v68-0002-Add-TAP-test-for-slot-invalidation-based-on-inac.patch

From 8a00d4d62454e9d3ae05d6aaf66a7de3860fa0e1 Mon Sep 17 00:00:00 2001
From: Nisha Moond <nisha.moond412@gmail.com>
Date: Thu, 30 Jan 2025 21:07:12 +0530
Subject: [PATCH v68 2/2] Add TAP test for slot invalidation based on inactive
 timeout.

This test uses injection points to bypass the time overhead caused by the
idle_replication_slot_timeout GUC, which has a minimum value of one minute.
---
 src/backend/replication/slot.c                |  34 ++++--
 src/test/recovery/meson.build                 |   1 +
 .../t/044_invalidate_inactive_slots.pl        | 103 ++++++++++++++++++
 3 files changed, 129 insertions(+), 9 deletions(-)
 create mode 100644 src/test/recovery/t/044_invalidate_inactive_slots.pl

diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 3eb1c09f7d..05a22f8b33 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -55,6 +55,7 @@
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/builtins.h"
+#include "utils/injection_point.h"
 #include "utils/guc_hooks.h"
 #include "utils/varlena.h"
 
@@ -1726,16 +1727,31 @@ InvalidatePossiblyObsoleteSlot(ReplicationSlotInvalidationCause cause,
 				case RS_INVAL_IDLE_TIMEOUT:
 					Assert(now > 0);
 
-					/*
-					 * Check if the slot needs to be invalidated due to
-					 * idle_replication_slot_timeout GUC.
-					 */
-					if (CanInvalidateIdleSlot(s) &&
-						TimestampDifferenceExceedsSeconds(s->inactive_since, now,
-														  idle_replication_slot_timeout_mins * SECS_PER_MINUTE))
+					if (CanInvalidateIdleSlot(s))
 					{
-						invalidation_cause = cause;
-						inactive_since = s->inactive_since;
+#ifdef USE_INJECTION_POINTS
+
+						/*
+						 * To test idle timeout slot invalidation, if the
+						 * slot-time-out-inval injection point is attached,
+						 * set inactive_since to a very old timestamp (1
+						 * microsecond since epoch) to immediately invalidate
+						 * the slot.
+						 */
+						if (IS_INJECTION_POINT_ATTACHED("slot-time-out-inval"))
+							s->inactive_since = 1;
+#endif
+
+						/*
+						 * Check if the slot needs to be invalidated due to
+						 * idle_replication_slot_timeout GUC.
+						 */
+						if (TimestampDifferenceExceedsSeconds(s->inactive_since, now,
+															  idle_replication_slot_timeout_mins * SECS_PER_MINUTE))
+						{
+							invalidation_cause = cause;
+							inactive_since = s->inactive_since;
+						}
 					}
 					break;
 				case RS_INVAL_NONE:
diff --git a/src/test/recovery/meson.build b/src/test/recovery/meson.build
index 0428704dbf..057bcde143 100644
--- a/src/test/recovery/meson.build
+++ b/src/test/recovery/meson.build
@@ -52,6 +52,7 @@ tests += {
       't/041_checkpoint_at_promote.pl',
       't/042_low_level_backup.pl',
       't/043_no_contrecord_switch.pl',
+      't/044_invalidate_inactive_slots.pl',
     ],
   },
 }
diff --git a/src/test/recovery/t/044_invalidate_inactive_slots.pl b/src/test/recovery/t/044_invalidate_inactive_slots.pl
new file mode 100644
index 0000000000..262e603eb5
--- /dev/null
+++ b/src/test/recovery/t/044_invalidate_inactive_slots.pl
@@ -0,0 +1,103 @@
+# Copyright (c) 2025, PostgreSQL Global Development Group
+
+# Test for replication slots invalidation
+use strict;
+use warnings FATAL => 'all';
+
+use PostgreSQL::Test::Utils;
+use PostgreSQL::Test::Cluster;
+use Test::More;
+
+if ($ENV{enable_injection_points} ne 'yes')
+{
+	plan skip_all => 'Injection points not supported by this build';
+}
+
+# Wait for slot to first become idle and then get invalidated
+sub wait_for_slot_invalidation
+{
+	my ($node, $slot, $offset) = @_;
+	my $node_name = $node->name;
+
+	# The slot's invalidation should be logged
+	$node->wait_for_log(qr/invalidating obsolete replication slot \"$slot\"/,
+		$offset);
+
+	# Check that the invalidation reason is 'idle_timeout'
+	$node->poll_query_until(
+		'postgres', qq[
+		SELECT COUNT(slot_name) = 1 FROM pg_replication_slots
+			WHERE slot_name = '$slot' AND
+			invalidation_reason = 'idle_timeout';
+	])
+	  or die
+	  "Timed out while waiting for invalidation reason of slot $slot to be set on node $node_name";
+
+	# Check that an invalidated slot cannot be acquired
+	my ($result, $stdout, $stderr);
+	($result, $stdout, $stderr) = $node->psql(
+		'postgres', qq[
+			SELECT pg_replication_slot_advance('$slot', '0/1');
+	]);
+	ok( $stderr =~ /can no longer access replication slot "$slot"/,
+		"detected error upon trying to acquire invalidated slot $slot on node $node_name"
+	  )
+	  or die
+	  "could not detect error upon trying to acquire invalidated slot $slot on node $node_name";
+}
+
+# ========================================================================
+# Testcase start
+#
+# Test invalidation of streaming standby slot and logical slot due to idle
+# timeout.
+
+# Initialize primary
+my $node = PostgreSQL::Test::Cluster->new('primary');
+$node->init(allows_streaming => 'logical');
+
+# Avoid unpredictability
+$node->append_conf(
+	'postgresql.conf', qq{
+checkpoint_timeout = 1h
+idle_replication_slot_timeout = 1min
+});
+$node->start;
+
+# Create both streaming standby and logical slot
+$node->safe_psql(
+	'postgres', qq[
+    SELECT pg_create_physical_replication_slot(slot_name := 'physical_slot', immediately_reserve := true);
+]);
+$node->psql('postgres',
+	q{SELECT pg_create_logical_replication_slot('logical_slot', 'test_decoding');}
+);
+
+my $logstart = -s $node->logfile;
+
+# Register an injection point on the primary to forcibly cause a slot timeout
+$node->safe_psql('postgres', 'CREATE EXTENSION injection_points;');
+
+# Check if the extension injection_points is available, as it may be
+# possible that this script is run with installcheck, where the module
+# would not be installed by default.
+if (!$node->check_extension('injection_points'))
+{
+	plan skip_all => 'Extension injection_points not installed';
+}
+
+$node->safe_psql('postgres',
+	"SELECT injection_points_attach('slot-time-out-inval', 'error');");
+
+# Run a checkpoint which will invalidate the slots
+$node->safe_psql('postgres', "CHECKPOINT");
+
+# Wait for slots to become inactive. Note that nobody has acquired the slot
+# yet, so it must get invalidated due to idle timeout.
+wait_for_slot_invalidation($node, 'physical_slot', $logstart);
+wait_for_slot_invalidation($node, 'logical_slot', $logstart);
+
+# Testcase end
+# =============================================================================
+
+done_testing();
-- 
2.34.1