Update HISTORY

Sometimes we're setting node status to active.

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) 2010-2015, 2ndQuadrant Limited
+Copyright (c) 2010-2016, 2ndQuadrant Limited
 All rights reserved.
 
 This program is free software: you can redistribute it and/or modify

FAILOVER.rst

@@ -1,231 +1 @@
-====================================================
+The contents of this file have been incorporated into the main README.md document.
- PostgreSQL Automatic Failover - User Documentation
-====================================================
-
-Automatic Failover
-==================
-
-repmgr allows for automatic failover when it detects the failure of the master node.
-Following is a quick setup for this.
-
-Installation
-============
-
-For convenience, we define:
-
-**node1**
-    is the fully qualified domain name of the Master server, IP 192.168.1.10
-**node2**
-    is the fully qualified domain name of the Standby server, IP 192.168.1.11
-**witness**
-    is the fully qualified domain name of the server used as a witness, IP 192.168.1.12
-
-**Note:** We don't recommend using names with the status of a server like «masterserver»,
-because it would be confusing once a failover takes place and the Master is
-now on the «standbyserver».
-
-Summary
--------
-
-2 PostgreSQL servers are involved in the replication.  Automatic failover needs
-a vote to decide what server it should promote, so an odd number is required.
-A witness-repmgrd is installed in a third server where it uses a PostgreSQL
-cluster to communicate with other repmgrd daemons.
-
-1. Install PostgreSQL in all the servers involved (including the witness server)
-
-2. Install repmgr in all the servers involved (including the witness server)
-
-3. Configure the Master PostreSQL
-
-4. Clone the Master to the Standby using "repmgr standby clone" command
-
-5. Configure repmgr in all the servers involved (including the witness server)
-
-6. Register Master and Standby nodes
-
-7. Initiate witness server
-
-8. Start the repmgrd daemons in all nodes
-
-**Note** A complete High-Availability design needs at least 3 servers to still have
-a backup node after a first failure.
-
-Install PostgreSQL
-------------------
-
-You can install PostgreSQL using any of the recommended methods. You should ensure
-it's 9.0 or later.
-
-Install repmgr
---------------
-
-Install repmgr following the steps in the README file.
-
-Configure PostreSQL
--------------------
-
-Log in to node1.
-
-Edit the file postgresql.conf and modify the parameters::
-
-  listen_addresses='*'
-  wal_level = 'hot_standby'
-  archive_mode = on
-  archive_command = 'cd .'   # we can also use exit 0, anything that
-                             # just does nothing
-  max_wal_senders = 10
-  wal_keep_segments = 5000   # 80 GB required on pg_xlog
-  hot_standby = on
-  shared_preload_libraries = 'repmgr_funcs'
-
-Edit the file pg_hba.conf and add lines for the replication::
-
-  host     repmgr           repmgr      127.0.0.1/32            trust
-  host     repmgr           repmgr      192.168.1.10/30         trust
-  host     replication      all         192.168.1.10/30         trust
-
-**Note:** It is also possible to use a password authentication (md5), .pgpass file
-should be edited to allow connection between each node.
-
-Create the user and database to manage replication::
-
-  su - postgres
-  createuser -s repmgr
-  createdb -O repmgr repmgr
-  psql -f /usr/share/postgresql/9.0/contrib/repmgr_funcs.sql repmgr
-
-Restart the PostgreSQL server::
-
-  pg_ctl -D $PGDATA restart
-
-And check everything is fine in the server log.
-
-Create the ssh-key for the postgres user and copy it to other servers::
-
-  su - postgres
-  ssh-keygen             # /!\ do not use a passphrase /!\
-  cat ~/.ssh/id_rsa.pub > ~/.ssh/authorized_keys
-  chmod 600 ~/.ssh/authorized_keys
-  exit
-  rsync -avz ~postgres/.ssh/authorized_keys node2:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/authorized_keys witness:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/id_rsa* node2:~postgres/.ssh/
-  rsync -avz ~postgres/.ssh/id_rsa* witness:~postgres/.ssh/
-
-Clone Master
-------------
-
-Log in to node2.
-
-Clone node1 (the current Master)::
-
-  su - postgres
-  repmgr -d repmgr -U repmgr -h node1 standby clone 
-
-Start the PostgreSQL server::
-
-  pg_ctl -D $PGDATA start
-
-And check everything is fine in the server log.
-
-Configure repmgr
-----------------
-
-Log in to each server and configure repmgr by editing the file
-/etc/repmgr/repmgr.conf::
-
-  cluster=my_cluster
-  node=1
-  node_name=earth
-  conninfo='host=192.168.1.10 dbname=repmgr user=repmgr'
-  master_response_timeout=60
-  reconnect_attempts=6
-  reconnect_interval=10
-  failover=automatic
-  promote_command='promote_command.sh'
-  follow_command='repmgr standby follow -f /etc/repmgr/repmgr.conf'
-
-**cluster**
-    is the name of the current replication.
-**node**
-    is the number of the current node (1, 2 or 3 in the current example).
-**node_name**
-    is an identifier for every node.
-**conninfo**
-    is used to connect to the local PostgreSQL server (where the configuration file is) from any node. In the witness server configuration you need to add a 'port=5499' to the conninfo.
-**master_response_timeout**
-    is the maximum amount of time we are going to wait before deciding the master has died and start the failover procedure.
-**reconnect_attempts**
-    is the number of times we will try to reconnect to master after a failure has been detected and before start the failover procedure.
-**reconnect_interval**
-    is the amount of time between retries to reconnect to master after a failure has been detected and before start the failover procedure.
-**failover**
-    configure behavior: *manual* or *automatic*.
-**promote_command**
-    the command executed to do the failover (including the PostgreSQL failover itself). The command must return 0 on success.
-**follow_command**
-    the command executed to address the current standby to another Master. The command must return 0 on success.
-
-Register Master and Standby
----------------------------
-
-Log in to node1.
-
-Register the node as Master::
-
-  su - postgres
-  repmgr -f /etc/repmgr/repmgr.conf master register
-
-Log in to node2. Register it as a standby::
-
-  su - postgres
-  repmgr -f /etc/repmgr/repmgr.conf standby register
-
-Initialize witness server
--------------------------
-
-Log in to witness.
-
-Initialize the witness server::
-
-  su - postgres
-  repmgr -d repmgr -U repmgr -h 192.168.1.10 -D $WITNESS_PGDATA -f /etc/repmgr/repmgr.conf witness create
-
-The witness server needs the following information from the command
-line:
-
-* Connection details for the current master, to copy the cluster
-  configuration.
-* A location for initializing its own $PGDATA.
-
-repmgr will also ask for the superuser password on the witness database so
-it can reconnect when needed (the command line option --initdb-no-pwprompt
-will set up a password-less superuser).
-
-Start the repmgrd daemons
--------------------------
-
-Log in to node2 and witness::
-
-  su - postgres
-  repmgrd -f /etc/repmgr/repmgr.conf --daemonize -> /var/log/postgresql/repmgr.log 2>&1
-
-**Note:** The Master does not need a repmgrd daemon.
-
-Suspend Automatic behavior
-==========================
-
-Edit the repmgr.conf of the node to remove from automatic processing and change::
-
-  failover=manual
-
-Then, signal repmgrd daemon::
-
-  su - postgres
-  kill -HUP $(pidof repmgrd)
-
-Usage
-=====
-
-The repmgr documentation is in the README file (how to build, options, etc.)

FAQ.md

@@ -34,6 +34,11 @@ General
   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:
+    https://www.postgresql.org/docs/current/interactive/sql-createindex.html#AEN74175
 
 `repmgr`
 --------
@@ -90,6 +95,49 @@ General
 
   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.
+
+- When cloning a standby, why do I need to provide the connection parameters
+  for the primary server on the command line, not in the configuration file?
+
+  Cloning a standby is a one-time action; the role of the server being cloned
+  from could change, so fixing it in the configuration file would create
+  confusion. If `repmgr` needs to establish a connection to the primary
+  server, it can retrieve this from the `repl_nodes` table or if necessary
+  scan the replication cluster until it locates the active primary.
+
+- Why is there no foreign key on the `node_id` column in the `repl_events`
+  table?
+
+  Under some circumstances event notifications can be generated for servers
+  which have not yet been registered; it's also useful to retain a record
+  of events which includes servers removed from the replication cluster
+  which no longer have an entry in the `repl_nodes` table.
+
+
 `repmgrd`
 ---------
 
@@ -102,7 +150,10 @@ General
 
 - How can I prevent a node from ever being promoted to master?
 
-  In `rempgr.conf`, set its priority to a value of 0 or less.
+  In `repmgr.conf`, set its priority to a value of 0 or less.
+
+  Additionally, if `failover` is set to `manual`, the node will never
+  be considered as a promotion candidate.
 
 - Does `repmgrd` support delayed standbys?
 
@@ -117,3 +168,16 @@ General
 
   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
+
+- I've recloned a failed master as a standby, but `repmgrd` refuses to start?
+
+  Check you registered the standby after recloning. If unregistered the standby
+  cannot be considered as a promotion candidate even if `failover` is set to
+  `automatic`, which is probably not what you want. `repmgrd` will start if
+  `failover` is set to `manual` so the node's replication status can still
+  be monitored, if desired.

HISTORY

@@ -1,4 +1,149 @@
-3.0
+3.3     2016-12-27
+        repmgr: always log to STDERR even if log facility defined (Ian)
+        repmgr: add --log-to-file to log repmgr output to the defined
+          log facility (Ian)
+        repmgr: improve handling of command line parameter errors (Ian)
+        repmgr: add option --upstream-conninfo to explicitly set
+          'primary_conninfo' in recovery.conf (Ian)
+        repmgr: enable a standby to be registered which isn't running (Ian)
+        repmgr: enable `standby register --force` to update a node record
+          with cascaded downstream node records (Ian)
+        repmgr: add option `--no-conninfo-password` (Abhijit, Ian)
+        repmgr: add initial support for PostgreSQL 10.0 (Ian)
+        repmgr: escape values in primary_conninfo if needed (Ian)
+
+3.2.1   2016-10-24
+        repmgr: require a valid repmgr cluster name unless -F/--force
+          supplied (Ian)
+        repmgr: check master server is registered with repmgr before
+          cloning (Ian)
+        repmgr: ensure data directory defaults to that of the source node (Ian)
+        repmgr: various fixes to Barman cloning mode (Gianni, Ian)
+        repmgr: fix `repmgr cluster crosscheck` output (Ian)
+
+3.2     2016-10-05
+        repmgr: add support for cloning from a Barman backup (Gianni)
+        repmgr: add commands `standby matrix` and `standby crosscheck` (Gianni)
+        repmgr: suppress connection error display in `repmgr cluster show`
+          unless `--verbose` supplied (Ian)
+        repmgr: add commands `witness register` and `witness unregister` (Ian)
+        repmgr: enable `standby unregister` / `witness unregister` to be
+          executed for a node which is not running (Ian)
+        repmgr: remove deprecated command line options --initdb-no-pwprompt and
+           -l/--local-port (Ian)
+        repmgr: before cloning with pg_basebackup, check that sufficient free
+           walsenders are available (Ian)
+        repmgr: add option `--wait-sync` for `standby register` which causes
+           repmgr to wait for the registered node record to synchronise to
+           the standby (Ian)
+        repmgr: add option `--copy-external-config-files` for files outside
+           of the data directory (Ian)
+        repmgr: only require `wal_keep_segments` to be set in certain corner
+           cases (Ian)
+        repmgr: better support cloning from a node other than the one to
+           stream from (Ian)
+        repmgrd: add configuration options to override the default pg_ctl
+           commands (Jarkko Oranen, Ian)
+        repmgrd: don't start if node is inactive and failover=automatic (Ian)
+        packaging: improve "repmgr-auto" Debian package (Gianni)
+
+
+3.1.5   2016-08-15
+        repmgrd: in a failover situation, prevent endless looping when
+          attempting to establish the status of a node with
+          `failover=manual` (Ian)
+        repmgrd: improve handling of failover events on standbys with
+          `failover=manual`, and create a new event notification
+          for this, `standby_disconnect_manual` (Ian)
+        repmgr: add further event notifications (Gianni)
+        repmgr: when executing `standby switchover`, don't collect remote
+          command output unless required (Gianni, Ian)
+        repmgrd: improve standby monitoring query (Ian, based on suggestion
+          from  Álvaro)
+        repmgr: various command line handling improvements (Ian)
+
+3.1.4   2016-07-12
+        repmgr: new configuration option for setting "restore_command"
+          in the recovery.conf file generated by repmgr (Martín)
+        repmgr: add --csv option to "repmgr cluster show" (Gianni)
+        repmgr: enable provision of a conninfo string as the -d/--dbname
+          parameter, similar to other PostgreSQL utilities (Ian)
+        repmgr: during switchover operations improve detection of
+          demotion candidate shutdown (Ian)
+        various bugfixes and documentation updates (Ian, Martín)
+
+3.1.3   2016-05-17
+        repmgrd: enable monitoring when a standby is catching up by
+          replaying archived WAL (Ian)
+        repmgrd: when upstream_node_id is NULL, assume upstream node
+          to be current master (Ian)
+        repmgrd: check for reappearance of the master node if standby
+          promotion fails (Ian)
+        improve handling of rsync failure conditions (Martín)
+
+3.1.2   2016-04-12
+        Fix pg_ctl path generation in do_standby_switchover() (Ian)
+        Regularly sync witness server repl_nodes table (Ian)
+        Documentation improvements (Gianni, dhyannataraj)
+        (Experimental) ensure repmgr handles failover slots when copying
+          in rsync mode (Craig, Ian)
+        rsync mode handling fixes (Martín)
+        Enable repmgr to compile against 9.6devel (Ian)
+
+3.1.1   2016-02-24
+        Add '-P/--pwprompt' option for "repmgr create witness" (Ian)
+        Prevent repmgr/repmgrd running as root (Ian)
+
+3.1.0   2016-02-01
+        Add "repmgr standby switchover" command (Ian)
+        Revised README file (Ian)
+        Remove requirement for 'archive_mode' to be enabled (Ian)
+        Improve -?/--help output, showing default values if relevant (Ian)
+        Various bugfixes to command line/configuration parameter handling (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
@@ -11,6 +156,11 @@
         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)

Makefile

@@ -1,24 +1,33 @@
 #
 # Makefile
-# Copyright (c) 2ndQuadrant, 2010-2015
+# Copyright (c) 2ndQuadrant, 2010-2016
+
+HEADERS = $(wildcard *.h)
 
 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
+repmgr_OBJS = dbutils.o check_dir.o config.o repmgr.o log.o strutil.o dirmod.o compat.o
 
 DATA = repmgr.sql uninstall_repmgr.sql
 
 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
+	$(CC) -o repmgrd $(CFLAGS) $(repmgrd_OBJS) $(PG_LIBS) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS)
 	$(MAKE) -C sql
 
 repmgr: $(repmgr_OBJS)
-	$(CC) $(CFLAGS) $(repmgr_OBJS) $(PG_LIBS) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS) -o repmgr
+	$(CC) -o repmgr $(CFLAGS) $(repmgr_OBJS) $(PG_LIBS) $(LDFLAGS) $(LDFLAGS_EX) $(LIBS)
+
+# Make all objects depend on all include files. This is a bit of a
+# shotgun approach, but the codebase is small enough that a complete rebuild
+# is very fast anyway.
+$(repmgr_OBJS): $(HEADERS)
+$(repmgrd_OBJS): $(HEADERS)
 
 ifdef USE_PGXS
 PG_CONFIG = pg_config
@@ -31,8 +40,8 @@ include $(top_builddir)/src/Makefile.global
 include $(top_srcdir)/contrib/contrib-global.mk
 endif
 
-# XXX: Try to use PROGRAM construct (see pgxs.mk) someday. Right now
+# XXX: This overrides the pgxs install target - we're building two binaries,
-# is overriding pgxs install.
+# which is not supported by pgxs.mk's PROGRAM construct.
 install: install_prog install_ext
 
 install_prog:
@@ -43,6 +52,12 @@ install_prog:
 install_ext:
 	$(MAKE) -C sql install
 
+# Distribution-specific package building targets
+# ----------------------------------------------
+#
+# XXX we recommend using the PGDG-supplied packages where possible;
+# see README.md for details.
+
 install_rhel:
 	mkdir -p '$(DESTDIR)/etc/init.d/'
 	$(INSTALL_PROGRAM) RHEL/repmgrd.init '$(DESTDIR)/etc/init.d/repmgrd'
@@ -67,16 +82,23 @@ clean:
 	rm -f repmgr
 	$(MAKE) -C sql clean
 
+# Get correct version numbers and install paths, depending on your postgres version
+PG_VERSION = $(shell pg_config --version | cut -d ' ' -f 2 | cut -d '.' -f 1,2)
+REPMGR_VERSION = $(shell grep REPMGR_VERSION version.h | cut -d ' ' -f 3 | cut -d '"' -f 2)
+PKGLIBDIR = $(shell pg_config --pkglibdir)
+SHAREDIR = $(shell pg_config --sharedir)
+PGBINDIR = /usr/lib/postgresql/$(PG_VERSION)/bin
+
 deb: repmgrd repmgr
-	mkdir -p ./debian/usr/bin
+	mkdir -p ./debian/usr/bin ./debian$(PGBINDIR)
-	cp repmgrd repmgr ./debian/usr/bin/
+	cp repmgrd repmgr ./debian$(PGBINDIR)
-	mkdir -p ./debian/usr/share/postgresql/9.0/contrib/
+	ln -s ../..$(PGBINDIR)/repmgr ./debian/usr/bin/repmgr
-	cp sql/repmgr_funcs.sql ./debian/usr/share/postgresql/9.0/contrib/
+	mkdir -p ./debian$(SHAREDIR)/contrib/
-	cp sql/uninstall_repmgr_funcs.sql ./debian/usr/share/postgresql/9.0/contrib/
+	cp sql/repmgr_funcs.sql ./debian$(SHAREDIR)/contrib/
-	mkdir -p ./debian/usr/lib/postgresql/9.0/lib/
+	cp sql/uninstall_repmgr_funcs.sql ./debian$(SHAREDIR)/contrib/
-	cp sql/repmgr_funcs.so ./debian/usr/lib/postgresql/9.0/lib/
+	mkdir -p ./debian$(PKGLIBDIR)/
+	cp sql/repmgr_funcs.so ./debian$(PKGLIBDIR)/
 	dpkg-deb --build debian
-	mv debian.deb ../postgresql-repmgr-9.0_1.0.0.deb
+	mv debian.deb ../postgresql-repmgr-$(PG_VERSION)_$(REPMGR_VERSION).deb
 	rm -rf ./debian/usr
 
-

PACKAGES.md

@@ -4,10 +4,10 @@ Packaging
 Notes on RedHat Linux, Fedora, and CentOS Builds
 ------------------------------------------------
 
-The RPM packages of PostgreSQL put ``pg_config`` into the ``postgresql-devel``
+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``
+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
@@ -15,31 +15,33 @@ 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::
+occur:
 
     /usr/bin/ld: cannot find -lxslt
     /usr/bin/ld: cannot find -lpam
 
-Install the following packages to correct those::
+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
+directories using sudo, the syntax is hard.  `pg_config` won't be in root's
-path either.  The following recipe should work::
+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::
+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::
+`postgresql90-devel` package installed.  You can check that like this:
 
     rpm -qa --queryformat '%{NAME}\t%{ARCH}\n'  | grep postgresql90-devel
 
@@ -47,7 +49,8 @@ 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::
+here is an example sessions demonstrating the problem case appearing:
+
 
     # yum install postgresql-devel
     ..
@@ -67,20 +70,21 @@ here is an example sessions demonstrating the problem case appearing::
      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::
+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::
+If you already tried to build repmgr before doing this, you'll need to do:
 
     make USE_PGXS=1 clean
 
@@ -89,17 +93,17 @@ 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
+The Debian packages of PostgreSQL put `pg_config` into the development package
-called ``postgresql-server-dev-$version``.
+called `postgresql-server-dev-$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::
+packages installed:
 
     sudo apt-get install libxslt-dev libxml2-dev libpam-dev libedit-dev
 
-If your using Debian packages for PostgreSQL and are building repmgr with the
+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::
+USE_PGXS option you also need to install the corresponding development package:
 
     sudo apt-get install postgresql-server-dev-9.0
 
@@ -110,12 +114,12 @@ 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::
+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::
+You can also make a deb package of repmgr using:
 
     make USE_PGXS=1 deb
 

QUICKSTART.md

@@ -1,114 +1 @@
-repmgr quickstart guide
+The contents of this file have been incorporated into the main README.md document.
-=======================
-
-This quickstart guide provides some annotated examples on basic
-`repmgr` setup. It assumes you are familiar with PostgreSQL replication
-concepts setup and Linux/UNIX system administration.
-
-For the purposes of this guide, we'll assume the database user will be
-`repmgr_usr` and the database will be `repmgr_db`.
-
-
-Master setup
-------------
-
-1. Configure PostgreSQL
-
-  - create user and database:
-
-	```
-	CREATE ROLE repmgr_usr LOGIN SUPERUSER;
-	CREATE DATABASE repmgr_db OWNER repmgr_usr;
-	```
-
-  - configure `postgresql.conf` for replication (see above)
-
-  - update `pg_hba.conf`, e.g.:
-
-	```
-	host    repmgr_db       repmgr_usr  192.168.1.0/24         trust
-	host    replication     repmgr_usr  192.168.1.0/24         trust
-	```
-
-  Restart the PostgreSQL server after making these changes.
-
-2. Create the `repmgr` configuration file:
-
-        $ cat /path/to/repmgr/node1/repmgr.conf
-        cluster=test
-        node=1
-        node_name=node1
-        conninfo='host=repmgr_node1 user=repmgr_usr dbname=repmgr_db'
-        pg_bindir=/path/to/postgres/bin
-
-   (For an annotated `repmgr.conf` file, see `repmgr.conf.sample` in the
-   repository's root directory).
-
-3. Register the master node with `repmgr`:
-
-        $ repmgr -f /path/to/repmgr/node1/repmgr.conf --verbose master register
-        [2015-03-03 17:45:53] [INFO] repmgr connecting to master database
-        [2015-03-03 17:45:53] [INFO] repmgr connected to master, checking its state
-        [2015-03-03 17:45:53] [INFO] master register: creating database objects inside the repmgr_test schema
-        [2015-03-03 17:45:53] [NOTICE] Master node correctly registered for cluster test with id 1 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
-
-Standby setup
--------------
-
-1. Use `repmgr standby clone` to clone a standby from the master:
-
-        repmgr -D /path/to/standby/data -d repmgr_db -U repmgr_usr --verbose standby clone 192.168.1.2
-        [2015-03-03 18:18:21] [NOTICE] No configuration file provided and default file './repmgr.conf' not found - continuing with default values
-        [2015-03-03 18:18:21] [NOTICE] repmgr Destination directory ' /path/to/standby/data' provided
-        [2015-03-03 18:18:21] [INFO] repmgr connecting to upstream node
-        [2015-03-03 18:18:21] [INFO] repmgr connected to upstream node, checking its state
-        [2015-03-03 18:18:21] [INFO] Successfully connected to upstream node. Current installation size is 27 MB
-        [2015-03-03 18:18:21] [NOTICE] Starting backup...
-        [2015-03-03 18:18:21] [INFO] creating directory " /path/to/standby/data"...
-        [2015-03-03 18:18:21] [INFO] Executing: 'pg_basebackup -l "repmgr base backup"  -h localhost -p 9595 -U repmgr_usr -D  /path/to/standby/data '
-        NOTICE:  pg_stop_backup complete, all required WAL segments have been archived
-        [2015-03-03 18:18:23] [NOTICE] repmgr standby clone (using pg_basebackup) complete
-        [2015-03-03 18:18:23] [NOTICE] HINT: You can now start your postgresql server
-        [2015-03-03 18:18:23] [NOTICE] for example : pg_ctl -D  /path/to/standby/data start
-
-  Note that at this point it does not matter if the `repmgr.conf` file is not found.
-
-  This will clone the PostgreSQL database files from the master, including its
-  `postgresql.conf` and `pg_hba.conf` files, and additionally automatically create
-  the `recovery.conf` file containing the correct parameters to start streaming
-  from the primary node.
-
-2. Start the PostgreSQL server
-
-3. Create the `repmgr` configuration file:
-
-        $ cat /path/node2/repmgr/repmgr.conf
-        cluster=test
-        node=2
-        node_name=node2
-        conninfo='host=repmgr_node2 user=repmgr_usr dbname=repmgr_db'
-        pg_bindir=/path/to/postgres/bin
-
-4. Register the standby node with `repmgr`:
-
-        $ repmgr -f /path/to/repmgr/node2/repmgr.conf --verbose standby register
-        [2015-03-03 18:24:34] [NOTICE] Opening configuration file: /path/to/repmgr/node2/repmgr.conf
-        [2015-03-03 18:24:34] [INFO] repmgr connecting to standby database
-        [2015-03-03 18:24:34] [INFO] repmgr connecting to master database
-        [2015-03-03 18:24:34] [INFO] finding node list for cluster 'test'
-        [2015-03-03 18:24:34] [INFO] checking role of cluster node '1'
-        [2015-03-03 18:24:34] [INFO] repmgr connected to master, checking its state
-        [2015-03-03 18:24:34] [INFO] repmgr registering the standby
-        [2015-03-03 18:24:34] [INFO] repmgr registering the standby complete
-        [2015-03-03 18:24:34] [NOTICE] Standby node correctly registered for cluster test with id 2 (conninfo: host=localhost user=repmgr_usr dbname=repmgr_db)
-
-
-This concludes the basic `repmgr` setup of master and standby. The records
-created in the `repl_nodes` table should look something like this:
-
-        repmgr_db=# SELECT * from repmgr_test.repl_nodes;
-         id |  type   | upstream_node_id | cluster | name  |                     conninfo                    | slot_name | priority | active
-        ----+---------+------------------+---------+-------+-------------------------------------------------+-----------+----------+--------
-          1 | primary |                  | test    | node1 | host=localhost user=repmgr_usr dbname=repmgr_db |           |        0 | t
-          2 | standby |                1 | test    | node2 | host=localhost user=repmgr_usr dbname=repmgr_db |           |        0 | t
-        (2 rows)

RHEL/repmgr3-93.spec

@@ -1,61 +0,0 @@
-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

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

RHEL/repmgrd.sysconfig

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

SSH-RSYNC.md

@@ -1,12 +1,13 @@
 Set up trusted copy between postgres accounts
 ---------------------------------------------
 
-If you need to use rsync to clone standby servers, the postgres account
+If you need to use `rsync` to clone standby servers, the `postgres` account
-on your master and standby servers must be each able to access the other
+on your primary and standby servers must be each able to access the other
 using SSH without a password.
 
-First generate a ssh key, using an empty passphrase, and copy the resulting
+First generate an ssh key, using an empty passphrase, and copy the resulting
-keys and a maching authorization file to a privledged user on the other system::
+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.
@@ -22,8 +23,8 @@ keys and a maching authorization file to a privledged user on the other system::
     [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
+Login as a user on the other system, and install the files into the `postgres`
-user's account::
+user's account:
 
     [user@node2 ~]$ sudo chown postgres.postgres authorized_keys id_rsa.pub id_rsa
     [user@node2 ~]$ sudo mkdir -p ~postgres/.ssh

TODO

@@ -5,9 +5,16 @@ Known issues in repmgr
   the database server using the ``pg_ctl`` command may accidentally
   terminate after their associated ssh session ends.
 
+* PGPASSFILE may not be passed to pg_basebackup
+
+
 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
@@ -20,6 +27,48 @@ Planned feature improvements
 * Use pg_basebackup for the data directory, and ALSO rsync for the
   configuration files.
 
-* Use pg_basebackup -X s
+* If no configuration file supplied, search in sensible default locations
-  NOTE: this can be used by including `-X s` in the configuration parameter
+  (currently: current directory and `pg_config --sysconfdir`); if
-  `pg_basebackup_options`
+  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).
+
+* 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).
+
+* repmgr: enable "standby follow" to point a standby at another standby, not
+  just the replication cluster master (see GitHub #130)
+
+
+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, 2010-2015
+ * 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
@@ -23,14 +23,19 @@
 #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 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
  * we use this function to check the new data directory and
@@ -243,6 +248,19 @@ is_pg_dir(char *dir)
 
 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;
 
@@ -279,21 +297,33 @@ create_pg_dir(char *dir, bool force)
 
 			pg_dir = is_pg_dir(dir);
 
-			/*
+
-			 * we use force to reduce the time needed to restore a node which
-			 * turn async after a failover or anything else
-			 */
 			if (pg_dir && force)
 			{
+
+				/*
+				 * 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_warning(_("\nThis looks like a PostgreSQL directory.\n"
+				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 --force option\n"));
+							"running and use the -F/--force option\n"));
 				return false;
 			}
 
@@ -306,3 +336,14 @@ create_pg_dir(char *dir, bool force)
 	}
 	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, 2010-2015
+ * 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
@@ -26,5 +26,6 @@ bool		create_dir(char *dir);
 bool		set_dir_permissions(char *dir);
 bool		is_pg_dir(char *dir);
 bool		create_pg_dir(char *dir, bool force);
+bool		create_witness_pg_dir(char *dir, bool force);
 
 #endif

compat.c

@@ -0,0 +1,111 @@
+/*
+ *
+ * compat.c
+ *	  Provide backports of various functions not publicly
+ *    exposed before PostgreSQL 9.6
+ *
+ * Copyright (C) 2ndQuadrant, 2010-2016
+ *
+ * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#if (PG_VERSION_NUM < 90600)
+
+#include "repmgr.h"
+#include "compat.h"
+
+/*
+ * Append the given string to the buffer, with suitable quoting for passing
+ * the string as a value, in a keyword/pair value in a libpq connection
+ * string
+ *
+ * This function is copied from src/bin/pg_dump/dumputils.c
+ * as it is only publicly exposed from 9.6
+ */
+void
+appendConnStrVal(PQExpBuffer buf, const char *str)
+{
+	const char *s;
+	bool		needquotes;
+
+	/*
+	 * If the string is one or more plain ASCII characters, no need to quote
+	 * it. This is quite conservative, but better safe than sorry.
+	 */
+	needquotes = true;
+	for (s = str; *s; s++)
+	{
+		if (!((*s >= 'a' && *s <= 'z') || (*s >= 'A' && *s <= 'Z') ||
+			  (*s >= '0' && *s <= '9') || *s == '_' || *s == '.'))
+		{
+			needquotes = true;
+			break;
+		}
+		needquotes = false;
+	}
+
+	if (needquotes)
+	{
+		appendPQExpBufferChar(buf, '\'');
+		while (*str)
+		{
+			/* ' and \ must be escaped by to \' and \\ */
+			if (*str == '\'' || *str == '\\')
+				appendPQExpBufferChar(buf, '\\');
+
+			appendPQExpBufferChar(buf, *str);
+			str++;
+		}
+		appendPQExpBufferChar(buf, '\'');
+	}
+	else
+		appendPQExpBufferStr(buf, str);
+}
+
+/*
+ * Adapted from: src/fe_utils/string_utils.c
+ *
+ * Function not publicly available before PostgreSQL 9.6.
+ */
+void
+appendShellString(PQExpBuffer buf, const char *str)
+{
+	const char *p;
+
+	appendPQExpBufferChar(buf, '\'');
+	for (p = str; *p; p++)
+	{
+		if (*p == '\n' || *p == '\r')
+		{
+			fprintf(stderr,
+					_("shell command argument contains a newline or carriage return: \"%s\"\n"),
+					str);
+			exit(ERR_BAD_CONFIG);
+		}
+
+		if (*p == '\'')
+			appendPQExpBufferStr(buf, "'\"'\"'");
+		else
+			appendPQExpBufferChar(buf, *p);
+	}
+
+	appendPQExpBufferChar(buf, '\'');
+}
+
+
+#endif

compat.h

@@ -0,0 +1,29 @@
+/*
+ * compat.h
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#ifndef _COMPAT_H_
+#define _COMPAT_H_
+
+extern void
+appendConnStrVal(PQExpBuffer buf, const char *str);
+
+extern void
+appendShellString(PQExpBuffer buf, const char *str);
+
+#endif

config.h

@@ -1,6 +1,7 @@
 /*
  * config.h
- * Copyright (c) 2ndQuadrant, 2010-2015
+ *
+ * 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
@@ -24,6 +25,7 @@
 
 #include "strutil.h"
 
+#define CONFIG_FILE_NAME	"repmgr.conf"
 
 typedef struct EventNotificationListCell
 {
@@ -56,36 +58,90 @@ typedef struct
 	int			node;
 	int         upstream_node;
 	char		conninfo[MAXLEN];
+	char		barman_server[MAXLEN];
+	char		barman_config[MAXLEN];
 	int			failover;
 	int			priority;
 	char		node_name[MAXLEN];
+	/* commands executed by repmgrd */
 	char		promote_command[MAXLEN];
 	char		follow_command[MAXLEN];
+	/* Overrides for pg_ctl commands */
+	char		service_stop_command[MAXLEN];
+	char		service_start_command[MAXLEN];
+	char		service_restart_command[MAXLEN];
+	char		service_reload_command[MAXLEN];
+	char		service_promote_command[MAXLEN];
 	char		loglevel[MAXLEN];
 	char		logfacility[MAXLEN];
 	char		rsync_options[QUERY_STR_LEN];
 	char		ssh_options[QUERY_STR_LEN];
 	int			master_response_timeout;
 	int			reconnect_attempts;
-	int			reconnect_intvl;
+	int			reconnect_interval;
 	char		pg_bindir[MAXLEN];
 	char		pg_ctl_options[MAXLEN];
 	char		pg_basebackup_options[MAXLEN];
+	char		restore_command[MAXLEN];
 	char		logfile[MAXLEN];
 	int			monitor_interval_secs;
 	int			retry_promote_interval_secs;
+	int			witness_repl_nodes_sync_interval_secs;
 	int			use_replication_slots;
 	char		event_notification_command[MAXLEN];
 	EventNotificationList event_notifications;
 	TablespaceList tablespace_mapping;
 }	t_configuration_options;
 
-#define T_CONFIGURATION_OPTIONS_INITIALIZER { "", -1, NO_UPSTREAM_NODE, "", MANUAL_FAILOVER, -1, "", "", "", "", "", "", "", -1, -1, -1, "", "", "", "", 0, 0, 0, "", { NULL, NULL }, {NULL, NULL} }
+/*
+ * The following will initialize the structure with a minimal set of options;
+ * actual defaults are set in parse_config() before parsing the configuration file
+ */
+#define T_CONFIGURATION_OPTIONS_INITIALIZER { "", UNKNOWN_NODE_ID, NO_UPSTREAM_NODE, "", "", "", MANUAL_FAILOVER, -1, "", "", "", "", "", "", "", "", "", "", "", "", -1, -1, -1, "", "", "", "", "", 0, 0, 0, 0, "", { NULL, NULL }, { NULL, NULL } }
 
+typedef struct ItemListCell
+{
+	struct ItemListCell *next;
+	char			    *string;
+} ItemListCell;
+
+typedef struct ItemList
+{
+	ItemListCell *head;
+	ItemListCell *tail;
+} ItemList;
+
+typedef struct TablespaceDataListCell
+{
+	struct TablespaceDataListCell *next;
+	char	   *name;
+	char	   *oid;
+	char	   *location;
+	/* optional payload */
+	FILE       *f;
+} TablespaceDataListCell;
+
+typedef struct TablespaceDataList
+{
+	TablespaceDataListCell *head;
+	TablespaceDataListCell *tail;
+} TablespaceDataList;
+
+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);
+
+void		_parse_config(t_configuration_options *options, ItemList *error_list);
+bool		parse_config(t_configuration_options *options);
+bool		reload_config(t_configuration_options *orig_options);
 
-bool		parse_config(const char *config_file, t_configuration_options *options);
 void		parse_line(char *buff, char *name, char *value);
 char	   *trim(char *s);
-bool		reload_config(char *config_file, t_configuration_options *orig_options);
+void		item_list_append(ItemList *item_list, char *error_message);
-
+int			repmgr_atoi(const char *s,
+						const char *config_item,
+						ItemList *error_list,
+						bool allow_negative);
+extern bool		config_file_found;
 #endif

dbutils.h

@@ -1,6 +1,7 @@
 /*
  * dbutils.h
- * Copyright (c) 2ndQuadrant, 2010-2015
+ *
+ * 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
@@ -20,16 +21,80 @@
 #ifndef _REPMGR_DBUTILS_H_
 #define _REPMGR_DBUTILS_H_
 
+#include "access/xlogdefs.h"
+#include "pqexpbuffer.h"
+
 #include "config.h"
 #include "strutil.h"
 
 
+typedef enum {
+	UNKNOWN = 0,
+	MASTER,
+	STANDBY,
+	WITNESS
+} t_server_type;
 
+/*
+ * Struct to store node information
+ */
+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 \
+}
+
+/*
+ * Struct to store replication slot information
+ */
+
+typedef struct s_replication_slot
+{
+	char slot_name[MAXLEN];
+    char slot_type[MAXLEN];
+	bool active;
+}   t_replication_slot;
+
+extern char		repmgr_schema[MAXLEN];
+
+PGconn *_establish_db_connection(const char *conninfo,
+								 const bool exit_on_error,
+								 const bool log_notice,
+								 const bool verbose_only);
 PGconn *establish_db_connection(const char *conninfo,
 								const bool exit_on_error);
+PGconn *establish_db_connection_quiet(const char *conninfo);
+PGconn *test_db_connection(const char *conninfo);
 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);
@@ -42,7 +107,7 @@ 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);
-
+bool		get_conninfo_value(const char *conninfo, const char *keyword, char *output);
 PGconn     *get_upstream_connection(PGconn *standby_conn, char *cluster,
 									int node_id,
 									int *upstream_node_id_ptr,
@@ -54,15 +119,24 @@ 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		create_replication_slot(PGconn *conn, char *slot_name, int server_version_num, PQExpBufferData *error_msg);
-
+int			get_slot_record(PGconn *conn, char *slot_name, t_replication_slot *record);
+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		witness_copy_node_records(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		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 active);
 bool		delete_node_record(PGconn *conn, int node, char *action);
+int			get_node_record(PGconn *conn, char *cluster, int node_id, t_node_info *node_info);
+int			get_node_record_by_name(PGconn *conn, char *cluster, const char *node_name, t_node_info *node_info);
+bool        update_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 active);
+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);
 bool        create_event_record(PGconn *conn, t_configuration_options *options, int node_id, char *event, bool successful, char *details);
 
-
+int		    get_node_replication_state(PGconn *conn, char *node_name, char *output);
+t_server_type parse_node_type(const char *type);
+int			get_data_checksum_version(const char *data_directory);
 #endif
+

debian/DEBIAN/control

@@ -1,9 +1,9 @@
 Package: repmgr-auto
-Version: 2.0beta2
+Version: 3.2dev
 Section: database
 Priority: optional
 Architecture: all
-Depends: rsync, postgresql-9.0 | postgresql-9.1 | postgresql-9.2 | postgresql-9.3 | postgresql-9.4
+Depends: rsync, postgresql-9.3 | postgresql-9.4 | postgresql-9.5
-Maintainer: Jaime Casanova <jaime@2ndQuadrant.com>
+Maintainer: Self built package <user@localhost>
 Description: PostgreSQL replication setup, magament and monitoring
  has two main executables

debian/repmgr.repmgrd.default

@@ -12,7 +12,7 @@ REPMGRD_ENABLED=no
 #REPMGRD_USER=postgres
 
 # repmgrd binary
-#REPMGR_BIN=/usr/bin/repmgr
+#REPMGRD_BIN=/usr/bin/repmgrd
 
 # pid file
-#REPMGR_PIDFILE=/var/run/repmgrd.pid
+#REPMGRD_PIDFILE=/var/run/repmgrd.pid

debian/repmgr.repmgrd.init

@@ -59,7 +59,7 @@ do_stop()
 	#   0 if daemon has been stopped
 	#   1 if daemon was already stopped
 	#   other if daemon could not be stopped or a failure occurred
-	start-stop-daemon --stop --quiet --retry=TERM/30/KILL/5 --pidfile $REPMGRD_PIDFILE --exec $REPMGRD_BIN
+	start-stop-daemon --stop --quiet --retry=TERM/30/KILL/5 --pidfile $REPMGRD_PIDFILE --name "$(basename $REPMGRD_BIN)"
 }
 
 case "$1" in

dirmod.c

@@ -0,0 +1,194 @@
+/*
+ *
+ * dirmod.c
+ *	  directory handling functions
+ *
+ * Copyright (C) 2ndQuadrant, 2010-2016
+ *
+ * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include "postgres_fe.h"
+
+/* Don't modify declarations in system headers */
+
+#include <unistd.h>
+#include <dirent.h>
+#include <sys/stat.h>
+
+/*
+ * pgfnames
+ *
+ * return a list of the names of objects in the argument directory.  Caller
+ * must call pgfnames_cleanup later to free the memory allocated by this
+ * function.
+ */
+char	  **
+pgfnames(const char *path)
+{
+	DIR		   *dir;
+	struct dirent *file;
+	char	  **filenames;
+	int			numnames = 0;
+	int			fnsize = 200;	/* enough for many small dbs */
+
+	dir = opendir(path);
+	if (dir == NULL)
+	{
+		return NULL;
+	}
+
+	filenames = (char **) palloc(fnsize * sizeof(char *));
+
+	while (errno = 0, (file = readdir(dir)) != NULL)
+	{
+		if (strcmp(file->d_name, ".") != 0 && strcmp(file->d_name, "..") != 0)
+		{
+			if (numnames + 1 >= fnsize)
+			{
+				fnsize *= 2;
+				filenames = (char **) repalloc(filenames,
+											   fnsize * sizeof(char *));
+			}
+			filenames[numnames++] = pstrdup(file->d_name);
+		}
+	}
+
+	if (errno)
+	{
+		fprintf(stderr, _("could not read directory \"%s\": %s\n"),
+				path, strerror(errno));
+	}
+
+	filenames[numnames] = NULL;
+
+	if (closedir(dir))
+	{
+		fprintf(stderr, _("could not close directory \"%s\": %s\n"),
+				path, strerror(errno));
+	}
+
+	return filenames;
+}
+
+
+/*
+ *	pgfnames_cleanup
+ *
+ *	deallocate memory used for filenames
+ */
+void
+pgfnames_cleanup(char **filenames)
+{
+	char	  **fn;
+
+	for (fn = filenames; *fn; fn++)
+		pfree(*fn);
+
+	pfree(filenames);
+}
+
+
+/*
+ *	rmtree
+ *
+ *	Delete a directory tree recursively.
+ *	Assumes path points to a valid directory.
+ *	Deletes everything under path.
+ *	If rmtopdir is true deletes the directory too.
+ *	Returns true if successful, false if there was any problem.
+ *	(The details of the problem are reported already, so caller
+ *	doesn't really have to say anything more, but most do.)
+ */
+bool
+rmtree(const char *path, bool rmtopdir)
+{
+	bool		result = true;
+	char		pathbuf[MAXPGPATH];
+	char	  **filenames;
+	char	  **filename;
+	struct stat statbuf;
+
+	/*
+	 * we copy all the names out of the directory before we start modifying
+	 * it.
+	 */
+	filenames = pgfnames(path);
+
+	if (filenames == NULL)
+		return false;
+
+	/* now we have the names we can start removing things */
+	for (filename = filenames; *filename; filename++)
+	{
+		snprintf(pathbuf, MAXPGPATH, "%s/%s", path, *filename);
+
+		/*
+		 * It's ok if the file is not there anymore; we were just about to
+		 * delete it anyway.
+		 *
+		 * This is not an academic possibility. One scenario where this
+		 * happens is when bgwriter has a pending unlink request for a file in
+		 * a database that's being dropped. In dropdb(), we call
+		 * ForgetDatabaseFsyncRequests() to flush out any such pending unlink
+		 * requests, but because that's asynchronous, it's not guaranteed that
+		 * the bgwriter receives the message in time.
+		 */
+		if (lstat(pathbuf, &statbuf) != 0)
+		{
+			if (errno != ENOENT)
+			{
+				result = false;
+			}
+			continue;
+		}
+
+		if (S_ISDIR(statbuf.st_mode))
+		{
+			/* call ourselves recursively for a directory */
+			if (!rmtree(pathbuf, true))
+			{
+				/* we already reported the error */
+				result = false;
+			}
+		}
+		else
+		{
+			if (unlink(pathbuf) != 0)
+			{
+				if (errno != ENOENT)
+				{
+					result = false;
+				}
+			}
+		}
+	}
+
+	if (rmtopdir)
+	{
+		if (rmdir(path) != 0)
+		{
+			result = false;
+		}
+	}
+
+	pgfnames_cleanup(filenames);
+
+	return result;
+}
+

dirmod.h

@@ -0,0 +1,23 @@
+/*
+ * dirmod.h
+ * 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
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#ifndef _DIRMOD_H_
+#define _DIRMOD_H_
+
+#endif

docs/repmgrd-failover-mechanism.md

@@ -0,0 +1,75 @@
+repmgrd's failover algorithm
+============================
+
+When implementing automatic failover, there are two factors which are critical in
+ensuring the desired result is achieved:
+
+  - has the master node genuinely failed?
+  - which is the best node to promote to the new master?
+
+This document outlines repmgrd's decision-making process during automatic failover
+for standbys directly connected to the master node.
+
+
+Master node failure detection
+-----------------------------
+
+If a `repmgrd` instance running on a PostgreSQL standby node is unable to connect to
+the master node, this doesn't neccesarily mean that the master is down and a
+failover is required. Factors such as network connectivity issues could mean that
+even though the standby node is isolated, the replication cluster as a whole
+is functioning correctly, and promoting the standby without further verification
+could result in a "split-brain" situation.
+
+In the event that `repmgrd` is unable to connect to the master node, it will attempt
+to reconnect to the master server several times (as defined by the `reconnect_attempts`
+parameter in `repmgr.conf`), with reconnection attempts  occuring at the interval
+specified by `reconnect_interval`. This happens to verify that the master is definitively
+not accessible (e.g. that connection was not lost due to a brief network glitch).
+
+Appropriate values for these settings will depend very much on the replication
+cluster environment. There will necessarily be a trade-off between the time it
+takes to assume the master is not reachable, and the reliability of that conclusion.
+A standby in a different physical location to the master will probably need a longer
+check interval to rule out possible network issues, whereas one located in the same
+rack with a direct connection between servers could perform the check very quickly.
+
+Note that it's possible the master comes back online after this point is reached,
+but before a new master has been selected; in this case it will be noticed
+during the selection of a new master and no actual failover will take place.
+
+Promotion candidate selection
+-----------------------------
+
+Once `repmgrd` has decided the master is definitively unreachable, following checks
+will be carried out:
+
+* attempts to connect to all other nodes in the cluster (including the witness
+  node, if defined) to establish the state of the cluster, including their
+  current LSN
+
+* If less than half of the nodes are visible (from the viewpoint
+  of this node), `repmgrd` will not take any further action. This is to ensure that
+  e.g. if a replication cluster is spread over multiple data centres, a split-brain
+  situation does not occur if there is a network failure between datacentres. Note
+  that if nodes are split evenly between data centres, a witness server can be
+  used to establish the "majority" daat centre.
+
+* `repmgrd` polls all visible servers and waits for each node to return a valid LSN;
+  it updates the LSN previously  stored for this node if it has increased since
+  the initial check
+
+* once all LSNs have been retrieved, `repmgrd` will check for the highest LSN; if
+  its own node has the highest LSN, it will attempt to promote itself (using the
+  command defined in `promote_command` in `repmgr.conf`. Note that if using
+  `repmgr standby promote` as the promotion command, and the original master becomes available
+  before the promotion takes effect, `repmgr` will return an error and no promotion
+  will take place, and `repmgrd` will resume monitoring as usual.
+
+* if the node is not the promotion candidate, `repmgrd` will execute the
+  `follow_command` defined in `repmgr.conf`. If using `repmgr standby follow` here,
+  `repmgr` will attempt to detect the new master node and attach to that.
+
+
+
+

docs/repmgrd-node-fencing.md

@@ -0,0 +1,152 @@
+Fencing a failed master node with repmgrd and pgbouncer
+=======================================================
+
+With automatic failover, it's essential to ensure that a failed master
+remains inaccessible to your application, even if it comes back online
+again, to avoid a split-brain situation.
+
+By using `pgbouncer` together with `repmgrd`, it's possible to combine
+automatic failover with a process to isolate the failed master from
+your application and ensure that all connections which should go to
+the master are directed there smoothly without having to reconfigure
+your application. (Note that as a connection pooler, `pgbouncer` can
+benefit your application in other ways, but those are beyond the scope
+of this document).
+
+* * *
+
+> *WARNING*: automatic failover is tricky to get right. This document
+> demonstrates one possible implementation method, however you should
+> carefully configure and test any setup to suit the needs of your own
+> replication cluster/application.
+
+* * *
+
+In a failover situation, `repmgrd` promotes a standby to master by executing
+the command defined in `promote_command`. Normally this would be something like:
+
+    repmgr standby promote -f /etc/repmgr.conf
+
+By wrapping this in a custom script which adjusts the `pgbouncer` configuration
+on all nodes, it's possible to fence the failed master and redirect write
+connections to the new master.
+
+The script consists of three sections:
+
+* commands to pause `pgbouncer` on all nodes
+* the promotion command itself
+* commands to reconfigure and restart `pgbouncer` on all nodes
+
+Note that it requires password-less SSH access between all nodes to be able to
+update the `pgbouncer` configuration files.
+
+For the purposes of this demonstration, we'll assume there are 3 nodes (master
+and two standbys), with `pgbouncer` listening on port 6432 handling connections
+to a database called `appdb`.  The `postgres` system user must have write
+access to the `pgbouncer` configuration files on all nodes. We'll assume
+there's a main `pgbouncer` configuration file, `/etc/pgbouncer.ini`, which uses
+the `%include` directive (available from PgBouncer 1.6) to include a separate
+configuration file, `/etc/pgbouncer.database.ini`, which will be modified by
+`repmgr`.
+
+`/etc/pgbouncer.ini` should look something like this:
+
+    [pgbouncer]
+
+    logfile = /var/log/pgbouncer/pgbouncer.log
+    pidfile = /var/run/pgbouncer/pgbouncer.pid
+
+    listen_addr = *
+    listen_port = 6532
+    unix_socket_dir = /tmp
+
+    auth_type = trust
+    auth_file = /etc/pgbouncer.auth
+
+    admin_users = postgres
+    stats_users = postgres
+
+    pool_mode = transaction
+
+    max_client_conn = 100
+    default_pool_size = 20
+    min_pool_size = 5
+    reserve_pool_size = 5
+    reserve_pool_timeout = 3
+
+    log_connections = 1
+    log_disconnections = 1
+    log_pooler_errors = 1
+
+    %include /etc/pgbouncer.database.ini
+
+The actual script is as follows; adjust the configurable items as appropriate:
+
+`/var/lib/postgres/repmgr/promote.sh`
+
+
+    #!/usr/bin/env bash
+    set -u
+    set -e
+
+    # Configurable items
+    PGBOUNCER_HOSTS="node1 node2 node3"
+    PGBOUNCER_DATABASE_INI="/etc/pgbouncer.database.ini"
+    PGBOUNCER_DATABASE="appdb"
+    PGBOUNCER_PORT=6432
+
+    REPMGR_DB="repmgr"
+    REPMGR_USER="repmgr"
+    REPMGR_SCHEMA="repmgr_test"
+
+    # 1. Pause running pgbouncer instances
+    for HOST in $PGBOUNCER_HOSTS
+    do
+        psql -t -c "pause" -h $HOST -p $PGBOUNCER_PORT -U postgres pgbouncer
+    done
+
+    # 2. Promote this node from standby to master
+
+    repmgr standby promote -f /etc/repmgr.conf
+
+    # 3. Reconfigure pgbouncer instances
+
+    PGBOUNCER_DATABASE_INI_NEW="/tmp/pgbouncer.database.ini"
+
+    for HOST in $PGBOUNCER_HOSTS
+    do
+        # Recreate the pgbouncer config file
+        echo -e "[databases]\n" > $PGBOUNCER_DATABASE_INI_NEW
+
+        psql -d $REPMGR_DB -U $REPMGR_USER -t -A \
+          -c "SELECT '${PGBOUNCER_DATABASE}-rw= ' || conninfo || ' application_name=pgbouncer_${HOST}' \
+              FROM ${REPMGR_SCHEMA}.repl_nodes \
+              WHERE active = TRUE AND type='master'" >> $PGBOUNCER_DATABASE_INI_NEW
+
+        psql -d $REPMGR_DB -U $REPMGR_USER -t -A \
+          -c "SELECT '${PGBOUNCER_DATABASE}-ro= ' || conninfo || ' application_name=pgbouncer_${HOST}' \
+              FROM $REPMGR_SCHEMA.repl_nodes \
+              WHERE node_name='${HOST}'" >> $PGBOUNCER_DATABASE_INI_NEW
+
+        rsync $PGBOUNCER_DATABASE_INI_NEW $HOST:$PGBOUNCER_DATABASE_INI
+
+        psql -tc "reload" -h $HOST -p $PGBOUNCER_PORT -U postgres pgbouncer
+        psql -tc "resume" -h $HOST -p $PGBOUNCER_PORT -U postgres pgbouncer
+
+    done
+
+    # Clean up generated file
+    rm $PGBOUNCER_DATABASE_INI_NEW
+
+    echo "Reconfiguration of pgbouncer complete"
+
+Script and template file should be installed on each node where
+`repmgrd` is running.
+
+Finally, set `promote_command` in `repmgr.conf` on each node to
+point to the custom promote script:
+
+    promote_command=/var/lib/postgres/repmgr/promote.sh
+
+and reload/restart any running `repmgrd` instances for the changes to take
+effect.

errcode.h

@@ -1,6 +1,6 @@
 /*
  * errcode.h
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * 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
@@ -29,11 +29,17 @@
 #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
+#define ERR_BAD_BACKUP_LABEL 17
+#define ERR_SWITCHOVER_FAIL 18
+#define ERR_BARMAN 19
+#define ERR_REGISTRATION_SYNC 20
+
 
 #endif   /* _ERRCODE_H_ */

log.c

@@ -1,6 +1,6 @@
 /*
  * log.c - Logging methods
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  * This module is a set of methods for logging (currently only syslog)
  *
@@ -39,39 +39,128 @@
 
 /* #define REPMGR_DEBUG */
 
-void
+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)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 0)));
+
+int			log_type = REPMGR_STDERR;
+int			log_level = LOG_NOTICE;
+int			last_log_level = LOG_NOTICE;
+int			verbose_logging = false;
+int			terse_logging = false;
+/*
+ * Global variable to be set by the main application to ensure any log output
+ * emitted before logger_init is called, is output in the correct format
+ */
+int			logger_output_mode = OM_DAEMON;
+
+extern void
 stderr_log_with_level(const char *level_name, int level, const char *fmt, ...)
 {
-	time_t		t;
+	va_list		arglist;
-	struct tm  *tm;
+
-	char		buff[100];
+	va_start(arglist, fmt);
-	va_list		ap;
+	_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)
+{
+	char		buf[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)
 	{
+
+		/* Format log line prefix with timestamp if in daemon mode */
+		if (logger_output_mode == OM_DAEMON)
+		{
+			time_t		t;
+			struct tm  *tm;
 			time(&t);
 			tm = localtime(&t);
-		strftime(buff, 100, "[%Y-%m-%d %H:%M:%S]", tm);
+			strftime(buf, 100, "[%Y-%m-%d %H:%M:%S]", tm);
-		fprintf(stderr, "%s [%s] ", buff, level_name);
+			fprintf(stderr, "%s [%s] ", buf, level_name);
+		}
+		else
+		{
+			fprintf(stderr, "%s: ", level_name);
+		}
 
-		va_start(ap, fmt);
 		vfprintf(stderr, fmt, ap);
-		va_end(ap);
 
 		fflush(stderr);
 	}
 }
 
+void
+log_hint(const char *fmt, ...)
+{
+	va_list		ap;
 
-static int	detect_log_level(const char *level);
+	if (terse_logging == false)
-static int	detect_log_facility(const char *facility);
+	{
+		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);
+}
 
-int			log_type = REPMGR_STDERR;
-int			log_level = LOG_NOTICE;
 
 bool
-logger_init(t_configuration_options * opts, const char *ident, const char *level, const char *facility)
+logger_init(t_configuration_options *opts, const char *ident)
 {
+	char	   *level = opts->loglevel;
+	char	   *facility = opts->logfacility;
+
 	int			l;
 	int			f;
 
@@ -95,12 +184,19 @@ logger_init(t_configuration_options * opts, const char *ident, const char *level
 		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);
 	}
 
+	/*
+	 * STDERR only logging requested - finish here without setting up any further
+	 * logging facility.
+	 */
+	if (logger_output_mode == OM_COMMAND_LINE)
+		return true;
+
 	if (facility && *facility)
 	{
 
@@ -144,19 +240,40 @@ logger_init(t_configuration_options * opts, const char *ident, const char *level
 	{
 		FILE	   *fd;
 
-		fd = freopen(opts->logfile, "a", stderr);
+		/* 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)
 		{
-			fprintf(stderr, "error reopening stderr to '%s': %s",
+			stderr_log_err(_("Unable to open specified logfile '%s' for writing: %s\n"), opts->logfile, strerror(errno));
-					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)
 {
@@ -169,17 +286,32 @@ 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)
+logger_set_verbose(void)
 {
-	if (log_level < minimum)
+	verbose_logging = true;
-		log_level = minimum;
 }
 
+
+/*
+ * 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)
 {
@@ -200,17 +332,16 @@ detect_log_level(const char *level)
 	if (!strcmp(level, "EMERG"))
 		return LOG_EMERG;
 
-	return 0;
+	return -1;
 }
 
-int
+static int
 detect_log_facility(const char *facility)
 {
 	int			local = 0;
 
 	if (!strncmp(facility, "LOCAL", 5) && strlen(facility) == 6)
 	{
-
 		local = atoi(&facility[5]);
 
 		switch (local)

log.h

@@ -1,6 +1,6 @@
 /*
  * log.h
- * Copyright (c) 2ndQuadrant, 2010-2015
+ * 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
@@ -25,7 +25,10 @@
 #define REPMGR_SYSLOG 1
 #define REPMGR_STDERR 2
 
-void
+#define OM_COMMAND_LINE 1
+#define OM_DAEMON       2
+
+extern void
 stderr_log_with_level(const char *level_name, int level, const char *fmt,...)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 
@@ -112,15 +115,26 @@ __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
 #endif
 
 
+int			detect_log_level(const char *level);
+
 /* Logger initialisation and shutdown */
+
+bool		logger_init(t_configuration_options * opts, const char *ident);
+
 bool		logger_shutdown(void);
 
-bool logger_init(t_configuration_options * opts, const char *ident,
+void		logger_set_verbose(void);
-			const char *level, const char *facility);
+void		logger_set_terse(void);
 
-void		logger_min_verbose(int minimum);
+void		log_hint(const char *fmt, ...)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 1, 2)));
+void		log_verbose(int level, const char *fmt, ...)
+__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
 
 extern int	log_type;
 extern int	log_level;
+extern int	verbose_logging;
+extern int	terse_logging;
+extern int	logger_output_mode;
 
-#endif
+#endif /* _REPMGR_LOG_H_ */

repmgr.conf.sample

@@ -2,23 +2,42 @@
 # Replication Manager sample configuration file
 ###################################################
 
+# Some configuration items will be set with a default value; this
+# is noted for each item. Where no default value is shown, the
+# parameter will be treated as empty or false.
+
 # Required configuration items
 # ============================
 #
 # repmgr and repmgrd require these items to be configured:
 
-# Cluster name
+# Cluster name - this will be used by repmgr to generate its internal
-cluster=test
+# 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.
+#  replication function, as this will cause confusion when e.g.
-#  "standby2" is promoted to master)
+#  "standby2" is promoted to primary)
-node=2
+#node=2           # a unique integer
-node_name=node2
+#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
+# Database connection information as a conninfo string
-conninfo='host=192.168.204.104 dbname=repmgr_db user=repmgr_usr'
+# This must be accessible to all servers in the cluster; for details see:
+#
+#   https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNSTRING
+#
+#conninfo='host=192.168.204.104 dbname=repmgr user=repmgr'
+#
+# If repmgrd is in use, consider explicitly setting `connect_timeout` in the
+# conninfo string to determine the length of time which elapses before
+# a network connection attempt is abandoned; for details see:
+#
+#   https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-CONNECT-CONNECT-TIMEOUT
 
 # Optional configuration items
 # ============================
@@ -26,33 +45,46 @@ conninfo='host=192.168.204.104 dbname=repmgr_db user=repmgr_usr'
 # Replication settings
 # ---------------------
 
-# when using cascading replication and a standby is to be connected to an
+# When using cascading replication, a standby can connect to another
-# upstream standby, specify that node's ID with 'upstream_node'. The node
+# upstream standby node which is specified by setting 'upstream_node'.
-# must exist before the new standby can be registered. If a standby is
+# In that case, the upstream node must exist before the new standby
-# to connect directly to a master node, this parameter is not required.
+# can be registered. If 'upstream_node' is not set, then the standby
-#
+# will connect directly to the primary node.
 #upstream_node=1
 
-# physical replication slots - PostgreSQL 9.4 and later only
+# use 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
+#loglevel=NOTICE
+
+# Note that logging facility settings will only apply to `repmgrd` by default;
+# `repmgr` will always write to STDERR unless the switch `--log-to-file` is
+# supplied, in which case it will log to the same destination as `repmgrd`.
+# This is mainly intended for those cases when `repmgr` is executed directly
+# by `repmgrd`.
 
 # Logging facility: possible values are STDERR or - for Syslog integration - one of LOCAL0, LOCAL1, ..., LOCAL7, USER
 # (default: STDERR)
-logfacility=STDERR
+#logfacility=STDERR
 
 # stderr can be redirected to an arbitrary file:
 #
-# logfile='/var/log/repmgr.log'
+#logfile='/var/log/repmgr/repmgr.log'
+
+# By default only repmgrd log output will be written to a file,
+# if defined in "logfile"
+# enable this to restore old behaviour where output from the repmgr
+# client will be written to the logfile too
+#log_repmgr_to_file = 0
 
 # event notifications can be passed to an arbitrary external program
 # together with the following parameters:
@@ -80,13 +112,41 @@ logfacility=STDERR
 # path to PostgreSQL binary directory (location of pg_ctl, pg_basebackup etc.)
 # (if not provided, defaults to system $PATH)
 #pg_bindir=/usr/bin/
+#
+# Debian/Ubuntu users: you will probably need to set this to the directory
+# where `pg_ctl` is located, e.g. /usr/lib/postgresql/9.5/bin/
+
+# service control commands
+#
+# repmgr provides options to override the default pg_ctl commands
+# used to stop, start, restart, reload and promote the PostgreSQL cluster
+#
+# NOTE: These commands must be runnable on remote nodes as well for switchover
+# to function correctly.
+#
+# If you use sudo, the user repmgr runs as (usually 'postgres')  must have
+# passwordless sudo access to execute the command
+#
+# For example, to use systemd, you may use the following configuration:
+#
+#    # this is required when running sudo over ssh without -t:
+#    Defaults:postgres !requiretty
+#    postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.5, \
+#       /usr/bin/systemctl start postgresql-9.5, \
+#       /usr/bin/systemctl restart postgresql-9.5
+#
+# service_start_command = systemctl start postgresql-9.5
+# service_stop_command = systemctl stop postgresql-9.5
+# service_restart_command = systemctl restart postgresql-9.5
+# service_reload_command = pg_ctlcluster 9.5 main reload
+# service_promote_command = pg_ctlcluster 9.5 main promote
 
 # external command options
 
 #rsync_options=--archive --checksum --compress --progress --rsh="ssh -o \"StrictHostKeyChecking no\""
 #ssh_options=-o "StrictHostKeyChecking no"
 
-# external command arguments
+# external command arguments. Values shown are examples.
 
 #pg_ctl_options='-s'
 #pg_basebackup_options='--xlog-method=s'
@@ -101,34 +161,51 @@ logfacility=STDERR
 #
 # tablespace_mapping=/path/to/original/tablespace=/path/to/new/tablespace
 
+# You can specify a restore_command to be used in the recovery.conf that
+# will be placed in the cloned standby
+#
+# restore_command = cp /path/to/archived/wals/%f %p
 
 # Failover settings (repmgrd)
 # ---------------------------
 #
-# These settings are only applied when repmgrd is running.
+# These settings are only applied when repmgrd is running. Values shown
+# are defaults.
 
-# How many seconds we wait for master response before declaring master failure
+# monitoring interval in seconds; default is 2
-master_response_timeout=60
-
-# How many time we try to reconnect to master before starting 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 master
-promote_command='repmgr standby promote -f /path/to/repmgr.conf'
-follow_command='repmgr standby follow -f /path/to/repmgr.conf -W'
-
-# monitoring interval; default is 2s
-#
 #monitor_interval_secs=2
 
-# change wait time for master; before we bail out and exit when the master
+# Maximum number of seconds to wait for a response from the primary server
+# before deciding it has failed.
+#master_response_timeout=60
+
+# Number of attempts at what interval (in seconds) to try and
+# connect to  a server to establish its status (e.g. master
+# during failover)
+#reconnect_attempts=6
+#reconnect_interval=10
+
+# Autofailover options
+#failover=manual    # one of 'automatic', 'manual' (default: manual)
+                    # defines the action to take in the event of upstream failure
+                    #
+                    # 'automatic': repmgrd will automatically attempt to promote the
+                    #    node or follow the new upstream node
+                    # 'manual': repmgrd will take no action and the mode will require
+                    #    manual attention to reattach it to replication
+
+#priority=100       # indicate a preferred priorty for promoting nodes
+                    # a value of zero or less prevents the node being promoted to primary
+                    # (default: 100)
+
+#promote_command='repmgr standby promote -f /path/to/repmgr.conf'
+#follow_command='repmgr standby follow -f /path/to/repmgr.conf -W'
+
+# 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
 
-
+# Number of seconds after which the witness server resyncs the repl_nodes table
+#witness_repl_nodes_sync_interval_secs=15

repmgr.h

@@ -1,6 +1,6 @@
 /*
  * repmgr.h
- * Copyright (c) 2ndQuadrant, 2010-2015
+ * 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
@@ -20,92 +20,228 @@
 #ifndef _REPMGR_H_
 #define _REPMGR_H_
 
-#include "postgres_fe.h"
+#include <libpq-fe.h>
-#include "libpq-fe.h"
+#include <postgres_fe.h>
-
+#include <getopt_long.h>
-
+#include "pqexpbuffer.h"
-#include "getopt_long.h"
 
 #include "strutil.h"
 #include "dbutils.h"
 #include "errcode.h"
 #include "config.h"
+#include "dirmod.h"
 
 #define MIN_SUPPORTED_VERSION		"9.3"
 #define MIN_SUPPORTED_VERSION_NUM	90300
 
-#include "config.h"
-#define MAXFILENAME		1024
 #define ERRBUFF_SIZE	512
 
-#define DEFAULT_CONFIG_FILE		"./repmgr.conf"
+#define DEFAULT_WAL_KEEP_SEGMENTS	"0"
-#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
 
+/* command line options without short versions */
+#define OPT_HELP                         1
+#define OPT_CHECK_UPSTREAM_CONFIG        2
+#define OPT_RECOVERY_MIN_APPLY_DELAY     3
+#define OPT_COPY_EXTERNAL_CONFIG_FILES   4
+#define OPT_CONFIG_ARCHIVE_DIR           5
+#define OPT_PG_REWIND                    6
+#define OPT_PWPROMPT                     7
+#define OPT_CSV                          8
+#define OPT_NODE                         9
+#define OPT_WITHOUT_BARMAN               10
+#define OPT_NO_UPSTREAM_CONNECTION       11
+#define OPT_REGISTER_WAIT                12
+#define OPT_CLUSTER                      13
+#define OPT_LOG_TO_FILE                  14
+#define OPT_UPSTREAM_CONNINFO            15
+#define OPT_NO_CONNINFO_PASSWORD         16
+#define OPT_REPLICATION_USER             17
 
-typedef enum {
+/* deprecated command line options */
-    UNKNOWN = 0,
+#define OPT_INITDB_NO_PWPROMPT           998
-	MASTER,
+#define OPT_IGNORE_EXTERNAL_CONFIG_FILES 999
-	STANDBY,
-	WITNESS
-} t_server_type;
 
+/* values for --copy-external-config-files */
+#define CONFIG_FILE_SAMEPATH 1
+#define CONFIG_FILE_PGDATA 2
 
 
 /* Run time options type */
 typedef struct
 {
+	/* general repmgr options */
+	char		config_file[MAXPGPATH];
+	bool		verbose;
+	bool		terse;
+	bool		force;
+	char		pg_bindir[MAXLEN]; /* overrides setting in repmgr.conf */
 
+	/* logging parameters */
+	char		loglevel[MAXLEN];  /* overrides setting in repmgr.conf */
+	bool		log_to_file;
+
+	/* connection parameters */
 	char		dbname[MAXLEN];
 	char		host[MAXLEN];
 	char		username[MAXLEN];
-	char		dest_dir[MAXFILENAME];
+	char		dest_dir[MAXPGPATH];
-	char		config_file[MAXFILENAME];
 	char		remote_user[MAXLEN];
 	char		superuser[MAXLEN];
+	char		masterport[MAXLEN];
+	bool		conninfo_provided;
+	bool		connection_param_provided;
+	bool		host_param_provided;
+
+	/* standby clone parameters */
+	bool		wal_keep_segments_used;
 	char		wal_keep_segments[MAXLEN];
-	bool		verbose;
-	bool		force;
-	bool		wait_for_master;
 	bool		ignore_rsync_warn;
-	bool		initdb_no_pwprompt;
 	bool		rsync_only;
 	bool		fast_checkpoint;
-	bool		ignore_external_config_files;
+	bool		without_barman;
-	char		masterport[MAXLEN];
+	bool		no_upstream_connection;
-	char		localport[MAXLEN];
+	bool		no_conninfo_password;
-
+	bool		copy_external_config_files;
-	/* parameter used by CLUSTER CLEANUP */
+	int			copy_external_config_files_destination;
-	int			keep_history;
+	char		upstream_conninfo[MAXLEN];
-
+	char		replication_user[MAXLEN];
-	char		pg_bindir[MAXLEN];
 
 	char		recovery_min_apply_delay[MAXLEN];
+
+	/* standby register paarameters */
+	bool		wait_register_sync;
+	int			wait_register_sync_seconds;
+
+	/* witness create parameters */
+	bool		witness_pwprompt;
+
+	/* standby follow parameters */
+	bool		wait_for_master;
+
+	/* cluster {show|matrix|crosscheck} parameters */
+	bool		csv_mode;
+
+	/* cluster cleanup parameters */
+	int			keep_history;
+
+	/* standby switchover parameters */
+	char		remote_config_file[MAXLEN];
+	bool		pg_rewind_supplied;
+	char		pg_rewind[MAXPGPATH];
+	char		pg_ctl_mode[MAXLEN];
+
+	/* standby {archive_config | restore_config} parameters  */
+	char		config_archive_dir[MAXLEN];
+
+	/* {standby|witness} unregister parameters */
+	int			node;
+
 }	t_runtime_options;
 
-#define T_RUNTIME_OPTIONS_INITIALIZER { "", "", "", "", "", "", "", DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, false, false, false, false, false, "", "", 0, "", "" }
+#define T_RUNTIME_OPTIONS_INITIALIZER { \
+		/* general repmgr options */	\
+		"", false, false, false, "",	\
+		/* logging parameters */ \
+		"", false,                      \
+		/* connection parameters */		\
+		"", "", "", "", "", "", "", 	\
+		false, false, false,		    \
+		/* standby clone parameters */  \
+		false, DEFAULT_WAL_KEEP_SEGMENTS, false, false, false, false, false, false, \
+		false, CONFIG_FILE_SAMEPATH, "", "", "", \
+		/* standby register paarameters */ \
+	    false, 0,							 \
+		/* witness create parameters */ \
+		false,                          \
+		/* standby follow parameters */ \
+		false,                          \
+		/* cluster {show|matrix|crosscheck} parameters */ \
+		false,                          \
+		/* cluster cleanup parameters */ \
+		0,                              \
+		/* standby switchover parameters */ \
+		"", false, "", "fast",          \
+		/* standby {archive_config | restore_config} parameters  */ \
+		"",                             \
+		/* {standby|witness} unregister parameters */ \
+		UNKNOWN_NODE_ID }
 
-extern char		repmgr_schema[MAXLEN];
+struct BackupLabel
-
-typedef struct ErrorListCell
 {
-	struct ErrorListCell *next;
+	XLogRecPtr start_wal_location;
-	char			     *error_message;
+	char start_wal_file[MAXLEN];
-} ErrorListCell;
+	XLogRecPtr checkpoint_location;
+	char backup_from[MAXLEN];
+	char backup_method[MAXLEN];
+	char start_time[MAXLEN];
+	char label[MAXLEN];
+	XLogRecPtr min_failover_slot_lsn;
+};
 
-typedef struct ErrorList
+
+typedef struct
 {
-	ErrorListCell *head;
+	char		slot[MAXLEN];
-	ErrorListCell *tail;
+	char		xlog_method[MAXLEN];
-} ErrorList;
+} t_basebackup_options;
+
+#define T_BASEBACKUP_OPTIONS_INITIALIZER { "", "" }
+
+typedef struct
+{
+	int    size;
+	char **keywords;
+	char **values;
+} t_conninfo_param_list;
+
+typedef struct
+{
+	char filepath[MAXPGPATH];
+	char filename[MAXPGPATH];
+	bool in_data_directory;
+} t_configfile_info;
+
+
+typedef struct
+{
+	int    size;
+	int    entries;
+	t_configfile_info **files;
+} t_configfile_list;
+
+#define T_CONFIGFILE_LIST_INITIALIZER { 0, 0, NULL }
+
+
+typedef struct
+{
+	int node_id;
+	int node_status;
+} t_node_status_rec;
+
+typedef struct
+{
+	int node_id;
+	char node_name[MAXLEN];
+	t_node_status_rec **node_status_list;
+} t_node_matrix_rec;
+
+typedef struct
+{
+	int node_id;
+	char node_name[MAXLEN];
+	t_node_matrix_rec **matrix_list_rec;
+} t_node_status_cube;
+
+
 
 #endif

repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  */
 
@@ -59,3 +59,12 @@ WHERE (standby_node, last_monitor_time) IN (SELECT standby_node, MAX(last_monito
 ALTER VIEW repl_status OWNER TO repmgr;
 
 CREATE INDEX idx_repl_status_sort ON repl_monitor(last_monitor_time, standby_node);
+
+/*
+ * This view shows the list of nodes with the information of which one is the upstream
+ * in each case (when appliable)
+ */
+CREATE VIEW repl_show_nodes AS
+SELECT rn.id, rn.conninfo, rn.type, rn.name, rn.cluster,
+	rn.priority, rn.active, sq.name AS upstream_node_name
+FROM repl_nodes as rn LEFT JOIN repl_nodes AS sq ON sq.id=rn.upstream_node_id;

sql/Makefile

@@ -1,7 +1,7 @@
 #
 # Makefile
 #
-# Copyright (c) 2ndQuadrant, 2010-2015
+# Copyright (c) 2ndQuadrant, 2010-2016
 #
 
 MODULE_big = repmgr_funcs

sql/repmgr2_repmgr3.sql

@@ -63,6 +63,15 @@ UPDATE repl_nodes SET type = 'master' WHERE id = $master_id;
 
 -- UPDATE repl_nodes SET active = FALSE WHERE id IN (...);
 
+/* There's also an event table which we need to create */
+CREATE TABLE repl_events (
+  node_id          INTEGER NOT NULL,
+  event            TEXT NOT NULL,
+  successful       BOOLEAN NOT NULL DEFAULT TRUE,
+  event_timestamp  TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
+  details          TEXT NULL
+);
+
 /* When you're sure of your changes, commit them */
 
 -- COMMIT;

sql/repmgr3.0_repmgr3.1.sql

@@ -0,0 +1,35 @@
+/*
+ * Update a repmgr 3.0 installation to repmgr 3.1
+ * ----------------------------------------------
+ *
+ * The new repmgr package should be installed first. Then
+ * carry out these steps:
+ *
+ *   1. (If repmgrd is used) stop any running repmgrd instances
+ *   2. On the master node, execute the SQL statements listed below
+ *   3. (If repmgrd is used) restart repmgrd
+ */
+
+/*
+ * If your repmgr installation is not included in your repmgr
+ * user's search path, please set the search path to the name
+ * of the repmgr schema to ensure objects are installed in
+ * the correct location.
+ *
+ * The repmgr schema is  "repmgr_" + the cluster name defined in
+ * 'repmgr.conf'.
+ */
+
+-- SET search_path TO 'name_of_repmgr_schema';
+
+BEGIN;
+
+-- New view "repl_show_nodes" which also displays the server's
+-- upstream node
+
+CREATE VIEW repl_show_nodes AS
+SELECT rn.id, rn.conninfo, rn.type, rn.name, rn.cluster,
+	rn.priority, rn.active, sq.name AS upstream_node_name
+FROM repl_nodes as rn LEFT JOIN repl_nodes AS sq ON sq.id=rn.upstream_node_id;
+
+COMMIT;

sql/repmgr3.1.1_repmgr3.1.2.sql

@@ -0,0 +1,32 @@
+/*
+ * Update a repmgr 3.1.1 installation to repmgr 3.1.2
+ * --------------------------------------------------
+ *
+ * This update is only required if repmgrd is being used in conjunction
+ * with a witness server.
+ *
+ * The new repmgr package should be installed first. Then
+ * carry out these steps:
+ *
+ *   1. (If repmgrd is used) stop any running repmgrd instances
+ *   2. On the master node, execute the SQL statement listed below
+ *   3. (If repmgrd is used) restart repmgrd
+ */
+
+/*
+ * If your repmgr installation is not included in your repmgr
+ * user's search path, please set the search path to the name
+ * of the repmgr schema to ensure objects are installed in
+ * the correct location.
+ *
+ * The repmgr schema is  "repmgr_" + the cluster name defined in
+ * 'repmgr.conf'.
+ */
+
+-- SET search_path TO 'name_of_repmgr_schema';
+
+BEGIN;
+
+ALTER TABLE repl_nodes DROP CONSTRAINT repl_nodes_upstream_node_id_fkey,
+      ADD CONSTRAINT repl_nodes_upstream_node_id_fkey FOREIGN KEY (upstream_node_id) REFERENCES repl_nodes(id) DEFERRABLE;
+COMMIT;

sql/repmgr_funcs.c

@@ -83,7 +83,12 @@ _PG_init(void)
 	 * resources in repmgr_shmem_startup().
 	 */
 	RequestAddinShmemSpace(repmgr_memsize());
+
+#if (PG_VERSION_NUM >= 90600)
+	RequestNamedLWLockTranche("repmgr", 1);
+#else
 	RequestAddinLWLocks(1);
+#endif
 
 	/*
 	 * Install hooks.
@@ -128,7 +133,11 @@ repmgr_shmem_startup(void)
 	if (!found)
 	{
 		/* First time through ... */
+#if (PG_VERSION_NUM >= 90600)
+		shared_state->lock = &(GetNamedLWLockTranche("repmgr"))->lock;
+#else
 		shared_state->lock = LWLockAssign();
+#endif
 		snprintf(shared_state->location,
 				 sizeof(shared_state->location), "%X/%X", 0, 0);
 	}

sql/repmgr_funcs.sql.in

@@ -1,6 +1,6 @@
 /*
  * repmgr_function.sql
- * Copyright (c) 2ndQuadrant, 2010-2015
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  */
 

sql/uninstall_repmgr_funcs.sql

@@ -1,6 +1,6 @@
 /*
  * uninstall_repmgr_funcs.sql
- * Copyright (c) 2ndQuadrant, 2010-2015
+ * Copyright (c) 2ndQuadrant, 2010-2016
  *
  */
 

strutil.c

@@ -1,7 +1,7 @@
 /*
  * strutil.c
  *
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * 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
@@ -87,3 +87,21 @@ maxlen_snprintf(char *str, const char *format,...)
 
 	return retval;
 }
+
+
+/*
+ * Escape a string for use as a parameter in recovery.conf
+ * Caller must free returned value
+ */
+char *
+escape_recovery_conf_value(const char *src)
+{
+	char	   *result = escape_single_quotes_ascii(src);
+
+	if (!result)
+	{
+		fprintf(stderr, _("%s: out of memory\n"), progname());
+		exit(ERR_INTERNAL);
+	}
+	return result;
+}

strutil.h

@@ -1,6 +1,6 @@
 /*
  * strutil.h
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  *
  * This program is free software: you can redistribute it and/or modify
@@ -22,14 +22,20 @@
 #define _STRUTIL_H_
 
 #include <stdlib.h>
+#include "pqexpbuffer.h"
 #include "errcode.h"
 
+
 #define QUERY_STR_LEN	8192
 #define MAXLEN			1024
 #define MAXLINELENGTH	4096
 #define MAXVERSIONSTR	16
 #define MAXCONNINFO		1024
 
+/* Why? http://stackoverflow.com/a/5459929/398670 */
+#define STR(x) CppAsString(x)
+
+#define MAXLEN_STR STR(MAXLEN)
 
 extern int
 xsnprintf(char *str, size_t size, const char *format,...)
@@ -43,4 +49,6 @@ extern int
 maxlen_snprintf(char *str, const char *format,...)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
 
+extern char *
+escape_recovery_conf_value(const char *src);
 #endif   /* _STRUTIL_H_ */

uninstall_repmgr.sql

@@ -1,7 +1,7 @@
 /*
  * uninstall_repmgr.sql
  *
- * Copyright (C) 2ndQuadrant, 2010-2015
+ * Copyright (C) 2ndQuadrant, 2010-2016
  *
  */
 

version.h

@@ -1,6 +1,6 @@
 #ifndef _VERSION_H_
 #define _VERSION_H_
 
-#define REPMGR_VERSION "3.0dev"
+#define REPMGR_VERSION "3.3"
 
 #endif