Fix comment typo

There's no compelling reason to require "archive_mode" to be enabled
for streaming replication. It is of course a good idea to archive WAL
using e.g. barman ( http://www.pgbarman.org/ ) as part of a comprehensive
backup strategy, but repmgr and streaming replication work fine without
it.

Per GitHub #141.

Also revise the configuration check for "archive_command" to be
triggered only when "archive_mode" is not "off", as from PostgreSQL
9.5 onwards "archive_mode" can also be "on" or "always".

.gitignore

@@ -1,6 +1,9 @@
 *~
 *.o
+*.so
 repmgr
 repmgrd
 README.htm*
 README.pdf
+sql/repmgr_funcs.so
+sql/repmgr_funcs.sql

CONTRIBUTING.md

@@ -0,0 +1,29 @@
+License and Contributions
+=========================
+
+`repmgr` is licensed under the GPL v3.  All of its code and documentation is
+Copyright 2010-2016, 2ndQuadrant Limited.  See the files COPYRIGHT and LICENSE for
+details.
+
+The development of repmgr has primarily been sponsored by 2ndQuadrant customers.
+
+Additional work has been sponsored by the 4CaaST project for cloud computing,
+which has received funding from the European Union's Seventh Framework Programme
+(FP7/2007-2013) under grant agreement 258862.
+
+Contributions to `repmgr` are welcome, and will be listed in the file `CREDITS`.
+2ndQuadrant Limited requires that any contributions provide a copyright
+assignment and a disclaimer of any work-for-hire ownership claims from the
+employer of the developer.  This lets us make sure that all of the repmgr
+distribution remains free code.  Please contact info@2ndQuadrant.com for a
+copy of the relevant Copyright Assignment Form.
+
+Code style
+----------
+
+Code in repmgr is formatted to a consistent style using the following command:
+
+    astyle --style=ansi --indent=tab --suffix=none *.c *.h
+
+Contributors should reformat their code similarly before submitting code to
+the project, in order to minimize merge conflicts with other work.

COPYRIGHT

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2011, 2ndQuadrant Limited
+Copyright (c) 2010-2016, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

CREDITS

@@ -10,5 +10,7 @@ Hannu Krosing <hannu@2ndQuadrant.com>
 Cédric Villemain <cedric@2ndquadrant.com>
 Charles Duffy <charles@dyfis.net>
 Daniel Farina <daniel@heroku.com>
-Marco Nenciarini <marco.nenciarini@2ndquadrant.it>
+Shawn Ellis <shawn.ellis17@gmail.com>
-Carlo Ascani <carlo.ascani@2ndquadrant.it>
+Jay Taylor <jay@jaytaylor.com>
+Christian Kruse <christian@2ndQuadrant.com>
+Krzysztof Gajdemski <songo@debian.org.pl>

FAILOVER.rst

@@ -0,0 +1,238 @@
+====================================================
+ 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
+
+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
+
+This will also create the repmgr schema and functions.
+
+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).
+
+By default the witness server will listen on port 5499; this value can be
+overridden by explicitly providing the port number in the conninfo string
+in repmgr.conf. (Note that it is also possible to specify the port number
+with the -l/--local-port option, however this option is now deprecated and
+will be overridden by a port setting in the conninfo string).
+
+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 +1,155 @@
+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.
+
+- Does `repmgr` support hash indexes?
+
+  No. Hash indexes and replication do not mix well and their use is
+  explicitly discouraged; see:
+    http://www.postgresql.org/docs/current/interactive/sql-createindex.html#AEN74175
+
+`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.
+
+- How can I make the witness server use a particular port?
+
+  By default the witness server is configured to use port 5499; this
+  is intended to support running the witness server as  a separate
+  instance on a normal node server, rather than on its own dedicated server.
+
+  To specify different port for the witness server, supply the port number
+  in the `conninfo` string in `repmgr.conf`
+  (repmgr 3.0.1 and earlier: use the `-l/--local-port` option)
+
+- Do I need to include `shared_preload_libraries = 'repmgr_funcs'`
+  in `postgresql.conf` if I'm not using `repmgrd`?
+
+  No, the `repmgr_funcs` library is only needed when running `repmgrd`.
+  If you later decide to run `repmgrd`, you just need to add
+  `shared_preload_libraries = 'repmgr_funcs'` and restart PostgreSQL.
+
+- I've provided replication permission for the `repmgr` user in `pg_hba.conf`
+  but `repmgr`/`repmgrd` complains it can't connect to the server... Why?
+
+  `repmgr`/`repmgrd` need to be able to connect to the repmgr database
+  with a normal connection to query metadata. The `replication` connection
+  permission is for PostgreSQL's streaming replication and doesn't
+  necessarily need to be the `repmgr` user.
+
+
+`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 `repmgr.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.
+
+- How can I get `repmgrd` to rotate its logfile?
+
+  Configure your system's `logrotate` service to do this; see example
+  in README.md

HISTORY

@@ -1,15 +1,120 @@
-1.2.0	2012-07-27
+3.0.4   2016-01-
-		Test ssh connection before trying to rsync (Cédric)
+        Remove requirement for 'archive_mode' to be enabled (Ian)
+
+3.0.3   2016-01-04
+        Create replication slot if required before base backup is run (Abhijit)
+        standy clone: when using rsync, clean up "pg_replslot" directory (Ian)
+        Improve --help output (Ian)
+        Improve config file parsing (Ian)
+        Various logging output improvements, including explicit HINTS (Ian)
+        Add --log-level to explicitly set log level on command line (Ian)
+        Repurpose --verbose to display extra log output (Ian)
+        Add --terse to hide hints and other non-critical output (Ian)
+        Reference internal functions with explicit catalog path (Ian)
+        When following a new primary, have repmgr (not repmgrd) create the new slot (Ian)
+        Add /etc/repmgr.conf as a default configuration file location (Ian)
+        Prevent repmgrd's -v/--verbose option expecting a parameter (Ian)
+        Prevent invalid replication_lag values being written to the monitoring table (Ian)
+        Improve repmgrd behaviour when monitored standby node is temporarily
+          unavailable (Martín)
+
+3.0.2   2015-10-02
+        Improve handling of --help/--version options; and improve help output (Ian)
+        Improve handling of situation where logfile can't be opened (Ian)
+        Always pass -D/--pgdata option to pg_basebackup (Ian)
+        Bugfix: standby clone --force does not empty pg_xlog (Gianni)
+        Bugfix: autofailover with reconnect_attempts > 1 (Gianni)
+        Bugfix: ignore comments after values (soxwellfb)
+        Bugfix: handle string values in 'node' parameter correctly (Gregory Duchatelet)
+        Allow repmgr to be compiled with a newer libpq (Marco)
+        Bugfix: call update_node_record_set_upstream() for STANDBY FOLLOW (Tomas)
+        Update `repmgr --help` output (per Github report from renard)
+        Update tablespace remapping in --rsync-only mode for 9.5 and later (Ian)
+        Deprecate `-l/--local-port` option - the port can be extracted
+          from the conninfo string in repmgr.conf (Ian)
+        Add STANDBY UNREGISTER (Vik Fearing)
+        Don't fail with error when registering master if schema already defined (Ian)
+        Fixes to whitespace handling when parsing config file (Ian)
+
+3.0.1   2015-04-16
+        Prevent repmgrd from looping infinitely if node was not registered (Ian)
+        When promoting a standby, have repmgr (not repmgrd) handle metadata updates (Ian)
+        Re-use replication slot if it already exists (Ian)
+        Prevent a test SSH connection being made when not needed (Ian)
+        Correct monitoring table column names (Ian)
+
+3.0     2015-03-27
+        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)
+
+2.0.3   2015-04-16
+        Add -S/--superuser option for witness database creation Ian)
+        Add -c/--fast-checkpoint option for cloning (Christoph)
+        Add option "--initdb-no-pwprompt" (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)
+        Add autofailover capabilities (Jaime)
+        Add a configuration parameter to indicate the script to execute on failover or follow (Jaime)
+        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
+        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 repl_status view (Jaime) 
+        Improve performance of the repl_status view (Jaime)
         Remove last argument from log_err (Jaime, Reported by Jeroen Dekkers)
         Complete documentation about possible error conditions (Jaime)
         Document how to clean history (Jaime)

Makefile

@@ -1,6 +1,6 @@
 #
 # Makefile
-# Copyright (c) 2ndQuadrant, 2010-2011
+# Copyright (c) 2ndQuadrant, 2010-2016
 
 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
@@ -11,15 +11,18 @@ PG_CPPFLAGS = -I$(libpq_srcdir)
 PG_LIBS = $(libpq_pgport)
 
 all:  repmgrd repmgr
+	$(MAKE) -C sql
 
 repmgrd: $(repmgrd_OBJS)
 	$(CC) $(CFLAGS) $(repmgrd_OBJS) $(PG_LIBS) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o repmgrd
+	$(MAKE) -C sql
 
 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
@@ -30,9 +33,26 @@ 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 \
@@ -45,10 +65,18 @@ clean:
 	rm -f *.o
 	rm -f repmgrd
 	rm -f repmgr
+	$(MAKE) -C sql clean
 
 deb: repmgrd repmgr
 	mkdir -p ./debian/usr/bin
 	cp repmgrd repmgr ./debian/usr/bin/
+	mkdir -p ./debian/usr/share/postgresql/9.0/contrib/
+	cp sql/repmgr_funcs.sql ./debian/usr/share/postgresql/9.0/contrib/
+	cp sql/uninstall_repmgr_funcs.sql ./debian/usr/share/postgresql/9.0/contrib/
+	mkdir -p ./debian/usr/lib/postgresql/9.0/lib/
+	cp sql/repmgr_funcs.so ./debian/usr/lib/postgresql/9.0/lib/
 	dpkg-deb --build debian
 	mv debian.deb ../postgresql-repmgr-9.0_1.0.0.deb
+	rm -rf ./debian/usr
+
 

PACKAGES.md

@@ -0,0 +1,127 @@
+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 you're 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 +1,118 @@
+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 README.md for sample
+    settings)
+
+  - 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 the `repmgr.conf` file is not required when cloning a standby.
+  However we recommend providing a valid `repmgr.conf` if you wish to use
+  replication slots, or want `repmgr` to log the clone event to the
+  `repl_events` table.
+
+  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=repmgr_node1 user=repmgr_usr dbname=repmgr_db |           |        0 | t
+          2 | standby |                1 | test    | node2 | host=repmgr_node2 user=repmgr_usr dbname=repmgr_db |           |        0 | t
+        (2 rows)

README.md

@@ -0,0 +1,666 @@
+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 9.3 and later.
+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 PostgreSQL 9.2 and earlier.
+For a list of changes since `repmgr 2` and instructions on upgrading to
+`repmgr 3`, see the "Upgrading from repmgr 2" section below.
+
+For a list of frequently asked questions about `repmgr`, please refer
+to the file `FAQ.md`.
+
+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 later.
+
+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 settings
+like the following 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; from 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 .'
+
+    # If you plan to use repmgrd, ensure that shared_preload_libraries
+    # is configured to load 'repmgr_funcs'
+
+    shared_preload_libraries = 'repmgr_funcs'
+
+PostgreSQL 9.4 makes it possible to use replication slots, which means
+the value of `wal_keep_segments` need no longer be set. See section
+"Replication slots" below for more details.
+
+With PostgreSQL 9.3, `repmgr` expects `wal_keep_segments` 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 user and database, 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). We also recommend
+that you set the `repmgr` user's search path to include the `repmgr` schema
+for convenience when querying the metadata tables and views.
+
+The `repmgr` application will create its metadata schema in the `repmgr`
+database when the master server is registered.
+
+### 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
+
+Note that currently `repmgrd` does not provide logfile rotation. To ensure
+the current logfile does not grow indefinitely, configure your system's `logrotate`
+to do this. Sample configuration to rotate logfiles weekly with retention
+for up to 52 weeks and rotation forced if a file grows beyond 100Mb:
+
+    /var/log/postgresql/repmgr-9.4.log {
+        missingok
+        compress
+        rotate 52
+        maxsize 100M
+        weekly
+        create 0600 postgres postgres
+    }
+
+
+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_unregister
+    standby_clone
+    standby_promote
+    witness_create
+    repmgrd_start
+    repmgrd_monitor
+    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.
+
+Be aware that when initially cloning a standby, you will need to ensure
+that all required WAL files remain available while the cloning is taking
+place. If using the default `pg_basebackup` method, we recommend setting
+`pg_basebackup`'s `--xlog-method` parameter to `stream` like this:
+
+    pg_basebackup_options='--xlog-method=stream'
+
+See the `pg_basebackup` documentation [*] for details. Otherwise you'll need
+to set `wal_keep_segments` to an appropriately high value.
+
+[*] http://www.postgresql.org/docs/current/static/app-pgbasebackup.html
+
+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.
+
+    `primary register` can be used as an alias for `master register`.
+
+* `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 unregister`
+
+    Unregisters a standby with `repmgr`. This command does not affect the actual
+    replication.
+
+* `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
+* ERR_MONITORING_FAIL (16) Unrecoverable error encountered during monitoring (repmgrd only)
+
+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 +1,133 @@
+#!/bin/sh
+#
+# chkconfig: - 75 16
+# description: Enable repmgrd replication management and monitoring daemon for PostgreSQL
+# processname: repmgrd
+# pidfile="/var/run/${NAME}.pid"
+
+# Source function library.
+INITD=/etc/rc.d/init.d
+. $INITD/functions
+
+# Get function listing for cross-distribution logic.
+TYPESET=`typeset -f|grep "declare"`
+
+# Get network config.
+. /etc/sysconfig/network
+
+DESC="PostgreSQL replication management and monitoring daemon"
+NAME=repmgrd
+
+REPMGRD_ENABLED=no
+REPMGRD_OPTS=
+REPMGRD_USER=postgres
+REPMGRD_BIN=/usr/pgsql-9.3/bin/repmgrd
+REPMGRD_PIDFILE=/var/run/repmgrd.pid
+REPMGRD_LOCK=/var/lock/subsys/${NAME}
+REPMGRD_LOG=/var/lib/pgsql/9.3/data/pg_log/repmgrd.log
+
+# Read configuration variable file if it is present
+[ -r /etc/sysconfig/$NAME ] && . /etc/sysconfig/$NAME
+
+# For SELinux we need to use 'runuser' not 'su'
+if [ -x /sbin/runuser ]
+then
+    SU=runuser
+else
+    SU=su
+fi
+
+test -x $REPMGRD_BIN || exit 0
+
+case "$REPMGRD_ENABLED" in
+    [Yy]*)
+	break
+	;;
+    *)
+	exit 0
+	;;
+esac
+
+
+if [ -z "${REPMGRD_OPTS}" ]
+then
+    echo "Not starting ${NAME}, REPMGRD_OPTS not set in /etc/sysconfig/${NAME}"
+    exit 0
+fi
+
+start()
+{
+    REPMGRD_START=$"Starting ${NAME} service: "
+
+    # Make sure startup-time log file is valid
+    if [ ! -e "${REPMGRD_LOG}" -a ! -h "${REPMGRD_LOG}" ]
+    then
+        touch "${REPMGRD_LOG}" || exit 1
+        chown ${REPMGRD_USER}:postgres "${REPMGRD_LOG}"
+        chmod go-rwx "${REPMGRD_LOG}"
+        [ -x /sbin/restorecon ] && /sbin/restorecon "${REPMGRD_LOG}"
+    fi
+
+    echo -n "${REPMGRD_START}"
+    $SU -l $REPMGRD_USER -c "${REPMGRD_BIN} ${REPMGRD_OPTS} -p ${REPMGRD_PIDFILE} &" >> "${REPMGRD_LOG}" 2>&1 < /dev/null
+    sleep 2
+    pid=`head -n 1 "${REPMGRD_PIDFILE}" 2>/dev/null`
+    if [ "x${pid}" != "x" ]
+    then
+        success "${REPMGRD_START}"
+        touch "${REPMGRD_LOCK}"
+        echo $pid > "${REPMGRD_PIDFILE}"
+        echo
+    else
+        failure "${REPMGRD_START}"
+        echo
+        script_result=1
+    fi
+}
+
+stop()
+{
+    echo -n $"Stopping ${NAME} service: "
+    if [ -e "${REPMGRD_LOCK}" ]
+    then
+        killproc ${NAME}
+        ret=$? 
+        if [ $ret -eq 0 ]
+        then
+            echo_success
+            rm -f "${REPMGRD_PIDFILE}"
+            rm -f "${REPMGRD_LOCK}"
+        else
+            echo_failure
+            script_result=1
+        fi
+    else
+        # not running; per LSB standards this is "ok"   
+        echo_success
+    fi
+    echo
+}
+
+
+# See how we were called.
+case "$1" in
+  start)
+        start
+        ;;
+  stop)
+        stop
+        ;;
+  status)
+        status -p $REPMGRD_PIDFILE $NAME
+        script_result=$?
+        ;;
+  restart)
+        stop
+	start
+        ;;
+  *)
+        echo $"Usage: $0 {start|stop|status|restart}"
+        exit 2
+esac
+
+exit $script_result

RHEL/repmgrd.sysconfig

@@ -0,0 +1,21 @@
+# 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="--verbose -d -f /var/lib/pgsql/repmgr/repmgr.conf"
+
+# User to run repmgrd as
+#REPMGRD_USER=postgres
+
+# repmgrd binary
+#REPMGRD_BIN=/usr/bin/repmgrd
+
+# pid file
+#REPMGRD_PIDFILE=/var/lib/pgsql/repmgr/repmgrd.pid
+
+# log file
+#REPMGRD_LOG=/var/lib/pgsql/repmgr/repmgrd.log

SSH-RSYNC.md

@@ -0,0 +1,36 @@
+Set up trusted copy between postgres accounts
+---------------------------------------------
+
+If you need to use `rsync` to clone standby servers, the `postgres` account
+on your primary and standby servers must be each able to access the other
+using SSH without a password.
+
+First generate an ssh key, using an empty passphrase, and copy the resulting
+keys and a matching authorization file to a privileged user account 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

@@ -1,14 +1,77 @@
 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
+* PGPASSFILE may not be passed to pg_basebackup
-  control-C causes the program to crash.
+
+
+Planned feature improvements
+============================
+
+* Use 'primary' instead of 'master' in documentation and log output
+  for consistency with PostgreSQL documentation. See also commit
+  870b0a53b627eeb9aca1fc14cbafe25b5beafe12.
+
+* A better check which standby did receive most of the data
+
+* Make the fact that a standby may be delayed a factor in the voting
+  algorithm
+
+* include support for delayed standbys
+
+* Create the repmgr user/database on "master register".
+
+* Use pg_basebackup for the data directory, and ALSO rsync for the
+  configuration files.
+
+* If no configuration file supplied, search in sensible default locations
+  (currently: current directory and `pg_config --sysconfdir`); if
+  possible this should include the location provided by the package,
+  if installed.
+
+* repmgrd: if connection to the upstream node fails on startup, optionally
+  retry for a certain period before giving up; this will cover cases when
+  e.g. primary and standby are both starting up, and the standby comes up
+  before the primary. See github issue #80.
+
+* make old master node ID available for event notification commands
+  (See github issue #80).
+
+* Have pg_basebackup use replication slots, if and when support for
+  this is added; see:
+    http://www.postgresql.org/message-id/555DD2B2.7020000@gmx.net
+
+* use "primary/standby" terminology in place of "master/slave" for consistency
+  with main PostrgreSQL usage
+
+* repmgr standby clone: possibility to use barman instead of performing a new base backup
+
+* possibility to transform a failed master into a new standby with pg_rewind
+
+* "repmgr standby switchover" to promote a standby in a controlled manner
+   and convert the existing primary into a standby
+
+* make repmgrd more robust
+
+* repmgr: when cloning a standby using pg_basebackup and replication slots are
+  requested, activate the replication slot using pg_receivexlog to negate the
+  need to set `wal_keep_segments` just for the initial clone (9.4 and 9.5).
+
+Usability improvements
+======================
+
+* repmgr: add interrupt handler, so that if the program is interrupted
+  while running a backup, an attempt can be made to execute pg_stop_backup()
+  on the primary, to prevent an orphaned backup state existing.
+
+* repmgr: when unregistering a node, delete any entries in the repl_monitoring
+  table.
+
+* repmgr: for "standby unregister", accept connection parameters for the
+  primary and perform metadata updates (and slot removal) directly on
+  the primary, to allow a shutdown standby to be unregistered
+  (currently the standby must still be running, which means the replication
+  slot can't be dropped).

check_dir.c

@@ -1,6 +1,6 @@
 /*
  * check_dir.c - Directories management functions
- * Copyright (C) 2ndQuadrant, 2010-2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -23,15 +23,18 @@
 #include <errno.h>
 #include <stdio.h>
 #include <string.h>
+#include <ftw.h>
 
 /* NB: postgres_fe must be included BEFORE check_dir */
-#include "postgres_fe.h"
+#include <libpq-fe.h>
-#include "check_dir.h"
+#include <postgres_fe.h>
 
+#include "check_dir.h"
 #include "strutil.h"
 #include "log.h"
 
-static int mkdir_p(char *path, mode_t omode);
+static bool _create_pg_dir(char *dir, bool force, bool for_witness);
+static int unlink_dir_callback(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf);
 
 /*
  * make sure the directory either doesn't exist or is empty
@@ -46,9 +49,9 @@ static int mkdir_p(char *path, mode_t omode);
 int
 check_dir(char *dir)
 {
-	DIR        *chkdir;
+	DIR		   *chkdir;
-	struct 		dirent *file;
+	struct dirent *file;
-	int         result = 1;
+	int			result = 1;
 
 	errno = 0;
 
@@ -60,7 +63,7 @@ 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;
@@ -73,6 +76,7 @@ check_dir(char *dir)
 	}
 
 #ifdef WIN32
+
 	/*
 	 * This fix is in mingw cvs (runtime/mingwex/dirent.c rev 1.4), but not in
 	 * released version
@@ -84,29 +88,29 @@ 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;
 }
@@ -124,15 +128,15 @@ set_directory_permissions(char *dir)
  * note that on failure, the path arg has been modified to show the particular
  * directory level we had problems with.
  */
-static int
+int
 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;
@@ -151,8 +155,8 @@ 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;
@@ -223,10 +227,123 @@ 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;
 
+	/* test pgdata */
 	xsnprintf(path, buf_sz, "%s/PG_VERSION", dir);
+	if (stat(path, &sb) == 0)
+		return true;
 
-	return (stat(path, &sb) == 0) ? true : false;
+	/* test tablespace dir */
+	sprintf(path, "ls %s/PG_*/ -I*", dir);
+	r = system(path);
+	if (r == 0)
+		return true;
+
+	return false;
+}
+
+
+bool
+create_pg_dir(char *dir, bool force)
+{
+	return _create_pg_dir(dir, force, false);
+}
+
+bool
+create_witness_pg_dir(char *dir, bool force)
+{
+	return _create_pg_dir(dir, force, true);
+}
+
+
+static bool
+_create_pg_dir(char *dir, bool force, bool for_witness)
+{
+	bool		pg_dir = false;
+
+	/* Check this directory could be used as a PGDATA dir */
+	switch (check_dir(dir))
+	{
+		case 0:
+			/* dir not there, must create it */
+			log_info(_("creating directory \"%s\"...\n"), dir);
+
+			if (!create_dir(dir))
+			{
+				log_err(_("unable to create directory \"%s\"...\n"),
+						dir);
+				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_dir_permissions(dir))
+			{
+				log_err(_("unable to change permissions of directory \"%s\": %s\n"),
+						dir, strerror(errno));
+				return false;
+			}
+			break;
+		case 2:
+			/* Present and not empty */
+			log_warning(_("directory \"%s\" exists but is not empty\n"),
+						dir);
+
+			pg_dir = is_pg_dir(dir);
+
+
+			if (pg_dir && force)
+			{
+
+				/*
+				 * The witness server does not store any data other than a copy of the
+				 * repmgr metadata, so in --force mode we can simply overwrite the
+				 * directory.
+				 *
+				 * For non-witness servers, we'll leave the data in place, both to reduce
+				 * the risk of unintentional data loss and to make it possible for the
+				 * data directory to be brought up-to-date with rsync.
+				 */
+				if (for_witness)
+				{
+					log_notice(_("deleting existing data directory \"%s\"\n"), dir);
+					nftw(dir, unlink_dir_callback, 64, FTW_DEPTH | FTW_PHYS);
+				}
+				/* Let it continue */
+				break;
+			}
+			else if (pg_dir && !force)
+			{
+				log_hint(_("This 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 -F/--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;
+}
+
+static int
+unlink_dir_callback(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf)
+{
+    int rv = remove(fpath);
+
+    if (rv)
+        perror(fpath);
+
+    return rv;
 }

check_dir.h

@@ -1,6 +1,6 @@
 /*
  * check_dir.h
- * Copyright (c) 2ndQuadrant, 2010-2011
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  * 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
@@ -20,9 +20,12 @@
 #ifndef _REPMGR_CHECK_DIR_H_
 #define _REPMGR_CHECK_DIR_H_
 
-int  check_dir(char *dir);
+int			mkdir_p(char *path, mode_t omode);
-bool create_directory(char *dir);
+int			check_dir(char *dir);
-bool set_directory_permissions(char *dir);
+bool		create_dir(char *dir);
-bool is_pg_dir(char *dir);
+bool		set_dir_permissions(char *dir);
+bool		is_pg_dir(char *dir);
+bool		create_pg_dir(char *dir, bool force);
+bool		create_witness_pg_dir(char *dir, bool force);
 
 #endif

config.h

@@ -1,6 +1,6 @@
 /*
  * config.h
- * Copyright (c) 2ndQuadrant, 2010-2011
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  * 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
@@ -20,21 +20,92 @@
 #ifndef _REPMGR_CONFIG_H_
 #define _REPMGR_CONFIG_H_
 
-#include "repmgr.h"
+#include "postgres_fe.h"
+
 #include "strutil.h"
 
+#define CONFIG_FILE_NAME	"repmgr.conf"
+
+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;
-	char loglevel[MAXLEN];
+	char		conninfo[MAXLEN];
-	char logfacility[MAXLEN];
+	int			failover;
-	char rsync_options[QUERY_STR_LEN];
+	int			priority;
-} t_configuration_options;
+	char		node_name[MAXLEN];
+	char		promote_command[MAXLEN];
+	char		follow_command[MAXLEN];
+	char		loglevel[MAXLEN];
+	char		logfacility[MAXLEN];
+	char		rsync_options[QUERY_STR_LEN];
+	char		ssh_options[QUERY_STR_LEN];
+	int			master_response_timeout;
+	int			reconnect_attempts;
+	int			reconnect_interval;
+	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);
+typedef struct ErrorListCell
+{
+	struct ErrorListCell *next;
+	char			     *error_message;
+} ErrorListCell;
+
+typedef struct ErrorList
+{
+	ErrorListCell *head;
+	ErrorListCell *tail;
+} ErrorList;
+
+void set_progname(const char *argv0);
+const char * progname(void);
+
+bool		load_config(const char *config_file, bool verbose, t_configuration_options *options, char *argv0);
+bool		reload_config(t_configuration_options *orig_options);
+bool		parse_config(t_configuration_options *options);
+void		parse_line(char *buff, char *name, char *value);
+char	   *trim(char *s);
+void		error_list_append(ErrorList *error_list, char *error_message);
+int			repmgr_atoi(const char *s,
+						const char *config_item,
+						ErrorList *error_list);
 
 #endif

dbutils.h

@@ -1,6 +1,6 @@
 /*
  * dbutils.h
- * Copyright (c) 2ndQuadrant, 2010-2011
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  * 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
@@ -20,18 +20,96 @@
 #ifndef _REPMGR_DBUTILS_H_
 #define _REPMGR_DBUTILS_H_
 
+#include "access/xlogdefs.h"
+
+#include "config.h"
 #include "strutil.h"
 
-PGconn *establishDBConnection(const char *conninfo, const bool exit_on_error);
+
-PGconn *establishDBConnectionByParams(const char *keywords[],
+typedef enum {
-                                      const char *values[],
+	UNKNOWN = 0,
-                                      const bool exit_on_error);
+	MASTER,
-bool	is_standby(PGconn *conn);
+	STANDBY,
-char   *pg_version(PGconn *conn, char* major_version);
+	WITNESS
-bool	guc_setted(PGconn *conn, const char *parameter, const char *op,
+} t_server_type;
-                   const char *value);
+
-const char	 *get_cluster_size(PGconn *conn);
+/*
-PGconn *getMasterConnection(PGconn *standby_conn, char *cluster,
+ * Struct to store node information
-                            int *master_id, char *master_conninfo_out);
+ */
+typedef struct s_node_info
+{
+	int			  node_id;
+	int			  upstream_node_id;
+	t_server_type type;
+	char		  name[MAXLEN];
+	char		  conninfo_str[MAXLEN];
+	char		  slot_name[MAXLEN];
+	int			  priority;
+	bool		  active;
+	bool		  is_ready;
+	bool		  is_visible;
+	XLogRecPtr	  xlog_location;
+}	t_node_info;
+
+
+#define T_NODE_INFO_INITIALIZER { \
+  NODE_NOT_FOUND, \
+  NO_UPSTREAM_NODE, \
+  UNKNOWN, \
+  "", \
+  "", \
+  "", \
+  DEFAULT_PRIORITY, \
+  true, \
+  false, \
+  false, \
+  InvalidXLogRecPtr \
+}
+
+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		begin_transaction(PGconn *conn);
+bool		commit_transaction(PGconn *conn);
+bool		rollback_transaction(PGconn *conn);
+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		drop_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);
+bool        update_node_record_status(PGconn *conn, char *cluster_name, int this_node_id, char *type, int upstream_node_id, bool active);
+bool        update_node_record_set_upstream(PGconn *conn, char *cluster_name, int this_node_id, int new_upstream_node_id);
+PGresult *	get_node_record(PGconn *conn, char *cluster, int node_id);
 
 #endif

debian/DEBIAN/control

@@ -1,9 +1,9 @@
-Package: repmgr
+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
+#REPMGRD_BIN=/usr/bin/repmgrd
+
+# pid file
+#REPMGRD_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 $REPMGRD_PIDFILE --name "$(basename $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, 2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  * 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
@@ -25,13 +25,17 @@
 #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_SYS_FAILURE 13
+#define ERR_BAD_BASEBACKUP 14
+#define ERR_INTERNAL 15
+#define ERR_MONITORING_FAIL 16
 
-#endif	/* _ERRCODE_H_ */
+#endif   /* _ERRCODE_H_ */

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (C) 2ndQuadrant, 2010-2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  * 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 +39,118 @@
 
 /* #define REPMGR_DEBUG */
 
-static int detect_log_level(const char* level);
+static int	detect_log_facility(const char *facility);
-static int detect_log_facility(const char* facility);
+static void _stderr_log_with_level(const char *level_name, int level, const char *fmt, va_list ap);
 
-int log_type = REPMGR_STDERR;
+int			log_type = REPMGR_STDERR;
-int log_level = LOG_NOTICE;
+int			log_level = LOG_NOTICE;
+int			last_log_level = LOG_NOTICE;
+int			verbose_logging = false;
+int			terse_logging = false;
 
-bool logger_init(const char* ident, const char* level, const char* facility)
+void
+stderr_log_with_level(const char *level_name, int level, const char *fmt, ...)
 {
+	va_list		arglist;
 
-	int l;
+	va_start(arglist, fmt);
-	int f;
+	_stderr_log_with_level(level_name, level, fmt, arglist);
+	va_end(arglist);
+}
+
+static void
+_stderr_log_with_level(const char *level_name, int level, const char *fmt, va_list ap)
+{
+	time_t		t;
+	struct tm  *tm;
+	char		buff[100];
+
+	/*
+	 * Store the requested level so that if there's a subsequent
+	 * log_hint(), we can suppress that if appropriate.
+	 */
+	last_log_level = level;
+
+	if (log_level >= level)
+	{
+		time(&t);
+		tm = localtime(&t);
+		strftime(buff, 100, "[%Y-%m-%d %H:%M:%S]", tm);
+		fprintf(stderr, "%s [%s] ", buff, level_name);
+
+		vfprintf(stderr, fmt, ap);
+
+		fflush(stderr);
+	}
+}
+
+void
+log_hint(const char *fmt, ...)
+{
+	va_list		ap;
+
+	if (terse_logging == false)
+	{
+		va_start(ap, fmt);
+		_stderr_log_with_level("HINT", last_log_level, fmt, ap);
+		va_end(ap);
+	}
+}
+
+
+void
+log_verbose(int level, const char *fmt, ...)
+{
+	va_list		ap;
+
+	va_start(ap, fmt);
+
+	if (verbose_logging == true)
+	{
+		switch(level)
+		{
+			case LOG_EMERG:
+				_stderr_log_with_level("EMERG", level, fmt, ap);
+				break;
+			case LOG_ALERT:
+				_stderr_log_with_level("ALERT", level, fmt, ap);
+				break;
+			case LOG_CRIT:
+				_stderr_log_with_level("CRIT", level, fmt, ap);
+				break;
+			case LOG_ERR:
+				_stderr_log_with_level("ERR", level, fmt, ap);
+				break;
+			case LOG_WARNING:
+				_stderr_log_with_level("WARNING", level, fmt, ap);
+				break;
+			case LOG_NOTICE:
+				_stderr_log_with_level("NOTICE", level, fmt, ap);
+				break;
+			case LOG_INFO:
+				_stderr_log_with_level("INFO", level, fmt, ap);
+				break;
+			case LOG_DEBUG:
+				_stderr_log_with_level("DEBUG", level, fmt, ap);
+				break;
+		}
+	}
+
+	va_end(ap);
+}
+
+
+bool
+logger_init(t_configuration_options * opts, const char *ident)
+{
+	char	   *level = opts->loglevel;
+	char	   *facility = opts->logfacility;
+
+	int			l;
+	int			f;
 
 #ifdef HAVE_SYSLOG
-	int syslog_facility = DEFAULT_SYSLOG_FACILITY;
+	int			syslog_facility = DEFAULT_SYSLOG_FACILITY;
 #endif
 
 #ifdef REPMGR_DEBUG
@@ -69,10 +169,10 @@ bool logger_init(const char* ident, const char* level, const char* facility)
 		printf("Assigned level for logger: %d\n", l);
 #endif
 
-		if (l > 0)
+		if (l >= 0)
 			log_level = l;
 		else
-			stderr_log_warning(_("Cannot detect log level %s (use any of DEBUG, INFO, NOTICE, WARNING, ERR, ALERT, CRIT or EMERG)\n"), level);
+			stderr_log_warning(_("Invalid log level \"%s\" (available values: DEBUG, INFO, NOTICE, WARNING, ERR, ALERT, CRIT or EMERG)\n"), level);
 	}
 
 	if (facility && *facility)
@@ -107,21 +207,53 @@ 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
 
-	return true;
+	if (*opts->logfile)
+	{
+		FILE	   *fd;
 
+		/* Check if we can write to the specified file before redirecting
+		 * stderr - if freopen() fails, stderr output will vanish into
+		 * the ether and the user won't know what's going on.
+		 */
+
+		fd = fopen(opts->logfile, "a");
+		if (fd == NULL)
+		{
+			stderr_log_err(_("Unable to open specified logfile '%s' for writing: %s\n"), opts->logfile, strerror(errno));
+			stderr_log_err(_("Terminating\n"));
+			exit(ERR_BAD_CONFIG);
+		}
+		fclose(fd);
+
+		stderr_log_notice(_("Redirecting logging output to '%s'\n"), opts->logfile);
+		fd = freopen(opts->logfile, "a", stderr);
+
+		/* It's possible freopen() may still fail due to e.g. a race condition;
+		   as it's not feasible to restore stderr after a failed freopen(),
+		   we'll write to stdout as a last resort.
+		 */
+		if (fd == NULL)
+		{
+			printf(_("Unable to open specified logfile %s for writing: %s\n"), opts->logfile, strerror(errno));
+			printf(_("Terminating\n"));
+			exit(ERR_BAD_CONFIG);
+		}
+	}
+
+	return true;
 }
 
-bool logger_shutdown(void)
-{
 
+bool
+logger_shutdown(void)
+{
 #ifdef HAVE_SYSLOG
 	if (log_type == REPMGR_SYSLOG)
 		closelog();
@@ -131,17 +263,34 @@ bool logger_shutdown(void)
 }
 
 /*
- * Set a minimum logging level.  Intended for command line verbosity
+ * Indicate whether extra-verbose logging is required. This will
- * options, which might increase requested logging over what's specified
+ * generate a lot of output, particularly debug logging, and should
- * in the regular configuration file.
+ * not be permanently enabled in production.
+ *
+ * NOTE: in previous repmgr versions, this option forced the log
+ * level to INFO.
  */
-void logger_min_verbose(int minimum)
+void
+logger_set_verbose(void)
 {
-	if (log_level < minimum)
+	verbose_logging = true;
-		log_level = minimum;
 }
 
-int detect_log_level(const char* level)
+
+/*
+ * Indicate whether some non-critical log messages can be omitted.
+ * Currently this includes warnings about irrelevant command line
+ * options and hints.
+ */
+
+void logger_set_terse(void)
+{
+	terse_logging = true;
+}
+
+
+int
+detect_log_level(const char *level)
 {
 	if (!strcmp(level, "DEBUG"))
 		return LOG_DEBUG;
@@ -160,43 +309,44 @@ int detect_log_level(const char* level)
 	if (!strcmp(level, "EMERG"))
 		return LOG_EMERG;
 
-	return 0;
+	return -1;
 }
 
-int detect_log_facility(const char* facility)
+static 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, 2010-2011
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  * 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 +109,24 @@
 #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
 
 
+int			detect_log_level(const char *level);
+
 /* Logger initialisation and shutdown */
-bool logger_shutdown(void);
-bool logger_init(const char* ident, const char* level, const char* facility);
-void logger_min_verbose(int minimum);
 
-extern int log_type;
+bool		logger_init(t_configuration_options * opts, const char *ident);
-extern int log_level;
+
+bool		logger_shutdown(void);
+
+void		logger_set_verbose(void);
+void		logger_set_terse(void);
+
+void		log_hint(const char *fmt, ...);
+void		log_verbose(int level, const char *fmt, ...);
+
+extern int	log_type;
+extern int	log_level;
 
 #endif

repmgr.conf

@@ -1,21 +0,0 @@
-###################################################
-# Replication Manager configuration file
-###################################################
-
-# Cluster name
-cluster=test
-
-# Node ID
-node=2
-
-# Connection information
-conninfo='host=192.168.204.104'
-rsync_options=--archive --checksum --compress --progress --rsh=ssh
-
-# 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.conf.sample

@@ -0,0 +1,144 @@
+###################################################
+# Replication Manager sample configuration file
+###################################################
+
+# Required configuration items
+# ============================
+#
+# repmgr and repmgrd require these items to be configured:
+
+# Cluster name - this will be used by repmgr to generate its internal
+# schema (pattern: "repmgr_{cluster}"); while this name will be quoted
+# to preserve case, we recommend using lower case and avoiding whitespace
+# to facilitate easier querying of the repmgr views and tables.
+cluster=example_cluster
+
+# 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 primary)
+node=2           # a unique integer
+node_name=node2  # an arbitrary (but unique) string; we recommend using
+                 # the server's hostname or another identifier unambiguously
+                 # associated with the server to avoid confusion
+
+# Database connection information as a conninfo string
+# This must be accessible to all servers in the cluster; for details see:
+#   http://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING
+conninfo='host=192.168.204.104 dbname=repmgr_db user=repmgr_usr'
+
+# 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 primary node, this parameter is not required.
+#
+# upstream_node=1
+
+# physical replication slots - PostgreSQL 9.4 and later only
+# (default: 0)
+#
+# use_replication_slots=0
+#
+# NOTE: 'max_replication_slots' should be configured for at least the
+# number of standbys which will connect to the primary.
+
+# 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.
+
+# Number of seconds to wait for a response from the primary server before
+# deciding it has failed
+
+master_response_timeout=60
+
+# Number of times to try and reconnect to the primary before starting
+# the failover procedure
+reconnect_attempts=6
+reconnect_interval=10
+
+# Autofailover options
+failover=automatic  # one of 'automatic', 'manual'
+priority=100        # a value of zero or less prevents the node being promoted to primary
+promote_command='repmgr standby promote -f /path/to/repmgr.conf'
+follow_command='repmgr standby follow -f /path/to/repmgr.conf -W'
+
+# monitoring interval in seconds; default is 2
+#
+# monitor_interval_secs=2
+
+# change wait time for primary; before we bail out and exit when the primary
+# 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

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2011
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  * 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
@@ -20,47 +20,74 @@
 #ifndef _REPMGR_H_
 #define _REPMGR_H_
 
-#include "postgres_fe.h"
+#include <libpq-fe.h>
-#include "getopt_long.h"
+#include <postgres_fe.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
 
 #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"
 #define DEFAULT_DEST_DIR		"."
 #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 NODE_NOT_FOUND      -1
+#define NO_UPSTREAM_NODE	-1
+#define UNKNOWN_NODE_ID     -1
+
+
 
 /* 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		terse;
-
+	bool		force;
-	char masterport[MAXLEN];
+	bool		wait_for_master;
+	bool		ignore_rsync_warn;
+	bool		initdb_no_pwprompt;
+	bool		rsync_only;
+	bool		fast_checkpoint;
+	bool		ignore_external_config_files;
+	char		masterport[MAXLEN];
+	char		localport[MAXLEN];
+	char		loglevel[MAXLEN];
 
 	/* parameter used by CLUSTER CLEANUP */
-	int	keep_history;
+	int			keep_history;
-} t_runtime_options;
+
+	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, false, "", "", "", 0, "", "" }
+
+extern char		repmgr_schema[MAXLEN];
+
 
 #endif

repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  */
 
@@ -14,8 +14,11 @@ CREATE SCHEMA repmgr;
  */
 CREATE TABLE repl_nodes (
   id            integer primary key,
-  cluster   text        not null,       -- Name to identify the cluster
+  cluster   	text    not null,       -- Name to identify the cluster
-  conninfo      text    not null
+  name			text	not null,
+  conninfo      text    not null,
+  priority  	integer not null,
+  witness   	boolean not null default false
 );
 ALTER TABLE repl_nodes OWNER TO repmgr;
 
@@ -28,13 +31,12 @@ CREATE TABLE repl_monitor (
   standby_node                   INTEGER NOT NULL,
   last_monitor_time                      TIMESTAMP WITH TIME ZONE NOT NULL,
   last_wal_primary_location      TEXT NOT NULL,
-  last_wal_standby_location      TEXT NOT NULL,
+  last_wal_standby_location      TEXT,		-- In case of a witness server this will be NULL
   replication_lag                BIGINT NOT NULL,
   apply_lag                      BIGINT NOT NULL
 );
 ALTER TABLE repl_monitor OWNER TO repmgr;
 
-
 /*
  * This view shows the latest monitor info about every node.
  * Interesting thing to see:
@@ -46,14 +48,14 @@ ALTER TABLE repl_monitor OWNER TO repmgr;
  * time_lag: how many seconds are we from being up-to-date with master
  */
 CREATE VIEW repl_status AS
-WITH monitor_info AS (SELECT *, ROW_NUMBER() OVER (PARTITION BY primary_node, standby_node
+SELECT primary_node, standby_node, name AS standby_name, last_monitor_time, last_wal_primary_location,
-                                                       ORDER BY last_monitor_time desc)
-                        FROM repl_monitor)
-SELECT primary_node, standby_node, last_monitor_time, last_wal_primary_location,
        last_wal_standby_location, pg_size_pretty(replication_lag) replication_lag,
        pg_size_pretty(apply_lag) apply_lag,
        age(now(), last_monitor_time) AS time_lag
-  FROM monitor_info a
+ FROM repl_monitor JOIN repl_nodes ON standby_node = id
- WHERE row_number = 1;
+WHERE (standby_node, last_monitor_time) IN (SELECT standby_node, MAX(last_monitor_time)
+                                              FROM repl_monitor GROUP BY 1);
 
 ALTER VIEW repl_status OWNER TO repmgr;
+
+CREATE INDEX idx_repl_status_sort ON repl_monitor(last_monitor_time, standby_node);

sql/Makefile

@@ -0,0 +1,21 @@
+#
+# Makefile
+#
+# Copyright (c) 2ndQuadrant, 2010-2016
+#
+
+MODULE_big = repmgr_funcs
+DATA_built=repmgr_funcs.sql
+DATA=uninstall_repmgr_funcs.sql
+OBJS=repmgr_funcs.o
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/repmgr/sql
+top_builddir = ../../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif

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

@@ -0,0 +1,236 @@
+/*
+ * repmgr_funcs.c
+ * Copyright (c) 2ndQuadrant, 2010
+ *
+ * Shared memory state management and some backend functions in SQL
+ */
+
+#include "postgres.h"
+#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
+
+PG_MODULE_MAGIC;
+
+/*
+ * Global shared state
+ */
+typedef struct repmgrSharedState
+{
+	LWLockId	lock;			/* protects search/modification */
+	char		location[MAXFNAMELEN];	/* last known xlog location */
+	TimestampTz last_updated;
+}	repmgrSharedState;
+
+/* Links to shared memory state */
+static repmgrSharedState *shared_state = NULL;
+
+static shmem_startup_hook_type prev_shmem_startup_hook = NULL;
+
+void		_PG_init(void);
+void		_PG_fini(void);
+
+static void repmgr_shmem_startup(void);
+static Size repmgr_memsize(void);
+
+static bool repmgr_set_standby_location(char *locationstr);
+
+Datum		repmgr_update_standby_location(PG_FUNCTION_ARGS);
+Datum		repmgr_get_last_standby_location(PG_FUNCTION_ARGS);
+
+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
+ */
+void
+_PG_init(void)
+{
+	/*
+	 * In order to create our shared memory area, we have to be loaded via
+	 * shared_preload_libraries.  If not, fall out without hooking into any of
+	 * the main system.  (We don't throw error here because it seems useful to
+	 * allow the repmgr functions to be created even when the module isn't
+	 * active.	The functions must protect themselves against being called
+	 * then, however.)
+	 */
+	if (!process_shared_preload_libraries_in_progress)
+		return;
+
+	/*
+	 * Request additional shared resources.  (These are no-ops if we're not in
+	 * the postmaster process.)  We'll allocate or attach to the shared
+	 * resources in repmgr_shmem_startup().
+	 */
+	RequestAddinShmemSpace(repmgr_memsize());
+	RequestAddinLWLocks(1);
+
+	/*
+	 * Install hooks.
+	 */
+	prev_shmem_startup_hook = shmem_startup_hook;
+	shmem_startup_hook = repmgr_shmem_startup;
+}
+
+/*
+ * Module unload callback
+ */
+void
+_PG_fini(void)
+{
+	/* Uninstall hooks. */
+	shmem_startup_hook = prev_shmem_startup_hook;
+}
+
+/*
+ * shmem_startup hook: allocate or attach to shared memory,
+ */
+static void
+repmgr_shmem_startup(void)
+{
+	bool		found;
+
+	if (prev_shmem_startup_hook)
+		prev_shmem_startup_hook();
+
+	/* reset in case this is a restart within the postmaster */
+	shared_state = NULL;
+
+	/*
+	 * Create or attach to the shared memory state, including hash table
+	 */
+	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
+
+	shared_state = ShmemInitStruct("repmgr shared state",
+								   sizeof(repmgrSharedState),
+								   &found);
+
+	if (!found)
+	{
+		/* First time through ... */
+		shared_state->lock = LWLockAssign();
+		snprintf(shared_state->location,
+				 sizeof(shared_state->location), "%X/%X", 0, 0);
+	}
+
+	LWLockRelease(AddinShmemInitLock);
+}
+
+
+/*
+ * Estimate shared memory space needed.
+ */
+static Size
+repmgr_memsize(void)
+{
+	return MAXALIGN(sizeof(repmgrSharedState));
+}
+
+
+static bool
+repmgr_set_standby_location(char *locationstr)
+{
+	/* Safety check... */
+	if (!shared_state)
+		return false;
+
+	LWLockAcquire(shared_state->lock, LW_EXCLUSIVE);
+	strncpy(shared_state->location, locationstr, MAXFNAMELEN);
+	LWLockRelease(shared_state->lock);
+
+	return true;
+}
+
+
+/* SQL Functions */
+
+/* Read last xlog location reported by this standby from shared memory */
+Datum
+repmgr_get_last_standby_location(PG_FUNCTION_ARGS)
+{
+	char		location[MAXFNAMELEN];
+
+	/* Safety check... */
+	if (!shared_state)
+		PG_RETURN_NULL();
+
+	LWLockAcquire(shared_state->lock, LW_SHARED);
+	strncpy(location, shared_state->location, MAXFNAMELEN);
+	LWLockRelease(shared_state->lock);
+
+	PG_RETURN_TEXT_P(cstring_to_text(location));
+}
+
+
+/* Set update last xlog location reported by this standby to shared memory */
+Datum
+repmgr_update_standby_location(PG_FUNCTION_ARGS)
+{
+	text	   *location = PG_GETARG_TEXT_P(0);
+	char	   *locationstr;
+
+	/* Safety check... */
+	if (!shared_state)
+		PG_RETURN_BOOL(false);
+
+	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

@@ -0,0 +1,23 @@
+/*
+ * repmgr_function.sql
+ * Copyright (c) 2ndQuadrant, 2010-2016
+ *
+ */
+
+-- SET SEARCH_PATH TO 'repmgr';
+
+CREATE FUNCTION repmgr_update_standby_location(text) RETURNS boolean
+AS 'MODULE_PATHNAME', 'repmgr_update_standby_location'
+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

@@ -0,0 +1,11 @@
+/*
+ * uninstall_repmgr_funcs.sql
+ * Copyright (c) 2ndQuadrant, 2010-2016
+ *
+ */
+
+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, 2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  * 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, 2010-2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  *
  * 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, 2010-2011
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  */
 

version.h

@@ -1,4 +1,6 @@
 #ifndef _VERSION_H_
 #define _VERSION_H_
-#define REPMGR_VERSION "1.2.0"
+
+#define REPMGR_VERSION "3.0.3"
+
 #endif