Bump specfile version number

And standardized nomenclature on "master" rather than "primary".

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2012, 2ndQuadrant Limited
+Copyright (c) 2010-2015, 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>

FAILOVER.rst

@@ -0,0 +1,231 @@
+====================================================
+ PostgreSQL Automatic Failover - User Documentation
+====================================================
+
+Automatic Failover
+==================
+
+repmgr allows 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 fully qualified domain name of the Master server, IP 192.168.1.10
+**node2**
+    is the fully qualified domain name of the Standby server, IP 192.168.1.11
+**witness**
+    is the fully qualified domain name of the server used as a witness, IP 192.168.1.12
+
+**Note:** We don't recommend using names with the status of a server like «masterserver»,
+because it would be confusing once a failover takes place and the Master is
+now on the «standbyserver».
+
+Summary
+-------
+
+2 PostgreSQL servers are involved in the replication.  Automatic failover needs
+a vote to decide what server it should promote, so an odd number is required.
+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 witness server)
+
+2. Install repmgr in all the servers involved (including the witness server)
+
+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 witness server)
+
+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 to 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 to node2.
+
+Clone 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 to 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 you need 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 the 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 the failover procedure.
+**reconnect_interval**
+    is the amount of time between retries to reconnect to master after a failure has been detected and before start the 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 to node1.
+
+Register the node as Master::
+
+  su - postgres
+  repmgr -f /etc/repmgr/repmgr.conf master register
+
+Log in to node2. Register it as a standby::
+
+  su - postgres
+  repmgr -f /etc/repmgr/repmgr.conf standby register
+
+Initialize witness server
+-------------------------
+
+Log in to 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
+
+The witness server needs the following information from the command
+line:
+
+* Connection details for the current master, to copy the cluster
+  configuration.
+* A location for initializing its own $PGDATA.
+
+repmgr will also ask for the superuser password on the witness database so
+it can reconnect when needed (the command line option --initdb-no-pwprompt
+will set up a password-less superuser).
+
+Start the repmgrd daemons
+-------------------------
+
+Log in to node2 and witness::
+
+  su - postgres
+  repmgrd -f /etc/repmgr/repmgr.conf --daemonize -> /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.)

FAQ.md

@@ -0,0 +1,119 @@
+FAQ - Frequently Asked Questions about repmgr
+=============================================
+
+This FAQ applies to `repmgr` 3.0 and later.
+
+General
+-------
+
+- What's the difference between the repmgr versions?
+
+  repmgr 3.x builds on the improved replication facilities added
+  in PostgreSQL 9.3, as well as improved automated failover support
+  via `repmgrd`, and is not compatible with PostgreSQL 9.2 and earlier.
+
+  repmgr 2.x supports PostgreSQL 9.0 onwards. While it is compatible
+  with  PostgreSQL 9.3 and later, we recommend repmgr v3.
+
+- What's the advantage of using replication slots?
+
+  Replication slots, introduced in PostgreSQL 9.4, ensure that the
+  master server will retain WAL files until they have been consumed
+  by all standby servers. This makes WAL file management much easier,
+  and if used `repmgr` will no longer insist on a fixed number (default: 5000)
+  of WAL files being preserved.
+
+  (However this does mean that if a standby is no longer connected to the
+  master, the master will retain WAL files indefinitely).
+
+- How many replication slots should I define in `max_replication_slots`?
+
+  Normally at least same number as the number of standbys which will connect
+  to the node. Note that changes to `max_replication_slots` require a server
+  restart to take effect, and as there is no particular penalty for unused
+  replication slots, setting a higher figure will make adding new nodes
+  easier.
+
+
+`repmgr`
+--------
+
+- When should I use the --rsync-only option?
+
+  By default, `repmgr` uses `pg_basebackup` to clone a standby from
+  a master. However, `pg_basebackup` copies the entire data directory, which
+  can take some time depending on installation size. If you have an
+  existing but "stale" standby, `repmgr` can use `rsync` instead,
+  which means only changed or added files need to be copied.
+
+- Can I register an existing master/standby?
+
+  Yes, this is no problem.
+
+- How can a failed master be re-added as a standby?
+
+  This is a two-stage process. First, the failed master's data directory
+  must be re-synced with the current master; secondly the failed master
+  needs to be re-registered as a standby. The section "Converting a failed
+  master to a standby" in the `README.md` file contains more detailed
+  information on this process.
+
+- Is there an easy way to check my master server is correctly configured
+  for use with `repmgr`?
+
+  Yes - execute `repmgr` with the `--check-upstream-config` option, and it
+  will let you know which items in `postgresql.conf` need to be modified.
+
+- Even though I specified custom `rsync` options, `repmgr` appends
+  the `--checksum` - why?
+
+  When syncing a stale data directory from an active server, it's
+  essential that `rsync` compares the content of files rather than
+  just timestamp and size, to ensure that all changed files are
+  copied and prevent corruption.
+
+- When cloning a standby, how can I prevent `repmgr` from copying
+  `postgresql.conf` and `pg_hba.conf` from the PostgreSQL configuration
+  directory in `/etc`?
+
+  Use the command line option `--ignore-external-config-files`
+
+- How can I prevent `repmgr` from copying local configuration files
+  in the data directory?
+
+  If you're updating an existing but stale data directory which
+  contains e.g. configuration files you don't want to be overwritten
+  with the same file from the master, specify the files in the
+  `rsync_options` configuration option, e.g.
+
+      rsync_options=--exclude=postgresql.local.conf
+
+  This option is only available when using the `--rsync-only` option.
+
+`repmgrd`
+---------
+
+- Do I need a witness server?
+
+  Not necessarily. However if you have an uneven number of nodes spread
+  over more than one network segment, a witness server will enable
+  better handling of a 'split brain' situation by providing a "casting
+  vote" on the preferred network segment.
+
+- How can I prevent a node from ever being promoted to master?
+
+  In `rempgr.conf`, set its priority to a value of 0 or less.
+
+- Does `repmgrd` support delayed standbys?
+
+  `repmgrd` can monitor delayed standbys - those set up with
+  `recovery_min_apply_delay` set to a non-zero value in `recovery.conf` -
+  but as it's not currently possible to directly examine the value
+  applied to the standby, `repmgrd` may not be able to properly evaluate
+  the node as a promotion candidate.
+
+  We recommend that delayed standbys are explicitly excluded from promotion
+  by setting `priority` to 0 in `repmgr.conf`.
+
+  Note that after registering a delayed standby, `repmgrd` will only start
+  once the metadata added in the master node has been replicated.

HISTORY

@@ -1,4 +1,50 @@
-2.0beta 2012-07-27
+3.0
+        Require PostgreSQL 9.3 or later (Ian)
+        Use `pg_basebackup` by default (instead of `rsync`) to clone standby servers (Ian)
+        Use `pg_ctl promote` to promote a standby to primary
+        Enable tablespace remapping using `pg_basebackup` (in PostgreSQL 9.3 with `rsync`) (Ian)
+        Support cascaded standbys (Ian)
+        "pg_bindir" no longer required as a configuration parameter (Ian)
+        Enable replication slots to be used (PostgreSQL 9.4 and later (Ian)
+        Command line option "--check-upstream-config" (Ian)
+        Add event logging table and option to execute an external program when an event occurs (Ian)
+        General usability and logging message improvements (Ian)
+        Code consolidation and cleanup (Ian)
+
+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)
@@ -7,15 +53,15 @@
         Make the monitoring optional and turned off by default, it can be turned on with --monitoring-history switch (Jaime)
         Add tunables to specify number of retries to reconnect to master and the time between them (Jaime)
 
-1.2.0	2012-07-27
+1.2.0   2012-07-27
-		Test ssh connection before trying to rsync (Cédric)
+        Test ssh connection before trying to rsync (Cédric)
         Add CLUSTER SHOW command (Carlo)
         Add CLUSTER CLEANUP command (Jaime)
         Add function write_primary_conninfo (Marco)
         Teach repmgr how to get tablespace's location in different pg version (Jaime)
-		Improve version message (Carlo)
+        Improve version message (Carlo)
 
-1.1.1	2012-04-18
+1.1.1   2012-04-18
         Add --ignore-rsync-warning (Cédric)
         Add strnlen for compatibility with OS X (Greg)
         Improve performance of the repl_status view (Jaime)
@@ -26,7 +72,7 @@
 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, 2010-2015
 
 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: install_prog install_ext
-	$(INSTALL_PROGRAM) repmgrd$(X) '$(DESTDIR)$(bindir)'
+
-	$(INSTALL_PROGRAM) repmgr$(X) '$(DESTDIR)$(bindir)'
+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
 
+

PACKAGES.md

@@ -0,0 +1,123 @@
+Packaging
+=========
+
+Notes on RedHat Linux, Fedora, and CentOS Builds
+------------------------------------------------
+
+The RPM packages of PostgreSQL put ``pg_config`` into the ``postgresql-devel``
+package, not the main server one.  And if you have a RPM install of PostgreSQL
+9.0, the entire PostgreSQL binary directory will not be in your PATH by default
+either.  Individual utilities are made available via the ``alternatives``
+mechanism, but not all commands will be wrapped that way.  The files installed
+by repmgr will certainly not be in the default PATH for the postgres user
+on such a system.  They will instead be in /usr/pgsql-9.0/bin/ on this
+type of system.
+
+When building repmgr against a RPM packaged build, you may discover that some
+development packages are needed as well.  The following build errors can
+occur::
+
+  /usr/bin/ld: cannot find -lxslt
+  /usr/bin/ld: cannot find -lpam
+
+Install the following packages to correct those::
+
+  yum install libxslt-devel
+  yum install pam-devel
+
+If building repmgr as a regular user, then doing the install into the system
+directories using sudo, the syntax is hard.  ``pg_config`` won't be in root's
+path either.  The following recipe should work::
+
+  sudo PATH="/usr/pgsql-9.0/bin:$PATH" make USE_PGXS=1 install
+
+Issues with 32 and 64 bit RPMs
+------------------------------
+
+If when building, you receive a series of errors of this form::
+
+  /usr/bin/ld: skipping incompatible /usr/pgsql-9.0/lib/libpq.so when searching for -lpq
+
+This is likely because you have both the 32 and 64 bit versions of the
+``postgresql90-devel`` package installed.  You can check that like this::
+
+  rpm -qa --queryformat '%{NAME}\t%{ARCH}\n'  | grep postgresql90-devel
+
+And if two packages appear, one for i386 and one for x86_64, that's not supposed
+to be allowed.
+
+This can happen when using the PGDG repo to install that package;
+here is an example sessions demonstrating the problem case appearing::
+
+  # yum install postgresql-devel
+  ..
+  Setting up Install Process
+  Resolving Dependencies
+  --> Running transaction check
+  ---> Package postgresql90-devel.i386 0:9.0.2-2PGDG.rhel5 set to be updated
+  ---> Package postgresql90-devel.x86_64 0:9.0.2-2PGDG.rhel5 set to be updated
+  --> Finished Dependency Resolution
+
+  Dependencies Resolved
+
+  =========================================================================
+   Package               Arch      Version              Repository    Size
+  =========================================================================
+  Installing:
+   postgresql90-devel    i386      9.0.2-2PGDG.rhel5    pgdg90        1.5 M
+   postgresql90-devel    x86_64    9.0.2-2PGDG.rhel5    pgdg90        1.6 M
+
+Note how both the i386 and x86_64 platform architectures are selected for
+installation.  Your main PostgreSQL package will only be compatible with one of
+those, and if the repmgr build finds the wrong postgresql90-devel these
+"skipping incompatible" messages appear.
+
+In this case, you can temporarily remove both packages, then just install the
+correct one for your architecture.  Example::
+
+  rpm -e postgresql90-devel --allmatches
+  yum install postgresql90-devel-9.0.2-2PGDG.rhel5.x86_64
+
+Instead just deleting the package from the wrong platform might not leave behind
+the correct files, due to the way in which these accidentally happen to interact.
+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.
+
+Notes on Ubuntu, Debian or other Debian-based Builds
+----------------------------------------------------
+
+The Debian packages of PostgreSQL put ``pg_config`` into the development package
+called ``postgresql-server-dev-$version``.
+
+When building repmgr against a Debian packages build, you may discover that some
+development packages are needed as well. You will need the following development
+packages installed::
+
+  sudo apt-get install libxslt-dev libxml2-dev libpam-dev libedit-dev
+
+If your using Debian packages for PostgreSQL and are building repmgr with the
+USE_PGXS option you also need to install the corresponding development package::
+
+  sudo apt-get install postgresql-server-dev-9.0
+
+If you build and install repmgr manually it will not be on the system path. The
+binaries will be installed in /usr/lib/postgresql/$version/bin/ which is not on
+the default path. The reason behind this is that Ubuntu/Debian systems manage
+multiple installed versions of PostgreSQL on the same system through a wrapper
+called pg_wrapper and repmgr is not (yet) known to this wrapper.
+
+You can solve this in many different ways, the most Debian like is to make an
+alternate for repmgr and repmgrd::
+
+  sudo update-alternatives --install /usr/bin/repmgr repmgr /usr/lib/postgresql/9.0/bin/repmgr 10
+  sudo update-alternatives --install /usr/bin/repmgrd repmgrd /usr/lib/postgresql/9.0/bin/repmgrd 10
+
+You can also make a deb package of repmgr using::
+
+  make USE_PGXS=1 deb
+
+This will build a Debian package one level up from where you build, normally the
+same directory that you have your repmgr/ directory in.

QUICKSTART.md

@@ -0,0 +1,114 @@
+repmgr quickstart guide
+=======================
+
+This quickstart guide provides some annotated examples on basic
+`repmgr` setup. It assumes you are familiar with PostgreSQL replication
+concepts setup and Linux/UNIX system administration.
+
+For the purposes of this guide, we'll assume the database user will be
+`repmgr_usr` and the database will be `repmgr_db`.
+
+
+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 /path/to/repmgr/node1/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
+
+   (For an annotated `repmgr.conf` file, see `repmgr.conf.sample` in the
+   repository's root directory).
+
+3. Register the master node with `repmgr`:
+
+        $ repmgr -f /path/to/repmgr/node1/repmgr.conf --verbose master register
+        [2015-03-03 17:45:53] [INFO] repmgr connecting to master database
+        [2015-03-03 17:45:53] [INFO] repmgr connected to master, checking its state
+        [2015-03-03 17:45:53] [INFO] master register: creating database objects inside the repmgr_test schema
+        [2015-03-03 17:45:53] [NOTICE] Master node correctly registered for cluster test with id 1 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
+
+Standby setup
+-------------
+
+1. Use `repmgr standby clone` to clone a standby from the master:
+
+        repmgr -D /path/to/standby/data -d repmgr_db -U repmgr_usr --verbose standby clone 192.168.1.2
+        [2015-03-03 18:18:21] [NOTICE] No configuration file provided and default file './repmgr.conf' not found - continuing with default values
+        [2015-03-03 18:18:21] [NOTICE] repmgr Destination directory ' /path/to/standby/data' provided
+        [2015-03-03 18:18:21] [INFO] repmgr connecting to upstream node
+        [2015-03-03 18:18:21] [INFO] repmgr connected to upstream node, checking its state
+        [2015-03-03 18:18:21] [INFO] Successfully connected to upstream node. Current installation size is 27 MB
+        [2015-03-03 18:18:21] [NOTICE] Starting backup...
+        [2015-03-03 18:18:21] [INFO] creating directory " /path/to/standby/data"...
+        [2015-03-03 18:18:21] [INFO] Executing: 'pg_basebackup -l "repmgr base backup"  -h localhost -p 9595 -U repmgr_usr -D  /path/to/standby/data '
+        NOTICE:  pg_stop_backup complete, all required WAL segments have been archived
+        [2015-03-03 18:18:23] [NOTICE] repmgr standby clone (using pg_basebackup) complete
+        [2015-03-03 18:18:23] [NOTICE] HINT: You can now start your postgresql server
+        [2015-03-03 18:18:23] [NOTICE] for example : pg_ctl -D  /path/to/standby/data start
+
+  Note that 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 /path/node2/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 standby node with `repmgr`:
+
+        $ repmgr -f /path/to/repmgr/node2/repmgr.conf --verbose standby register
+        [2015-03-03 18:24:34] [NOTICE] Opening configuration file: /path/to/repmgr/node2/repmgr.conf
+        [2015-03-03 18:24:34] [INFO] repmgr connecting to standby database
+        [2015-03-03 18:24:34] [INFO] repmgr connecting to master database
+        [2015-03-03 18:24:34] [INFO] finding node list for cluster 'test'
+        [2015-03-03 18:24:34] [INFO] checking role of cluster node '1'
+        [2015-03-03 18:24:34] [INFO] repmgr connected to master, checking its state
+        [2015-03-03 18:24:34] [INFO] repmgr registering the standby
+        [2015-03-03 18:24:34] [INFO] repmgr registering the standby complete
+        [2015-03-03 18:24:34] [NOTICE] Standby node correctly registered for cluster test with id 2 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
+
+
+This concludes the basic `repmgr` setup of master and standby. The records
+created in the `repl_nodes` table should look something like this:
+
+        repmgr_db=# SELECT * from repmgr_test.repl_nodes;
+         id |  type   | upstream_node_id | cluster | name  |                     conninfo                    | slot_name | priority | active
+        ----+---------+------------------+---------+-------+-------------------------------------------------+-----------+----------+--------
+          1 | primary |                  | test    | node1 | host=localhost user=repmgr_usr dbname=repmgr_db |           |        0 | t
+          2 | standby |                1 | test    | node2 | host=localhost user=repmgr_usr dbname=repmgr_db |           |        0 | t
+        (2 rows)

README.md

@@ -0,0 +1,619 @@
+repmgr: Replication Manager for PostgreSQL
+==========================================
+
+`repmgr` is an open-source tool to manage replication and failover
+between multiple PostgreSQL servers. It enhances PostgreSQL's built-in
+hot-standby capabilities with tools to set up standby servers, monitor
+replication, and perform administrative tasks such as failover or manual
+switchover operations.
+
+This document covers `repmgr 3`, which supports PostgreSQL 9.4 and 9.3.
+This version can use `pg_basebackup` to clone standby servers, supports
+replication slots and cascading replication, doesn't require a restart
+after promotion, and has many usability improvements.
+
+Please continue to use `repmgr 2` with earlier PostgreSQL 9.x versions.
+For a list of changes since `repmgr 2` and instructions on upgrading to
+`repmgr 3`, see the "Upgrading from repmgr 2" section below.
+
+Overview
+--------
+
+The `repmgr` command-line tool is used to perform administrative tasks,
+and the `repmgrd` daemon is used to optionally monitor replication and
+manage automatic failover.
+
+To get started, each PostgreSQL node in your cluster must have a
+`repmgr.conf` file. The current master node must be registered using
+`repmgr master register`. Existing standby servers can be registered
+using `repmgr standby register`. A new standby server can be created
+using `repmgr standby clone` followed by `repmgr standby register`.
+
+See the `QUICKSTART.md` file for examples of how to use these commands.
+
+Once the cluster is in operation, run `repmgr cluster show` to see the
+status of the registered primary and standby nodes. Any standby can be
+manually promoted using `repmgr standby promote`. Other standby nodes
+can be told to follow the new master using `repmgr standby follow`. We
+show examples of these commands below.
+
+Next, for detailed monitoring, you must run `repmgrd` (with the same
+configuration file) on all your nodes. Replication status information is
+stored in a custom schema along with information about registered nodes.
+You also need `repmgrd` to configure automatic failover in your cluster.
+
+See the `FAILOVER.rst` file for an explanation of how to set up
+automatic failover.
+
+Requirements
+------------
+
+`repmgr` is developed and tested on Linux and OS X, but it should work
+on any UNIX-like system which PostgreSQL itself supports.
+
+All nodes must be running the same major version of PostgreSQL, and we
+recommend that they also run the same minor version. This version of
+`repmgr` (v3) supports PostgreSQL 9.3 and 9.4.
+
+Earlier versions of `repmgr` needed password-less SSH access between
+nodes in order to clone standby servers using `rsync`. `repmgr 3` can
+use `pg_basebackup` instead in most circumstances; ssh is not required.
+
+You will need to use rsync only if your PostgreSQL configuration files
+are outside your data directory (as on Debian) and you wish these to
+be copied by `repmgr`. See the `SSH-RSYNC.md` file for details on
+configuring password-less SSH between your nodes.
+
+Installation
+------------
+
+`repmgr` must be installed on each PostgreSQL server node.
+
+* Packages
+  - PGDG publishes RPM packages for RedHat-based distributions
+  - Debian/Ubuntu provide .deb packages.
+  - See `PACKAGES.md` for details on building .deb and .rpm packages
+    from the `repmgr` source code.
+
+* Source installation
+  - `git clone https://github.com/2ndQuadrant/repmgr`
+  - Or download tar.gz files from
+    https://github.com/2ndQuadrant/repmgr/releases
+  - To install from source, run `sudo make USE_PGXS=1 install`
+
+After installation, you should be able to run `repmgr --version` and
+`repmgrd --version`. These binaries should be installed in the same
+directory as other PostgreSQL binaries, such as `psql`.
+
+Configuration
+-------------
+
+### Server configuration
+
+By default, `repmgr` uses PostgreSQL's built-in replication protocol to
+clone a primary and create a standby server. If your configuration files
+live outside your data directory, however, you will still need to set up
+password-less SSH so that rsync can be used. See the `SSH-RSYNC.md` file
+for details.
+
+### PostgreSQL configuration
+
+The primary server needs to be configured for replication with the
+following settings in `postgresql.conf`:
+
+    # Allow read-only queries on standby servers. The number of WAL
+    # senders should be larger than the number of standby servers.
+
+    hot_standby = on
+    wal_level = 'hot_standby'
+    max_wal_senders = 10
+
+    # How much WAL to retain on the primary to allow a temporarily
+    # disconnected standby to catch up again. The larger this is, the
+    # longer the standby can be disconnected. This is needed only in
+    # 9.3; in 9.4, replication slots can be used instead (see below).
+
+    wal_keep_segments = 5000
+
+    # Enable archiving, but leave it unconfigured (so that it can be
+    # configured without a restart later). Recommended, not required.
+
+    archive_mode = on
+    archive_command = 'cd .'
+
+    # You can also set additional replication parameters here, such as
+    # hot_standby_feedback or synchronous_standby_names.
+
+PostgreSQL 9.4 makes it possible to use replication slots, which means
+the value of wal_keep_segments need no longer be set. With 9.3, `repmgr`
+expects it to be set to at least 5000 (= 80GB of WAL) by default, though
+this can be overriden with the `-w N` argument.
+
+A dedicated PostgreSQL superuser account and a database in which to
+store monitoring and replication data are required. Create them by
+running the following commands:
+
+    createuser -s repmgr
+    createdb repmgr -O repmgr
+
+We recommend using the name `repmgr` for both, but you can use whatever
+name you like (and you need to set the names you chose in the `conninfo`
+string in `repmgr.conf`; see below). `repmgr` will create the schema and
+objects it needs when it connects to the server.
+
+### repmgr configuration
+
+Create a `repmgr.conf` file on each server. Here's a minimal sample:
+
+    cluster=test
+    node=1
+    node_name=node1
+    conninfo='host=repmgr_node1 user=repmgr dbname=repmgr'
+
+The `cluster` name must be the same on all nodes. The `node` (an
+integer) and `node_name` must be unique to each node.
+
+The `conninfo` string must point to repmgr's database *on this node*.
+The host must be an IP or a name that all the nodes in the cluster can
+resolve (not `localhost`!). All nodes must use the same username and
+database name, but other parameters, such as the port, can vary between
+nodes.
+
+Your `repmgr.conf` should not be stored inside the PostgreSQL data
+directory. We recommend `/etc/repmgr/repmgr.conf`, but you can place it
+anywhere and use the `-f /path/to/repmgr.conf` option to tell `repmgr`
+where it is. If not specified, `repmgr` will search for `repmgr.conf` in
+the current working directory.
+
+If your PostgreSQL binaries (`pg_ctl`, `pg_basebackup`) are not in your
+`PATH`, you can specify an alternate location in `repmgr.conf`:
+
+    pg_bindir=/path/to/postgres/bin
+
+See `repmgr.conf.sample` for an example configuration file with all
+available configuration settings annotated.
+
+### Starting up
+
+The master node must be registered first using `repmgr master register`,
+and standby servers must be registered using `repmgr standby register`;
+this inserts details about each node into the control database. Use
+`repmgr cluster show` to see the result.
+
+See the `QUICKSTART.md` file for examples of how to use these commands.
+
+Failover
+--------
+
+To promote a standby to master, on the standby execute e.g.:
+
+    repmgr -f /etc/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 e.g.:
+
+    repmgr -f /etc/repmgr/repmgr.conf --verbose standby follow
+
+See file `FAILOVER.rst` for details on setting up automated failover.
+
+
+Converting a failed master to a standby
+---------------------------------------
+
+Often it's desirable to bring a failed master back into replication
+as a standby. First, ensure that the master's PostgreSQL server is
+no longer running; then use `repmgr standby clone` to re-sync its
+data directory with the current master, e.g.:
+
+    repmgr -f /etc/repmgr/repmgr.conf \
+      --force --rsync-only \
+      -h node2 -d repmgr -U repmgr --verbose \
+      standby clone
+
+Here it's essential to use the command line options `--force`, to
+ensure `repmgr` will re-use the existing data directory, and
+`--rsync-only`, which causes `repmgr` to use `rsync` rather than
+`pg_basebackup`, as the latter can only be used to clone a fresh
+standby.
+
+The node can then be restarted.
+
+The node will then need to be re-registered with `repmgr`; again
+the `--force` option is required to update the existing record:
+
+     repmgr -f /etc/repmgr/repmgr.conf
+       --force \
+       standby register
+
+
+
+Replication management with repmgrd
+-----------------------------------
+
+`repmgrd` is a management and monitoring daemon which runs on standby nodes
+and which can automate actions such as failover and updating standbys to
+follow the new master.`repmgrd`   can be started simply with e.g.:
+
+    repmgrd -f /etc/repmgr/repmgr.conf --verbose > $HOME/repmgr/repmgr.log 2>&1
+
+or alternatively:
+
+    repmgrd -f /etc/repmgr/repmgr.conf --verbose --monitoring-history > $HOME/repmgr/repmgrd.log 2>&1
+
+which will track replication advance or lag on all registered standbys.
+
+For permanent operation, we recommend using the options `-d/--daemonize` to
+detach the `repmgrd` process, and `-p/--pid-file` to write the process PID
+to a file.
+
+Example log output (at default log level):
+
+    [2015-03-11 13:15:40] [INFO] checking cluster configuration with schema 'repmgr_test'
+    [2015-03-11 13:15:40] [INFO] checking node 2 in cluster 'test'
+    [2015-03-11 13:15:40] [INFO] reloading configuration file and updating repmgr tables
+    [2015-03-11 13:15:40] [INFO] starting continuous standby node monitoring
+
+
+Witness server
+--------------
+
+In a situation caused e.g. by a network interruption between two
+data centres, it's important to avoid a "split-brain" situation where
+both sides of the network assume they are the active segment and the
+side without an active master unilaterally promotes one of its standbys.
+
+To prevent this situation happening, it's essential to ensure that one
+network segment has a "voting majority", so other segments will know
+they're in the minority and not attempt to promote a new master. Where
+an odd number of servers exists, this is not an issue. However, if each
+network has an even number of nodes, it's necessary to provide some way
+of ensuring a majority, which is where the witness server becomes useful.
+
+This is not a fully-fledged standby node and is not integrated into
+replication, but it effectively represents the "casting vote" when
+deciding which network segment has a majority. A witness server can
+be set up using `repmgr witness create` (see below for details) and
+can run on a dedicated server or an existing node. Note that it only
+makes sense to create a witness server in conjunction with running
+`repmgrd`; the witness server will require its own `repmgrd` instance.
+
+
+Monitoring
+----------
+
+When `repmgrd` is running with the option `-m/--monitoring-history`, it will
+constantly write node status information to the `repl_monitor` table, which can
+be queried easily using the view `repl_status`:
+
+    repmgr=# SELECT * FROM repmgr_test.repl_status;
+    -[ RECORD 1 ]-------------+-----------------------------
+    primary_node              | 1
+    standby_node              | 2
+    standby_name              | node2
+    node_type                 | standby
+    active                    | t
+    last_monitor_time         | 2015-03-11 14:02:34.51713+09
+    last_wal_primary_location | 0/3012AF0
+    last_wal_standby_location | 0/3012AF0
+    replication_lag           | 0 bytes
+    replication_time_lag      | 00:00:03.463085
+    apply_lag                 | 0 bytes
+    communication_time_lag    | 00:00:00.955385
+
+
+Event logging and notifications
+-------------------------------
+
+To help understand what significant events (e.g. failure of a node) happened
+when and for what reason, `repmgr` logs such events into the `repl_events`
+table, e.g.:
+
+    repmgr_db=# SELECT * from repmgr_test.repl_events ;
+     node_id |      event       | successful |        event_timestamp        |                                      details
+    ---------+------------------+------------+-------------------------------+-----------------------------------------------------------------------------------
+           1 | master_register  | t          | 2015-03-16 17:36:21.711796+09 |
+           2 | standby_clone    | t          | 2015-03-16 17:36:31.286934+09 | Cloned from host 'localhost', port 5500; backup method: pg_basebackup; --force: N
+           2 | standby_register | t          | 2015-03-16 17:36:32.391567+09 |
+    (3 rows)
+
+
+Additionally `repmgr` can execute an external program each time an event is
+logged. This program is defined with the configuration variable
+`event_notification_command`; the command string can contain the following
+placeholders, which will be replaced with the same content which is
+written to the `repl_events` table:
+
+    %n - node id
+    %e - event type
+    %s - success (1 or 0)
+    %t - timestamp
+    %d - description
+
+Example:
+
+    event_notification_command=/path/to/some-script %n %e %s "%t" "%d"
+
+By default the program defined with `event_notification_command` will be
+executed for every event; to restrict execution to certain events, list
+these in the parameter `event_notifications`
+
+    event_notifications=master_register,standby_register
+
+Following event types currently exist:
+
+    master_register
+    standby_register
+    standby_clone
+    standby_promote
+    witness_create
+    repmgrd_start
+    repmgrd_failover_promote
+    repmgrd_failover_follow
+
+
+Cascading replication
+---------------------
+
+Cascading replication - where a standby can connect to an upstream node and not
+the master server itself - was introduced in PostgreSQL 9.2. `repmgr` and
+`repmgrd` support cascading replication by keeping track of the relationship
+between standby servers - each node record is stored with the node id of its
+upstream ("parent") server (except of course the master server).
+
+In a failover situation where the master node fails and a top-level standby
+is promoted, a standby connected to another standby will not be affected
+and continue working as normal (even if the upstream standby it's connected
+to becomes the master node). If however the node's direct upstream fails,
+the "cascaded standby" will attempt to reconnect to that node's parent.
+
+To configure standby servers for cascading replication, add the parameter
+`upstream_node` to `repmgr.conf` and set it to the id of the node it should
+connect to, e.g.:
+
+    cluster=test
+    node=2
+    node_name=node2
+    upstream_node=1
+
+Replication slots
+-----------------
+
+Replication slots were introduced with PostgreSQL 9.4 and enable standbys to
+notify the master of their WAL consumption, ensuring that the master will
+not remove any WAL files until they have been received by all standbys.
+This mitigates the requirement to manage WAL file retention using
+`wal_keep_segments` etc., with the caveat that if a standby fails, no WAL
+files will be removed until the standby's replication slot is deleted.
+
+To enable replication slots, set the boolean parameter `use_replication_slots`
+in `repmgr.conf`:
+
+    use_replication_slots=1
+
+`repmgr` will automatically generate an appropriate slot name, which is
+stored in the `repl_nodes` table.
+
+Note that `repmgr` will fail with an error if this option is specified when
+working with PostgreSQL 9.3.
+
+Further reading:
+ * http://www.postgresql.org/docs/current/interactive/warm-standby.html#STREAMING-REPLICATION-SLOTS
+ * http://blog.2ndquadrant.com/postgresql-9-4-slots/
+
+Upgrading from repmgr 2
+-----------------------
+
+`repmgr 3` is largely compatible with `repmgr 2`; the only step required
+to upgrade is to update the `repl_nodes` table to the definition needed
+by `repmgr 3`. See the file `sql/repmgr2_repmgr3.sql` for details on how
+to do this.
+
+`repmgrd` must *not* be running while `repl_nodes` is being updated.
+
+Existing `repmgr.conf` files can be retained as-is.
+
+---------------------------------------
+
+Reference
+---------
+
+### repmgr command reference
+
+Not all of these commands need the ``repmgr.conf`` file, but they need to be able to
+connect to the remote and local databases.
+
+You can teach it which is the remote database by using the -h parameter or
+as a last parameter in standby clone and standby follow. If you need to specify
+a port different then the default 5432 you can specify a -p parameter.
+Standby is always considered as localhost and a second -p parameter will indicate
+its port if is different from the default one.
+
+* `master register`
+
+    Registers a master in a cluster. This command needs to be executed before any
+    standby nodes are registered.
+
+* `standby register`
+
+    Registers a standby with `repmgr`. This command needs to be executed to enable
+    promote/follow operations and to allow `repmgrd` to work with the node.
+    An existing standby can be registered using this command.
+
+* `standby clone [node to be cloned]`
+
+    Clones a new standby node from the data directory of the master (or
+    an upstream cascading standby) using `pg_basebackup` or `rsync`.
+    Additionally it will create the `recovery.conf` file required to
+    start the server as a standby. This command does not require
+    `repmgr.conf` to be provided, but does require connection details
+    of the master or upstream server as command line parameters.
+
+    Provide the `-D/--data-dir` option to specify the destination data
+    directory; if not, the same directory path as on the source server
+    will be used. By default, `pg_basebackup` will be used to copy data
+    from the master or upstream node but this can only be used for
+    bootstrapping new installations. To update an existing but 'stale'
+    data directory (for example belonging to a failed master), `rsync`
+    must be used by specifying `--rsync-only`. In this case,
+    password-less SSH connections between servers are required.
+
+* `standby promote`
+
+    Promotes a standby to a master if the current master has failed. This
+    command requires a valid `repmgr.conf` file for the standby, either
+    specified explicitly  with `-f/--config-file` or located in the current
+    working directory; no additional arguments are required.
+
+    If the standby promotion succeeds, the server will not need to be
+    restarted. However any other standbys will need to follow the new server,
+    by using `standby follow` (see below); if `repmgrd` is active, it will
+    handle this.
+
+    This command will not function if the current master is still running.
+
+* `witness create`
+
+    Creates a witness server as a separate PostgreSQL instance. This instance
+    can be on a separate server or a server running an existing node. The
+    witness server contain a copy of the repmgr metadata tables but will not
+    be set up as a standby; instead it will update its metadata copy each
+    time a failover occurs.
+
+    Note that it only makes sense to create a witness server if `repmgrd`
+    is in use; see section "witness server" above.
+
+    By default the witness server will use port 5499 to facilitate easier setup
+    on a server running an existing node.
+
+* `standby follow`
+
+    Attaches the standby to a new master. This command requires a valid
+    `repmgr.conf` file for the standby, either specified explicitly with
+    `-f/--config-file` or located in the current working directory; no
+    additional arguments are required.
+
+    This command will force a restart of the standby server. It can only be used
+    to attach a standby to a new master node.
+
+* `cluster show`
+
+    Displays information about each node in the replication cluster. This
+    command polls each registered server and shows its role (master / standby /
+    witness) or "FAILED" if the node doesn't respond. It polls each server
+    directly and can be run on any node in the cluster; this is also useful
+    when analyzing connectivity from a particular node.
+
+    This command requires a valid `repmgr.conf` file for the node on which it is
+    executed, either specified explicitly with `-f/--config-file` or located in
+    the current working directory; no additional arguments are required.
+
+    Example:
+
+        repmgr -f /path/to/repmgr.conf cluster show
+        Role      | Connection String
+        * master  | host=node1 dbname=repmgr user=repmgr
+          standby | host=node2 dbname=repmgr user=repmgr
+          standby | host=node3 dbname=repmgr user=repmgr
+
+
+* `cluster cleanup`
+
+    Purges monitoring history from the `repl_monitor` table to prevent excessive
+    table growth. Use the `-k/--keep-history` to specify the number of days of
+    monitoring history to retain. This command can be used manually or as a
+    cronjob.
+
+    This command requires a valid `repmgr.conf` file for the node on which it is
+    executed, either specified explicitly with `-f/--config-file` or located in
+    the current working directory; no additional arguments are required.
+
+### repmgr configuration file
+
+See `repmgr.conf.sample` for an example configuration file with available
+configuration settings annotated.
+
+### 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 (generated by `repmgrd` with
+  `-m/--monitoring-history` option enabled)
+
+and one view:
+* `repl_status`
+  summarizes the latest monitoring information for each node (generated by `repmgrd` with
+  `-m/--monitoring-history` option enabled)
+
+### Error codes
+
+`repmgr` or `repmgrd` will return one of the following error codes on program
+exit:
+
+* SUCCESS (0)             Program ran successfully.
+* ERR_BAD_CONFIG (1)      Configuration file could not be parsed or was invalid
+* ERR_BAD_RSYNC (2)       An rsync call made by the program returned an error
+* ERR_NO_RESTART (4)      An attempt to restart a PostgreSQL instance failed
+* ERR_DB_CON (6)          Error when trying to connect to a database
+* ERR_DB_QUERY (7)        Error while executing a database query
+* ERR_PROMOTED (8)        Exiting program because the node has been promoted to master
+* ERR_BAD_PASSWORD (9)    Password used to connect to a database was rejected
+* ERR_STR_OVERFLOW (10)   String overflow error
+* ERR_FAILOVER_FAIL (11)  Error encountered during failover (repmgrd only)
+* ERR_BAD_SSH (12)        Error when connecting to remote host via SSH
+* ERR_SYS_FAILURE (13)    Error when forking (repmgrd only)
+* ERR_BAD_BASEBACKUP (14) Error when executing pg_basebackup
+
+
+Support and Assistance
+----------------------
+
+2ndQuadrant provides 24x7 production support for repmgr, including
+configuration assistance, installation verification and training for
+running a robust replication cluster. For further details see:
+
+* http://2ndquadrant.com/en/support/
+
+There is a mailing list/forum to discuss contributions or issues
+http://groups.google.com/group/repmgr
+
+The IRC channel #repmgr is registered with freenode.
+
+Further information is available at http://www.repmgr.org/
+
+We'd love to hear from you about how you use repmgr. Case studies and
+news are always welcome. Send us an email at info@2ndQuadrant.com, or
+send a postcard to
+
+    repmgr
+    c/o 2ndQuadrant
+    7200 The Quorum
+    Oxford Business Park North
+    Oxford
+    OX4 2JZ
+    United Kingdom
+
+Thanks from the repmgr core team.
+
+* Ian Barwick
+* Jaime Casanova
+* Abhijit Menon-Sen
+* Simon Riggs
+* Cedric Villemain
+
+Further reading
+---------------
+
+* http://blog.2ndquadrant.com/announcing-repmgr-2-0/
+* http://blog.2ndquadrant.com/managing-useful-clusters-repmgr/
+* http://blog.2ndquadrant.com/easier_postgresql_90_clusters/

RHEL/repmgr3-93.spec

@@ -0,0 +1,61 @@
+Summary: repmgr
+Name: repmgr
+Version: 3.0
+Release: 1
+License: GPLv3
+Group: System Environment/Daemons
+URL: http://repmgr.org
+Packager: Ian Barwick <ian@2ndquadrant.com>
+Vendor: 2ndQuadrant Limited
+Distribution: centos
+Source0: %{name}-%{version}.tar.gz
+BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root
+
+%description
+repmgr is a utility suite which greatly simplifies
+the process of setting up and managing replication
+using streaming replication within a cluster of
+PostgreSQL servers.
+
+%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
+* Tue Mar 10 2015 Ian Barwick ian@2ndquadrant.com>
+- build for repmgr 3.0
+* 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"

SSH-RSYNC.md

@@ -0,0 +1,35 @@
+Set up trusted copy between postgres accounts
+---------------------------------------------
+
+If you need to use rsync to clone standby servers, the postgres account
+on your master and standby servers must be each able to access the other
+using SSH without a password.
+
+First generate a ssh key, using an empty passphrase, and copy the resulting
+keys and a maching authorization file to a privledged user on the other system::
+
+  [postgres@node1]$ ssh-keygen -t rsa
+  Generating public/private rsa key pair.
+  Enter file in which to save the key (/var/lib/pgsql/.ssh/id_rsa):
+  Enter passphrase (empty for no passphrase):
+  Enter same passphrase again:
+  Your identification has been saved in /var/lib/pgsql/.ssh/id_rsa.
+  Your public key has been saved in /var/lib/pgsql/.ssh/id_rsa.pub.
+  The key fingerprint is:
+  aa:bb:cc:dd:ee:ff:aa:11:22:33:44:55:66:77:88:99 postgres@db1.domain.com
+  [postgres@node1]$ cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
+  [postgres@node1]$ chmod go-rwx ~/.ssh/*
+  [postgres@node1]$ cd ~/.ssh
+  [postgres@node1]$ scp id_rsa.pub id_rsa authorized_keys user@node2:
+
+Login as a user on the other system, and install the files into the postgres
+user's account::
+
+  [user@node2 ~]$ sudo chown postgres.postgres authorized_keys id_rsa.pub id_rsa
+  [user@node2 ~]$ sudo mkdir -p ~postgres/.ssh
+  [user@node2 ~]$ sudo chown postgres.postgres ~postgres/.ssh
+  [user@node2 ~]$ sudo mv authorized_keys id_rsa.pub id_rsa ~postgres/.ssh
+  [user@node2 ~]$ sudo chmod -R go-rwx ~postgres/.ssh
+
+Now test that ssh in both directions works.  You may have to accept some new
+known hosts in the process.

TODO

@@ -1,21 +1,25 @@
 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 better check which standby did receive most of the data
-  a working ssh connection to the destination would help find
+
-  configuration errors before disturbing the database.
+* Make the fact that a standby may be delayed a factor in the voting
+  algorithm
+
+* include support for delayed standbys
+
+* Create the repmgr user/database on "master register".
+
+* Use pg_basebackup for the data directory, and ALSO rsync for the
+configuration files.
+
+* Use pg_basebackup -X s
+  NOTE: this can be used by including `-X s` in the configuration parameter
+  `pg_basebackup_options`

autofailover_quick_setup.rst

@@ -1,213 +0,0 @@
-=====================================================
- 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.)

check_dir.c

@@ -1,6 +1,6 @@
 /*
  * check_dir.c - Directories management functions
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2015
  *
  * 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;
+	DIR		   *chkdir;
-	struct 		dirent *file;
+	struct dirent *file;
-	int         result = 1;
+	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"),
+	log_err(_("unable to 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,
+				last,
-	retval;
+				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];
+	char		path[buf_sz];
-	struct stat	 sb;
+	struct stat sb;
-	int		r;
+	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:
+		case 0:
-		/* dir not there, must create it */
+			/* dir not there, must create it */
-		log_info(_("creating directory \"%s\"...\n"), dir);
+			log_info(_("creating directory \"%s\"...\n"), dir);
 
-		if (!create_directory(dir))
+			if (!create_dir(dir))
-		{
+			{
-			log_err(_("couldn't create directory \"%s\"...\n"),
+				log_err(_("unable to create directory \"%s\"...\n"),
-			        dir);
+						dir);
-			exit(ERR_BAD_CONFIG);
+				return false;
-		}
+			}
-		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 */
 			break;
-		}
+		case 1:
-		else if (pg_dir && !force)
+			/* Present but empty, fix permissions and use it */
-		{
+			log_info(_("checking and correcting permissions on existing directory %s ...\n"),
-			log_warning(_("\nThis looks like a PostgreSQL directory.\n"
+					 dir);
-			              "If you are sure you want to clone here, "
-			              "please check there is no PostgreSQL server "
-			              "running and use the --force option\n"));
-			exit(ERR_BAD_CONFIG);
-		}
 
-		return false;
+			if (!set_dir_permissions(dir))
-	default:
+			{
-		/* Trouble accessing directory */
+				log_err(_("unable to change permissions of directory \"%s\": %s\n"),
-		log_err(_("could not access directory \"%s\": %s\n"),
+						dir, strerror(errno));
-		        dir, strerror(errno));
+				return false;
-		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 */
+				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, 2010-2015
  *
  * 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			mkdir_p(char *path, mode_t omode);
-int  check_dir(char *dir);
+int			check_dir(char *dir);
-bool create_directory(char *dir);
+bool		create_dir(char *dir);
-bool set_directory_permissions(char *dir);
+bool		set_dir_permissions(char *dir);
-bool is_pg_dir(char *dir);
+bool		is_pg_dir(char *dir);
-bool create_pgdir(char *dir, bool force);
+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, 2010-2015
  *
  * 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
@@ -17,51 +17,138 @@
  *
  */
 
+#include <sys/stat.h>			/* for stat() */
+
 #include "config.h"
 #include "log.h"
 #include "strutil.h"
 #include "repmgr.h"
 
-void
+static void parse_event_notifications_list(t_configuration_options *options, const char *arg);
+static void tablespace_list_append(t_configuration_options *options, const char *arg);
+
+
+/*
+ * parse_config()
+ *
+ * Set default options and overwrite with values from provided configuration
+ * file.
+ *
+ * Returns true if a configuration file could be parsed, otherwise false.
+ *
+ * Any configuration options changed in this function must also be changed in
+ * reload_config()
+ */
+bool
 parse_config(const char *config_file, t_configuration_options *options)
 {
-	char *s, buff[MAXLINELENGTH];
+	char	   *s,
-	char name[MAXLEN];
+				buff[MAXLINELENGTH];
-	char value[MAXLEN];
+	char		config_file_buf[MAXLEN];
+	char		name[MAXLEN];
+	char		value[MAXLEN];
+	bool 		config_file_provided = false;
+	FILE	   *fp;
 
-	FILE *fp = fopen (config_file, "r");
+	/* Sanity checks */
 
-	/* Initialize */
+	/*
+	 * If a configuration file was provided, check it exists, otherwise
+	 * emit an error
+	 */
+	if (config_file[0])
+	{
+		struct stat config;
+
+		strncpy(config_file_buf, config_file, MAXLEN);
+		canonicalize_path(config_file_buf);
+
+		if(stat(config_file_buf, &config) != 0)
+		{
+			log_err(_("provided configuration file '%s' not found: %s\n"),
+					config_file,
+					strerror(errno)
+				);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		config_file_provided = true;
+	}
+
+	/*
+	 * If no configuration file was provided, set to a default file
+	 * which `parse_config()` will attempt to read if it exists
+	 */
+	else
+	{
+		strncpy(config_file_buf, DEFAULT_CONFIG_FILE, MAXLEN);
+	}
+
+
+	fp = fopen(config_file_buf, "r");
+
+	/*
+	 * Since some commands don't require a config file at all, not having one
+	 * isn't necessarily a problem.
+	 *
+	 * If the user explictly provided a configuration file and we can't
+	 * read it we'll raise an error.
+	 *
+	 * If no configuration file was provided, we'll try and read the default\
+	 * file if it exists and is readable, but won't worry if it's not.
+	 */
+	if (fp == NULL)
+	{
+		if(config_file_provided)
+		{
+			log_err(_("unable to open provided configuration file '%s'; terminating\n"), config_file_buf);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		log_notice(_("no configuration file provided and default file '%s' not found - "
+					 "continuing with default values\n"),
+				   DEFAULT_CONFIG_FILE);
+		return false;
+	}
+
+	/* Initialize configuration options with sensible defaults */
 	memset(options->cluster_name, 0, sizeof(options->cluster_name));
 	options->node = -1;
+	options->upstream_node = NO_UPSTREAM_NODE;
 	memset(options->conninfo, 0, sizeof(options->conninfo));
 	options->failover = MANUAL_FAILOVER;
-	options->priority = 0;
+	options->priority = DEFAULT_PRIORITY;
 	memset(options->node_name, 0, sizeof(options->node_name));
 	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->pg_ctl_options, 0, sizeof(options->pg_ctl_options));
+	memset(options->pg_basebackup_options, 0, sizeof(options->pg_basebackup_options));
 
-	/* if nothing has been provided defaults to 60 */
+	/* default master_response_timeout is 60 seconds */
 	options->master_response_timeout = 60;
 
-	/* it defaults to 6 retries with a time between retries of 10s */
+	/* default to 6 reconnection attempts at intervals of 10 seconds */
 	options->reconnect_attempts = 6;
 	options->reconnect_intvl = 10;
 
-	/*
+	options->monitor_interval_secs = 2;
-	 * Since some commands don't require a config file at all, not
+	options->retry_promote_interval_secs = 300;
-	 * having one isn't necessarily a problem.
+
-	 */
+	memset(options->event_notification_command, 0, sizeof(options->event_notification_command));
-	if (fp == NULL)
+
-	{
+	options->tablespace_mapping.head = NULL;
-		log_err(_("Did not find the configuration file '%s', continuing\n"), config_file);
+	options->tablespace_mapping.tail = NULL;
-		return;
+
-	}
+
 
 	/* Read next line */
-	while ((s = fgets (buff, sizeof buff, fp)) != NULL)
+	while ((s = fgets(buff, sizeof buff, fp)) != NULL)
 	{
+		bool known_parameter = true;
+
 		/* Skip blank lines and comments */
 		if (buff[0] == '\n' || buff[0] == '#')
 			continue;
@@ -71,30 +158,39 @@ 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, "upstream_node") == 0)
+			options->upstream_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)
+			{
 				options->failover = MANUAL_FAILOVER;
+			}
 			else if (strcmp(failoverstr, "automatic") == 0)
+			{
 				options->failover = AUTOMATIC_FAILOVER;
+			}
 			else
 			{
-				log_warning(_("value for failover option is incorrect, it should be automatic or manual. Defaulting to manual.\n"));
+				log_err(_("value for 'failover' must be 'automatic' or 'manual'\n"));
-				options->failover = MANUAL_FAILOVER;
+				exit(ERR_BAD_CONFIG);
 			}
 		}
 		else if (strcmp(name, "priority") == 0)
@@ -111,76 +207,133 @@ 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->pg_ctl_options, value, MAXLEN);
+		else if (strcmp(name, "pg_basebackup_options") == 0)
+			strncpy(options->pg_basebackup_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 if (strcmp(name, "use_replication_slots") == 0)
+			options->use_replication_slots = atoi(value);
+		else if (strcmp(name, "event_notification_command") == 0)
+			strncpy(options->event_notification_command, value, MAXLEN);
+		else if (strcmp(name, "event_notifications") == 0)
+			parse_event_notifications_list(options, value);
+		else if (strcmp(name, "tablespace_mapping") == 0)
+			tablespace_list_append(options, value);
 		else
-			log_warning(_("%s/%s: Unknown name/value pair!\n"), name, value);
+		{
+			known_parameter = false;
+			log_warning(_("%s/%s: unknown name/value pair provided; ignoring\n"), name, value);
+		}
+
+		/*
+		 * Raise an error if a known parameter is provided with an empty value.
+		 * Currently there's no reason why empty parameters are needed; if
+		 * we want to accept those, we'd need to add stricter default checking,
+		 * as currently e.g. an empty `node` value will be converted to '0'.
+		 */
+		if(known_parameter == true && !strlen(value)) {
+			log_err(_("no value provided for parameter '%s'\n"), name);
+			exit(ERR_BAD_CONFIG);
+		}
 	}
 
-	/* Close file */
+	fclose(fp);
-	fclose (fp);
 
 	/* Check config settings */
-	if (strnlen(options->cluster_name, MAXLEN)==0)
+
+	/* The following checks are for the presence of the parameter */
+	if (*options->cluster_name == '\0')
 	{
-		log_err(_("Cluster name is missing. Check the configuration file.\n"));
+		log_err(_("required parameter 'cluster' was not found\n"));
 		exit(ERR_BAD_CONFIG);
 	}
 
 	if (options->node == -1)
 	{
-		log_err(_("Node information is missing. Check the configuration file.\n"));
+		log_err(_("required parameter 'node' was not found\n"));
 		exit(ERR_BAD_CONFIG);
 	}
 
+	if (*options->node_name == '\0')
+	{
+		log_err(_("required parameter 'node_name' was not found\n"));
+		exit(ERR_BAD_CONFIG);
+	}
+
+	if (*options->conninfo == '\0')
+	{
+		log_err(_("required parameter 'conninfo' was not found\n"));
+		exit(ERR_BAD_CONFIG);
+	}
+
+	/* The following checks are for valid parameter values */
 	if (options->master_response_timeout <= 0)
 	{
-		log_err(_("Master response timeout must be greater than zero. Check the configuration file.\n"));
+		log_err(_("'master_response_timeout' must be greater than zero\n"));
 		exit(ERR_BAD_CONFIG);
 	}
 
 	if (options->reconnect_attempts < 0)
 	{
-		log_err(_("Reconnect attempts must be zero or greater. Check the configuration file.\n"));
+		log_err(_("'reconnect_attempts' must be zero or greater\n"));
 		exit(ERR_BAD_CONFIG);
 	}
 
-	if (options->reconnect_intvl <= 0)
+	if (options->reconnect_intvl < 0)
 	{
-		log_err(_("Reconnect intervals must be zero or greater. Check the configuration file.\n"));
+		log_err(_("'reconnect_interval' must be zero or greater\n"));
 		exit(ERR_BAD_CONFIG);
 	}
+
+	return true;
 }
 
 
 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];
+
+	/* If string is empty, no action needed */
+	if(s2 < s1)
+		return s;
 
 	/* 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			i = 0;
-	int j = 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 +346,7 @@ 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')
@@ -205,97 +358,363 @@ 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;
+	bool	  config_changed = false;
 
 	/*
 	 * Re-read the configuration file: repmgr.conf
 	 */
-	log_info(_("Reloading configuration file and updating repmgr tables\n"));
+	log_info(_("reloading configuration file and updating repmgr tables\n"));
+
 	parse_config(config_file, &new_options);
 	if (new_options.node == -1)
 	{
-		log_warning(_("\nCannot load new configuration, will keep current one.\n"));
+		log_warning(_("unable to parse new configuration, retaining current configuration\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(_("unable to change cluster name, retaining 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(_("unable to change node ID, retaining 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(_("unable to change standby name, keeping 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' must be 'automatic' or 'manual'\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' must 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' must be zero or greater\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' must be zero or greater\n"));
 		return false;
 	}
 
-	/* Test conninfo string */
+	if(strcmp(orig_options->conninfo, new_options.conninfo) != 0)
-	conn = establishDBConnection(new_options.conninfo, false);
-	if (!conn || (PQstatus(conn) != CONNECTION_OK))
 	{
-		log_warning(_("\nconninfo string is not valid, will keep current configuration.\n"));
+		/* Test conninfo string */
-		return false;
+		conn = establish_db_connection(new_options.conninfo, false);
+		if (!conn || (PQstatus(conn) != CONNECTION_OK))
+		{
+			log_warning(_("'conninfo' string is not valid, retaining current configuration\n"));
+			return false;
+		}
+		PQfinish(conn);
+	}
+
+	/*
+	 * No configuration problems detected - copy any changed values
+	 *
+	 * NB: keep these in the same order as in config.h to make it easier
+	 * to manage them
+	 */
+
+	/* cluster_name */
+	if(strcmp(orig_options->cluster_name, new_options.cluster_name) != 0)
+	{
+		strcpy(orig_options->cluster_name, new_options.cluster_name);
+		config_changed = true;
+	}
+
+	/* conninfo */
+	if(strcmp(orig_options->conninfo, new_options.conninfo) != 0)
+	{
+		strcpy(orig_options->conninfo, new_options.conninfo);
+		config_changed = true;
+	}
+
+	/* node */
+	if(orig_options->node != new_options.node)
+	{
+		orig_options->node = new_options.node;
+		config_changed = true;
+	}
+
+	/* failover */
+	if(orig_options->failover != new_options.failover)
+	{
+		orig_options->failover = new_options.failover;
+		config_changed = true;
+	}
+
+	/* priority */
+	if(orig_options->priority != new_options.priority)
+	{
+		orig_options->priority = new_options.priority;
+		config_changed = true;
+	}
+
+	/* node_name */
+	if(strcmp(orig_options->node_name, new_options.node_name) != 0)
+	{
+		strcpy(orig_options->node_name, new_options.node_name);
+		config_changed = true;
+	}
+
+	/* promote_command */
+	if(strcmp(orig_options->promote_command, new_options.promote_command) != 0)
+	{
+		strcpy(orig_options->promote_command, new_options.promote_command);
+		config_changed = true;
+	}
+
+	/* follow_command */
+	if(strcmp(orig_options->follow_command, new_options.follow_command) != 0)
+	{
+		strcpy(orig_options->follow_command, new_options.follow_command);
+		config_changed = true;
 	}
-	PQfinish(conn);
 
-	/* Configuration seems ok, will load new values */
-	strcpy(orig_options->cluster_name, new_options.cluster_name);
-	orig_options->node = new_options.node;
-	strcpy(orig_options->conninfo, new_options.conninfo);
-	orig_options->failover = new_options.failover;
-	orig_options->priority = new_options.priority;
-	strcpy(orig_options->node_name, new_options.node_name);
-	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);
-	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);
+	/* rsync_options */
-		strcpy (orig_options->logfacility, new_options.logfacility);
+	if(strcmp(orig_options->rsync_options, new_options.rsync_options) != 0)
+	{
+		strcpy(orig_options->rsync_options, new_options.rsync_options);
+		config_changed = true;
+	}
 
-		logger_shutdown();
+	/* ssh_options */
-		XXX do we have progname here ?
+	if(strcmp(orig_options->ssh_options, new_options.ssh_options) != 0)
-		logger_init(progname, orig_options.loglevel, orig_options.logfacility);
+	{
-	*/
+		strcpy(orig_options->ssh_options, new_options.ssh_options);
+		config_changed = true;
+	}
 
-	return true;
+	/* master_response_timeout */
+	if(orig_options->master_response_timeout != new_options.master_response_timeout)
+	{
+		orig_options->master_response_timeout = new_options.master_response_timeout;
+		config_changed = true;
+	}
+
+	/* reconnect_attempts */
+	if(orig_options->reconnect_attempts != new_options.reconnect_attempts)
+	{
+		orig_options->reconnect_attempts = new_options.reconnect_attempts;
+		config_changed = true;
+	}
+
+	/* reconnect_intvl */
+	if(orig_options->reconnect_intvl != new_options.reconnect_intvl)
+	{
+		orig_options->reconnect_intvl = new_options.reconnect_intvl;
+		config_changed = true;
+	}
+
+	/* pg_ctl_options */
+	if(strcmp(orig_options->pg_ctl_options, new_options.pg_ctl_options) != 0)
+	{
+		strcpy(orig_options->pg_ctl_options, new_options.pg_ctl_options);
+		config_changed = true;
+	}
+
+	/* pg_basebackup_options */
+	if(strcmp(orig_options->pg_basebackup_options, new_options.pg_basebackup_options) != 0)
+	{
+		strcpy(orig_options->pg_basebackup_options, new_options.pg_basebackup_options);
+		config_changed = true;
+	}
+
+	/* monitor_interval_secs */
+	if(orig_options->monitor_interval_secs != new_options.monitor_interval_secs)
+	{
+		orig_options->monitor_interval_secs = new_options.monitor_interval_secs;
+		config_changed = true;
+	}
+
+	/* retry_promote_interval_secs */
+	if(orig_options->retry_promote_interval_secs != new_options.retry_promote_interval_secs)
+	{
+		orig_options->retry_promote_interval_secs = new_options.retry_promote_interval_secs;
+		config_changed = true;
+	}
+
+	/* use_replication_slots */
+	if(orig_options->use_replication_slots != new_options.use_replication_slots)
+	{
+		orig_options->use_replication_slots = new_options.use_replication_slots;
+		config_changed = true;
+	}
+
+	if(config_changed == true)
+	{
+		log_debug(_("reload_config(): configuration has changed\n"));
+	}
+	else
+	{
+		log_debug(_("reload_config(): configuration has not changed\n"));
+	}
+
+	return config_changed;
+}
+
+
+
+/*
+ * Split argument into old_dir and new_dir and append to tablespace mapping
+ * list.
+ *
+ * Adapted from pg_basebackup.c
+ */
+static void
+tablespace_list_append(t_configuration_options *options, const char *arg)
+{
+	TablespaceListCell *cell;
+	char	   *dst;
+	char	   *dst_ptr;
+	const char *arg_ptr;
+
+	cell = (TablespaceListCell *) pg_malloc0(sizeof(TablespaceListCell));
+	if(cell == NULL)
+	{
+		log_err(_("unable to allocate memory; terminating\n"));
+		exit(ERR_BAD_CONFIG);
+	}
+
+	dst_ptr = dst = cell->old_dir;
+	for (arg_ptr = arg; *arg_ptr; arg_ptr++)
+	{
+		if (dst_ptr - dst >= MAXPGPATH)
+		{
+			log_err(_("directory name too long\n"));
+			exit(ERR_BAD_CONFIG);
+		}
+
+		if (*arg_ptr == '\\' && *(arg_ptr + 1) == '=')
+			;					/* skip backslash escaping = */
+		else if (*arg_ptr == '=' && (arg_ptr == arg || *(arg_ptr - 1) != '\\'))
+		{
+			if (*cell->new_dir)
+			{
+				log_err(_("multiple \"=\" signs in tablespace mapping\n"));
+				exit(ERR_BAD_CONFIG);
+			}
+			else
+			{
+				dst = dst_ptr = cell->new_dir;
+			}
+		}
+		else
+			*dst_ptr++ = *arg_ptr;
+	}
+
+	if (!*cell->old_dir || !*cell->new_dir)
+	{
+		log_err(_("invalid tablespace mapping format \"%s\", must be \"OLDDIR=NEWDIR\"\n"),
+				arg);
+		exit(ERR_BAD_CONFIG);
+	}
+
+	canonicalize_path(cell->old_dir);
+	canonicalize_path(cell->new_dir);
+
+	if (options->tablespace_mapping.tail)
+		options->tablespace_mapping.tail->next = cell;
+	else
+		options->tablespace_mapping.head = cell;
+
+	options->tablespace_mapping.tail = cell;
+}
+
+/*
+ * parse_event_notifications_list()
+ *
+ *
+ */
+
+static void
+parse_event_notifications_list(t_configuration_options *options, const char *arg)
+{
+	const char *arg_ptr;
+	char	    event_type_buf[MAXLEN] = "";
+	char	   *dst_ptr = event_type_buf;
+
+
+	for (arg_ptr = arg; arg_ptr <= (arg + strlen(arg)); arg_ptr++)
+	{
+		/* ignore whitespace */
+		if(*arg_ptr == ' ' || *arg_ptr == '\t')
+		{
+			continue;
+		}
+
+		/*
+		 * comma (or end-of-string) should mark the end of an event type -
+		 * just as long as there was something preceding it
+		 */
+		if((*arg_ptr == ',' || *arg_ptr == '\0') && event_type_buf[0] != '\0')
+		{
+			EventNotificationListCell *cell;
+
+			cell = (EventNotificationListCell *) pg_malloc0(sizeof(EventNotificationListCell));
+
+			if(cell == NULL)
+			{
+				log_err(_("unable to allocate memory; terminating\n"));
+				exit(ERR_BAD_CONFIG);
+			}
+
+			strncpy(cell->event_type, event_type_buf, MAXLEN);
+
+			if (options->event_notifications.tail)
+			{
+				options->event_notifications.tail->next = cell;
+			}
+			else
+			{
+				options->event_notifications.head = cell;
+			}
+
+			options->event_notifications.tail = cell;
+
+			memset(event_type_buf, 0, MAXLEN);
+			dst_ptr = event_type_buf;
+		}
+		/* ignore duplicated commas */
+		else if(*arg_ptr == ',')
+		{
+			continue;
+		}
+		else
+		{
+			*dst_ptr++ = *arg_ptr;
+		}
+	}
 }

config.h

@@ -1,6 +1,6 @@
 /*
  * config.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2015
  *
  * 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
@@ -20,30 +20,72 @@
 #ifndef _REPMGR_CONFIG_H_
 #define _REPMGR_CONFIG_H_
 
-#include "repmgr.h"
+#include "postgres_fe.h"
+
 #include "strutil.h"
 
+
+typedef struct EventNotificationListCell
+{
+	struct EventNotificationListCell *next;
+	char event_type[MAXLEN];
+} EventNotificationListCell;
+
+typedef struct EventNotificationList
+{
+	EventNotificationListCell *head;
+	EventNotificationListCell *tail;
+} EventNotificationList;
+
+typedef struct TablespaceListCell
+{
+	struct TablespaceListCell *next;
+	char		old_dir[MAXPGPATH];
+	char		new_dir[MAXPGPATH];
+} TablespaceListCell;
+
+typedef struct TablespaceList
+{
+	TablespaceListCell *head;
+	TablespaceListCell *tail;
+} TablespaceList;
+
 typedef struct
 {
-	char cluster_name[MAXLEN];
+	char		cluster_name[MAXLEN];
-	int node;
+	int			node;
-	char conninfo[MAXLEN];
+	int         upstream_node;
-	int failover;
+	char		conninfo[MAXLEN];
-	int priority;
+	int			failover;
-	char node_name[MAXLEN];
+	int			priority;
-	char promote_command[MAXLEN];
+	char		node_name[MAXLEN];
-	char follow_command[MAXLEN];
+	char		promote_command[MAXLEN];
-	char loglevel[MAXLEN];
+	char		follow_command[MAXLEN];
-	char logfacility[MAXLEN];
+	char		loglevel[MAXLEN];
-	char rsync_options[QUERY_STR_LEN];
+	char		logfacility[MAXLEN];
-	int  master_response_timeout;
+	char		rsync_options[QUERY_STR_LEN];
-	int  reconnect_attempts;
+	char		ssh_options[QUERY_STR_LEN];
-	int  reconnect_intvl;
+	int			master_response_timeout;
-} t_configuration_options;
+	int			reconnect_attempts;
+	int			reconnect_intvl;
+	char		pg_bindir[MAXLEN];
+	char		pg_ctl_options[MAXLEN];
+	char		pg_basebackup_options[MAXLEN];
+	char		logfile[MAXLEN];
+	int			monitor_interval_secs;
+	int			retry_promote_interval_secs;
+	int			use_replication_slots;
+	char		event_notification_command[MAXLEN];
+	EventNotificationList event_notifications;
+	TablespaceList tablespace_mapping;
+}	t_configuration_options;
 
-void parse_config(const char *config_file, t_configuration_options *options);
+#define T_CONFIGURATION_OPTIONS_INITIALIZER { "", -1, NO_UPSTREAM_NODE, "", MANUAL_FAILOVER, -1, "", "", "", "", "", "", "", -1, -1, -1, "", "", "", "", 0, 0, 0, "", { NULL, NULL }, {NULL, NULL} }
-void parse_line(char *buff, char *name, char *value);
+
-char *trim(char *s);
+
-bool reload_configuration(char *config_file, t_configuration_options *orig_options);
+bool		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.h

@@ -1,6 +1,6 @@
 /*
  * dbutils.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2015
  *
  * 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
@@ -20,22 +20,49 @@
 #ifndef _REPMGR_DBUTILS_H_
 #define _REPMGR_DBUTILS_H_
 
+#include "config.h"
 #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);
 
-int wait_connection_availability(PGconn *conn, int timeout);
+
-void CancelQuery(PGconn *conn, int timeout);
+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);
+bool		check_cluster_schema(PGconn *conn);
+int			is_standby(PGconn *conn);
+bool		is_pgup(PGconn *conn, int timeout);
+int			get_master_node_id(PGconn *conn, char *cluster);
+int			get_server_version(PGconn *conn, char *server_version);
+bool		get_cluster_size(PGconn *conn, char *size);
+bool		get_pg_setting(PGconn *conn, const char *setting, char *output);
+
+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);
+
+PGconn     *get_upstream_connection(PGconn *standby_conn, char *cluster,
+									int node_id,
+									int *upstream_node_id_ptr,
+									char *upstream_conninfo_out);
+PGconn	   *get_master_connection(PGconn *standby_conn, 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);
+char       *get_repmgr_schema(void);
+char       *get_repmgr_schema_quoted(PGconn *conn);
+bool		create_replication_slot(PGconn *conn, char *slot_name);
+
+bool		start_backup(PGconn *conn, char *first_wal_segment, bool fast_checkpoint);
+bool		stop_backup(PGconn *conn, char *last_wal_segment);
+bool		set_config_bool(PGconn *conn, const char *config_param, bool state);
+bool		copy_configuration(PGconn *masterconn, PGconn *witnessconn, char *cluster_name);
+bool		create_node_record(PGconn *conn, char *action, int node, char *type, int upstream_node, char *cluster_name, char *node_name, char *conninfo, int priority, char *slot_name);
+bool		delete_node_record(PGconn *conn, int node, char *action);
+bool        create_event_record(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details);
+
+
 #endif

debian/DEBIAN/control

@@ -1,9 +1,9 @@
 Package: repmgr-auto
-Version: 1.0-1
+Version: 2.0beta2
 Section: database
 Priority: optional
 Architecture: all
-Depends: rsync, postgresql-9.0
+Depends: rsync, postgresql-9.0 | postgresql-9.1 | postgresql-9.2 | postgresql-9.3 | postgresql-9.4
-Maintainer: Greg Smith <greg@2ndQuadrant.com>
+Maintainer: Jaime Casanova <jaime@2ndQuadrant.com>
 Description: PostgreSQL replication setup, magament and monitoring
  has two main executables

debian/repmgr.repmgrd.default

@@ -0,0 +1,18 @@
+# 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, 2010-2015
  *
  * 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 +25,15 @@
 #define SUCCESS 0
 #define ERR_BAD_CONFIG 1
 #define ERR_BAD_RSYNC 2
-#define ERR_STOP_BACKUP 3
 #define ERR_NO_RESTART 4
-#define ERR_NEEDS_XLOG 5
 #define ERR_DB_CON 6
 #define ERR_DB_QUERY 7
 #define ERR_PROMOTED 8
 #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
+#define ERR_BAD_BASEBACKUP 14
 
-#endif	/* _ERRCODE_H_ */
+#endif   /* _ERRCODE_H_ */

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2015
  *
  * 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);
+void
-static int detect_log_facility(const char* facility);
+stderr_log_with_level(const char *level_name, int level, const char *fmt, ...)
-
-int log_type = REPMGR_STDERR;
-int log_level = LOG_NOTICE;
-
-bool logger_init(const char* ident, const char* level, const char* facility)
 {
+	time_t		t;
+	struct tm  *tm;
+	char		buff[100];
+	va_list		ap;
 
-	int l;
+	if (log_level >= level)
-	int f;
+	{
+		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));
+		setlogmask(LOG_UPTO(log_level));
-		openlog (ident, LOG_CONS | LOG_PID | LOG_NDELAY, syslog_facility);
+		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:
+			case 0:
-			return LOG_LOCAL0;
+				return LOG_LOCAL0;
-			break;
+				break;
-		case 1:
+			case 1:
-			return LOG_LOCAL1;
+				return LOG_LOCAL1;
-			break;
+				break;
-		case 2:
+			case 2:
-			return LOG_LOCAL2;
+				return LOG_LOCAL2;
-			break;
+				break;
-		case 3:
+			case 3:
-			return LOG_LOCAL3;
+				return LOG_LOCAL3;
-			break;
+				break;
-		case 4:
+			case 4:
-			return LOG_LOCAL4;
+				return LOG_LOCAL4;
-			break;
+				break;
-		case 5:
+			case 5:
-			return LOG_LOCAL5;
+				return LOG_LOCAL5;
-			break;
+				break;
-		case 6:
+			case 6:
-			return LOG_LOCAL6;
+				return LOG_LOCAL6;
-			break;
+				break;
-		case 7:
+			case 7:
-			return LOG_LOCAL7;
+				return LOG_LOCAL7;
-			break;
+				break;
 		}
 
 	}

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2015
  *
  * 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_debug(...) stderr_log_with_level("DEBUG", LOG_DEBUG, __VA_ARGS__)
-#define stderr_log_info(...) if (log_level >= LOG_INFO) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_info(...)  stderr_log_with_level("INFO", LOG_INFO, __VA_ARGS__)
-#define stderr_log_notice(...) if (log_level >= LOG_NOTICE) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_notice(...) stderr_log_with_level("NOTICE", LOG_NOTICE, __VA_ARGS__)
-#define stderr_log_warning(...) if (log_level >= LOG_WARNING) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_warning(...) stderr_log_with_level("WARNING", LOG_WARNING, __VA_ARGS__)
-#define stderr_log_err(...) if (log_level >= LOG_ERR) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_err(...) stderr_log_with_level("ERROR", LOG_ERR, __VA_ARGS__)
-#define stderr_log_crit(...) if (log_level >= LOG_CRIT) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_crit(...) stderr_log_with_level("CRITICAL", LOG_CRIT, __VA_ARGS__)
-#define stderr_log_alert(...) if (log_level >= LOG_ALERT) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_alert(...) stderr_log_with_level("ALERT", LOG_ALERT, __VA_ARGS__)
-#define stderr_log_emerg(...) if (log_level >= LOG_EMERG) fprintf(stderr, __VA_ARGS__)
+#define stderr_log_emerg(...) stderr_log_with_level("EMERGENCY", LOG_EMERG, __VA_ARGS__)
 
 #ifdef HAVE_SYSLOG
 
@@ -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_EMERG	0			/* system is unusable */
-#define	LOG_ALERT	1	/* action must be taken immediately */
+#define LOG_ALERT	1			/* action must be taken immediately */
-#define	LOG_CRIT	2	/* critical conditions */
+#define LOG_CRIT	2			/* critical conditions */
-#define	LOG_ERR		3	/* error conditions */
+#define LOG_ERR		3			/* error conditions */
-#define	LOG_WARNING	4	/* warning conditions */
+#define LOG_WARNING 4			/* warning conditions */
-#define	LOG_NOTICE	5	/* normal but significant condition */
+#define LOG_NOTICE	5			/* normal but significant condition */
-#define	LOG_INFO	6	/* informational */
+#define LOG_INFO	6			/* informational */
-#define	LOG_DEBUG	7	/* debug-level messages */
+#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_shutdown(void);
-bool logger_init(const char* ident, const char* level, const char* facility);
-void logger_min_verbose(int minimum);
 
-extern int log_type;
+bool logger_init(t_configuration_options * opts, const char *ident,
-extern int log_level;
+			const char *level, const char *facility);
+
+void		logger_min_verbose(int minimum);
+
+extern int	log_type;
+extern int	log_level;
 
 #endif

repmgr.conf.sample

@@ -1,17 +1,111 @@
 ###################################################
-# Replication Manager configuration file
+# Replication Manager sample configuration file
 ###################################################
 
+# Required configuration items
+# ============================
+#
+# repmgr and repmgrd require these items to be configured:
+
 # Cluster name
 cluster=test
 
-# Node ID
+# Node ID and name
+# (Note: we recommend to avoid naming nodes after their initial
+#  replication funcion, as this will cause confusion when e.g.
+#  "standby2" is promoted to master)
 node=2
-node_name=standby2
+node_name=node2
 
-# Connection information
+# Database connection information
-conninfo='host=192.168.204.104'
+conninfo='host=192.168.204.104 dbname=repmgr_db user=repmgr_usr'
-rsync_options=--archive --checksum --compress --progress --rsh=ssh
+
+# Optional configuration items
+# ============================
+
+# Replication settings
+# ---------------------
+
+# when using cascading replication and a standby is to be connected to an
+# upstream standby, specify that node's ID with 'upstream_node'. The node
+# must exist before the new standby can be registered. If a standby is
+# to connect directly to a master node, this parameter is not required.
+#
+# upstream_node=1
+
+# physical replication slots - PostgreSQL 9.4 and later only
+# (default: 0)
+#
+# use_replication_slots=0
+
+
+# Logging and monitoring settings
+# -------------------------------
+
+# Log level: possible values are DEBUG, INFO, NOTICE, WARNING, ERR, ALERT, CRIT or EMERG
+# (default: NOTICE)
+loglevel=NOTICE
+
+# Logging facility: possible values are STDERR or - for Syslog integration - one of LOCAL0, LOCAL1, ..., LOCAL7, USER
+# (default: STDERR)
+logfacility=STDERR
+
+# stderr can be redirected to an arbitrary file:
+#
+# logfile='/var/log/repmgr.log'
+
+# event notifications can be passed to an arbitrary external program
+# together with the following parameters:
+#
+#   %n - node ID
+#   %e - event type
+#   %s - success (1 or 0)
+#   %t - timestamp
+#   %d - details
+#
+# the values provided for "%t" and "%d" will probably contain spaces,
+# so should be quoted in the provided command configuration, e.g.:
+#
+# event_notification_command='/path/to/some/script %n %e %s "%t" "%d"'
+
+# By default, all notifications will be passed; the notification types
+# can be filtered to explicitly named ones:
+#
+# event_notifications=master_register,standby_register,witness_create
+
+
+# Environment/command settings
+# ----------------------------
+
+# path to PostgreSQL binary directory (location of pg_ctl, pg_basebackup etc.)
+# (if not provided, defaults to system $PATH)
+# pg_bindir=/usr/bin/
+
+# external command options
+
+# rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
+# ssh_options=-o "StrictHostKeyChecking no"
+
+# external command arguments
+
+# pg_ctl_options='-s'
+# pg_basebackup_options='--xlog-method=s'
+
+
+# Standby clone settings
+# ----------------------
+#
+# These settings apply when cloning a standby (`repmgr standby clone`).
+
+# Tablespaces can be remapped from one file system location to another:
+#
+# tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
+
+
+# Failover settings (repmgrd)
+# ---------------------------
+#
+# These settings are only applied when repmgrd is running.
 
 # How many seconds we wait for master response before declaring master failure
 master_response_timeout=60
@@ -21,15 +115,20 @@ reconnect_attempts=6
 reconnect_interval=10
 
 # Autofailover options
-failover=automatic
+failover=automatic  # one of 'automatic', 'manual'
-priority=-1
+priority=100        # a value of zero or less prevents the node being promoted to master
-promote_command='repmgr promote'
+promote_command='repmgr standby promote -f /path/to/repmgr.conf'
-follow_command='repmgr follow'
+follow_command='repmgr standby follow -f /path/to/repmgr.conf -W'
+
+# 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 'reconnect_attempts' * 'retry_promote_interval_secs'
+# seconds; by default this would be half an hour, as 'retry_promote_interval_secs'
+# default value is 300)
+#
+# retry_promote_interval_secs=300
 
-# Log level: possible values are DEBUG, INFO, NOTICE, WARNING, ERR, ALERT, CRIT or EMERG
-# Default: NOTICE
-loglevel=NOTICE
 
-# Logging facility: possible values are STDERR or - for Syslog integration - one of LOCAL0, LOCAL1, ..., LOCAL7, USER
-# Default: STDERR
-logfacility=STDERR

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2012
+ * Copyright (c) 2ndQuadrant, 2010-2015
  *
  * 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
@@ -21,20 +21,22 @@
 #define _REPMGR_H_
 
 #include "postgres_fe.h"
-#include "getopt_long.h"
 #include "libpq-fe.h"
 
+
+#include "getopt_long.h"
+
 #include "strutil.h"
 #include "dbutils.h"
 #include "errcode.h"
+#include "config.h"
 
-#define PRIMARY_MODE		0
+#define MIN_SUPPORTED_VERSION		"9.3"
-#define STANDBY_MODE		1
+#define MIN_SUPPORTED_VERSION_NUM	90300
-#define WITNESS_MODE		2
 
 #include "config.h"
 #define MAXFILENAME		1024
-#define ERRBUFF_SIZE		512
+#define ERRBUFF_SIZE	512
 
 #define DEFAULT_CONFIG_FILE		"./repmgr.conf"
 #define DEFAULT_WAL_KEEP_SEGMENTS	"5000"
@@ -42,32 +44,68 @@
 #define DEFAULT_MASTER_PORT		"5432"
 #define DEFAULT_DBNAME			"postgres"
 #define DEFAULT_REPMGR_SCHEMA_PREFIX	"repmgr_"
+#define DEFAULT_PRIORITY		100
+#define FAILOVER_NODES_MAX_CHECK 50
 
 #define MANUAL_FAILOVER		0
 #define AUTOMATIC_FAILOVER	1
+#define NO_UPSTREAM_NODE	-1
+
+
+typedef enum {
+    UNKNOWN = 0,
+	MASTER,
+	STANDBY,
+	WITNESS
+} t_server_type;
+
+
 
 /* Run time options type */
 typedef struct
 {
 
-	char dbname[MAXLEN];
+	char		dbname[MAXLEN];
-	char host[MAXLEN];
+	char		host[MAXLEN];
-	char username[MAXLEN];
+	char		username[MAXLEN];
-	char dest_dir[MAXFILENAME];
+	char		dest_dir[MAXFILENAME];
-	char config_file[MAXFILENAME];
+	char		config_file[MAXFILENAME];
-	char remote_user[MAXLEN];
+	char		remote_user[MAXLEN];
-	char wal_keep_segments[MAXLEN];
+	char		superuser[MAXLEN];
-	bool verbose;
+	char		wal_keep_segments[MAXLEN];
-	bool force;
+	bool		verbose;
-	bool ignore_rsync_warn;
+	bool		force;
-
+	bool		wait_for_master;
-	char masterport[MAXLEN];
+	bool		ignore_rsync_warn;
-	char localport[MAXLEN];
+	bool		initdb_no_pwprompt;
+	bool		rsync_only;
+	bool		fast_checkpoint;
+	bool		ignore_external_config_files;
+	char		masterport[MAXLEN];
+	char		localport[MAXLEN];
 
 	/* parameter used by CLUSTER CLEANUP */
-	int keep_history;
+	int			keep_history;
-} t_runtime_options;
 
-#define SLEEP_MONITOR		2
+	char		pg_bindir[MAXLEN];
+
+	char		recovery_min_apply_delay[MAXLEN];
+}	t_runtime_options;
+
+#define T_RUNTIME_OPTIONS_INITIALIZER { "", "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, false, false, false, false, false, "", "", 0, "", "" }
+
+extern char		repmgr_schema[MAXLEN];
+
+typedef struct ErrorListCell
+{
+	struct ErrorListCell *next;
+	char			     *error_message;
+} ErrorListCell;
+
+typedef struct ErrorList
+{
+	ErrorListCell *head;
+	ErrorListCell *tail;
+} ErrorList;
 
 #endif

repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2010-2012
+ * Copyright (C) 2ndQuadrant, 2010-2015
  *
  */
 

sql/Makefile

@@ -1,6 +1,7 @@
 #
 # Makefile
-# Copyright (c) 2ndQuadrant, 2010
+#
+# Copyright (c) 2ndQuadrant, 2010-2015
 #
 
 MODULE_big = repmgr_funcs
@@ -9,7 +10,8 @@ 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/repmgr2_repmgr3.sql

@@ -0,0 +1,76 @@
+/*
+ * Update a repmgr 2.x installation to repmgr 3.0
+ * ----------------------------------------------
+ *
+ * 1. Stop any running repmgrd instances
+ * 2. On the master node, execute the SQL statements listed below,
+ *    taking care to identify the master node and any inactive
+ *    nodes
+ * 3. Restart repmgrd (being sure to use repmgr 3.0)
+ */
+
+/*
+ * Set the search path to the name of the schema used by
+ * your repmgr installation
+ * (this should be "repmgr_" + the cluster name defined in
+ * 'repmgr.conf')
+ */
+
+-- SET search_path TO 'name_of_repmgr_schema';
+
+BEGIN;
+
+ALTER TABLE repl_nodes RENAME TO repl_nodes2_0;
+
+CREATE TABLE repl_nodes (
+  id               INTEGER PRIMARY KEY,
+  type             TEXT    NOT NULL CHECK (type IN('master','standby','witness')),
+  upstream_node_id INTEGER NULL REFERENCES repl_nodes (id),
+  cluster          TEXT    NOT NULL,
+  name             TEXT    NOT NULL,
+  conninfo         TEXT    NOT NULL,
+  slot_name        TEXT    NULL,
+  priority         INTEGER NOT NULL,
+  active           BOOLEAN NOT NULL DEFAULT TRUE
+);
+
+INSERT INTO repl_nodes
+           (id, type, cluster, name, conninfo, priority)
+     SELECT id,
+            CASE
+               WHEN witness IS TRUE THEN 'witness'
+               ELSE 'standby'
+            END AS type,
+            cluster,
+            name,
+            conninfo,
+            priority + 100
+       FROM repl_nodes2_0;
+
+/*
+ * You'll need to set the master explicitly; the following query
+ * should identify the master node ID but will only work if all
+ * standby servers are connected:
+ *
+ * SELECT id FROM repmgr_test.repl_nodes WHERE name NOT IN (SELECT application_name FROM pg_stat_replication)
+ *
+ * If in doubt, execute 'repmgr cluster show' will definitively identify
+ * the master.
+ */
+UPDATE repl_nodes SET type = 'master' WHERE id = $master_id;
+
+/* If any nodes are known to be inactive, update them here */
+
+-- UPDATE repl_nodes SET active = FALSE WHERE id IN (...);
+
+/* When you're sure of your changes, commit them */
+
+-- COMMIT;
+
+
+/*
+ * execute the following command when you are sure you no longer
+ * require the old table:
+ */
+
+-- DROP TABLE repl_nodes2_0;

sql/repmgr_funcs.c

@@ -9,15 +9,17 @@
 #include "fmgr.h"
 #include "access/xlog.h"
 #include "miscadmin.h"
+#include "replication/walreceiver.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
 #include "storage/procarray.h"
 #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 +28,37 @@ PG_MODULE_MAGIC;
  */
 typedef struct repmgrSharedState
 {
-    LWLockId    lock;           		/* protects search/modification */
+	LWLockId	lock;			/* protects search/modification */
-    char		location[MAXFNAMELEN];	/* last known xlog location */
+	char		location[MAXFNAMELEN];	/* last known xlog location */
-} repmgrSharedState;
+	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_init(void);
-void        _PG_fini(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_update_standby_location(PG_FUNCTION_ARGS);
-Datum repmgr_get_last_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 +70,9 @@ _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
+	 * allow the repmgr functions to be created even when the module isn't
-	 * module isn't active.  The functions must protect themselves against
+	 * active.	The functions must protect themselves against being called
-	 * being called then, however.)
+	 * then, however.)
 	 */
 	if (!process_shared_preload_libraries_in_progress)
 		return;
@@ -112,15 +122,15 @@ repmgr_shmem_startup(void)
 	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
 
 	shared_state = ShmemInitStruct("repmgr shared state",
-						   sizeof(repmgrSharedState),
+								   sizeof(repmgrSharedState),
-						   &found);
+								   &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 +143,20 @@ 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... */
+	/* Safety check... */
-    if (!shared_state)
+	if (!shared_state)
-        return false;
+		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 +168,7 @@ 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 +186,51 @@ repmgr_get_last_standby_location(PG_FUNCTION_ARGS)
 Datum
 repmgr_update_standby_location(PG_FUNCTION_ARGS)
 {
-	text       *location = PG_GETARG_TEXT_P(0);
+	text	   *location = PG_GETARG_TEXT_P(0);
-	char       *locationstr;
+	char	   *locationstr;
 
-    /* Safety check... */
+	/* Safety check... */
-    if (!shared_state)
+	if (!shared_state)
-        PG_RETURN_BOOL(false);
+		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, 2010-2015
  *
  */
 
@@ -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, 2010-2015
+ *
+ */
+
 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, 2010-2015
  *
  * 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);
+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 */
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 0)));
-#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)
 {
-	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;
+	va_list		arglist;
-	int retval;
+	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, 2010-2015
  *
  *
  * 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
-extern int sqlquery_snprintf(char *str, const char *format, ...);
+xsnprintf(char *str, size_t size, const char *format,...)
-extern int maxlen_snprintf(char *str, const char *format, ...);
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 
-/* Add strnlen on platforms that don't have it, like OS X */
+extern int
-#ifndef strnlen
+sqlquery_snprintf(char *str, const char *format,...)
-extern size_t strnlen(const char *s, size_t n);
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
-#endif
 
-#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, 2010-2015
  *
  */
 

version.h

@@ -1,4 +1,6 @@
 #ifndef _VERSION_H_
 #define _VERSION_H_
-#define REPMGR_VERSION "2.0beta1"
+
+#define REPMGR_VERSION "3.0dev"
+
 #endif