Update version and history for minor release 2.0.2

Check introduced in dc0dfe9b56
was comparing the provided database name instead of the port.

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

@@ -1,5 +1,38 @@
-2.0beta 2012-07-27
-        Make CLONE command try to make an exact copy including $PGDATA location (Cedric) 
+2.0.2   2015-02-17
+        Add "--checksum" in rsync when using "--force" (Jaime)
+        Use createdb/createuser instead of psql (Jaime)
+        Fixes to witness creation and monitoring (wamonite)
+        Use default master port if none supplied (Martín)
+        Documentation fixes and improvements (Ian)
+
+2.0.1   2014-07-16
+        Documentation fixes and new QUICKSTART file (Ian)
+        Explicitly specify directories to ignore when cloning (Ian)
+        Fix log level for some log messages (Ian)
+        RHEL/CentOS specfile, init script and Makefile fixes (Nathan Van Overloop)
+        Debian init script and config file documentation fixes (József Kószó)
+        Typo fixes (Riegie Godwin Jeyaranchen, PriceChild)
+
+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)
         Add autofailover capabilities (Jaime)
@@ -26,7 +59,7 @@
 1.1.0   2011-03-09
         Make options -U, -R and -p not mandatory (Jaime)
 
-1.1.0b1 2011-02-24 
+1.1.0b1 2011-02-24
         Fix missing "--force" option in help (Greg Smith)
         Correct warning message for wal_keep_segments (Bas van Oostveen)
         Add Debian build/usage docs (Bas, Hannu Krosing, Cedric Villemain)

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
@@ -32,11 +33,27 @@ endif
 
 # XXX: Try to use PROGRAM construct (see pgxs.mk) someday. Right now
 # is overriding pgxs install.
-install:
-	$(INSTALL_PROGRAM) repmgrd$(X) '$(DESTDIR)$(bindir)'
-	$(INSTALL_PROGRAM) repmgr$(X) '$(DESTDIR)$(bindir)'
+install: install_prog install_ext
+
+install_prog:
+	mkdir -p '$(DESTDIR)$(bindir)'
+	$(INSTALL_PROGRAM) repmgrd$(X) '$(DESTDIR)$(bindir)/'
+	$(INSTALL_PROGRAM) repmgr$(X) '$(DESTDIR)$(bindir)/'
+
+install_ext:
 	$(MAKE) -C sql install
 
+install_rhel:
+	mkdir -p '$(DESTDIR)/etc/init.d/'
+	$(INSTALL_PROGRAM) RHEL/repmgrd.init '$(DESTDIR)/etc/init.d/repmgrd'
+	mkdir -p '$(DESTDIR)/etc/sysconfig/'
+	$(INSTALL_PROGRAM) RHEL/repmgrd.sysconfig '$(DESTDIR)/etc/sysconfig/repmgrd'
+	mkdir -p '$(DESTDIR)/etc/repmgr/'
+	$(INSTALL_PROGRAM) repmgr.conf.sample '$(DESTDIR)/etc/repmgr/'
+	mkdir -p '$(DESTDIR)/usr/bin/'
+	$(INSTALL_PROGRAM) repmgrd$(X) '$(DESTDIR)/usr/bin/'
+	$(INSTALL_PROGRAM) repmgr$(X) '$(DESTDIR)/usr/bin/'
+
 ifneq (,$(DATA)$(DATA_built))
 	@for file in $(addprefix $(srcdir)/, $(DATA)) $(DATA_built); do \
 	  echo "$(INSTALL_DATA) $$file '$(DESTDIR)$(datadir)/$(datamoduledir)'"; \
@@ -62,3 +79,4 @@ deb: repmgrd repmgr
 	mv debian.deb ../postgresql-repmgr-9.0_1.0.0.deb
 	rm -rf ./debian/usr
 
+

QUICKSTART.md

@@ -0,0 +1,292 @@
+repmgr: Quickstart guide
+========================
+
+repmgr is an open-source tool suite for mananaging replication and failover
+among multiple PostgreSQL server nodes. It enhances PostgreSQL's built-in
+hot-standby capabilities with a set of administration tools for monitoring
+replication, setting up standby servers and performing failover/switchover
+operations.
+
+This quickstart guide assumes you are familiar with PostgreSQL replication
+setup and Linux/UNIX system administration. For a more detailed tutorial
+covering setup on a variety of different systems, see the README.rst file.
+
+Conceptual Overview
+-------------------
+
+repmgr provides two binaries:
+
+ - `repmgr`: a command-line client to manage replication and repmgr configuration
+ - `repmgrd`: an optional daemon process which runs on standby nodes to monitor
+   replication and node status
+
+Each PostgreSQL node requires a repmgr configuration file; additionally
+it must be "registered" using the repmgr command-line client. repmgr stores
+information about managed nodes in a custom schema on the node's current master
+database.
+
+
+Requirements
+------------
+
+repmgr works with PostgreSQL 9.0 and later. All server nodes must be running the
+same PostgreSQL major version, and preferably should be running the same minor
+version.
+
+repmgr will work on any Linux or UNIX-like environment capable of running
+PostgreSQL. rsync must also be installed.
+
+
+Installation
+------------
+
+repmgr must be installed on each PostgreSQL server node.
+
+* Packages
+ - RPM packages for RedHat-based distributions are available from PGDG
+ - Debian/Ubuntu provide .deb packages.
+
+  It is also possible to build .deb packages directly from the repmgr source;
+  see README.rst for further details.
+
+* Source installation
+ - repmgr source code is hosted at github (https://github.com/2ndQuadrant/repmgr);
+   tar.gz files can be downloaded from https://github.com/2ndQuadrant/repmgr/releases .
+
+   repmgr can be built easily using PGXS:
+
+   sudo make USE_PGXS=1 install
+
+
+Configuration
+-------------
+
+### Server configuration
+
+Password-less SSH logins must be enabled for the database system user (typically `postgres`)
+between all server nodes to enable repmgr to copy required files.
+
+### PostgreSQL configuration
+
+The master PostgreSQL node needs to be configured for replication with the
+following settings:
+
+	wal_level = 'hot_standby'      # minimal, archive, hot_standby, or logical
+	archive_mode = on              # allows archiving to be done
+	archive_command = 'cd .'       # command to use to archive a logfile segment
+	max_wal_senders = 10           # max number of walsender processes
+	wal_keep_segments = 5000       # in logfile segments, 16MB each; 0 disables
+	hot_standby = on               # "on" allows queries during recovery
+
+Note that repmgr expects a default of 5000 wal_keep_segments, although this
+value can be overridden when executing the `repmgr` client.
+
+Additionally, repmgr requires a dedicated PostgreSQL superuser account
+and a database in which to store monitoring and replication data. The repmgr
+user account will also be used for replication connections from the standby,
+so a seperate replication user with the `REPLICATION` privilege is not required.
+The database can in principle be any database, including the default `postgres`
+one, however it's probably advisable to create a dedicated database for repmgr
+usage.
+
+
+### repmgr configuration
+
+Each PostgreSQL node requires a repmgr configuration file containing
+identification and database connection information:
+
+  cluster=test
+  node=1
+  node_name=node1
+  conninfo='host=repmgr_node1 user=repmgr_usr dbname=repmgr_db'
+  pg_bindir=/path/to/postgres/bin
+
+* `cluster`: common name for the replication cluster; this must be the same on all nodes
+* `node`: a unique, abitrary integer identifier
+* `name`: a unique, human-readable name
+* `conninfo`: a standard conninfo string enabling repmgr to connect to the
+   control database; user and name must be the same on all nodes, while other
+   parameters such as port may differ. The `host` parameter *must* be a hostname
+   resolvable by all nodes on the cluster.
+* `pg_bindir`: (optional) location of PostgreSQL binaries, if not in the default $PATH
+
+Note that the configuration file should not be stored inside the PostgreSQL
+data directory.
+
+Each node configuration needs to be registered with repmgr, either using the
+repmgr command line tool, or the repmgrd daemon; for details see below. Details
+about each node are inserted into the repmgr database (for details see below).
+
+
+Replication setup and monitoring
+--------------------------------
+
+For the purposes of this guide, we'll assume the database user will be
+`repmgr_usr` and the database will be `repmgr_db`, and that the following
+environment variables are set on each node:
+
+ - $HOME: the PostgreSQL system user's home directory
+ - $PGDATA: the PostgreSQL data directory
+
+
+Master setup
+------------
+
+1. Configure PostgreSQL
+
+  - create user and database:
+
+	```
+	CREATE ROLE repmgr_usr LOGIN SUPERUSER;
+	CREATE DATABASE repmgr_db OWNER repmgr_usr;
+	```
+
+  - configure postgresql.conf for replication (see above)
+
+  - update pg_hba.conf, e.g.:
+
+	```
+	host    repmgr_db       repmgr_usr  192.168.1.0/24         trust
+	host    replication     repmgr_usr  192.168.1.0/24         trust
+	```
+
+  Restart the PostgreSQL server after making these changes.
+
+2. Create the repmgr configuration file:
+
+    $ cat $HOME/repmgr/repmgr.conf
+    cluster=test
+    node=1
+    node_name=node1
+    conninfo='host=repmgr_node1 user=repmgr_usr dbname=repmgr_db'
+    pg_bindir=/path/to/postgres/bin
+
+3. Register the master node with repmgr:
+
+    $ repmgr -f $HOME/repmgr/repmgr.conf --verbose master register
+    [2014-07-04 10:43:42] [INFO] repmgr mgr connecting to master database
+    [2014-07-04 10:43:42] [INFO] repmgr connected to master, checking its state
+    [2014-07-04 10:43:42] [INFO] master register: creating database objects inside the repmgr_test schema
+    [2014-07-04 10:43:43] [NOTICE] Master node correctly registered for cluster test with id 1 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
+
+
+Slave/standby setup
+-------------------
+
+1. Use repmgr to clone the master:
+
+    $ repmgr -f $HOME/repmgr/repmgr.conf -D $PGDATA -d repmgr_db -U repmgr_usr -R postgres --verbose standby clone 192.168.1.2
+    Opening configuration file: ./repmgr.conf
+    [2014-07-04 10:49:00] [ERROR] Did not find the configuration file './repmgr.conf', continuing
+    [2014-07-04 10:49:00] [INFO] repmgr connecting to master database
+    [2014-07-04 10:49:00] [INFO] repmgr connected to master, checking its state
+    [2014-07-04 10:49:00] [INFO] Successfully connected to primary. Current installation size is 1807 MB
+    [2014-07-04 10:49:00] [NOTICE] Starting backup...
+    [2014-07-04 10:49:00] [INFO] creating directory "/path/to/data/"...
+    (...)
+    [2014-07-04 10:53:19] [NOTICE] Finishing backup...
+    NOTICE:  pg_stop_backup complete, all required WAL segments have been archived
+    [2014-07-04 10:53:21] [INFO] repmgr requires primary to keep WAL files 0000000100000000000000AD until at least 0000000100000000000000AD
+    [2014-07-04 10:53:21] [NOTICE] repmgr standby clone complete
+    [2014-07-04 10:53:21] [NOTICE] HINT: You can now start your postgresql server
+    [2014-07-04 10:53:21] [NOTICE] for example : /etc/init.d/postgresql start
+
+  -R is the database system user on the master node. At this point it does not matter
+  if the `repmgr.conf` file is not found.
+
+  This will clone the PostgreSQL database files from the master, including its
+  `postgresql.conf` and `pg_hba.conf` files, and additionally automatically create
+  the `recovery.conf` file containing the correct parameters to start streaming
+  from the primary node.
+
+2. Start the PostgreSQL server
+
+3. Create the repmgr configuration file:
+
+    $ cat $HOME/repmgr/repmgr.conf
+    cluster=test
+    node=2
+    node_name=node2
+    conninfo='host=repmgr_node2 user=repmgr_usr dbname=repmgr_db'
+    pg_bindir=/path/to/postgres/bin
+
+4. Register the master node with repmgr:
+
+    $ repmgr -f $HOME/repmgr/repmgr.conf --verbose standby register
+    Opening configuration file: /path/to/repmgr/repmgr.conf
+    [2014-07-04 11:48:13] [INFO] repmgr connecting to standby database
+    [2014-07-04 11:48:13] [INFO] repmgr connected to standby, checking its state
+    [2014-07-04 11:48:13] [INFO] repmgr connecting to master database
+    [2014-07-04 11:48:13] [INFO] finding node list for cluster 'test'
+    [2014-07-04 11:48:13] [INFO] checking role of cluster node 'host=repmgr_node1 user=repmgr_usr dbname=repmgr_db'
+    [2014-07-04 11:48:13] [INFO] repmgr connected to master, checking its state
+    [2014-07-04 11:48:13] [INFO] repmgr registering the standby
+    [2014-07-04 11:48:13] [INFO] repmgr registering the standby complete
+    [2014-07-04 11:48:13] [NOTICE] Standby node correctly registered for cluster test with id 2 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
+
+Monitoring
+----------
+
+`repmgrd` is a management and monitoring daemon which runs on standby nodes
+and which and can automate remote actions. It can be started simply with e.g.:
+
+    repmgrd -f $HOME/repmgr/repmgr.conf --verbose > $HOME/repmgr/repmgr.log 2>&1
+
+or alternatively:
+
+    repmgrd -f $HOME/repmgr/repmgr.conf --verbose --monitoring-history > $HOME/repmgr/repmgrd.log 2>&1
+
+which will track advance or lag of the replication in every standby in the
+`repl_monitor` table.
+
+Example log output:
+
+    [2014-07-04 11:55:17] [INFO] repmgrd Connecting to database 'host=localhost user=repmgr_usr dbname=repmgr_db'
+    [2014-07-04 11:55:17] [INFO] repmgrd Connected to database, checking its state
+    [2014-07-04 11:55:17] [INFO] repmgrd Connecting to primary for cluster 'test'
+    [2014-07-04 11:55:17] [INFO] finding node list for cluster 'test'
+    [2014-07-04 11:55:17] [INFO] checking role of cluster node 'host=repmgr_node1 user=repmgr_usr dbname=repmgr_db'
+    [2014-07-04 11:55:17] [INFO] repmgrd Checking cluster configuration with schema 'repmgr_test'
+    [2014-07-04 11:55:17] [INFO] repmgrd Checking node 2 in cluster 'test'
+    [2014-07-04 11:55:17] [INFO] Reloading configuration file and updating repmgr tables
+    [2014-07-04 11:55:17] [INFO] repmgrd Starting continuous standby node monitoring
+
+
+Failover
+--------
+
+To promote a standby to master, on the standby execute e.g.:
+
+    repmgr -f  $HOME/repmgr/repmgr.conf --verbose standby promote
+
+repmgr will attempt to connect to the current master to verify that it
+is not available (if it is, repmgr will not promote the standby).
+
+Other standby servers need to be told to follow the new master with:
+
+    repmgr -f  $HOME/repmgr/repmgr.conf --verbose standby follow
+
+See file `autofailover_quick_setup.rst` for details on setting up
+automated failover.
+
+
+repmgr database schema
+----------------------
+
+repmgr creates a small schema for its own use in the database specified in
+each node's conninfo configuration parameter. This database can in principle
+be any database. The schema name is the global `cluster` name prefixed
+with `repmgr_`, so for the example setup above the schema name is
+`repmgr_test`.
+
+The schema contains two tables:
+
+* `repl_nodes`
+  stores information about all registered servers in the cluster
+* `repl_monitor`
+  stores monitoring information about each node
+
+and one view, `repl_status`, which summarizes the latest monitoring information
+for each node.
+
+

README.rst

@@ -23,7 +23,7 @@ databases as a single cluster.  repmgr includes two components:
 Supported Releases
 ------------------
 
-repmgr works with PostgreSQL versions 9.0 and superior.
+repmgr works with PostgreSQL versions 9.0 and later.
 
 There are currently no incompatibilities when upgrading repmgr from 9.0 to 9.1,
 so your 9.0 configuration will work with 9.1
@@ -77,7 +77,7 @@ and run::
   
 And if a previously failed node becomes available again, such as
 the lost node1 above, you can get it to resynchronize by only copying
-over changes made while it was down using.  That hapens with what's
+over changes made while it was down.  That happens with what's
 called a forced clone, which overwrites existing data rather than
 assuming it starts with an empty database directory tree::
 
@@ -131,19 +131,19 @@ If you need to remove the source code temporary files from this directory,
 that can be done like this::
 
   make USE_PGXS=1 clean
-  
+
 See below for building notes specific to RedHat Linux variants.
 
 Using a full source code tree
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 In this method, the repmgr distribution is copied into the PostgreSQL source
-code tree, assumed to be at the ${postgresql_sources} for this example.
+code tree, assumed to be under ${postgresql_sources} for this example.
 The resulting subdirectory must be named ``contrib/repmgr``, without any
 version number::
 
   cp repmgr.tar.gz ${postgresql_sources}/contrib
-  cd ${postgresql_sources}/contrib 
+  cd ${postgresql_sources}/contrib
   tar xvzf repmgr-1.0.tar.gz
   cd repmgr
   make
@@ -237,7 +237,7 @@ If you already tried to build repmgr before doing this, you'll need to do::
 
     make USE_PGXS=1 clean
 
-To get rid of leftover files from the wrong architecture.
+to get rid of leftover files from the wrong architecture.
 
 Notes on Ubuntu, Debian or other Debian-based Builds
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -279,8 +279,8 @@ Confirm software was built correctly
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 You should now find the repmgr programs available in the subdirectory where
-the rest of your PostgreSQL installation is at.  You can confirm the software
-is available by checking its version::
+the rest of your PostgreSQL binary files are located.  You can confirm the
+software is available by checking its version::
 
   repmgr --version
   repmgrd --version
@@ -374,10 +374,10 @@ Usage walkthrough
 This assumes you've already followed the steps in "Installation Outline" to
 install repmgr and repmgrd on the system.
 
-A normal production installation of ``repmgr`` will normally involve two
-different systems running on the same port, typically the default of 5432, 
-with both using files owned by the ``postgres`` user account.  This
-walkthrough assumes the following setup:
+A typical production installation of ``repmgr`` might involve two PostgreSQL
+instances on seperate servers, both running under the ``postgres`` user account
+and both using the default port (5432). This walkthrough assumes the following
+setup:
 
 * A primary (master) server called "node1," running as the "postgres" user 
   who is also the owner of the files. This server is operating on port 5432.  This
@@ -625,18 +625,18 @@ Now restore to the original configuration by stopping
 primary server, then bringing up "node2" as a standby with a valid
 ``recovery.conf`` file.
 
-Stop the "node2" server::
+Stop the "node2" server and type the following on "node1" server::
 
   repmgr -f /var/lib/pgsql/repmgr/repmgr.conf standby promote
 
-Now the original primary, "node1" is acting again as primary.
+Now the original primary, "node1", is acting again as primary.
 
-Start the "node2" server and type this on "node1"::
+Start the "node2" server and type this on "node2"::
 
   repmgr standby clone --force -h node2 -p 5432 -U postgres -R postgres --verbose
 
-Verify the roles have reversed by attempting to insert a record on "node"
-and on "node1".
+Verify the roles have reversed by attempting to insert a record on "node1"
+and on "node2".
 
 The servers are now again acting as primary on "node1" and standby on "node2".
 
@@ -660,7 +660,7 @@ You can usually leave out changes to the port number in this case too.
 
 * A database exists on "prime" called "testdb."
 
-* The Postgress installation in each of the above is defined as $PGDATA, 
+* The Postgres installation in each of the above is defined as $PGDATA, 
   which is represented here with ``/data/prime`` as the "prime" server and 
   ``/data/standby`` as the "standby" server.
 
@@ -890,7 +890,7 @@ The output from this program looks like this::
 
   Configuration options:
     -D, --data-dir=DIR         local directory where the files will be copied to
-    -f, --config_file=PATH     path to the configuration file
+    -f, --config-file=PATH     path to the configuration file
     -R, --remote-user=USERNAME database server username for rsync
     -w, --wal-keep-segments=VALUE  minimum value for the GUC wal_keep_segments (default: 5000)
     -I, --ignore-rsync-warning ignore rsync partial transfer warning
@@ -1014,7 +1014,7 @@ The output from this program looks like this::
     --version                 output version information, then exit
     --verbose                 output verbose activity information
     --monitoring-history      track advance or lag of the replication in every standby in repl_monitor
-    -f, --config_file=PATH    database to connect to
+    -f, --config-file=PATH    path to the configuration file
   
   repmgrd monitors a cluster of servers.
 
@@ -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.

RHEL/repmgr.spec

@@ -0,0 +1,57 @@
+Summary: repmgr
+Name: repmgr
+Version: 2.0
+Release: 2
+License: GPLv3
+Group: System Environment/Daemons
+URL: http://repmgr.org 
+Packager: Nathan Van Overloop <nathan.van.overloop@nexperteam.be>
+Vendor: 2ndQuadrant Limited
+Distribution: centos
+Source0: %{name}-%{version}.tar.gz
+BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root
+
+%description
+repmgr for centos6
+
+%prep
+%setup
+
+%build
+export PATH=$PATH:/usr/pgsql-9.3/bin/
+%{__make} USE_PGXS=1
+
+%install
+[ "%{buildroot}" != "/" ] && %{__rm} -rf %{buildroot}
+
+export PATH=$PATH:/usr/pgsql-9.3/bin/
+%{__make} USE_PGXS=1 install DESTDIR=%{buildroot} INSTALL="install -p"
+%{__make} USE_PGXS=1 install_prog DESTDIR=%{buildroot} INSTALL="install -p"
+%{__make} USE_PGXS=1 install_rhel DESTDIR=%{buildroot} INSTALL="install -p"
+
+
+%clean
+[ "%{buildroot}" != "/" ] && %{__rm} -rf %{buildroot}
+ 
+
+%files
+%defattr(-,root,root)
+/usr/bin/repmgr
+/usr/bin/repmgrd
+/usr/pgsql-9.3/bin/repmgr
+/usr/pgsql-9.3/bin/repmgrd
+/usr/pgsql-9.3/lib/repmgr_funcs.so
+/usr/pgsql-9.3/share/contrib/repmgr.sql
+/usr/pgsql-9.3/share/contrib/repmgr_funcs.sql
+/usr/pgsql-9.3/share/contrib/uninstall_repmgr.sql
+/usr/pgsql-9.3/share/contrib/uninstall_repmgr_funcs.sql
+%attr(0755,root,root)/etc/init.d/repmgrd 
+%attr(0644,root,root)/etc/sysconfig/repmgrd
+%attr(0644,root,root)/etc/repmgr/repmgr.conf.sample
+
+%changelog
+* Thu Jun 05 2014 Nathan Van Overloop <nathan.van.overloop@nexperteam.be> 2.0.2
+- fix witness creation to create db and user if needed
+* Fri Apr 04 2014 Nathan Van Overloop <nathan.van.overloop@nexperteam.be> 2.0.1
+- initial build for RHEL6
+

RHEL/repmgrd.init

@@ -0,0 +1,114 @@
+#!/bin/bash
+#
+# repmgrd	Start up the repmgrd daemon
+#		repmrgd (replication manager daemon)
+#
+# chkconfig: -  75 16
+# description: repmgrd is the repliation manager daemon \
+# The repmgrd replication management and monitoring daemon for PostgreSQL.
+
+### 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-9.3
+# Should-Stop: $syslog postgresql-9.3
+# Short-Description: start and stop repmrgd
+# Description: Enable repmgrd replication management and monitoring daemon for PostgreSQL
+#	       this is used to monitor a postgresql cluster.
+### END INIT INFO
+
+# Source function library.
+. /etc/init.d/functions
+
+# Source networking configuration.
+. /etc/sysconfig/network
+
+prog=repmgrd
+REPMGRD_ENABLED=yes
+REPMGRD_OPTS=
+REPMGRD_USER=postgres
+DAEMONIZE="-d"
+
+# pull in sysconfig settings
+[ -f /etc/sysconfig/repmgrd ] && . /etc/sysconfig/repmgrd
+
+LOCKFILE=/var/lock/subsys/$prog
+RETVAL=0
+
+case "$REPMGRD_ENABLED" in
+    [Yy]*)
+	#nothing to do here	
+	;;
+    *)
+	exit 2
+	;;
+esac
+
+
+if [ -z "$REPMGRD_OPTS" ]
+then
+    echo "Not starting $prog, REPMGRD_OPTS not set in /etc/sysconfig/$prog"
+    exit 2
+fi
+
+start() {
+	[ "$EUID" != "0" ] && exit 4
+        [ "$NETWORKING" = "no" ] && exit 1
+
+        # Start daemons.
+        echo -n $"Starting $prog: "
+        daemon --user $REPMGRD_USER $prog $DAEMONIZE $REPMGRD_OPTS
+        RETVAL=$?
+        echo
+        [ $RETVAL -eq 0 ] && touch $LOCKFILE
+        return $RETVAL
+}
+
+stop() {
+	[ "$EUID" != "0" ] && exit 4
+        echo -n $"Shutting down $prog: "
+        killproc $prog
+        RETVAL=$?
+        echo
+        [ $RETVAL -eq 0 ] && rm -f $LOCKFILE
+        return $RETVAL
+}
+status() {
+        if [ -f "$LOCKFILE" ]; then
+            echo "$prog is running"
+        else
+	    RETVAL=3
+            echo "$prog is stopped"
+        fi
+        return $RETVAL
+}
+
+# See how we were called.
+case "$1" in
+  start)
+        start
+        ;;
+  stop)
+        stop
+        ;;
+  status)
+        status $prog
+        ;;
+  restart|force-reload)
+        stop
+        start
+        ;;
+  try-restart|condrestart)
+        if status $prog > /dev/null; then
+            stop
+            start
+        fi
+        ;;
+  reload)
+        exit 3
+        ;;
+  *)
+        echo $"Usage: $0 {start|stop|status|restart|try-restart|force-reload}"
+        exit 2
+esac

RHEL/repmgrd.sysconfig

@@ -0,0 +1,4 @@
+#default sysconfig file for repmrgd
+#custom overrides can be placed here
+
+REPMGRD_OPTS="-f /etc/repmgr/repmgr.conf"

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
-  a working ssh connection to the destination would help find
-  configuration errors before disturbing the database.
+* Timeline increases when promoting a standby
+
+* 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
-=====================================================
-
-Automatic Failover
-==================
-
-repmgr allows setups for automatic failover when it detects the failure of the master node.
-Following is a quick setup for this.
-
-Installation
-============
-
-For convenience, we define:
-
-  * node1 is the hostname fully qualified of the Master server, IP 192.168.1.10
-  * node2 is the hostname fully qualified of the Standby server, IP 192.168.1.11
-  * witness is the hostname fully qualified of the server used for witness, IP 192.168.1.12
-
-:Note: It is not recommanded to use name defining status of a server like «masterserver»,
-       this is a name leading to confusion once a failover take place and the Master is
-       now on the «standbyserver».
-
-Summary
--------
-
-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
-and a witness-repmgrd is installed in a third server where it uses a PostgreSQL
-cluster to communicate with other repmgrd daemons.
-
-1. Install PostgreSQL in all the servers involved (including the server used for
-witness)
-2. Install repmgr in all the servers involved (including the server used for witness)
-3. Configure the Master PostreSQL
-4. Clone the Master to the Standby using "repmgr standby clone" command
-5. Configure repmgr in all the servers involved (including the server used for witness)
-6. Register Master and Standby nodes
-7. Initiate witness server
-8. Start the repmgrd daemons in all nodes
-
-:Note: A complete Hight-Availability design need at least 3 servers to still have
-       a backup node after a first failure.
-
-Install PostgreSQL
-------------------
-
-You can install PostgreSQL using any of the recommended methods. You should ensure
-it's 9.0 or superior.
-
-Install repmgr
---------------
-
-Install repmgr following the steps in the README.
-
-Configure PostreSQL
--------------------
-
-Log in node1.
-
-Edit the file postgresql.conf and modify the parameters::
-
-  listen_addresses='*'
-  wal_level = 'hot_standby'
-  archive_mode = on
-  archive_command = 'cd .'	 # we can also use exit 0, anything that 
-                             # just does nothing
-  max_wal_senders = 10
-  wal_keep_segments = 5000   # 80 GB required on pg_xlog
-  hot_standby = on
-  shared_preload_libraries = 'repmgr_funcs'
-
-Edit the file pg_hba.conf and add lines for the replication::
-
-  host     repmgr           repmgr      127.0.0.1/32            trust
-  host     repmgr           repmgr      192.168.1.10/30         trust
-  host     replication      all         192.168.1.10/30         trust
-
-:Note: It is also possible to use a password authentication (md5), .pgpass file
-       should be edited to allow connection between each node.
-
-Create the user and database to manage replication::
-
-  su - postgres
-  createuser -s repmgr
-  createdb -O repmgr repmgr
-  psql -f /usr/share/postgresql/9.0/contrib/repmgr_funcs.sql repmgr
-
-Restart the PostgreSQL server::
-
-  pg_ctl -D $PGDATA restart
-
-And check everything is fine in the server log.
-
-Create the ssh-key for the postgres user and copy it to other servers::
-
-  su - postgres
-  ssh-keygen             # /!\ do not use a passphrase /!\
-  cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
-  chmod 600 ~/.ssh/authorized_keys
-  exit
-  rsync -avz ~postgres/.ssh/authorized_keys node2:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/authorized_keys witness:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/id_rsa* node2:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/id_rsa* witness:~postgres/.ssh/
-
-Clone Master
-------------
-
-Log in node2.
-
-Clone the node1 (the current Master)::
-
-  su - postgres
-  repmgr -d repmgr -U repmgr standby clone node1
-
-Start the PostgreSQL server::
-
-  pg_ctl -D $PGDATA start
-
-And check everything is fine in the server log.
-
-Configure repmgr
-----------------
-
-Log in each server and configure repmgr by editing the file
-/etc/repmgr/repmgr.conf::
-
-  cluster=my_cluster
-  node=1
-  node_name=earth
-  conninfo='host=192.168.1.10 dbname=repmgr user=repmgr'
-  master_response_timeout=60
-  reconnect_attempts=6
-  reconnect_interval=10
-  failover=automatic
-  promote_command='promote_command.sh'
-  follow_command='repmgr standby follow -f /etc/repmgr/repmgr.conf'
-
-* *cluster* is the name of the current replication.
-* *node* is the number of the current node (1, 2 or 3 in the current example).
-* *node_name* is an identifier for every node.
-* *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* is the maximum amount of time we are going to wait before deciding the master has died and start failover procedure.
-* *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* is the amount of time between retries to reconnect to master after a failure has been detected and before start failover procedure.
-* *failover* configure behavior : *manual* or *automatic*.
-* *promote_command* the command executed to do the failover (including the PostgreSQL failover itself). The command must return 0 on success.
-* *follow_command* the command executed to address the current standby to another Master. The command must return 0 on success.
-
-Register Master and Standby
----------------------------
-
-Log in node1.
-
-Register the node as Master::
-
-  su - postgres
-  repmgr -f /etc/repmgr/repmgr.conf master register
-
-Log in node2.
-
-Register the node as Standby::
-
-  su - postgres
-  repmgr -f /etc/repmgr/repmgr.conf standby register
-
-Initialize witness server
--------------------------
-
-Log in witness.
-
-Initialize the witness server::
-
-  su - postgres
-  repmgr -d repmgr -U repmgr -h 192.168.1.10 -D $WITNESS_PGDATA -f /etc/repmgr/repmgr.conf witness create node1
-
-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.
-As part of the procees it also ask for the superuser password so it can connect when needed.
-
-Start the repmgrd daemons
--------------------------
-
-Log in node2 and witness.
-
-  su - postgres
-  repmgrd -f /etc/repmgr/repmgr.conf > /var/log/postgresql/repmgr.log 2>&1
-
-:Note: The Master does not need a repmgrd daemon.
-
-
-Suspend Automatic behavior
-==========================
-
-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`
-
-TODO : -HUP configuration update is not implemented and it should check its
-	   configuration file  against its configuration in DB, updating
-	   accordingly the SQL conf (especialy the failover manual or auto)
-	   this allow witness-standby and standby-not-promotable features
-	   and simpler usage of the tool ;)
-
-Usage
-=====
-
-The repmgr documentation is in the README file (how to build, options, etc.)
+=====================================================
+ PostgreSQL Automatic Fail-Over - User Documentation
+=====================================================
+
+Automatic Failover
+==================
+
+repmgr allows setups for automatic failover when it detects the failure of the master node.
+Following is a quick setup for this.
+
+Installation
+============
+
+For convenience, we define:
+
+**node1**
+    is the hostname fully qualified of the Master server, IP 192.168.1.10
+**node2**
+    is the hostname fully qualified of the Standby server, IP 192.168.1.11
+**witness**
+    is the hostname fully qualified of the server used for witness, IP 192.168.1.12
+
+**Note:** It is not recommanded to use name defining status of a server like «masterserver»,
+this is a name leading to confusion once a failover take place and the Master is
+now on the «standbyserver».
+
+Summary
+-------
+
+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
+and a witness-repmgrd is installed in a third server where it uses a PostgreSQL
+cluster to communicate with other repmgrd daemons.
+
+1. Install PostgreSQL in all the servers involved (including the server used for
+   witness)
+
+2. Install repmgr in all the servers involved (including the server used for witness)
+
+3. Configure the Master PostreSQL
+
+4. Clone the Master to the Standby using "repmgr standby clone" command
+
+5. Configure repmgr in all the servers involved (including the server used for witness)
+
+6. Register Master and Standby nodes
+
+7. Initiate witness server
+
+8. Start the repmgrd daemons in all nodes
+
+**Note** A complete High-Availability design needs at least 3 servers to still have
+a backup node after a first failure.
+
+Install PostgreSQL
+------------------
+
+You can install PostgreSQL using any of the recommended methods. You should ensure
+it's 9.0 or later.
+
+Install repmgr
+--------------
+
+Install repmgr following the steps in the README file.
+
+Configure PostreSQL
+-------------------
+
+Log in node1.
+
+Edit the file postgresql.conf and modify the parameters::
+
+  listen_addresses='*'
+  wal_level = 'hot_standby'
+  archive_mode = on
+  archive_command = 'cd .'	 # we can also use exit 0, anything that
+                             # just does nothing
+  max_wal_senders = 10
+  wal_keep_segments = 5000   # 80 GB required on pg_xlog
+  hot_standby = on
+  shared_preload_libraries = 'repmgr_funcs'
+
+Edit the file pg_hba.conf and add lines for the replication::
+
+  host     repmgr           repmgr      127.0.0.1/32            trust
+  host     repmgr           repmgr      192.168.1.10/30         trust
+  host     replication      all         192.168.1.10/30         trust
+
+**Note:** It is also possible to use a password authentication (md5), .pgpass file
+should be edited to allow connection between each node.
+
+Create the user and database to manage replication::
+
+  su - postgres
+  createuser -s repmgr
+  createdb -O repmgr repmgr
+  psql -f /usr/share/postgresql/9.0/contrib/repmgr_funcs.sql repmgr
+
+Restart the PostgreSQL server::
+
+  pg_ctl -D $PGDATA restart
+
+And check everything is fine in the server log.
+
+Create the ssh-key for the postgres user and copy it to other servers::
+
+  su - postgres
+  ssh-keygen             # /!\ do not use a passphrase /!\
+  cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
+  chmod 600 ~/.ssh/authorized_keys
+  exit
+  rsync -avz ~postgres/.ssh/authorized_keys node2:~postgres/.ssh/
+  rsync -avz ~postgres/.ssh/authorized_keys witness:~postgres/.ssh/
+  rsync -avz ~postgres/.ssh/id_rsa* node2:~postgres/.ssh/
+  rsync -avz ~postgres/.ssh/id_rsa* witness:~postgres/.ssh/
+
+Clone Master
+------------
+
+Log in node2.
+
+Clone the node1 (the current Master)::
+
+  su - postgres
+  repmgr -d repmgr -U repmgr -h node1 standby clone 
+
+Start the PostgreSQL server::
+
+  pg_ctl -D $PGDATA start
+
+And check everything is fine in the server log.
+
+Configure repmgr
+----------------
+
+Log in each server and configure repmgr by editing the file
+/etc/repmgr/repmgr.conf::
+
+  cluster=my_cluster
+  node=1
+  node_name=earth
+  conninfo='host=192.168.1.10 dbname=repmgr user=repmgr'
+  master_response_timeout=60
+  reconnect_attempts=6
+  reconnect_interval=10
+  failover=automatic
+  promote_command='promote_command.sh'
+  follow_command='repmgr standby follow -f /etc/repmgr/repmgr.conf'
+
+**cluster**
+    is the name of the current replication.
+**node**
+    is the number of the current node (1, 2 or 3 in the current example).
+**node_name**
+    is an identifier for every node.
+**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**
+    is the maximum amount of time we are going to wait before deciding the master has died and start failover procedure.
+**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**
+    is the amount of time between retries to reconnect to master after a failure has been detected and before start failover procedure.
+**failover**
+    configure behavior: *manual* or *automatic*.
+**promote_command**
+    the command executed to do the failover (including the PostgreSQL failover itself). The command must return 0 on success.
+**follow_command**
+    the command executed to address the current standby to another Master. The command must return 0 on success.
+
+Register Master and Standby
+---------------------------
+
+Log in node1.
+
+Register the node as Master::
+
+  su - postgres
+  repmgr -f /etc/repmgr/repmgr.conf master register
+
+Log in node2. Register it as a standby::
+
+  su - postgres
+  repmgr -f /etc/repmgr/repmgr.conf standby register
+
+Initialize witness server
+-------------------------
+
+Log in witness.
+
+Initialize the witness server::
+
+  su - postgres
+  repmgr -d repmgr -U repmgr -h 192.168.1.10 -D $WITNESS_PGDATA -f /etc/repmgr/repmgr.conf witness create
+
+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.
+As part of the procees it also ask for the superuser password so it can connect when needed.
+
+Start the repmgrd daemons
+-------------------------
+
+Log in node2 and witness.
+
+	su - postgres
+	repmgrd -f /etc/repmgr/repmgr.conf > /var/log/postgresql/repmgr.log 2>&1
+
+**Note:** The Master does not need a repmgrd daemon.
+
+
+Suspend Automatic behavior
+==========================
+
+Edit the repmgr.conf of the node to remove from automatic processing and change::
+
+	failover=manual
+
+Then, signal repmgrd daemon::
+
+	su - postgres
+	kill -HUP `pidof 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
@@ -44,9 +44,9 @@
 int
 check_dir(char *dir)
 {
-	DIR        *chkdir;
-	struct 		dirent *file;
-	int         result = 1;
+	DIR		   *chkdir;
+	struct dirent *file;
+	int			result = 1;
 
 	errno = 0;
 
@@ -58,7 +58,7 @@ check_dir(char *dir)
 	while ((file = readdir(chkdir)) != NULL)
 	{
 		if (strcmp(".", file->d_name) == 0 ||
-		        strcmp("..", file->d_name) == 0)
+			strcmp("..", file->d_name) == 0)
 		{
 			/* skip this and parent directory */
 			continue;
@@ -71,6 +71,7 @@ check_dir(char *dir)
 	}
 
 #ifdef WIN32
+
 	/*
 	 * This fix is in mingw cvs (runtime/mingwex/dirent.c rev 1.4), but not in
 	 * released version
@@ -82,29 +83,29 @@ check_dir(char *dir)
 	closedir(chkdir);
 
 	if (errno != 0)
-		return -1;          /* some kind of I/O error? */
+		return -1;				/* some kind of I/O error? */
 
 	return result;
 }
 
 
 /*
- * Create directory
+ * Create directory with error log message when failing
  */
 bool
-create_directory(char *dir)
+create_dir(char *dir)
 {
 	if (mkdir_p(dir, 0700) == 0)
 		return true;
 
 	log_err(_("Could not create directory \"%s\": %s\n"),
-	        dir, strerror(errno));
+			dir, strerror(errno));
 
 	return false;
 }
 
 bool
-set_directory_permissions(char *dir)
+set_dir_permissions(char *dir)
 {
 	return (chmod(dir, 0700) != 0) ? false : true;
 }
@@ -127,10 +128,10 @@ 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;
@@ -149,8 +150,8 @@ mkdir_p(char *path, mode_t omode)
 				return 1;
 		}
 		else if (p[1] == ':' &&
-		         ((p[0] >= 'a' && p[0] <= 'z') ||
-		          (p[0] >= 'A' && p[0] <= 'Z')))
+				 ((p[0] >= 'a' && p[0] <= 'z') ||
+				  (p[0] >= 'A' && p[0] <= 'Z')))
 		{
 			/* local drive */
 			p += 2;
@@ -221,16 +222,16 @@ bool
 is_pg_dir(char *dir)
 {
 	const size_t buf_sz = 8192;
-	char		 path[buf_sz];
-	struct stat	 sb;
-	int		r;
+	char		path[buf_sz];
+	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)
@@ -241,67 +242,67 @@ is_pg_dir(char *dir)
 
 
 bool
-create_pgdir(char *dir, bool force)
+create_pg_dir(char *dir, bool force)
 {
-	bool	pg_dir = false;
+	bool		pg_dir = false;
 
 	/* Check this directory could be used as a PGDATA dir */
 	switch (check_dir(dir))
 	{
-	case 0:
-		/* dir not there, must create it */
-		log_info(_("creating directory \"%s\"...\n"), dir);
+		case 0:
+			/* dir not there, must create it */
+			log_info(_("creating directory \"%s\"...\n"), dir);
 
-		if (!create_directory(dir))
-		{
-			log_err(_("couldn't create directory \"%s\"...\n"),
-			        dir);
-			exit(ERR_BAD_CONFIG);
-		}
-		break;
-	case 1:
-		/* Present but empty, fix permissions and use it */
-		log_info(_("checking and correcting permissions on existing directory %s ...\n"),
-		         dir);
-
-		if (!set_directory_permissions(dir))
-		{
-			log_err(_("could not change permissions of directory \"%s\": %s\n"),
-			        dir, strerror(errno));
-			exit(ERR_BAD_CONFIG);
-		}
-		break;
-	case 2:
-		/* Present and not empty */
-		log_warning(_("directory \"%s\" exists but is not empty\n"),
-		            dir);
-
-		pg_dir = is_pg_dir(dir);
-
-		/*
-		 * we use force to reduce the time needed to restore a node which
-		 * turn async after a failover or anything else
-		 */
-		if (pg_dir && force)
-		{
-			/* Let it continue */
+			if (!create_dir(dir))
+			{
+				log_err(_("couldn't create directory \"%s\"...\n"),
+						dir);
+				return false;
+			}
 			break;
-		}
-		else if (pg_dir && !force)
-		{
-			log_warning(_("\nThis looks like a PostgreSQL directory.\n"
-			              "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);
-		}
+		case 1:
+			/* Present but empty, fix permissions and use it */
+			log_info(_("checking and correcting permissions on existing directory %s ...\n"),
+					 dir);
 
-		return false;
-	default:
-		/* Trouble accessing directory */
-		log_err(_("could not access directory \"%s\": %s\n"),
-		        dir, strerror(errno));
-		exit(ERR_BAD_CONFIG);
+			if (!set_dir_permissions(dir))
+			{
+				log_err(_("could not change permissions of directory \"%s\": %s\n"),
+						dir, strerror(errno));
+				return false;
+			}
+			break;
+		case 2:
+			/* Present and not empty */
+			log_warning(_("directory \"%s\" exists but is not empty\n"),
+						dir);
+
+			pg_dir = is_pg_dir(dir);
+
+			/*
+			 * we use force to reduce the time needed to restore a node which
+			 * turn async after a failover or anything else
+			 */
+			if (pg_dir && force)
+			{
+				/* Let it continue */
+				break;
+			}
+			else if (pg_dir && !force)
+			{
+				log_warning(_("\nThis looks like a PostgreSQL directory.\n"
+							  "If you are sure you want to clone here, "
+							  "please check there is no PostgreSQL server "
+							  "running and use the --force option\n"));
+				return false;
+			}
+
+			return false;
+		default:
+			/* Trouble accessing directory */
+			log_err(_("could not access directory \"%s\": %s\n"),
+					dir, strerror(errno));
+			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
@@ -20,11 +20,11 @@
 #ifndef _REPMGR_CHECK_DIR_H_
 #define _REPMGR_CHECK_DIR_H_
 
-int mkdir_p(char *path, mode_t omode);
-int  check_dir(char *dir);
-bool create_directory(char *dir);
-bool set_directory_permissions(char *dir);
-bool is_pg_dir(char *dir);
-bool create_pgdir(char *dir, bool force);
+int			mkdir_p(char *path, mode_t omode);
+int			check_dir(char *dir);
+bool		create_dir(char *dir);
+bool		set_dir_permissions(char *dir);
+bool		is_pg_dir(char *dir);
+bool		create_pg_dir(char *dir, bool force);
 
 #endif

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
@@ -23,13 +23,14 @@
 #include "repmgr.h"
 
 void
-parse_config(const char *config_file, t_configuration_options *options)
+parse_config(const char *config_file, t_configuration_options * options)
 {
-	char *s, buff[MAXLINELENGTH];
-	char name[MAXLEN];
-	char value[MAXLEN];
+	char	   *s,
+				buff[MAXLINELENGTH];
+	char		name[MAXLEN];
+	char		value[MAXLEN];
 
-	FILE *fp = fopen (config_file, "r");
+	FILE	   *fp = fopen(config_file, "r");
 
 	/* Initialize */
 	memset(options->cluster_name, 0, sizeof(options->cluster_name));
@@ -41,6 +42,9 @@ 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;
@@ -49,18 +53,22 @@ 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.
+	 * Since some commands don't require a config file at all, not having one
+	 * isn't necessarily a problem.
 	 */
 	if (fp == NULL)
 	{
-		log_err(_("Did not find the configuration file '%s', continuing\n"), config_file);
+		log_err(_("Did not find the configuration file '%s', continuing\n"),
+				config_file);
 		return;
 	}
 
 	/* Read next line */
-	while ((s = fgets (buff, sizeof buff, fp)) != NULL)
+	while ((s = fgets(buff, sizeof buff, fp)) != NULL)
 	{
 		/* Skip blank lines and comments */
 		if (buff[0] == '\n' || buff[0] == '#')
@@ -71,20 +79,23 @@ parse_config(const char *config_file, t_configuration_options *options)
 
 		/* Copy into correct entry in parameters struct */
 		if (strcmp(name, "cluster") == 0)
-			strncpy (options->cluster_name, value, MAXLEN);
+			strncpy(options->cluster_name, value, MAXLEN);
 		else if (strcmp(name, "node") == 0)
 			options->node = atoi(value);
 		else if (strcmp(name, "conninfo") == 0)
-			strncpy (options->conninfo, value, MAXLEN);
+			strncpy(options->conninfo, value, MAXLEN);
 		else if (strcmp(name, "rsync_options") == 0)
-			strncpy (options->rsync_options, value, QUERY_STR_LEN);
+			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);
+			strncpy(options->loglevel, value, MAXLEN);
 		else if (strcmp(name, "logfacility") == 0)
-			strncpy (options->logfacility, value, MAXLEN);
+			strncpy(options->logfacility, value, MAXLEN);
 		else if (strcmp(name, "failover") == 0)
 		{
-			char failoverstr[MAXLEN];
+			char		failoverstr[MAXLEN];
+
 			strncpy(failoverstr, value, MAXLEN);
 
 			if (strcmp(failoverstr, "manual") == 0)
@@ -111,15 +122,25 @@ 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);
 	}
 
 	/* Close file */
-	fclose (fp);
+	fclose(fp);
 
 	/* Check config settings */
-	if (strnlen(options->cluster_name, MAXLEN)==0)
+	if (*options->cluster_name == '\0')
 	{
 		log_err(_("Cluster name is missing. Check the configuration file.\n"));
 		exit(ERR_BAD_CONFIG);
@@ -148,39 +169,48 @@ 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);
+	}
 }
 
 
 char *
-trim (char *s)
+trim(char *s)
 {
 	/* Initialize start, end pointers */
-	char *s1 = s, *s2 = &s[strlen (s) - 1];
+	char	   *s1 = s,
+			   *s2 = &s[strlen(s) - 1];
 
 	/* Trim and delimit right side */
-	while ( (isspace (*s2)) && (s2 >= s1) )
+	while ((isspace(*s2)) && (s2 >= s1))
 		--s2;
-	*(s2+1) = '\0';
+	*(s2 + 1) = '\0';
 
 	/* Trim left side */
-	while ( (isspace (*s1)) && (s1 < s2) )
+	while ((isspace(*s1)) && (s1 < s2))
 		++s1;
 
 	/* Copy finished string */
-	strcpy (s, s1);
+	memmove(s, s1, s2 - s1);
+	s[s2 - s1 + 1] = '\0';
+
 	return s;
 }
 
 void
 parse_line(char *buff, char *name, char *value)
 {
-	int i = 0;
-	int j = 0;
+	int			i = 0;
+	int			j = 0;
 
 	/*
 	 * first we find the name of the parameter
 	 */
-	for ( ; i < MAXLEN; ++i)
+	for (; i < MAXLEN; ++i)
 	{
 		if (buff[i] != '=')
 			name[j++] = buff[i];
@@ -193,7 +223,7 @@ parse_line(char *buff, char *name, char *value)
 	 * Now the value
 	 */
 	j = 0;
-	for ( ++i ; i < MAXLEN; ++i)
+	for (++i; i < MAXLEN; ++i)
 		if (buff[i] == '\'')
 			continue;
 		else if (buff[i] != '\n')
@@ -205,9 +235,9 @@ parse_line(char *buff, char *name, char *value)
 }
 
 bool
-reload_configuration(char *config_file, t_configuration_options *orig_options)
+reload_config(char *config_file, t_configuration_options * orig_options)
 {
-	PGconn	*conn;
+	PGconn	   *conn;
 
 	t_configuration_options new_options;
 
@@ -218,57 +248,57 @@ 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;
 	}
 
 	/* Test conninfo string */
-	conn = establishDBConnection(new_options.conninfo, false);
+	conn = establish_db_connection(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);
@@ -283,19 +313,20 @@ 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;
+
 	/*
 	 * XXX These ones can change with a simple SIGHUP?
-
-		strcpy (orig_options->loglevel, new_options.loglevel);
-		strcpy (orig_options->logfacility, new_options.logfacility);
-
-		logger_shutdown();
-		XXX do we have progname here ?
-		logger_init(progname, orig_options.loglevel, orig_options.logfacility);
-	*/
+	 *
+	 * strcpy (orig_options->loglevel, new_options.loglevel); strcpy
+	 * (orig_options->logfacility, new_options.logfacility);
+	 *
+	 * logger_shutdown(); XXX do we have progname here ? logger_init(progname,
+	 * orig_options.loglevel, orig_options.logfacility);
+	 */
 
 	return true;
 }

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
@@ -25,25 +25,33 @@
 
 typedef struct
 {
-	char cluster_name[MAXLEN];
-	int node;
-	char conninfo[MAXLEN];
-	int failover;
-	int priority;
-	char node_name[MAXLEN];
-	char promote_command[MAXLEN];
-	char follow_command[MAXLEN];
-	char loglevel[MAXLEN];
-	char logfacility[MAXLEN];
-	char rsync_options[QUERY_STR_LEN];
-	int  master_response_timeout;
-	int  reconnect_attempts;
-	int  reconnect_intvl;
-} t_configuration_options;
+	char		cluster_name[MAXLEN];
+	int			node;
+	char		conninfo[MAXLEN];
+	int			failover;
+	int			priority;
+	char		node_name[MAXLEN];
+	char		promote_command[MAXLEN];
+	char		follow_command[MAXLEN];
+	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;
 
-void parse_config(const char *config_file, t_configuration_options *options);
-void parse_line(char *buff, char *name, char *value);
-char *trim(char *s);
-bool reload_configuration(char *config_file, t_configuration_options *orig_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);
+bool		reload_config(char *config_file, t_configuration_options * orig_options);
 
 #endif

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
@@ -18,17 +18,19 @@
  */
 
 #include <unistd.h>
+#include <time.h>
+#include <sys/time.h>
 
 #include "repmgr.h"
 #include "strutil.h"
 #include "log.h"
 
 PGconn *
-establishDBConnection(const char *conninfo, const bool exit_on_error)
+establish_db_connection(const char *conninfo, const bool exit_on_error)
 {
 	/* Make a connection to the database */
-	PGconn *conn = NULL;
-	char    connection_string[MAXLEN];
+	PGconn	   *conn = NULL;
+	char		connection_string[MAXLEN];
 
 	strcpy(connection_string, conninfo);
 	strcat(connection_string, " fallback_application_name='repmgr'");
@@ -38,7 +40,7 @@ establishDBConnection(const char *conninfo, const bool exit_on_error)
 	if ((PQstatus(conn) != CONNECTION_OK))
 	{
 		log_err(_("Connection to database failed: %s\n"),
-		        PQerrorMessage(conn));
+				PQerrorMessage(conn));
 
 		if (exit_on_error)
 		{
@@ -51,16 +53,17 @@ establishDBConnection(const char *conninfo, const bool exit_on_error)
 }
 
 PGconn *
-establishDBConnectionByParams(const char *keywords[], const char *values[],const bool exit_on_error)
+establish_db_connection_by_params(const char *keywords[], const char *values[],
+								  const bool exit_on_error)
 {
 	/* Make a connection to the database */
-	PGconn *conn = PQconnectdbParams(keywords, values, true);
+	PGconn	   *conn = PQconnectdbParams(keywords, values, true);
 
 	/* Check to see that the backend connection was successfully made */
 	if ((PQstatus(conn) != CONNECTION_OK))
 	{
 		log_err(_("Connection to database failed: %s\n"),
-		        PQerrorMessage(conn));
+				PQerrorMessage(conn));
 		if (exit_on_error)
 		{
 			PQfinish(conn);
@@ -71,25 +74,22 @@ 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);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
+				PQerrorMessage(conn));
+		result = -1;
 	}
-
-	if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
-		result = true;
+	else if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
+		result = 1;
 
 	PQclear(res);
 	return result;
@@ -97,26 +97,23 @@ 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",
-	                  schema, cluster, node_id);
+					  schema, cluster, node_id);
 	res = PQexec(conn, sqlquery);
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Can't query server mode: %s"), PQerrorMessage(conn));
-		PQclear(res);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
+		result = -1;
 	}
-
-	if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
-		result = true;
+	else if (PQntuples(res) == 1 && strcmp(PQgetvalue(res, 0, 0), "t") == 0)
+		result = 1;
 
 	PQclear(res);
 	return result;
@@ -128,6 +125,7 @@ bool
 is_pgup(PGconn *conn, int timeout)
 {
 	char		sqlquery[QUERY_STR_LEN];
+
 	/* Check the connection status twice in case it changes after reset */
 	bool		twice = false;
 
@@ -138,23 +136,24 @@ is_pgup(PGconn *conn, int timeout)
 		{
 			if (twice)
 				return false;
-			PQreset(conn);  // reconnect
+			PQreset(conn);		/* reconnect */
 			twice = true;
 		}
 		else
 		{
 			/*
-			* Send a SELECT 1 just to check if the connection is OK
-			*/
-			CancelQuery(conn, timeout);
+			 * Send a SELECT 1 just to check if the connection is OK
+			 */
+			if (!cancel_query(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"), 
-								PQerrorMessage(conn));
+				log_warning(_("PQsendQuery: Query could not be sent to primary. %s\n"),
+							PQerrorMessage(conn));
 				goto failed;
 			}
 			if (wait_connection_availability(conn, timeout) != 1)
@@ -162,11 +161,15 @@ is_pgup(PGconn *conn, int timeout)
 
 			break;
 
-failed:
-			// we need to retry, because we might just have loose the connection once
+	failed:
+
+			/*
+			 * 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;
 		}
 	}
@@ -179,26 +182,25 @@ failed:
  * if 8 or inferior returns an empty string
  */
 char *
-pg_version(PGconn *conn, char* major_version)
+pg_version(PGconn *conn, char *major_version)
 {
-	PGresult	*res;
+	PGresult   *res;
 
-	int					 major_version1;
-	char				*major_version2;
+	int			major_version1;
+	char	   *major_version2;
 
 	res = PQexec(conn,
-	             "WITH pg_version(ver) AS "
-	             "(SELECT split_part(version(), ' ', 2)) "
-	             "SELECT split_part(ver, '.', 1), split_part(ver, '.', 2) "
-	             "FROM pg_version");
+				 "WITH pg_version(ver) AS "
+				 "(SELECT split_part(version(), ' ', 2)) "
+				 "SELECT split_part(ver, '.', 1), split_part(ver, '.', 2) "
+				 "FROM pg_version");
 
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Version check PQexec failed: %s"),
-		        PQerrorMessage(conn));
+				PQerrorMessage(conn));
 		PQclear(res);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
+		return NULL;
 	}
 
 	major_version1 = atoi(PQgetvalue(res, 0, 0));
@@ -208,7 +210,7 @@ pg_version(PGconn *conn, char* major_version)
 	{
 		/* form a major version string */
 		xsnprintf(major_version, MAXVERSIONSTR, "%d.%s", major_version1,
-		          major_version2);
+				  major_version2);
 	}
 	else
 		strcpy(major_version, "");
@@ -219,59 +221,92 @@ pg_version(PGconn *conn, char* major_version)
 }
 
 
-bool
-guc_setted(PGconn *conn, const char *parameter, const char *op,
-           const char *value)
+int
+guc_set(PGconn *conn, const char *parameter, const char *op,
+		const char *value)
 {
-	PGresult	*res;
+	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'",
-	                  parameter, op, value);
+					  " WHERE name = '%s' AND setting %s '%s'",
+					  parameter, op, value);
 
 	res = PQexec(conn, sqlquery);
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("GUC setting check PQexec failed: %s"),
-		        PQerrorMessage(conn));
-		PQclear(res);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
+				PQerrorMessage(conn));
+		retval = -1;
 	}
-	if (PQntuples(res) == 0)
+	else if (PQntuples(res) == 0)
 	{
-		PQclear(res);
-		return false;
+		retval = 0;
 	}
+
 	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;
 }
 
 
 const char *
 get_cluster_size(PGconn *conn)
 {
-	PGresult	*res;
-	const char	*size;
-	char		 sqlquery[QUERY_STR_LEN];
+	PGresult   *res;
+	const char *size = NULL;
+	char		sqlquery[QUERY_STR_LEN];
 
 	sqlquery_snprintf(
-	    sqlquery,
-	    "SELECT pg_size_pretty(SUM(pg_database_size(oid))::bigint) "
-	    "	 FROM pg_database ");
+					  sqlquery,
+				 "SELECT pg_size_pretty(SUM(pg_database_size(oid))::bigint) "
+					  "	 FROM pg_database ");
 
 	res = PQexec(conn, sqlquery);
 	if (PQresultStatus(res) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Get cluster size PQexec failed: %s"),
-		        PQerrorMessage(conn));
-		PQclear(res);
-		PQfinish(conn);
-		exit(ERR_DB_QUERY);
+				PQerrorMessage(conn));
 	}
-	size = PQgetvalue(res, 0, 0);
+	else
+	{
+		size = PQgetvalue(res, 0, 0);
+	}
+
 	PQclear(res);
 	return size;
 }
@@ -280,23 +315,23 @@ get_cluster_size(PGconn *conn)
  * get a connection to master by reading repl_nodes, creating a connection
  * to each node (one at a time) and finding if it is a master or a standby
  *
- * NB: If master_conninfo_out may be NULL.  If it is non-null, it is assumed to
+ * NB: If master_conninfo_out may be NULL.	If it is non-null, it is assumed to
  * point to allocated memory of MAXCONNINFO in length, and the master server
  * connection string is placed there.
  */
 PGconn *
-getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
-                    int *master_id, char *master_conninfo_out)
+get_master_connection(PGconn *standby_conn, char *schema, char *cluster,
+					  int *master_id, char *master_conninfo_out)
 {
-	PGconn		*master_conn	 = NULL;
-	PGresult	*res1;
-	PGresult	*res2;
-	char		 sqlquery[QUERY_STR_LEN];
-	char		 master_conninfo_stack[MAXCONNINFO];
-	char		*master_conninfo = &*master_conninfo_stack;
-	char		 schema_quoted[MAXLEN];
+	PGconn	   *master_conn = NULL;
+	PGresult   *res1;
+	PGresult   *res2;
+	char		sqlquery[QUERY_STR_LEN];
+	char		master_conninfo_stack[MAXCONNINFO];
+	char	   *master_conninfo = &*master_conninfo_stack;
+	char		schema_quoted[MAXLEN];
 
-	int		 i;
+	int			i;
 
 	/*
 	 * If the caller wanted to get a copy of the connection info string, sub
@@ -311,8 +346,8 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 	 * Assemble the unquoted schema name
 	 */
 	{
-		char *identifier = PQescapeIdentifier(standby_conn, schema,
-		                                      strlen(schema));
+		char	   *identifier = PQescapeIdentifier(standby_conn, schema,
+													strlen(schema));
 
 		maxlen_snprintf(schema_quoted, "%s", identifier);
 		PQfreemem(identifier);
@@ -320,20 +355,19 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 
 	/* find all nodes belonging to this cluster */
 	log_info(_("finding node list for cluster '%s'\n"),
-	         cluster);
+			 cluster);
 
 	sqlquery_snprintf(sqlquery, "SELECT id, conninfo FROM %s.repl_nodes "
-	                  " WHERE cluster = '%s' and not witness",
-	                  schema_quoted, cluster);
+					  " WHERE cluster = '%s' and not witness",
+					  schema_quoted, cluster);
 
 	res1 = PQexec(standby_conn, sqlquery);
 	if (PQresultStatus(res1) != PGRES_TUPLES_OK)
 	{
 		log_err(_("Can't get nodes info: %s\n"),
-		        PQerrorMessage(standby_conn));
+				PQerrorMessage(standby_conn));
 		PQclear(res1);
-		PQfinish(standby_conn);
-		exit(ERR_DB_QUERY);
+		return NULL;
 	}
 
 	for (i = 0; i < PQntuples(res1); i++)
@@ -342,23 +376,23 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 		*master_id = atoi(PQgetvalue(res1, i, 0));
 		strncpy(master_conninfo, PQgetvalue(res1, i, 1), MAXCONNINFO);
 		log_info(_("checking role of cluster node '%s'\n"),
-		         master_conninfo);
-		master_conn = establishDBConnection(master_conninfo, false);
+				 master_conninfo);
+		master_conn = establish_db_connection(master_conninfo, false);
 
 		if (PQstatus(master_conn) != CONNECTION_OK)
 			continue;
 
 		/*
 		 * Can't use the is_standby() function here because on error that
-		 * function closes the connection passed and exits.  This still
-		 * needs to close master_conn first.
+		 * function closes the connection passed and exits.  This still needs
+		 * to close master_conn first.
 		 */
 		res2 = PQexec(master_conn, "SELECT pg_is_in_recovery()");
 
 		if (PQresultStatus(res2) != PGRES_TUPLES_OK)
 		{
 			log_err(_("Can't get recovery state from this node: %s\n"),
-			        PQerrorMessage(master_conn));
+					PQerrorMessage(master_conn));
 			PQclear(res2);
 			PQfinish(master_conn);
 			continue;
@@ -380,14 +414,13 @@ getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
 		}
 	}
 
-	/* If we finish this loop without finding a master then
-	 * we doesn't have the info or the master has failed (or we
-	 * reached max_connections or superuser_reserved_connections,
-	 * anything else I'm missing?).
+	/*
+	 * If we finish this loop without finding a master then we doesn't have
+	 * the info or the master has failed (or we reached max_connections or
+	 * superuser_reserved_connections, anything else I'm missing?).
 	 *
-	 * Probably we will need to check the error to know if we need
-	 * to start failover procedure or just fix some situation on the
-	 * standby.
+	 * Probably we will need to check the error to know if we need to start
+	 * failover procedure or just fix some situation on the standby.
 	 */
 	PQclear(res1);
 	return NULL;
@@ -395,52 +428,102 @@ 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 
+ * wait until current query finishes ignoring any results, this could be an
+ * async command 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"), 
-							PQerrorMessage(conn));
+			log_warning(_("wait_connection_availability: could not receive data from connection. %s\n"),
+						PQerrorMessage(conn));
 			return 0;
 		}
-	
+
 		if (PQisBusy(conn) == 0)
 		{
-			res = PQgetResult(conn);
-			if (res == NULL)
-				break;
-			PQclear(res);
+			do
+			{
+				res = PQgetResult(conn);
+				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
-CancelQuery(PGconn *conn, int timeout)
+bool
+cancel_query(PGconn *conn, int timeout)
 {
-	char errbuf[ERRBUFF_SIZE];
-	PGcancel *pgcancel;
+	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
@@ -22,20 +22,25 @@
 
 #include "strutil.h"
 
-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);
-bool    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,
-                const char *value);
-const char	 *get_cluster_size(PGconn *conn);
-PGconn *getMasterConnection(PGconn *standby_conn, char *schema, char *cluster,
-                            int *master_id, char *master_conninfo_out);
+PGconn *establish_db_connection(const char *conninfo,
+						const bool exit_on_error);
+PGconn *establish_db_connection_by_params(const char *keywords[],
+								  const char *values[],
+								  const bool exit_on_error);
+int			is_standby(PGconn *conn);
+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);
+int guc_set(PGconn *conn, const char *parameter, const char *op,
+		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 *get_master_connection(PGconn *standby_conn, char *schema, char *cluster,
+					  int *master_id, char *master_conninfo_out);
+
+int			wait_connection_availability(PGconn *conn, long long timeout);
+bool		cancel_query(PGconn *conn, int timeout);
 
-int wait_connection_availability(PGconn *conn, int timeout);
-void 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
-Maintainer: Greg Smith <greg@2ndQuadrant.com>
+Depends: rsync, postgresql-9.0 | postgresql-9.1 | postgresql-9.2 | postgresql-9.3
+Maintainer: Jaime Casanova <jaime@2ndQuadrant.com>
 Description: PostgreSQL replication setup, magament and monitoring
  has two main executables

debian/repmgr.repmgrd.default

@@ -0,0 +1,18 @@
+# default settings for repmgrd. This file is source by /bin/sh from
+# /etc/init.d/repmgrd
+
+# disable repmgrd by default so it won't get started upon installation
+# valid values: yes/no
+REPMGRD_ENABLED=no
+
+# Options for repmgrd (required)
+#REPMGRD_OPTS="--config-file /path/to/repmgr.conf"
+
+# User to run repmgrd as
+#REPMGRD_USER=postgres
+
+# repmgrd binary
+#REPMGR_BIN=/usr/bin/repmgr
+
+# pid file
+#REPMGR_PIDFILE=/var/run/repmgrd.pid

debian/repmgr.repmgrd.init

@@ -0,0 +1,101 @@
+#!/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:	     $syslog postgresql
+# Default-Start:     2 3 4 5
+# Default-Stop:	     0 1 6
+# Short-Description: Start/stop repmgrd
+# Description:       Enable repmgrd replication management and monitoring daemon for PostgreSQL
+### END INIT INFO
+
+set -e
+
+DESC="PostgreSQL replication management and monitoring daemon"
+NAME=repmgrd
+
+REPMGRD_ENABLED=no
+REPMGRD_OPTS=
+REPMGRD_USER=postgres
+REPMGRD_BIN=/usr/bin/repmgrd
+REPMGRD_PIDFILE=/var/run/repmgrd.pid
+
+# Read configuration variable file if it is present
+[ -r /etc/default/$NAME ] && . /etc/default/$NAME
+
+test -x $REPMGRD_BIN || exit 0
+
+case "$REPMGRD_ENABLED" in
+    [Yy]*)
+	break
+	;;
+    *)
+	exit 0
+	;;
+esac
+
+# Define LSB log_* functions.
+. /lib/lsb/init-functions
+
+if [ -z "$REPMGRD_OPTS" ]
+then
+    log_warning_msg "Not starting $NAME, REPMGRD_OPTS not set in /etc/default/$NAME"
+    exit 0
+fi
+
+do_start()
+{
+	# Return
+	#   0 if daemon has been started
+	#   1 if daemon was already running
+	#   other if daemon could not be started or a failure occured
+	start-stop-daemon --start --quiet --background --chuid $REPMGRD_USER --make-pidfile --pidfile $REPMGRD_PIDFILE --exec $REPMGRD_BIN -- $REPMGRD_OPTS
+}
+
+do_stop()
+{
+	# Return
+	#   0 if daemon has been stopped
+	#   1 if daemon was already stopped
+	#   other if daemon could not be stopped or a failure occurred
+	start-stop-daemon --stop --quiet --retry=TERM/30/KILL/5 --pidfile $REPMGRD_PIDFILE --exec $REPMGRD_BIN
+}
+
+case "$1" in
+  start)
+	log_daemon_msg "Starting $DESC" "$NAME"
+	do_start
+	case "$?" in
+		0) log_end_msg 0 ;;
+		1) log_progress_msg "already started"
+		   log_end_msg 0 ;;
+		*) log_end_msg 1 ;;
+	esac
+
+	;;
+  stop)
+	log_daemon_msg "Stopping $DESC" "$NAME"
+	do_stop
+	case "$?" in
+		0) log_end_msg 0 ;;
+		1) log_progress_msg "already stopped"
+		   log_end_msg 0 ;;
+		*) log_end_msg 1 ;;
+	esac
+
+	;;
+  restart|force-reload)
+	$0 stop
+	$0 start
+	;;
+  status)
+	status_of_proc -p $REPMGRD_PIDFILE $REPMGRD_BIN $NAME && exit 0 || exit $?
+	;;
+  *)
+	echo "Usage: $SCRIPTNAME {start|stop|restart|force-reload|status}" >&2
+	exit 3
+	;;
+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
@@ -34,6 +34,7 @@
 #define ERR_BAD_PASSWORD 9
 #define ERR_STR_OVERFLOW 10
 #define ERR_FAILOVER_FAIL 11
-#define ERR_BAD_SSH	12
+#define ERR_BAD_SSH 12
+#define ERR_SYS_FAILURE 13
 
-#endif	/* _ERRCODE_H_ */
+#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"
@@ -37,20 +39,44 @@
 
 /* #define REPMGR_DEBUG */
 
-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)
+void
+stderr_log_with_level(const char *level_name, int level, const char *fmt, ...)
 {
+	time_t		t;
+	struct tm  *tm;
+	char		buff[100];
+	va_list		ap;
 
-	int l;
-	int f;
+	if (log_level >= level)
+	{
+		time(&t);
+		tm = localtime(&t);
+		strftime(buff, 100, "[%Y-%m-%d %H:%M:%S]", tm);
+		fprintf(stderr, "%s [%s] ", buff, level_name);
+
+		va_start(ap, fmt);
+		vfprintf(stderr, fmt, 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(t_configuration_options * opts, const char *ident, const char *level, const char *facility)
+{
+	int			l;
+	int			f;
 
 #ifdef HAVE_SYSLOG
-	int syslog_facility = DEFAULT_SYSLOG_FACILITY;
+	int			syslog_facility = DEFAULT_SYSLOG_FACILITY;
 #endif
 
 #ifdef REPMGR_DEBUG
@@ -107,21 +133,33 @@ bool logger_init(const char* ident, const char* level, const char* facility)
 
 	if (log_type == REPMGR_SYSLOG)
 	{
-		setlogmask (LOG_UPTO (log_level));
-		openlog (ident, LOG_CONS | LOG_PID | LOG_NDELAY, syslog_facility);
+		setlogmask(LOG_UPTO(log_level));
+		openlog(ident, LOG_CONS | LOG_PID | LOG_NDELAY, syslog_facility);
 
 		stderr_log_notice(_("Setup syslog (level: %s, facility: %s)\n"), level, facility);
 	}
-
 #endif
 
+	if (*opts->logfile)
+	{
+		FILE	   *fd;
+
+		fd = freopen(opts->logfile, "a", stderr);
+
+		if (fd == NULL)
+		{
+			fprintf(stderr, "error reopening stderr to '%s': %s",
+					opts->logfile, strerror(errno));
+		}
+	}
+
 	return true;
 
 }
 
-bool logger_shutdown(void)
+bool
+logger_shutdown(void)
 {
-
 #ifdef HAVE_SYSLOG
 	if (log_type == REPMGR_SYSLOG)
 		closelog();
@@ -135,13 +173,15 @@ bool logger_shutdown(void)
  * options, which might increase requested logging over what's specified
  * in the regular configuration file.
  */
-void logger_min_verbose(int minimum)
+void
+logger_min_verbose(int minimum)
 {
 	if (log_level < minimum)
 		log_level = minimum;
 }
 
-int detect_log_level(const char* level)
+int
+detect_log_level(const char *level)
 {
 	if (!strcmp(level, "DEBUG"))
 		return LOG_DEBUG;
@@ -163,40 +203,42 @@ int detect_log_level(const char* level)
 	return 0;
 }
 
-int detect_log_facility(const char* facility)
+int
+detect_log_facility(const char *facility)
 {
-	int local = 0;
+	int			local = 0;
+
 	if (!strncmp(facility, "LOCAL", 5) && strlen(facility) == 6)
 	{
 
-		local = atoi (&facility[5]);
+		local = atoi(&facility[5]);
 
 		switch (local)
 		{
-		case 0:
-			return LOG_LOCAL0;
-			break;
-		case 1:
-			return LOG_LOCAL1;
-			break;
-		case 2:
-			return LOG_LOCAL2;
-			break;
-		case 3:
-			return LOG_LOCAL3;
-			break;
-		case 4:
-			return LOG_LOCAL4;
-			break;
-		case 5:
-			return LOG_LOCAL5;
-			break;
-		case 6:
-			return LOG_LOCAL6;
-			break;
-		case 7:
-			return LOG_LOCAL7;
-			break;
+			case 0:
+				return LOG_LOCAL0;
+				break;
+			case 1:
+				return LOG_LOCAL1;
+				break;
+			case 2:
+				return LOG_LOCAL2;
+				break;
+			case 3:
+				return LOG_LOCAL3;
+				break;
+			case 4:
+				return LOG_LOCAL4;
+				break;
+			case 5:
+				return LOG_LOCAL5;
+				break;
+			case 6:
+				return LOG_LOCAL6;
+				break;
+			case 7:
+				return LOG_LOCAL7;
+				break;
 		}
 
 	}

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 +25,19 @@
 #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_info(...) if (log_level >= LOG_INFO) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_notice(...) if (log_level >= LOG_NOTICE) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_warning(...) if (log_level >= LOG_WARNING) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_err(...) if (log_level >= LOG_ERR) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_crit(...) if (log_level >= LOG_CRIT) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_alert(...) if (log_level >= LOG_ALERT) fprintf(stderr, __VA_ARGS__)
-#define stderr_log_emerg(...) if (log_level >= LOG_EMERG) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_debug(...) stderr_log_with_level("DEBUG", LOG_DEBUG, __VA_ARGS__)
+#define stderr_log_info(...)  stderr_log_with_level("INFO", LOG_INFO, __VA_ARGS__)
+#define stderr_log_notice(...) stderr_log_with_level("NOTICE", LOG_NOTICE, __VA_ARGS__)
+#define stderr_log_warning(...) stderr_log_with_level("WARNING", LOG_WARNING, __VA_ARGS__)
+#define stderr_log_err(...) stderr_log_with_level("ERROR", LOG_ERR, __VA_ARGS__)
+#define stderr_log_crit(...) stderr_log_with_level("CRITICAL", LOG_CRIT, __VA_ARGS__)
+#define stderr_log_alert(...) stderr_log_with_level("ALERT", LOG_ALERT, __VA_ARGS__)
+#define stderr_log_emerg(...) stderr_log_with_level("EMERGENCY", LOG_EMERG, __VA_ARGS__)
 
 #ifdef HAVE_SYSLOG
 
@@ -86,17 +90,16 @@
 		if (log_type == REPMGR_SYSLOG) syslog(LOG_ALERT, __VA_ARGS__); \
 		else stderr_log_alert(__VA_ARGS__); \
 	}
-
 #else
 
-#define	LOG_EMERG	0	/* system is unusable */
-#define	LOG_ALERT	1	/* action must be taken immediately */
-#define	LOG_CRIT	2	/* critical conditions */
-#define	LOG_ERR		3	/* error conditions */
-#define	LOG_WARNING	4	/* warning conditions */
-#define	LOG_NOTICE	5	/* normal but significant condition */
-#define	LOG_INFO	6	/* informational */
-#define	LOG_DEBUG	7	/* debug-level messages */
+#define LOG_EMERG	0			/* system is unusable */
+#define LOG_ALERT	1			/* action must be taken immediately */
+#define LOG_CRIT	2			/* critical conditions */
+#define LOG_ERR		3			/* error conditions */
+#define LOG_WARNING 4			/* warning conditions */
+#define LOG_NOTICE	5			/* normal but significant condition */
+#define LOG_INFO	6			/* informational */
+#define LOG_DEBUG	7			/* debug-level messages */
 
 #define log_debug(...) stderr_log_debug(__VA_ARGS__)
 #define log_info(...) stderr_log_info(__VA_ARGS__)
@@ -106,16 +109,18 @@
 #define log_crit(...) stderr_log_crit(__VA_ARGS__)
 #define log_alert(...) stderr_log_alert(__VA_ARGS__)
 #define log_emerg(...) stderr_log_emerg(__VA_ARGS__)
-
 #endif
 
 
 /* Logger initialisation and shutdown */
-bool logger_shutdown(void);
-bool logger_init(const char* ident, const char* level, const char* facility);
-void logger_min_verbose(int minimum);
+bool		logger_shutdown(void);
 
-extern int log_type;
-extern int log_level;
+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;
+extern int	log_level;
 
 #endif

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'
-follow_command='repmgr follow'
+promote_command='repmgr standby promote -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
@@ -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
@@ -50,24 +50,25 @@
 typedef struct
 {
 
-	char dbname[MAXLEN];
-	char host[MAXLEN];
-	char username[MAXLEN];
-	char dest_dir[MAXFILENAME];
-	char config_file[MAXFILENAME];
-	char remote_user[MAXLEN];
-	char wal_keep_segments[MAXLEN];
-	bool verbose;
-	bool force;
-	bool ignore_rsync_warn;
+	char		dbname[MAXLEN];
+	char		host[MAXLEN];
+	char		username[MAXLEN];
+	char		dest_dir[MAXFILENAME];
+	char		config_file[MAXFILENAME];
+	char		remote_user[MAXLEN];
+	char		wal_keep_segments[MAXLEN];
+	bool		verbose;
+	bool		force;
+	bool		wait_for_master;
+	bool		ignore_rsync_warn;
 
-	char masterport[MAXLEN];
-	char localport[MAXLEN];
+	char		masterport[MAXLEN];
+	char		localport[MAXLEN];
 
 	/* parameter used by CLUSTER CLEANUP */
-	int keep_history;
-} t_runtime_options;
+	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

@@ -15,9 +15,10 @@
 #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
+#define MAXFNAMELEN		64
 
 PG_MODULE_MAGIC;
 
@@ -26,29 +27,36 @@ PG_MODULE_MAGIC;
  */
 typedef struct repmgrSharedState
 {
-    LWLockId    lock;           		/* protects search/modification */
-    char		location[MAXFNAMELEN];	/* last known xlog location */
-} repmgrSharedState;
+	LWLockId	lock;			/* protects search/modification */
+	char		location[MAXFNAMELEN];	/* last known xlog location */
+	TimestampTz last_updated;
+}	repmgrSharedState;
 
 /* Links to shared memory state */
 static repmgrSharedState *shared_state = NULL;
 
 static shmem_startup_hook_type prev_shmem_startup_hook = NULL;
 
-void        _PG_init(void);
-void        _PG_fini(void);
+void		_PG_init(void);
+void		_PG_fini(void);
 
 static void repmgr_shmem_startup(void);
 static Size repmgr_memsize(void);
 
 static bool repmgr_set_standby_location(char *locationstr);
 
-Datum repmgr_update_standby_location(PG_FUNCTION_ARGS);
-Datum repmgr_get_last_standby_location(PG_FUNCTION_ARGS);
+Datum		repmgr_update_standby_location(PG_FUNCTION_ARGS);
+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
@@ -60,9 +68,9 @@ _PG_init(void)
 	 * In order to create our shared memory area, we have to be loaded via
 	 * shared_preload_libraries.  If not, fall out without hooking into any of
 	 * the main system.  (We don't throw error here because it seems useful to
-	 * allow the repmgr functions to be created even when the
-	 * module isn't active.  The functions must protect themselves against
-	 * being called then, however.)
+	 * allow the repmgr functions to be created even when the module isn't
+	 * active.	The functions must protect themselves against being called
+	 * then, however.)
 	 */
 	if (!process_shared_preload_libraries_in_progress)
 		return;
@@ -112,15 +120,15 @@ repmgr_shmem_startup(void)
 	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
 
 	shared_state = ShmemInitStruct("repmgr shared state",
-						   sizeof(repmgrSharedState),
-						   &found);
+								   sizeof(repmgrSharedState),
+								   &found);
 
 	if (!found)
 	{
 		/* First time through ... */
 		shared_state->lock = LWLockAssign();
 		snprintf(shared_state->location,
-				sizeof(shared_state->location), "%X/%X", 0, 0);
+				 sizeof(shared_state->location), "%X/%X", 0, 0);
 	}
 
 	LWLockRelease(AddinShmemInitLock);
@@ -133,20 +141,20 @@ repmgr_shmem_startup(void)
 static Size
 repmgr_memsize(void)
 {
-    return MAXALIGN(sizeof(repmgrSharedState));
+	return MAXALIGN(sizeof(repmgrSharedState));
 }
 
 
 static bool
 repmgr_set_standby_location(char *locationstr)
 {
-    /* Safety check... */
-    if (!shared_state)
-        return false;
+	/* Safety check... */
+	if (!shared_state)
+		return false;
 
-    LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
 	strncpy(shared_state->location, locationstr, MAXFNAMELEN);
-    LWLockRelease(shared_state->lock);
+	LWLockRelease(shared_state->lock);
 
 	return true;
 }
@@ -158,7 +166,7 @@ repmgr_set_standby_location(char *locationstr)
 Datum
 repmgr_get_last_standby_location(PG_FUNCTION_ARGS)
 {
-	char location[MAXFNAMELEN];
+	char		location[MAXFNAMELEN];
 
 	/* Safety check... */
 	if (!shared_state)
@@ -176,14 +184,49 @@ repmgr_get_last_standby_location(PG_FUNCTION_ARGS)
 Datum
 repmgr_update_standby_location(PG_FUNCTION_ARGS)
 {
-	text       *location = PG_GETARG_TEXT_P(0);
-	char       *locationstr;
+	text	   *location = PG_GETARG_TEXT_P(0);
+	char	   *locationstr;
 
-    /* Safety check... */
-    if (!shared_state)
-        PG_RETURN_BOOL(false);
+	/* Safety check... */
+	if (!shared_state)
+		PG_RETURN_BOOL(false);
 
-    locationstr = text_to_cstring(location);
+	locationstr = text_to_cstring(location);
 
 	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
@@ -25,29 +25,21 @@
 #include "log.h"
 #include "strutil.h"
 
-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)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 0)));
 
 static int
 xvsnprintf(char *str, size_t size, const char *format, va_list ap)
 {
-	int retval;
+	int			retval;
 
 	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);
+				str);
 		exit(ERR_STR_OVERFLOW);
 	}
 
@@ -56,10 +48,10 @@ xvsnprintf(char *str, size_t size, const char *format, va_list ap)
 
 
 int
-xsnprintf(char *str, size_t size, const char *format, ...)
+xsnprintf(char *str, size_t size, const char *format,...)
 {
-	va_list arglist;
-	int retval;
+	va_list		arglist;
+	int			retval;
 
 	va_start(arglist, format);
 	retval = xvsnprintf(str, size, format, arglist);
@@ -70,7 +62,7 @@ xsnprintf(char *str, size_t size, const char *format, ...)
 
 
 int
-sqlquery_snprintf(char *str, const char *format, ...)
+sqlquery_snprintf(char *str, const char *format,...)
 {
 	va_list		arglist;
 	int			retval;
@@ -83,7 +75,8 @@ sqlquery_snprintf(char *str, const char *format, ...)
 }
 
 
-int maxlen_snprintf(char *str, const char *format, ...)
+int
+maxlen_snprintf(char *str, const char *format,...)
 {
 	va_list		arglist;
 	int			retval;

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
@@ -22,7 +22,7 @@
 #define _STRUTIL_H_
 
 #include <stdlib.h>
-#include <errcode.h>
+#include "errcode.h"
 
 #define QUERY_STR_LEN	8192
 #define MAXLEN			1024
@@ -31,13 +31,16 @@
 #define MAXCONNINFO		1024
 
 
-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, ...);
+extern int
+xsnprintf(char *str, size_t size, const char *format,...)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 
-/* 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
+extern int
+sqlquery_snprintf(char *str, const char *format,...)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
 
-#endif	/* _STRUTIL_H_ */
+extern int
+maxlen_snprintf(char *str, const char *format,...)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
+
+#endif   /* _STRUTIL_H_ */

uninstall_repmgr.sql

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

version.h

@@ -1,4 +1,6 @@
 #ifndef _VERSION_H_
 #define _VERSION_H_
-#define REPMGR_VERSION "2.0beta1"
+
+#define REPMGR_VERSION "2.0.2"
+
 #endif