Add --repmgrd option to "repmgr node check"

This provides a simple way for checking whether the node's repmgrd is
running.

GitHub #719.

dbutils.c

@@ -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

@@ -69,6 +69,14 @@
                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>
         </itemizedlist>
       </para>
     </sect2>

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-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},

strutil.c

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