mirror of
https://github.com/EnterpriseDB/repmgr.git
synced 2026-03-22 22:56:29 +00:00
doc: update repmgrd configuration documentation
This commit is contained in:
Ian Barwick
@@ -5,7 +5,7 @@
|
||||
<secondary>configuration</secondary>
|
||||
</indexterm>
|
||||
|
||||
<title>repmgrd configuration</title>
|
||||
<title>repmgrd setup and configuration</title>
|
||||
|
||||
<para>
|
||||
<application>repmgrd</application> is a daemon which runs on each PostgreSQL node,
|
||||
@@ -20,7 +20,7 @@
|
||||
</para>
|
||||
|
||||
<sect1 id="repmgrd-basic-configuration">
|
||||
<title>repmgrd basic configuration</title>
|
||||
<title>repmgrd configuration</title>
|
||||
|
||||
<para>
|
||||
To use <application>repmgrd</application>, its associated function library <emphasis>must</emphasis> be
|
||||
@@ -34,6 +34,112 @@
|
||||
the <ulink url="https://www.postgresql.org/docs/current/runtime-config-client.html#GUC-SHARED-PRELOAD-LIBRARIES">PostgreSQL documentation</ulink>.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
The following configuraton options apply to <application>repmgrd</application> in all circumstances:
|
||||
</para>
|
||||
<variablelist>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>monitor_interval_secs</primary>
|
||||
</indexterm>
|
||||
<term><option>monitor_interval_secs</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
The interval (in seconds, default: <literal>2</literal>) to check the availability of the upstream node.
|
||||
</para>
|
||||
</listitem>
|
||||
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>connection_check_type</primary>
|
||||
</indexterm>
|
||||
<term><option>connection_check_type</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
The option <option>connection_check_type</option> is used to select the method
|
||||
<application>repmgrd</application> uses to determine whether the upstream node is available.
|
||||
</para>
|
||||
<para>
|
||||
Possible values are:
|
||||
<itemizedlist spacing="compact" mark="bullet">
|
||||
<listitem>
|
||||
<simpara>
|
||||
<literal>ping</literal> (default) - uses <command>PQping()</command> to
|
||||
determine server availability
|
||||
</simpara>
|
||||
</listitem>
|
||||
<listitem>
|
||||
<simpara>
|
||||
<literal>connection</literal> - determines server availability
|
||||
by executing an SQL statement on the node via the existing connection
|
||||
</simpara>
|
||||
</listitem>
|
||||
</itemizedlist>
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry>
|
||||
<indexterm>
|
||||
<primary>reconnect_attempts</primary>
|
||||
</indexterm>
|
||||
<term><option>reconnect_attempts</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
The number of attempts (default: <literal>6</literal>) will be made to reconnect to an unreachable
|
||||
upstream node before initiating a failover.
|
||||
</para>
|
||||
<para>
|
||||
There will be an interval of <option>reconnect_interval</option> seconds between each reconnection
|
||||
attempt.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
<varlistentry>
|
||||
<indexterm>
|
||||
<primary>reconnect_interval</primary>
|
||||
</indexterm>
|
||||
<term><option>reconnect_interval</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
Interval (in seconds, default: <literal>10</literal>) between attempts to reconnect to an unreachable
|
||||
upstream node.
|
||||
</para>
|
||||
<para>
|
||||
The number of reconnection attempts is defined by the parameter <option>reconnect_attempts</option>.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
|
||||
|
||||
<varlistentry>
|
||||
<indexterm>
|
||||
<primary>degraded_monitoring_timeout</primary>
|
||||
</indexterm>
|
||||
<term><option>degraded_monitoring_timeout</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
Interval (in seconds) after which <application>repmgrd</application> will terminate if
|
||||
either of the servers (local node and or upstream node) being monitored is no longer available
|
||||
(<link linkend="repmgrd-degraded-monitoring">degraded monitoring mode</link>).
|
||||
</para>
|
||||
<para>
|
||||
<literal>-1</literal> (default) disables this timeout completely.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
</variablelist>
|
||||
|
||||
<para>
|
||||
See also <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename> for an annotated sample configuration file..
|
||||
</para>
|
||||
|
||||
<sect2 id="repmgrd-automatic-failover-configuration">
|
||||
<title>Required configuration for automatic failover</title>
|
||||
@@ -194,51 +300,24 @@
|
||||
<title>Optional configuration for automatic failover</title>
|
||||
|
||||
<para>
|
||||
The following configuraton options can be used to fine-tune automatic failove:
|
||||
The following configuraton options can be use to fine-tune automatic failover:
|
||||
</para>
|
||||
<variablelist>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>monitor_interval_secs</primary>
|
||||
</indexterm>
|
||||
<term><option>monitor_interval_secs</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
The interval (in seconds, default: <literal>2</literal>) to check the availability of the upstream node.
|
||||
</para>
|
||||
</listitem>
|
||||
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>connection_check_type</primary>
|
||||
<primary>priority</primary>
|
||||
</indexterm>
|
||||
<term><option>connection_check_type</option></term>
|
||||
<term><option>priority</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
The option <option>connection_check_type</option> is used to select the method
|
||||
<application>repmgrd</application> uses to determine whether the upstream node is available.
|
||||
Indicates a preferred priority (default: <literal>100</literal>) for promoting nodes;
|
||||
a value of zero prevents the node being promoted to primary.
|
||||
</para>
|
||||
<para>
|
||||
Possible values are:
|
||||
<itemizedlist spacing="compact" mark="bullet">
|
||||
<listitem>
|
||||
<simpara>
|
||||
<literal>ping</literal> (default) - uses <command>PQping()</command> to
|
||||
determine server availability
|
||||
</simpara>
|
||||
</listitem>
|
||||
<listitem>
|
||||
<simpara>
|
||||
<literal>connection</literal> - determines server availability
|
||||
by executing an SQL statement on the node via the existing connection
|
||||
</simpara>
|
||||
</listitem>
|
||||
</itemizedlist>
|
||||
Note that the priority setting is only applied if two or more nodes are
|
||||
determined as promotion candidates; in that case the node with the
|
||||
higher priority is selected.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
@@ -255,7 +334,7 @@
|
||||
</para>
|
||||
<note>
|
||||
<para>
|
||||
This optiom <emphasis>must</emphasis> be identically configurered
|
||||
This option <emphasis>must</emphasis> be identically configured
|
||||
on all nodes.
|
||||
</para>
|
||||
</note>
|
||||
@@ -275,6 +354,70 @@
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>primary_visibility_consensus</primary>
|
||||
</indexterm>
|
||||
<term><option>primary_visibility_consensus</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
If <literal>true</literal>, only continue with failover if no standbys have seen
|
||||
the primary node recently.
|
||||
</para>
|
||||
<note>
|
||||
<para>
|
||||
This option <emphasis>must</emphasis> be identically configured
|
||||
on all nodes.
|
||||
</para>
|
||||
</note>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
<varlistentry>
|
||||
|
||||
<indexterm>
|
||||
<primary>standby_disconnect_on_failover</primary>
|
||||
</indexterm>
|
||||
<term><option>standby_disconnect_on_failover</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
In a failover situation, disconnect the local node's WAL receiver.
|
||||
</para>
|
||||
<para>
|
||||
This option is available from PostgreSQL 9.5 and later.
|
||||
</para>
|
||||
<note>
|
||||
<para>
|
||||
This option <emphasis>must</emphasis> be identically configured
|
||||
on all nodes.
|
||||
</para>
|
||||
<para>
|
||||
Additionally the &repmgr; user <emphasis>must</emphasis> be a superuser
|
||||
for this option.
|
||||
</para>
|
||||
<para>
|
||||
<application>repmgrd</application> will refuse to start if this option is set
|
||||
but either of these prerequisites is not met.
|
||||
</para>
|
||||
</note>
|
||||
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
|
||||
|
||||
|
||||
</variablelist>
|
||||
|
||||
<para>
|
||||
The following options can be used to further fine-tune failover behaviour.
|
||||
In practice it's unlikely these will need to be changed from their default
|
||||
values, but are available as configuration options should the need arise.
|
||||
</para>
|
||||
<variablelist>
|
||||
|
||||
<varlistentry>
|
||||
<indexterm>
|
||||
<primary>election_rerun_interval</primary>
|
||||
@@ -288,12 +431,24 @@
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
||||
|
||||
<varlistentry>
|
||||
<indexterm>
|
||||
<primary>sibling_nodes_disconnect_timeout</primary>
|
||||
</indexterm>
|
||||
<term><option>sibling_nodes_disconnect_timeout</option></term>
|
||||
<listitem>
|
||||
<para>
|
||||
If <option>standby_disconnect_on_failover</option> is <literal>true</literal>, the
|
||||
maximum length of time (in seconds, default: <literal>30</literal>)
|
||||
to wait for other standbys to confirm they have disconnected their
|
||||
WAL receivers.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
</variablelist>
|
||||
|
||||
<para>
|
||||
See <filename><ulink url="https://raw.githubusercontent.com/2ndQuadrant/repmgr/master/repmgr.conf.sample">repmgr.conf.sample</ulink></filename>
|
||||
for further <application>repmgrd</application>-specific settings.
|
||||
</para>
|
||||
|
||||
|
||||
</sect2>
|
||||
|
||||
|
||||
@@ -4,6 +4,10 @@
|
||||
<secondary>degraded monitoring</secondary>
|
||||
</indexterm>
|
||||
|
||||
<indexterm>
|
||||
<primary>degraded monitoring</primary>
|
||||
</indexterm>
|
||||
|
||||
<title>"degraded monitoring" mode</title>
|
||||
<para>
|
||||
In certain circumstances, <application>repmgrd</application> is not able to fulfill its primary mission
|
||||
|
||||
@@ -281,7 +281,7 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
|
||||
# manual attention to reattach it to replication
|
||||
# (does not apply to BDR mode)
|
||||
|
||||
#priority=100 # indicate a preferred priority for promoting nodes;
|
||||
#priority=100 # indicates a preferred priority for promoting nodes;
|
||||
# a value of zero prevents the node being promoted to primary
|
||||
# (default: 100)
|
||||
|
||||
@@ -311,7 +311,7 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
|
||||
#monitoring_history=no # Whether to write monitoring data to the "montoring_history" table
|
||||
#monitor_interval_secs=2 # Interval (in seconds) at which to write monitoring data
|
||||
#degraded_monitoring_timeout=-1 # Interval (in seconds) after which repmgrd will terminate if the
|
||||
# server being monitored is no longer available. -1 (default)
|
||||
# server(s) being monitored are no longer available. -1 (default)
|
||||
# disables the timeout completely.
|
||||
#async_query_timeout=60 # Interval (in seconds) which repmgrd will wait before
|
||||
# cancelling an asynchronous query.
|
||||
@@ -323,12 +323,13 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
|
||||
# Note: there is normally no need to set this, particularly if
|
||||
# repmgr was installed from packages.
|
||||
#standby_disconnect_on_failover=false # If "true", in a failover situation wait for all standbys to
|
||||
# disconnect their WAL receivers before electing a new primary
|
||||
#sibling_nodes_disconnect_timeout=30 # If "standby_disconnect_on_failover", maximum length of time (in seconds)
|
||||
# to wait for other standbys to confirm they have disconnected their
|
||||
# disconnect their WAL receivers before electing a new primary
|
||||
# (PostgreSQL 9.5 and later only; repmgr user must be a superuser for this)
|
||||
#sibling_nodes_disconnect_timeout=30 # If "standby_disconnect_on_failover" is true, the maximum length of time
|
||||
# (in seconds) to wait for other standbys to confirm they have disconnected their
|
||||
# WAL receivers
|
||||
#primary_visibility_consensus=false # If "true", only continue with failover if no standbys have seen
|
||||
# the primary node recently
|
||||
# the primary node recently. *Must* be the same on all nodes.
|
||||
#failover_validation_command= # Script to execute for an external mechanism to validate the failover
|
||||
# decision made by repmgrd. One or both of the following parameter placeholders
|
||||
# should be provided, which will be replaced by repmgrd with the appropriate
|
||||
|
||||
Reference in New Issue
Block a user