From 30e9d061728abfdcdc6ea6b94c0fab641f786a59 Mon Sep 17 00:00:00 2001
From: Jaime Casanova <jaime@2ndQuadrant.com>
Date: Sun, 11 Nov 2012 10:07:34 -0500
Subject: [PATCH] Add an option for STANDBY FOLLOW to wait for a master to
 appear. This is important for autofailover to do the right thing when
 standbys detected master death at different times.

While this is a new option, seems important for the autofailover
to work properly so i will consider the lack of it a bug and
will backpatch to 2.0 where autofailover was introduced.

For gripe from Alex Railean, about a standby not finding the new
master because the new master hasn't finish promoting.
---
 repmgr.c           | 25 +++++++++++++++++++------
 repmgr.conf.sample |  2 +-
 repmgr.h           |  1 +
 3 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/repmgr.c b/repmgr.c
index eb9d254c..2d4772c6 100644
--- a/repmgr.c
+++ b/repmgr.c
@@ -85,7 +85,7 @@ 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, "", "", 0 };
+t_runtime_options runtime_options = { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, false, "", "", 0 };
 t_configuration_options options = { "", -1, "", MANUAL_FAILOVER, -1, "", "", "", "", "", "", -1 };
 
 static char		*server_mode = NULL;
@@ -107,6 +107,7 @@ main(int argc, char **argv)
 		{"wal-keep-segments", required_argument, NULL, 'w'},
         {"keep-history", required_argument, NULL, 'k'},
 		{"force", no_argument, NULL, 'F'},
+		{"wait", no_argument, NULL, 'W'},
 		{"ignore-rsync-warning", no_argument, NULL, 'I'},
 		{"verbose", no_argument, NULL, 'v'},
 		{NULL, 0, NULL, 0}
@@ -133,7 +134,7 @@ main(int argc, char **argv)
 	}
 
 
-	while ((c = getopt_long(argc, argv, "d:h:p:U:D:l:f:R:w:k:F:I:v", long_options,
+	while ((c = getopt_long(argc, argv, "d:h:p:U:D:l:f:R:w:k:F:W:I:v", long_options,
 	                        &optindex)) != -1)
 	{
 		switch (c)
@@ -177,6 +178,9 @@ main(int argc, char **argv)
 		case 'F':
 			runtime_options.force = true;
 			break;
+		case 'W':
+			runtime_options.wait_for_master = true;
+			break;
 		case 'I':
 			runtime_options.ignore_rsync_warn = true;
 			break;
@@ -1378,10 +1382,18 @@ do_standby_follow(void)
 		exit(ERR_BAD_CONFIG);
 	}
 
-	/* 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, repmgr_schema, 
-	                                  options.cluster_name, &master_id,(char *) &master_conninfo);
+	/* 
+	 * we also need to check if there is any master in the cluster 
+	 * or wait for one to appear if we have set the wait option
+	 */
+	log_info(_("%s discovering new master...\n"), progname);
+
+	do
+	{
+		master_conn = getMasterConnection(conn, repmgr_schema, 
+	    	                              options.cluster_name, &master_id,(char *) &master_conninfo);
+	} while (master_conn == NULL && runtime_options.wait_for_master);
+
 	if (master_conn == NULL)
 	{
 		log_err(_("There isn't a master to follow in this cluster\n"));
@@ -1700,6 +1712,7 @@ help(const char *progname)
 	printf(_("	-I, --ignore-rsync-warning ignore rsync partial transfer warning\n"));
     printf(_("  -k, --keep-history=VALUE   keeps indicated number of days of history\n"));
 	printf(_("	-F, --force				   force potentially dangerous operations to happen\n"));
+	printf(_("	-W, --wait				   wait for a master to appear"));
 
 	printf(_("\n%s performs some tasks like clone a node, promote it "), progname);
 	printf(_("or making follow another node and then exits.\n"));
diff --git a/repmgr.conf.sample b/repmgr.conf.sample
index 6e81aa3f..9daaf3f4 100644
--- a/repmgr.conf.sample
+++ b/repmgr.conf.sample
@@ -24,7 +24,7 @@ reconnect_interval=10
 failover=automatic
 priority=-1
 promote_command='repmgr standby promote -f /path/to/repmgr.conf'
-follow_command='repmgr standby follow -f /path/to/repmgr.conf'
+follow_command='repmgr standby follow -f /path/to/repmgr.conf -W'
 
 # Log level: possible values are DEBUG, INFO, NOTICE, WARNING, ERR, ALERT, CRIT or EMERG
 # Default: NOTICE
diff --git a/repmgr.h b/repmgr.h
index dcab7d46..295a4645 100644
--- a/repmgr.h
+++ b/repmgr.h
@@ -59,6 +59,7 @@ typedef struct
 	char wal_keep_segments[MAXLEN];
 	bool verbose;
 	bool force;
+	bool wait_for_master;
 	bool ignore_rsync_warn;
 
 	char masterport[MAXLEN];