From 0643dad3d343b9b9557704abef564881df9b4dc0 Mon Sep 17 00:00:00 2001 From: Nisha Moond Date: Thu, 30 Jan 2025 21:07:12 +0530 Subject: [PATCH v70 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 | 29 +++-- src/test/recovery/meson.build | 1 + .../t/044_invalidate_inactive_slots.pl | 110 ++++++++++++++++++ 3 files changed, 131 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 29749ce917..601e8063f3 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" @@ -1724,16 +1725,26 @@ 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; + /* + * Check if the slot needs to be invalidated due to + * idle_replication_slot_timeout GUC. + * + * To test idle timeout slot invalidation, if the + * "slot-timeout-inval" injection point is attached, + * immediately invalidate the slot. + */ + if ( + #ifdef USE_INJECTION_POINTS + IS_INJECTION_POINT_ATTACHED("slot-timeout-inval") || + #endif + 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..2392f24711 --- /dev/null +++ b/src/test/recovery/t/044_invalidate_inactive_slots.pl @@ -0,0 +1,110 @@ +# Copyright (c) 2025, PostgreSQL Global Development Group + +# Test for replication slots invalidation due to idle_timeout +use strict; +use warnings FATAL => 'all'; + +use PostgreSQL::Test::Utils; +use PostgreSQL::Test::Cluster; +use Test::More; + +# This test depends on injection point that forces slot invalidation +# due to idle_timeout. Enabling injections points requires +# --enable-injection-points with configure or +# -Dinjection_points=true with Meson. +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_name, $offset) = @_; + my $node_name = $node->name; + + # The slot's invalidation should be logged + $node->wait_for_log( + qr/invalidating obsolete replication slot \"$slot_name\"/, $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_name' AND + invalidation_reason = 'idle_timeout'; + ]) + or die + "Timed out while waiting for invalidation reason of slot $slot_name to be set on node $node_name"; +} + +# ======================================================================== +# Testcase start +# +# Test invalidation of streaming standby slot and logical slot due to idle +# timeout. + +# Initialize the node +my $node = PostgreSQL::Test::Cluster->new('node'); +$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->safe_psql('postgres', + q{SELECT pg_create_logical_replication_slot('logical_slot', 'test_decoding');} +); + +my $log_offset = -s $node->logfile; + +# Register an injection point on the node to forcibly cause a slot +# invalidation due to idle_timeout +$node->safe_psql('postgres', 'CREATE EXTENSION injection_points;'); + +# Check if the 'injection_points' extension 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-timeout-inval', 'error');"); + +# Idle timeout slot invalidation occurs during a checkpoint, so run a +# checkpoint to invalidate the slots. +$node->safe_psql('postgres', "CHECKPOINT"); + +# Wait for slots to become inactive. Note that since nobody has acquired the +# slot yet, then if it has been invalidated that can only be due to the idle +# timeout mechanism. +wait_for_slot_invalidation($node, 'physical_slot', $log_offset); +wait_for_slot_invalidation($node, 'logical_slot', $log_offset); + +# Check that the invalidated slot cannot be acquired +my $node_name = $node->name; +my ($result, $stdout, $stderr); +($result, $stdout, $stderr) = $node->psql( + 'postgres', qq[ + SELECT pg_replication_slot_advance('logical_slot', '0/1'); +]); +ok( $stderr =~ /can no longer access replication slot "logical_slot"/, + "detected error upon trying to acquire invalidated slot on node") + or die + "could not detect error upon trying to acquire invalidated slot \"logical_slot\" on node"; + +# Testcase end +# ============================================================================= + +done_testing(); -- 2.34.1