v49-0001-Add-error-handling-while-acquiring-a-replication.patch

From 795a0c837329ec376f1214c4278ca95a2378e8f3 Mon Sep 17 00:00:00 2001
From: Nisha Moond <nisha.moond412@gmail.com>
Date: Mon, 18 Nov 2024 16:13:26 +0530
Subject: [PATCH v49 1/2] Add error handling while acquiring a replication slot

In ReplicationSlotAcquire(), raise an error for invalid slots if caller
specify error_if_invalid=true.
---
 .../replication/logical/logicalfuncs.c        |  2 +-
 src/backend/replication/logical/slotsync.c    |  4 +-
 src/backend/replication/slot.c                | 48 +++++++++++++++++--
 src/backend/replication/slotfuncs.c           |  2 +-
 src/backend/replication/walsender.c           |  4 +-
 src/backend/utils/adt/pg_upgrade_support.c    |  2 +-
 src/include/replication/slot.h                |  3 +-
 src/test/recovery/t/019_replslot_limit.pl     |  2 +-
 8 files changed, 55 insertions(+), 12 deletions(-)

diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c
index b4dd5cce75..56fc1a45a9 100644
--- a/src/backend/replication/logical/logicalfuncs.c
+++ b/src/backend/replication/logical/logicalfuncs.c
@@ -197,7 +197,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin
 	else
 		end_of_wal = GetXLogReplayRecPtr(NULL);
 
-	ReplicationSlotAcquire(NameStr(*name), true);
+	ReplicationSlotAcquire(NameStr(*name), true, true);
 
 	PG_TRY();
 	{
diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c
index d62186a510..69a32422bf 100644
--- a/src/backend/replication/logical/slotsync.c
+++ b/src/backend/replication/logical/slotsync.c
@@ -446,7 +446,7 @@ drop_local_obsolete_slots(List *remote_slot_list)
 
 			if (synced_slot)
 			{
-				ReplicationSlotAcquire(NameStr(local_slot->data.name), true);
+				ReplicationSlotAcquire(NameStr(local_slot->data.name), true, false);
 				ReplicationSlotDropAcquired();
 			}
 
@@ -665,7 +665,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid)
 		 * pre-check to ensure that at least one of the slot properties is
 		 * changed before acquiring the slot.
 		 */
-		ReplicationSlotAcquire(remote_slot->name, true);
+		ReplicationSlotAcquire(remote_slot->name, true, false);
 
 		Assert(slot == MyReplicationSlot);
 
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 6828100cf1..0cbfd4fbaf 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -535,9 +535,12 @@ ReplicationSlotName(int index, Name name)
  *
  * An error is raised if nowait is true and the slot is currently in use. If
  * nowait is false, we sleep until the slot is released by the owning process.
+ *
+ * An error is raised if error_if_invalid is true and the slot has been
+ * invalidated previously.
  */
 void
-ReplicationSlotAcquire(const char *name, bool nowait)
+ReplicationSlotAcquire(const char *name, bool nowait, bool error_if_invalid)
 {
 	ReplicationSlot *s;
 	int			active_pid;
@@ -615,6 +618,45 @@ retry:
 	/* We made this slot active, so it's ours now. */
 	MyReplicationSlot = s;
 
+	/*
+	 * An error is raised if error_if_invalid is true and the slot has been
+	 * previously invalidated.
+	 */
+	if (error_if_invalid &&
+		s->data.invalidated != RS_INVAL_NONE)
+	{
+		StringInfoData err_detail;
+
+		initStringInfo(&err_detail);
+		appendStringInfo(&err_detail, _("This slot has been invalidated because "));
+
+		switch (s->data.invalidated)
+		{
+			case RS_INVAL_WAL_REMOVED:
+				appendStringInfo(&err_detail, _("the required WAL has been removed."));
+				break;
+
+			case RS_INVAL_HORIZON:
+				appendStringInfo(&err_detail, _("the required rows have been removed."));
+				break;
+
+			case RS_INVAL_WAL_LEVEL:
+				appendStringInfo(&err_detail, _("wal_level is insufficient for slot."));
+				break;
+
+			case RS_INVAL_NONE:
+				pg_unreachable();
+		}
+
+		ereport(ERROR,
+				errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				errmsg("can no longer get changes from replication slot \"%s\"",
+					   NameStr(s->data.name)),
+				errdetail_internal("%s", err_detail.data));
+
+		pfree(err_detail.data);
+	}
+
 	/*
 	 * The call to pgstat_acquire_replslot() protects against stats for a
 	 * different slot, from before a restart or such, being present during
@@ -785,7 +827,7 @@ ReplicationSlotDrop(const char *name, bool nowait)
 {
 	Assert(MyReplicationSlot == NULL);
 
-	ReplicationSlotAcquire(name, nowait);
+	ReplicationSlotAcquire(name, nowait, false);
 
 	/*
 	 * Do not allow users to drop the slots which are currently being synced
@@ -812,7 +854,7 @@ ReplicationSlotAlter(const char *name, const bool *failover,
 	Assert(MyReplicationSlot == NULL);
 	Assert(failover || two_phase);
 
-	ReplicationSlotAcquire(name, false);
+	ReplicationSlotAcquire(name, false, false);
 
 	if (SlotIsPhysical(MyReplicationSlot))
 		ereport(ERROR,
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index 488a161b3e..578cff64c8 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -536,7 +536,7 @@ pg_replication_slot_advance(PG_FUNCTION_ARGS)
 		moveto = Min(moveto, GetXLogReplayRecPtr(NULL));
 
 	/* Acquire the slot so we "own" it */
-	ReplicationSlotAcquire(NameStr(*slotname), true);
+	ReplicationSlotAcquire(NameStr(*slotname), true, true);
 
 	/* A slot whose restart_lsn has never been reserved cannot be advanced */
 	if (XLogRecPtrIsInvalid(MyReplicationSlot->data.restart_lsn))
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 371eef3ddd..b36ae90b2c 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -816,7 +816,7 @@ StartReplication(StartReplicationCmd *cmd)
 
 	if (cmd->slotname)
 	{
-		ReplicationSlotAcquire(cmd->slotname, true);
+		ReplicationSlotAcquire(cmd->slotname, true, true);
 		if (SlotIsLogical(MyReplicationSlot))
 			ereport(ERROR,
 					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
@@ -1434,7 +1434,7 @@ StartLogicalReplication(StartReplicationCmd *cmd)
 
 	Assert(!MyReplicationSlot);
 
-	ReplicationSlotAcquire(cmd->slotname, true);
+	ReplicationSlotAcquire(cmd->slotname, true, true);
 
 	/*
 	 * Force a disconnect, so that the decoding code doesn't need to care
diff --git a/src/backend/utils/adt/pg_upgrade_support.c b/src/backend/utils/adt/pg_upgrade_support.c
index 8a45b5827e..3322848e03 100644
--- a/src/backend/utils/adt/pg_upgrade_support.c
+++ b/src/backend/utils/adt/pg_upgrade_support.c
@@ -298,7 +298,7 @@ binary_upgrade_logical_slot_has_caught_up(PG_FUNCTION_ARGS)
 	slot_name = PG_GETARG_NAME(0);
 
 	/* Acquire the given slot */
-	ReplicationSlotAcquire(NameStr(*slot_name), true);
+	ReplicationSlotAcquire(NameStr(*slot_name), true, false);
 
 	Assert(SlotIsLogical(MyReplicationSlot));
 
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index 45582cf9d8..2c325fd942 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -249,7 +249,8 @@ extern void ReplicationSlotDropAcquired(void);
 extern void ReplicationSlotAlter(const char *name, const bool *failover,
 								 const bool *two_phase);
 
-extern void ReplicationSlotAcquire(const char *name, bool nowait);
+extern void ReplicationSlotAcquire(const char *name, bool nowait,
+								   bool error_if_invalid);
 extern void ReplicationSlotRelease(void);
 extern void ReplicationSlotCleanup(bool synced_only);
 extern void ReplicationSlotSave(void);
diff --git a/src/test/recovery/t/019_replslot_limit.pl b/src/test/recovery/t/019_replslot_limit.pl
index efb4ba3af1..333e040e7f 100644
--- a/src/test/recovery/t/019_replslot_limit.pl
+++ b/src/test/recovery/t/019_replslot_limit.pl
@@ -234,7 +234,7 @@ my $failed = 0;
 for (my $i = 0; $i < 10 * $PostgreSQL::Test::Utils::timeout_default; $i++)
 {
 	if ($node_standby->log_contains(
-			"requested WAL segment [0-9A-F]+ has already been removed",
+			"This slot has been invalidated because the required WAL has been removed",
 			$logstart))
 	{
 		$failed = 1;
-- 
2.34.1