This parameter can be provided multiple times.
+    </para>
+   </sect2>
+
  </sect1>
 
 

doc/configuration-file-optional-settings.xml

@@ -119,6 +119,27 @@
       </listitem>
     </varlistentry>
 
+    <varlistentry id="repmgr-conf-ssh-options" xreflabel="ssh_options">
+      <term><varname>ssh_options</varname> (<type>string</type>)
+        <indexterm>
+          <primary><varname>ssh_options</varname> configuration file parameter</primary>
+        </indexterm>
+      </term>
+      <listitem>
+        <para>
+          Options to append to the <command>ssh</command> command when executed
+          by &repmgr;.
+        </para>
+        <para>
+          We recommend adding <literal>-q</literal> to suppress any superfluous
+          SSH chatter such as login banners, and also an explicit
+          <option>ConnectTimeout</option> value,
+          e.g.:
+<programlisting>
+ssh_options='-q -o ConnectTimeout=10'</programlisting>
+        </para>
+      </listitem>
+    </varlistentry>
 
   </variablelist>
 </sect1>

doc/configuration-file.xml

@@ -31,6 +31,8 @@
       <secondary>format</secondary>
     </indexterm>
 
+
+
     <para>
       <filename>repmgr.conf</filename> is a plain text file with one parameter/value
       combination per line.
@@ -39,14 +41,10 @@
       Whitespace is insignificant (except within a quoted parameter value) and blank lines are ignored.
       Hash marks (<literal>#</literal>) designate the remainder of the line as a comment.
       Parameter values that are not simple identifiers or numbers should be single-quoted.
-      Note that single quote cannot be embedded in a parameter value.
     </para>
-    <important>
-      <para>
-        &repmgr; will interpret double-quotes as being part of a string value; only use single quotes
-        to quote parameter values.
-      </para>
-    </important>
+    <para>
+      To embed a single quote in a parameter value, write either two quotes (preferred) or backslash-quote.
+    </para>
 
     <para>
       Example of a valid <filename>repmgr.conf</filename> file:
@@ -56,9 +54,32 @@
 node_id=1
 node_name= node1
 conninfo ='host=node1 dbname=repmgr user=repmgr connect_timeout=2'
-data_directory = /var/lib/pgsql/11/data</programlisting>
+data_directory = '/var/lib/pgsql/12/data'</programlisting>
 
     </para>
+
+    <note>
+      <para>
+        Beginning with <link linkend="release-5.0">repmgr 5.0</link>, configuration
+        file parsing has been tightened up and now matches the way PostgreSQL
+        itself parses configuration files.
+      </para>
+      <para>
+        This means <filename>repmgr.conf</filename> files used with earlier &repmgr;
+        versions may need slight modification before they can be used with &repmgr; 5
+        and later.
+      </para>
+      <para>
+        The main change is that &repmgr; requires most string values to be
+        enclosed in single quotes. For example, this was previously valid:
+          <programlisting>
+conninfo=host=node1 user=repmgr dbname=repmgr connect_timeout=2</programlisting>
+          but must now be changed to:
+          <programlisting>
+conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'</programlisting>
+      </para>
+    </note>
+
   </sect2>
 
 

doc/configuration-password-management.xml

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

doc/configuration-permissions.xml

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

doc/configuration.xml

@@ -148,9 +148,19 @@
             instances in the replication cluster which may potentially become a primary server or
             (in cascading replication) the upstream server of a standby.
           </para>
-          <para>
+         <para>
             PostgreSQL documentation: <ulink url="https://www.postgresql.org/docs/current/runtime-config-replication.html#GUC-MAX-WAL-SENDERS">max_wal_senders</ulink>.
           </para>
+          <note>
+            <para>
+              From <productname>PostgreSQL 12</productname>, <option>max_wal_senders</option>
+              <emphasis>must</emphasis> be set to the same or a higher value as the primary node
+              (at the time the node was cloned), otherwise the standby will refuse
+              to start (unless <option>hot_standby</option> is set to <literal>off</literal>, which
+              will prevent the node from accepting queries).
+            </para>
+          </note>
+
         </listitem>
       </varlistentry>
 
@@ -308,23 +318,7 @@
   &configuration-file-optional-settings;
   &configuration-file-log-settings;
   &configuration-file-service-commands;
+  &configuration-permissions;
+  &configuration-password-management;
 
-  <sect1 id="configuration-permissions" xreflabel="Database user permissions">
-    <title>repmgr database user permissions</title>
-
-    <indexterm>
-      <primary>configuration</primary>
-      <secondary>database user permissions</secondary>
-    </indexterm>
-
-    <para>
-      &repmgr; will create an extension database containing objects
-      for administering &repmgr; metadata. The user defined in the <varname>conninfo</varname>
-      setting must be able to access all objects. Additionally, superuser permissions
-      are required to install the &repmgr; extension. The easiest way to do this
-      is create the &repmgr; user as a superuser, however if this is not
-      desirable, the &repmgr; user can be created as a normal user and a
-      superuser specified with <literal>--superuser</literal> when registering a &repmgr; node.
-    </para>
-  </sect1>
 </chapter>

doc/event-notifications.xml

@@ -148,7 +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>
 

doc/filelist.xml

@@ -21,6 +21,8 @@
 <!ENTITY configuration-file-optional-settings      SYSTEM "configuration-file-optional-settings.xml">
 <!ENTITY configuration-file-log-settings      SYSTEM "configuration-file-log-settings.xml">
 <!ENTITY configuration-file-service-commands   SYSTEM "configuration-file-service-commands.xml">
+<!ENTITY configuration-permissions   SYSTEM "configuration-permissions.xml">
+<!ENTITY configuration-password-management   SYSTEM "configuration-password-management.xml">
 <!ENTITY cloning-standbys  SYSTEM "cloning-standbys.xml">
 <!ENTITY promoting-standby  SYSTEM "promoting-standby.xml">
 <!ENTITY follow-new-primary  SYSTEM "follow-new-primary.xml">
@@ -54,11 +56,11 @@
 <!ENTITY repmgr-cluster-crosscheck SYSTEM "repmgr-cluster-crosscheck.xml">
 <!ENTITY repmgr-cluster-event SYSTEM "repmgr-cluster-event.xml">
 <!ENTITY repmgr-cluster-cleanup SYSTEM "repmgr-cluster-cleanup.xml">
-<!ENTITY repmgr-daemon-status SYSTEM "repmgr-daemon-status.xml">
+<!ENTITY repmgr-service-status SYSTEM "repmgr-service-status.xml">
+<!ENTITY repmgr-service-pause SYSTEM "repmgr-service-pause.xml">
+<!ENTITY repmgr-service-unpause SYSTEM "repmgr-service-unpause.xml">
 <!ENTITY repmgr-daemon-start SYSTEM "repmgr-daemon-start.xml">
 <!ENTITY repmgr-daemon-stop SYSTEM "repmgr-daemon-stop.xml">
-<!ENTITY repmgr-daemon-pause SYSTEM "repmgr-daemon-pause.xml">
-<!ENTITY repmgr-daemon-unpause SYSTEM "repmgr-daemon-unpause.xml">
 
 <!ENTITY appendix-release-notes  SYSTEM "appendix-release-notes.xml">
 <!ENTITY appendix-faq      SYSTEM "appendix-faq.xml">

doc/install-packages.xml

@@ -26,10 +26,18 @@
 	<ulink url="https://dl.2ndquadrant.com/">public repository</ulink>; see following
 	section for details.
   </para>
+  <note>
+    <para>
+      Currently the <ulink url="https://2ndquadrant.com">2ndQuadrant</ulink>
+	  <ulink url="https://dl.2ndquadrant.com/">public repository</ulink> provides
+      support for RedHat/CentOS versions 5, 6 and 7. Support for version 8 is
+      available via the PGDG repository; see below for details.
+    </para>
+  </note>
   <para>
    RPM packages for &repmgr; are also available via Yum through
-   the PostgreSQL Global Development Group RPM repository
-   (<ulink url="https://yum.postgresql.org/">http://yum.postgresql.org/</ulink>).
+   the PostgreSQL Global Development Group (PGDG) RPM repository
+   (<ulink url="https://yum.postgresql.org/">https://yum.postgresql.org/</ulink>).
    Follow the instructions for your distribution (RedHat, CentOS,
    Fedora, etc.) and architecture as detailed there. Note that it can take some days
    for new &repmgr; packages to become available via the this repository.
@@ -42,6 +50,10 @@
       customers, as the PostgreSQL filesystem layout may be different to the community RPMs.
       Please contact your support vendor for assistance.
     </para>
+    <para>
+      See also <link linkend="appendix-faq">FAQ</link> entry
+      <xref linkend="faq-third-party-packages"/>.
+    </para>
   </note>
 
   <para>
@@ -81,9 +93,9 @@
 	    (this enables the 2ndQuadrant repository as a source of &repmgr; packages).
 	  </para>
 	  <para>
-	    For example, for PostgreSQL 10 on CentOS, execute:
+	    For example, for PostgreSQL 11 on CentOS, execute:
 	    <programlisting>
-curl https://dl.2ndquadrant.com/default/release/get/10/rpm | sudo bash</programlisting>
+curl https://dl.2ndquadrant.com/default/release/get/11/rpm | sudo bash</programlisting>
 	  </para>
 
 	  <para>
@@ -99,8 +111,8 @@ curl https://dl.2ndquadrant.com/default/release/get/9.6/rpm | sudo bash</program
 sudo yum repolist</programlisting>
 	    The output should contain two entries like this:
 	    <programlisting>
-2ndquadrant-dl-default-release-pg10/7/x86_64        2ndQuadrant packages (PG10) for 7 - x86_64          4
-2ndquadrant-dl-default-release-pg10-debug/7/x86_64  2ndQuadrant packages (PG10) for 7 - x86_64 - Debug  3</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>
 	  </para>
 	</listitem>
 
@@ -108,7 +120,7 @@ sudo yum repolist</programlisting>
           <para>
             Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
             <programlisting>
-sudo yum install repmgr10</programlisting>
+sudo yum install repmgr11</programlisting>
           </para>
           <note>
             <para>
@@ -153,19 +165,23 @@ yum search repmgr</programlisting>
       To install a specific package version, execute <command>yum --showduplicates list</command>
       for the package in question:
       <programlisting>
-        [root@localhost ~]# yum --showduplicates list repmgr10
-        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>
+[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>
       then append the appropriate version number to the package name with a hyphen, e.g.:
       <programlisting>
-        [root@localhost ~]# yum install repmgr10-4.0.3-1.rhel7</programlisting>
+[root@localhost ~]# yum install repmgr11-4.3-1.el7</programlisting>
     </para>
 
     <para>
@@ -190,7 +206,7 @@ yum search repmgr</programlisting>
   </indexterm>
 
   <para>.deb packages for &repmgr; are available from the
-  PostgreSQL Community APT repository (<ulink url="http://apt.postgresql.org/">http://apt.postgresql.org/</ulink>).
+  PostgreSQL Community APT repository (<ulink url="https://apt.postgresql.org/">https://apt.postgresql.org/</ulink>).
   Instructions can be found in the APT section of the PostgreSQL Wiki
   (<ulink url="https://wiki.postgresql.org/wiki/Apt">https://wiki.postgresql.org/wiki/Apt</ulink>).
   </para>
@@ -220,13 +236,13 @@ yum search repmgr</programlisting>
 
       <itemizedlist>
 
-	<listitem>
-	  <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:
@@ -242,20 +258,20 @@ curl https://dl.2ndquadrant.com/default/release/get/deb | sudo bash</programlist
           </note>
         </listitem>
 
-	<listitem>
-	  <para>
-            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr10</literal>):
+	    <listitem>
+	      <para>
+            Install the &repmgr; version appropriate for your PostgreSQL version (e.g. <literal>repmgr11</literal>):
             <programlisting>
-sudo apt-get install postgresql-10-repmgr</programlisting>
-	  </para>
+              sudo apt-get install postgresql-11-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

@@ -99,6 +99,9 @@
             <entry>
               &repmgr; version
             </entry>
+            <entry>
+              Supported?
+            </entry>
             <entry>
               Latest release
             </entry>
@@ -109,12 +112,31 @@
         </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>
-              <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-4.4">4.4</link> (2019-06-27)
             </entry>
             <entry>
               9.3, 9.4, 9.5, 9.6, 10, 11
@@ -125,6 +147,9 @@
             <entry>
               &repmgr; 3.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-3.3.2.html">3.3.2</ulink> (2017-05-30)
             </entry>
@@ -137,6 +162,9 @@
             <entry>
               &repmgr; 2.x
             </entry>
+            <entry>
+              NO
+            </entry>
             <entry>
               <ulink url="https://repmgr.org/release-notes-2.0.3.html">2.0.3</ulink> (2015-04-16)
             </entry>
@@ -154,8 +182,23 @@
         The &repmgr; 2.x and 3.x series are no longer maintained or supported.
         We strongly recommend  upgrading to the latest &repmgr; version.
       </para>
+      <para>
+        Following the release of &repmgr; 5.0, there will be no further releases of
+        the &repmgr; 4.x series. Note that &repmgr; 5.x is an incremental development
+        of the 4.x series and &repmgr; 4.x users should upgrade to this as soon as possible.
+      </para>
     </important>
 
+  </sect2>
+
+  <sect2 id="install-postgresql-93-94">
+
+    <title>PostgreSQL 9.3 and 9.4 support</title>
+
+    <indexterm>
+      <primary>PostgreSQL 9.3</primary>
+      <secondary>repmgr support</secondary>
+    </indexterm>
 
     <para>
       Note that some &repmgr; functionality is not available in PostgreSQL 9.3 and PostgreSQL 9.4:
@@ -177,5 +220,26 @@
       </listitem>
     </itemizedlist>
 
+    <important>
+      <para>
+        PostgreSQL 9.3 has reached the end of its community support period (final release was
+        <ulink url="https://www.postgresql.org/docs/9.3/release-9-3-25.html">9.3.25</ulink>
+        in November 2018) and will no longer be updated with security or bugfixes.
+      </para>
+      <para>
+        PostgreSQL 9.4 has reached the end of its community support period (final release was
+        <ulink url="https://www.postgresql.org/docs/9.4/release-9-4-26.html">9.4.26</ulink>
+        in February 2020) and will no longer be updated with security or bugfixes.
+      </para>
+      <para>
+        We recommend that users of these versions migrate to a recent PostgreSQL version
+        as soon as possible.
+      </para>
+      <para>
+        For further details, see the  <ulink url="https://www.postgresql.org/support/versioning/">PostgreSQL Versioning Policy</ulink>.
+      </para>
+    </important>
+
   </sect2>
+
  </sect1>

doc/install-source.xml

@@ -24,8 +24,7 @@
     <listitem>
      <para>
       <literal>Debian</literal> and <literal>Ubuntu</literal>: First
-      add the <ulink
-      url="http://apt.postgresql.org/">apt.postgresql.org</ulink>
+      add the <ulink url="https://apt.postgresql.org/">apt.postgresql.org</ulink>
       repository to your <filename>sources.list</filename> if you
       have not already done so, and ensure the source repository is enabled.
      </para>
@@ -36,8 +35,8 @@
          line in the repository file, which is usually
          <filename>/etc/apt/sources.list.d/pgdg.list</filename>, e.g.:
          <programlisting>
-deb http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main
-deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</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>
        </para>
      </tip>
      <para>
@@ -61,6 +60,9 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
          <itemizedlist spacing="compact" mark="bullet">
 
+           <listitem>
+             <simpara><literal>flex</literal></simpara>
+           </listitem>
            <listitem>
              <simpara><literal>libedit-dev</literal></simpara>
            </listitem>
@@ -115,6 +117,9 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
 
          <itemizedlist spacing="compact" mark="bullet">
 
+           <listitem>
+             <simpara><literal>flex</literal></simpara>
+           </listitem>
            <listitem>
              <simpara><literal>libselinux-devel</literal></simpara>
            </listitem>
@@ -177,7 +182,8 @@ deb-src http://apt.postgresql.org/pub/repos/apt/ stretch-pgdg main</programlisti
    </para>
 
    <para>
-    There are also tags for each &repmgr; release, e.g. <literal>v4.2.0</literal>.
+    There are also tags for each <ulink url="https://github.com/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>.
    </para>
 
    <para>

doc/quickstart.xml

@@ -254,7 +254,7 @@
   </para>
   <programlisting>
     node_id=1
-    node_name=node1
+    node_name='node1'
     conninfo='host=node1 user=repmgr dbname=repmgr connect_timeout=2'
     data_directory='/var/lib/postgresql/data'
   </programlisting>
@@ -265,7 +265,6 @@
    server. See sections <xref linkend="configuration"/> and <xref linkend="configuration-file"/>
    for further details about <filename>repmgr.conf</filename>.
   </para>
-
   <note>
     <para>
       &repmgr; only uses <option>pg_bindir</option> when it executes
@@ -368,7 +367,7 @@
   </para>
   <programlisting>
     node_id=2
-    node_name=node2
+    node_name='node2'
     conninfo='host=node2 user=repmgr dbname=repmgr connect_timeout=2'
     data_directory='/var/lib/postgresql/data'</programlisting>
   <para>
@@ -478,6 +477,8 @@
     latest_end_lsn        | 0/7000538
     latest_end_time       | 2017-08-28 15:20:56.418735+09
     slot_name             |
+    sender_host           | node1
+    sender_port           | 5432
     conninfo              | user=repmgr dbname=replication host=node1 application_name=node2
    </programlisting>
    Note that the <varname>conninfo</varname> value is that generated in <filename>recovery.conf</filename>
@@ -497,11 +498,12 @@
   <para>
     Check the node is registered by executing <command>repmgr cluster show</command> on the standby:
     <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster show
-     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>
+      $ 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>
   </para>
   <para>
    Both nodes are now registered with &repmgr; and the records have been copied to the standby server.

doc/repmgr-cluster-show.xml

@@ -55,7 +55,7 @@
     $ repmgr -f /etc/repmgr.conf cluster show
 
      ID | Name  | Role    | Status    | Upstream | Location | Priority | Timeline | Connection string
-    ----+-------+---------+-----------+----------+----------+----------+----------+-----------------------------------------
+    ----+-------+---------+-----------+----------+----------+----------+-----------------------------------------
      1  | node1 | primary | * running |          | default  | 100      | 1        | host=db_node1 dbname=repmgr user=repmgr
      2  | node2 | standby |   running | node1    | default  | 100      | 1        | host=db_node2 dbname=repmgr user=repmgr
      3  | node3 | standby |   running | node1    | default  | 100      | 1        | host=db_node3 dbname=repmgr user=repmgr</programlisting>
@@ -82,18 +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      | 1        | 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 "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>
@@ -233,7 +233,7 @@
   <refsect1>
     <title>See also</title>
     <para>
-     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-daemon-status"/>
+     <xref linkend="repmgr-node-status"/>, <xref linkend="repmgr-node-check"/>, <xref linkend="repmgr-service-status"/>
     </para>
   </refsect1>
 

doc/repmgr-daemon-start.xml

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

doc/repmgr-daemon-stop.xml

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

doc/repmgr-node-rejoin.xml

@@ -356,7 +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 11) may appear to succeed (or indicate there is no action
+     which currently (as of PostgreSQL 12) may appear to succeed (or indicate there is no action
      needed) but potentially allow an impossible action, such as trying to rejoin a standby to a
      primary which is behind the standby. &repmgr; will prevent this situation from occurring.
    </para>

doc/repmgr-node-service.xml

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

doc/repmgr-primary-register.xml

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

doc/repmgr-service-pause.xml

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

doc/repmgr-service-status.xml

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

doc/repmgr-service-unpause.xml

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

doc/repmgr-standby-clone.xml

@@ -18,7 +18,7 @@
     <para>
       <command>repmgr standby clone</command> clones a PostgreSQL node from another
       PostgreSQL node, typically the primary, but optionally from any other node in
-      the cluster or from Barman. It creates the <filename>recovery.conf</filename> file required
+      the cluster or from Barman. It creates the replication configuration required
       to attach the cloned node to the primary node (or another standby, if cascading replication
       is in use).
     </para>
@@ -85,15 +85,20 @@
   </refsect1>
 
   <refsect1 id="repmgr-standby-clone-recovery-conf">
-    <title>Customising recovery.conf</title>
+    <title>Customising replication configuration</title>
     <indexterm>
      <primary>recovery.conf</primary>
      <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
     </indexterm>
 
+	<indexterm>
+     <primary>replication configuration</primary>
+     <secondary>customising with &quot;repmgr standby clone&quot;</secondary>
+    </indexterm>
+
 
    <para>
-     By default, &repmgr; will create a minimal <filename>recovery.conf</filename>
+     By default, &repmgr; will create a minimal replication configuration
      containing following parameters:
    </para>
 
@@ -119,7 +124,7 @@
 
    <para>
      The following additional parameters can be specified in <filename>repmgr.conf</filename>
-     for inclusion in <filename>recovery.conf</filename>:
+     for inclusion in the replication configuration:
    </para>
 
    <itemizedlist spacing="compact" mark="bullet">
@@ -193,9 +198,14 @@
      <secondary>generating for a standby cloned by another method</secondary>
    </indexterm>
 
+   <indexterm>
+     <primary>replication configuration</primary>
+     <secondary>generating for a standby cloned by another method</secondary>
+   </indexterm>
+
    <para>
      &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
-     <command><ulink url="http://docs.pgbarman.org/release/2.5/#recover">barman recover</ulink></command> command).
+     <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command> command).
    </para>
    <para>
      To integrate the standby as a &repmgr; node, once the standby has been cloned,
@@ -216,26 +226,22 @@
    <para>
      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, and will also create a replication slot on the
+     the node to its upstream (in PostgreSQL 12 and later: append replication configuration
+     to <filename>postgresql.auto.conf</filename>), and will also create a replication slot on the
      upstream node if required.
    </para>
    <para>
-     Note that the upstream node must be running. An existing
+     Note that the upstream node must be running. In PostgreSQL 11 and earlier, an existing
      <filename>recovery.conf</filename> will not be overwritten unless the
      <option>-F/--force</option> option is provided.
    </para>
    <para>
      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.
+     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.
    </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>
@@ -261,8 +267,8 @@
           </para>
           <para>
             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.
+            the generated recovery configuration will be displayed
+            but not written.
           </para>
         </listitem>
       </varlistentry>
@@ -309,8 +315,16 @@
         <term><option> --recovery-conf-only</option></term>
         <listitem>
           <para>
-            Create <filename>recovery.conf</filename> file for a previously cloned instance. &repmgr; 4.0.4 and later.
+            Create recovery configuration for a previously cloned instance.
           </para>
+		  <para>
+			In PostgreSQL 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>
 
@@ -338,7 +352,7 @@
         <term><option>--upstream-conninfo</option></term>
         <listitem>
           <para>
-            <literal>primary_conninfo</literal> value to write in <filename>recovery.conf</filename>
+            <literal>primary_conninfo</literal> value to include in the recovery configuration
             when the intended upstream server does not yet exist.
           </para>
           <para>

doc/repmgr-standby-promote.xml

@@ -23,7 +23,8 @@
     <important>
       <para>
         If &repmgrd; is active, you must execute
-        <command><link linkend="repmgr-daemon-pause">repmgr daemon pause</link></command>
+        <command><link linkend="repmgr-service-pause">repmgr service pause</link></command>
+        (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-pause">repmgr service pause</link></command>)
         to temporarily disable &repmgrd; while making any changes
         to the replication cluster.
       </para>
@@ -85,6 +86,7 @@
   </refsect1>
 
 
+
   <refsect1>
     <title>Example</title>
     <para>
@@ -100,6 +102,31 @@
   </refsect1>
 
 
+  <refsect1>
+    <title>User permission requirements</title>
+    <para><emphasis>pg_promote() (PostgreSQL 12)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; uses the <command>pg_promote()</command> function to promote a standby
+      to primary.
+    </para>
+    <para>
+      By default, execution of <command>pg_promote()</command> is restricted to superusers.
+      If the <literal>repmgr</literal> use is not a superuser, execution permission for this
+      function must be granted with e.g.:
+      <programlisting>
+    GRANT EXECUTE ON FUNCTION pg_catalog.pg_promote TO repmgr</programlisting>
+      </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>
+
+    <para>
+      A future &repmgr; release will relax this restriction by falling back to
+      <command>pg_ctl promote</command>, as used for pre-PostgreSQL 12 versions.
+    </para>
+  </refsect1>
+
   <refsect1>
     <title>Options</title>
     <variablelist>

doc/repmgr-standby-register.xml

@@ -108,7 +108,8 @@
     <title>Registering a node not cloned by repmgr</title>
     <para>
       If you've cloned a standby using another method (e.g. <application>barman</application>'s
-     <command>barman recover</command> command), register the node as detailed in section
+     <command><ulink url="https://docs.pgbarman.org/#recover">barman recover</ulink></command>
+     command), register the node as detailed in section
      <xref linkend="repmgr-standby-register-inactive-node"/> then execute
      <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
      to generate the appropriate replication configuration.

doc/repmgr-standby-switchover.xml

@@ -63,6 +63,37 @@
   </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.
+    </para>
+    <para>
+      Note that <command>CHECKPOINT</command> requires database superuser permissions to execute.
+      If the <literal>repmgr</literal> user is not a superuser, the checkpoint operation will
+      fail, though this is not a fatal error &repmgr; will continue the switchover process.
+    </para>
+    <para><emphasis>pg_promote() (PostgreSQL 12)</emphasis></para>
+    <para>
+      From PostgreSQL 12, &repmgr; uses the <command>pg_promote()</command> function to promote a standby
+      to primary.
+    </para>
+    <para>
+      By default, execution of <command>pg_promote()</command> is restricted to superusers.
+      If the <literal>repmgr</literal> use is not a superuser, execution permission for this
+      function must be granted with e.g.:
+      <programlisting>
+    GRANT EXECUTE ON FUNCTION pg_catalog.pg_promote TO repmgr</programlisting>
+    </para>
+    <para>
+      A future &repmgr; release will relax this restriction by falling back to
+      <command>pg_ctl promote</command>, as used for pre-PostgreSQL 12 versions.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
     <title>Options</title>
     <variablelist>
 

doc/repmgr.xml

@@ -26,7 +26,7 @@
   <abstract>
    <para>
    This is the official documentation of &repmgr; &repmgrversion; for
-   use with PostgreSQL 9.3 - PostgreSQL 11.
+   use with PostgreSQL 9.3 - PostgreSQL 12.
    </para>
    <para>
      &repmgr; is being continually developed and we strongly recommend using the
@@ -116,11 +116,11 @@
   &repmgr-cluster-crosscheck;
   &repmgr-cluster-event;
   &repmgr-cluster-cleanup;
-  &repmgr-daemon-status;
+  &repmgr-service-status;
+  &repmgr-service-pause;
+  &repmgr-service-unpause;
   &repmgr-daemon-start;
   &repmgr-daemon-stop;
-  &repmgr-daemon-pause;
-  &repmgr-daemon-unpause;
  </part>
 
  &appendix-release-notes;

doc/repmgrd-automatic-failover.xml

@@ -192,21 +192,23 @@
     connected. Beginning with <link linkend="release-4.4">&repmgr; 4.4</link>
     it is now possible for the affected standbys to build a consensus about whether
     the primary is still available to some standbys (&quot;primary visibility consensus&quot;).
-    This is done by polling each standby for the time it last saw the primary;
-    if any have seen the primary very recently, it's reasonable
+    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
     to infer that the primary is still available and a failover should not be started.
   </para>
 
   <para>
     The time the primary was last seen by each node can be checked by executing
-    <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>,
+    <link linkend="repmgr-service-status"><command>repmgr service status</command></link>
+    (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-status"><command>repmgr daemon status</command></link>)
     which includes this in its output, e.g.:
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+    <programlisting>$ repmgr -f /etc/repmgr.conf service status
  ID | Name  | Role    | Status    | Upstream | repmgrd | PID   | Paused? | Upstream last seen
 ----+-------+---------+-----------+----------+---------+-------+---------+--------------------
- 1  | node1 | primary | * running |          | running | 96563 | no      | n/a
- 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>
+ 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>
 
   </para>
 
@@ -267,11 +269,12 @@
   <para>
     If <option>standby_disconnect_on_failover</option> is set to <literal>true</literal> in
     <filename>repmgr.conf</filename>, in a failover situation &repmgrd; will forcibly disconnect
-    the local node's WAL receiver before making a failover decision.
+    the local node's WAL receiver, and wait for the WAL receiver on all sibling nodes to be
+	disconnected, before making a failover decision.
   </para>
   <note>
     <para>
-      <option>standby_disconnect_on_failover</option> is available from PostgreSQL 9.5 and later.
+      <option>standby_disconnect_on_failover</option> is available with PostgreSQL 9.5 and later.
       Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
     </para>
   </note>
@@ -290,6 +293,12 @@
     plus however many seconds it takes to confirm the WAL receiver is disconnected before
     &repmgrd; proceeds with the failover decision.
   </para>
+  <para>
+	&repmgrd; will wait up to <option>sibling_nodes_disconnect_timeout</option> seconds (default:
+	<literal>30</literal>) to confirm that the WAL receiver on all sibling nodes hase been
+	disconnected before proceding with the failover operation. If the timeout is reached, the
+	failover operation will go ahead anyway.
+  </para>
   <para>
     Following the failover operation, no matter what the outcome, each node will reconnect its WAL receiver.
   </para>

doc/repmgrd-bdr.xml

@@ -94,7 +94,7 @@
         replication_type='bdr'
 
         # Event notification configuration
-        event_notifications=bdr_failover
+        event_notifications='bdr_failover'
         event_notification_command='/path/to/bdr-pgbouncer.sh %n %e %s "%c" "%a" >> /tmp/bdr-failover.log 2>&1'
 
         # repmgrd options

doc/repmgrd-configuration.xml

@@ -8,7 +8,7 @@
   </indexterm>
 
   <para>
-    &repmgrd; is a daemon which runs on each PostgreSQL node,
+    &repmgrd; is a daemon process which runs on each PostgreSQL node,
     monitoring the local node, and (unless it's the primary node) the upstream server
     (the primary server or with cascading replication, another standby) which it's
     connected to.
@@ -81,7 +81,7 @@
               <listitem>
                 <simpara>
                   <literal>connection</literal> - determines server availability
-                  by attempt ingto make a new connection to the upstream node
+                  by attempting to make a new connection to the upstream node
                 </simpara>
               </listitem>
               <listitem>
@@ -398,8 +398,8 @@
             </indexterm>
 
             <para>
-              If <literal>true</literal>, only continue with failover if no standbys have seen
-			  the primary node recently.
+              If <literal>true</literal>, only continue with failover if no standbys
+              (or the witness server, if present) have seen the primary node recently.
             </para>
             <note>
               <para>
@@ -490,6 +490,23 @@
 
     </sect2>
 
+
+    <sect2 id="repmgrd-automatic-failover-configuration-pgbouncer-fencing">
+      <title>Configuring &repmgrd; and pgbouncer to fence a failed primary node</title>
+      <indexterm>
+        <primary>fencing</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>PgBouncer</primary>
+        <secondary>using repmgrd and pgbouncer to fence a failed primary node</secondary>
+      </indexterm>
+      <para>
+        For further details and a reference implementation, see the separate document
+        <ulink url="https://github.com/2ndQuadrant/repmgr/blob/master/doc/repmgrd-node-fencing.md">Fencing a failed master node with repmgrd and PgBouncer</ulink>.
+      </para>
+    </sect2>
+
     <sect2 id="postgresql-service-configuration">
       <title>PostgreSQL service configuration</title>
 
@@ -523,7 +540,8 @@
       </indexterm>
       <para>
         If you are intending to use the <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link>
-        and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> commands, the following
+        and <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link>
+        commands, the following
         parameters <emphasis>must</emphasis> be set in <filename>repmgr.conf</filename>:
         <itemizedlist spacing="compact" mark="bullet">
 
@@ -539,10 +557,10 @@
 
       </para>
       <para>
-        Example (for &repmgr; with PostgreSQL 11 on CentOS 7):
+        Example (for &repmgr; with PostgreSQL 12 on CentOS 7):
         <programlisting>
-repmgrd_service_start_command='sudo systemctl repmgr11 start'
-repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
+repmgrd_service_start_command='sudo systemctl repmgr12 start'
+repmgrd_service_stop_command='sudo systemctl repmgr12 stop'
 </programlisting>
       </para>
       <para>
@@ -865,7 +883,7 @@ repmgrd_service_stop_command='sudo systemctl repmgr11 stop'
     <para>
       The commands <link linkend="repmgr-daemon-start"><command>repmgr daemon start</command></link> and
       <link linkend="repmgr-daemon-stop"><command>repmgr daemon stop</command></link> can be used
-      as convenience wrappers to start and stop &repmgrd;.
+      as convenience wrappers to start and stop &repmgrd; on the local node.
     </para>
     <important>
       <para>

doc/repmgrd-node-fencing.md

@@ -146,7 +146,7 @@ Script and template file should be installed on each node where `repmgrd` is run
 Finally, set `promote_command` in `repmgr.conf` on each node to
 point to the custom promote script:
 
-    promote_command=/var/lib/postgres/repmgr/promote.sh
+    promote_command='/var/lib/postgres/repmgr/promote.sh'
 
 and reload/restart any running `repmgrd` instances for the changes to take
 effect.

doc/repmgrd-operation.xml

@@ -6,9 +6,9 @@
     <secondary>operation</secondary>
   </indexterm>
 
-  <sect1 id="repmgrd-pausing">
+  <sect1 id="repmgrd-pausing" xreflabel="pausing the repmgrd service">
 
-    <title>Pausing repmgrd</title>
+    <title>Pausing the repmgrd service</title>
 
   <indexterm>
     <primary>repmgrd</primary>
@@ -47,7 +47,7 @@
 
   <note>
     <para>
-      For major PostgreSQL upgrades, e.g. from PostgreSQL 10 to PostgreSQL 11,
+      For major PostgreSQL upgrades, e.g. from PostgreSQL 11 to PostgreSQL 12,
       &repmgrd; should be shut down completely and only started up
       once the &repmgr; packages for the new PostgreSQL major version have been installed.
     </para>
@@ -88,17 +88,21 @@
   <sect2 id="repmgrd-pausing-execution">
     <title>Pausing/unpausing &repmgrd;</title>
     <para>
-      To pause &repmgrd;, execute <link linkend="repmgr-daemon-pause"><command>repmgr daemon pause</command></link>, e.g.:
+      To pause &repmgrd;, execute <link linkend="repmgr-service-pause"><command>repmgr service pause</command></link>
+      (&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-pause"><command>repmgr daemon pause</command></link>),
+      e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon pause
+$ repmgr -f /etc/repmgr.conf service pause
 NOTICE: node 1 (node1) paused
 NOTICE: node 2 (node2) paused
 NOTICE: node 3 (node3) paused</programlisting>
     </para>
     <para>
       The state of &repmgrd; on each node can be checked with
-      <link linkend="repmgr-daemon-status"><command>repmgr daemon status</command></link>, e.g.:
-    <programlisting>$ repmgr -f /etc/repmgr.conf daemon status
+      <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
  ID | Name  | Role    | Status  | repmgrd | PID  | Paused?
 ----+-------+---------+---------+---------+------+---------
  1  | node1 | primary | running | running | 7851 | yes
@@ -108,8 +112,8 @@ NOTICE: node 3 (node3) paused</programlisting>
 
     <note>
       <para>
-        If executing a switchover with  <link linkend="repmgr-standby-switchover"><command>repmgr standby switchover</command></link>,
-		&repmgr; will automatically pause/unpause &repmgrd; 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 the &repmgrd; service as part of the switchover process.
       </para>
     </note>
 
@@ -117,29 +121,32 @@ NOTICE: node 3 (node3) paused</programlisting>
       If the primary (in this example, <literal>node1</literal>) is stopped, &repmgrd;
       running on one of the standbys (here: <literal>node2</literal>) will react like this:
       <programlisting>
-[2018-09-20 12:22:21] [WARNING] unable to connect to upstream node "node1" (ID: 1)
-[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 12:22:21] [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 12:22:24] [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>
+[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>
     </para>
     <para>
       If the primary becomes available again (e.g. following a software upgrade), &repmgrd;
       will automatically reconnect, e.g.:
       <programlisting>
-[2018-09-20 13:12:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
+[2019-08-28 12:25:41] [NOTICE] reconnected to upstream node 1 after 8 seconds, resuming monitoring</programlisting>
     </para>
 
     <para>
-      To unpause &repmgrd;, execute <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>, e.g.:
+      To unpause the &repmgrd; service, execute
+      <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
+      ((&repmgr; 4.2 - 4.4: <link linkend="repmgr-service-unpause"><command>repmgr daemon unpause</command></link>),
+      e.g.:
    <programlisting>
-$ repmgr -f /etc/repmgr.conf daemon unpause
+$ repmgr -f /etc/repmgr.conf service unpause
 NOTICE: node 1 (node1) unpaused
 NOTICE: node 2 (node2) unpaused
 NOTICE: node 3 (node3) unpaused</programlisting>
@@ -150,11 +157,11 @@ NOTICE: node 3 (node3) unpaused</programlisting>
         If the previous primary is no longer accessible when &repmgrd;
         is unpaused, no failover action will be taken. Instead, a new primary must be manually promoted using
         <link linkend="repmgr-standby-promote"><command>repmgr standby promote</command></link>,
-		and any standbys attached to the new primary with
-		<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 <link linkend="repmgr-daemon-unpause"><command>repmgr daemon unpause</command></link>
+        This is to prevent execution of <link linkend="repmgr-service-unpause"><command>repmgr service unpause</command></link>
         resulting in the automatic promotion of a new primary, which may be a problem particularly
         in larger clusters, where &repmgrd; could select a different promotion
         candidate to the one intended by the administrator.
@@ -168,17 +175,23 @@ NOTICE: node 3 (node3) unpaused</programlisting>
       The pause state of each node will be stored over a PostgreSQL restart.
     </para>
 
-	<para>
-	  <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>
+    <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>
     <note>
       <para>
-		<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;.
+	    <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.
       </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-daemon-pause"><command>single command</command></link>
+           <link linkend="repmgr-service-pause"><command>single command</command></link>
          </simpara>
        </listitem>
 
@@ -100,11 +100,11 @@
   Start &repmgrd; on each standby and verify that it's running by examining the
   log output, which at log level <literal>INFO</literal> will look like this:
   <programlisting>
-    [2019-03-15 06:32:05] [NOTICE] repmgrd (repmgrd 4.3) starting up
-    [2019-03-15 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>
+    [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>
  </para>
  <para>
   Each &repmgrd; should also have recorded its successful startup as an event:
@@ -112,9 +112,9 @@
     $ repmgr -f /etc/repmgr.conf cluster event --event=repmgrd_start
      Node ID | Name  | Event         | OK | Timestamp           | Details
     ---------+-------+---------------+----+---------------------+--------------------------------------------------------
-     3       | node3 | repmgrd_start | t  | 2019-03-14 04:17:30 | monitoring connection to upstream node "node1" (ID: 1)
-     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>
+     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>
  </para>
  <para>
   Now stop the current primary server with e.g.:
@@ -128,33 +128,33 @@
   decision is made. This is an extract from the log of a standby server (<literal>node2</literal>)
   which has promoted to new primary after failure of the original primary (<literal>node1</literal>).
   <programlisting>
-    [2019-03-15 06:37:50] [WARNING] unable to connect to upstream node "node1" (ID: 1)
-    [2019-03-15 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"
+    [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"
     NOTICE: promoting standby to primary
-    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-11/bin/pg_ctl  -w -D '/var/lib/pgsql/11/data' promote"
+    DETAIL: promoting server "node2" (ID: 2) using "/usr/pgsql-12/bin/pg_ctl  -w -D '/var/lib/pgsql/12/data' promote"
     NOTICE: waiting up to 60 seconds (parameter "promote_check_timeout") for promotion to complete
     NOTICE: STANDBY PROMOTE successful
     DETAIL: server "node2" (ID: 2) was successfully promoted to primary
-    [2019-03-15 06:38:01] [INFO] 3 followers to notify
-    [2019-03-15 06:38:01] [NOTICE] notifying node "node3" (ID: 3) to follow node 2
+    [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
     INFO:  node 3 received notification to follow node 2
-    [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>
+    [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>
  </para>
  <para>
   The cluster status will now look like this, with the original primary (<literal>node1</literal>)
@@ -176,11 +176,11 @@
     $ repmgr -f /etc/repmgr.conf cluster event
      Node ID | Name  | Event                      | OK | Timestamp           | Details
     ---------+-------+----------------------------+----+---------------------+-------------------------------------------------------------
-     3       | node3 | repmgrd_failover_follow    | t  | 2019-03-15 06:38:03 | node 3 now following new upstream node 2
-     3       | node3 | 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>
+     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>
  </para>
 
   </sect1>

doc/switchover.xml

@@ -186,6 +186,7 @@
       NOTICE: local node "node2" (ID: 2) will be promoted to primary; current primary "node1" (ID: 1) will be demoted to standby
       INFO: following shutdown command would be run on node "node1":
         "pg_ctl -l /var/log/postgresql/startup.log -D '/var/lib/postgresql/data' -m fast -W stop"
+      INFO: parameter "shutdown_check_timeout" is set to 60 seconds
     </programlisting>
    </para>
 
@@ -317,7 +318,9 @@
   </para>
   <para>
     If &repmgrd; is in use, it's worth double-checking that
-    all nodes are unpaused by executing <command><link linkend="repmgr-daemon-status">repmgr daemon status</link></command>.
+    all nodes are unpaused by executing
+    <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+    (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-status">repmgr daemon status</link></command>).
   </para>
 
    <note>

doc/upgrading-repmgr.xml

@@ -216,7 +216,9 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
 	  <secondary>checking repmgrd status</secondary>
 	</indexterm>
 	<para>
-      From <link linkend="release-4.2">repmgr 4.2</link>, once the upgrade is complete, execute the <command><link linkend="repmgr-daemon-status">repmgr daemon status</link></command>
+      From <link linkend="release-4.2">repmgr 4.2</link>, once the upgrade is complete, execute the
+      <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+      (&repmgr; 4.2 - 4.4: <command><link linkend="repmgr-service-status">repmgr daemon status</link></command>)
       command (on any node) to show an overview of the status of &repmgrd; on all nodes.
     </para>
   </sect2>
@@ -417,13 +419,13 @@ 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
@@ -432,8 +434,7 @@ ALTER EXTENSION repmgr UPDATE</programlisting>
     <para>
       Please note that the the conversion script will add an empty
       placeholder parameter for <varname>data_directory</varname>, which
-      is a required parameter in repmgr4 and which <emphasis>must</emphasis>
-      be provided.
+      is a required parameter from &repmgr; 4.
     </para>
    </sect3>
   </sect2>

repmgr--4.4--5.0.sql

@@ -0,0 +1,5 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
+
+ALTER FUNCTION set_repmgrd_pid(INT, TEXT) RETURNS NULL ON NULL INPUT;
+

repmgr--5.0.sql

@@ -0,0 +1,224 @@
+-- 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 am_bdr_failover_handler(INT)
+  RETURNS BOOL
+  AS 'MODULE_PATHNAME', 'am_bdr_failover_handler'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION unset_bdr_failover_handler()
+  RETURNS VOID
+  AS 'MODULE_PATHNAME', 'unset_bdr_failover_handler'
+  LANGUAGE C STRICT;
+
+CREATE FUNCTION get_repmgrd_pid()
+  RETURNS INT
+  AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
+  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-action-cluster.c

@@ -247,13 +247,13 @@ do_cluster_show(void)
 		if (cell->node_info->replication_info->timeline_id == UNKNOWN_TIMELINE_ID)
 		{
 			/* display "?" */
-			headers_show[SHOW_PRIORITY].cur_length = 1;
+			headers_show[SHOW_TIMELINE_ID].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);
+			headers_show[SHOW_TIMELINE_ID].cur_length = strlen(buf.data);
 			termPQExpBuffer(&buf);
 		}
 
@@ -987,7 +987,19 @@ build_cluster_matrix(t_node_matrix_rec ***matrix_rec_dest, int *name_length, Ite
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " cluster show --csv -L NOTICE --terse\"");
+							 " cluster show --csv --terse");
+
+		/*
+		 * Usually we'll want NOTICE as the log level, but if the user
+		 * explicitly provided one with --log-level, that will be passed
+		 * in the remote repmgr invocation.
+		 */
+		if (runtime_options.log_level[0] == '\0')
+		{
+			appendPQExpBufferStr(&command,
+								 " -L NOTICE");
+		}
+		appendPQExpBufferChar(&command, '"');
 
 		log_verbose(LOG_DEBUG, "build_cluster_matrix(): executing:\n  %s", command.data);
 
@@ -1175,7 +1187,18 @@ build_cluster_crosscheck(t_node_status_cube ***dest_cube, int *name_length, Item
 		make_remote_repmgr_path(&command, cell->node_info);
 
 		appendPQExpBufferStr(&command,
-							 " cluster matrix --csv -L NOTICE --terse");
+							 " cluster matrix --csv --terse");
+
+		/*
+		 * Usually we'll want NOTICE as the log level, but if the user
+		 * explicitly provided one with --log-level, that will be passed
+		 * in the remote repmgr invocation.
+		 */
+		if (runtime_options.log_level[0] == '\0')
+		{
+			appendPQExpBufferStr(&command,
+								 " -L NOTICE");
+		}
 
 		initPQExpBuffer(&command_output);
 

repmgr-action-daemon.c

@@ -26,478 +26,9 @@
 #include "repmgr-client-global.h"
 #include "repmgr-action-daemon.h"
 
-#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);
-	}
-}
-
+#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")
 
 void
 do_daemon_start(void)
@@ -583,12 +114,12 @@ do_daemon_start(void)
 
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
-		log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+		log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
+		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
 
 		if (runtime_options.wait_provided)
 			timeout = runtime_options.wait;
@@ -598,7 +129,7 @@ do_daemon_start(void)
 		if (PQstatus(conn) != CONNECTION_OK)
 		{
 			log_notice(_("unable to connect to local node"));
-			log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+			log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 			exit(ERR_DB_CONN);
 		}
 
@@ -616,7 +147,7 @@ do_daemon_start(void)
 				PQfinish(conn);
 				log_error(_("repmgrd does not appear to have started after %i seconds"),
 						  timeout);
-				log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+				log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 				exit(ERR_REPMGRD_SERVICE);
 			}
 
@@ -712,12 +243,12 @@ void do_daemon_stop(void)
 	if (runtime_options.no_wait == true || runtime_options.wait == 0)
 	{
 		if (have_db_connection == true)
-			log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
+			log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
 	}
 	else
 	{
 		int i = 0;
-		int timeout = REPMGR_DAEMON_STOP_START_WAIT;
+		int timeout = REPMGR_SERVICE_STOP_START_WAIT;
 		/*
 		 *
 		 */
@@ -732,7 +263,7 @@ void do_daemon_stop(void)
 			log_warning(_("unable to determine repmgrd PID"));
 
 			if (have_db_connection == true)
-				log_hint(REPMGR_DAEMON_STATUS_STOP_HINT);
+				log_hint(REPMGR_SERVICE_STATUS_STOP_HINT);
 
 			exit(ERR_REPMGRD_SERVICE);
 		}
@@ -764,7 +295,7 @@ void do_daemon_stop(void)
 						  timeout);
 
 				if (have_db_connection == true)
-					log_hint(REPMGR_DAEMON_STATUS_START_HINT);
+					log_hint(REPMGR_SERVICE_STATUS_START_HINT);
 
 				exit(ERR_REPMGRD_SERVICE);
 			}
@@ -783,53 +314,29 @@ void do_daemon_help(void)
 	print_help_header();
 
 	printf(_("Usage:\n"));
-	printf(_("    %s [OPTIONS] daemon status\n"),  progname());
-	printf(_("    %s [OPTIONS] daemon pause\n"),   progname());
-	printf(_("    %s [OPTIONS] daemon unpause\n"), progname());
 	printf(_("    %s [OPTIONS] daemon start\n"),   progname());
 	printf(_("    %s [OPTIONS] daemon stop\n"),    progname());
-	puts("");
 
-	printf(_("DAEMON STATUS\n"));
-	puts("");
-	printf(_("  \"daemon status\" shows the status of repmgrd on each node in the cluster\n"));
-	puts("");
-	printf(_("    --csv                     emit output as CSV\n"));
-	printf(_("    --detail                  show additional detail\n"));
-	printf(_("    --verbose                 show text of database connection error messages\n"));
 	puts("");
 
 	printf(_("DAEMON START\n"));
 	puts("");
-	printf(_("  \"daemon start\" attempts to start repmgrd\n"));
+	printf(_("  \"daemon start\" attempts to start repmgrd on the local node\n"));
 	puts("");
 	printf(_("    --dry-run               check prerequisites but don't start repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to start (default: %i seconds)\n"), REPMGR_SERVICE_STOP_START_WAIT);
 	printf(_("    --no-wait               don't wait for repmgrd to start\n"));
 	puts("");
 
 	printf(_("DAEMON STOP\n"));
 	puts("");
-	printf(_("  \"daemon stop\" attempts to stop repmgrd\n"));
+	printf(_("  \"daemon stop\" attempts to stop repmgrd on the local node\n"));
 	puts("");
 	printf(_("    --dry-run               check prerequisites but don't stop repmgrd\n"));
-	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_DAEMON_STOP_START_WAIT);
+	printf(_("    -w/--wait               wait for repmgrd to stop (default: %i seconds)\n"), REPMGR_SERVICE_STOP_START_WAIT);
 	printf(_("    --no-wait               don't wait for repmgrd to stop\n"));
 	puts("");
 
-	printf(_("DAEMON PAUSE\n"));
-	puts("");
-	printf(_("  \"daemon pause\" instructs repmgrd on each node to pause failover detection\n"));
-	puts("");
-	printf(_("    --dry-run               check if nodes are reachable but don't pause repmgrd\n"));
 	puts("");
 
-	printf(_("DAEMON UNPAUSE\n"));
-	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

@@ -19,10 +19,6 @@
 #ifndef _REPMGR_ACTION_DAEMON_H_
 #define _REPMGR_ACTION_DAEMON_H_
 
-
-extern void do_daemon_status(void);
-extern void do_daemon_pause(void);
-extern void do_daemon_unpause(void);
 extern void do_daemon_start(void);
 extern void do_daemon_stop(void);
 

repmgr-action-primary.c

@@ -106,7 +106,7 @@ do_primary_register(void)
 	current_primary_id = get_primary_node_id(conn);
 	if (current_primary_id != NODE_NOT_FOUND && current_primary_id != config_file_options.node_id)
 	{
-		log_debug("XXX %i", current_primary_id);
+		log_debug("current active primary node ID is %i", current_primary_id);
 		primary_conn = establish_primary_db_connection(conn, false);
 
 		if (PQstatus(primary_conn) == CONNECTION_OK)

repmgr-action-service.c

@@ -0,0 +1,535 @@
+/*
+ * repmgr-action-service.c
+ *
+ * Implements repmgrd 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 <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;
+
+		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_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-service.h

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

repmgr-action-standby.c

@@ -112,8 +112,10 @@ static void get_barman_property(char *dst, char *name, char *local_repmgr_direct
 static int	get_tablespace_data_barman(char *, TablespaceDataList *);
 static char *make_barman_ssh_command(char *buf);
 
-static bool create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_conninfo, char *dest, bool as_file);
+static bool create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_conninfo, int server_version_num, char *dest, bool as_file);
 static void write_primary_conninfo(PQExpBufferData *dest, t_conninfo_param_list *param_list);
+static bool write_standby_signal(void);
+
 static bool check_sibling_nodes(NodeInfoList *sibling_nodes, SiblingNodeStats *sibling_nodes_stats);
 static bool check_free_wal_senders(int available_wal_senders, SiblingNodeStats *sibling_nodes_stats, bool *dry_run_success);
 static bool check_free_slots(t_node_info *local_node_record, SiblingNodeStats *sibling_nodes_stats, bool *dry_run_success);
@@ -133,12 +135,13 @@ static bool parse_data_directory_config(const char *node_check_output);
  *
  * Parameters:
  *  --upstream-conninfo
+ *  --upstream-node-id
  *  --no-upstream-connection
  *  -F/--force
  *  --dry-run
  *  -c/--fast-checkpoint
  *  --copy-external-config-files
- *  --recovery-min-apply-delay
+ *  -R/--remote-user
  *  --replication-user (only required if no upstream record)
  *  --without-barman
  *  --recovery-conf-only
@@ -215,7 +218,7 @@ do_standby_clone(void)
 
 	/*
 	 * Initialise list of conninfo parameters which will later be used to
-	 * create the `primary_conninfo` string in recovery.conf .
+	 * create the "primary_conninfo" recovery parameter.
 	 *
 	 * We'll initialise it with the host settings specified on the command
 	 * line. As it's possible the standby will be cloned from a node different
@@ -665,10 +668,21 @@ do_standby_clone(void)
 
 	/* Write the recovery.conf file */
 
-	if (create_recovery_file(&local_node_record, &recovery_conninfo, local_data_directory, true) == false)
+	if (create_recovery_file(&local_node_record,
+							 &recovery_conninfo,
+							 source_server_version_num,
+							 local_data_directory,
+							 true) == false)
 	{
 		/* create_recovery_file() will log an error */
-		log_notice(_("unable to create recovery.conf; see preceding error messages"));
+		if (source_server_version_num >= 120000)
+		{
+			log_notice(_("unable to write replication configuration; see preceding error messages"));
+		}
+		else
+		{
+			log_notice(_("unable to create recovery.conf; see preceding error messages"));
+		}
 		log_hint(_("data directory (\"%s\") may need to be cleaned up manually"),
 				 local_data_directory);
 
@@ -944,6 +958,13 @@ _do_create_recovery_conf(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
+
+	/* check connection */
+	source_conn = establish_db_connection_by_params(&source_conninfo, true);
+
+	/* Verify that source is a supported server version */
+	(void) check_server_version(source_conn, "source node", true, NULL);
+
 	/*
 	 * Do some sanity checks on the data directory to make sure
 	 * it contains a valid but dormant instance
@@ -953,14 +974,17 @@ _do_create_recovery_conf(void)
 		case DIR_ERROR:
 			log_error(_("unable to access specified data directory \"%s\""), local_data_directory);
 			log_detail("%s", strerror(errno));
+			PQfinish(source_conn);
 			exit(ERR_BAD_CONFIG);
 			break;
 		case DIR_NOENT:
 			log_error(_("specified data directory \"%s\" does not exist"), local_data_directory);
+			PQfinish(source_conn);
 			exit(ERR_BAD_CONFIG);
 			break;
 		case DIR_EMPTY:
 			log_error(_("specified data directory \"%s\" is empty"), local_data_directory);
+			PQfinish(source_conn);
 			exit(ERR_BAD_CONFIG);
 			break;
 		case DIR_NOT_EMPTY:
@@ -968,6 +992,7 @@ _do_create_recovery_conf(void)
 			if (!is_pg_dir(local_data_directory))
 			{
 				log_error(_("specified data directory \"%s\" does not contain a PostgreSQL instance"), local_data_directory);
+				PQfinish(source_conn);
 				exit(ERR_BAD_CONFIG);
 			}
 
@@ -977,7 +1002,16 @@ _do_create_recovery_conf(void)
 				{
 					log_error(_("specified data directory \"%s\" appears to contain a running PostgreSQL instance"),
 							  local_data_directory);
-					log_hint(_("use -F/--force to create \"recovery.conf\" anyway"));
+
+					if (PQserverVersion(source_conn) >= 120000)
+					{
+						log_hint(_("use -F/--force to create replication configuration anyway"));
+					}
+					else
+					{
+						log_hint(_("use -F/--force to create \"recovery.conf\" anyway"));
+					}
+
 					exit(ERR_BAD_CONFIG);
 				}
 
@@ -985,11 +1019,25 @@ _do_create_recovery_conf(void)
 
 				if (runtime_options.dry_run == true)
 				{
-					log_warning(_("\"recovery.conf\" would be created in an active data directory"));
+					if (PQserverVersion(source_conn) >= 120000)
+					{
+						log_warning(_("replication configuration would be created in an active data directory"));
+					}
+					else
+					{
+						log_warning(_("\"recovery.conf\" would be created in an active data directory"));
+					}
 				}
 				else
 				{
-					log_warning(_("creating \"recovery.conf\" in an active data directory"));
+					if (PQserverVersion(source_conn) >= 120000)
+					{
+						log_warning(_("creating replication configuration in an active data directory"));
+					}
+					else
+					{
+						log_warning(_("creating \"recovery.conf\" in an active data directory"));
+					}
 				}
 			}
 			break;
@@ -997,11 +1045,6 @@ _do_create_recovery_conf(void)
 			break;
 	}
 
-	/* check connection */
-	source_conn = establish_db_connection_by_params(&source_conninfo, true);
-
-	/* Verify that source is a supported server version */
-	(void) check_server_version(source_conn, "source node", true, NULL);
 
 	/* determine node for primary_conninfo */
 
@@ -1174,60 +1217,92 @@ _do_create_recovery_conf(void)
 		}
 	}
 
-	/* check if recovery.conf exists */
-
-	snprintf(recovery_file_path, sizeof(recovery_file_path),
-			 "%s/%s",
-			 local_data_directory,
-			 RECOVERY_COMMAND_FILE);
-
-	if (stat(recovery_file_path, &st) == -1)
+	/* check if recovery.conf exists (Pg11 and earlier only) */
+	if (PQserverVersion(upstream_conn) < 120000)
 	{
-		if (errno != ENOENT)
-		{
-			log_error(_("unable to check for existing \"recovery.conf\" file in \"%s\""),
-					  local_data_directory);
-			log_detail("%s", strerror(errno));
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-	else
-	{
-		if (runtime_options.force == false)
-		{
-			log_error(_("\"recovery.conf\" already exists in \"%s\""),
-					  local_data_directory);
-			log_hint(_("use -F/--force to overwrite an existing \"recovery.conf\" file"));
-			exit(ERR_BAD_CONFIG);
-		}
+		snprintf(recovery_file_path, sizeof(recovery_file_path),
+				 "%s/%s",
+				 local_data_directory,
+				 RECOVERY_COMMAND_FILE);
 
-		if (runtime_options.dry_run == true)
+		if (stat(recovery_file_path, &st) == -1)
 		{
-			log_warning(_("the existing \"recovery.conf\" file would be overwritten"));
+			if (errno != ENOENT)
+			{
+				log_error(_("unable to check for existing \"recovery.conf\" file in \"%s\""),
+						  local_data_directory);
+				log_detail("%s", strerror(errno));
+			exit(ERR_BAD_CONFIG);
+			}
 		}
 		else
 		{
-			log_warning(_("the existing \"recovery.conf\" file will be overwritten"));
+			if (runtime_options.force == false)
+			{
+				log_error(_("\"recovery.conf\" already exists in \"%s\""),
+						  local_data_directory);
+				log_hint(_("use -F/--force to overwrite an existing \"recovery.conf\" file"));
+				exit(ERR_BAD_CONFIG);
+			}
+
+			if (runtime_options.dry_run == true)
+			{
+				log_warning(_("the existing \"recovery.conf\" file would be overwritten"));
+			}
+			else
+			{
+				log_warning(_("the existing \"recovery.conf\" file will be overwritten"));
+			}
 		}
 	}
 
 	if (runtime_options.dry_run == true)
 	{
 		char		recovery_conf_contents[MAXLEN] = "";
-		create_recovery_file(&local_node_record, &recovery_conninfo, recovery_conf_contents, false);
+		create_recovery_file(&local_node_record,
+							 &recovery_conninfo,
+							 PQserverVersion(upstream_conn),
+							 recovery_conf_contents,
+							 false);
+
+		if (PQserverVersion(upstream_conn) >= 120000)
+		{
+			log_info(_("following items would be added to \"postgresql.auto.conf\" in \"%s\""), local_data_directory);
+		}
+		else
+		{
+			log_info(_("would create \"recovery.conf\" file in \"%s\""), local_data_directory);
+		}
 
-		log_info(_("would create \"recovery.conf\" file in \"%s\""), local_data_directory);
 		log_detail(_("\n%s"), recovery_conf_contents);
 	}
 	else
 	{
-		if (!create_recovery_file(&local_node_record, &recovery_conninfo, local_data_directory, true))
+		if (!create_recovery_file(&local_node_record,
+								  &recovery_conninfo,
+								  PQserverVersion(upstream_conn),
+								  local_data_directory,
+								  true))
 		{
-			log_error(_("unable to create \"recovery.conf\""));
+			if (PQserverVersion(upstream_conn) >= 120000)
+			{
+				log_error(_("unable to write replication configuration to \"postgresql.auto.conf\""));
+			}
+			else
+			{
+				log_error(_("unable to create \"recovery.conf\""));
+			}
 		}
 		else
 		{
-			log_notice(_("\"recovery.conf\" created as \"%s\""), recovery_file_path);
+			if (PQserverVersion(upstream_conn) >= 120000)
+			{
+				log_notice(_("replication configuration written to \"postgresql.auto.conf\""));
+			}
+			else
+			{
+				log_notice(_("\"recovery.conf\" created as \"%s\""), recovery_file_path);
+			}
 
 			if (node_is_running == true)
 			{
@@ -1236,6 +1311,23 @@ _do_create_recovery_conf(void)
 		}
 	}
 
+	/* Pg12 and later: add standby.signal, if not already there */
+	if (PQserverVersion(upstream_conn) >= 120000)
+	{
+		if (runtime_options.dry_run == true)
+		{
+			log_info(_("would write \"standby.signal\" file"));
+
+		}
+		else
+		{
+			if (write_standby_signal() == false)
+			{
+				log_error(_("unable to write \"standby.signal\" file"));
+			}
+		}
+	}
+
 	/* add replication slot, if required */
 	if (slot_creation_required == true)
 	{
@@ -3069,7 +3161,11 @@ do_standby_follow_internal(PGconn *primary_conn, PGconn *follow_target_conn, t_n
 	log_notice(_("setting node %i's upstream to node %i"),
 			   config_file_options.node_id, follow_target_node_record->node_id);
 
-	if (!create_recovery_file(&local_node_record, &recovery_conninfo, config_file_options.data_directory, true))
+	if (!create_recovery_file(&local_node_record,
+							  &recovery_conninfo,
+							  PQserverVersion(primary_conn),
+							  config_file_options.data_directory,
+							  true))
 	{
 		*error_code = general_error_code;
 		return false;
@@ -3683,7 +3779,9 @@ do_standby_switchover(void)
 
 	if (runtime_options.dry_run == true)
 	{
-		log_info(_("able to execute \"%s\" on remote host \"localhost\""), progname());
+		log_info(_("able to execute \"%s\" on remote host \"%s\""),
+				 progname(),
+				 remote_host);
 	}
 
 	/*
@@ -3844,7 +3942,7 @@ do_standby_switchover(void)
 							exit(ERR_SWITCHOVER_FAIL);
 						}
 
-						log_warning(_("number of pending archive files on demotion candidate \"%s\" is critical"),
+						log_warning(_("number of pending archive files on demotion candidate \"%s\" exceeds the critical threshold"),
 									remote_node_record.node_name);
 						log_detail(_("%i pending archive files (critical threshold: %i)"),
 								   files, threshold);
@@ -3854,7 +3952,7 @@ do_standby_switchover(void)
 
 				case CHECK_STATUS_WARNING:
 					{
-						log_warning(_("number of pending archive files on demotion candidate \"%s\" is warning"),
+						log_warning(_("number of pending archive files on demotion candidate \"%s\" exceeds the warning threshold"),
 									remote_node_record.node_name);
 						log_detail(_("%i pending archive files (warning threshold: %i)"),
 								   files, threshold);
@@ -4263,6 +4361,9 @@ do_standby_switchover(void)
 				 remote_node_record.node_name,
 				 shutdown_command);
 
+		log_info(_("parameter \"shutdown_check_timeout\" is set to %i seconds"),
+				 config_file_options.shutdown_check_timeout);
+
 		clear_node_info_list(&sibling_nodes);
 
 		key_value_list_free(&remote_config_files);
@@ -4724,7 +4825,7 @@ do_standby_switchover(void)
 				log_warning(_("unable to unpause repmgrd on %i node(s)"),
 							error_node_count);
 				log_detail(_("errors encountered for following node(s):\n%s"), detail.data);
-				log_hint(_("check node connection and status; unpause manually with \"repmgr daemon unpause\""));
+				log_hint(_("check node connection and status; unpause manually with \"repmgr service unpause\""));
 
 				termPQExpBuffer(&detail);
 			}
@@ -5431,7 +5532,7 @@ check_upstream_config(PGconn *conn, int server_version_num, t_node_info *upstrea
 	{
 		if (i == 0)
 		{
-			log_error(_("parameter 'hot_standby' must be set to 'on'"));
+			log_error(_("parameter \"hot_standby\" must be set to \"on\""));
 		}
 
 		if (exit_on_error == true)
@@ -5449,7 +5550,7 @@ check_upstream_config(PGconn *conn, int server_version_num, t_node_info *upstrea
 	{
 		if (pg_setting_ok == true)
 		{
-			log_error(_("parameter \"max_wal_senders\" must be set to be at least 1 %i"), i);
+			log_error(_("parameter \"max_wal_senders\" must be set to be at least %i"), i);
 			log_hint(_("\"max_wal_senders\" should be set to at least the number of expected standbys"));
 		}
 
@@ -6014,7 +6115,7 @@ run_basebackup(t_node_info *node_record)
 				if (record_status == RECORD_FOUND)
 				{
 					log_verbose(LOG_INFO,
-								_("replication slot \"%s\" aleady exists on upstream node %i"),
+								_("replication slot \"%s\" already exists on upstream node %i"),
 								node_record->slot_name,
 								upstream_node_id);
 					slot_exists_on_upstream = true;
@@ -6668,9 +6769,8 @@ make_barman_ssh_command(char *buf)
 
 
 static int
-			get_tablespace_data_barman
-			(char *tablespace_data_barman,
-			 TablespaceDataList *tablespace_list)
+get_tablespace_data_barman(char *tablespace_data_barman,
+						   TablespaceDataList *tablespace_list)
 {
 	/*
 	 * Example: [('main', 24674, '/var/lib/postgresql/tablespaces/9.5/main'),
@@ -6944,49 +7044,55 @@ check_recovery_type(PGconn *conn)
 
 
 /*
- * Creates a recovery.conf file for a standby
+ * Creates recovery configuration for a standby.
  *
  * A database connection pointer is required for escaping primary_conninfo
  * parameters. When cloning from Barman and --no-upstream-connection supplied,
  * this might not be available.
  */
 static bool
-create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_conninfo, char *dest, bool as_file)
+create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_conninfo, int server_version_num, char *dest, bool as_file)
 {
 	PQExpBufferData recovery_file_buf;
+	PQExpBufferData primary_conninfo_buf;
 	char		recovery_file_path[MAXPGPATH] = "";
 	FILE	   *recovery_file;
 	mode_t		um;
 
-	/* create file in buffer */
-	initPQExpBuffer(&recovery_file_buf);
+	KeyValueList recovery_config = {NULL, NULL};
+	KeyValueListCell *cell = NULL;
 
-	/* standby_mode = 'on' */
-	appendPQExpBufferStr(&recovery_file_buf,
-						 "standby_mode = 'on'\n");
+	initPQExpBuffer(&primary_conninfo_buf);
+
+	/* standby_mode = 'on' (Pg 11 and earlier) */
+	if (server_version_num < 120000)
+	{
+		key_value_list_set(&recovery_config,
+						   "standby_mode", "on");
+	}
 
 	/* primary_conninfo = '...' */
-	write_primary_conninfo(&recovery_file_buf, primary_conninfo);
+	write_primary_conninfo(&primary_conninfo_buf, primary_conninfo);
+	key_value_list_set(&recovery_config,
+					   "primary_conninfo", primary_conninfo_buf.data);
 
 	/* recovery_target_timeline = 'latest' */
-	appendPQExpBufferStr(&recovery_file_buf,
-						 "recovery_target_timeline = 'latest'\n");
+	key_value_list_set(&recovery_config,
+					   "recovery_target_timeline", "latest");
 
 
 	/* recovery_min_apply_delay = ... (optional) */
 	if (config_file_options.recovery_min_apply_delay_provided == true)
 	{
-		appendPQExpBuffer(&recovery_file_buf,
-						  "recovery_min_apply_delay = %s\n",
-						  config_file_options.recovery_min_apply_delay);
+		key_value_list_set(&recovery_config,
+						   "recovery_min_apply_delay", config_file_options.recovery_min_apply_delay);
 	}
 
 	/* primary_slot_name = '...' (optional, for 9.4 and later) */
 	if (config_file_options.use_replication_slots)
 	{
-		appendPQExpBuffer(&recovery_file_buf,
-						  "primary_slot_name = %s\n",
-						  node_record->slot_name);
+		key_value_list_set(&recovery_config,
+						   "primary_slot_name", node_record->slot_name);
 	}
 
 	/*
@@ -6997,9 +7103,8 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_co
 	{
 		char	   *escaped = escape_recovery_conf_value(config_file_options.restore_command);
 
-		appendPQExpBuffer(&recovery_file_buf,
-						  "restore_command = '%s'\n",
-						  escaped);
+		key_value_list_set(&recovery_config,
+						  "restore_command", escaped);
 		free(escaped);
 	}
 
@@ -7007,33 +7112,84 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_co
 	if (config_file_options.archive_cleanup_command[0] != '\0')
 	{
 		char	   *escaped = escape_recovery_conf_value(config_file_options.archive_cleanup_command);
-		appendPQExpBuffer(&recovery_file_buf,
-						  "archive_cleanup_command = '%s'\n",
-						  escaped);
+
+		key_value_list_set(&recovery_config,
+						  "archive_cleanup_command", escaped);
 		free(escaped);
 	}
 
-	if (as_file == true)
+
+
+
+	if (as_file == false)
 	{
-		maxpath_snprintf(recovery_file_path, "%s/%s", dest, RECOVERY_COMMAND_FILE);
-		log_debug("create_recovery_file(): creating \"%s\"...",
-				  recovery_file_path);
+		/* create file in buffer */
+		initPQExpBuffer(&recovery_file_buf);
 
-		/* Set umask to 0600 */
-		um = umask((~(S_IRUSR | S_IWUSR)) & (S_IRWXG | S_IRWXO));
-		recovery_file = fopen(recovery_file_path, "w");
-		umask(um);
-
-		if (recovery_file == NULL)
+		for (cell = recovery_config.head; cell; cell = cell->next)
 		{
-			log_error(_("unable to create recovery.conf file at \"%s\""),
-					  recovery_file_path);
-			log_detail("%s", strerror(errno));
+			appendPQExpBuffer(&recovery_file_buf,
+							  "%s = '%s'\n",
+							  cell->key, cell->value);
+		}
 
+		maxlen_snprintf(dest, "%s", recovery_file_buf.data);
+
+		termPQExpBuffer(&recovery_file_buf);
+
+		return true;
+	}
+
+
+	/*
+	 * PostgreSQL 12 and later: modify postgresql.auto.conf
+	 *
+	 */
+	if (server_version_num >= 120000)
+	{
+
+		if (modify_auto_conf(dest, &recovery_config) == false)
+		{
 			return false;
 		}
 
-		log_debug("recovery file is:\n%s", recovery_file_buf.data);
+		if (write_standby_signal() == false)
+		{
+			return false;
+		}
+
+		return true;
+	}
+
+	/*
+	 * PostgreSQL 11 and earlier: write recovery.conf
+	 */
+	maxpath_snprintf(recovery_file_path, "%s/%s", dest, RECOVERY_COMMAND_FILE);
+	log_debug("create_recovery_file(): creating \"%s\"...",
+			  recovery_file_path);
+
+	/* Set umask to 0600 */
+	um = umask((~(S_IRUSR | S_IWUSR)) & (S_IRWXG | S_IRWXO));
+	recovery_file = fopen(recovery_file_path, "w");
+	umask(um);
+
+	if (recovery_file == NULL)
+	{
+		log_error(_("unable to create recovery.conf file at \"%s\""),
+				  recovery_file_path);
+		log_detail("%s", strerror(errno));
+
+		return false;
+	}
+
+	for (cell = recovery_config.head; cell; cell = cell->next)
+	{
+		initPQExpBuffer(&recovery_file_buf);
+		appendPQExpBuffer(&recovery_file_buf,
+						  "%s = '%s'\n",
+						  cell->key, cell->value);
+
+		log_debug("recovery.conf line: %s", recovery_file_buf.data);
 
 		if (fputs(recovery_file_buf.data, recovery_file) == EOF)
 		{
@@ -7043,14 +7199,58 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *primary_co
 			return false;
 		}
 
-		fclose(recovery_file);
-	}
-	else
-	{
-		maxlen_snprintf(dest, "%s", recovery_file_buf.data);
+		termPQExpBuffer(&recovery_file_buf);
 	}
 
-	termPQExpBuffer(&recovery_file_buf);
+
+	fclose(recovery_file);
+
+	return true;
+}
+
+
+/*
+ * create standby.signal (PostgreSQL 12 and later)
+ */
+
+static bool
+write_standby_signal(void)
+{
+	char	    standby_signal_file_path[MAXPGPATH] = "";
+	FILE	   *file;
+	mode_t		um;
+
+	snprintf(standby_signal_file_path, MAXPGPATH,
+			 "%s/%s",
+			 config_file_options.data_directory,
+			 STANDBY_SIGNAL_FILE);
+
+	/* Set umask to 0600 */
+	um = umask((~(S_IRUSR | S_IWUSR)) & (S_IRWXG | S_IRWXO));
+	file = fopen(standby_signal_file_path, "w");
+	umask(um);
+
+	if (file == NULL)
+	{
+		log_error(_("unable to create %s file at \"%s\""),
+				  STANDBY_SIGNAL_FILE,
+				  standby_signal_file_path);
+		log_detail("%s", strerror(errno));
+
+		return false;
+	}
+
+	if (fputs("# created by repmgr\n", file) == EOF)
+	{
+		log_error(_("unable to write to %s file at \"%s\""),
+				  STANDBY_SIGNAL_FILE,
+				  standby_signal_file_path);
+		fclose(file);
+
+		return false;
+	}
+
+	fclose(file);
 
 	return true;
 }
@@ -7140,8 +7340,7 @@ write_primary_conninfo(PQExpBufferData *dest, t_conninfo_param_list *param_list)
 
 	escaped = escape_recovery_conf_value(conninfo_buf.data);
 
-	appendPQExpBuffer(dest,
-					  "primary_conninfo = '%s'\n", escaped);
+	appendPQExpBufferStr(dest, escaped);
 
 	free(escaped);
 	free_conninfo_params(&env_conninfo);
@@ -7796,7 +7995,7 @@ do_standby_help(void)
 			 "                                        when the intended upstream server does not yet exist\n"));
 	printf(_("  --upstream-node-id                  ID of the upstream node to replicate from (optional, defaults to primary node)\n"));
 	printf(_("  --without-barman                    do not use Barman even if configured\n"));
-	printf(_("  --recovery-conf-only                create \"recovery.conf\" file for a previously cloned instance\n"));
+	printf(_("  --recovery-conf-only                generate replication configuration for a previously cloned instance\n"));
 
 	puts("");
 

repmgr-client-global.h

@@ -260,5 +260,6 @@ extern void drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slo
 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 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.c

@@ -33,9 +33,10 @@
  * NODE SERVICE
  * NODE CONTROL
  *
- * DAEMON STATUS
- * DAEMON PAUSE
- * DAEMON UNPAUSE
+ * SERVICE STATUS
+ * SERVICE PAUSE
+ * SERVICE UNPAUSE
+ *
  * DAEMON START
  * DAEMON STOP
  *
@@ -57,6 +58,7 @@
 #include <sys/stat.h>
 #include <signal.h>
 
+
 #include "repmgr.h"
 #include "compat.h"
 #include "controldata.h"
@@ -68,11 +70,11 @@
 #include "repmgr-action-bdr.h"
 #include "repmgr-action-node.h"
 #include "repmgr-action-cluster.h"
+#include "repmgr-action-service.h"
 #include "repmgr-action-daemon.h"
 
 #include <storage/fd.h>			/* for PG_TEMP_FILE_PREFIX */
 
-
 /* globally available variables *
  * ============================ */
 
@@ -184,7 +186,7 @@ main(int argc, char **argv)
 		strncpy(runtime_options.username, pw->pw_name, MAXLEN);
 	}
 
-	/* Make getopt emitting errors */
+	/* Make getopt emit errors */
 	opterr = 1;
 
 	while ((c = getopt_long(argc, argv, "?Vb:f:FwWd:h:p:U:R:S:D:ck:L:qtvC:", long_options,
@@ -669,33 +671,20 @@ main(int argc, char **argv)
 				break;
 
 				/*-----------------------------
-				 * options deprecated since 3.3
+				 * options deprecated since 4.0
 				 *-----------------------------
 				 */
 			case OPT_CHECK_UPSTREAM_CONFIG:
 				item_list_append(&cli_warnings,
 								 _("--check-upstream-config is deprecated; use --dry-run instead"));
 				break;
-			case OPT_DATA_DIR:
-				item_list_append(&cli_warnings,
-								 _("--data-dir is deprecated; use -D/--pgdata instead"));
-				break;
-			case OPT_NO_CONNINFO_PASSWORD:
-				item_list_append(&cli_warnings,
-								 _("--no-conninfo-password is deprecated; use --use-recovery-conninfo-password to explicitly set a password"));
-				break;
+
 				/* -C/--remote-config-file */
 			case 'C':
 				item_list_append(&cli_warnings,
 								 _("--remote-config-file is no longer required"));
 				break;
 
-				/* --recovery-min-apply-delay */
-			case OPT_RECOVERY_MIN_APPLY_DELAY:
-				item_list_append(&cli_warnings,
-								 _("--recovery-min-apply-delay is now a configuration file parameter, \"recovery_min_apply_delay\""));
-				break;
-
 			case ':':   /* missing option argument */
 				option_error_found = true;
 				break;
@@ -817,7 +806,6 @@ main(int argc, char **argv)
 		exit_with_cli_errors(&cli_errors, NULL);
 	}
 
-
 	/*----------
 	 * Determine the node type and action; following are valid:
 	 *
@@ -827,7 +815,7 @@ main(int argc, char **argv)
 	 *   BDR { REGISTER | UNREGISTER } |
 	 *   NODE { STATUS | CHECK | REJOIN | SERVICE } |
 	 *   CLUSTER { CROSSCHECK | MATRIX | SHOW | EVENT | CLEANUP }
-	 *   DAEMON { STATUS | PAUSE | UNPAUSE | START | STOP }
+	 *   SERVICE { STATUS | PAUSE | UNPAUSE | START | STOP }
 	 *
 	 * [node] is an optional hostname, provided instead of the -h/--host
 	 * option
@@ -966,6 +954,22 @@ main(int argc, char **argv)
 			else if (strcasecmp(repmgr_action, "CLEANUP") == 0)
 				action = CLUSTER_CLEANUP;
 		}
+		else if (strcasecmp(repmgr_command, "SERVICE") == 0)
+		{
+			if (help_option == true)
+			{
+				do_service_help();
+				exit(SUCCESS);
+			}
+
+			if (strcasecmp(repmgr_action, "STATUS") == 0)
+				action = SERVICE_STATUS;
+			else if (strcasecmp(repmgr_action, "PAUSE") == 0)
+				action = SERVICE_PAUSE;
+			else if (strcasecmp(repmgr_action, "UNPAUSE") == 0)
+				action = SERVICE_UNPAUSE;
+
+		}
 		else if (strcasecmp(repmgr_command, "DAEMON") == 0)
 		{
 			if (help_option == true)
@@ -974,16 +978,18 @@ main(int argc, char **argv)
 				exit(SUCCESS);
 			}
 
-			if (strcasecmp(repmgr_action, "STATUS") == 0)
-				action = DAEMON_STATUS;
-			else if (strcasecmp(repmgr_action, "PAUSE") == 0)
-				action = DAEMON_PAUSE;
-			else if (strcasecmp(repmgr_action, "UNPAUSE") == 0)
-				action = DAEMON_UNPAUSE;
-			else if (strcasecmp(repmgr_action, "START") == 0)
+			if (strcasecmp(repmgr_action, "START") == 0)
 				action = DAEMON_START;
 			else if (strcasecmp(repmgr_action, "STOP") == 0)
 				action = DAEMON_STOP;
+
+			/* allow "daemon" as an alias for "service" for repmgr 4.x compatibility */
+			if (strcasecmp(repmgr_action, "STATUS") == 0)
+				action = SERVICE_STATUS;
+			else if (strcasecmp(repmgr_action, "PAUSE") == 0)
+				action = SERVICE_PAUSE;
+			else if (strcasecmp(repmgr_action, "UNPAUSE") == 0)
+				action = SERVICE_UNPAUSE;
 		}
 		else
 		{
@@ -1386,16 +1392,18 @@ main(int argc, char **argv)
 			do_cluster_cleanup();
 			break;
 
+			/* SERVICE */
+		case SERVICE_STATUS:
+			do_service_status();
+			break;
+		case SERVICE_PAUSE:
+			do_service_pause();
+			break;
+		case SERVICE_UNPAUSE:
+			do_service_unpause();
+			break;
+
 			/* DAEMON */
-		case DAEMON_STATUS:
-			do_daemon_status();
-			break;
-		case DAEMON_PAUSE:
-			do_daemon_pause();
-			break;
-		case DAEMON_UNPAUSE:
-			do_daemon_unpause();
-			break;
 		case DAEMON_START:
 			do_daemon_start();
 			break;
@@ -1906,9 +1914,9 @@ check_cli_parameters(const int action)
 			case WITNESS_UNREGISTER:
 			case NODE_REJOIN:
 			case NODE_SERVICE:
-			case DAEMON_PAUSE:
-			case DAEMON_UNPAUSE:
-			case DAEMON_STATUS:
+			case SERVICE_PAUSE:
+			case SERVICE_UNPAUSE:
+			case SERVICE_STATUS:
 			case DAEMON_START:
 			case DAEMON_STOP:
 				break;
@@ -1947,7 +1955,7 @@ check_cli_parameters(const int action)
 		{
 			case CLUSTER_SHOW:
 			case CLUSTER_EVENT:
-			case DAEMON_STATUS:
+			case SERVICE_STATUS:
 				break;
 			default:
 				item_list_append_format(&cli_warnings,
@@ -1961,7 +1969,7 @@ check_cli_parameters(const int action)
 	{
 		switch (action)
 		{
-			case DAEMON_STATUS:
+			case SERVICE_STATUS:
 				break;
 			default:
 				item_list_append_format(&cli_warnings,
@@ -2011,7 +2019,7 @@ check_cli_parameters(const int action)
 
 /*
  * Generate formatted node status output for display by "cluster show" and
- * "daemon status".
+ * "service status".
  */
 bool
 format_node_status(t_node_info *node_info, PQExpBufferData *node_status, PQExpBufferData *upstream, ItemList *warnings)
@@ -2448,6 +2456,8 @@ action_name(const int action)
 			return "STANDBY PROMOTE";
 		case STANDBY_FOLLOW:
 			return "STANDBY FOLLOW";
+		case STANDBY_SWITCHOVER:
+			return "STANDBY SWITCHOVER";
 
 		case WITNESS_REGISTER:
 			return "WITNESS REGISTER";
@@ -2467,9 +2477,13 @@ action_name(const int action)
 			return "NODE REJOIN";
 		case NODE_SERVICE:
 			return "NODE SERVICE";
+		case NODE_CONTROL:
+			return "NODE CONTROL";
 
 		case CLUSTER_SHOW:
 			return "CLUSTER SHOW";
+		case CLUSTER_CLEANUP:
+			return "CLUSTER CLEANUP";
 		case CLUSTER_EVENT:
 			return "CLUSTER EVENT";
 		case CLUSTER_MATRIX:
@@ -2477,12 +2491,13 @@ action_name(const int action)
 		case CLUSTER_CROSSCHECK:
 			return "CLUSTER CROSSCHECK";
 
-		case DAEMON_STATUS:
-			return "DAEMON STATUS";
-		case DAEMON_PAUSE:
-			return "DAEMON PAUSE";
-		case DAEMON_UNPAUSE:
-			return "DAEMON UNPAUSE";
+		case SERVICE_STATUS:
+			return "SERVICE STATUS";
+		case SERVICE_PAUSE:
+			return "SERVICE PAUSE";
+		case SERVICE_UNPAUSE:
+			return "SERVICE UNPAUSE";
+
 		case DAEMON_START:
 			return "DAEMON START";
 		case DAEMON_STOP:
@@ -2597,11 +2612,12 @@ do_help(void)
 	printf(_("    %s [OPTIONS] node    {status|check|rejoin|service}\n"), progname());
 	printf(_("    %s [OPTIONS] cluster {show|event|matrix|crosscheck|cleanup}\n"), progname());
 	printf(_("    %s [OPTIONS] witness {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] daemon  {status|pause|unpause|start|stop}\n"), progname());
+	printf(_("    %s [OPTIONS] service {status|pause|unpause}\n"), progname());
+	printf(_("    %s [OPTIONS] daemon  {start|stop}\n"), progname());
 
 	puts("");
 
-	printf(_("  Execute \"%s {primary|standby|bdr|node|cluster|witness|daemon} --help\" to see command-specific options\n"), progname());
+	printf(_("  Execute \"%s {primary|standby|bdr|node|cluster|witness|service} --help\" to see command-specific options\n"), progname());
 
 	puts("");
 
@@ -3122,8 +3138,8 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 			 * Ideally we'd use PG_AUTOCONF_FILENAME from utils/guc.h, but
 			 * that has too many dependencies for a mere client program.
 			 */
-			appendPQExpBufferStr(&rsync_flags,
-								 " --exclude=postgresql.auto.conf.tmp");
+			appendPQExpBuffer(&rsync_flags, " --exclude=%s.tmp",
+							  PG_AUTOCONF_FILENAME);
 		}
 
 		/* Temporary files which we don't want, if they exist */
@@ -3199,6 +3215,18 @@ make_remote_repmgr_path(PQExpBufferData *output_buf, t_node_info *remote_node_re
 					  "%s -f %s ",
 					  progname(),
 					  remote_node_record->config_file);
+
+	/*
+	 * If --log-level was explicitly supplied, pass that through
+	 * to the remote repmgr client too.
+	 */
+	if (runtime_options.log_level[0] != '\0')
+	{
+		appendPQExpBuffer(output_buf,
+						  " -L %s ",
+						  runtime_options.log_level);
+	}
+
 }
 
 
@@ -3912,3 +3940,44 @@ is_repmgrd_running(PGconn *conn)
 
 	return is_running;
 }
+
+
+/**
+ * Parse the string returned by "repmgr --version", e.g. "repmgr 4.1.2",
+ * and return it as a version integer (e.g. 40102).
+ *
+ * This is required for backwards compatibility as versions prior to
+ * 4.3 do not have the --version-number option.
+ */
+int
+parse_repmgr_version(const char *version_string)
+{
+	int series, major, minor;
+	int version_integer = UNKNOWN_REPMGR_VERSION_NUM;
+	PQExpBufferData sscanf_string;
+
+	initPQExpBuffer(&sscanf_string);
+
+	appendPQExpBuffer(&sscanf_string, "%s ",
+					  progname());
+	appendPQExpBufferStr(&sscanf_string, "%i.%i.%i");
+
+	if (sscanf(version_string, sscanf_string.data, &series, &major, &minor) == 3)
+	{
+		version_integer = (series * 10000) + (major * 100) + minor;
+	}
+	else
+	{
+		resetPQExpBuffer(&sscanf_string);
+		appendPQExpBuffer(&sscanf_string, "%s ",
+						  progname());
+		appendPQExpBufferStr(&sscanf_string, "%i.%i");
+
+		if (sscanf(version_string, "repmgr %i.%i", &series, &major) == 2)
+		{
+			version_integer = (series * 10000) + (major * 100);
+		}
+	}
+
+	return version_integer;
+}

repmgr-client.h

@@ -46,9 +46,9 @@
 #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 SERVICE_STATUS		   23
+#define SERVICE_PAUSE		   24
+#define SERVICE_UNPAUSE		   25
 #define DAEMON_START 		   26
 #define DAEMON_STOP 		   27
 
@@ -101,13 +101,9 @@
 #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		    996
-#define OPT_NODE						    995
+#define OPT_CHECK_UPSTREAM_CONFIG		    999
+#define OPT_NODE						    998
 
 
 static struct option long_options[] =
@@ -157,7 +153,6 @@ 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},
@@ -215,11 +210,8 @@ 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.conf.sample

@@ -6,12 +6,13 @@
 # is noted for each item. Where no default value is shown, the
 # parameter will be treated as empty or false.
 #
-# 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.:
+# 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).
 #
-#  node_name=foo
-#  node_name = 'foo'
+# For details on the configuration file format see the documentation at:
+#
+#   https://repmgr.org/docs/current/configuration-file.html#CONFIGURATION-FILE-FORMAT
 #
 # =============================================================================
 # Required configuration items
@@ -20,7 +21,7 @@
 # repmgr and repmgrd require the following items to be explicitly configured.
 
 
-#node_id=    	     	     	 # A unique integer greater than zero
+#node_id=			 # A unique integer greater than zero
 #node_name=''			 # An arbitrary (but unique) string; we recommend
 				 # using the server's hostname or another identifier
 				 # unambiguously associated with the server to avoid
@@ -28,8 +29,8 @@
 				 # node's current role, e.g. 'primary' or 'standby1',
 				 # as roles can change and it will be confusing if
 				 # the current primary is called 'standby1'.
-                                 # The string's maximum length is 63 characters and it should
-                                 # 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
@@ -70,13 +71,13 @@
 #replication_user='repmgr'	 # User to make replication connections with, if not set
 				 #  defaults to the user defined in "conninfo".
 
-#replication_type=physical	 # Must be one of "physical" or "bdr".
+#replication_type='physical'	 # Must 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 +102,10 @@
 # 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
@@ -159,12 +160,13 @@
 
 #repmgr_bindir=''			# Path to repmgr binary directory (location of the repmgr
 					# binary. Only needed if the repmgr executable is not in
-                                        # the system $PATH or the path defined in "pg_bindir".
+					# the system $PATH or the path defined in "pg_bindir".
 
-#use_primary_conninfo_password=false	# explicitly set "password" in recovery.conf's
-					# "primary_conninfo" parameter using the value contained
-					# in the environment variable PGPASSWORD
+#use_primary_conninfo_password=false	# explicitly set "password" in "primary_conninfo"
+					# using the value contained in the environment variable
+					# PGPASSWORD
 #passfile=''				# path to .pgpass file to include in "primary_conninfo"
+
 #------------------------------------------------------------------------------
 # external command options
 #------------------------------------------------------------------------------
@@ -178,7 +180,7 @@
 #   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"
@@ -196,19 +198,19 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #   tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
 #   restore_command = 'cp /path/to/archived/wals/%f %p'
 
-#tablespace_mapping=''	  		# Tablespaces can be remapped from one
+#tablespace_mapping=''			# Tablespaces can be remapped from one
 					# file system location to another. This
 					# parameter can be provided multiple times.
 
-#restore_command=''			# This will be placed in the recovery.conf file generated
-					# by repmgr.
+#restore_command=''			# This will be included in the recovery configuration
+					# generated by repmgr.
 
-#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 )
+#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 )
 
-#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" in recovery.conf
-					# will be set to this value (PostgreSQL 9.4 and later).
+#recovery_min_apply_delay=		# If provided, "recovery_min_apply_delay" will be set to
+					# this value (PostgreSQL 9.4 and later).
 
 
 #------------------------------------------------------------------------------
@@ -281,7 +283,7 @@ 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
@@ -295,17 +297,17 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 					# (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
+					#  '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
@@ -317,8 +319,8 @@ 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.
@@ -339,7 +341,7 @@ 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.
@@ -347,14 +349,14 @@ 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
@@ -372,7 +374,7 @@ 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
@@ -385,8 +387,8 @@ 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.
 #
@@ -402,7 +404,7 @@ 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 daemon (start|stop)" to control repmgrd
+# Used by "repmgr service (start|stop)" to control repmgrd
 #
 #repmgrd_service_start_command = ''
 #repmgrd_service_stop_command = ''
@@ -413,7 +415,7 @@ 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
@@ -438,8 +440,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 # BDR monitoring options
 #------------------------------------------------------------------------------
 
-#bdr_local_monitoring_only=false         # Only monitor the local node; no checks will be
+#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
+#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 = '4.4'
+default_version = '5.0'
 module_pathname = '$libdir/repmgr'
 relocatable = false
 schema = repmgr

repmgr.h

@@ -77,14 +77,12 @@
 #define MIN_SUPPORTED_VERSION		"9.3"
 #define MIN_SUPPORTED_VERSION_NUM	90300
 
-#define MAX_UNSUPPORTED_VERSION		"12"
-#define MAX_UNSUPPORTED_VERSION_NUM	120000
-
 #define REPLICATION_TYPE_PHYSICAL 1
 #define REPLICATION_TYPE_BDR	  2
 
 #define UNKNOWN_SERVER_VERSION_NUM -1
 #define UNKNOWN_BDR_VERSION_NUM -1
+#define UNKNOWN_REPMGR_VERSION_NUM -1
 
 #define UNKNOWN_TIMELINE_ID -1
 #define UNKNOWN_SYSTEM_IDENTIFIER 0
@@ -142,6 +140,11 @@
 #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

@@ -1,4 +1,5 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.4"
-#define REPMGR_VERSION_NUM 40400
-#define REPMGR_RELEASE_DATE "2019-06-27"
+#define REPMGR_VERSION "5.0.0"
+#define REPMGR_VERSION_NUM 50000
+#define REPMGR_RELEASE_DATE "2019-10-15"
+#define PG_ACTUAL_VERSION_NUM 

repmgrd-physical.c

@@ -1580,7 +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 daemon unpause\" to resume normal failover mode"));
+						log_hint(_("execute \"repmgr service unpause\" to resume normal failover mode"));
 						monitoring_state = MS_DEGRADED;
 						INSTR_TIME_SET_CURRENT(degraded_monitoring_start);
 					}
@@ -1710,9 +1710,6 @@ 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)
 				{
@@ -1802,6 +1799,9 @@ 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)
 						{
@@ -1828,16 +1828,19 @@ monitor_streaming_standby(void)
 
 							if (get_recovery_type(cell->node_info->conn) == RECTYPE_PRIMARY)
 							{
-								follow_node_id = cell->node_info->node_id;
+								follow_node_info = cell->node_info;
 								close_connection(&cell->node_info->conn);
 								break;
 							}
 							close_connection(&cell->node_info->conn);
 						}
 
-						if (follow_node_id != UNKNOWN_NODE_ID)
+						if (follow_node_info != NULL)
 						{
-							follow_new_primary(follow_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);
 						}
 					}
 
@@ -1881,7 +1884,7 @@ loop:
 					if (PQstatus(local_conn) == CONNECTION_OK && repmgrd_is_paused(local_conn))
 					{
 						log_detail(_("repmgrd paused by administrator"));
-						log_hint(_("execute \"repmgr daemon unpause\" to resume normal failover mode"));
+						log_hint(_("execute \"repmgr service unpause\" to resume normal failover mode"));
 					}
 					else
 					{
@@ -2083,7 +2086,6 @@ loop:
 			}
 		}
 
-
 		if (got_SIGHUP)
 		{
 			handle_sighup(&local_conn, STANDBY);
@@ -2093,13 +2095,34 @@ loop:
 
 		if (local_monitoring_state == MS_NORMAL && last_known_upstream_node_id != local_node_info.upstream_node_id)
 		{
-			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;
+			/*
+			 * 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 %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\")",
@@ -2380,8 +2403,6 @@ 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,
@@ -2391,6 +2412,9 @@ 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)
 					{
@@ -2416,18 +2440,22 @@ monitor_streaming_witness(void)
 
 						if (get_recovery_type(cell->node_info->conn) == RECTYPE_PRIMARY)
 						{
-							follow_node_id = cell->node_info->node_id;
+							follow_node_info = cell->node_info;
 							close_connection(&cell->node_info->conn);
 							break;
 						}
 						close_connection(&cell->node_info->conn);
 					}
 
-					if (follow_node_id != UNKNOWN_NODE_ID)
+					if (follow_node_info != NULL)
 					{
-						witness_follow_new_primary(follow_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);
 					}
 				}
+
 				clear_node_info_list(&sibling_nodes);
 			}
 		}
@@ -3594,6 +3622,10 @@ 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)
@@ -3623,7 +3655,7 @@ follow_new_primary(int new_primary_id)
 		else
 		{
 			new_primary_ok = false;
-			log_warning(_("new primary is not in recovery"));
+			log_warning(_("new primary is in recovery"));
 			close_connection(&upstream_conn);
 		}
 	}
@@ -3816,7 +3848,7 @@ witness_follow_new_primary(int new_primary_id)
 				break;
 			case RECTYPE_STANDBY:
 				new_primary_ok = false;
-				log_warning(_("new primary is not in recovery"));
+				log_warning(_("new primary is in recovery"));
 				break;
 			case RECTYPE_UNKNOWN:
 				new_primary_ok = false;
@@ -3997,7 +4029,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 	}
 	else
 	{
-		log_info(_("primary and this node have the same location (\"%s\")"),
+		log_info(_("primary node  \"%s\" (ID: %i) and this node have the same location (\"%s\")"),
+				 upstream_node_info.node_name,
+				 upstream_node_info.node_id,
 				 local_node_info.location);
 	}
 
@@ -4237,7 +4271,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 			else
 			{
 				nodes_with_primary_still_visible++;
-				log_notice(_("node %i last saw primary node %i second(s) ago, considering primary still visible"),
+				log_notice(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago, considering primary still visible"),
+						   get_node_type_string(cell->node_info->type),
+						   cell->node_info->node_name,
 						   cell->node_info->node_id,
 						   sibling_replication_info.upstream_last_seen);
 				appendPQExpBuffer(&nodes_with_primary_visible,
@@ -4249,7 +4285,9 @@ do_election(NodeInfoList *sibling_nodes, int *new_primary_id)
 		}
 		else
 		{
-			log_info(_("node %i last saw primary node %i second(s) ago"),
+			log_info(_("%s node \"%s\" (ID: %i) last saw primary node %i second(s) ago"),
+					 get_node_type_string(cell->node_info->type),
+					 cell->node_info->node_name,
 					 cell->node_info->node_id,
 					 sibling_replication_info.upstream_last_seen);
 		}

strutil.c

@@ -29,6 +29,9 @@ static int
 xvsnprintf(char *str, size_t size, const char *format, va_list ap)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 0)));
 
+static void
+_key_value_list_set(KeyValueList *item_list, bool replace, const char *key, const char *value);
+
 static int
 xvsnprintf(char *str, size_t size, const char *format, va_list ap)
 {
@@ -164,16 +167,74 @@ item_list_free(ItemList *item_list)
 void
 key_value_list_set(KeyValueList *item_list, const char *key, const char *value)
 {
-	key_value_list_set_format(item_list, key, "%s", value);
+	_key_value_list_set(item_list, false, key, value);
 	return;
 }
 
 void
-key_value_list_set_format(KeyValueList *item_list, const char *key, const char *value,...)
+key_value_list_replace_or_set(KeyValueList *item_list, const char *key, const char *value)
+{
+	_key_value_list_set(item_list, true, key, value);
+	return;
+}
+
+void
+key_value_list_set_format(KeyValueList *item_list, const char *key, const char *value, ...)
+{
+	va_list		arglist;
+	char formatted_value[MAXLEN];
+
+	va_start(arglist, value);
+	(void) xvsnprintf(formatted_value, MAXLEN, value, arglist);
+	va_end(arglist);
+
+	return _key_value_list_set(item_list, false, key, formatted_value);
+}
+
+static void
+_key_value_list_set(KeyValueList *item_list, bool replace, const char *key, const char *value)
 {
 	KeyValueListCell *cell = NULL;
-	va_list		arglist;
 	int			keylen = 0;
+	int			vallen = 0;
+
+	if (replace == true)
+	{
+		KeyValueListCell *prev_cell = NULL;
+		KeyValueListCell *next_cell = NULL;
+
+
+		for (cell = item_list->head; cell; cell = next_cell)
+		{
+			next_cell = cell->next;
+
+			if (strcmp(cell->key, key) == 0)
+			{
+				if (item_list->head == cell)
+					item_list->head = cell->next;
+
+				if (prev_cell)
+				{
+					prev_cell->next = cell->next;
+
+					if (item_list->tail == cell)
+						item_list->tail = prev_cell;
+				}
+				else if (item_list->tail == cell)
+				{
+					item_list->tail = NULL;
+				}
+
+				pfree(cell->key);
+				pfree(cell->value);
+				pfree(cell);
+			}
+			else
+			{
+				prev_cell = cell;
+			}
+		}
+	}
 
 	cell = (KeyValueListCell *) pg_malloc0(sizeof(KeyValueListCell));
 
@@ -184,17 +245,14 @@ key_value_list_set_format(KeyValueList *item_list, const char *key, const char *
 	}
 
 	keylen = strlen(key);
+	vallen = strlen(value);
 
 	cell->key = pg_malloc0(keylen + 1);
-	cell->value = pg_malloc0(MAXLEN);
+	cell->value = pg_malloc0(vallen + 1);
 	cell->output_mode = OM_NOT_SET;
 
 	strncpy(cell->key, key, keylen);
-
-	va_start(arglist, value);
-	(void) xvsnprintf(cell->value, MAXLEN, value, arglist);
-	va_end(arglist);
-
+	strncpy(cell->value, value, vallen);
 
 	if (item_list->tail)
 		item_list->tail->next = cell;

strutil.h

@@ -119,6 +119,9 @@ extern void
 extern void
 			key_value_list_set(KeyValueList *item_list, const char *key, const char *value);
 
+extern void
+key_value_list_replace_or_set(KeyValueList *item_list, const char *key, const char *value);
+
 extern void
 key_value_list_set_format(KeyValueList *item_list, const char *key, const char *value,...)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));

sysutils.c

@@ -1,6 +1,8 @@
 /*
  * sysutils.c
  *
+ * Functions which need to be executed on the local system.
+ *
  * Copyright (c) 2ndQuadrant, 2010-2019
  *
  * This program is free software: you can redistribute it and/or modify
@@ -115,7 +117,7 @@ bool
 remote_command(const char *host, const char *user, const char *command, const char *ssh_options, PQExpBufferData *outputbuf)
 {
 	FILE	   *fp;
-	char		ssh_command[MAXLEN] = "";
+	PQExpBufferData ssh_command;
 	PQExpBufferData ssh_host;
 
 	char		output[MAXLEN] = "";
@@ -129,24 +131,29 @@ remote_command(const char *host, const char *user, const char *command, const ch
 
 	appendPQExpBufferStr(&ssh_host, host);
 
-	maxlen_snprintf(ssh_command,
-					"ssh -o Batchmode=yes %s %s %s",
-					ssh_options,
-					ssh_host.data,
-					command);
+	initPQExpBuffer(&ssh_command);
+
+	appendPQExpBuffer(&ssh_command,
+					  "ssh -o Batchmode=yes %s %s %s",
+					  ssh_options,
+					  ssh_host.data,
+					  command);
 
 	termPQExpBuffer(&ssh_host);
 
-	log_debug("remote_command():\n  %s", ssh_command);
+	log_debug("remote_command():\n  %s", ssh_command.data);
 
-	fp = popen(ssh_command, "r");
+	fp = popen(ssh_command.data, "r");
 
 	if (fp == NULL)
 	{
-		log_error(_("unable to execute remote command:\n  %s"), ssh_command);
+		log_error(_("unable to execute remote command:\n  %s"), ssh_command.data);
+		termPQExpBuffer(&ssh_command);
 		return false;
 	}
 
+	termPQExpBuffer(&ssh_command);
+
 	if (outputbuf != NULL)
 	{
 		/* TODO: better error handling */
@@ -364,3 +371,5 @@ enable_wal_receiver(PGconn *conn, bool wait_startup)
 
 	return wal_receiver_pid;
 }
+
+

sysutils.h

@@ -28,5 +28,4 @@ extern bool remote_command(const char *host, const char *user, const char *comma
 extern pid_t disable_wal_receiver(PGconn *conn);
 extern pid_t enable_wal_receiver(PGconn *conn, bool wait_startup);
 
-
 #endif							/* _SYSUTILS_H_ */