Fix HISTORY to show from newest to oldest

only postgresql's one

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
+1.2.0	2012-07-27
-        First public release
+		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)
@@ -28,6 +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
+1.0.0   2010-12-05
-        Make options -U, -R and -p not mandatory (Jaime)
+        First public release
-

README.rst

@@ -814,6 +814,23 @@ and on "prime."
 
 The servers are now again acting as primary on "prime" and standby on "standby".
 
+Maintainance of monitor history
+-------------------------------
+
+Once you have changed roles (with a failover or to restore original roles)
+you would end up with records saying that node1 is primary and other records
+saying that node2 is the primary. Which could be confusing.
+Also, if you don't do anything about it the monitor history will keep growing.
+For both of those reasons you sometime want to make some maintainance of the 
+``repl_monitor`` table.
+
+If you want to clean the history after a few days you can execute a 
+truncate/delete (wheter you want to completely clean history or want to keep
+a few days of history) in a cron. For example to keep just one day of history
+you can put this in your crontab::
+
+0 1 * * *   psql -c "DELETE FROM repmgr_schema.repl_monitor where now() - last_monitor_time >= '1 day'::interval;" postgres
+
 Configuration and command reference
 ===================================
 
@@ -845,6 +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
@@ -863,6 +881,8 @@ The output from this program looks like this::
     -R, --remote-user=USERNAME database server username for rsync
     -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:
@@ -871,6 +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.
@@ -941,6 +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
 --------------
 
@@ -1023,6 +1065,7 @@ following
 * ERR_DB_QUERY 7:  Error executing a database query.
 * ERR_PROMOTED 8:  Exiting program because the node has been promoted to master.
 * ERR_BAD_PASSWORD 9:  Password used to connect to a database was rejected.
+* ERR_STR_OVERFLOW 10: A string was larger than expected.
 
 License and Contributions
 =========================

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.

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",
+	                  " WHERE cluster = '%s'",
-	                  schema_quoted, cluster, id);
+	                  schema_quoted, cluster);
 
 	res1 = PQexec(standby_conn, sqlquery);
 	if (PQresultStatus(res1) != PGRES_TUPLES_OK)

dbutils.h

@@ -20,6 +20,8 @@
 #ifndef _REPMGR_DBUTILS_H_
 #define _REPMGR_DBUTILS_H_
 
+#include "strutil.h"
+
 PGconn *establishDBConnection(const char *conninfo, const bool exit_on_error);
 PGconn *establishDBConnectionByParams(const char *keywords[],
                                       const char *values[],
@@ -29,7 +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
@@ -35,6 +35,7 @@
 #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 +46,25 @@
 #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 +78,7 @@ bool need_a_node = true;
 bool require_password = false;
 
 /* Initialization of runtime options */
-t_runtime_options runtime_options = { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, "" };
+t_runtime_options runtime_options = { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, "", 0 };
 t_configuration_options options = { "", -1, "", "", "" };
 
 static char		*server_mode = NULL;
@@ -90,7 +97,9 @@ 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'},
 		{NULL, 0, NULL, 0}
 	};
@@ -110,13 +119,13 @@ 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:v", long_options,
+	while ((c = getopt_long(argc, argv, "d:h:p:U:D:f:R:w:k:F:I:v", long_options,
 	                        &optindex)) != -1)
 	{
 		switch (c)
@@ -147,9 +156,18 @@ 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;
+		case 'I':
+			runtime_options.ignore_rsync_warn = true;
+			break;
 		case 'v':
 			runtime_options.verbose = true;
 			break;
@@ -162,7 +180,8 @@ 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
@@ -170,8 +189,8 @@ main(int argc, char **argv)
 	if (optind < argc)
 	{
 		server_mode = argv[optind++];
-		if (strcasecmp(server_mode, "STANDBY") != 0 &&
+		if (strcasecmp(server_mode, "STANDBY") != 0 && strcasecmp(server_mode, "MASTER") != 0 &&
-		        strcasecmp(server_mode, "MASTER") != 0)
+		        strcasecmp(server_mode, "CLUSTER") != 0 )
 		{
 			usage();
 			exit(ERR_BAD_CONFIG);
@@ -200,13 +219,21 @@ 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();
+			if(strcasecmp(server_cmd, "SHOW") == 0)
-			exit(ERR_BAD_CONFIG);
+				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)
 	{
@@ -310,6 +337,12 @@ 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);
@@ -319,6 +352,114 @@ 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)
 {
@@ -346,7 +487,7 @@ do_master_register(void)
 	log_info(_("%s connected to master, checking its state\n"), progname);
 	if (is_standby(conn))
 	{
-		log_err(_("%s needs master to be PostgreSQL 9.0 or better\n"), progname);
+		log_err(_("Trying to register a standby node as a master\n"));
 		PQfinish(conn);
 		exit(ERR_BAD_CONFIG);
 	}
@@ -438,14 +579,13 @@ do_master_register(void)
 
 		/* and the view */
 		sqlquery_snprintf(sqlquery, "CREATE VIEW %s.repl_status AS "
-		                  "  WITH monitor_info AS (SELECT *, ROW_NUMBER() OVER (PARTITION BY primary_node, standby_node "
-		                  " ORDER BY last_monitor_time desc) "
-		                  "  FROM %s.repl_monitor) "
 		                  "  SELECT primary_node, standby_node, last_monitor_time, last_wal_primary_location, "
 		                  "         last_wal_standby_location, pg_size_pretty(replication_lag) replication_lag, "
 		                  "         pg_size_pretty(apply_lag) apply_lag, age(now(), last_monitor_time) AS time_lag "
-		                  "    FROM monitor_info a "
+		                  "    FROM %s.repl_monitor "
-		                  "   WHERE row_number = 1", repmgr_schema, repmgr_schema);
+		                  "  WHERE (standby_node, last_monitor_time) IN (SELECT standby_node, MAX(last_monitor_time) "
+		                  "                                                FROM %s.repl_monitor GROUP BY 1)",
+		                  repmgr_schema, repmgr_schema, repmgr_schema);
 		log_debug("master register: %s\n", sqlquery);
 		if (!PQexec(conn, sqlquery))
 		{
@@ -454,6 +594,19 @@ do_master_register(void)
 			PQfinish(conn);
 			exit(ERR_BAD_CONFIG);
 		}
+
+		/* an index to improve performance of the view */
+		sqlquery_snprintf(sqlquery, "CREATE INDEX idx_repl_status_sort "
+		                  "    ON %s.repl_monitor (last_monitor_time, standby_node) ",
+		                  repmgr_schema);
+		log_debug(_("master register: %s\n"), sqlquery);
+		if (!PQexec(conn, sqlquery))
+		{
+			log_err(_("Cannot indexing table %s.repl_monitor: %s\n"),
+			        repmgr_schema, PQerrorMessage(conn));
+			PQfinish(conn);
+			exit(ERR_BAD_CONFIG);
+		}
 	}
 	else
 	{
@@ -461,8 +614,7 @@ do_master_register(void)
 		int		id;
 
 		/* Ensure there isn't any other master already registered */
-		master_conn = getMasterConnection(conn, options.node,
+		master_conn = getMasterConnection(conn, options.cluster_name, &id,NULL);
-		                                  options.cluster_name, &id,NULL);
 		if (master_conn != NULL)
 		{
 			PQfinish(master_conn);
@@ -581,7 +733,7 @@ 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)
 	{
@@ -788,10 +940,17 @@ do_standby_clone(void)
 	 * Check if the tablespace locations exists and that we can write to
 	 * them.
 	 */
-	sqlquery_snprintf(sqlquery,
+	if (strcmp(master_version, "9.0") == 0 || strcmp(master_version, "9.1") == 0)
-	                  "SELECT spclocation "
+		sqlquery_snprintf(sqlquery,
-	                  "  FROM pg_tablespace "
+		                  "SELECT spclocation "
-	                  "WHERE spcname NOT IN ('pg_default', 'pg_global')");
+		                  "  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);
@@ -845,6 +1004,7 @@ 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"),
@@ -855,7 +1015,14 @@ 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,
@@ -871,6 +1038,16 @@ 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)
@@ -886,6 +1063,22 @@ 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
+	 */
+	sqlquery_snprintf(sqlquery, "SET synchronous_commit TO OFF");
+	res = PQexec(conn, sqlquery);
+	if (PQresultStatus(res) != PGRES_COMMAND_OK)
+	{
+		log_err("Can't set synchronous_commit: %s\n", PQerrorMessage(conn));
+		PQclear(res);
+		PQfinish(conn);
+		exit(ERR_BAD_CONFIG);
+	}
+
 	/*
 	 * inform the master we will start a backup and get the first XLog filename
 	 * so we can say to the user we need those files
@@ -963,10 +1156,17 @@ do_standby_clone(void)
 	 * find and appropiate rsync option but besides we could someday make all
 	 * these rsync happen concurrently
 	 */
-	sqlquery_snprintf(sqlquery,
+	if (strcmp(master_version, "9.0") == 0 || strcmp(master_version, "9.1") == 0)
-	                  "SELECT spclocation "
+		sqlquery_snprintf(sqlquery,
-	                  "  FROM pg_tablespace "
+		                  "SELECT spclocation "
-	                  "  WHERE spcname NOT IN ('pg_default', 'pg_global')");
+		                  "  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)
@@ -1022,9 +1222,6 @@ stop_backup:
 	 * Don't have this one exit if it fails, so that a more informative
 	 * error message will also appear about the backup not being stopped.
 	 */
-	log_info(_("%s connecting to master database to stop backup\n"), progname);
-	conn=establishDBConnectionByParams(keywords,values,false);
-
 	log_notice("Finishing backup...\n");
 	sqlquery_snprintf(sqlquery, "SELECT pg_xlogfile_name(pg_stop_backup())");
 	log_debug("standby clone: %s\n", sqlquery);
@@ -1039,8 +1236,10 @@ stop_backup:
 	}
 	last_wal_segment = PQgetvalue(res, 0, 0);
 
-	log_info(_("%s requires primary to keep WAL files %s until at least %s\n"),
+	/* don't show this message if rsync failed */
-	         progname, first_wal_segment, last_wal_segment);
+	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);
 
 	/* Finished with the database connection now */
 	PQclear(res);
@@ -1121,7 +1320,7 @@ 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)
 	{
@@ -1225,8 +1424,7 @@ 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,
+	master_conn = getMasterConnection(conn, options.cluster_name, &master_id,(char *) &master_conninfo);
-	                                  options.cluster_name, &master_id,(char *) &master_conninfo);
 	if (master_conn == NULL)
 	{
 		PQfinish(conn);
@@ -1272,7 +1470,7 @@ 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 "
@@ -1322,6 +1520,7 @@ 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"));
@@ -1337,6 +1536,8 @@ void help(const char *progname)
 	printf(_("	-R, --remote-user=USERNAME database server username for rsync\n"));
 	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"));
@@ -1347,6 +1548,8 @@ 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"));
 }
 
 
@@ -1379,41 +1582,7 @@ 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,
+	write_primary_conninfo(line);
-	                (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);
-			}
-		}
-	}
 
 	if (fputs(line, recovery_file) == EOF)
 	{
@@ -1428,6 +1597,24 @@ 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;
+
+	/* Check if we have ssh connectivity to host before trying to rsync */
+	if (!remote_user[0])
+		maxlen_snprintf(script, "ssh -o Batchmode=yes %s /bin/true", host);
+	else
+		maxlen_snprintf(script, "ssh -o Batchmode=yes %s -l %s /bin/true", host, remote_user);
+
+	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,
@@ -1473,6 +1660,29 @@ copy_remote_files(char *host, char *remote_user, char *remote_path,
 
 	r = system(script);
 
+	/*
+	 * If we are transfering a directory (ie: data directory, tablespace directories)
+	 * then we can ignore some rsync warning, so if we get some of those errors we
+	 * treat them as 0 if we have --ignore-rsync-warning commandline option set
+	 * List of ignorable rsync errors:
+	 * 24     Partial transfer due to vanished source files
+	 */
+	if ((WEXITSTATUS(r) == 24) && is_directory)
+	{
+		if (!runtime_options.ignore_rsync_warn)
+		{
+			log_warning( _("\nrsync completed with return code 24 "
+			               "\"Partial transfer due to vanished source files\".\n"
+			               "This can happen because of normal operation "
+			               "on the master server, but it may indicate an "
+			               "issue during cloning.  If you are certain no "
+			               "changes were made to the master, try cloning "
+			               "again using \"repmgr --force --ignore-rsync-warning\"."));
+			exit(ERR_BAD_RSYNC);
+		}
+		else
+			r = 0;
+	}
 	if (r != 0)
 		log_err(_("Can't rsync from remote file or directory (%s:%s)\n"),
 		        host_string, remote_path);
@@ -1599,7 +1809,48 @@ 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

@@ -55,9 +55,12 @@ typedef struct
 	char wal_keep_segments[MAXLEN];
 	bool verbose;
 	bool force;
+	bool ignore_rsync_warn;
 
 	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);
+	}
 }
 
 

strutil.c

@@ -27,6 +27,15 @@
 
 static int xvsnprintf(char *str, size_t size, const char *format, va_list ap);
 
+/* Add strnlen on platforms that don't have it, like OS X */
+#ifndef strnlen
+size_t
+strnlen(const char *s, size_t n)
+{
+	const char *end = (const char *) memchr(s, '\0', n);
+	return(end ? end - s : n);
+}
+#endif
 
 static int
 xvsnprintf(char *str, size_t size, const char *format, va_list ap)

strutil.h

@@ -35,4 +35,9 @@ extern int xsnprintf(char *str, size_t size, const char *format, ...);
 extern int sqlquery_snprintf(char *str, const char *format, ...);
 extern int maxlen_snprintf(char *str, const char *format, ...);
 
+/* Add strnlen on platforms that don't have it, like OS X */
+#ifndef strnlen
+extern size_t strnlen(const char *s, size_t n);
+#endif
+
 #endif	/* _STRUTIL_H_ */

version.h

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