The cluster properties file v4

# cp /etc/edb/efm-4.8/efm.properties.in /etc/edb/efm-4.8/efm.properties

# chown efm:efm efm.properties

# The value for the password property should be the output from
# 'efm encrypt' -- do not include a cleartext password here. To
# prevent accidental sharing of passwords among clusters, the
# cluster name is incorporated into the encrypted password. If
# you change the cluster name (the name of this file), you must
# encrypt the password again with the new name.
# The db.port property must be the same for all nodes.
db.user=
db.password.encrypted=
db.port=
db.database=

# This property tells EFM which OS user owns the $PGDATA dir for
# the 'db.database'. By default, the owner is either 'postgres'
# for PostgreSQL or 'enterprisedb' for EDB Postgres Advanced
# Server. However, if you have configured your db to run as a
# different user, you will need to copy the /etc/sudoers.d/efm-XX
# conf file to grant the necessary permissions to your db owner.
#
# This username must have write permission to the
# 'db.data.dir' specified below.
db.service.owner=

# Specify the proper service name in order to use service commands
# rather than pg_ctl to start/stop/restart a database. For example, if
# this property is set, then 'service <name> restart' or 'systemctl
# restart <name>'
# (depending on OS version) will be used to restart the database rather
# than pg_ctl.
# This property is required if running the database as a service.
db.service.name=

# Specify the directory containing the pg_controldata/pg_ctl commands,
# for example:
# /usr/edb/as12/bin. Unless the db.service.name property is used, the
# pg_ctl command is used to start/stop/restart databases as needed
# after a failover or switchover. This property is required.
db.bin=

# For database version 12 and up, this is the directory where a
# standby.signal file will exist for a standby node. For previous
# versions, this is the location of the db recovery.conf file on
# the node.
# After a failover, the recovery.conf files on remaining standbys are
# changed to point to the new primary db (a copy of the original is made
# first). On a primary node, a recovery.conf file will be written during
# failover and promotion to ensure that the primary node can not be
# restarted as the primary database.
# This corresponds to database environment variable PGDATA and should
# be same as the output of query 'show data_directory;' on respective
# database.
db.data.dir=

# For database version 12 and up, this is the directory where a
# standby.signal file will exist for a standby node. For previous
# versions, this is the location of the db recovery.conf file on
# the node.
# After a failover, the recovery.conf files on remaining standbys are
# changed to point to the new primary db (a copy of the original is made
# first). On a primary node, a recovery.conf file will be written during
# failover and promotion to ensure that the primary node can not be
# restarted as the primary database.
# This corresponds to database environment variable PGDATA and should
# be same as the output of query 'show data_directory;' on respective
# database.
db.data.dir=

# Specify the location of database configuration files if they are
# not contained in the same location as the recovery.conf or
# standby.signal file. This is most likely the case for Debian
# installations. The location specified will be used as the -D value
# (the location of the data directory for the cluster) when calling
# pg_ctl to start or stop the database. If this property is blank,
# the db.data.dir location specified by the db.data.dir property will
# be used. This corresponds to the output of query 'show config_file;'
# on respective database.
db.config.dir=

# Use the jdbc.sslmode property to enable ssl for EFM
# connections. Setting this property to anything but 'disable'
# will force the agents to use 'ssl=true' for all JDBC database
# connections (to both local and remote databases).
# Valid values are:
#
# disable - Do not use ssl for connections.
# verify-ca - EFM will perform CA verification before allowing
# the certificate.
# require - Verification will not be performed on the server
# certificate.
jdbc.sslmode=disable

# Email address(es) for notifications. The value of this
# property must be the same across all agents. Multiple email
# addresses must be separated by space. If using a notification
# script instead, this property can be left blank.
user.email=

# Use the from.email property to specify the from email address that
# will be used for email notifications. Use the %h placeholder to
# represent the name of the node host (e.g. example@%h). The
# placeholder will be replaced with the name of the host as returned
# by the hostname command.
# Leave blank to use the default, efm@localhost.
from.email=

# Minimum severity level of notifications that will be sent by
# the agent. The minimum level also applies to the notification
# script (below). Valid values are INFO, WARNING, and SEVERE.
# A list of notifications is grouped by severity in the user's
# guide.
notification.level=INFO

# Text to add to the beginning of every notification. This could
# be used to help identify what the cluster is used for, the role
# of this node, etc. To use multiple lines, add a backslash \ to
# the end of a line of text. To include a newline use \n.
# Example:
# notification.text.prefix=Development cluster for Example dept.\n\
# Used by Dev and QA \
# See Example group for questions.
notification.text.prefix=

# Absolute path to script run for user notifications.
#
# This is an optional user-supplied script that can be used for
# notifications instead of email. This is required if not using
# email notifications. Either/both can be used. The script will
# be passed two parameters: the message subject and the message
# body.
script.notification=

# This property specifies the ip address and port that jgroups
# will bind to on this node. The value is of the form
# <ip>:<port>.
# Note that the port specified here is used for communicating
# with other nodes, and is not the same as the admin.port below,
# used only to communicate with the local agent to send control
# signals.
# For example, <provide_your_ip_address_here>:7800
bind.address=

# This is the ip address/hostname to be used for communication with all
# other Failover Manager agents. All traffic towards this address
# should be routed by the network to the bind.address of the node.
# The value is in the ip/hostname format only. This address will be
# used in scenarios where nodes are on different networks and broadcast
# an IP address other than the bind.address to the external world.
external.address=

# This property controls the port binding of the administration
# server which is used for some commands (ie cluster-status). The
# default is 7809; you can modify this value if the port is
# already in use.
admin.port=7809

# Specifies whether or not this is a witness node. Witness nodes
# do not have local databases running.
is.witness=

# These properties apply to the connection(s) EFM uses to monitor
# the local database. Every 'local.period' seconds, a database
# check is made in a background thread. If the main monitoring
# thread does not see that any checks were successful in
# 'local.timeout' seconds, then the main thread makes a final
# check with a timeout value specified by the
# 'local.timeout.final' value. All values are in seconds.
# Whether EFM uses single or multiple connections for database
# checks is controlled by the 'db.reuse.connection.count'
# property.
local.period=10
local.timeout=60
local.timeout.final=10

# Timeout for a call to check if a remote database is responsive.
# For example, this is how long a standby would wait for a
# DB ping request from itself and the witness to the primary DB
# before performing failover.
remote.timeout=10

# The total amount of time in seconds to wait before determining
# that a node has failed or been disconnected from this node.
#
# The value of this property must be the same across all agents.
node.timeout=50

- The `local.*` properties are for failure detection of an agent's local database.
- The `node.timeout` property is for failure detection of other nodes.
- The `remote.timeout` property limits how long agents wait for responses from other agents.

# Set to true to encrypt messages that are sent between agents.
# This property must be the same on all agents or else the agents
# will not be able to connect.
encrypt.agent.messages=false

# Whether or not the 'efm stop-cluster <cluster name>' command is enabled.
# Set to false to disable the command, in which case all Failover
# Manager agents must be stopped individually. Note that stopping each
# agent separately will change the .nodes files on remaining agents
# unless stable.nodes.file is also true. This property value must
# be the same on all agents if set. The default is true if not set.
enable.stop.cluster=true

# Shut down the database after a primary agent detects that it has
# been isolated from the majority of the efm cluster. If set to
# true, efm will stop the database before running the
# 'script.primary.isolated' script, if a script is specified.
stop.isolated.primary=true

# Attempt to shut down a failed primary database after EFM can no
# longer connect to it. This can be used for added safety in the
# case a failover is caused by a failure of the network on the
# primary node.
# If specified, a 'script.db.failure' script is run after this attempt.
stop.failed.primary=true

# Treat a primary agent shutdown as an agent failure. This can be set
# to true to treat a primary agent shutdown as a failure situation.
# Caution should be used when using this feature, as it could
# cause an unwanted promotion in the case of performing primary
# database maintenance.
# Please see the user's guide for more information.
primary.shutdown.as.failure=false

# Period in seconds between having the primary agent update promotable
# standbys with physical replication slot information so that
# the cluster will continue to use replication slots after a failover.
# Set to zero to turn off.
update.physical.slots.period=0

# This is the address of a well-known server that EFM can ping
# in an effort to determine network reachability issues. It
# might be the IP address of a nameserver within your corporate
# firewall or another server that *should* always be reachable
# via a 'ping' command from each of the EFM nodes.
#
# There are many reasons why this node might not be considered
# reachable: firewalls might be blocking the request, ICMP might
# be filtered out, etc.
#
# Do not use the IP address of any node in the EFM cluster
# (primary, standby, or witness) because this ping server is meant
# to provide an additional layer of information should the EFM
# nodes lose sight of each other.
#
# The installation default is Google's DNS server.
ping.server.ip=8.8.8.8

# This command will be used to test the reachability of certain
# nodes.
#
# Do not include an IP address or hostname on the end of
# this command - it will be added dynamically at runtime with the
# values contained in 'virtual.ip' and 'ping.server.ip'.
#
# Make sure this command returns reasonably quickly - test it
# from a shell command line first to make sure it works properly.
ping.server.command=/bin/ping -q -c3 -w5

# Have the first nostarts automatically add the addresses
# from its .nodes file to the allowed host list. This will make
# it faster to start the cluster when the initial set of hosts
# is already known.
auto.allow.hosts=false

# When set to true, EFM will not rewrite the .nodes file whenever
# new nodes join or leave the cluster. This can help starting a
# cluster in the cases where it is expected for member addresses
# to be mostly static, and combined with 'auto.allow.hosts' makes
# startup easier when learning failover manager.
stable.nodes.file=false

# This property controls how many times a database connection is
# reused before creating a new one. If set to zero, a new
# connection will be created every time an agent pings its local
# database.
db.reuse.connection.count=0

# Whether or not failover will happen automatically when the primary
# fails. Set to false if you want to receive the failover notifications
# but not have EFM actually perform the failover steps.
# The value of this property must be the same across all agents.
auto.failover=true

# After a standby is promoted, Failover Manager will attempt to
# update the remaining standbys to use the new primary. For database
# versions before 12, Failover Manager will back up recovery.conf.
# Then it will change the host parameter of the primary_conninfo entry
# in recovery.conf or postgresql.auto.conf, and restart the database.
# The restart command is contained in either the efm_db_functions or
# efm_root_functions file; default when not running db as an os
# service is: "pg_ctl restart -m fast -w -t <timeout> -D <directory>"
# where the timeout is the local.timeout property value and the
# directory is specified by db.data.dir. To turn off
# automatic reconfiguration, set this property to false.
auto.reconfigure=true

# A standby with this set to false will not be added to the
# failover priority list, and so will not be available for
# promotion. The property will be used whenever an agent starts
# as a standby or resumes as a standby after being idle. After
# startup/resume, the node can still be added or removed from the
# priority list with the 'efm set-priority' command. This
# property is required for all non-witness nodes.
promotable=true

# Use replay LSN value for tiebreaker when choosing a standby to
# promote before using failover priority. Set this property to true to
# consider replay location as more important than failover priority
# (as seen in cluster-status command) when choosing the "most ahead"
# standby to promote.
use.replay.tiebreaker=true

# Time in seconds for this standby to delay restarting to follow the
# primary after a promotion. This can be used to have standbys restart
# at different times to increase availability. Caution should be used
# when using this feature, as a delayed standby will not be following
# the new primary and care must be taken that the new primary retains
# enough WAL for the standby to follow it.
# Please see the user's guide for more information.
standby.restart.delay=0

# During a switchover, recovery settings are copied from a standby
# to the original primary. If the application.name property is set,
# Failover Manager will replace the application_name portion of the
# primary_conninfo entry with this property value before starting
# the original primary database as a standby. If this property is
# not set, Failover Manager will remove the parameter value
# from primary_conninfo.
application.name=

# If the restore_command on a standby restores directly from the
# primary node, use this property to have Failover Manager change
# the command when a new primary is promoted.
#
# Use the %h placeholder to represent the address of the new primary.
# During promotion it will be replaced with the address of the new
# primary.
#
# If not specified, failover manager will not change the
# restore_command value, if any, on standby nodes.
#
# Example:
# restore.command=scp <db service owner>@%h:/var/lib/edb/as12/data/archive/%f %p
restore.command=

# Reduce num_sync when the number of synchronous standbys drops below
# the value required by the primary database. If set to true, Failover
# Manager will reduce the number of standbys needed in the primary's
# synchronous_standby_names property and reload the primary
# configuration. Failover Manager will not reduce the number below 1,
# taking the primary out of synchronous replication, unless the
# reconfigure.sync.primary property is also set to true.
# To raise num_sync, see the reconfigure.num.sync.max property below.
reconfigure.num.sync=false

# If reconfigure.num.sync is set to true and this property is set,
# Failover Manager will check if num_sync can be raised when a standby
# is added to the cluster.
# Failover Manager will not raise the value above the maximum set here.
# If the primary database has been taken out of synchronous mode
# completely (see the reconfigure.sync.primary property), then Failover
# Manager will not reconfigure the primary database if standbys are
# added to the cluster.
reconfigure.num.sync.max=

# Take the primary database out of synchronous replication mode when
# needed. If set to true, Failover Manager will clear the
# synchronous_standby_names configuration parameter on the primary
# if the number of synchronous standbys drops below the required
# level for the primary to accept writes.
# If set to false, Failover Manager will detect the situation but
# will only send a notification if the standby count drops below the
# required level.
#
# CAUTION: TAKING THE PRIMARY DATABASE OUT OF SYNCHRONOUS MODE MEANS
# THERE MAY ONLY BE ONE COPY OF DATA. DO NOT MAKE THIS CHANGE UNLESS
# YOU ARE SURE THIS IS OK.
reconfigure.sync.primary=false

# Instead of setting specific standbys as being unavailable for
# promotion, this property can be used to set a minimum number
# of standbys that will not be promoted. Set to one, for
# example, promotion will not happen if it will drop the number
# of standbys below this value. This property must be the same on
# each node.
minimum.standbys=0

# Space-separated list of standby addresses that are high priority for
# promotion when this node is the primary. If set, when this node is
# promoted, addresses in this list will be added to the front of the
# standby priority list. If this list contains addresses that are not
# standbys at the time of promotion, they will not be added.
priority.standbys=

# Time in seconds between checks to see if a promoting database
# is out of recovery.
recovery.check.period=1

# Time in seconds to keep trying to connect to a database after a
# start or restart command returns successfully but the database
# is not ready to accept connections yet (a rare occurance). This
# applies to standby databases that are restarted when being
# reconfigured for a new primary, and to primary databases that
# are stopped astarts as standbys during a switchover.
# This retry mechanism is unrelated to the auto.resume.period
# parameter.
restart.connection.timeout=60

# Period in seconds for IDLE agents to try to resume monitoring
# after a database failure or when starting in IDLE mode. Set to
# 0 for agents to not try to resume (in which case the
# 'efm resume <cluster>' command is used after bringing a
# database back up).
auto.resume.period=0

# These properties specify the IP and prefix length that will be
# remapped during failover. If you do not use a VIP as part of
# your failover solution, leave the virtual.ip property blank to
# disable Failover Manager support for VIP processing (assigning,
# releasing, testing reachability, etc).
#
# If you specify a VIP, the interface and prefix are required.
#
# If you specify a host name, it will be resolved to an IP address
# when acquiring or releasing the VIP. If the host name resolves
# to more than one IP address, there is no way to predict which
# address Failover Manager will use.
#
# By default, the virtual.ip and virtual.ip.prefix values must be
# the same across all agents. If you set virtual.ip.single to
# false, you can specify unique values for virtual.ip and
# virtual.ip.prefix on each node.
#
# If you are using an IPv4 address, the virtual.ip.interface value
# should not contain a secondary virtual ip id (do not include
# ":1", etc).
virtual.ip=
virtual.ip.interface=
virtual.ip.prefix=
virtual.ip.single=true

# Whether to check if the VIP (when used) is still in use before
# promoting after a primary failure. Turning this off may allow
# the new primary to have the VIP even though another node is also
# broadcasting it. This should only be used in environments where
# it is known that the failed primary node will be isolated or
# shut down through other means.
check.vip.before.promotion=true

# A boolean property to enable Failover Manager managed Pgpool HA.
# If enabled, Failover Manager would natively update the joining
# and leaving status of database nodes to active pgpool instance.
# Failover manager expects properly configured and running pgpool
# instances on required nodes. It does not manage setup and
# configuration of pgpool on any node.
#
# By default the property is disabled.
pgpool.enable=false

# Configurations required for pgpool integration.
# 'pcp.user' - User that would be invoking PCP commands
# 'pcp.host' - Virtual IP that would be used by pgpool. Same as
# pgpool parameter 'delegate_IP'
# 'pcp.port' - The port on which pgpool listens for pcp commands.
# 'pcp.pass.file' - Absolute path of PCPPASSFILE.
# 'pgpool.bin' - Absolute path of pgpool bin directory

# These properties are required if 'pgpool.enable' is set to true.
pcp.user=
pcp.host=
pcp.port=
pcp.pass.file=
pgpool.bin=

# Absolute path to load balancer scripts
# The attach script is called when a node should be attached to
# the load balancer, for example after a promotion. The detach
# script is called when a node should be removed, for example
# when a database has failed or is about to be stopped. Use %h to
# represent the IP/hostname of the node that is being
# attached/detached. Use %t to represent the type of node being
# attached or detached: the letter m will be passed in for primary nodes
#and the letter s for standby nodes.
#
# Example:
# script.load.balancer.attach=/somepath/attachscript %h %t
script.load.balancer.attach=
script.load.balancer.detach=

# If set to true, Failover Manager will detach the node from load
# balancer if the primary agent fails but the database is still
# reachable. In most scenarios this is NOT the desired situation. In
# scenarios where the detach script should run with a failed primary
# agent, even when the primary database is still healthy this parameter
# should be set to true. If no value specified it defaults to true (for
# backwards compatibility).
# This is not applicable for standbys.
detach.on.agent.failure=

# absolute path to fencing script run during promotion
#
# This is an optional user-supplied script that will be run
# during failover on the standby database node. If left blank,
# no action will be taken. If specified, EFM will execute this
# script before promoting the standby.
#
# Parameters can be passed into this script for the failed primary
# and new primary node addresses. Use %p for new primary and %f
# for failed primary. On a node that has just been promoted, %p
# should be the same as the node's efm binding address.
#
# Example:
# script.fence=/somepath/myscript %p %f
#
# NOTE: FAILOVER WILL NOT OCCUR IF THIS SCRIPT RETURNS A NON-ZERO EXIT
# CODE.
script.fence=

# Absolute path to fencing script run after promotion
#
# This is an optional user-supplied script that will be run after
# failover on the standby node after it has been promoted and
# is no longer in recovery. The exit code from this script has
# no effect on failover manager, but will be included in a
# notification sent after the script executes.
#
# Parameters can be passed into this script for the failed primary
# and new primary node addresses. Use %p for new primary and %f
# for failed primary. On a node that has just been promoted, %p
# should be the same as the node's efm binding address.
#
# Example:
# script.post.promotion=/somepath/myscript %f %p
script.post.promotion=

# Absolute path to resume script
#
# This script is run before an IDLE agent resumes
# monitoring its local database.
script.resumed=

# Absolute path to script run after database failure
# This is an optional user-supplied script that will be run after
# an agent detects that its local database has failed.
script.db.failure=

# Absolute path to script run on isolated primary
# This is an optional user-supplied script that will be run after
# a primary agent detects that it has been isolated from the
# majority of the efm cluster.
script.primary.isolated=

# Absolute path to script invoked on non-promoting agent nodes
# before a promotion.
#
# This optional user-supplied script will be invoked on other
# agents when a node is about to promote its database. The exit
# code from this script has no effect on Failover Manager, but
# will be included in a notification sent after the script
# executes.
#
# Pass a parameter (%p) with the script to identify the new
# primary node address.
#
# Example:
# script.remote.pre.promotion=/path_name/script_name %p
script.remote.pre.promotion=

# Absolute path to script invoked on non-primary agent nodes
# after a promotion.
#
# This optional user-supplied script will be invoked on nodes
# (except the new primary) after a promotion occurs. The exit code
# from this script has no effect on Failover Manager, but will be
# included in a notification sent after the script executes.
#
# Pass a parameter (%p) with the script to identify the new
# primary node address.
#
# Example:
# script.remote.post.promotion=/path_name/script_name %p
script.remote.post.promotion=

# Absolute path to a custom monitoring script.
#
# Use script.custom.monitor to specify the location and name of
# an optional user-supplied script that will be invoked
# periodically to perform custom monitoring tasks. A non-zero
# exit value means that a check has failed; this will be treated
# as a database failure. On a primary node, script failure will
# cause a promotion. On a standby node script failure will
# generate a notification and the agent will become IDLE.
#
# The custom.monitor.\* properties are required if a custom
# monitoring script is specified:
#
# custom.monitor.interval is the time in seconds between executions
# of the script.
#
# custom.monitor.timeout is a timeout value in seconds for how
# long the script will be allowed to run. If script execution
# exceeds the specified time, the task will be stopped and a
# notification sent. Subsequent runs will continue.
#
# If custom.monitor.safe.mode is set to true, non-zero exit codes
# from the script will be reported but will not cause a promotion
# or be treated as a database failure. This allows testing of the
# script without affecting EFM.
#
script.custom.monitor=
custom.monitor.interval=
custom.monitor.timeout=
custom.monitor.safe.mode=

# Command to use in place of 'sudo' if desired when efm runs
# the efm_db_functions or efm_root_functions, or efm_address
# scripts.
# Sudo is used in the following ways by efm:
#
# sudo /usr/edb/efm-<version>/bin/efm_address <arguments>
# sudo /usr/edb/efm-<version>/bin/efm_root_functions <arguments>
# sudo -u <db service owner> /usr/edb/efm-<version>/bin/efm_db_functions <arguments>
#
# 'sudo' in the first two examples will be replaced by the value
# of the sudo.command property. 'sudo -u <db service owner>' will
# be replaced by the value of the sudo.user.command property.
# The '%u' field will be replaced with the db owner.
sudo.command=sudo
sudo.user.command=sudo -u %u

# Specify the directory of lock file on the node. Failover
# Manager creates a file named <cluster>.lock at this location to
# avoid starting multiple agents for same cluster. If the path
# does not exist, Failover Manager will attempt to create it. If
# not specified defaults to '/var/lock/efm-<version>'
lock.dir=

# Specify the directory of agent logs on the node. If the path
# does not exist, Failover Manager will attempt to create it. If
# not specified defaults to '/var/log/efm-<version>'. (To store
# Failover Manager startup logs in a custom location, modify the
# path in the service script to point to an existing, writable
# directory.)
# If using a custom log directory, you must configure
# logrotate separately. Use 'man logrotate' for more information.
log.dir=

# Syslog information. The syslog service must be listening on
# the port for the given protocol, which can be UDP or TCP.
# The facilities supported are LOCAL0 through LOCAL7.
syslog.host=localhost
syslog.port=514
syslog.protocol=UDP
syslog.facility=LOCAL1

# Which logging is enabled.
file.log.enabled=true
syslog.enabled=false

# Logging levels for JGroups and EFM.
# Valid values are: TRACE, DEBUG, INFO, WARN, ERROR
# Default value: INFO
# It is not necessary to increase these values unless debugging a
# specific issue. If nodes are not discovering each other at
# startup, increasing the jgroups level to DEBUG will show
# information about the TCP connection attempts that may help
# diagnose the connection failures.
# TRACE level logging should be used for diagnosing problems only.
# It is not supported for production use.
jgroups.loglevel=INFO
efm.loglevel=INFO

# Extra information that will be passed to the JVM when starting
# the agent.
jvm.options=-Xmx128m