Add dummy include file

This is a workaround required to facilitate Debian package builds
against PostgreSQL Extended.

HISTORY

@@ -1,11 +1,9 @@
-5.3.0   2021-??-??
+5.3.0   2021-10-12
         standby switchover: improve handling of node rejoin failure (Ian)
         repmgrd: prefix all shared library functions with "repmgr_" to
           minimize the risk of clashes with other shared libraries (Ian)
         repmgrd: at startup, if node record is marked as "inactive", attempt
           to set it to "active" (Ian)
-
-5.2.2.  2021-??-??
         standby clone: set "slot_name" in node record if required (Ian)
         node rejoin: emit rejoin target note information as NOTICE (Ian)
         repmgrd: ensure short option "-s" is accepted (Ian)

Makefile.in

@@ -13,6 +13,7 @@ DATA = \
   repmgr--unpackaged--4.0.sql \
   repmgr--unpackaged--5.1.sql \
   repmgr--unpackaged--5.2.sql \
+  repmgr--unpackaged--5.3.sql \
   repmgr--4.0.sql \
   repmgr--4.0--4.1.sql \
   repmgr--4.1.sql \

bdr_api_version.h

@@ -0,0 +1,7 @@
+/*
+ * bdr_version_api.h
+ *
+ * This is a dummy file to facilitated building Debian packages against
+ * PostgreSQL Extended. It may be removed in the future. Do not add any
+ * code to this file.
+ */

dbutils.c

@@ -4242,7 +4242,7 @@ _create_event(PGconn *conn, t_configuration_options *options, int node_id, char
 						}
 						break;
 					case 'p':
-						/* %p: primary id ("standby_switchover": former primary id) */
+						/* %p: primary id ("standby_switchover"/"repmgrd_failover_promote": former primary id) */
 						src_ptr++;
 						if (event_info->node_id != UNKNOWN_NODE_ID)
 						{
@@ -6008,6 +6008,43 @@ is_wal_replay_paused(PGconn *conn, bool check_pending_wal)
 	return is_paused;
 }
 
+/* repmgrd status functions */
+
+CheckStatus
+get_repmgrd_status(PGconn *conn)
+{
+	PQExpBufferData query;
+	PGresult   *res = NULL;
+	CheckStatus	repmgrd_status = CHECK_STATUS_CRITICAL;
+
+	initPQExpBuffer(&query);
+
+	appendPQExpBufferStr(&query,
+						 " SELECT "
+						 " CASE "
+						 "   WHEN repmgr.repmgrd_is_running() "
+						 "   THEN "
+						 "     CASE "
+						 "       WHEN repmgr.repmgrd_is_paused() THEN 1 ELSE 0 "
+						 "     END "
+						 "   ELSE 2 "
+						 " END AS repmgrd_status");
+	res = PQexec(conn, query.data);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_db_error(conn, query.data, _("unable to execute repmgrd status query"));
+	}
+	else
+	{
+		repmgrd_status = atoi(PQgetvalue(res, 0, 0));
+	}
+
+	termPQExpBuffer(&query);
+	PQclear(res);
+	return repmgrd_status;
+}
+
 
 /* miscellaneous debugging functions */
 

dbutils.h

@@ -602,6 +602,9 @@ int			get_upstream_last_seen(PGconn *conn, t_server_type node_type);
 
 bool		is_wal_replay_paused(PGconn *conn, bool check_pending_wal);
 
+/* repmgrd status functions */
+CheckStatus	get_repmgrd_status(PGconn *conn);
+
 /* miscellaneous debugging functions */
 const char *print_node_status(NodeStatus node_status);
 const char *print_pqping_status(PGPing ping_status);

doc/appendix-release-notes.xml

@@ -18,13 +18,13 @@
 <!-- remember to update the release date in ../repmgr_version.h.in -->
   <sect1 id="release-5.3.0">
     <title id="release-current">Release 5.3.0</title>
-    <para><emphasis>??? ? ???, 2021</emphasis></para>
+    <para><emphasis>Tue 12 October, 2021</emphasis></para>
     <para>
       &repmgr; 5.3.0 is a major release.
     </para>
     <para>
       This release provides support for <ulink url="https://www.postgresql.org/docs/14/release-14.html">PostgreSQL 14</ulink>,
-      to be released later in 2021.
+      released in September 2021.
     </para>
     <sect2>
       <title>Improvements</title>
@@ -44,6 +44,11 @@
               This makes it easier to identify unexpected events during a switchover operation, such as
               the demotion candidate being unexpectedly restarted by an external process.
             </para>
+            <para>
+              Note that the output of the <link linkend="repmgr-node-rejoin"><command>repmgr node rejoin</command></link>
+              operation on the demotion candidate will now be logged to a temporary file on that node;
+              the location of the file will be reported in the error message, if one is emitted.
+            </para>
           </listitem>
           <listitem>
             <para>
@@ -55,38 +60,39 @@
               <varname>repmgrd_exit_on_inactive_node</varname> to <literal>true</literal>.
             </para>
           </listitem>
-        </itemizedlist>
-      </para>
-    </sect2>
-
-    <sect2>
-      <title>Bug fixes</title>
-      <para>
-        <itemizedlist>
            <listitem>
              <para>
-              &repmgrd;: rename internal shared library functions to minimize the
-              risk of clashes with other shared libraries.
+               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
+               emit rejoin target note information as <literal>NOTICE</literal>.
              </para>
              <para>
-              This does not affect user-facing SQL functions.
+               This makes it clearer what &repmgr; is trying to do.
              </para>
            </listitem>
+
+          <listitem>
+            <para>
+              <link linkend="repmgr-node-check">repmgr node check</link>:
+              option <option>--repmgrd</option> added to check &repmgrd;
+              status.
+            </para>
+          </listitem>
+
+          <listitem>
+            <para>
+              Add <literal>%p</literal> <link linkend="event-notifications">event notification parameter</link>
+              providing the node ID of the former primary for the <literal>repmgrd_failover_promote</literal> event.
+            </para>
+          </listitem>
+
         </itemizedlist>
+
       </para>
     </sect2>
-  </sect1>
 
-  <sect1 id="release-5.2.2">
-    <title>Release 5.2.2</title>
-    <para><emphasis>??? ? ???, 2021</emphasis></para>
-    <para>
-      &repmgr; 5.2.2 is a minor release.
-    </para>
     <sect2>
       <title>Bug fixes</title>
       <para>
-
         <itemizedlist>
            <listitem>
             <para>
@@ -99,23 +105,24 @@
             </para>
            </listitem>
 
+
            <listitem>
             <para>
-               <command><link linkend="repmgr-node-rejoin">repmgr node rejoin</link></command>:
-               emit rejoin target note information as <literal>NOTICE</literal>.
+              &repmgrd;: rename internal shared library functions to minimize the
+              risk of clashes with other shared libraries.
             </para>
             <para>
-               This makes it clearer what &repmgr; is trying to do.
+              This does not affect user-facing SQL functions. However an upgrade
+              of the installed extension version is required.
             </para>
           </listitem>
+
           <listitem>
             <para>
               &repmgrd;: ensure short option <option>-s</option> is accepted.
             </para>
           </listitem>
-
         </itemizedlist>
-
       </para>
     </sect2>
   </sect1>

doc/event-notifications.xml

@@ -95,7 +95,8 @@
  </para>
 
  <para>
-   The following parameters are provided for a subset of event notifications:
+   The following parameters are provided for a subset of event notifications; their meaning may
+   change according to context:
  </para>
 
  <variablelist>
@@ -108,6 +109,9 @@
     <para>
      node ID of the demoted primary (<xref linkend="repmgr-standby-switchover"/> only)
     </para>
+    <para>
+     node ID of the former primary (<literal>repmgrd_failover_promote</literal> only)
+    </para>
    </listitem>
   </varlistentry>
   <varlistentry>
@@ -133,7 +137,7 @@
 
  <para>
   The values provided for <literal>%c</literal> and <literal>%a</literal>
-  will probably contain spaces, so should always be quoted.
+  may contain spaces, so should always be quoted.
  </para>
 
  <para>

doc/install-requirements.xml

@@ -112,10 +112,9 @@
         </thead>
 
         <tbody>
-
           <row>
             <entry>
-              &repmgr; 5.2
+              &repmgr; 5.3
             </entry>
             <entry>
               YES
@@ -123,6 +122,21 @@
             <entry>
               <link linkend="release-current">&repmgrversion;</link> (&releasedate;)
             </entry>
+            <entry>
+              9.4, 9.5, 9.6, 10, 11, 12, 13, 14
+            </entry>
+          </row>
+
+          <row>
+            <entry>
+              &repmgr; 5.2
+            </entry>
+            <entry>
+              NO
+            </entry>
+            <entry>
+              <link linkend="release-5.2.0">5.2.0</link> (2020-10-22)
+            </entry>
             <entry>
               9.4, 9.5, 9.6, 10, 11, 12, 13
             </entry>

doc/repmgr-node-check.xml

@@ -125,12 +125,29 @@
         is correctly configured.
       </simpara>
      </listitem>
-
-
     </itemizedlist>
   </para>
   </refsect1>
 
+
+  <refsect1>
+    <title>repmgrd</title>
+    <para>
+      A separate check is available to verify whether &repmgrd; is running,
+      This is not included in the general output, as this does not
+      per-se constitute a check of the node's replication status.
+    </para>
+    <itemizedlist spacing="compact" mark="bullet">
+     <listitem>
+      <simpara>
+        <option>--repmgrd</option>: checks whether &repmgrd; is running.
+        If &repmgrd; is running but paused, status <literal>1</literal>
+        (<literal>WARNING</literal>) is returned.
+      </simpara>
+     </listitem>
+    </itemizedlist>
+  </refsect1>
+
   <refsect1>
     <title>Additional checks</title>
     <para>

doc/repmgrd-configuration.xml

@@ -1079,6 +1079,29 @@ REPMGRD_OPTS="--daemonize=false"
       </para>
 
     </sect2>
+
+    <sect2 id="repmgrd-daemon-monitoring">
+      <title>repmgrd daemon monitoring</title>
+      <indexterm>
+        <primary>repmgrd</primary>
+        <secondary>monitoring</secondary>
+      </indexterm>
+      <indexterm>
+        <primary>monitoring</primary>
+        <secondary>repmgrd</secondary>
+      </indexterm>
+
+      <para>
+        The command <command><link linkend="repmgr-service-status">repmgr service status</link></command>
+        provides an overview of the &repmgrd; daemon status (including pause status)
+        on all nodes in the cluster.
+      </para>
+      <para>
+        From &repmgr; 5.3, <command><link linkend="repmgr-node-check">repmgr node check --repmgrd</link></command>
+        can be used to check the status of &repmgrd; (including pause status)
+        on the local node.
+      </para>
+    </sect2>
   </sect1>
 
   <sect1 id="repmgrd-connection-settings">

repmgr--unpackaged--5.3.sql

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

repmgr-action-node.c

@@ -35,6 +35,7 @@
 static bool copy_file(const char *src_file, const char *dest_file);
 static void format_archive_dir(PQExpBufferData *archive_dir);
 static t_server_action parse_server_action(const char *action);
+static const char *output_repmgrd_status(CheckStatus status);
 
 static void exit_optformat_error(const char *error, int errcode);
 
@@ -52,9 +53,11 @@ static CheckStatus do_node_check_role(PGconn *conn, OutputMode mode, t_node_info
 static CheckStatus do_node_check_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
+static CheckStatus do_node_check_repmgrd(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_replication_config_owner(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output);
 static CheckStatus do_node_check_db_connection(PGconn *conn, OutputMode mode);
 
+
 /*
  * NODE STATUS
  *
@@ -941,6 +944,16 @@ do_node_check(void)
 		exit(return_code);
 	}
 
+	if (runtime_options.repmgrd == true)
+	{
+		return_code = do_node_check_repmgrd(conn,
+											runtime_options.output_mode,
+											&node_info,
+											NULL);
+		PQfinish(conn);
+		exit(return_code);
+	}
+
 	if (runtime_options.replication_config_owner == true)
 	{
 		return_code = do_node_check_replication_config_owner(conn,
@@ -2024,7 +2037,6 @@ do_node_check_missing_slots(PGconn *conn, OutputMode mode, t_node_info *node_inf
 	return status;
 }
 
-
 CheckStatus
 do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
 {
@@ -2159,6 +2171,53 @@ do_node_check_data_directory(PGconn *conn, OutputMode mode, t_node_info *node_in
 	return status;
 }
 
+CheckStatus
+do_node_check_repmgrd(PGconn *conn, OutputMode mode, t_node_info *node_info, CheckStatusList *list_output)
+{
+	CheckStatus status = CHECK_STATUS_OK;
+
+	if (mode == OM_CSV && list_output == NULL)
+	{
+		log_error(_("--csv output not provided with --repmgrd option"));
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	status = get_repmgrd_status(conn);
+	switch (mode)
+	{
+		case OM_OPTFORMAT:
+			printf("--repmgrd=%s\n",
+				   output_check_status(status));
+			break;
+		case OM_NAGIOS:
+			printf("REPMGRD %s: %s\n",
+				   output_check_status(status),
+				   output_repmgrd_status(status));
+
+			break;
+		case OM_CSV:
+		case OM_TEXT:
+			if (list_output != NULL)
+			{
+				check_status_list_set(list_output,
+									  "repmgrd",
+									  status,
+									  output_repmgrd_status(status));
+			}
+			else
+			{
+				printf("%s (%s)\n",
+					   output_check_status(status),
+					   output_repmgrd_status(status));
+			}
+		default:
+			break;
+	}
+
+	return status;
+}
+
 /*
  * This is not included in the general list output
  */
@@ -3570,6 +3629,25 @@ copy_file(const char *src_file, const char *dest_file)
 }
 
 
+static const char *
+output_repmgrd_status(CheckStatus status)
+{
+	switch (status)
+	{
+		case CHECK_STATUS_OK:
+			return "repmgrd running";
+		case CHECK_STATUS_WARNING:
+			return "repmgrd running but paused";
+		case CHECK_STATUS_CRITICAL:
+			return "repmgrd not running";
+		case CHECK_STATUS_UNKNOWN:
+			return "repmgrd status unknown";
+	}
+
+	return "UNKNOWN";
+}
+
+
 void
 do_node_help(void)
 {
@@ -3612,6 +3690,7 @@ do_node_help(void)
 	printf(_("    --role                    check node has expected role\n"));
 	printf(_("    --slots                   check for inactive replication slots\n"));
 	printf(_("    --missing-slots           check for missing replication slots\n"));
+	printf(_("    --repmgrd                 check if repmgrd is running\n"));
 	printf(_("    --data-directory-config   check repmgr's data directory configuration\n"));
 
 	puts("");

repmgr-client-global.h

@@ -120,6 +120,7 @@ typedef struct
 	bool		missing_slots;
 	bool		has_passfile;
 	bool		replication_connection;
+	bool		repmgrd;
 	bool		data_directory_config;
 	bool		replication_config_owner;
 	bool		db_connection;
@@ -175,7 +176,7 @@ typedef struct
 		/* "node status" options */ \
 		false, \
 		/* "node check" options */ \
-		false, false, false, false, false, false, false, false,	false, false, false, false, \
+		false, false, false, false, false, false, false, false,	false, false, false, false, false, \
 		/* "node rejoin" options */ \
 		"", \
 		/* "node service" options */ \

repmgr-client.c

@@ -549,6 +549,10 @@ main(int argc, char **argv)
 				runtime_options.data_directory_config = true;
 				break;
 
+			case OPT_REPMGRD:
+				runtime_options.repmgrd = true;
+				break;
+
 			case OPT_REPLICATION_CONFIG_OWNER:
 				runtime_options.replication_config_owner = true;
 				break;

repmgr-client.h

@@ -100,6 +100,7 @@
 #define OPT_DB_CONNECTION				   1047
 #define OPT_VERIFY_BACKUP				   1048
 #define OPT_RECOVERY_MIN_APPLY_DELAY       1049
+#define OPT_REPMGRD						   1050
 
 /* These options are for internal use only */
 #define OPT_CONFIG_ARCHIVE_DIR			   2001
@@ -193,6 +194,7 @@ static struct option long_options[] =
 	{"role", no_argument, NULL, OPT_ROLE},
 	{"slots", no_argument, NULL, OPT_SLOTS},
 	{"missing-slots", no_argument, NULL, OPT_MISSING_SLOTS},
+	{"repmgrd", no_argument, NULL, OPT_REPMGRD},
 	{"has-passfile", no_argument, NULL, OPT_HAS_PASSFILE},
 	{"replication-connection", no_argument, NULL, OPT_REPL_CONN},
 	{"data-directory-config", no_argument, NULL, OPT_DATA_DIRECTORY_CONFIG},

repmgr_version.h.in

@@ -1,7 +1,7 @@
 #define REPMGR_VERSION_DATE ""
-#define REPMGR_VERSION "5.3dev"
+#define REPMGR_VERSION "5.3.0"
 #define REPMGR_VERSION_NUM 50300
 #define REPMGR_EXTENSION_VERSION "5.3"
 #define REPMGR_EXTENSION_NUM 50300
-#define REPMGR_RELEASE_DATE "2021-XX-XX"
+#define REPMGR_RELEASE_DATE "2021-10-12"
 #define PG_ACTUAL_VERSION_NUM 

repmgrd-physical.c

@@ -172,37 +172,85 @@ void
 do_physical_node_check(PGconn *conn)
 {
 	/*
-	 * Check if node record is active - if not, and `failover=automatic`, the
-	 * node won't be considered as a promotion candidate; this often happens
-	 * when a failed primary is recloned and the node was not re-registered,
-	 * giving the impression failover capability is there when it's not. In
-	 * this case abort with an error and a hint about registering.
+	 * If node record is "inactive"; if not, attempt to set it to "active".
 	 *
-	 * If `failover=manual`, repmgrd can continue to passively monitor the
-	 * node, but we should nevertheless issue a warning and the same hint.
+	 * Usually it will have become inactive due to e.g. a standby being shut down
+	 * while repmgrd was running in an unpaused state. In this case it's
+	 * perfectly reasonable to automatically mark the node as "active".
 	 */
 
 	if (local_node_info.active == false)
 	{
 		char	   *hint = "Check that \"repmgr (primary|standby) register\" was executed for this node";
+		RecoveryType recovery_type = get_recovery_type(conn);
+
+		/*
+		 * If the local node's recovery status is incompatible with its registered
+		 * status, e.g. registered as primary but running as a standby, refuse to start.
+		 *
+		 * This typically happens when a failed primary is recloned but the node was not
+		 * re-registered, leaving the cluster in a potentially ambiguous state. In
+		 * this case it would not be possible or desirable to attempt to set the
+		 * node to active; the user should ensure the cluster is in the correct state.
+		 */
+		if (recovery_type != RECTYPE_UNKNOWN && local_node_info.type != UNKNOWN)
+		{
+			bool	require_reregister = false;
+			PQExpBufferData event_details;
+			initPQExpBuffer(&event_details);
+
+			if (recovery_type == RECTYPE_STANDBY && local_node_info.type != STANDBY)
+			{
+				appendPQExpBuffer(&event_details,
+								  _("node is registered as a %s but running as a standby"),
+								  get_node_type_string(local_node_info.type));
+
+				require_reregister = true;
+			}
+			else if (recovery_type == RECTYPE_PRIMARY && local_node_info.type == STANDBY)
+			{
+				log_error(_("node is registered as a standby but running as a %s"), get_node_type_string(local_node_info.type));
+				require_reregister = true;
+			}
+
+			if (require_reregister == true)
+			{
+				log_error("%s", event_details.data);
+				log_hint(_("%s"), hint);
+
+				create_event_notification(NULL,
+										  &config_file_options,
+										  config_file_options.node_id,
+										  "repmgrd_start",
+										  false,
+										  event_details.data);
+
+				termPQExpBuffer(&event_details);
+				terminate(ERR_BAD_CONFIG);
+			}
+
+			termPQExpBuffer(&event_details);
+		}
 
 		/*
 		 * Attempt to set node record active (unless explicitly configured not to)
 		 */
+		log_notice(_("setting node record for node \"%s\" (ID: %i) to \"active\""),
+				   local_node_info.node_name,
+				   local_node_info.node_id);
+
 		if (config_file_options.repmgrd_exit_on_inactive_node == false)
 		{
-			PGconn *primary_conn = get_primary_connection_quiet(conn, NULL, NULL);
+			PGconn *primary_conn = get_primary_connection(conn, NULL, NULL);
 			bool	success = true;
 
 			if (PQstatus(primary_conn) != CONNECTION_OK)
 			{
+				log_error(_("unable to connect to the primary node to activate the node record"));
 				success = false;
 			}
 			else
 			{
-				log_notice(_("setting node record for node \"%s\" (ID: %i) to \"active\""),
-						   local_node_info.node_name,
-						   local_node_info.node_id);
 				success = update_node_record_set_active(primary_conn, local_node_info.node_id, true);
 				PQfinish(primary_conn);
 			}
@@ -210,13 +258,16 @@ do_physical_node_check(PGconn *conn)
 			if (success == true)
 			{
 				local_node_info.active = true;
-				return;
 			}
 		}
 
+		/*
+		 * Corner-case where it was not possible to set the node to "active"
+		 */
+		if (local_node_info.active == false)
+		{
 			switch (config_file_options.failover)
 			{
-
 				/* "failover" is an enum, all values should be covered here */
 
 				case FAILOVER_AUTOMATIC:
@@ -226,7 +277,7 @@ do_physical_node_check(PGconn *conn)
 					create_event_notification(NULL,
 											  &config_file_options,
 											  config_file_options.node_id,
-										  "repmgrd_shutdown",
+											  "repmgrd_start",
 											  false,
 											  "node is inactive and cannot be used as a failover target");
 
@@ -239,6 +290,7 @@ do_physical_node_check(PGconn *conn)
 					break;
 			}
 		}
+	}
 
 	if (config_file_options.failover == FAILOVER_AUTOMATIC)
 	{
@@ -1842,6 +1894,7 @@ monitor_streaming_standby(void)
 						int			former_upstream_node_id = local_node_info.upstream_node_id;
 						NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
 						PQExpBufferData event_details;
+						t_event_info event_info = T_EVENT_INFO_INITIALIZER;
 
 						update_node_record_set_primary(local_conn,  local_node_info.node_id);
 						record_status = get_node_record(local_conn, local_node_info.node_id, &local_node_info);
@@ -1854,12 +1907,16 @@ monitor_streaming_standby(void)
 						initPQExpBuffer(&event_details);
 						appendPQExpBufferStr(&event_details,
 											 _("promotion command failed but promotion completed successfully"));
-						create_event_notification(local_conn,
+
+						event_info.node_id = former_upstream_node_id;
+
+						create_event_notification_extended(local_conn,
 														   &config_file_options,
 														   local_node_info.node_id,
 														   "repmgrd_failover_promote",
 														   true,
-												  event_details.data);
+														   event_details.data,
+														   &event_info);
 
 						termPQExpBuffer(&event_details);
 
@@ -3703,6 +3760,7 @@ promote_self(void)
 
 	{
 		PQExpBufferData event_details;
+		t_event_info event_info = T_EVENT_INFO_INITIALIZER;
 
 		/* update own internal node record */
 		record_status = get_node_record(local_conn, local_node_info.node_id, &local_node_info);
@@ -3719,13 +3777,16 @@ promote_self(void)
 						  failed_primary.node_name,
 						  failed_primary.node_id);
 
+		event_info.node_id = failed_primary.node_id;
+
 		/* local_conn is now the primary connection */
-		create_event_notification(local_conn,
+		create_event_notification_extended(local_conn,
 										   &config_file_options,
 										   local_node_info.node_id,
 										   "repmgrd_failover_promote",
 										   true,
-								  event_details.data);
+										   event_details.data,
+										   &event_info);
 
 		termPQExpBuffer(&event_details);
 	}

strutil.c

@@ -369,7 +369,6 @@ check_status_list_free(CheckStatusList *list)
 }
 
 
-
 const char *
 output_check_status(CheckStatus status)
 {