doc: update "repmgr primary unregister" description

As noted by GitHub user yonj1e in GitHub #396.
doc: update FAQ
2026-03-23 07:06:30 +00:00 · 2018-03-08 15:01:25 +09:00 · 2018-03-08 10:04:30 +09:00 · 2018-03-08 10:04:30 +09:00 · 2018-03-07 19:14:18 +09:00 · 2018-03-07 14:17:04 +09:00
31 changed files with 1552 additions and 345 deletions
--- a/19
+++ b/19
@@ -1,4 +1,20 @@
-4.0.3   2018-02-
+4.0.4   2018-03-08
+        repmgr: add "standby clone --recovery-conf-only" option; GitHub #382 (Ian)
+        repmgr: make "standby promote" timeout values configurable; GitHub #387 (Ian)
+        repmgr: improve replication slot warnings generated by "node status";
+          GitHub #385 (Ian)
+        repmgr: remove restriction on replication slots when cloning from
+          a Barman server; GitHub #379 (Ian)
+        repmgr: ensure "node rejoin" honours "--dry-run" option; GitHub #383 (Ian)
+        repmgr: fix --superuser handling when cloning a standby; GitHub #380 (Ian)
+        repmgr: update various help options; GitHub #391, #392 (hasegeli)
+        repmgrd: add event "repmgrd_shutdown"; GitHub #393 (Ian)
+        repmgrd: improve detection of status change from primary to standby (Ian)
+        repmgrd: improve log output in various situations (Ian)
+        repmgrd: improve reconnection to the local node after a failover (Ian)
+        repmgrd: ensure witness server connects to new primary after a failover (Ian)
+
+4.0.3   2018-02-15
        repmgr: improve switchover handling when "pg_ctl" used to control the
          server and logging output is not explicitly redirected (Ian)
        repmgr: improve switchover log messages and exit code when old primary could
@@ -17,6 +33,7 @@
        repmgr: fix upstream node display in "repmgr node status"; GitHub #363 (fanf2)
        repmgr: improve/clarify documentation and update --help output for
          "primary unregister"; GitHub #373 (Ian)
+        repmgr: allow replication slots when Barman is configured; GitHub #379 (Ian)
        repmgr: fix parsing of "pg_basebackup_options"; GitHub #376 (Ian)
        repmgr: ensure "pg_subtrans" directory is created when cloning a standby in
          Barman mode (Ian)
--- a/configfile.c
+++ b/configfile.c
@@ -303,7 +303,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->log_status_interval = DEFAULT_LOG_STATUS_INTERVAL;

 	/*-----------------------
-	 * standby action settings
+	 * standby clone settings
 	 *------------------------
 	 */
 	options->use_replication_slots = false;
@@ -317,6 +317,13 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->use_primary_conninfo_password = false;
 	memset(options->passfile, 0, sizeof(options->passfile));

+	/*-----------------------
+	 * standby promote settings
+	 *------------------------
+	 */
+	options->promote_check_timeout = DEFAULT_PROMOTE_CHECK_TIMEOUT;
+	options->promote_check_interval = DEFAULT_PROMOTE_CHECK_INTERVAL;
+
 	/*-----------------
 	 * repmgrd settings
 	 *-----------------
@@ -337,6 +344,7 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 	options->async_query_timeout = DEFAULT_ASYNC_QUERY_TIMEOUT;
 	options->primary_notification_timeout = DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT;
 	options->primary_follow_timeout = DEFAULT_PRIMARY_FOLLOW_TIMEOUT;
+	options->standby_reconnect_timeout = DEFAULT_STANDBY_RECONNECT_TIMEOUT;

 	/*-------------
 	 * witness settings
@@ -505,6 +513,13 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 		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);
+
 		/* node check settings */
 		else if (strcmp(name, "archive_ready_warning") == 0)
 			options->archive_ready_warning = repmgr_atoi(value, name, error_list, 1);
@@ -556,6 +571,8 @@ _parse_config(t_configuration_options *options, ItemList *error_list, ItemList *
 			options->primary_notification_timeout = repmgr_atoi(value, name, error_list, 0);
 		else if (strcmp(name, "primary_follow_timeout") == 0)
 			options->primary_follow_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);

 		/* witness settings */
 		else if (strcmp(name, "witness_sync_interval") == 0)
@@ -1028,7 +1045,7 @@ reload_config(t_configuration_options *orig_options)
 		return false;
 	}

-	if (strcmp(new_options.node_name, orig_options->node_name) != 0)
+	if (strncmp(new_options.node_name, orig_options->node_name, MAXLEN) != 0)
 	{
 		log_warning(_("\"node_name\" cannot be changed, keeping current configuration"));
 		return false;
@@ -1072,7 +1089,7 @@ reload_config(t_configuration_options *orig_options)
 	}

 	/* conninfo */
-	if (strcmp(orig_options->conninfo, new_options.conninfo) != 0)
+	if (strncmp(orig_options->conninfo, new_options.conninfo, MAXLEN) != 0)
 	{
 		/* Test conninfo string works */
 		conn = establish_db_connection(new_options.conninfo, false);
@@ -1099,7 +1116,7 @@ reload_config(t_configuration_options *orig_options)
 	}

 	/* event_notification_command */
-	if (strcmp(orig_options->event_notification_command, new_options.event_notification_command) != 0)
+	if (strncmp(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->event_notification_command, new_options.event_notification_command, MAXLEN);
 		log_info(_("\"event_notification_command\" is now \"%s\""), new_options.event_notification_command);
@@ -1108,7 +1125,7 @@ reload_config(t_configuration_options *orig_options)
 	}

 	/* event_notifications */
-	if (strcmp(orig_options->event_notifications_orig, new_options.event_notifications_orig) != 0)
+	if (strncmp(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN) != 0)
 	{
 		strncpy(orig_options->event_notifications_orig, new_options.event_notifications_orig, MAXLEN);
 		log_info(_("\"event_notifications\" is now \"%s\""), new_options.event_notifications_orig);
@@ -1128,7 +1145,7 @@ reload_config(t_configuration_options *orig_options)
 	}

 	/* follow_command */
-	if (strcmp(orig_options->follow_command, new_options.follow_command) != 0)
+	if (strncmp(orig_options->follow_command, new_options.follow_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->follow_command, new_options.follow_command, MAXLEN);
 		log_info(_("\"follow_command\" is now \"%s\""), new_options.follow_command);
@@ -1165,7 +1182,7 @@ reload_config(t_configuration_options *orig_options)


 	/* promote_command */
-	if (strcmp(orig_options->promote_command, new_options.promote_command) != 0)
+	if (strncmp(orig_options->promote_command, new_options.promote_command, MAXLEN) != 0)
 	{
 		strncpy(orig_options->promote_command, new_options.promote_command, MAXLEN);
 		log_info(_("\"promote_command\" is now \"%s\""), new_options.promote_command);
@@ -1205,18 +1222,18 @@ reload_config(t_configuration_options *orig_options)
 	 */

 	/* log_facility */
-	if (strcmp(orig_options->log_facility, new_options.log_facility) != 0)
+	if (strncmp(orig_options->log_facility, new_options.log_facility, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_facility, new_options.log_facility);
+		strncpy(orig_options->log_facility, new_options.log_facility, MAXLEN);
 		log_info(_("\"log_facility\" is now \"%s\""), new_options.log_facility);

 		log_config_changed = true;
 	}

 	/* log_file */
-	if (strcmp(orig_options->log_file, new_options.log_file) != 0)
+	if (strncmp(orig_options->log_file, new_options.log_file, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_file, new_options.log_file);
+		strncpy(orig_options->log_file, new_options.log_file, MAXLEN);
 		log_info(_("\"log_file\" is now \"%s\""), new_options.log_file);

 		log_config_changed = true;
@@ -1224,9 +1241,9 @@ reload_config(t_configuration_options *orig_options)


 	/* log_level */
-	if (strcmp(orig_options->log_level, new_options.log_level) != 0)
+	if (strncmp(orig_options->log_level, new_options.log_level, MAXLEN) != 0)
 	{
-		strcpy(orig_options->log_level, new_options.log_level);
+		strncpy(orig_options->log_level, new_options.log_level, MAXLEN);
 		log_info(_("\"log_level\" is now \"%s\""), new_options.log_level);

 		log_config_changed = true;
--- a/configfile.h
+++ b/configfile.h
@@ -82,7 +82,7 @@ typedef struct
 	char		log_file[MAXLEN];
 	int			log_status_interval;

-	/* standby action settings */
+	/* standby clone settings */
 	bool		use_replication_slots;
 	char		pg_basebackup_options[MAXLEN];
 	char		restore_command[MAXLEN];
@@ -92,6 +92,10 @@ typedef struct
 	bool		use_primary_conninfo_password;
 	char		passfile[MAXPGPATH];

+	/* standby promote settings */
+	int			promote_check_timeout;
+	int			promote_check_interval;
+
 	/* node check settings */
 	int			archive_ready_warning;
 	int			archive_ready_critical;
@@ -115,6 +119,7 @@ typedef struct
 	int			async_query_timeout;
 	int			primary_notification_timeout;
 	int			primary_follow_timeout;
+	int			standby_reconnect_timeout;

 	/* BDR settings */
 	bool		bdr_local_monitoring_only;
@@ -158,6 +163,8 @@ typedef struct
 		"", "", "", DEFAULT_LOG_STATUS_INTERVAL,	\
 		/* standby action settings */ \
 		false, "", "", { NULL, NULL }, "", false, false, "",	\
+		/* standby promote settings */ \
+		DEFAULT_PROMOTE_CHECK_TIMEOUT, DEFAULT_PROMOTE_CHECK_INTERVAL, \
 		/* node check settings */ \
 		DEFAULT_ARCHIVE_READY_WARNING, DEFAULT_ARCHIVE_READY_CRITICAL, \
 		DEFAULT_REPLICATION_LAG_WARNING, DEFAULT_REPLICATION_LAG_CRITICAL, \
@@ -172,6 +179,7 @@ typedef struct
 		DEFAULT_ASYNC_QUERY_TIMEOUT, \
 		DEFAULT_PRIMARY_NOTIFICATION_TIMEOUT,	\
 		DEFAULT_PRIMARY_FOLLOW_TIMEOUT,	\
+		DEFAULT_STANDBY_RECONNECT_TIMEOUT,	\
 		/* BDR settings */ \
 		false, DEFAULT_BDR_RECOVERY_TIMEOUT, \
 		/* service settings */ \
--- a/18
+++ b/18
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for repmgr 4.0.3.
+# Generated by GNU Autoconf 2.69 for repmgr 4.0.4.
 #
 # Report bugs to <pgsql-bugs@postgresql.org>.
 #
@@ -582,8 +582,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='repmgr'
 PACKAGE_TARNAME='repmgr'
-PACKAGE_VERSION='4.0.3'
-PACKAGE_STRING='repmgr 4.0.3'
+PACKAGE_VERSION='4.0.4'
+PACKAGE_STRING='repmgr 4.0.4'
 PACKAGE_BUGREPORT='pgsql-bugs@postgresql.org'
 PACKAGE_URL='https://2ndquadrant.com/en/resources/repmgr/'

@@ -1178,7 +1178,7 @@ if test "$ac_init_help" = "long"; then
  # Omit some internal or obsolete options to make the list less imposing.
  # This message is too long to be a string in the A/UX 3.1 sh.
  cat <<_ACEOF
-\`configure' configures repmgr 4.0.3 to adapt to many kinds of systems.
+\`configure' configures repmgr 4.0.4 to adapt to many kinds of systems.

 Usage: $0 [OPTION]... [VAR=VALUE]...

@@ -1239,7 +1239,7 @@ fi

 if test -n "$ac_init_help"; then
  case $ac_init_help in
-     short | recursive ) echo "Configuration of repmgr 4.0.3:";;
+     short | recursive ) echo "Configuration of repmgr 4.0.4:";;
   esac
  cat <<\_ACEOF

@@ -1313,7 +1313,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
  cat <<\_ACEOF
-repmgr configure 4.0.3
+repmgr configure 4.0.4
 generated by GNU Autoconf 2.69

 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1332,7 +1332,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.

-It was created by repmgr $as_me 4.0.3, which was
+It was created by repmgr $as_me 4.0.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was

  $ $0 $@
@@ -2359,7 +2359,7 @@ cat >>$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 4.0.3, which was
+This file was extended by repmgr $as_me 4.0.4, which was
 generated by GNU Autoconf 2.69.  Invocation command line was

  CONFIG_FILES    = $CONFIG_FILES
@@ -2422,7 +2422,7 @@ _ACEOF
 cat >>$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 4.0.3
+repmgr config.status 4.0.4
 configured by $0, generated by GNU Autoconf 2.69,
  with options \\"\$ac_cs_config\\"

--- a/configure.in
+++ b/configure.in
@@ -1,4 +1,4 @@
-AC_INIT([repmgr], [4.0.3], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])
+AC_INIT([repmgr], [4.0.4], [pgsql-bugs@postgresql.org], [repmgr], [https://2ndquadrant.com/en/resources/repmgr/])

 AC_COPYRIGHT([Copyright (c) 2010-2018, 2ndQuadrant Ltd.])

--- a/dbutils.c
+++ b/dbutils.c
@@ -219,8 +219,7 @@ establish_db_connection_quiet(const char *conninfo)
 }


-PGconn
-		   *
+PGconn *
 establish_primary_db_connection(PGconn *conn,
 								const bool exit_on_error)
 {
@@ -237,36 +236,6 @@ establish_primary_db_connection(PGconn *conn,
 }


-PGconn *
-establish_db_connection_as_user(const char *conninfo,
-								const char *user,
-								const bool exit_on_error)
-{
-	PGconn	   *conn = NULL;
-	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
-	bool		parse_success = false;
-	char	   *errmsg = NULL;
-
-	initialize_conninfo_params(&conninfo_params, false);
-
-	parse_success = parse_conninfo_string(conninfo, &conninfo_params, errmsg, true);
-
-	if (parse_success == false)
-	{
-		log_error(_("unable to pass provided conninfo string:\n	 %s"), errmsg);
-		return NULL;
-	}
-
-	param_set(&conninfo_params, "user", user);
-
-	conn = establish_db_connection_by_params(&conninfo_params, false);
-
-	return conn;
-}
-
-
-
-
 PGconn *
 establish_db_connection_by_params(t_conninfo_param_list *param_list,
 								  const bool exit_on_error)
@@ -1060,7 +1029,7 @@ get_server_version(PGconn *conn, char *server_version)
 	}

 	if (server_version != NULL)
-		strcpy(server_version, PQgetvalue(res, 0, 1));
+		strncpy(server_version, PQgetvalue(res, 0, 1), MAXVERSIONSTR);

 	server_version_num = atoi(PQgetvalue(res, 0, 0));

@@ -1803,7 +1772,7 @@ _populate_node_record(PGresult *res, t_node_info *node_info, int row)
 	strncpy(node_info->config_file, PQgetvalue(res, row, 10), MAXLEN);

 	/* This won't normally be set */
-	strncpy(node_info->upstream_node_name, PQgetvalue(res, row, 10), MAXLEN);
+	strncpy(node_info->upstream_node_name, PQgetvalue(res, row, 11), MAXLEN);

 	/* Set remaining struct fields with default values */
 	node_info->node_status = NODE_STATUS_UNKNOWN;
@@ -1887,6 +1856,36 @@ get_node_record(PGconn *conn, int node_id, t_node_info *node_info)
 }


+RecordStatus
+get_node_record_with_upstream(PGconn *conn, int node_id, t_node_info *node_info)
+{
+	PQExpBufferData query;
+	RecordStatus result;
+
+	initPQExpBuffer(&query);
+	appendPQExpBuffer(&query,
+					  "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
+					  "           n.slot_name, n.location, n.priority, n.active, n.config_file, un.node_name AS upstream_node_name "
+					  "      FROM repmgr.nodes n "
+					  " LEFT JOIN repmgr.nodes un "
+					  "        ON un.node_id = n.upstream_node_id"
+					  " WHERE n.node_id = %i",
+					  node_id);
+
+	log_verbose(LOG_DEBUG, "get_node_record():\n  %s", query.data);
+
+	result = _get_node_record(conn, query.data, node_info);
+	termPQExpBuffer(&query);
+
+	if (result == RECORD_NOT_FOUND)
+	{
+		log_verbose(LOG_DEBUG, "get_node_record(): no record found for node %i", node_id);
+	}
+
+	return result;
+}
+
+
 RecordStatus
 get_node_record_by_name(PGconn *conn, const char *node_name, t_node_info *node_info)
 {
@@ -2140,7 +2139,7 @@ get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list)

 	appendPQExpBuffer(&query,
 					  "    SELECT n.node_id, n.type, n.upstream_node_id, n.node_name, n.conninfo, n.repluser, "
-					  "           n.slot_name, n.location, n.priority, n.active, un.node_name AS upstream_node_name "
+					  "           n.slot_name, n.location, n.priority, n.active, n.config_file, un.node_name AS upstream_node_name "
 					  "      FROM repmgr.nodes n "
 					  " LEFT JOIN repmgr.nodes un "
 					  "        ON un.node_id = n.upstream_node_id"
@@ -2170,7 +2169,7 @@ get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list)


 bool
-get_downsteam_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *node_list)
+get_downstream_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *node_list)
 {
 	PQExpBufferData query;
 	PGresult   *res = NULL;
@@ -2181,9 +2180,10 @@ get_downsteam_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoLi
 					  "   SELECT " REPMGR_NODES_COLUMNS
 					  "     FROM repmgr.nodes n "
 					  "LEFT JOIN pg_catalog.pg_replication_slots rs "
-					  "       ON rs.slot_name = n.node_name "
-					  "    WHERE rs.slot_name IS NULL "
-                      "      AND n.node_id != %i ",
+					  "       ON rs.slot_name = n.slot_name "
+					  "    WHERE n.slot_name IS NOT NULL"
+                      "      AND rs.slot_name IS NULL "
+                      "      AND n.upstream_node_id = %i ",
 					  this_node_id);

 	log_verbose(LOG_DEBUG, "get_all_node_records_with_missing_slot():\n%s", query.data);
@@ -2347,8 +2347,7 @@ update_node_record_set_active(PGconn *conn, int this_node_id, bool active)

 	initPQExpBuffer(&query);

-	appendPQExpBuffer(
-					  &query,
+	appendPQExpBuffer(&query,
 					  "UPDATE repmgr.nodes SET active = %s "
 					  " WHERE node_id = %i",
 					  active == true ? "TRUE" : "FALSE",
@@ -2373,6 +2372,40 @@ update_node_record_set_active(PGconn *conn, int this_node_id, bool active)
 }


+bool
+update_node_record_set_active_standby(PGconn *conn, int this_node_id)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+
+	initPQExpBuffer(&query);
+
+	appendPQExpBuffer(&query,
+					  "UPDATE repmgr.nodes "
+					  "   SET type = 'standby', "
+					  "       active = TRUE "
+					  " WHERE node_id = %i",
+					  this_node_id);
+
+	log_verbose(LOG_DEBUG, "update_node_record_set_active_standby():\n  %s", query.data);
+
+	res = PQexec(conn, query.data);
+	termPQExpBuffer(&query);
+
+	if (PQresultStatus(res) != PGRES_COMMAND_OK)
+	{
+		log_error(_("unable to update node record:\n  %s"),
+				  PQerrorMessage(conn));
+		PQclear(res);
+		return false;
+	}
+
+	PQclear(res);
+
+	return true;
+}
+
+
 bool
 update_node_record_set_primary(PGconn *conn, int this_node_id)
 {
@@ -3461,6 +3494,9 @@ create_replication_slot(PGconn *conn, char *slot_name, int server_version_num, P
 	PGresult   *res = NULL;
 	t_replication_slot slot_info = T_REPLICATION_SLOT_INITIALIZER;

+	if (server_version_num == UNKNOWN_SERVER_VERSION_NUM)
+		server_version_num = get_server_version(conn, NULL);
+
 	/*
 	 * Check whether slot exists already; if it exists and is active, that
 	 * means another active standby is using it, which creates an error
--- a/dbutils.h
+++ b/dbutils.h
@@ -343,9 +343,6 @@ bool		atobool(const char *value);
 PGconn *establish_db_connection(const char *conninfo,
 						const bool exit_on_error);
 PGconn	   *establish_db_connection_quiet(const char *conninfo);
-PGconn *establish_db_connection_as_user(const char *conninfo,
-								const char *user,
-								const bool exit_on_error);

 PGconn *establish_db_connection_by_params(t_conninfo_param_list *param_list,
 								  const bool exit_on_error);
@@ -408,6 +405,8 @@ t_server_type parse_node_type(const char *type);
 const char *get_node_type_string(t_server_type type);

 RecordStatus get_node_record(PGconn *conn, int node_id, t_node_info *node_info);
+RecordStatus get_node_record_with_upstream(PGconn *conn, int node_id, t_node_info *node_info);
+
 RecordStatus get_node_record_by_name(PGconn *conn, const char *node_name, t_node_info *node_info);
 t_node_info *get_node_record_pointer(PGconn *conn, int node_id);

@@ -419,7 +418,7 @@ void		get_downstream_node_records(PGconn *conn, int node_id, NodeInfoList *nodes
 void		get_active_sibling_node_records(PGconn *conn, int node_id, int upstream_node_id, NodeInfoList *node_list);
 void		get_node_records_by_priority(PGconn *conn, NodeInfoList *node_list);
 bool		get_all_node_records_with_upstream(PGconn *conn, NodeInfoList *node_list);
-bool		get_downsteam_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *noede_list);
+bool		get_downstream_nodes_with_missing_slot(PGconn *conn, int this_node_id, NodeInfoList *noede_list);

 bool		create_node_record(PGconn *conn, char *repmgr_action, t_node_info *node_info);
 bool		update_node_record(PGconn *conn, char *repmgr_action, t_node_info *node_info);
@@ -428,6 +427,7 @@ bool		truncate_node_records(PGconn *conn);

 bool		update_node_record_set_active(PGconn *conn, int this_node_id, bool active);
 bool		update_node_record_set_primary(PGconn *conn, int this_node_id);
+bool		update_node_record_set_active_standby(PGconn *conn, int this_node_id);
 bool		update_node_record_set_upstream(PGconn *conn, int this_node_id, int new_upstream_node_id);
 bool		update_node_record_status(PGconn *conn, int this_node_id, char *type, int upstream_node_id, bool active);
 bool		update_node_record_conn_priority(PGconn *conn, t_configuration_options *options);
--- a/doc/appendix-faq.sgml
+++ b/doc/appendix-faq.sgml
@@ -69,12 +69,35 @@
    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/static/pgupgrade.html">pg_upgrade</ulink>
+     and recloning standbys from this.
+   </para>
+   <para>
+     To minimize downtime during major upgrades, for more recent PostgreSQL
+     versions <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>
 </sect1>

 <sect1 id="faq-repmgr" xreflabel="repmgr">
  <title><command>repmgr</command></title>

-  <sect2 id="faq-register-existing-node" xreflabel="">
+  <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
@@ -82,6 +105,18 @@
    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>
+
+   <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-failed-primary-standby" xreflabel="Reintegrate a failed primary as a standby">
   <title>How can a failed primary be re-added as a standby?</title>
@@ -180,6 +215,9 @@
   </para>
  </sect2>

+
+
+
 </sect1>

 <sect1 id="faq-repmgrd" xreflabel="repmgrd">
--- a/doc/appendix-release-notes.sgml
+++ b/doc/appendix-release-notes.sgml
@@ -15,9 +15,124 @@
    See also: <xref linkend="upgrading-repmgr">
  </para>

+  <sect1 id="release-4.0.4">
+    <title>Release 4.0.4</title>
+    <para><emphasis>Thu Mar 8, 2018</emphasis></para>
+
+    <para>
+      &repmgr; 4.0.4 contains some bug fixes and and a number of
+      usability enhancements related to logging/diagnostics,
+      event notifications and pre-action checks.
+    </para>
+    <para>
+      This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.3;
+      <application>repmgrd</application> (if running) should be restarted. See <xref linkend="upgrading-repmgr">
+      for more details.
+    </para>
+
+    <sect2>
+      <title>Usability enhancements</title>
+
+      <para>
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              add <command><link linkend="repmgr-standby-clone">repmgr standby clone --recovery-conf-only</link></command>
+              option to enable integration of a standby cloned from another source into a &repmgr; cluster (GitHub #382)
+            </para>
+          </listitem>
+
+         <listitem>
+            <para>
+              remove restriction on using replication slots when cloning from a Barman server (GitHub #379)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              make <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command>
+              timeout values configurable (GitHub #387)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              add missing options to main <literal>--help</literal> output (GitHub #391, #392)
+            </para>
+          </listitem>
+
+        </itemizedlist>
+      </para>
+
+    </sect2>
+
+    <sect2>
+      <title>Bug fixes</title>
+      <para>
+
+        <itemizedlist>
+
+          <listitem>
+            <para>
+              ensure <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>
+              honours the <option>--dry-run</option> option (GitHub #383)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              improve replication slot warnings generated by
+              <command><link linkend="repmgr-node-status">repmgr node status</link></command>
+              (GitHub #385)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              fix --superuser handling when cloning a standby (GitHub #380)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: improve detection of status change from primary to
+              standby
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>:  improve reconnection to the local node after a
+              failover (previously a connection error due to the node starting up was being
+              interpreted as the node being unavailable)
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: when running on a witness server, correctly connect
+              to new primary after a failover
+           </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              <application>repmgrd</application>: add <link linkend="event-notifications">event notification</link>
+              <literal>repmgrd_shutdown</literal> (GitHub #393)
+           </para>
+          </listitem>
+
+        </itemizedlist>
+
+      </para>
+    </sect2>
+
+  </sect1>
+
  <sect1 id="release-4.0.3">
    <title>Release 4.0.3</title>
-    <para><emphasis>??? Feb ??, 2018</emphasis></para>
+    <para><emphasis>Thu Feb 15, 2018</emphasis></para>

    <para>
      &repmgr; 4.0.3 contains some bug fixes and and a number of
@@ -25,6 +140,10 @@
      event notifications and pre-action checks.
    </para>

+    <para>
+      This release can be installed as a simple package upgrade from repmgr 4.0 ~ 4.0.2;
+      repmgrd (if running) should be restarted.
+    </para>
    <sect2>
      <title>Usability enhancements</title>

@@ -65,16 +184,24 @@
          <listitem>
            <para>
              add --dry-run mode to <command><link linkend="repmgr-standby-switchover">repmgr standby follow</link></command>
-              (GitHub #369)
+              (GitHub #368)
            </para>
          </listitem>

          <listitem>
            <para>
-              add <literal>standby_register_sync</literal> event notification, which is fired when
+              provide information about the primary node for
+              <command><link linkend="repmgr-standby-register">repmgr standby register</link></command> and
+              <command><link linkend="repmgr-standby-follow">repmgr standby follow</link></command> event notifications (GitHub #375)
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              add <literal>standby_register_sync</literal> <link linkend="event-notifications">event notification</link>, which is fired when
              <command><link linkend="repmgr-standby-register">repmgr standby register</link></command>
              is run with the <option>--wait-sync</option> option and the new or updated standby node
-              record has synchronised to the standy (GitHub #374)
+              record has synchronised to the standby (GitHub #374)
            </para>
          </listitem>

--- a/doc/repmgr-primary-register.sgml
+++ b/doc/repmgr-primary-register.sgml
@@ -26,7 +26,7 @@
  <refsect1>
    <title>Execution</title>
    <para>
-      Execute with the <literal>--dry-run</literal> option to check what would happen without
+      Execute with the <option>--dry-run</option> option to check what would happen without
      actually registering the primary.
    </para>
    <para>
@@ -36,7 +36,7 @@

    <note>
    <para>
-      If providing the configuration file location with <literal>-f/--config-file</literal>,
+      If providing the configuration file location with <option>-f/--config-file</option>,
      avoid using a relative path, as &repmgr; stores the configuration file location
      in the repmgr metadata for use when &repmgr; is executed remotely (e.g. during
      <xref linkend="repmgr-standby-switchover">). &repmgr; will attempt to convert the
@@ -48,6 +48,33 @@
    </note>
  </refsect1>

+  <refsect1>
+
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually register the primary.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+       <term><option>-F</option><option>--force</option></term>
+        <listitem>
+          <para>
+            Overwrite an existing node record
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
+
  <refsect1>
    <title>Event notifications</title>
    <para>
--- a/doc/repmgr-primary-unregister.sgml
+++ b/doc/repmgr-primary-unregister.sgml
@@ -22,7 +22,7 @@
  <refsect1>
    <title>Execution</title>
    <para>
-      <command>repmgr primary unregister</command> should be run on the current primary,
+      <command>repmgr primary unregister</command> can be run on any active &repmgr; node,
      with the ID of the node to unregister passed as <option>--node-id</option>.
    </para>
    <para>
--- a/doc/repmgr-standby-clone.sgml
+++ b/doc/repmgr-standby-clone.sgml
@@ -100,6 +100,150 @@
   </note>
  </refsect1>

+
+  <refsect1 id="repmgr-standby-create-recovery-conf">
+   <title>Using a standby cloned by another method</title>
+   <para>
+     &repmgr; supports standbys cloned by another method (e.g. using <application>barman</application>'s
+     <command>barman recover</command> command).
+   </para>
+   <para>
+     To integrate the standby as a &repmgr; node, ensure the <filename>repmgr.conf</filename>
+     file is created for the node, 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
+     upstream node if required.
+   </para>
+   <para>
+     Note that the upstream node must be running. An existing
+     <filename>recovery.conf</filename> will not be overwritten unless the
+     <option>-F/--force</option> option is provided.
+   </para>
+   <para>
+     Execute <command>repmgr standby clone --recovery-conf-only --dry-run</command>
+     to check the prerequisites for creating the <filename>recovery.conf</filename> file,
+     and display the contents of the file without actually creating it.
+   </para>
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually clone the standby.
+          </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.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-c, --fast-checkpoint</option></term>
+        <listitem>
+          <para>
+            force fast checkpoint (not effective when cloning from Barman
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--copy-external-config-files[={samepath|pgdata}]</option></term>
+        <listitem>
+          <para>
+            copy configuration files located outside the data directory on the source
+            node to the same path on the standby (default) or to the
+            PostgreSQL data directory.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--no-upstream-connection</option></term>
+        <listitem>
+          <para>
+            when using Barman, do not connect to upstream node
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>-R, --remote-user=USERNAME</option></term>
+        <listitem>
+          <para>
+            remote system username for SSH operations (default: current local system username)
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option> --recovery-conf-only</option></term>
+        <listitem>
+          <para>
+            create <filename>recovery.conf</filename> file for a previously cloned instance
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--replication-user</option></term>
+        <listitem>
+          <para>
+            user to make replication connections with (optional, not usually required)
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--superuser</option></term>
+        <listitem>
+          <para>
+            if the &repmgr; user is not a superuser, the name of a valid superuser must
+            be provided with this option
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>--upstream-conninfo</option></term>
+        <listitem>
+          <para>
+            <literal>primary_conninfo</literal> value to write in recovery.conf
+            when the intended upstream server does not yet exist
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--upstream-node-id</option></term>
+        <listitem>
+          <para>
+            ID of the upstream node to replicate from (optional, defaults to primary node)
+          </para>
+        </listitem>
+      </varlistentry>
+      <varlistentry>
+        <term><option>--without-barman </option></term>
+        <listitem>
+          <para>
+            do not use Barman even if configured
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
  <refsect1>
    <title>Event notifications</title>
    <para>
--- a/doc/repmgr-standby-follow.sgml
+++ b/doc/repmgr-standby-follow.sgml
@@ -30,6 +30,7 @@
      To re-add an inactive node to the replication cluster, see
      <xref linkend="repmgr-node-rejoin">
    </para>
+
  </refsect1>

  <refsect1>
@@ -74,7 +75,10 @@
        <term><option>--wait</option></term>
        <listitem>
          <para>
-            Wait for a primary to appear.
+            Wait for a primary to appear. &repmgr; will wait for up to
+            <varname>primary_follow_timeout</varname> seconds
+            (default: 60 seconds) to verify that the standby is following the new primary.
+            This value can be defined in <filename>repmgr.conf</filename>.
          </para>
        </listitem>
      </varlistentry>
--- a/doc/repmgr-standby-promote.sgml
+++ b/doc/repmgr-standby-promote.sgml
@@ -26,6 +26,12 @@
      by using <xref linkend="repmgr-standby-follow">; if <application>repmgrd</application>
        is active, it will handle this automatically.
    </para>
+    <para>
+      Note that &repmgr; will wait for up to <varname>promote_check_timeout</varname> seconds
+      (default: 60 seconds) to verify that the standby has been promoted, and will
+      check the promotion every <varname>promote_check_interval</varname> seconds (default: 1 second).
+      Both values can be defined in <filename>repmgr.conf</filename>.
+    </para>
  </refsect1>

  <refsect1>
@@ -42,6 +48,7 @@
    </para>
  </refsect1>

+
  <refsect1>
    <title>Event notifications</title>
    <para>
--- a/doc/repmgr-standby-register.sgml
+++ b/doc/repmgr-standby-register.sgml
@@ -92,6 +92,73 @@
   </para>
  </refsect1>

+  <refsect1 id="repmgr-standby-register-node-cloned-other-source">
+    <title>Registering a node not cloned by repmgr</title>
+    <para>
+      If you've cloned a standby using another method (e.g. <application>barman</application>'s
+     <command>barman recover</command> command), first execute
+     <link linkend="repmgr-standby-create-recovery-conf">repmgr standby clone --recovery-conf-only</link>
+     to add the <filename>recovery.conf</filename> file, then register the standby as usual.
+    </para>
+  </refsect1>
+
+  <refsect1>
+
+    <title>Options</title>
+
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--dry-run</option></term>
+        <listitem>
+          <para>
+            Check prerequisites but don't actually register the standby.
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+       <term><option>-F</option><option>--force</option></term>
+        <listitem>
+          <para>
+            Overwrite an existing node record
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+      <varlistentry>
+        <term><option>--upstream-node-id</option></term>
+        <listitem>
+          <para>
+            ID of the upstream node to replicate from (optional)
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
+        <term><option>--wait-start</option></term>
+        <listitem>
+          <para>
+            wait for the standby to start (timeout in seconds, default 30 seconds)
+          </para>
+        </listitem>
+      </varlistentry>
+
+     <varlistentry>
+        <term><option>--wait-sync</option></term>
+        <listitem>
+          <para>
+            wait for the node record to synchronise to the standby (optional timeout in seconds)
+          </para>
+        </listitem>
+      </varlistentry>
+
+
+    </variablelist>
+  </refsect1>
+
  <refsect1>
    <title>Event notifications</title>
    <para>
--- a/doc/repmgr-standby-unregister.sgml
+++ b/doc/repmgr-standby-unregister.sgml
@@ -43,6 +43,22 @@
    </para>
  </refsect1>

+  <refsect1>
+    <title>Options</title>
+    <variablelist>
+
+      <varlistentry>
+        <term><option>--node-id</option></term>
+        <listitem>
+          <para>
+            <varname>node_id</varname> of the node to unregister (optional)
+          </para>
+        </listitem>
+      </varlistentry>
+
+    </variablelist>
+  </refsect1>
+
  <refsect1>
    <title>Event notifications</title>
    <para>
--- a/doc/repmgrd-degraded-monitoring.sgml
+++ b/doc/repmgrd-degraded-monitoring.sgml
@@ -40,7 +40,7 @@
   </listitem>

   <listitem>
-    <simpara>repmgrd is monitoring the primary node, but it is not available</simpara>
+    <simpara>repmgrd is monitoring the primary node, but it is not available (and no other node has been promoted as primary)</simpara>
   </listitem>
  </itemizedlist>
 </para>
@@ -69,7 +69,15 @@
  By default, <literal>repmgrd</literal> will continue in degraded monitoring mode indefinitely.
  However a timeout (in seconds) can be set with <varname>degraded_monitoring_timeout</varname>,
  after which <application>repmgrd</application> will terminate.
-
 </para>

+ <note>
+   <para>
+     If <application>repmgrd</application> is monitoring a primary mode which has been stopped
+     and manually restarted as a standby attached to a new primary, it will automatically detect
+     the status change and update the node record to reflect the node's new status
+     as an active standby. It will then resume monitoring the node as a standby.
+   </para>
+ </note>
+
 </chapter>
--- a/doc/version.sgml
+++ b/doc/version.sgml
@@ -1 +1 @@
-<!ENTITY repmgrversion "4.0.3">
+<!ENTITY repmgrversion "4.0.4">
--- a/repmgr-action-node.c
+++ b/repmgr-action-node.c
@@ -92,7 +92,7 @@ do_node_status(void)

 	/* Check node exists and is really a standby */

-	if (get_node_record(conn, config_file_options.node_id, &node_info) != RECORD_FOUND)
+	if (get_node_record_with_upstream(conn, config_file_options.node_id, &node_info) != RECORD_FOUND)
 	{
 		log_error(_("no record found for node %i"), config_file_options.node_id);
 		PQfinish(conn);
@@ -308,14 +308,16 @@ do_node_status(void)

 	/*
 	 * check for missing replication slots - we do this regardless of
-	 * what "max_replication_slots" is set to
+	 * what "max_replication_slots" is set to, in case the downstream
+	 * node was configured with "use_replication_slots=true" and is
+	 * expecting a replication slot to be available
 	 */

 	{
 		NodeInfoList missing_slots = T_NODE_INFO_LIST_INITIALIZER;
-		get_downsteam_nodes_with_missing_slot(conn,
-											  config_file_options.node_id,
-											  &missing_slots);
+		get_downstream_nodes_with_missing_slot(conn,
+											   config_file_options.node_id,
+											   &missing_slots);

 		if (missing_slots.node_count > 0)
 		{
@@ -1814,7 +1816,7 @@ do_node_rejoin(void)
 	 * Forcibly rewind node if requested (this is mainly for use when this
 	 * action is being executed by "repmgr standby switchover")
 	 */
-	if (runtime_options.force_rewind == true)
+	if (runtime_options.force_rewind == true && runtime_options.dry_run == false)
 	{
 		int			ret;
 		PQExpBufferData		filebuf;
@@ -1949,6 +1951,12 @@ do_node_rejoin(void)
 		}
 	}

+	if (runtime_options.dry_run == true)
+	{
+		log_info(_("prerequisites for executing NODE REJOIN are met"));
+		exit(SUCCESS);
+	}
+
 	initPQExpBuffer(&follow_output);

 	success = do_standby_follow_internal(upstream_conn,
--- a/repmgr-action-standby.c
+++ b/repmgr-action-standby.c
@@ -73,6 +73,7 @@ static char datadir_list_filename[MAXLEN];
 static char barman_command_buf[MAXLEN] = "";

 static void _do_standby_promote_internal(PGconn *conn, const char *data_dir);
+static void _do_create_recovery_conf(void);

 static void check_barman_config(void);
 static void check_source_server(void);
@@ -95,9 +96,8 @@ 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 *recovery_conninfo, const char *data_dir);
-static void write_primary_conninfo(char *line, t_conninfo_param_list *param_list);
-static bool write_recovery_file_line(FILE *recovery_file, char *recovery_file_path, char *line);
+static bool create_recovery_file(t_node_info *node_record, t_conninfo_param_list *recovery_conninfo, char *dest, bool as_file);
+static void write_primary_conninfo(PQExpBufferData *dest, t_conninfo_param_list *param_list);

 static NodeStatus parse_node_status_is_shutdown_cleanly(const char *node_status_output, XLogRecPtr *checkPoint);
 static CheckStatus parse_node_check_archiver(const char *node_check_output, int *files, int *threshold);
@@ -119,6 +119,7 @@ static ConnectionStatus parse_remote_node_replication_connection(const char *nod
 *  --recovery-min-apply-delay
 *  --replication-user (only required if no upstream record)
 *  --without-barman
+ *  --recovery-conf-only
 */

 void
@@ -128,7 +129,15 @@ do_standby_clone(void)
 	int			r = 0;

 	/* dummy node record */
-	t_node_info node_record = T_NODE_INFO_INITIALIZER;
+	t_node_info local_node_record = T_NODE_INFO_INITIALIZER;
+
+	/*
+	 * --recovery-conf-only provided - we'll handle that separately
+	 */
+	if (runtime_options.recovery_conf_only == true)
+	{
+		return _do_create_recovery_conf();
+	}

 	/*
 	 * conninfo params for the actual upstream node (which might be different
@@ -177,8 +186,8 @@ do_standby_clone(void)
 		check_barman_config();
 	}

-	init_node_record(&node_record);
-	node_record.type = STANDBY;
+	init_node_record(&local_node_record);
+	local_node_record.type = STANDBY;

 	/*
 	 * Initialise list of conninfo parameters which will later be used to
@@ -521,7 +530,7 @@ do_standby_clone(void)

 	if (mode != barman)
 	{
-		initialise_direct_clone(&node_record);
+		initialise_direct_clone(&local_node_record);
 	}

 	switch (mode)
@@ -545,13 +554,17 @@ do_standby_clone(void)
 		}
 	}

-	if (mode == pg_basebackup)
+	switch (mode)
 	{
-		r = run_basebackup(&node_record);
-	}
-	else
-	{
-		r = run_file_backup(&node_record);
+		case pg_basebackup:
+			r = run_basebackup(&local_node_record);
+			break;
+		case barman:
+			r = run_file_backup(&local_node_record);
+			break;
+		default:
+			/* should never reach here */
+			log_error(_("unknown clone mode"));
 	}


@@ -561,7 +574,7 @@ do_standby_clone(void)
 		/* If a replication slot was previously created, drop it */
 		if (config_file_options.use_replication_slots == true)
 		{
-			drop_replication_slot(source_conn, node_record.slot_name);
+			drop_replication_slot(source_conn, local_node_record.slot_name);
 		}

 		log_error(_("unable to take a base backup of the primary server"));
@@ -588,7 +601,7 @@ do_standby_clone(void)

 	/* Write the recovery.conf file */

-	if (create_recovery_file(&node_record, &recovery_conninfo, local_data_directory) == false)
+	if (create_recovery_file(&local_node_record, &recovery_conninfo, local_data_directory, true) == false)
 	{
 		/* create_recovery_file() will log an error */
 		log_notice(_("unable to create recovery.conf; see preceding error messages"));
@@ -789,6 +802,375 @@ check_barman_config(void)
 }


+/*
+ * _do_create_recovery_conf()
+ *
+ * Create recovery.conf for a previously cloned instance.
+ *
+ * Prerequisites:
+ *
+ * - data directory must be provided
+ * - the instance should not be running
+ * - an existing "recovery.conf" file can only be overwritten with
+ *   -F/--force
+ * - connection parameters for an existing, running node must be provided
+ * - --upstream-node-id, if provided, will be "primary_conninfo",
+ *   otherwise primary node id; node must exist; unless -F/--force
+ *   provided, must be active and connection possible
+ * - if replication slots in use, create (respect --dry-run)
+ *
+ * not compatible with --no-upstream-connection
+ *
+ */
+
+static void
+_do_create_recovery_conf(void)
+{
+	t_node_info local_node_record = T_NODE_INFO_INITIALIZER;
+	t_node_info upstream_node_record = T_NODE_INFO_INITIALIZER;
+
+	RecordStatus record_status = RECORD_NOT_FOUND;
+	char		recovery_file_path[MAXPGPATH] = "";
+	struct stat st;
+	bool		node_is_running = false;
+	bool		slot_creation_required = false;
+	PGconn	   *upstream_conn = NULL;
+	PGconn	   *upstream_repl_conn = NULL;
+
+	get_node_data_directory(local_data_directory);
+
+	if (local_data_directory[0] == '\0')
+	{
+		log_error(_("no data directory provided"));
+		log_hint(_("provide the node's \"repmgr.conf\" file with -f/--config-file or the data directory with -D/--pgdata"));
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/*
+	 * Do some sanity checks on the data directory to make sure
+	 * it contains a valid but dormant instance
+	 */
+	switch (check_dir(local_data_directory))
+	{
+		case DIR_ERROR:
+			log_error(_("unable to access specified data directory \"%s\""), local_data_directory);
+			log_detail("%s", strerror(errno));
+			exit(ERR_BAD_CONFIG);
+			break;
+		case DIR_NOENT:
+			log_error(_("specified data directory \"%s\" does not exist"), local_data_directory);
+			exit(ERR_BAD_CONFIG);
+			break;
+		case DIR_EMPTY:
+			log_error(_("specified data directory \"%s\" is empty"), local_data_directory);
+			exit(ERR_BAD_CONFIG);
+			break;
+		case DIR_NOT_EMPTY:
+			/* Present but not empty */
+			if (!is_pg_dir(local_data_directory))
+			{
+				log_error(_("specified data directory \"%s\" does not contain a PostgreSQL instance"), local_data_directory);
+				exit(ERR_BAD_CONFIG);
+			}
+
+			if (is_pg_running(local_data_directory))
+			{
+				if (runtime_options.force == false)
+				{
+					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"));
+					exit(ERR_BAD_CONFIG);
+				}
+
+				node_is_running = true;
+
+				if (runtime_options.dry_run == true)
+				{
+					log_warning(_("\"recovery.conf\" would be created in an active data directory"));
+				}
+				else
+				{
+					log_warning(_("creating \"recovery.conf\" in an active data directory"));
+				}
+			}
+			break;
+		default:
+			break;
+	}
+
+	/* check connection */
+	source_conn = establish_db_connection_by_params(&source_conninfo, true);
+
+	/* determine node for primary_conninfo */
+
+	if (runtime_options.upstream_node_id != UNKNOWN_NODE_ID)
+	{
+		upstream_node_id = runtime_options.upstream_node_id;
+	}
+	else
+	{
+		/* if --upstream-node-id not specifically supplied, get primary node id */
+		upstream_node_id = get_primary_node_id(source_conn);
+
+		if (upstream_node_id == NODE_NOT_FOUND)
+		{
+			log_error(_("unable to determine primary node for this replication cluster"));
+			PQfinish(source_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		log_debug("primary node determined as: %i", upstream_node_id);
+	}
+
+	/* attempt to retrieve upstream node record */
+	record_status = get_node_record(source_conn,
+									upstream_node_id,
+									&upstream_node_record);
+
+	if (record_status != RECORD_FOUND)
+	{
+		log_error(_("unable to retrieve node record for upstream node %i"), upstream_node_id);
+
+		if (record_status == RECORD_ERROR)
+		{
+			log_detail("%s", PQerrorMessage(source_conn));
+		}
+
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* attempt to retrieve local node record */
+	record_status = get_node_record(source_conn,
+									config_file_options.node_id,
+									&local_node_record);
+
+	if (record_status != RECORD_FOUND)
+	{
+		log_error(_("unable to retrieve node record for local node %i"), config_file_options.node_id);
+
+		if (record_status == RECORD_ERROR)
+		{
+			log_detail("%s", PQerrorMessage(source_conn));
+		}
+
+
+		exit(ERR_BAD_CONFIG);
+	}
+
+	PQfinish(source_conn);
+
+
+	/* connect to upstream (which could be different to source) */
+
+	upstream_conn = establish_db_connection(upstream_node_record.conninfo, false);
+	if (PQstatus(upstream_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to connect to upstream node \"%s\" (ID: %i)"),
+				  upstream_node_record.node_name,
+ 				  upstream_node_id);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* Set the application name to this node's name */
+	if (config_file_options.node_name[0] != '\0')
+		param_set(&recovery_conninfo, "application_name", config_file_options.node_name);
+
+	/* Set the replication user from the primary node record */
+	param_set(&recovery_conninfo, "user", upstream_node_record.repluser);
+
+	initialize_conninfo_params(&recovery_conninfo, false);
+
+	/* We ignore any application_name set in the primary's conninfo */
+	parse_conninfo_string(upstream_node_record.conninfo, &recovery_conninfo, NULL, true);
+
+	/* check that a replication connection can be made (--force = override) */
+	upstream_repl_conn = establish_db_connection_by_params(&recovery_conninfo, false);
+
+	if (PQstatus(upstream_repl_conn) != CONNECTION_OK)
+	{
+		if (runtime_options.force == false)
+		{
+			log_error(_("unable to initiate replication connection to upstream node \"%s\" (ID: %i)"),
+					  upstream_node_record.node_name,
+					  upstream_node_id);
+			PQfinish(upstream_conn);
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+	/* if replication slots are in use, perform some checks */
+	if (config_file_options.use_replication_slots == true)
+	{
+		PQExpBufferData msg;
+		t_replication_slot slot_info = T_REPLICATION_SLOT_INITIALIZER;
+
+		record_status = get_slot_record(upstream_conn, local_node_record.slot_name, &slot_info);
+
+		/* check if replication slot exists*/
+		if (record_status == RECORD_FOUND)
+		{
+			if (slot_info.active == true)
+			{
+				initPQExpBuffer(&msg);
+
+				appendPQExpBuffer(&msg,
+								  _("an active replication slot named \"%s\" already exists on upstream node \"%s\" (ID: %i)"),
+								  local_node_record.slot_name,
+								  upstream_node_record.node_name,
+								  upstream_node_id);
+				if (runtime_options.force == false && runtime_options.dry_run == false)
+				{
+					log_error("%s", msg.data);
+					log_hint(_("use -F/--force to continue anyway"));
+					termPQExpBuffer(&msg);
+					PQfinish(upstream_conn);
+					exit(ERR_BAD_CONFIG);
+				}
+
+				log_warning("%s", msg.data);
+				termPQExpBuffer(&msg);
+			}
+			else
+			{
+				log_info(_("an inactive replication slot for this node exists on the upstream node"));
+			}
+		}
+		/* if not, if check one can and should be created */
+		else
+		{
+			get_node_replication_stats(upstream_conn, UNKNOWN_SERVER_VERSION_NUM, &upstream_node_record);
+
+		    if (upstream_node_record.max_replication_slots > upstream_node_record.total_replication_slots)
+			{
+				slot_creation_required = true;
+			}
+			else
+			{
+				initPQExpBuffer(&msg);
+
+				appendPQExpBuffer(&msg,
+								  _("insufficient free replicaiton slots on upstream node \"%s\" (ID: %i)"),
+								  upstream_node_record.node_name,
+								  upstream_node_id);
+
+				if (runtime_options.force == false && runtime_options.dry_run == false)
+				{
+					log_error("%s", msg.data);
+					log_hint(_("use -F/--force to continue anyway"));
+					termPQExpBuffer(&msg);
+					PQfinish(upstream_conn);
+					exit(ERR_BAD_CONFIG);
+				}
+
+				log_warning("%s", msg.data);
+				termPQExpBuffer(&msg);
+			}
+		}
+	}
+
+	/* check if recovery.conf exists */
+
+	maxpath_snprintf(recovery_file_path, "%s/%s", local_data_directory, RECOVERY_COMMAND_FILE);
+
+	if (stat(recovery_file_path, &st) == -1)
+	{
+		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);
+		}
+
+		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(&upstream_node_record, &recovery_conninfo, recovery_conf_contents, false);
+
+		log_info(_("would create \"recovery.conf\" file in \"%s\""), local_data_directory);
+		log_detail(_("\n%s"), recovery_conf_contents);
+	}
+	else
+	{
+		if (!create_recovery_file(&upstream_node_record, &recovery_conninfo, local_data_directory, true))
+		{
+			log_error(_("unable to create \"recovery.conf\""));
+		}
+		else
+		{
+			log_notice(_("\"recovery.conf\" created as \"%s\""), recovery_file_path);
+
+			if (node_is_running == true)
+			{
+				log_hint(_("node must be restarted for the new file to take effect"));
+			}
+		}
+	}
+
+	/* add replication slot, if required */
+	if (slot_creation_required == true)
+	{
+		if (runtime_options.dry_run == true)
+		{
+			log_info(_("would create replication slot \"%s\" on upstream node \"%s\" (ID: %i)"),
+					 local_node_record.slot_name,
+					 upstream_node_record.node_name,
+					 upstream_node_id);
+		}
+		else
+		{
+			PQExpBufferData msg;
+			initPQExpBuffer(&msg);
+
+			if (create_replication_slot(upstream_conn,
+										local_node_record.slot_name,
+										UNKNOWN_SERVER_VERSION_NUM,
+										&msg) == false)
+			{
+				log_error("%s", msg.data);
+				PQfinish(upstream_conn);
+				termPQExpBuffer(&msg);
+				exit(ERR_BAD_CONFIG);
+			}
+
+			termPQExpBuffer(&msg);
+
+			log_notice(_("replication slot \"%s\" created on upstream node \"%s\" (ID: %i)"),
+					   local_node_record.slot_name,
+					   upstream_node_record.node_name,
+					   upstream_node_id);
+		}
+	}
+
+
+	PQfinish(upstream_conn);
+
+	return;
+}
+
+
 /*
 * do_standby_register()
 *
@@ -1516,10 +1898,8 @@ static void
 _do_standby_promote_internal(PGconn *conn, const char *data_dir)
 {
 	char		script[MAXLEN];
-	int			r;
-	int			i,
-				promote_check_timeout = 60,
-				promote_check_interval = 2;
+	int			r,
+				i;
 	bool		promote_success = false;
 	PQExpBufferData details;

@@ -1566,8 +1946,7 @@ _do_standby_promote_internal(PGconn *conn, const char *data_dir)
 		exit(ERR_PROMOTION_FAIL);
 	}

-	/* TODO: make these values configurable */
-	for (i = 0; i < promote_check_timeout; i += promote_check_interval)
+	for (i = 0; i < config_file_options.promote_check_timeout; i += config_file_options.promote_check_interval)
 	{
 		recovery_type = get_recovery_type(conn);

@@ -1576,7 +1955,7 @@ _do_standby_promote_internal(PGconn *conn, const char *data_dir)
 			promote_success = true;
 			break;
 		}
-		sleep(promote_check_interval);
+		sleep(config_file_options.promote_check_interval);
 	}

 	if (promote_success == false)
@@ -1595,6 +1974,7 @@ _do_standby_promote_internal(PGconn *conn, const char *data_dir)
 		}
 	}

+	log_verbose(LOG_INFO, _("standby promoted to primary after %i second(s)"), i);

 	/*
 	 * Execute a CHECKPOINT as soon as possible after promotion. The primary
@@ -2056,7 +2436,7 @@ do_standby_follow_internal(PGconn *primary_conn, t_node_info *primary_node_recor
 	log_notice(_("setting node %i's primary to node %i"),
 			   config_file_options.node_id, primary_node_record->node_id);

-	if (!create_recovery_file(&local_node_record, &recovery_conninfo, config_file_options.data_directory))
+	if (!create_recovery_file(&local_node_record, &recovery_conninfo, config_file_options.data_directory, true))
 	{
 		/* XXX ERR_RECOVERY_FILE ??? */
 		*error_code = ERR_BAD_CONFIG;
@@ -4005,10 +4385,14 @@ check_upstream_config(PGconn *conn, int server_version_num, t_node_info *node_in

 		param_set(&repl_conninfo, "replication", "1");

-		if (*runtime_options.replication_user)
+		if (runtime_options.replication_user[0] != '\0')
 		{
 			param_set(&repl_conninfo, "user", runtime_options.replication_user);
 		}
+		else if (upstream_repluser[0] != '\0')
+		{
+			param_set(&repl_conninfo, "user", upstream_repluser);
+		}
 		else if (node_info->repluser[0] != '\0')
 		{
 			param_set(&repl_conninfo, "user", node_info->repluser);
@@ -4060,12 +4444,13 @@ check_upstream_config(PGconn *conn, int server_version_num, t_node_info *node_in
 			 * XXX at this point we could check
 			 * current_setting('max_wal_senders) - COUNT(*) FROM
 			 * pg_stat_replication; if >= min_replication_connections we could
-			 * infer possible authentication error.
+			 * infer possible authentication error / lack of permissions.
 			 *
 			 * Alternatively call PQconnectStart() and poll for
 			 * presence/absence of CONNECTION_AUTH_OK ?
 			 */
 			log_error(_("unable to establish necessary replication connections"));
+
 			log_hint(_("increase \"max_wal_senders\" by at least %i"),
 					 min_replication_connections - possible_replication_connections);

@@ -4278,10 +4663,14 @@ run_basebackup(t_node_info *node_record)
 		/* string will already have been parsed */
 		(void) parse_conninfo_string(runtime_options.dbname, &conninfo, NULL, false);

-		if (*runtime_options.replication_user)
+		if (runtime_options.replication_user[0] != '\0')
 		{
 			param_set(&conninfo, "user", runtime_options.replication_user);
 		}
+		else if (upstream_repluser[0] != '\0')
+		{
+			param_set(&conninfo, "user", upstream_repluser);
+		}
 		else
 		{
 			param_set(&conninfo, "user", node_record->repluser);
@@ -4314,6 +4703,10 @@ run_basebackup(t_node_info *node_record)
 		{
 			appendPQExpBuffer(&params, " -U %s", runtime_options.replication_user);
 		}
+		else if (strlen(upstream_repluser))
+		{
+			appendPQExpBuffer(&params, " -U %s", upstream_repluser);
+		}
 		else if (strlen(node_record->repluser))
 		{
 			appendPQExpBuffer(&params, " -U %s", node_record->repluser);
@@ -4768,8 +5161,8 @@ run_file_backup(t_node_info *node_record)
 				100000,
 				90500,
 				90400, 90400, 90400, 90400, 90400,
-				0, 0, 0, 0, 0, 0,
-				0, -100000, 0
+				0, 0, 0, 0, 0,
+				0, 0, 0, -100000
 			};

 			for (i = 0; dirs[i]; i++)
@@ -4895,7 +5288,7 @@ run_file_backup(t_node_info *node_record)
 				if (unlink(tblspc_symlink.data) < 0 && errno != ENOENT)
 				{
 					log_error(_("unable to remove tablespace symlink %s"), tblspc_symlink.data);
-
+					log_detail("%s", strerror(errno));
 					r = ERR_BAD_BASEBACKUP;
 					goto stop_backup;
 				}
@@ -4935,9 +5328,9 @@ run_file_backup(t_node_info *node_record)
 		 */
 		if (unlink(tablespace_map_filename.data) < 0 && errno != ENOENT)
 		{
-			log_error(_("unable to remove tablespace_map file %s: %s"),
-					  tablespace_map_filename.data,
-					  strerror(errno));
+			log_error(_("unable to remove tablespace_map file \"%s\""),
+					  tablespace_map_filename.data);
+			log_detail("%s", strerror(errno));

 			r = ERR_BAD_BASEBACKUP;
 			goto stop_backup;
@@ -4971,6 +5364,90 @@ stop_backup:
 		rmtree(local_repmgr_tmp_directory, true);
 	}

+
+	/*
+	 * if replication slots in use, create replication slot
+	 */
+	if (r == SUCCESS)
+	{
+		if (config_file_options.use_replication_slots == true)
+		{
+			bool slot_warning = false;
+			if (runtime_options.no_upstream_connection == true)
+			{
+				slot_warning = true;
+			}
+			else
+			{
+				t_node_info upstream_node_record = T_NODE_INFO_INITIALIZER;
+				t_replication_slot slot_info = T_REPLICATION_SLOT_INITIALIZER;
+				RecordStatus record_status = RECORD_NOT_FOUND;
+				PGconn	   *upstream_conn = NULL;
+
+				record_status = get_node_record(source_conn, upstream_node_id, &upstream_node_record);
+
+				if (record_status != RECORD_FOUND)
+				{
+					log_error(_("unable to retrieve node record for upstream node %i"), upstream_node_id);
+					slot_warning = true;
+				}
+				else
+				{
+					upstream_conn = establish_db_connection(upstream_node_record.conninfo, false);
+					if (PQstatus(upstream_conn) != CONNECTION_OK)
+					{
+						log_error(_("unable to connect to upstream node %i to create a replication slot"), upstream_node_id);
+						slot_warning = true;
+					}
+					else
+					{
+						record_status = get_slot_record(upstream_conn, node_record->slot_name, &slot_info);
+
+						if (record_status == RECORD_FOUND)
+						{
+							log_verbose(LOG_INFO,
+										_("replication slot \"%s\" aleady exists on upstream node %i"),
+										node_record->slot_name,
+										upstream_node_id);
+						}
+						else
+						{
+							PQExpBufferData errmsg;
+
+							initPQExpBuffer(&errmsg);
+
+							if (create_replication_slot(upstream_conn, node_record->slot_name, source_server_version_num, &errmsg) == false)
+							{
+								log_error(_("unable to create replication slot on upstream node %i"), upstream_node_id);
+								log_detail("%s", errmsg.data);
+								slot_warning = true;
+							}
+							else
+							{
+								log_notice(_("replication slot \"%s\" created on upstream node \"%s\" (ID: %i)"),
+										   node_record->slot_name,
+										   upstream_node_record.node_name,
+										   upstream_node_id );
+							}
+							termPQExpBuffer(&errmsg);
+						}
+
+						PQfinish(upstream_conn);
+					}
+				}
+			}
+
+
+			if (slot_warning == true)
+			{
+				log_warning(_("\"use_replication_slots\" specified but a replication slot could not be created"));
+				log_hint(_("ensure a replication slot called \"%s\" is created on the upstream node (ID: %i)"),
+						 node_record->slot_name,
+						 upstream_node_id);
+			}
+		}
+	}
+
 	return r;
 }

@@ -5295,40 +5772,19 @@ drop_replication_slot_if_exists(PGconn *conn, int node_id, char *slot_name)
 * might not be available.
 */
 bool
-create_recovery_file(t_node_info *node_record, t_conninfo_param_list *recovery_conninfo, const char *data_dir)
+create_recovery_file(t_node_info *node_record, t_conninfo_param_list *recovery_conninfo, char *dest, bool as_file)
 {
-	FILE	   *recovery_file;
+	PQExpBufferData recovery_file_buf;
 	char		recovery_file_path[MAXPGPATH] = "";
-	char		line[MAXLEN] = "";
+	FILE	   *recovery_file;
 	mode_t		um;

-	maxpath_snprintf(recovery_file_path, "%s/%s", data_dir, RECOVERY_COMMAND_FILE);
-
-	/* 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;
-	}
-
-	log_debug("create_recovery_file(): creating \"%s\"...",
-			  recovery_file_path);
+	/* create file in buffer */
+	initPQExpBuffer(&recovery_file_buf);

 	/* standby_mode = 'on' */
-	maxlen_snprintf(line, "standby_mode = 'on'\n");
-
-	if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
-		return false;
-
-	trim(line);
-	log_debug("recovery.conf: %s", line);
+	appendPQExpBuffer(&recovery_file_buf,
+					  "standby_mode = 'on'\n");

 	/* primary_conninfo = '...' */

@@ -5339,8 +5795,10 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *recovery_c
 	{
 		char	   *escaped = escape_recovery_conf_value(runtime_options.upstream_conninfo);

-		maxlen_snprintf(line, "primary_conninfo = '%s'\n",
-						escaped);
+		appendPQExpBuffer(&recovery_file_buf,
+						  "primary_conninfo = '%s'\n",
+						  escaped);
+
 		free(escaped);
 	}

@@ -5350,84 +5808,90 @@ create_recovery_file(t_node_info *node_record, t_conninfo_param_list *recovery_c
 	 */
 	else
 	{
-		write_primary_conninfo(line, recovery_conninfo);
+		write_primary_conninfo(&recovery_file_buf, recovery_conninfo);
 	}

-	if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
-		return false;
-
-	trim(line);
-	log_debug("recovery.conf: %s", line);
-
 	/* recovery_target_timeline = 'latest' */
-	maxlen_snprintf(line, "recovery_target_timeline = 'latest'\n");
+	appendPQExpBuffer(&recovery_file_buf,
+					  "recovery_target_timeline = 'latest'\n");

-	if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
-		return false;
-
-	trim(line);
-	log_debug("recovery.conf: %s", line);

 	/* recovery_min_apply_delay = ... (optional) */
 	if (config_file_options.recovery_min_apply_delay_provided == true)
 	{
-		maxlen_snprintf(line, "recovery_min_apply_delay = %s\n",
-						config_file_options.recovery_min_apply_delay);
-		if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
-			return false;
+		appendPQExpBuffer(&recovery_file_buf,
+						  "recovery_min_apply_delay = %s\n",
+						  config_file_options.recovery_min_apply_delay);

-		trim(line);
-		log_debug("recovery.conf: %s", line);
 	}

 	/* primary_slot_name = '...' (optional, for 9.4 and later) */
 	if (config_file_options.use_replication_slots)
 	{
-		maxlen_snprintf(line, "primary_slot_name = %s\n",
-						node_record->slot_name);
-		if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
-			return false;
-
-		trim(line);
-		log_debug("recovery.conf: %s", line);
+		appendPQExpBuffer(&recovery_file_buf,
+						  "primary_slot_name = %s\n",
+						  node_record->slot_name);
 	}

 	/*
 	 * If restore_command is set, we use it as restore_command in
 	 * recovery.conf
 	 */
-	if (strcmp(config_file_options.restore_command, "") != 0)
+	if (config_file_options.restore_command[0] != '\0')
 	{
-		maxlen_snprintf(line, "restore_command = '%s'\n",
-						config_file_options.restore_command);
-		if (write_recovery_file_line(recovery_file, recovery_file_path, line) == false)
+		char	   *escaped = escape_recovery_conf_value(config_file_options.restore_command);
+
+		appendPQExpBuffer(&recovery_file_buf,
+						  "restore_command = '%s'\n",
+						  escaped);
+		free(escaped);
+	}
+
+	if (as_file == true)
+	{
+		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;
+		}

-		trim(line);
-		log_debug("recovery.conf: %s", line);
-	}
-	fclose(recovery_file);
+		log_debug("recovery file is:\n%s", recovery_file_buf.data);

-	return true;
-}
+		if (fputs(recovery_file_buf.data, recovery_file) == EOF)
+		{
+			log_error(_("unable to write to recovery file at \"%s\""), recovery_file_path);
+			fclose(recovery_file);
+			termPQExpBuffer(&recovery_file_buf);
+			return false;
+		}

-
-static bool
-write_recovery_file_line(FILE *recovery_file, char *recovery_file_path, char *line)
-{
-	if (fputs(line, recovery_file) == EOF)
-	{
-		log_error(_("unable to write to recovery file at \"%s\""), recovery_file_path);
 		fclose(recovery_file);
-		return false;
 	}
+	else
+	{
+		maxlen_snprintf(dest, "%s", recovery_file_buf.data);
+	}
+
+	termPQExpBuffer(&recovery_file_buf);

 	return true;
 }


 static void
-write_primary_conninfo(char *line, t_conninfo_param_list *param_list)
+write_primary_conninfo(PQExpBufferData *dest, t_conninfo_param_list *param_list)
 {
 	PQExpBufferData conninfo_buf;
 	bool		application_name_provided = false;
@@ -5509,7 +5973,9 @@ write_primary_conninfo(char *line, t_conninfo_param_list *param_list)
 	}

 	escaped = escape_recovery_conf_value(conninfo_buf.data);
-	maxlen_snprintf(line, "primary_conninfo = '%s'\n", escaped);
+
+	appendPQExpBuffer(dest,
+					  "primary_conninfo = '%s'\n", escaped);

 	free(escaped);
 	free_conninfo_params(&env_conninfo);
@@ -5771,6 +6237,8 @@ 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"));
+
 	puts("");

 	printf(_("STANDBY REGISTER\n"));
--- a/repmgr-client-global.h
+++ b/repmgr-client-global.h
@@ -80,6 +80,7 @@ typedef struct
 	char		replication_user[MAXLEN];
 	char		upstream_conninfo[MAXLEN];
 	bool		without_barman;
+	bool		recovery_conf_only;

 	/* "standby clone"/"standby follow" options */
 	int			upstream_node_id;
@@ -138,14 +139,14 @@ typedef struct
 		/* output options */ \
 		false, false, false,  \
 		/* database connection options */ \
-		"", "", "",	"",				  \
+		"", "", "",	"", \
 		/* other connection options */ \
-		"",	"",  \
+		"",	"", \
 		/* general node options */ \
 		UNKNOWN_NODE_ID, "", "", UNKNOWN_NODE_ID, \
 		/* "standby clone" options */ \
 		false, CONFIG_FILE_SAMEPATH, false, false, false, "", "", "", \
-		false,  \
+		false, false, \
 		/* "standby clone"/"standby follow" options */ \
 		NO_UPSTREAM_NODE, \
 		/* "standby register" options */ \
@@ -164,7 +165,7 @@ typedef struct
 		false, "", CLUSTER_EVENT_LIMIT,	\
 		/* "cluster cleanup" options */ \
 		0, \
-		/* Following options for internal use */ \
+		/* following options for internal use */ \
 		"/tmp", OM_TEXT	\
 }

--- a/repmgr-client.c
+++ b/repmgr-client.c
@@ -176,7 +176,7 @@ main(int argc, char **argv)
 		strncpy(runtime_options.username, pw->pw_name, MAXLEN);
 	}

-	while ((c = getopt_long(argc, argv, "?Vb:f:FWd:h:p:U:R:S:D:ckL:tvC:", long_options,
+	while ((c = getopt_long(argc, argv, "?Vb:f:FWd:h:p:U:R:S:D:ck:L:tvC:", long_options,
 							&optindex)) != -1)
 	{
 		/*
@@ -388,6 +388,11 @@ main(int argc, char **argv)
 				runtime_options.without_barman = true;
 				break;

+			case OPT_RECOVERY_CONF_ONLY:
+				runtime_options.recovery_conf_only = true;
+				break;
+
+
 				/*---------------------------
 				 * "standby register" options
 				 *---------------------------
@@ -993,31 +998,10 @@ main(int argc, char **argv)
 	}


-
-	/* check for conflicts between runtime options and configuration file */
-	/* ================================================================== */
-
-	if (action == STANDBY_CLONE)
-	{
-		standy_clone_mode mode = get_standby_clone_mode();
-
-		if (mode == barman && runtime_options.without_barman == false
-			&& config_file_options.use_replication_slots == true)
-		{
-			log_error(_("STANDBY CLONE in Barman mode is incompatible with configuration option \"use_replication_slots\""));
-			log_hint(_("set \"use_replication_slots\" to \"no\" in repmgr.conf, or use --without-barman to clone directly from the upstream server"));
-			exit(ERR_BAD_CONFIG);
-		}
-	}
-
-
 	/*
 	 * Check for configuration file items which can be overriden by runtime
 	 * options
-	 */
-
-	/*
-	 * ============================================================================
+	 * =====================================================================
 	 */

 	/*
@@ -1495,6 +1479,39 @@ check_cli_parameters(const int action)
 		}
 	}

+	if (runtime_options.replication_user[0])
+	{
+		switch (action)
+		{
+			case PRIMARY_REGISTER:
+			case STANDBY_REGISTER:
+			case STANDBY_CLONE:
+				break;
+
+			case STANDBY_FOLLOW:
+				item_list_append_format(&cli_warnings,
+										_("--replication-user ignored when executing %s"),
+										action_name(action));
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--replication-user not required when executing %s"),
+										action_name(action));
+		}
+	}
+
+	if (runtime_options.recovery_conf_only == true)
+	{
+		switch (action)
+		{
+			case STANDBY_CLONE:
+				break;
+			default:
+				item_list_append_format(&cli_warnings,
+										_("--create-recovery-conf will be ignored when executing %s"),
+										action_name(action));
+		}
+	}
+
 	if (runtime_options.event[0])
 	{
 		switch (action)
@@ -1508,25 +1525,6 @@ check_cli_parameters(const int action)
 		}
 	}

-	if (runtime_options.replication_user[0])
-	{
-		switch (action)
-		{
-			case PRIMARY_REGISTER:
-			case STANDBY_REGISTER:
-				break;
-			case STANDBY_CLONE:
-			case STANDBY_FOLLOW:
-				item_list_append_format(&cli_warnings,
-										_("--replication-user ignored when executing %s)"),
-										action_name(action));
-			default:
-				item_list_append_format(&cli_warnings,
-										_("--replication-user not required when executing %s"),
-										action_name(action));
-		}
-	}
-
 	if (runtime_options.limit_provided)
 	{
 		switch (action)
@@ -1777,10 +1775,11 @@ do_help(void)

 	printf(_("Usage:\n"));
 	printf(_("    %s [OPTIONS] primary {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow}\n"), progname());
+	printf(_("    %s [OPTIONS] standby {register|unregister|clone|promote|follow|switchover}\n"), progname());
 	printf(_("    %s [OPTIONS] bdr     {register|unregister}\n"), progname());
-	printf(_("    %s [OPTIONS] node    status\n"), progname());
+	printf(_("    %s [OPTIONS] node    {status|check|rejoin|service}\n"), progname());
 	printf(_("    %s [OPTIONS] cluster {show|event|matrix|crosscheck}\n"), progname());
+	printf(_("    %s [OPTIONS] witness {register|unregister}\n"), progname());

 	puts("");

@@ -2151,10 +2150,19 @@ local_command(const char *command, PQExpBufferData *outputbuf)
 }


+/*
+ * get_superuser_connection()
+ *
+ * Check if provided connection "conn" is a superuser connection, if not attempt to
+ * make a superuser connection "superuser_conn" with the provided --superuser parameter.
+ *
+ * "privileged_conn" is set to whichever connection is the superuser connection.
+ */
 void
 get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privileged_conn)
 {
 	t_connection_user userinfo = T_CONNECTION_USER_INITIALIZER;
+	t_conninfo_param_list conninfo_params = T_CONNINFO_PARAM_LIST_INITIALIZER;
 	bool		is_superuser = false;

 	/* this should never happen */
@@ -2180,9 +2188,11 @@ get_superuser_connection(PGconn **conn, PGconn **superuser_conn, PGconn **privil
 		exit(ERR_BAD_CONFIG);
 	}

-	*superuser_conn = establish_db_connection_as_user(config_file_options.conninfo,
-													  runtime_options.superuser,
-													  false);
+	initialize_conninfo_params(&conninfo_params, false);
+	conn_to_param_list(*conn, &conninfo_params);
+	param_set(&conninfo_params, "user", runtime_options.superuser);
+
+	*superuser_conn = establish_db_connection_by_params(&conninfo_params, false);

 	if (PQstatus(*superuser_conn) != CONNECTION_OK)
 	{
@@ -2707,7 +2717,7 @@ init_node_record(t_node_info *node_record)

 	if (config_file_options.replication_user[0] != '\0')
 	{
-		/* replication user explicitly provided */
+		/* replication user explicitly provided in configuration file */
 		strncpy(node_record->repluser, config_file_options.replication_user, NAMEDATALEN);
 	}
 	else
--- a/repmgr-client.h
+++ b/repmgr-client.h
@@ -85,6 +85,7 @@
 #define OPT_WAIT_START                     1036
 #define OPT_REPL_CONN                      1037
 #define OPT_REMOTE_NODE_ID                 1038
+#define OPT_RECOVERY_CONF_ONLY             1039

 /* deprecated since 3.3 */
 #define OPT_DATA_DIR						999
@@ -139,6 +140,7 @@ static struct option long_options[] =
 	{"upstream-conninfo", required_argument, NULL, OPT_UPSTREAM_CONNINFO},
 	{"upstream-node-id", required_argument, NULL, OPT_UPSTREAM_NODE_ID},
 	{"without-barman", no_argument, NULL, OPT_WITHOUT_BARMAN},
+	{"recovery-conf-only", no_argument, NULL, OPT_RECOVERY_CONF_ONLY},

 /* "standby register" options */
 	{"wait-start", required_argument, NULL, OPT_WAIT_START},
--- a/repmgr.conf.sample
+++ b/repmgr.conf.sample
@@ -161,7 +161,7 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"


 #------------------------------------------------------------------------------
-# Standby clone settings
+# "standby clone" settings
 #------------------------------------------------------------------------------
 #
 # These settings apply when cloning a standby ("repmgr standby clone").
@@ -178,6 +178,20 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #restore_command=''			# This will be placed in the recovery.conf
 					# file generated by repmgr

+
+#------------------------------------------------------------------------------
+# "standby promote" settings
+#------------------------------------------------------------------------------
+
+# These settings apply when instructing a standby to promote itself to the
+# new primary ("repmgr standby promote").
+
+#promote_check_timeout=60		# The length of time (in seconds) to wait
+					# for the new primary to finish promoting
+#promote_check_interval=1		# The interval (in seconds) to check whether
+					# the new primary has finished promoting
+
+
 #------------------------------------------------------------------------------
 # Standby follow settings
 #------------------------------------------------------------------------------
@@ -235,6 +249,8 @@ ssh_options='-q -o ConnectTimeout=10'	# Options to append to "ssh"
 #primary_notification_timeout=60	# Interval (in seconds) which repmgrd on a standby
 					# will wait for a notification from the new primary,
 					# before falling back to degraded monitoring
+#standby_reconnect_timeout=60	# Interval (in seconds) which repmgrd on a standby will wait
+					# to reconnect to the local node after executing "follow_command"

 #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
--- a/repmgr.h
+++ b/repmgr.h
@@ -77,6 +77,9 @@
 #define DEFAULT_REPLICATION_LAG_CRITICAL     600 /* seconds */
 #define DEFAULT_WITNESS_SYNC_INTERVAL        15  /* seconds */
 #define DEFAULT_WAIT_START                   30  /* seconds */
+#define DEFAULT_PROMOTE_CHECK_TIMEOUT        60  /* seconds */
+#define DEFAULT_PROMOTE_CHECK_INTERVAL       1   /* seconds */
+#define DEFAULT_STANDBY_RECONNECT_TIMEOUT    60  /* seconds */

 #ifndef RECOVERY_COMMAND_FILE
 #define RECOVERY_COMMAND_FILE "recovery.conf"
--- a/repmgr_version.h.in
+++ b/repmgr_version.h.in
@@ -1,3 +1,3 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "4.0.3"
+#define REPMGR_VERSION "4.0.4"

--- a/repmgrd-bdr.c
+++ b/repmgrd-bdr.c
@@ -35,6 +35,29 @@ do_bdr_node_check(void)
 	/* nothing to do at the moment */
 }

+void
+handle_sigint_bdr(SIGNAL_ARGS)
+{
+	PQExpBufferData event_details;
+
+	initPQExpBuffer(&event_details);
+
+	appendPQExpBuffer(&event_details,
+					  "%s signal received",
+					  postgres_signal_arg == SIGTERM
+					  ? "TERM" : "INT");
+
+	create_event_notification(local_conn,
+							  &config_file_options,
+							  config_file_options.node_id,
+							  "repmgrd_shutdown",
+							  true,
+							  event_details.data);
+	termPQExpBuffer(&event_details);
+
+	terminate(SUCCESS);
+}
+

 void
 monitor_bdr(void)
@@ -98,23 +121,6 @@ monitor_bdr(void)
 		exit(ERR_BAD_CONFIG);
 	}

-	/* Retrieve record for this node from the local database */
-	record_status = get_node_record(local_conn, config_file_options.node_id, &local_node_info);
-
-	/*
-	 * Terminate if we can't find the local node record. This is a
-	 * "fix-the-config" situation, not a lot else we can do.
-	 */
-	if (record_status != RECORD_FOUND)
-	{
-		log_error(_("unable to retrieve record for local node (ID: %i), terminating"),
-				  local_node_info.node_id);
-		log_hint(_("check that \"repmgr bdr register\" was executed for this node"));
-		PQfinish(local_conn);
-		exit(ERR_BAD_CONFIG);
-	}
-
-
 	if (local_node_info.active == false)
 	{
 		log_error(_("local node (ID: %i) is marked as inactive in repmgr"),
@@ -152,15 +158,16 @@ monitor_bdr(void)
 		cell->node_info->node_status = NODE_STATUS_UP;
 	}

-	log_debug("main_loop_bdr() monitoring local node %i", config_file_options.node_id);
+	log_info(_("starting continuous BDR node monitoring on node %i"),
+			 config_file_options.node_id);

-	log_info(_("starting continuous BDR node monitoring"));
+	INSTR_TIME_SET_CURRENT(log_status_interval_start);

 	while (true)
 	{

 		/* monitoring loop */
-		log_verbose(LOG_DEBUG, "BDR check loop...");
+		log_verbose(LOG_DEBUG, "BDR check loop - checking %i nodes", nodes.node_count);

 		for (cell = nodes.head; cell; cell = cell->next)
 		{
@@ -262,7 +269,6 @@ loop:
 		if (config_file_options.log_status_interval > 0)
 		{
 			int			log_status_interval_elapsed = calculate_elapsed(log_status_interval_start);
-
 			if (log_status_interval_elapsed >= config_file_options.log_status_interval)
 			{
 				log_info(_("monitoring BDR replication status on node \"%s\" (ID: %i)"),
@@ -273,8 +279,7 @@ loop:
 				{
 					if (cell->node_info->monitoring_state == MS_DEGRADED)
 					{
-						log_detail(
-								   _("monitoring node \"%s\" (ID: %i) in degraded mode"),
+						log_detail(_("monitoring node \"%s\" (ID: %i) in degraded mode"),
 								   cell->node_info->node_name,
 								   cell->node_info->node_id);
 					}
--- a/repmgrd-bdr.h
+++ b/repmgrd-bdr.h
@@ -22,4 +22,5 @@
 extern void do_bdr_node_check(void);
 extern void monitor_bdr(void);

+extern void	handle_sigint_bdr(SIGNAL_ARGS);
 #endif							/* _REPMGRD_BDR_H_ */
--- a/repmgrd-physical.c
+++ b/repmgrd-physical.c
@@ -85,6 +85,36 @@ static void update_monitoring_history(void);
 static const char * format_failover_state(FailoverState failover_state);


+void
+handle_sigint_physical(SIGNAL_ARGS)
+{
+	PGconn *writeable_conn;
+	PQExpBufferData event_details;
+
+	initPQExpBuffer(&event_details);
+
+	appendPQExpBuffer(&event_details,
+					  "%s signal received",
+					  postgres_signal_arg == SIGTERM
+					  ? "TERM" : "INT");
+
+	if (local_node_info.type == PRIMARY)
+		writeable_conn = local_conn;
+	else
+		writeable_conn = primary_conn;
+
+	create_event_notification(writeable_conn,
+							  &config_file_options,
+							  config_file_options.node_id,
+							  "repmgrd_shutdown",
+							  true,
+							  event_details.data);
+
+	termPQExpBuffer(&event_details);
+
+	terminate(SUCCESS);
+}
+
 /* perform some sanity checks on the node's configuration */

 void
@@ -113,6 +143,14 @@ do_physical_node_check(void)
 				log_error(_("this node is marked as inactive and cannot be used as a failover target"));
 				log_hint(_("%s"), hint);
 				PQfinish(local_conn);
+
+				create_event_notification(NULL,
+										  &config_file_options,
+										  config_file_options.node_id,
+										  "repmgrd_shutdown",
+										  false,
+										  "node is inactive and cannot be used as a failover target");
+
 				terminate(ERR_BAD_CONFIG);

 			case FAILOVER_MANUAL:
@@ -280,6 +318,7 @@ monitor_streaming_primary(void)

 				monitoring_state = MS_DEGRADED;
 				INSTR_TIME_SET_CURRENT(degraded_monitoring_start);
+				log_notice(_("unable to connect to local node, falling back to degraded monitoring"));
 			}

 		}
@@ -303,7 +342,7 @@ monitor_streaming_primary(void)
 				create_event_notification(NULL,
 										  &config_file_options,
 										  config_file_options.node_id,
-										  "repmgrd_terminate",
+										  "repmgrd_shutdown",
 										  true,
 										  event_details.data);

@@ -325,22 +364,20 @@ monitor_streaming_primary(void)
 				else
 				{
 					local_node_info.node_status = NODE_STATUS_UP;
-					monitoring_state = MS_NORMAL;
-
-					initPQExpBuffer(&event_details);

 					/* check to see if the node has been restored as a standby */
 					if (get_recovery_type(local_conn) == RECTYPE_STANDBY)
 					{
 						PGconn *new_primary_conn;

+						initPQExpBuffer(&event_details);
+
 						appendPQExpBuffer(&event_details,
 										  _("reconnected to node after %i seconds, node is now a standby, switching to standby monitoring"),
 										  degraded_monitoring_elapsed);
 						log_notice("%s", event_details.data);
 						termPQExpBuffer(&event_details);

-
 						primary_node_id = UNKNOWN_NODE_ID;

 						new_primary_conn = get_primary_connection_quiet(local_conn, &primary_node_id, NULL);
@@ -353,54 +390,103 @@ monitor_streaming_primary(void)
 						else
 						{
 							RecordStatus record_status;
-							int i = 0;

 							log_debug("primary node id is now %i", primary_node_id);

-							/*
-							 * poll for a while until record type is returned as "STANDBY" - it's possible
-							 * that there's a gap between the server being restarted and the record
-							 * being updated
-							 */
-							for (i = 0; i < 30; i++)
-							{
-								/*
-								 * try and refresh the local node record from the primary, as the updated
-								 * local node record may not have been replicated yet
-								 */
-
-								record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info);
-
-								if (record_status == RECORD_FOUND)
-								{
-									log_debug("type = %s", get_node_type_string(local_node_info.type));
-
-									if (local_node_info.type == STANDBY)
-									{
-										PQfinish(new_primary_conn);
-
-										/* XXX add event notification */
-										return;
-									}
-								}
-								sleep(1);
-							}
-
-							PQfinish(new_primary_conn);
+							record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info);

 							if (record_status == RECORD_FOUND)
 							{
-								log_warning(_("repmgr node record is still %s"), get_node_type_string(local_node_info.type));
+								bool resume_monitoring = true;
+
+								log_debug("node %i is registered with type = %s",
+										  config_file_options.node_id,
+										  get_node_type_string(local_node_info.type));
+
+								/*
+								 * node has recovered but metadata not updated - we can do that ourselves,
+								 */
+								if (local_node_info.type == PRIMARY)
+								{
+									log_notice(_("node \"%s\" (ID: %i) still registered as primary, setting to standby"),
+											   config_file_options.node_name,
+											   config_file_options.node_id);
+
+									if (update_node_record_set_active_standby(new_primary_conn, config_file_options.node_id) == false)
+									{
+										resume_monitoring = false;
+									}
+									else
+									{
+										record_status = get_node_record(new_primary_conn, config_file_options.node_id, &local_node_info);
+
+										if (record_status != RECORD_FOUND)
+										{
+											resume_monitoring = false;
+										}
+									}
+								}
+
+								if (resume_monitoring == true)
+								{
+									monitoring_state = MS_NORMAL;
+									log_notice(_("former primary has been restored as standby after %i seconds, updating node record and resuming monitoring"),
+											   degraded_monitoring_elapsed);
+
+									initPQExpBuffer(&event_details);
+
+									appendPQExpBuffer(&event_details,
+													  _("node restored as standby after %i seconds, monitoring connection to upstream node %i"),
+													  degraded_monitoring_elapsed,
+													  local_node_info.upstream_node_id);
+
+									create_event_notification(new_primary_conn,
+															  &config_file_options,
+															  config_file_options.node_id,
+															  "repmgrd_standby_reconnect",
+															  true,
+															  event_details.data);
+
+
+									termPQExpBuffer(&event_details);
+
+									PQfinish(new_primary_conn);
+
+									/* restart monitoring as standby */
+									return;
+								}
 							}
-							else
+							else if (record_status == RECORD_NOT_FOUND)
 							{
-								log_error(_("no metadata record found for this node"));
+								PQExpBufferData event_details;
+								initPQExpBuffer(&event_details);
+
+								appendPQExpBuffer(&event_details,
+												  _("no metadata record found for this node on current primary %i"),
+												  primary_node_id);
+
+								log_error("%s", event_details.data);
 								log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
+
+								PQfinish(new_primary_conn);
+
+								create_event_notification(NULL,
+														  &config_file_options,
+														  config_file_options.node_id,
+														  "repmgrd_shutdown",
+														  false,
+														  event_details.data);
+								termPQExpBuffer(&event_details);
+
+								terminate(ERR_BAD_CONFIG);
 							}
 						}
 					}
 					else
 					{
+						monitoring_state = MS_NORMAL;
+
+						initPQExpBuffer(&event_details);
 						appendPQExpBuffer(&event_details,
 										  _("reconnected to primary node after %i seconds, resuming monitoring"),
 										  degraded_monitoring_elapsed);
@@ -441,7 +527,7 @@ loop:

 				if (monitoring_state == MS_DEGRADED)
 				{
-					log_detail(_("waiting for primary to reappear"));
+					log_detail(_("waiting for the node to become available"));
 				}

 				INSTR_TIME_SET_CURRENT(log_status_interval_start);
@@ -472,8 +558,6 @@ loop:
 			got_SIGHUP = false;
 		}

-
-
 		log_verbose(LOG_DEBUG, "sleeping %i seconds (parameter \"monitor_interval_secs\")",
 					config_file_options.monitor_interval_secs);

@@ -1009,6 +1093,9 @@ loop:
 			got_SIGHUP = false;
 		}

+		log_verbose(LOG_DEBUG, "sleeping %i seconds (parameter \"monitor_interval_secs\")",
+					config_file_options.monitor_interval_secs);
+
 		sleep(config_file_options.monitor_interval_secs);
 	}
 }
@@ -1029,9 +1116,26 @@ monitor_streaming_witness(void)

 	if (get_primary_node_record(local_conn, &upstream_node_info) == false)
 	{
-		log_error(_("unable to retrieve record for primary node"));
+		PQExpBufferData event_details;
+
+		initPQExpBuffer(&event_details);
+
+		appendPQExpBuffer(&event_details,
+						  _("unable to retrieve record for primary node"));
+
+		log_error("%s", event_details.data);
 		log_hint(_("execute \"repmgr witness register --force\" to update the witness node "));
 		PQfinish(local_conn);
+
+		create_event_notification(NULL,
+								  &config_file_options,
+								  config_file_options.node_id,
+								  "repmgrd_shutdown",
+								  false,
+								  event_details.data);
+
+		termPQExpBuffer(&event_details);
+
 		terminate(ERR_BAD_CONFIG);
 	}

@@ -1339,6 +1443,9 @@ loop:
 			got_SIGHUP = false;
 		}

+		log_verbose(LOG_DEBUG, "sleeping %i seconds (parameter \"monitor_interval_secs\")",
+					config_file_options.monitor_interval_secs);
+
 		sleep(config_file_options.monitor_interval_secs);
 	}

@@ -1376,7 +1483,7 @@ do_primary_failover(void)

 		failover_state = promote_self();
 	}
-	else if (election_result == ELECTION_LOST)
+	else if (election_result == ELECTION_LOST || election_result == ELECTION_NOT_CANDIDATE)
 	{
 		log_info(_("follower node awaiting notification from the candidate node"));
 		failover_state = FAILOVER_STATE_WAITING_NEW_PRIMARY;
@@ -1392,7 +1499,7 @@ do_primary_failover(void)

 		/* TODO: rerun election if new primary doesn't appear after timeout */

-		/* either follow or time out; either way resume monitoring */
+		/* either follow, self-promote or time out; either way resume monitoring */
 		if (wait_primary_notification(&new_primary_id) == true)
 		{
 			/* if primary has reappeared, no action needed */
@@ -1443,11 +1550,9 @@ do_primary_failover(void)
 											  &config_file_options,
 											  local_node_info.node_id,
 											  "standby_disconnect_manual",
-
-					/*
-					 * here "true" indicates the action has occurred as
-					 * expected
-					 */
+											  /*
+											   * here "true" indicates the action has occurred as expected
+											   */
 											  true,
 											  event_details.data);
 					PQfinish(new_primary_conn);
@@ -1666,7 +1771,7 @@ do_upstream_standby_failover(void)
 	t_node_info primary_node_info = T_NODE_INFO_INITIALIZER;
 	RecordStatus record_status = RECORD_NOT_FOUND;
 	RecoveryType primary_type = RECTYPE_UNKNOWN;
-	int			r;
+	int			i, r;
 	char		parsed_follow_command[MAXPGPATH] = "";

 	PQfinish(upstream_conn);
@@ -1751,8 +1856,30 @@ do_upstream_standby_failover(void)
 		termPQExpBuffer(&event_details);
 	}

-	/* reconnect to local node */
-	local_conn = establish_db_connection(config_file_options.conninfo, false);
+	/*
+	 * It's possible that the standby is still starting up after the "follow_command"
+	 * completes, so poll for a while until we get a connection.
+	 */
+
+	for (i = 0; i < config_file_options.standby_reconnect_timeout; i++)
+	{
+		local_conn = establish_db_connection(local_node_info.conninfo, false);
+
+		if (PQstatus(local_conn) == CONNECTION_OK)
+			break;
+
+		log_debug("sleeping 1 second; %i of %i attempts to reconnect to local node",
+				  i + 1,
+				  config_file_options.standby_reconnect_timeout);
+		sleep(1);
+	}
+
+	if (PQstatus(local_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to reconnect to local node %i"),
+				  local_node_info.node_id);
+		return FAILOVER_STATE_FOLLOW_FAIL;
+	}

 	/* refresh shared memory settings which will have been zapped by the restart */
 	repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
@@ -2032,7 +2159,7 @@ follow_new_primary(int new_primary_id)
 	char		parsed_follow_command[MAXPGPATH] = "";

 	PQExpBufferData event_details;
-	int			r;
+	int			i, r;

 	/* Store details of the failed node here */
 	t_node_info failed_primary = T_NODE_INFO_INITIALIZER;
@@ -2144,8 +2271,6 @@ follow_new_primary(int new_primary_id)
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}

-
-
 	/*
 	 * refresh local copy of local and primary node records - we get these
 	 * directly from the primary to ensure they're the current version
@@ -2168,7 +2293,30 @@ follow_new_primary(int new_primary_id)
 		return FAILOVER_STATE_FOLLOW_FAIL;
 	}

-	local_conn = establish_db_connection(local_node_info.conninfo, false);
+	/*
+	 * It's possible that the standby is still starting up after the "follow_command"
+	 * completes, so poll for a while until we get a connection.
+	 */
+
+	for (i = 0; i < config_file_options.standby_reconnect_timeout; i++)
+	{
+		local_conn = establish_db_connection(local_node_info.conninfo, false);
+
+		if (PQstatus(local_conn) == CONNECTION_OK)
+			break;
+
+		log_debug("sleeping 1 second; %i of %i attempts to reconnect to local node",
+				  i + 1,
+				  config_file_options.standby_reconnect_timeout);
+		sleep(1);
+	}
+
+	if (PQstatus(local_conn) != CONNECTION_OK)
+	{
+		log_error(_("unable to reconnect to local node %i"),
+				  local_node_info.node_id);
+		return FAILOVER_STATE_FOLLOW_FAIL;
+	}

 	/* refresh shared memory settings which will have been zapped by the restart */
 	repmgrd_set_local_node_id(local_conn, config_file_options.node_id);
@@ -2181,8 +2329,7 @@ follow_new_primary(int new_primary_id)

 	log_notice("%s", event_details.data);

-	create_event_notification(
-							  upstream_conn,
+	create_event_notification(upstream_conn,
 							  &config_file_options,
 							  local_node_info.node_id,
 							  "repmgrd_failover_follow",
@@ -2356,18 +2503,20 @@ do_election(void)

 	if (config_file_options.failover == FAILOVER_MANUAL)
 	{
-		log_notice(_("this node is not configured for automatic failover so will not be considered as promotion candidate"));
+		log_notice(_("this node is not configured for automatic failover so will not be considered as promotion candidate, and will not follow the new primary"));
+		log_detail(_("\"failover\" is set to \"manual\" in repmgr.conf"));
+		log_hint(_("manually execute \"repmgr standby follow\" to have this node follow the new primary"));

-		return ELECTION_LOST;
+		return ELECTION_NOT_CANDIDATE;
 	}

-	/* node priority is set to zero - don't ever become a candidate */
+	/* node priority is set to zero - don't become a candidate, and lose by default */
 	if (local_node_info.priority <= 0)
 	{
 		log_notice(_("this node's priority is %i so will not be considered as an automatic promotion candidate"),
 				   local_node_info.priority);

-		return ELECTION_NOT_CANDIDATE;
+		return ELECTION_LOST;
 	}

 	/* get all active nodes attached to upstream, excluding self */
--- a/repmgrd-physical.h
+++ b/repmgrd-physical.h
@@ -26,4 +26,6 @@ void		monitor_streaming_standby(void);
 void		monitor_streaming_witness(void);
 void		close_connections_physical(void);

+void		handle_sigint_physical(SIGNAL_ARGS);
+
 #endif							/* _REPMGRD_PHYSICAL_H_ */
--- a/repmgrd.c
+++ b/repmgrd.c
@@ -73,7 +73,6 @@ static void start_monitoring(void);
 #ifndef WIN32
 static void setup_event_handlers(void);
 static void handle_sighup(SIGNAL_ARGS);
-static void handle_sigint(SIGNAL_ARGS);
 #endif

 int			calculate_elapsed(instr_time start_time);
@@ -255,6 +254,8 @@ main(int argc, char **argv)
 		strncpy(config_file_options.log_level, cli_log_level, MAXLEN);
 	}

+	log_notice(_("repmgrd (repmgr %s) starting up"), REPMGR_VERSION);
+
 	/*
 	 * -m/--monitoring-history, if provided, will override repmgr.conf's
 	 * monitoring_history; this is for backwards compatibility as it's
@@ -353,10 +354,24 @@ main(int argc, char **argv)
 	/* Retrieve record for this node from the local database */
 	record_status = get_node_record(local_conn, config_file_options.node_id, &local_node_info);

+	/*
+	 * Terminate if we can't find the local node record. This is a
+	 * "fix-the-config" situation, not a lot else we can do.
+	 */
+
 	if (record_status != RECORD_FOUND)
 	{
 		log_error(_("no metadata record found for this node - terminating"));
-		log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
+
+		switch (config_file_options.replication_type)
+		{
+			case REPLICATION_TYPE_PHYSICAL:
+				log_hint(_("check that 'repmgr (primary|standby) register' was executed for this node"));
+				break;
+			case REPLICATION_TYPE_BDR:
+				log_hint(_("check that 'repmgr bdr register' was executed for this node"));
+				break;
+		}

 		PQfinish(local_conn);
 		terminate(ERR_BAD_CONFIG);
@@ -440,6 +455,7 @@ start_monitoring(void)
 				break;
 			case WITNESS:
 				monitor_streaming_witness();
+				break;
 			case BDR:
 				monitor_bdr();
 				return;
@@ -612,11 +628,6 @@ check_and_create_pid_file(const char *pid_file)


 #ifndef WIN32
-static void
-handle_sigint(SIGNAL_ARGS)
-{
-	terminate(SUCCESS);
-}

 /* SIGHUP: set flag to re-read config file at next convenient time */
 static void
@@ -629,8 +640,23 @@ static void
 setup_event_handlers(void)
 {
 	pqsignal(SIGHUP, handle_sighup);
-	pqsignal(SIGINT, handle_sigint);
-	pqsignal(SIGTERM, handle_sigint);
+
+	/*
+	 * we want to be able to write a "repmgrd_shutdown" event, so delegate
+	 * signal handling to the respective replication type handler, as it
+	 * will know best which database connection to use
+	 */
+	switch (config_file_options.replication_type)
+	{
+		case REPLICATION_TYPE_BDR:
+			pqsignal(SIGINT, handle_sigint_bdr);
+			pqsignal(SIGTERM, handle_sigint_bdr);
+			break;
+		case REPLICATION_TYPE_PHYSICAL:
+			pqsignal(SIGINT, handle_sigint_physical);
+			pqsignal(SIGTERM, handle_sigint_physical);
+			break;
+	}
 }
 #endif
Author	SHA1	Message	Date
Ian Barwick	b17993abdb	doc: update "repmgr primary unregister" description As noted by GitHub user yonj1e in GitHub #396.	2018-03-08 15:01:25 +09:00
Ian Barwick	8f68344f9a	doc: update FAQ Additional clarification for "repmgr standby clone --recovery-conf-only"	2018-03-08 10:04:30 +09:00
Ian Barwick	125ac6c297	doc: update FAQ Add entry about upgrading PostgreSQL	2018-03-08 10:04:30 +09:00
Ian Barwick	955860923f	Fix parsing of -k/--keep-history option GitHub #394.	2018-03-07 19:14:18 +09:00
Ian Barwick	50626f90cc	Add 4.0.4 release notes	2018-03-07 14:17:04 +09:00
Ian Barwick	9aea5b8aa7	repmgrd: fix failover handling in "manual" mode Regression was introduced in commit `c7a585c555`	2018-03-06 22:35:51 +09:00
Ian Barwick	ed1bcb159e	repmgrd: remove duplicate local record check in BDR mode	2018-03-06 12:31:07 +09:00
Ian Barwick	9c72c0d66e	Add event "repmgrd_shutdown" Implements GitHub #393	2018-03-06 10:59:54 +09:00
Emre Hasegeli	0ddc226c2a	Add witness options to the main help GitHub #392	2018-03-06 10:57:33 +09:00
Ian Barwick	93830cad61	Fix directory creation when cloning from Barman	2018-03-05 19:31:53 +09:00
Ian Barwick	bca1660d5e	Improve repmgrd logging in BDR mode Also ensure interval status log line is shown as intended	2018-03-05 15:05:40 +09:00
Ian Barwick	5a52917421	repmgrd: add debug log output for "monitor_interval_secs" sleep in all modes	2018-03-05 14:23:58 +09:00
Emre Hasegeli	70752d7d4a	Add missing options to the main help	2018-03-05 09:52:04 +09:00
Ian Barwick	c29d1efc37	"standby clone": improve replication user selection Use the upstream node's replication user when checking the replication connection.	2018-03-02 16:21:32 +09:00
Ian Barwick	6fbbe2a97a	"standby clone": fix --superuser handling get_superuser_connection() was erroneously using the local node record to connect to as a superuser, which works when registering the primary but obviously not when cloning a standby. Addresses GitHub #380.	2018-03-02 14:49:17 +09:00
Ian Barwick	ce42d6827e	Update HISTORY	2018-03-01 15:51:09 +09:00
Ian Barwick	98384559a6	"standby clone": remove restriction on replication slots in Barman mode While it's preferable to avoid standby replication slots if Barman is in use, there's no technical reason to prevent this. Implements GitHub #379.	2018-03-01 15:47:28 +09:00
Ian Barwick	4a1477343b	repmgr: escape "restore_command" in generated recovery.conf	2018-03-01 10:39:04 +09:00
Ian Barwick	d2b9d20393	"standy clone": fix primary_conninfo when --upstream-conninfo provided	2018-03-01 09:18:40 +09:00
Ian Barwick	fe594c95ad	repmgrd: retry standby connection after cascading standby failover	2018-02-28 21:15:11 +09:00
Ian Barwick	60e63feaca	repmgrd: add configuration file parameter "standby_reconnect_timeout" This is used for determining a timeout when reconnecting to the standby after executing the "follow_command". This will normally not need to be set explicitly, but maybe useful in cases where the standby's startup phase can last longer than usual.	2018-02-28 18:56:33 +09:00
Ian Barwick	ae4d0f2622	repmgrd: fix main monitoring loop for witness server Missing "break" was breaking it when following a new primary.	2018-02-28 16:30:14 +09:00
Ian Barwick	5e8b41e221	repmgrd: retry standby connection after "follow_command" executed It's possible that the standby is still starting up after the "follow_command" completes, so poll for a while until we get a connection.	2018-02-28 15:35:47 +09:00
Ian Barwick	c7a585c555	repmgrd: improve log output - emit explicit startup NOTICE - emit NOTICE when falling back to degraded monitoring on a primary node - improve log message and event notification details when monitoring a former primary which has been reconnected as a standby	2018-02-28 12:35:13 +09:00
Ian Barwick	a27dd8c49c	doc: document "primary_follow_timeout" configuration file parameter.	2018-02-27 10:09:40 +09:00
Ian Barwick	9365bf3474	"standby promote": make timeout values configurable This introduces following new configuration file parameters, which were previously hard-coded values: - promote_check_timeout - promote_check_interval Implements GitHub #387.	2018-02-27 10:04:58 +09:00
Ian Barwick	e8ae0831fe	doc: add <options> section for various commands	2018-02-26 16:54:54 +09:00
Ian Barwick	518866eba5	"node status": improve replication slot warnings Addresses GitHub #385	2018-02-23 11:06:47 +09:00
Ian Barwick	ed0330c334	"standby clone": document --recovery-conf-only option	2018-02-23 10:54:42 +09:00
Ian Barwick	1f021dc9fa	"standby clone --recovery-conf-only": display generated file with --dry-run Refactor the original code which generates "recovery.conf" to place the output into a buffer, which can either be output as "recovery.conf" or copied to a buffer specified by the caller.	2018-02-23 10:16:47 +09:00
Ian Barwick	425839d764	Fix typo in function name	2018-02-22 15:48:41 +09:00
Ian Barwick	3a764f678a	"standby clone": add --recovery-conf-only option This will generate "recovery.conf" for an existing standby. Typical use-case is a standby cloned manually from an external data source (e.g. Barman), where "recovery.conf" needs to be created (and if required a replication slot). The --dry-run option will check the pre-requisites but not actually create "recovery.conf" or a replication slot. This requires that the upstream node is running, a replication connection can be made and if required a replication slot can be created. Implements GitHub #382.	2018-02-22 15:47:19 +09:00
Ian Barwick	829cf5cca4	repmgrd: improve detection of status change from primary to standby If repmgrd is running in degraded mode on a primary which has been stopped, then manually been brought back online as a standby (e.g. by creating recovery.conf and starting the server), ensure it not only detects the change but automatically updates the node record so it can resume monitoring the node as a standby. Previously, repmgrd was looping waiting for the record to be updated (as is done transparently when executing "repmgr node rejoin") but if the record was not updated within the timeout period (e.g. by "repmgr standby register) it would fail to resume monitoring as a standby. It seems reasonable to have repmgrd automatically update the node record, as this will restore failover capability as quickly as possible. If this is not desired, then the onus is on the user to shut down repmgrd while making the desired changes.	2018-02-22 11:35:47 +09:00
Ian Barwick	14420d83fa	"node rejoin": ensure --dry-run is honoured Addresses GitHub #383.	2018-02-20 15:28:39 +09:00
Ian Barwick	a80e22f0ed	Bump version 4.0.4	2018-02-16 12:19:31 +09:00
Ian Barwick	832993bfbc	doc: update 4.0.3 release notes	2018-02-16 12:15:10 +09:00
Ian Barwick	f1ea5e62df	doc: update release notes	2018-02-15 14:42:29 +09:00
Ian Barwick	b47448d0e5	Replace remaining instances of strcpy() with strncpy() Also use strncmp() to match.	2018-02-15 13:17:06 +09:00