Don't retreat slot's confirmed_flush LSN.

Amit Kapila · Amit Kapila · commit e323d9df002d · 2025-05-19T11:04:39.000+05:30
Prevent moving the confirmed_flush backwards, as this could lead to data duplication issues caused by replicating already replicated changes. This can happen when a client acknowledges an LSN it doesn't have to do anything for, and thus didn't store persistently. After a restart, the client can send the prior LSN that it stored persistently as an acknowledgement, but we need to ignore such an LSN to avoid retreating confirm_flush LSN. Diagnosed-by: Zhijie Hou <houzj.fnst@fujitsu.com> Author: shveta malik <shveta.malik@gmail.com> Reviewed-by: Amit Kapila <amit.kapila16@gmail.com> Reviewed-by: Dilip Kumar <dilipbalaut@gmail.com> Tested-by: Nisha Moond <nisha.moond412@gmail.com> Backpatch-through: 13 Discussion: https://postgr.es/m/CAJpy0uDZ29P=BYB1JDWMCh-6wXaNqMwG1u1mB4=10Ly0x7HhwQ@mail.gmail.com Discussion: https://postgr.es/m/OS0PR01MB57164AB5716AF2E477D53F6F9489A@OS0PR01MB5716.jpnprd01.prod.outlook.com
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
@@ -1037,7 +1037,19 @@ LogicalConfirmReceivedLocation(XLogRecPtr lsn)
 
 		SpinLockAcquire(&MyReplicationSlot->mutex);
 
-		MyReplicationSlot->data.confirmed_flush = lsn;
+		/*
+		 * Prevent moving the confirmed_flush backwards, as this could lead to
+		 * data duplication issues caused by replicating already replicated
+		 * changes.
+		 *
+		 * This can happen when a client acknowledges an LSN it doesn't have
+		 * to do anything for, and thus didn't store persistently. After a
+		 * restart, the client can send the prior LSN that it stored
+		 * persistently as an acknowledgement, but we need to ignore such an
+		 * LSN. See similar case handling in CreateDecodingContext.
+		 */
+		if (lsn > MyReplicationSlot->data.confirmed_flush)
+			MyReplicationSlot->data.confirmed_flush = lsn;
 
 		/* if we're past the location required for bumping xmin, do so */
 		if (MyReplicationSlot->candidate_xmin_lsn != InvalidXLogRecPtr &&
@@ -1102,7 +1114,14 @@ LogicalConfirmReceivedLocation(XLogRecPtr lsn)
 	else
 	{
 		SpinLockAcquire(&MyReplicationSlot->mutex);
-		MyReplicationSlot->data.confirmed_flush = lsn;
+
+		/*
+		 * Prevent moving the confirmed_flush backwards. See comments above
+		 * for the details.
+		 */
+		if (lsn > MyReplicationSlot->data.confirmed_flush)
+			MyReplicationSlot->data.confirmed_flush = lsn;
+
 		SpinLockRelease(&MyReplicationSlot->mutex);
 	}
 }
