Add "--checksum" in rsync when using "--force"

If the user don't put that option in rsync_options using of "--force"
could be unsafe.
While the probability of failures because of this are low they aren't
zero.

CREDITS

@@ -10,3 +10,5 @@ Hannu Krosing <hannu@2ndQuadrant.com>
 Cédric Villemain <cedric@2ndquadrant.com>
 Charles Duffy <charles@dyfis.net>
 Daniel Farina <daniel@heroku.com>
+Marco Nenciarini <marco.nenciarini@2ndquadrant.it>
+Carlo Ascani <carlo.ascani@2ndquadrant.it>

HISTORY

@@ -1,5 +1,21 @@
-1.0.0   2010-12-05
-        First public release
+1.2.0	2012-07-27
+		Test ssh connection before trying to rsync (Cédric)
+        Add CLUSTER SHOW command (Carlo)
+        Add CLUSTER CLEANUP command (Jaime)
+        Add function write_primary_conninfo (Marco)
+        Teach repmgr how to get tablespace's location in different pg version (Jaime)
+		Improve version message (Carlo)
+
+1.1.1	2012-04-18
+        Add --ignore-rsync-warning (Cédric)
+        Add strnlen for compatibility with OS X (Greg)
+        Improve performance of repl_status view (Jaime) 
+        Remove last argument from log_err (Jaime, Reported by Jeroen Dekkers)
+        Complete documentation about possible error conditions (Jaime)
+        Document how to clean history (Jaime)
+
+1.1.0   2011-03-09
+        Make options -U, -R and -p not mandatory (Jaime)
 
 1.1.0b1 2011-02-24 
         Fix missing "--force" option in help (Greg Smith)
@@ -28,13 +44,5 @@
         Map old verbose flag into a useful setting for the new logger (Greg)
         Document repmgrd startup restrictions and log info about them (Greg)
 
-1.1.0   2011-03-09
-        Make options -U, -R and -p not mandatory (Jaime)
-
-1.1.1	2012-04-18
-        Add --ignore-rsync-warning (Cédric)
-        Add strnlen for compatibility with OS X (Greg)
-        Improve performance of repl_status view (Jaime) 
-        Remove last argument from log_err (Jaime, Reported by Jeroen Dekkers)
-        Complete documentation about possible error conditions (Jaime)
-        Document how to clean history (Jaime)
+1.0.0   2010-12-05
+        First public release

README.rst

@@ -862,6 +862,7 @@ The output from this program looks like this::
   Usage:
    repmgr [OPTIONS] master  {register}
    repmgr [OPTIONS] standby {register|clone|promote|follow}
+   repmgr [OPTIONS] cluster {show|cleanup}
 
   General options:
     --help                     show this help, then exit
@@ -881,6 +882,7 @@ The output from this program looks like this::
     -w, --wal-keep-segments=VALUE  minimum value for the GUC wal_keep_segments (default: 5000)
     -F, --force                force potentially dangerous operations to happen
     -I, --ignore-rsync-warning Ignore partial transfert warning
+    -k, --keep-history         keeps indicated number of days of history
 
   repmgr performs some tasks like clone a node, promote it or making follow another node and then exits.
   COMMANDS:
@@ -889,6 +891,8 @@ The output from this program looks like this::
    standby clone [node]  - allows creation of a new standby
    standby promote       - allows manual promotion of a specific standby into a new master in the event of a failover
    standby follow        - allows the standby to re-point itself to a new master
+   cluster show          - print node informations
+   cluster cleanup       - cleans monitor's history
 
 The ``--verbose`` option can be useful in troubleshooting issues with
 the program.
@@ -959,6 +963,26 @@ its port if is different from the default one.
 
         ./repmgr standby follow
 
+* cluster show 
+
+    * Shows the role (standby/master) and connection string for all nodes configured 
+      in the cluster or "FAILED" if the node doesn't respond. This allow us to know 
+      which nodes are alive and which one needs attention and to have a notion of the
+      structure of clusters we just have access to.  Example::
+
+        ./repmgr cluster show
+
+* cluster cleanup 
+
+    * Cleans the monitor's history from repmgr tables. This avoids the repl_monitor table
+      to grow excesivelly which in turns affects repl_status view performance, also 
+      keeps controlled the space in disk used by repmgr. This command can be used manually
+      or in a cron to make it periodically.  
+      There is also a --keep-history (-k) option to indicate how many days of history we
+      want to keep, so the command will clean up history older than "keep-history" days. Example::
+
+        ./repmgr cluster cleanup -k 2
+
 repmgrd Daemon
 --------------
 

TODO

@@ -12,10 +12,3 @@ Known issues in repmgr
 
 * After running repmgrd as a regular foreground application, hitting
   control-C causes the program to crash.
-
-Planned feature improvements
-============================
-
-* Before running ``pg_start_backup()``, a sanity check that there is a
-  a working ssh connection to the destination would help find
-  configuration errors before disturbing the database.

check_dir.c

@@ -129,10 +129,10 @@ mkdir_p(char *path, mode_t omode)
 {
 	struct stat sb;
 	mode_t		numask,
-	         oumask;
+	            oumask;
 	int			first,
-	        last,
-	        retval;
+	            last,
+	            retval;
 	char	   *p;
 
 	p = path;

dbutils.c

@@ -202,7 +202,7 @@ get_cluster_size(PGconn *conn)
  * connection string is placed there.
  */
 PGconn *
-getMasterConnection(PGconn *standby_conn, int id, char *cluster,
+getMasterConnection(PGconn *standby_conn, char *cluster,
                     int *master_id, char *master_conninfo_out)
 {
 	PGconn		*master_conn	 = NULL;
@@ -242,8 +242,8 @@ getMasterConnection(PGconn *standby_conn, int id, char *cluster,
 	         cluster);
 
 	sqlquery_snprintf(sqlquery, "SELECT * FROM %s.repl_nodes "
-	                  " WHERE cluster = '%s' and id <> %d",
-	                  schema_quoted, cluster, id);
+	                  " WHERE cluster = '%s'",
+	                  schema_quoted, cluster);
 
 	res1 = PQexec(standby_conn, sqlquery);
 	if (PQresultStatus(res1) != PGRES_TUPLES_OK)

dbutils.h

@@ -31,7 +31,7 @@ char   *pg_version(PGconn *conn, char* major_version);
 bool	guc_setted(PGconn *conn, const char *parameter, const char *op,
                    const char *value);
 const char	 *get_cluster_size(PGconn *conn);
-PGconn *getMasterConnection(PGconn *standby_conn, int id, char *cluster,
+PGconn *getMasterConnection(PGconn *standby_conn, char *cluster,
                             int *master_id, char *master_conninfo_out);
 
 #endif

repmgr.c

@@ -7,7 +7,7 @@
  *
  * Commands implemented are.
  * MASTER REGISTER, STANDBY REGISTER, STANDBY CLONE, STANDBY FOLLOW,
- * STANDBY PROMOTE
+ * STANDBY PROMOTE, CLUSTER SHOW, CLUSTER CLEANUP
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -28,6 +28,7 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/wait.h>
 #include <time.h>
 #include <unistd.h>
 
@@ -35,6 +36,7 @@
 #include "config.h"
 #include "check_dir.h"
 #include "strutil.h"
+#include "version.h"
 
 #define RECOVERY_FILE "recovery.conf"
 #define RECOVERY_DONE_FILE "recovery.done"
@@ -45,19 +47,25 @@
 #define STANDBY_CLONE 	 3
 #define STANDBY_PROMOTE  4
 #define STANDBY_FOLLOW 	 5
+#define CLUSTER_SHOW     6
+#define CLUSTER_CLEANUP	 7
 
 static void help(const char *progname);
 static bool create_recovery_file(const char *data_dir, char *master_conninfo);
+static int test_ssh_connection(char *host, char *remote_user);
 static int	copy_remote_files(char *host, char *remote_user, char *remote_path,
                               char *local_path, bool is_directory);
 static bool check_parameters_for_action(const int action);
+static void write_primary_conninfo(char* line);
 
 static void do_master_register(void);
 static void do_standby_register(void);
 static void do_standby_clone(void);
 static void do_standby_promote(void);
 static void do_standby_follow(void);
-static void help(const char* progname);
+static void do_cluster_show(void);
+static void do_cluster_cleanup(void);
+
 static void usage(void);
 
 /* Global variables */
@@ -71,7 +79,7 @@ bool need_a_node = true;
 bool require_password = false;
 
 /* Initialization of runtime options */
-t_runtime_options runtime_options = { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, "" };
+t_runtime_options runtime_options = { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, "", 0 };
 t_configuration_options options = { "", -1, "", "", "" };
 
 static char		*server_mode = NULL;
@@ -90,6 +98,7 @@ main(int argc, char **argv)
 		{"config-file", required_argument, NULL, 'f'},
 		{"remote-user", required_argument, NULL, 'R'},
 		{"wal-keep-segments", required_argument, NULL, 'w'},
+		{"keep-history", required_argument, NULL, 'k'},
 		{"force", no_argument, NULL, 'F'},
 		{"ignore-rsync-warning", no_argument, NULL, 'I'},
 		{"verbose", no_argument, NULL, 'v'},
@@ -111,13 +120,13 @@ main(int argc, char **argv)
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
 		{
-			printf("%s (PostgreSQL) " PG_VERSION "\n", progname);
+			printf("%s %s (PostgreSQL %s)\n", progname, REPMGR_VERSION, PG_VERSION);
 			exit(SUCCESS);
 		}
 	}
 
 
-	while ((c = getopt_long(argc, argv, "d:h:p:U:D:f:R:w:F:I:v", long_options,
+	while ((c = getopt_long(argc, argv, "d:h:p:U:D:f:R:w:k:FIv", long_options,
 	                        &optindex)) != -1)
 	{
 		switch (c)
@@ -148,6 +157,12 @@ main(int argc, char **argv)
 			if (atoi(optarg) > 0)
 				strncpy(runtime_options.wal_keep_segments, optarg, MAXLEN);
 			break;
+		case 'k':
+			if (atoi(optarg) > 0)
+				runtime_options.keep_history = atoi(optarg);
+			else
+				runtime_options.keep_history = 0;
+			break;
 		case 'F':
 			runtime_options.force = true;
 			break;
@@ -166,7 +181,8 @@ main(int argc, char **argv)
 	/*
 	 * Now we need to obtain the action, this comes in one of these forms:
 	 * MASTER REGISTER |
-	 * STANDBY {REGISTER | CLONE [node] | PROMOTE | FOLLOW [node]}
+	 * STANDBY {REGISTER | CLONE [node] | PROMOTE | FOLLOW [node]} |
+	 * CLUSTER {SHOW | CLEANUP}
 	 *
 	 * the node part is optional, if we receive it then we shouldn't
 	 * have received a -h option
@@ -174,8 +190,8 @@ main(int argc, char **argv)
 	if (optind < argc)
 	{
 		server_mode = argv[optind++];
-		if (strcasecmp(server_mode, "STANDBY") != 0 &&
-		        strcasecmp(server_mode, "MASTER") != 0)
+		if (strcasecmp(server_mode, "STANDBY") != 0 && strcasecmp(server_mode, "MASTER") != 0 &&
+		        strcasecmp(server_mode, "CLUSTER") != 0 )
 		{
 			usage();
 			exit(ERR_BAD_CONFIG);
@@ -204,13 +220,21 @@ main(int argc, char **argv)
 			action = STANDBY_PROMOTE;
 		else if (strcasecmp(server_cmd, "FOLLOW") == 0)
 			action = STANDBY_FOLLOW;
-		else
+		else if (strcasecmp(server_mode, "CLUSTER") == 0)
 		{
-			usage();
-			exit(ERR_BAD_CONFIG);
+			if(strcasecmp(server_cmd, "SHOW") == 0)
+				action = CLUSTER_SHOW;
+			else if(strcasecmp(server_cmd, "CLEANUP") == 0)
+				action = CLUSTER_CLEANUP;
 		}
 	}
 
+	if (action == NO_ACTION)
+	{
+		usage();
+		exit(ERR_BAD_CONFIG);
+	}
+
 	/* For some actions we still can receive a last argument */
 	if (action == STANDBY_CLONE)
 	{
@@ -232,7 +256,7 @@ main(int argc, char **argv)
 		break;
 	default:
 		log_err(_("%s: too many command-line arguments (first extra is \"%s\")\n"),
-		        progname, argv[optind + 1]);
+		        progname, argv[optind]);
 		usage();
 		exit(ERR_BAD_CONFIG);
 	}
@@ -314,6 +338,12 @@ main(int argc, char **argv)
 	case STANDBY_FOLLOW:
 		do_standby_follow();
 		break;
+	case CLUSTER_SHOW:
+		do_cluster_show();
+		break;
+	case CLUSTER_CLEANUP:
+		do_cluster_cleanup();
+		break;
 	default:
 		usage();
 		exit(ERR_BAD_CONFIG);
@@ -323,6 +353,114 @@ main(int argc, char **argv)
 	return 0;
 }
 
+static void
+do_cluster_show(void)
+{
+	PGconn	 *conn;
+	PGconn	 *node_conn = NULL;
+	PGresult *res;
+	char	 sqlquery[QUERY_STR_LEN];
+	char	 node_role[MAXLEN];
+	int		 i;
+
+	/* We need to connect to check configuration */
+	log_info(_("%s connecting to database\n"), progname);
+	conn = establishDBConnection(options.conninfo, true);
+
+	sqlquery_snprintf(sqlquery, "SELECT conninfo FROM %s.repl_nodes;", repmgr_schema);
+	log_debug("cluster show: %s\n", sqlquery);
+	res = PQexec(conn, sqlquery);
+
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_err(_("Can't get nodes informations, have you regitered them?\n%s\n"), PQerrorMessage(conn));
+		PQclear(res);
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	printf("Role      | Connection String \n");
+	for (i = 0; i < PQntuples(res); i++)
+	{
+		node_conn = establishDBConnection(PQgetvalue(res, i, 0), false);
+		if (PQstatus(node_conn) != CONNECTION_OK)
+			strcpy(node_role, "  FAILED");
+		else if (is_standby(node_conn))
+			strcpy(node_role, "  standby");
+		else
+			strcpy(node_role, "* master");
+
+		printf("%-10s", node_role);
+		printf("| %s\n", PQgetvalue(res, i, 0));
+
+		PQfinish(node_conn);
+	}
+	PQclear(res);
+	PQfinish(conn);
+}
+
+
+static void
+do_cluster_cleanup(void)
+{
+	int			master_id;
+	PGconn	 *conn;
+	PGconn	 *master_conn;
+	PGresult *res;
+	char	 sqlquery[QUERY_STR_LEN];
+
+	/* I need a connection to my local db to know what node is the master */
+	log_info(_("%s connecting to database\n"), progname);
+	conn = establishDBConnection(options.conninfo, true);
+
+	/* check if there is a master in this cluster */
+	log_info(_("%s connecting to master database\n"), progname);
+	master_conn = getMasterConnection(conn, options.cluster_name,
+	                                  &master_id, NULL);
+	if (!master_conn)
+	{
+		log_err(_("cluster cleanup: cannot connect to master\n"));
+		PQfinish(conn);
+		exit(ERR_DB_CON);
+	}
+
+	/* I don't need a local connection anymore */
+	PQfinish(conn);
+
+	if (runtime_options.keep_history > 0)
+	{
+		sqlquery_snprintf(sqlquery, "DELETE FROM %s.repl_monitor "
+		                  " WHERE age(now(), last_monitor_time) >= '%d days'::interval;",
+		                  repmgr_schema, runtime_options.keep_history);
+	}
+	else
+	{
+		sqlquery_snprintf(sqlquery, "TRUNCATE TABLE %s.repl_monitor;", repmgr_schema);
+	}
+
+	log_debug("cluster cleanup: %s\n", sqlquery);
+	res = PQexec(master_conn, sqlquery);
+	if (PQresultStatus(res) != PGRES_COMMAND_OK)
+	{
+		log_err(_("cluster cleanup: Couldn't clean history\n%s\n"), PQerrorMessage(master_conn));
+		PQclear(res);
+		PQfinish(master_conn);
+		exit(ERR_BAD_CONFIG);
+	}
+	PQclear(res);
+
+	/* Let's VACUUM the table to avoid autovacuum to be launched in an unexpected hour */
+	sqlquery_snprintf(sqlquery, "VACUUM %s.repl_monitor;", repmgr_schema);
+	log_debug("cluster cleanup: %s\n", sqlquery);
+	res = PQexec(master_conn, sqlquery);
+
+	/* XXX There is any need to check this VACUUM happens without problems? */
+
+	PQclear(res);
+	PQfinish(master_conn);
+}
+
+
 static void
 do_master_register(void)
 {
@@ -477,8 +615,7 @@ do_master_register(void)
 		int		id;
 
 		/* Ensure there isn't any other master already registered */
-		master_conn = getMasterConnection(conn, options.node,
-		                                  options.cluster_name, &id,NULL);
+		master_conn = getMasterConnection(conn, options.cluster_name, &id,NULL);
 		if (master_conn != NULL)
 		{
 			PQfinish(master_conn);
@@ -597,7 +734,7 @@ do_standby_register(void)
 
 	/* check if there is a master in this cluster */
 	log_info(_("%s connecting to master database\n"), progname);
-	master_conn = getMasterConnection(conn, options.node, options.cluster_name,
+	master_conn = getMasterConnection(conn, options.cluster_name,
 	                                  &master_id, NULL);
 	if (!master_conn)
 	{
@@ -804,10 +941,17 @@ do_standby_clone(void)
 	 * Check if the tablespace locations exists and that we can write to
 	 * them.
 	 */
-	sqlquery_snprintf(sqlquery,
-	                  "SELECT spclocation "
-	                  "  FROM pg_tablespace "
-	                  "WHERE spcname NOT IN ('pg_default', 'pg_global')");
+	if (strcmp(master_version, "9.0") == 0 || strcmp(master_version, "9.1") == 0)
+		sqlquery_snprintf(sqlquery,
+		                  "SELECT spclocation "
+		                  "  FROM pg_tablespace "
+		                  "WHERE spcname NOT IN ('pg_default', 'pg_global')");
+	else
+		sqlquery_snprintf(sqlquery,
+		                  "SELECT pg_tablespace_location(oid) spclocation "
+		                  "  FROM pg_tablespace "
+		                  "WHERE spcname NOT IN ('pg_default', 'pg_global')");
+
 	log_debug("standby clone: %s\n", sqlquery);
 
 	res = PQexec(conn, sqlquery);
@@ -861,6 +1005,7 @@ do_standby_clone(void)
 				PQfinish(conn);
 				exit(ERR_BAD_CONFIG);
 			}
+			break;
 		default:
 			/* Trouble accessing directory */
 			log_err(_("%s: could not access directory \"%s\": %s\n"),
@@ -871,7 +1016,14 @@ do_standby_clone(void)
 		}
 	}
 
-	log_notice("Starting backup...\n");
+	r = test_ssh_connection(runtime_options.host, runtime_options.remote_user);
+	if (r != 0)
+	{
+		log_err(_("%s: Aborting, remote host %s is not reachable.\n"), progname, runtime_options.host);
+		PQclear(res);
+		PQfinish(conn);
+		exit(ERR_DB_CON);
+	}
 
 	/* Get the data directory full path and the configuration files location */
 	sqlquery_snprintf(sqlquery,
@@ -887,6 +1039,16 @@ do_standby_clone(void)
 		PQfinish(conn);
 		exit(ERR_BAD_CONFIG);
 	}
+
+	/* We need all 4 parameters, and they can be retrieved only by superusers */
+	if (PQntuples(res) != 4)
+	{
+		log_err("%s: STANDBY CLONE should be run by a SUPERUSER\n", progname);
+		PQclear(res);
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
 	for (i = 0; i < PQntuples(res); i++)
 	{
 		if (strcmp(PQgetvalue(res, i, 0), "data_directory") == 0)
@@ -902,6 +1064,8 @@ do_standby_clone(void)
 	}
 	PQclear(res);
 
+	log_notice("Starting backup...\n");
+
 	/*
 	 * in pg 9.1 default is to wait for a sync standby to ack,
 	 * avoid that by turning off sync rep for this session
@@ -993,10 +1157,17 @@ do_standby_clone(void)
 	 * find and appropiate rsync option but besides we could someday make all
 	 * these rsync happen concurrently
 	 */
-	sqlquery_snprintf(sqlquery,
-	                  "SELECT spclocation "
-	                  "  FROM pg_tablespace "
-	                  "  WHERE spcname NOT IN ('pg_default', 'pg_global')");
+	if (strcmp(master_version, "9.0") == 0 || strcmp(master_version, "9.1") == 0)
+		sqlquery_snprintf(sqlquery,
+		                  "SELECT spclocation "
+		                  "  FROM pg_tablespace "
+		                  "  WHERE spcname NOT IN ('pg_default', 'pg_global')");
+	else
+		sqlquery_snprintf(sqlquery,
+		                  "SELECT pg_tablespace_location(oid) spclocation "
+		                  "  FROM pg_tablespace "
+		                  "  WHERE spcname NOT IN ('pg_default', 'pg_global')");
+
 	log_debug("standby clone: %s\n", sqlquery);
 	res = PQexec(conn, sqlquery);
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
@@ -1067,7 +1238,7 @@ stop_backup:
 	last_wal_segment = PQgetvalue(res, 0, 0);
 
 	/* don't show this message if rsync failed */
-	if (r == 0)
+	if (r == 0 && runtime_options.verbose)
 		log_info(_("%s requires primary to keep WAL files %s until at least %s\n"),
 		         progname, first_wal_segment, last_wal_segment);
 
@@ -1150,7 +1321,7 @@ do_standby_promote(void)
 	}
 
 	/* we also need to check if there isn't any master already */
-	old_master_conn = getMasterConnection(conn, options.node, options.cluster_name,
+	old_master_conn = getMasterConnection(conn, options.cluster_name,
 	                                      &old_master_id, NULL);
 	if (old_master_conn != NULL)
 	{
@@ -1254,8 +1425,7 @@ do_standby_follow(void)
 
 	/* we also need to check if there is any master in the cluster */
 	log_info(_("%s connecting to master database\n"), progname);
-	master_conn = getMasterConnection(conn, options.node,
-	                                  options.cluster_name, &master_id,(char *) &master_conninfo);
+	master_conn = getMasterConnection(conn, options.cluster_name, &master_id,(char *) &master_conninfo);
 	if (master_conn == NULL)
 	{
 		PQfinish(conn);
@@ -1301,7 +1471,7 @@ do_standby_follow(void)
 	strncpy(runtime_options.masterport, PQport(master_conn), MAXLEN);
 	PQfinish(master_conn);
 
-	log_info(_("%s Changing standby's master"),progname);
+	log_info(_("%s Changing standby's master\n"),progname);
 
 	/* Get the data directory full path */
 	sqlquery_snprintf(sqlquery, "SELECT setting "
@@ -1351,6 +1521,7 @@ void help(const char *progname)
 	printf(_(" %s [OPTIONS] master	{register}\n"), progname);
 	printf(_(" %s [OPTIONS] standby {register|clone|promote|follow}\n"),
 	       progname);
+	printf(_(" %s [OPTIONS] cluster {show|cleanup}\n"), progname);
 	printf(_("\nGeneral options:\n"));
 	printf(_("	--help					   show this help, then exit\n"));
 	printf(_("	--version				   output version information, then exit\n"));
@@ -1367,6 +1538,7 @@ void help(const char *progname)
 	printf(_("	-w, --wal-keep-segments=VALUE  minimum value for the GUC wal_keep_segments (default: 5000)\n"));
 	printf(_("	-F, --force				   force potentially dangerous operations to happen\n"));
 	printf(_("	-I, --ignore-rsync-warning		   Ignore partial transfert warning\n"));
+	printf(_("	-k, --keep-history=VALUE   keeps indicated number of days of history\n"));
 
 	printf(_("\n%s performs some tasks like clone a node, promote it "), progname);
 	printf(_("or making follow another node and then exits.\n"));
@@ -1377,6 +1549,8 @@ void help(const char *progname)
 	printf(_(" standby promote		 - allows manual promotion of a specific standby into a "));
 	printf(_("new master in the event of a failover\n"));
 	printf(_(" standby follow		 - allows the standby to re-point itself to a new master\n"));
+	printf(_(" cluster show            - print node informations\n"));
+	printf(_(" cluster cleanup         - cleans monitor's history\n"));
 }
 
 
@@ -1409,41 +1583,7 @@ create_recovery_file(const char *data_dir, char *master_conninfo)
 		return false;
 	}
 
-	maxlen_snprintf(line, "primary_conninfo = 'host=%s port=%s'\n", runtime_options.host,
-	                (runtime_options.masterport[0]) ? runtime_options.masterport : "5432");
-
-	/*
-	 * Template a password into the connection string in recovery.conf
-	 * if a full connection string is not already provided.
-	 *
-	 * Sometimes this is passed by the user explicitly, and otherwise
-	 * we try to get it into the environment.
-	 *
-	 * XXX: This is pretty dirty, at least push this up to the caller rather
-	 * than hitting environment variables at this level.
-	 */
-	if (master_conninfo == NULL)
-	{
-		char *password = getenv("PGPASSWORD");
-
-		if (password != NULL)
-		{
-			maxlen_snprintf(line,
-			                "primary_conninfo = 'host=%s port=%s password=%s'\n",
-			                runtime_options.host,
-			                (runtime_options.masterport[0]) ? runtime_options.masterport : "5432",
-			                password);
-		}
-		else
-		{
-			if (require_password)
-			{
-				log_err(_("%s: PGPASSWORD not set, but having one is required\n"),
-				        progname);
-				exit(ERR_BAD_PASSWORD);
-			}
-		}
-	}
+	write_primary_conninfo(line);
 
 	if (fputs(line, recovery_file) == EOF)
 	{
@@ -1458,6 +1598,31 @@ create_recovery_file(const char *data_dir, char *master_conninfo)
 	return true;
 }
 
+static int
+test_ssh_connection(char *host, char *remote_user)
+{
+	char script[MAXLEN];
+	int	 r;
+
+	/* On some OS, true is located in a different place than in Linux */
+#ifdef __FreeBSD__
+#define TRUEBIN_PATH "/usr/bin/true"
+#else
+#define TRUEBIN_PATH "/bin/true"
+#endif
+
+	/* Check if we have ssh connectivity to host before trying to rsync */
+	if (!remote_user[0])
+		maxlen_snprintf(script, "ssh -o Batchmode=yes %s %s", host, TRUEBIN_PATH);
+	else
+		maxlen_snprintf(script, "ssh -o Batchmode=yes %s -l %s %s", host, remote_user, TRUEBIN_PATH);
+
+	log_debug(_("command is: %s"), script);
+	r = system(script);
+	if (r != 0)
+		log_info(_("Cannot connect to the remote host (%s)\n"), host);
+	return r;
+}
 
 static int
 copy_remote_files(char *host, char *remote_user, char *remote_path,
@@ -1476,7 +1641,7 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 		maxlen_snprintf(rsync_flags, "%s", options.rsync_options);
 
 	if (runtime_options.force)
-		strcat(rsync_flags, " --delete");
+		strcat(rsync_flags, " --delete --checksum");
 
 	if (!remote_user[0])
 	{
@@ -1652,7 +1817,52 @@ check_parameters_for_action(const int action)
 		}
 		need_a_node = false;
 		break;
+	case CLUSTER_SHOW:
+		/* allow all parameters to be supplied */
+		break;
+	case CLUSTER_CLEANUP:
+		/* allow all parameters to be supplied */
+		break;
 	}
 
 	return ok;
 }
+
+/* This function uses global variables to determine connection settings. Special
+ * usage of the PGPASSWORD variable is handled, but strongly discouraged */
+static void
+write_primary_conninfo(char* line)
+{
+	char host_buf[MAXLEN] = "";
+	char conn_buf[MAXLEN] = "";
+	char user_buf[MAXLEN] = "";
+	char password_buf[MAXLEN] = "";
+
+	/* Environment variable for password (UGLY, please use .pgpass!) */
+	const char *password = getenv("PGPASSWORD");
+	if (password != NULL)
+	{
+		maxlen_snprintf(password_buf, " password=%s", password);
+	}
+	else if (require_password)
+	{
+		log_err(_("%s: PGPASSWORD not set, but having one is required\n"),
+		        progname);
+		exit(ERR_BAD_PASSWORD);
+	}
+
+	if (runtime_options.host[0])
+	{
+		maxlen_snprintf(host_buf, " host=%s", runtime_options.host);
+	}
+
+	if (runtime_options.username[0])
+	{
+		maxlen_snprintf(user_buf, " user=%s", runtime_options.username);
+	}
+
+	maxlen_snprintf(conn_buf, "port=%s%s%s%s",
+	                (runtime_options.masterport[0]) ? runtime_options.masterport : "5432", host_buf, user_buf, password_buf);
+
+	maxlen_snprintf(line, "primary_conninfo = '%s'", conn_buf);
+}

repmgr.h

@@ -59,6 +59,8 @@ typedef struct
 
 	char masterport[MAXLEN];
 
+	/* parameter used by CLUSTER CLEANUP */
+	int	keep_history;
 } t_runtime_options;
 
 #endif

repmgrd.c

@@ -30,6 +30,7 @@
 #include "config.h"
 #include "log.h"
 #include "strutil.h"
+#include "version.h"
 
 #include "libpq/pqsignal.h"
 
@@ -116,7 +117,7 @@ main(int argc, char **argv)
 		}
 		if (strcmp(argv[1], "--version") == 0 || strcmp(argv[1], "-V") == 0)
 		{
-			printf("%s (PostgreSQL) " PG_VERSION "\n", progname);
+			printf("%s %s (PostgreSQL %s)\n", progname, REPMGR_VERSION, PG_VERSION);
 			exit(SUCCESS);
 		}
 	}
@@ -185,7 +186,7 @@ main(int argc, char **argv)
 		/* I need the id of the primary as well as a connection to it */
 		log_info(_("%s Connecting to primary for cluster '%s'\n"),
 		         progname, local_options.cluster_name);
-		primaryConn = getMasterConnection(myLocalConn, local_options.node,
+		primaryConn = getMasterConnection(myLocalConn,
 		                                  local_options.cluster_name,
 		                                  &primary_options.node,NULL);
 		if (primaryConn == NULL)
@@ -269,7 +270,7 @@ MonitorExecute(void)
 		log_err(_("We couldn't reconnect to master. Now checking if another node has been promoted.\n"));
 		for (connection_retries = 0; connection_retries < 6; connection_retries++)
 		{
-			primaryConn = getMasterConnection(myLocalConn, local_options.node,
+			primaryConn = getMasterConnection(myLocalConn,
 			                                  local_options.cluster_name, &primary_options.node,NULL);
 			if (PQstatus(primaryConn) == CONNECTION_OK)
 			{
@@ -456,7 +457,10 @@ checkNodeConfiguration(char *conninfo)
 			exit(ERR_BAD_CONFIG);
 		}
 	}
-	PQclear(res);
+	else
+	{
+		PQclear(res);
+	}
 }
 
 

version.h

@@ -0,0 +1,4 @@
+#ifndef _VERSION_H_
+#define _VERSION_H_
+#define REPMGR_VERSION "1.2.0"
+#endif