[CF 52/4770] v79 - Introduce XID age and inactive timeout based replication slot invalidation

This commit was automatically generated by a robot at cfbot.cputube.org.
It is based on patches submitted to the PostgreSQL mailing lists and
registered in the PostgreSQL Commitfest application.

This branch will be overwritten each time a new patch version is posted to
the email thread, and also periodically to check for bitrot caused by changes
on the master branch.

Commitfest entry: https://commitfest.postgresql.org/52/4770
Patch(es): https://www.postgresql.org/message-id/CABdArM7v0N0Kz1x0HjnuJZgDC8e=ZGgfCgSywsm4imgmpWghDA@mail.gmail.com
Author(s):

Author: Commitfest Bot

doc/src/sgml/config.sgml

@@ -4429,6 +4429,46 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"'  # Windows
        </listitem>
       </varlistentry>
 
+     <varlistentry id="guc-idle-replication-slot-timeout" xreflabel="idle_replication_slot_timeout">
+      <term><varname>idle_replication_slot_timeout</varname> (<type>integer</type>)
+      <indexterm>
+       <primary><varname>idle_replication_slot_timeout</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        Invalidate replication slots that have remained idle longer than this
+        duration. If this value is specified without units, it is taken as
+        minutes. A value of zero (the default) disables the idle timeout
+        invalidation mechanism. This parameter can only be set in the
+        <filename>postgresql.conf</filename> file or on the server command
+        line.
+       </para>
+
+       <para>
+        Slot invalidation due to idle timeout occurs during checkpoint.
+        Because checkpoints happen at <varname>checkpoint_timeout</varname>
+        intervals, there can be some lag between when the
+        <varname>idle_replication_slot_timeout</varname> was exceeded and when
+        the slot invalidation is triggered at the next checkpoint.
+        To avoid such lags, users can force a checkpoint to promptly invalidate
+        inactive slots. The duration of slot inactivity is calculated using the
+        slot's <link linkend="view-pg-replication-slots">pg_replication_slots</link>.<structfield>inactive_since</structfield>
+        value.
+       </para>
+
+       <para>
+        Note that the idle timeout invalidation mechanism is not applicable
+        for slots that do not reserve WAL or for slots on the standby server
+        that are being synced from the primary server (i.e., standby slots
+        having <link linkend="view-pg-replication-slots">pg_replication_slots</link>.<structfield>synced</structfield>
+        value <literal>true</literal>). Synced slots are always considered to
+        be inactive because they don't perform logical decoding to produce
+        changes.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-wal-sender-timeout" xreflabel="wal_sender_timeout">
       <term><varname>wal_sender_timeout</varname> (<type>integer</type>)
       <indexterm>

doc/src/sgml/logical-replication.sgml

@@ -2390,6 +2390,11 @@ CONTEXT:  processing remote data for replication origin "pg_16395" during "INSER
     plus some reserve for table synchronization.
    </para>
 
+   <para>
+    Logical replication slots are also affected by
+    <link linkend="guc-idle-replication-slot-timeout"><varname>idle_replication_slot_timeout</varname></link>.
+   </para>
+
    <para>
     <link linkend="guc-max-wal-senders"><varname>max_wal_senders</varname></link>
     should be set to at least the same as

doc/src/sgml/system-views.sgml

@@ -2619,6 +2619,13 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx
           perform logical decoding.  It is set only for logical slots.
          </para>
         </listitem>
+        <listitem>
+         <para>
+          <literal>idle_timeout</literal> means that the slot has remained
+          idle longer than the configured
+          <xref linkend="guc-idle-replication-slot-timeout"/> duration.
+         </para>
+        </listitem>
        </itemizedlist>
       </para></entry>
      </row>

src/backend/access/transam/xlog.c

@@ -7337,7 +7337,7 @@ CreateCheckPoint(int flags)
 	 */
 	XLByteToSeg(RedoRecPtr, _logSegNo, wal_segment_size);
 	KeepLogSeg(recptr, &_logSegNo);
-	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED,
+	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED | RS_INVAL_IDLE_TIMEOUT,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{
@@ -7792,7 +7792,7 @@ CreateRestartPoint(int flags)
 	replayPtr = GetXLogReplayRecPtr(&replayTLI);
 	endptr = (receivePtr < replayPtr) ? replayPtr : receivePtr;
 	KeepLogSeg(endptr, &_logSegNo);
-	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED,
+	if (InvalidateObsoleteReplicationSlots(RS_INVAL_WAL_REMOVED | RS_INVAL_IDLE_TIMEOUT,
 										   _logSegNo, InvalidOid,
 										   InvalidTransactionId))
 	{