Merge branch 'master' into REL2_0_STABLE

The leak is irrelevant

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2012, 2ndQuadrant Limited
+Copyright (c) 2010-2014, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

CREDITS

@@ -10,3 +10,7 @@ Hannu Krosing <hannu@2ndQuadrant.com>
 Cédric Villemain <cedric@2ndquadrant.com>
 Charles Duffy <charles@dyfis.net>
 Daniel Farina <daniel@heroku.com>
+Shawn Ellis <shawn.ellis17@gmail.com>
+Jay Taylor <jay@jaytaylor.com>
+Christian Kruse <christian@2ndQuadrant.com>
+Krzysztof Gajdemski <songo@debian.org.pl>

HISTORY

@@ -1,4 +1,22 @@
-2.0beta 2012-07-27
+2.0stable 2014-01-30
+        Documentation fixes (Christian)
+        General refactoring, code quality improvements and stabilization work (Christian)
+        Added proper daemonizing (-d/--daemonize) (Christian)
+        Added PID file handling (-p/--pid-file) (Christian)
+        New config option: monitor_interval_secs (Christian)
+        New config option: retry_promote_interval (Christian)
+        New config option: logfile (Christian)
+        New config option: pg_bindir (Christian)
+        New config option: pgctl_options (Christian)
+
+2.0beta2 2013-12-19
+        Improve autofailover logic and algorithms (Jaime, Andres)
+        Ignore pg_log when cloning (Jaime)
+        Add timestamps to log line in stderr (Christian)
+        Correctly check wal_keep_segments (Jay Taylor)
+        Add a ssh_options parameter (Jay Taylor)
+
+2.0beta1 2012-07-27
         Make CLONE command try to make an exact copy including $PGDATA location (Cedric) 
         Add detection of master failure (Jaime)
         Add the notion of a witness server (Jaime)

Makefile

@@ -1,6 +1,6 @@
 #
 # Makefile
-# Copyright (c) 2ndQuadrant, 2010-2012
+# Copyright (c) 2ndQuadrant, 2010-2014
 
 repmgrd_OBJS = dbutils.o config.o repmgrd.o log.o strutil.o
 repmgr_OBJS = dbutils.o check_dir.o config.o repmgr.o log.o strutil.o
@@ -21,7 +21,8 @@ repmgr: $(repmgr_OBJS)
 	$(CC) $(CFLAGS) $(repmgr_OBJS) $(PG_LIBS) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o repmgr
 
 ifdef USE_PGXS
-PGXS := $(shell pg_config --pgxs)
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
 include $(PGXS)
 else
 subdir = contrib/repmgr
@@ -32,9 +33,13 @@ endif
 
 # XXX: Try to use PROGRAM construct (see pgxs.mk) someday. Right now
 # is overriding pgxs install.
-install:
+install: install_prog install_ext
+
+install_prog:
 	$(INSTALL_PROGRAM) repmgrd$(X) '$(DESTDIR)$(bindir)'
 	$(INSTALL_PROGRAM) repmgr$(X) '$(DESTDIR)$(bindir)'
+
+install_ext:
 	$(MAKE) -C sql install
 
 ifneq (,$(DATA)$(DATA_built))

README.rst

@@ -1085,7 +1085,7 @@ License and Contributions
 =========================
 
 repmgr is licensed under the GPL v3.  All of its code and documentation is
-Copyright 2010-2012, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+Copyright 2010-2014, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
 details.
 
 Main sponsorship of repmgr has been from 2ndQuadrant customers.

TODO

@@ -1,21 +1,18 @@
 Known issues in repmgr
 ======================
 
-* The check for whether ``wal_keep_segments`` is considered large enough
-  does a string comparison rather than an integer one.  It can give both
-  false positive (setting is large enough but flagged as too small) and
-  false negative (setting is too small but not noted as such) errors.
-
 * When running repmgr against a remote machine, operations that start
   the database server using the ``pg_ctl`` command may accidentally
   terminate after their associated ssh session ends.
 
-* 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
+* Timeline increases when promoting a standby
-  a working ssh connection to the destination would help find
+
-  configuration errors before disturbing the database.
+* A better check which standby did receive most of the data
+
+* Make the fact that a standby may be delayed a factor in the voting
+  algorithm
+
+* include support for delayed standbys

autofailover_quick_setup.rst

@@ -1,213 +1,225 @@
-=====================================================
+=====================================================
- PostgreSQL Automatic Fail-Over - User Documentation
+ PostgreSQL Automatic Fail-Over - User Documentation
-=====================================================
+=====================================================
-
+
-Automatic Failover
+Automatic Failover
-==================
+==================
-
+
-repmgr allows setups for automatic failover when it detects the failure of the master node.
+repmgr allows setups for automatic failover when it detects the failure of the master node.
-Following is a quick setup for this.
+Following is a quick setup for this.
-
+
-Installation
+Installation
-============
+============
-
+
-For convenience, we define:
+For convenience, we define:
-
+
-  * node1 is the hostname fully qualified of the Master server, IP 192.168.1.10
+**node1**
-  * node2 is the hostname fully qualified of the Standby server, IP 192.168.1.11
+    is the hostname fully qualified of the Master server, IP 192.168.1.10
-  * witness is the hostname fully qualified of the server used for witness, IP 192.168.1.12
+**node2**
-
+    is the hostname fully qualified of the Standby server, IP 192.168.1.11
-:Note: It is not recommanded to use name defining status of a server like «masterserver»,
+**witness**
-       this is a name leading to confusion once a failover take place and the Master is
+    is the hostname fully qualified of the server used for witness, IP 192.168.1.12
-       now on the «standbyserver».
+
-
+**Note:** It is not recommanded to use name defining status of a server like «masterserver»,
-Summary
+this is a name leading to confusion once a failover take place and the Master is
--------
+now on the «standbyserver».
-
+
-2 PostgreSQL servers are involved in the replication.  Automatic fail-over need
+Summary
-to vote to decide what server it should promote, thus an odd number is required
+-------
-and a witness-repmgrd is installed in a third server where it uses a PostgreSQL
+
-cluster to communicate with other repmgrd daemons.
+2 PostgreSQL servers are involved in the replication.  Automatic fail-over need
-
+to vote to decide what server it should promote, thus an odd number is required
-1. Install PostgreSQL in all the servers involved (including the server used for
+and a witness-repmgrd is installed in a third server where it uses a PostgreSQL
-witness)
+cluster to communicate with other repmgrd daemons.
-2. Install repmgr in all the servers involved (including the server used for witness)
+
-3. Configure the Master PostreSQL
+1. Install PostgreSQL in all the servers involved (including the server used for
-4. Clone the Master to the Standby using "repmgr standby clone" command
+   witness)
-5. Configure repmgr in all the servers involved (including the server used for witness)
+
-6. Register Master and Standby nodes
+2. Install repmgr in all the servers involved (including the server used for witness)
-7. Initiate witness server
+
-8. Start the repmgrd daemons in all nodes
+3. Configure the Master PostreSQL
-
+
-:Note: A complete Hight-Availability design need at least 3 servers to still have
+4. Clone the Master to the Standby using "repmgr standby clone" command
-       a backup node after a first failure.
+
-
+5. Configure repmgr in all the servers involved (including the server used for witness)
-Install PostgreSQL
+
-------------------
+6. Register Master and Standby nodes
-
+
-You can install PostgreSQL using any of the recommended methods. You should ensure
+7. Initiate witness server
-it's 9.0 or superior.
+
-
+8. Start the repmgrd daemons in all nodes
-Install repmgr
+
---------------
+**Note** A complete Hight-Availability design need at least 3 servers to still have
-
+a backup node after a first failure.
-Install repmgr following the steps in the README.
+
-
+Install PostgreSQL
-Configure PostreSQL
+------------------
--------------------
+
-
+You can install PostgreSQL using any of the recommended methods. You should ensure
-Log in node1.
+it's 9.0 or superior.
-
+
-Edit the file postgresql.conf and modify the parameters::
+Install repmgr
-
+--------------
-  listen_addresses='*'
+
-  wal_level = 'hot_standby'
+Install repmgr following the steps in the README.
-  archive_mode = on
+
-  archive_command = 'cd .'	 # we can also use exit 0, anything that 
+Configure PostreSQL
-                             # just does nothing
+-------------------
-  max_wal_senders = 10
+
-  wal_keep_segments = 5000   # 80 GB required on pg_xlog
+Log in node1.
-  hot_standby = on
+
-  shared_preload_libraries = 'repmgr_funcs'
+Edit the file postgresql.conf and modify the parameters::
-
+
-Edit the file pg_hba.conf and add lines for the replication::
+  listen_addresses='*'
-
+  wal_level = 'hot_standby'
-  host     repmgr           repmgr      127.0.0.1/32            trust
+  archive_mode = on
-  host     repmgr           repmgr      192.168.1.10/30         trust
+  archive_command = 'cd .'	 # we can also use exit 0, anything that 
-  host     replication      all         192.168.1.10/30         trust
+                             # just does nothing
-
+  max_wal_senders = 10
-:Note: It is also possible to use a password authentication (md5), .pgpass file
+  wal_keep_segments = 5000   # 80 GB required on pg_xlog
-       should be edited to allow connection between each node.
+  hot_standby = on
-
+  shared_preload_libraries = 'repmgr_funcs'
-Create the user and database to manage replication::
+
-
+Edit the file pg_hba.conf and add lines for the replication::
-  su - postgres
+
-  createuser -s repmgr
+  host     repmgr           repmgr      127.0.0.1/32            trust
-  createdb -O repmgr repmgr
+  host     repmgr           repmgr      192.168.1.10/30         trust
-  psql -f /usr/share/postgresql/9.0/contrib/repmgr_funcs.sql repmgr
+  host     replication      all         192.168.1.10/30         trust
-
+
-Restart the PostgreSQL server::
+**Note:** It is also possible to use a password authentication (md5), .pgpass file
-
+should be edited to allow connection between each node.
-  pg_ctl -D $PGDATA restart
+
-
+Create the user and database to manage replication::
-And check everything is fine in the server log.
+
-
+  su - postgres
-Create the ssh-key for the postgres user and copy it to other servers::
+  createuser -s repmgr
-
+  createdb -O repmgr repmgr
-  su - postgres
+  psql -f /usr/share/postgresql/9.0/contrib/repmgr_funcs.sql repmgr
-  ssh-keygen             # /!\ do not use a passphrase /!\
+
-  cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
+Restart the PostgreSQL server::
-  chmod 600 ~/.ssh/authorized_keys
+
-  exit
+  pg_ctl -D $PGDATA restart
-  rsync -avz ~postgres/.ssh/authorized_keys node2:~postgres/.ssh/
+
-  rsync -avz ~postgres/.ssh/authorized_keys witness:~postgres/.ssh/
+And check everything is fine in the server log.
-  rsync -avz ~postgres/.ssh/id_rsa* node2:~postgres/.ssh/
+
-  rsync -avz ~postgres/.ssh/id_rsa* witness:~postgres/.ssh/
+Create the ssh-key for the postgres user and copy it to other servers::
-
+
-Clone Master
+  su - postgres
-------------
+  ssh-keygen             # /!\ do not use a passphrase /!\
-
+  cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
-Log in node2.
+  chmod 600 ~/.ssh/authorized_keys
-
+  exit
-Clone the node1 (the current Master)::
+  rsync -avz ~postgres/.ssh/authorized_keys node2:~postgres/.ssh/
-
+  rsync -avz ~postgres/.ssh/authorized_keys witness:~postgres/.ssh/
-  su - postgres
+  rsync -avz ~postgres/.ssh/id_rsa* node2:~postgres/.ssh/
-  repmgr -d repmgr -U repmgr standby clone node1
+  rsync -avz ~postgres/.ssh/id_rsa* witness:~postgres/.ssh/
-
+
-Start the PostgreSQL server::
+Clone Master
-
+------------
-  pg_ctl -D $PGDATA start
+
-
+Log in node2.
-And check everything is fine in the server log.
+
-
+Clone the node1 (the current Master)::
-Configure repmgr
+
-----------------
+  su - postgres
-
+  repmgr -d repmgr -U repmgr -h node1 standby clone 
-Log in each server and configure repmgr by editing the file
+
-/etc/repmgr/repmgr.conf::
+Start the PostgreSQL server::
-
+
-  cluster=my_cluster
+  pg_ctl -D $PGDATA start
-  node=1
+
-  node_name=earth
+And check everything is fine in the server log.
-  conninfo='host=192.168.1.10 dbname=repmgr user=repmgr'
+
-  master_response_timeout=60
+Configure repmgr
-  reconnect_attempts=6
+----------------
-  reconnect_interval=10
+
-  failover=automatic
+Log in each server and configure repmgr by editing the file
-  promote_command='promote_command.sh'
+/etc/repmgr/repmgr.conf::
-  follow_command='repmgr standby follow -f /etc/repmgr/repmgr.conf'
+
-
+  cluster=my_cluster
-* *cluster* is the name of the current replication.
+  node=1
-* *node* is the number of the current node (1, 2 or 3 in the current example).
+  node_name=earth
-* *node_name* is an identifier for every node.
+  conninfo='host=192.168.1.10 dbname=repmgr user=repmgr'
-* *conninfo* is used to connect to the local PostgreSQL server (where the configuration file is) from any node. In the witness server configuration it is needed to add a 'port=5499' to the conninfo.
+  master_response_timeout=60
-* *master_response_timeout* is the maximum amount of time we are going to wait before deciding the master has died and start failover procedure.
+  reconnect_attempts=6
-* *reconnect_attempts* is the number of times we will try to reconnect to master after a failure has been detected and before start failover procedure.
+  reconnect_interval=10
-* *reconnect_interval* is the amount of time between retries to reconnect to master after a failure has been detected and before start failover procedure.
+  failover=automatic
-* *failover* configure behavior : *manual* or *automatic*.
+  promote_command='promote_command.sh'
-* *promote_command* the command executed to do the failover (including the PostgreSQL failover itself). The command must return 0 on success.
+  follow_command='repmgr standby follow -f /etc/repmgr/repmgr.conf'
-* *follow_command* the command executed to address the current standby to another Master. The command must return 0 on success.
+
-
+**cluster**
-Register Master and Standby
+    is the name of the current replication.
----------------------------
+**node**
-
+    is the number of the current node (1, 2 or 3 in the current example).
-Log in node1.
+**node_name**
-
+    is an identifier for every node.
-Register the node as Master::
+**conninfo**
-
+    is used to connect to the local PostgreSQL server (where the configuration file is) from any node. In the witness server configuration it is needed to add a 'port=5499' to the conninfo.
-  su - postgres
+**master_response_timeout**
-  repmgr -f /etc/repmgr/repmgr.conf master register
+    is the maximum amount of time we are going to wait before deciding the master has died and start failover procedure.
-
+**reconnect_attempts**
-Log in node2.
+    is the number of times we will try to reconnect to master after a failure has been detected and before start failover procedure.
-
+**reconnect_interval**
-Register the node as Standby::
+    is the amount of time between retries to reconnect to master after a failure has been detected and before start failover procedure.
-
+**failover**
-  su - postgres
+    configure behavior: *manual* or *automatic*.
-  repmgr -f /etc/repmgr/repmgr.conf standby register
+**promote_command**
-
+    the command executed to do the failover (including the PostgreSQL failover itself). The command must return 0 on success.
-Initialize witness server
+**follow_command**
--------------------------
+    the command executed to address the current standby to another Master. The command must return 0 on success.
-
+
-Log in witness.
+Register Master and Standby
-
+---------------------------
-Initialize the witness server::
+
-
+Log in node1.
-  su - postgres
+
-  repmgr -d repmgr -U repmgr -h 192.168.1.10 -D $WITNESS_PGDATA -f /etc/repmgr/repmgr.conf witness create node1
+Register the node as Master::
-
+
-It needs information to connect to the master to copy the configuration of the cluster, also it needs to know where it should initialize it's own $PGDATA.
+  su - postgres
-As part of the procees it also ask for the superuser password so it can connect when needed.
+  repmgr -f /etc/repmgr/repmgr.conf master register
-
+
-Start the repmgrd daemons
+Log in node2. Register it as a standby::
--------------------------
+
-
+  su - postgres
-Log in node2 and witness.
+  repmgr -f /etc/repmgr/repmgr.conf standby register
-
+
-  su - postgres
+Initialize witness server
-  repmgrd -f /etc/repmgr/repmgr.conf > /var/log/postgresql/repmgr.log 2>&1
+-------------------------
-
+
-:Note: The Master does not need a repmgrd daemon.
+Log in witness.
-
+
-
+Initialize the witness server::
-Suspend Automatic behavior
+
-==========================
+  su - postgres
-
+  repmgr -d repmgr -U repmgr -h 192.168.1.10 -D $WITNESS_PGDATA -f /etc/repmgr/repmgr.conf witness create
-Edit the repmgr.conf of the node to remove from automatic processing and change::
+
-
+It needs information to connect to the master to copy the configuration of the cluster, also it needs to know where it should initialize it's own $PGDATA.
-	failover=manual
+As part of the procees it also ask for the superuser password so it can connect when needed.
-
+
-Then, signal repmgrd daemon::
+Start the repmgrd daemons
-
+-------------------------
-	su - postgres
+
-	kill -HUP `pidoff repmgrd`
+Log in node2 and witness.
-
+
-TODO : -HUP configuration update is not implemented and it should check its
+	su - postgres
-	   configuration file  against its configuration in DB, updating
+	repmgrd -f /etc/repmgr/repmgr.conf > /var/log/postgresql/repmgr.log 2>&1
-	   accordingly the SQL conf (especialy the failover manual or auto)
+
-	   this allow witness-standby and standby-not-promotable features
+**Note:** The Master does not need a repmgrd daemon.
-	   and simpler usage of the tool ;)
+
-
+
-Usage
+Suspend Automatic behavior
-=====
+==========================
-
+
-The repmgr documentation is in the README file (how to build, options, etc.)
+Edit the repmgr.conf of the node to remove from automatic processing and change::
+
+	failover=manual
+
+Then, signal repmgrd daemon::
+
+	su - postgres
+	kill -HUP `pidoff repmgrd`
+
+Usage
+=====
+
+The repmgr documentation is in the README file (how to build, options, etc.)

check_dir.c

@@ -1,6 +1,6 @@
 /*
  * check_dir.c - Directories management functions
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -127,10 +127,10 @@ mkdir_p(char *path, mode_t omode)
 {
 	struct stat sb;
 	mode_t		numask,
-	oumask;
+	            oumask;
 	int			first,
-	last,
+	            last,
-	retval;
+	            retval;
 	char	   *p;
 
 	p = path;
@@ -225,12 +225,12 @@ is_pg_dir(char *dir)
 	struct stat	 sb;
 	int		r;
 
-	// test pgdata
+	/* test pgdata */
 	xsnprintf(path, buf_sz, "%s/PG_VERSION", dir);
 	if (stat(path, &sb) == 0)
 		return true;
 
-	// test tablespace dir
+	/* test tablespace dir */
 	sprintf(path, "ls %s/PG_*/ -I*", dir);
 	r = system(path);
 	if (r == 0)
@@ -256,7 +256,7 @@ create_pgdir(char *dir, bool force)
 		{
 			log_err(_("couldn't create directory \"%s\"...\n"),
 			        dir);
-			exit(ERR_BAD_CONFIG);
+			return false;
 		}
 		break;
 	case 1:
@@ -268,7 +268,7 @@ create_pgdir(char *dir, bool force)
 		{
 			log_err(_("could not change permissions of directory \"%s\": %s\n"),
 			        dir, strerror(errno));
-			exit(ERR_BAD_CONFIG);
+			return false;
 		}
 		break;
 	case 2:
@@ -293,7 +293,7 @@ create_pgdir(char *dir, bool force)
 			              "If you are sure you want to clone here, "
 			              "please check there is no PostgreSQL server "
 			              "running and use the --force option\n"));
-			exit(ERR_BAD_CONFIG);
+			return false;
 		}
 
 		return false;
@@ -301,7 +301,7 @@ create_pgdir(char *dir, bool force)
 		/* Trouble accessing directory */
 		log_err(_("could not access directory \"%s\": %s\n"),
 		        dir, strerror(errno));
-		exit(ERR_BAD_CONFIG);
+		return false;
 	}
 	return true;
 }

check_dir.h

@@ -1,6 +1,6 @@
 /*
  * check_dir.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  * 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

config.c

@@ -1,6 +1,6 @@
 /*
  * config.c - Functions to parse the config file
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -41,6 +41,9 @@ parse_config(const char *config_file, t_configuration_options *options)
 	memset(options->promote_command, 0, sizeof(options->promote_command));
 	memset(options->follow_command, 0, sizeof(options->follow_command));
 	memset(options->rsync_options, 0, sizeof(options->rsync_options));
+	memset(options->ssh_options, 0, sizeof(options->ssh_options));
+	memset(options->pg_bindir, 0, sizeof(options->pg_bindir));
+	memset(options->pgctl_options, 0, sizeof(options->pgctl_options));
 
 	/* if nothing has been provided defaults to 60 */
 	options->master_response_timeout = 60;
@@ -49,6 +52,9 @@ parse_config(const char *config_file, t_configuration_options *options)
 	options->reconnect_attempts = 6;
 	options->reconnect_intvl = 10;
 
+	options->monitor_interval_secs = 2;
+	options->retry_promote_interval_secs = 300;
+
 	/*
 	 * Since some commands don't require a config file at all, not
 	 * having one isn't necessarily a problem.
@@ -78,6 +84,8 @@ parse_config(const char *config_file, t_configuration_options *options)
 			strncpy (options->conninfo, value, MAXLEN);
 		else if (strcmp(name, "rsync_options") == 0)
 			strncpy (options->rsync_options, value, QUERY_STR_LEN);
+		else if (strcmp(name, "ssh_options") == 0)
+			strncpy (options->ssh_options, value, QUERY_STR_LEN);
 		else if (strcmp(name, "loglevel") == 0)
 			strncpy (options->loglevel, value, MAXLEN);
 		else if (strcmp(name, "logfacility") == 0)
@@ -111,6 +119,16 @@ parse_config(const char *config_file, t_configuration_options *options)
 			options->reconnect_attempts = atoi(value);
 		else if (strcmp(name, "reconnect_interval") == 0)
 			options->reconnect_intvl = atoi(value);
+		else if (strcmp(name, "pg_bindir") == 0)
+			strncpy (options->pg_bindir, value, MAXLEN);
+		else if (strcmp(name, "pg_ctl_options") == 0)
+			strncpy (options->pgctl_options, value, MAXLEN);
+		else if (strcmp(name, "logfile") == 0)
+			strncpy(options->logfile, value, MAXLEN);
+		else if (strcmp(name, "monitor_interval_secs") == 0)
+			options->monitor_interval_secs = atoi(value);
+		else if (strcmp(name, "retry_promote_interval_secs") == 0)
+			options->retry_promote_interval_secs = atoi(value);
 		else
 			log_warning(_("%s/%s: Unknown name/value pair!\n"), name, value);
 	}
@@ -148,6 +166,12 @@ parse_config(const char *config_file, t_configuration_options *options)
 		log_err(_("Reconnect intervals must be zero or greater. Check the configuration file.\n"));
 		exit(ERR_BAD_CONFIG);
 	}
+
+	if (*options->pg_bindir == '\0')
+	{
+		log_err(_("pg_bindir config value not found. Check the configuration file.\n"));
+		exit(ERR_BAD_CONFIG);
+	}
 }
 
 
@@ -167,7 +191,9 @@ trim (char *s)
 		++s1;
 
 	/* Copy finished string */
-	strcpy (s, s1);
+	memmove (s, s1, s2 - s1);
+	s[s2 - s1 + 1] = '\0';
+
 	return s;
 }
 
@@ -218,49 +244,49 @@ reload_configuration(char *config_file, t_configuration_options *orig_options)
 	parse_config(config_file, &new_options);
 	if (new_options.node == -1)
 	{
-		log_warning(_("\nCannot load new configuration, will keep current one.\n"));
+		log_warning(_("Cannot load new configuration, will keep current one.\n"));
 		return false;
 	}
 
 	if (strcmp(new_options.cluster_name, orig_options->cluster_name) != 0)
 	{
-		log_warning(_("\nCannot change cluster name, will keep current configuration.\n"));
+		log_warning(_("Cannot change cluster name, will keep current configuration.\n"));
 		return false;
 	}
 
 	if (new_options.node != orig_options->node)
 	{
-		log_warning(_("\nCannot change node number, will keep current configuration.\n"));
+		log_warning(_("Cannot change node number, will keep current configuration.\n"));
 		return false;
 	}
 
-	if (new_options.node_name != orig_options->node_name)
+	if (strcmp(new_options.node_name, orig_options->node_name) != 0)
 	{
-		log_warning(_("\nCannot change standby name, will keep current configuration.\n"));
+		log_warning(_("Cannot change standby name, will keep current configuration.\n"));
 		return false;
 	}
 
 	if (new_options.failover != MANUAL_FAILOVER && new_options.failover != AUTOMATIC_FAILOVER)
 	{
-		log_warning(_("\nNew value for failover is not valid. Should be MANUAL or AUTOMATIC.\n"));
+		log_warning(_("New value for failover is not valid. Should be MANUAL or AUTOMATIC.\n"));
 		return false;
 	}
 
 	if (new_options.master_response_timeout <= 0)
 	{
-		log_warning(_("\nNew value for master_response_timeout is not valid. Should be greater than zero.\n"));
+		log_warning(_("New value for master_response_timeout is not valid. Should be greater than zero.\n"));
 		return false;
 	}
 
 	if (new_options.reconnect_attempts < 0)
 	{
-		log_warning(_("\nNew value for reconnect_attempts is not valid. Should be greater or equal than zero.\n"));
+		log_warning(_("New value for reconnect_attempts is not valid. Should be greater or equal than zero.\n"));
 		return false;
 	}
 
 	if (new_options.reconnect_intvl < 0)
 	{
-		log_warning(_("\nNew value for reconnect_interval is not valid. Should be greater or equal than zero.\n"));
+		log_warning(_("New value for reconnect_interval is not valid. Should be greater or equal than zero.\n"));
 		return false;
 	}
 
@@ -268,7 +294,7 @@ reload_configuration(char *config_file, t_configuration_options *orig_options)
 	conn = establishDBConnection(new_options.conninfo, false);
 	if (!conn || (PQstatus(conn) != CONNECTION_OK))
 	{
-		log_warning(_("\nconninfo string is not valid, will keep current configuration.\n"));
+		log_warning(_("conninfo string is not valid, will keep current configuration.\n"));
 		return false;
 	}
 	PQfinish(conn);
@@ -283,6 +309,7 @@ reload_configuration(char *config_file, t_configuration_options *orig_options)
 	strcpy(orig_options->promote_command, new_options.promote_command);
 	strcpy(orig_options->follow_command, new_options.follow_command);
 	strcpy(orig_options->rsync_options, new_options.rsync_options);
+	strcpy(orig_options->ssh_options, new_options.ssh_options);
 	orig_options->master_response_timeout = new_options.master_response_timeout;
 	orig_options->reconnect_attempts = new_options.reconnect_attempts;
 	orig_options->reconnect_intvl = new_options.reconnect_intvl;

config.h

@@ -1,6 +1,6 @@
 /*
  * config.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -36,11 +36,19 @@ typedef struct
 	char loglevel[MAXLEN];
 	char logfacility[MAXLEN];
 	char rsync_options[QUERY_STR_LEN];
+	char ssh_options[QUERY_STR_LEN];
 	int  master_response_timeout;
 	int  reconnect_attempts;
 	int  reconnect_intvl;
+	char pg_bindir[MAXLEN];
+	char pgctl_options[MAXLEN];
+	char logfile[MAXLEN];
+	int monitor_interval_secs;
+	int retry_promote_interval_secs;
 } t_configuration_options;
 
+#define T_CONFIGURATION_OPTIONS_INITIALIZER { "", -1, "", MANUAL_FAILOVER, -1, "", "", "", "", "", "", "", -1, -1, -1, "", "", "", 0, 0 }
+
 void parse_config(const char *config_file, t_configuration_options *options);
 void parse_line(char *buff, char *name, char *value);
 char *trim(char *s);

dbutils.c

@@ -1,6 +1,6 @@
 /*
  * dbutils.c - Database connection/management functions
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -18,6 +18,8 @@
  */
 
 #include <unistd.h>
+#include <time.h>
+#include <sys/time.h>
 
 #include "repmgr.h"
 #include "strutil.h"
@@ -71,25 +73,22 @@ establishDBConnectionByParams(const char *keywords[], const char *values[],const
 	return conn;
 }
 
-bool
+int
 is_standby(PGconn *conn)
 {
 	PGresult   *res;
-	bool		result = false;
+	int			result = 0;
 
 	res = PQexec(conn, "SELECT pg_is_in_recovery()");
 
-	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	if (res == NULL || PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Can't query server mode: %s"),
 		        PQerrorMessage(conn));
-		PQclear(res);
+		result = -1;
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
 	}
-
+	else if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
-	if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
+		result = 1;
-		result = true;
 
 	PQclear(res);
 	return result;
@@ -97,11 +96,11 @@ is_standby(PGconn *conn)
 
 
 
-bool
+int
 is_witness(PGconn *conn, char *schema, char *cluster, int node_id)
 {
 	PGresult   *res;
-	bool		result = false;
+	int			result = 0;
 	char		sqlquery[QUERY_STR_LEN];
 
 	sqlquery_snprintf(sqlquery, "SELECT witness from %s.repl_nodes where cluster = '%s' and id = %d",
@@ -110,13 +109,10 @@ is_witness(PGconn *conn, char *schema, char *cluster, int node_id)
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Can't query server mode: %s"), PQerrorMessage(conn));
-		PQclear(res);
+		result = -1;
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
 	}
-
+	else if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
-	if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
+		result = 1;
-		result = true;
 
 	PQclear(res);
 	return result;
@@ -138,7 +134,7 @@ is_pgup(PGconn *conn, int timeout)
 		{
 			if (twice)
 				return false;
-			PQreset(conn);  // reconnect
+			PQreset(conn);  /* reconnect */
 			twice = true;
 		}
 		else
@@ -146,15 +142,16 @@ is_pgup(PGconn *conn, int timeout)
 			/*
 			* Send a SELECT 1 just to check if the connection is OK
 			*/
-			CancelQuery(conn, timeout);
+			if (!CancelQuery(conn, timeout))
+				goto failed;
 			if (wait_connection_availability(conn, timeout) != 1)
 				goto failed;
 
 			sqlquery_snprintf(sqlquery, "SELECT 1");
 			if (PQsendQuery(conn, sqlquery) == 0)
 			{
-				log_warning(_("PQsendQuery: Query could not be sent to primary. %s\n"), 
+				log_warning(_("PQsendQuery: Query could not be sent to primary. %s\n"),
-								PQerrorMessage(conn));
+				            PQerrorMessage(conn));
 				goto failed;
 			}
 			if (wait_connection_availability(conn, timeout) != 1)
@@ -163,10 +160,10 @@ is_pgup(PGconn *conn, int timeout)
 			break;
 
 failed:
-			// we need to retry, because we might just have loose the connection once
+			/* we need to retry, because we might just have loose the connection once */
 			if (twice)
 				return false;
-			PQreset(conn);  // reconnect
+			PQreset(conn);  /* reconnect */
 			twice = true;
 		}
 	}
@@ -197,8 +194,7 @@ pg_version(PGconn *conn, char* major_version)
 		log_err(_("Version check PQexec failed: %s"),
 		        PQerrorMessage(conn));
 		PQclear(res);
-		PQfinish(conn);
+		return NULL;
-		exit(ERR_DB_QUERY);
 	}
 
 	major_version1 = atoi(PQgetvalue(res, 0, 0));
@@ -219,12 +215,13 @@ pg_version(PGconn *conn, char* major_version)
 }
 
 
-bool
+int
-guc_setted(PGconn *conn, const char *parameter, const char *op,
+guc_set(PGconn *conn, const char *parameter, const char *op,
            const char *value)
 {
 	PGresult	*res;
 	char		sqlquery[QUERY_STR_LEN];
+	int			retval = 1;
 
 	sqlquery_snprintf(sqlquery, "SELECT true FROM pg_settings "
 	                  " WHERE name = '%s' AND setting %s '%s'",
@@ -235,18 +232,49 @@ guc_setted(PGconn *conn, const char *parameter, const char *op,
 	{
 		log_err(_("GUC setting check PQexec failed: %s"),
 		        PQerrorMessage(conn));
-		PQclear(res);
+		retval = -1;
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
 	}
-	if (PQntuples(res) == 0)
+	else if (PQntuples(res) == 0)
 	{
-		PQclear(res);
+		retval = 0;
-		return false;
 	}
+
 	PQclear(res);
 
-	return true;
+	return retval;
+}
+
+/**
+ * Just like guc_set except with an extra parameter containing the name of
+ * the pg datatype so that the comparison can be done properly.
+ */
+int
+guc_set_typed(PGconn *conn, const char *parameter, const char *op, 
+                 const char *value, const char *datatype)
+{
+	PGresult	*res;
+	char		sqlquery[QUERY_STR_LEN];
+	int			retval = 1;
+
+	sqlquery_snprintf(sqlquery, "SELECT true FROM pg_settings "
+	                  " WHERE name = '%s' AND setting::%s %s '%s'::%s",
+	                  parameter, datatype, op, value, datatype);
+
+	res = PQexec(conn, sqlquery);
+	if (PQresultStatus(res) != PGRES_TUPLES_OK)
+	{
+		log_err(_("GUC setting check PQexec failed: %s"),
+		        PQerrorMessage(conn));
+		retval = -1;
+	}
+	else if (PQntuples(res) == 0)
+	{
+		retval = 0;
+	}
+
+	PQclear(res);
+
+	return retval;
 }
 
 
@@ -254,7 +282,7 @@ const char *
 get_cluster_size(PGconn *conn)
 {
 	PGresult	*res;
-	const char	*size;
+	const char	*size = NULL;
 	char		 sqlquery[QUERY_STR_LEN];
 
 	sqlquery_snprintf(
@@ -267,11 +295,12 @@ get_cluster_size(PGconn *conn)
 	{
 		log_err(_("Get cluster size PQexec failed: %s"),
 		        PQerrorMessage(conn));
-		PQclear(res);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
 	}
-	size = PQgetvalue(res, 0, 0);
+	else
+	{
+		size = PQgetvalue(res, 0, 0);
+	}
+
 	PQclear(res);
 	return size;
 }
@@ -332,8 +361,7 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 		log_err(_("Can't get nodes info: %s\n"),
 		        PQerrorMessage(standby_conn));
 		PQclear(res1);
-		PQfinish(standby_conn);
+		return NULL;
-		exit(ERR_DB_QUERY);
 	}
 
 	for (i = 0; i < PQntuples(res1); i++)
@@ -396,51 +424,99 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 
 /*
  * wait until current query finishes ignoring any results, this could be an async command
- * or a cancelation of a query 
+ * or a cancelation of a query
  * return 1 if Ok; 0 if any error ocurred; -1 if timeout reached
  */
 int
-wait_connection_availability(PGconn *conn, int timeout)
+wait_connection_availability(PGconn *conn, long long timeout)
 {
 	PGresult   *res;
+	fd_set      read_set;
+	int         sock = PQsocket(conn);
+	struct timeval tmout, before, after;
+	struct timezone tz;
 
-	while(timeout-- >= 0)
+	/* recalc to microseconds */
+	timeout *= 1000000;
+
+	while (timeout > 0)
 	{
 		if (PQconsumeInput(conn) == 0)
 		{
-			log_warning(_("PQconsumeInput: Query could not be sent to primary. %s\n"), 
+			log_warning(_("wait_connection_availability: could not receive data from connection. %s\n"),
-							PQerrorMessage(conn));
+						PQerrorMessage(conn));
 			return 0;
 		}
-	
+
 		if (PQisBusy(conn) == 0)
 		{
-			res = PQgetResult(conn);
+			do {
-			if (res == NULL)
+				res = PQgetResult(conn);
-				break;
+				PQclear(res);
-			PQclear(res);
+			} while(res != NULL);
+
+			break;
 		}
-		sleep(1);
+
+
+		tmout.tv_sec = 0;
+		tmout.tv_usec = 250000;
+
+		FD_ZERO(&read_set);
+		FD_SET(sock, &read_set);
+
+		gettimeofday(&before, &tz);
+		if (select(sock, &read_set, NULL, NULL, &tmout) == -1)
+		{
+			log_warning(
+				_("wait_connection_availability: select() returned with error: %s"),
+				strerror(errno));
+			return -1;
+		}
+		gettimeofday(&after, &tz);
+
+		timeout -= (after.tv_sec * 1000000 + after.tv_usec) -
+			(before.tv_sec * 1000000 + before.tv_usec);
 	}
+
+
 	if (timeout >= 0)
+	{
 		return 1;
-	else
+	}
-		return -1;
+
+	log_warning(_("wait_connection_availability: timeout reached"));
+	return -1;
 }
 
 
-void
+bool
 CancelQuery(PGconn *conn, int timeout)
 {
 	char errbuf[ERRBUFF_SIZE];
 	PGcancel *pgcancel;
 
-	wait_connection_availability(conn, timeout);
+	if (wait_connection_availability(conn, timeout) != 1)
+		return false;
 
 	pgcancel = PQgetCancel(conn);
 
-	if (!pgcancel || PQcancel(pgcancel, errbuf, ERRBUFF_SIZE) == 0)
+	if (pgcancel == NULL)
+		return false;
+
+	/*
+	 * PQcancel can only return 0 if socket()/connect()/send()
+ 	 * fails, in any of those cases we can assume something
+	 * bad happened to the connection
+	 */
+	if (PQcancel(pgcancel, errbuf, ERRBUFF_SIZE) == 0)
+	{
 		log_warning(_("Can't stop current query: %s\n"), errbuf);
+		PQfreeCancel(pgcancel);
+		return false;
+	}
 
 	PQfreeCancel(pgcancel);
+
+	return true;
 }

dbutils.h

@@ -1,6 +1,6 @@
 /*
  * dbutils.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -26,16 +26,19 @@ PGconn *establishDBConnection(const char *conninfo, const bool exit_on_error);
 PGconn *establishDBConnectionByParams(const char *keywords[],
                                       const char *values[],
                                       const bool exit_on_error);
-bool    is_standby(PGconn *conn);
+int     is_standby(PGconn *conn);
-bool    is_witness(PGconn *conn, char *schema, char *cluster, int node_id);
+int     is_witness(PGconn *conn, char *schema, char *cluster, int node_id);
 bool	is_pgup(PGconn *conn, int timeout);
 char   *pg_version(PGconn *conn, char* major_version);
-bool	guc_setted(PGconn *conn, const char *parameter, const char *op,
+int		guc_set(PGconn *conn, const char *parameter, const char *op,
-                const char *value);
+                   const char *value);
+int		guc_set_typed(PGconn *conn, const char *parameter, const char *op,
+                   const char *value, const char *datatype);
+
 const char	 *get_cluster_size(PGconn *conn);
 PGconn *getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
                             int *master_id, char *master_conninfo_out);
 
-int wait_connection_availability(PGconn *conn, int timeout);
+int wait_connection_availability(PGconn *conn, long long timeout);
-void CancelQuery(PGconn *conn, int timeout);
+bool CancelQuery(PGconn *conn, int timeout);
 #endif

debian/DEBIAN/control

@@ -1,9 +1,9 @@
 Package: repmgr-auto
-Version: 1.0-1
+Version: 2.0beta2
 Section: database
 Priority: optional
 Architecture: all
-Depends: rsync, postgresql-9.0
+Depends: rsync, postgresql-9.0 | postgresql-9.1 | postgresql-9.2 | postgresql-9.3
-Maintainer: Greg Smith <greg@2ndQuadrant.com>
+Maintainer: Jaime Casanova <jaime@2ndQuadrant.com>
 Description: PostgreSQL replication setup, magament and monitoring
  has two main executables

debian/repmgr.repmgrd.default

@@ -0,0 +1,14 @@
+#!/bin/sh
+# default settings for repmgrd. This file is source by /bin/sh from
+# /etc/init.d/repmgrd
+
+# Options for repmgrd
+REPMGRD_OPTS=""
+
+# repmgrd binary
+REPMGR_BIN="/usr/bin/repmgr"
+
+# pid file
+REPMGR_PIDFILE="/var/run/repmgrd.pid"
+
+

debian/repmgr.repmgrd.init

@@ -0,0 +1,48 @@
+#!/bin/sh
+### BEGIN INIT INFO
+# Provides:          repmgrd
+# Required-Start:    $local_fs $remote_fs $network $syslog $postgresql
+# Required-Stop:     $local_fs $remote_fs $network $syslog $postgresql
+# Should-Start:      $syslog $postgresql
+# Should-Start:      $syslog $postgresql
+# Default-Start:     2 3 4 5
+# Default-Stop:      0 1 6
+# Short-Description: Start/stop repmgrd
+### END INIT INFO
+
+set -e
+
+if test -f /etc/default/repmgrd; then
+    . /etc/default/repmgrd
+fi
+
+if [ -z "$REPMGRD_BIN" ]; then
+    REPMGRD_BIN="/usr/bin/repmgrd"
+fi
+
+if [ -z "$REPMGRD_PIDFILE" ]; then
+    REPMGRD_PIDFILE="/var/run/repmgrd.pid"
+fi
+
+test -x $REPMGRD_BIN || exit 0
+
+case "$1" in
+    start)
+        start-stop-daemon --start --quiet --make-pidfile --pidfile $REPMGRD_PIDFILE --exec $REPMGRD_BIN $REPMGRD_OPTS
+        ;;
+
+    stop)
+        start-stop-daemon --stop --oknodo --quiet --pidfile $REPMGRD_PIDFILE
+        ;;
+
+    restart)
+        $0 stop && $0 start || exit 1
+        ;;
+
+    *)
+        echo "Usage: $0 {start|stop|restart}"
+        exit 1
+        ;;
+esac
+
+exit 0

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -35,5 +35,6 @@
 #define ERR_STR_OVERFLOW 10
 #define ERR_FAILOVER_FAIL 11
 #define ERR_BAD_SSH	12
+#define ERR_SYS_FAILURE 13
 
 #endif	/* _ERRCODE_H_ */

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * This module is a set of methods for logging (currently only syslog)
  *
@@ -25,9 +25,11 @@
 
 #ifdef HAVE_SYSLOG
 #include <syslog.h>
-#include <stdarg.h>
 #endif
 
+#include <stdarg.h>
+#include <time.h>
+
 #include "log.h"
 
 #define DEFAULT_IDENT "repmgr"
@@ -37,13 +39,38 @@
 
 /* #define REPMGR_DEBUG */
 
+void stderr_log_with_level(const char *level_name, int level, const char *fmt, ...) {
+	size_t len = strlen(fmt);
+	char fmt1[len + 150];
+	time_t t;
+	struct tm *tm;
+	char buff[100];
+	va_list ap;
+
+	if(log_level >= level) {
+		time(&t);
+		tm = localtime(&t);
+
+		va_start(ap, fmt);
+
+		strftime(buff, 100, "[%Y-%m-%d %H:%M:%S]", tm);
+		snprintf(fmt1, len + 150, "%s [%s] %s", buff, level_name, fmt);
+		vfprintf(stderr, fmt1, ap);
+
+		va_end(ap);
+
+		fflush(stderr);
+	}
+}
+
+
 static int detect_log_level(const char* level);
 static int detect_log_facility(const char* facility);
 
 int log_type = REPMGR_STDERR;
 int log_level = LOG_NOTICE;
 
-bool logger_init(const char* ident, const char* level, const char* facility)
+bool logger_init(t_configuration_options *opts, const char* ident, const char* level, const char* facility)
 {
 
 	int l;
@@ -115,6 +142,11 @@ bool logger_init(const char* ident, const char* level, const char* facility)
 
 #endif
 
+	if (*opts->logfile)
+	{
+		freopen(opts->logfile, "a", stderr);
+	}
+
 	return true;
 
 }

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -25,15 +25,17 @@
 #define REPMGR_SYSLOG 1
 #define REPMGR_STDERR 2
 
+void stderr_log_with_level(const char *level_name, int level, const char *fmt, ...) __attribute__ ((format (PG_PRINTF_ATTRIBUTE, 3, 4)));
+
 /* Standard error logging */
-#define stderr_log_debug(...) if (log_level >= LOG_DEBUG) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_debug(...) stderr_log_with_level("DEBUG", LOG_DEBUG, __VA_ARGS__)
-#define stderr_log_info(...) if (log_level >= LOG_INFO) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_info(...)  stderr_log_with_level("INFO", LOG_INFO, __VA_ARGS__)
-#define stderr_log_notice(...) if (log_level >= LOG_NOTICE) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_notice(...) stderr_log_with_level("NOTICE", LOG_NOTICE, __VA_ARGS__)
-#define stderr_log_warning(...) if (log_level >= LOG_WARNING) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_warning(...) stderr_log_with_level("WARNING", LOG_WARNING, __VA_ARGS__)
-#define stderr_log_err(...) if (log_level >= LOG_ERR) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_err(...) stderr_log_with_level("ERROR", LOG_ERR, __VA_ARGS__)
-#define stderr_log_crit(...) if (log_level >= LOG_CRIT) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_crit(...) stderr_log_with_level("CRITICAL", LOG_CRIT, __VA_ARGS__)
-#define stderr_log_alert(...) if (log_level >= LOG_ALERT) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_alert(...) stderr_log_with_level("ALERT", LOG_ALERT, __VA_ARGS__)
-#define stderr_log_emerg(...) if (log_level >= LOG_EMERG) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_emerg(...) stderr_log_with_level("EMERGENCY", LOG_EMERG, __VA_ARGS__)
 
 #ifdef HAVE_SYSLOG
 
@@ -112,7 +114,7 @@
 
 /* Logger initialisation and shutdown */
 bool logger_shutdown(void);
-bool logger_init(const char* ident, const char* level, const char* facility);
+bool logger_init(t_configuration_options *opts, const char* ident, const char* level, const char* facility);
 void logger_min_verbose(int minimum);
 
 extern int log_type;

repmgr.conf.sample

@@ -11,7 +11,8 @@ node_name=standby2
 
 # Connection information
 conninfo='host=192.168.204.104'
-rsync_options=--archive --checksum --compress --progress --rsh=ssh
+rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
+ssh_options=-o "StrictHostKeyChecking no"
 
 # How many seconds we wait for master response before declaring master failure
 master_response_timeout=60
@@ -21,10 +22,10 @@ reconnect_attempts=6
 reconnect_interval=10
 
 # Autofailover options
-failover=automatic
+failover=manual
 priority=-1
-promote_command='repmgr promote'
+promote_command='repmgr standby promote -f /path/to/repmgr.conf'
-follow_command='repmgr follow'
+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
@@ -33,3 +34,29 @@ loglevel=NOTICE
 # Logging facility: possible values are STDERR or - for Syslog integration - one of LOCAL0, LOCAL1, ..., LOCAL7, USER
 # Default: STDERR
 logfacility=STDERR
+
+# path to pg_ctl executable
+pg_bindir=/usr/bin/
+
+#
+# you may add command line arguments for pg_ctl
+#
+# pg_ctl_options='-s'
+
+#
+# redirect stderr to a logfile
+#
+# logfile='/var/log/repmgr.log'
+
+#
+# change monitoring interval; default is 2s
+#
+# monitor_interval_secs=2
+
+#
+# change wait time for master; before we bail out and exit when the
+# master disappears, we wait 6 * retry_promote_interval_secs seconds;
+# by default this would be half an hour (since sleep_delay default
+# value is 300)
+#
+# retry_promote_interval_secs=300

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -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];
@@ -68,6 +69,6 @@ typedef struct
 	int keep_history;
 } t_runtime_options;
 
-#define SLEEP_MONITOR		2
+#define T_RUNTIME_OPTIONS_INITIALIZER { "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, false, "", "", 0 }
 
 #endif

repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  */
 

sql/Makefile

@@ -9,7 +9,8 @@ DATA=uninstall_repmgr_funcs.sql
 OBJS=repmgr_funcs.o
 
 ifdef USE_PGXS
-PGXS := $(shell pg_config --pgxs)
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
 include $(PGXS)
 else
 subdir = contrib/repmgr/sql

sql/repmgr_funcs.c

@@ -15,6 +15,7 @@
 #include "storage/shmem.h"
 #include "storage/spin.h"
 #include "utils/builtins.h"
+#include "utils/timestamp.h"
 
 /* same definition as the one in xlog_internal.h */
 #define MAXFNAMELEN 	64
@@ -28,6 +29,7 @@ typedef struct repmgrSharedState
 {
     LWLockId    lock;           		/* protects search/modification */
     char		location[MAXFNAMELEN];	/* last known xlog location */
+	TimestampTz last_updated;
 } repmgrSharedState;
 
 /* Links to shared memory state */
@@ -49,6 +51,12 @@ Datum repmgr_get_last_standby_location(PG_FUNCTION_ARGS);
 PG_FUNCTION_INFO_V1(repmgr_update_standby_location);
 PG_FUNCTION_INFO_V1(repmgr_get_last_standby_location);
 
+Datum repmgr_update_last_updated(PG_FUNCTION_ARGS);
+Datum repmgr_get_last_updated(PG_FUNCTION_ARGS);
+
+PG_FUNCTION_INFO_V1(repmgr_update_last_updated);
+PG_FUNCTION_INFO_V1(repmgr_get_last_updated);
+
 
 /*
  * Module load callback
@@ -187,3 +195,38 @@ repmgr_update_standby_location(PG_FUNCTION_ARGS)
 
 	PG_RETURN_BOOL(repmgr_set_standby_location(locationstr));
 }
+
+/* update and return last updated with current timestamp */
+Datum
+repmgr_update_last_updated(PG_FUNCTION_ARGS)
+{
+	TimestampTz last_updated = GetCurrentTimestamp();
+
+	/* Safety check... */
+	if (!shared_state)
+		PG_RETURN_NULL();
+
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+	shared_state->last_updated = last_updated;
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_TIMESTAMPTZ(last_updated);
+}
+
+
+/* get last updated timestamp */
+Datum
+repmgr_get_last_updated(PG_FUNCTION_ARGS)
+{
+	TimestampTz last_updated;
+
+    /* Safety check... */
+    if (!shared_state)
+        PG_RETURN_NULL();
+
+	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+	last_updated = shared_state->last_updated;
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_TIMESTAMPTZ(last_updated);
+}

sql/repmgr_funcs.sql.in

@@ -1,6 +1,6 @@
 /*
  * repmgr_function.sql
- * Copyright (c) 2ndQuadrant, 2010
+ * Copyright (c) 2ndQuadrant, 2010-2014
  *
  */
 
@@ -13,3 +13,11 @@ LANGUAGE C STRICT;
 CREATE FUNCTION repmgr_get_last_standby_location() RETURNS text
 AS 'MODULE_PATHNAME', 'repmgr_get_last_standby_location'
 LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgr_update_last_updated() RETURNS TIMESTAMP WITH TIME ZONE
+AS 'MODULE_PATHNAME', 'repmgr_update_last_updated'
+LANGUAGE C STRICT;
+
+CREATE FUNCTION repmgr_get_last_updated() RETURNS TIMESTAMP WITH TIME ZONE
+AS 'MODULE_PATHNAME', 'repmgr_get_last_updated'
+LANGUAGE C STRICT;

sql/uninstall_repmgr_funcs.sql

@@ -1,2 +1,11 @@
+/*
+ * uninstall_repmgr_funcs.sql
+ * Copyright (c) 2ndQuadrant, 2010-2014
+ *
+ */
+
 DROP FUNCTION repmgr_update_standby_location(text);
 DROP FUNCTION repmgr_get_last_standby_location();
+
+DROP FUNCTION repmgr_update_last_updated();
+DROP FUNCTION repmgr_get_last_updated();

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  * 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
@@ -25,7 +25,7 @@
 #include "log.h"
 #include "strutil.h"
 
-static int xvsnprintf(char *str, size_t size, const char *format, va_list ap);
+static int xvsnprintf(char *str, size_t size, const char *format, va_list ap) __attribute__ ((format (PG_PRINTF_ATTRIBUTE, 3, 0)));
 
 /* Add strnlen on platforms that don't have it, like OS X */
 #ifndef strnlen
@@ -44,7 +44,7 @@ xvsnprintf(char *str, size_t size, const char *format, va_list ap)
 
 	retval = vsnprintf(str, size, format, ap);
 
-	if (retval >= size)
+	if (retval >= (int)size)
 	{
 		log_err(_("Buffer of size not large enough to format entire string '%s'\n"),
 		        str);

strutil.h

@@ -1,6 +1,6 @@
 /*
  * strutil.h
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -31,9 +31,9 @@
 #define MAXCONNINFO		1024
 
 
-extern int xsnprintf(char *str, size_t size, const char *format, ...);
+extern int xsnprintf(char *str, size_t size, const char *format, ...) __attribute__ ((format (PG_PRINTF_ATTRIBUTE, 3, 4)));
-extern int sqlquery_snprintf(char *str, const char *format, ...);
+extern int sqlquery_snprintf(char *str, const char *format, ...) __attribute__ ((format (PG_PRINTF_ATTRIBUTE, 2, 3)));
-extern int maxlen_snprintf(char *str, const char *format, ...);
+extern int maxlen_snprintf(char *str, const char *format, ...) __attribute__ ((format (PG_PRINTF_ATTRIBUTE, 2, 3)));
 
 /* Add strnlen on platforms that don't have it, like OS X */
 #ifndef strnlen

uninstall_repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * uninstall_repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2014
  *
  */
 

version.h

@@ -1,4 +1,5 @@
 #ifndef _VERSION_H_
 #define _VERSION_H_
-#define REPMGR_VERSION "2.0beta1"
+
+#define REPMGR_VERSION "2.0RC1"
 #endif