From 88ab4ed8346103b61c37d471db40ea04f2837596 Mon Sep 17 00:00:00 2001 From: Bharath Rupireddy Date: Wed, 27 Mar 2024 15:28:40 +0000 Subject: [PATCH v29 2/2] Add inactive_timeout based replication slot invalidation. Till now, postgres has the ability to invalidate inactive replication slots based on the amount of WAL (set via max_slot_wal_keep_size GUC) that will be needed for the slots in case they become active. However, choosing a default value for max_slot_wal_keep_size is tricky. Because the amount of WAL a customer generates, and their allocated storage will vary greatly in production, making it difficult to pin down a one-size-fits-all value. It is often easy for developers to set a timeout of say 1 or 2 or 3 days at slot level, after which the inactive slots get dropped. To achieve the above, postgres introduces a GUC allowing users set inactive timeout and then a slot stays inactive for this much amount of time it invalidates the slot. The invalidation check happens at various locations to help being as latest as possible, these locations include the following: - Whenever the slot is acquired and the slot acquisition errors out if invalidated. - During checkpoint Note that this new invalidation mechanism won't kick-in for the slots that are currently being synced from the primary to the standby. Author: Bharath Rupireddy Reviewed-by: Bertrand Drouvot, Amit Kapila, Shveta Malik Discussion: https://www.postgresql.org/message-id/CALj2ACW4aUe-_uFQOjdWCEN-xXoLGhmvRFnL8SNw_TZ5nJe+aw@mail.gmail.com --- doc/src/sgml/config.sgml | 18 ++ doc/src/sgml/system-views.sgml | 7 + .../replication/logical/logicalfuncs.c | 2 +- src/backend/replication/logical/slotsync.c | 4 +- src/backend/replication/slot.c | 171 ++++++++++- src/backend/replication/slotfuncs.c | 2 +- src/backend/replication/walsender.c | 4 +- src/backend/utils/adt/pg_upgrade_support.c | 2 +- src/backend/utils/misc/guc_tables.c | 12 + src/backend/utils/misc/postgresql.conf.sample | 1 + src/include/replication/slot.h | 9 +- src/test/recovery/meson.build | 1 + src/test/recovery/t/050_invalidate_slots.pl | 278 ++++++++++++++++++ 13 files changed, 499 insertions(+), 12 deletions(-) create mode 100644 src/test/recovery/t/050_invalidate_slots.pl diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 65a6e6c408..db240c5b44 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -4544,6 +4544,24 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows + + replication_slot_inactive_timeout (integer) + + replication_slot_inactive_timeout configuration parameter + + + + + Invalidate replication slots that are inactive for longer than this + amount of time. If this value is specified without units, it is taken + as seconds. A value of zero (which is default) disables the timeout + mechanism. This parameter can only be set in the + postgresql.conf file or on the server + command line. + + + + track_commit_timestamp (boolean) diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml index c8d97ab375..5c05fd1c07 100644 --- a/doc/src/sgml/system-views.sgml +++ b/doc/src/sgml/system-views.sgml @@ -2582,6 +2582,13 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx perform logical decoding. It is set only for logical slots. + + + inactive_timeout means that the slot has been + inactive for the duration specified by + parameter. + + 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 9c95a4b062..71b6a254cf 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -321,7 +321,7 @@ 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(); } @@ -531,7 +531,7 @@ synchronize_one_slot(RemoteSlot *remote_slot, Oid remote_dbid) * InvalidatePossiblyObsoleteSlot() where it invalidates slot directly * if the slot is not acquired by other processes. */ - 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 7dbb44b7b0..0c5a601d87 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -108,10 +108,11 @@ const char *const SlotInvalidationCauses[] = { [RS_INVAL_WAL_REMOVED] = "wal_removed", [RS_INVAL_HORIZON] = "rows_removed", [RS_INVAL_WAL_LEVEL] = "wal_level_insufficient", + [RS_INVAL_INACTIVE_TIMEOUT] = "inactive_timeout", }; /* Maximum number of invalidation causes */ -#define RS_INVAL_MAX_CAUSES RS_INVAL_WAL_LEVEL +#define RS_INVAL_MAX_CAUSES RS_INVAL_INACTIVE_TIMEOUT StaticAssertDecl(lengthof(SlotInvalidationCauses) == (RS_INVAL_MAX_CAUSES + 1), "array length mismatch"); @@ -141,6 +142,7 @@ ReplicationSlot *MyReplicationSlot = NULL; /* GUC variables */ int max_replication_slots = 10; /* the maximum number of replication * slots */ +int replication_slot_inactive_timeout = 0; /* * This GUC lists streaming replication standby server slot names that @@ -159,6 +161,8 @@ static XLogRecPtr ss_oldest_flush_lsn = InvalidXLogRecPtr; static void ReplicationSlotShmemExit(int code, Datum arg); static void ReplicationSlotDropPtr(ReplicationSlot *slot); +static bool InvalidateSlotForInactiveTimeout(ReplicationSlot *slot, + bool need_locks); /* internal persistency functions */ static void RestoreSlotFromDisk(const char *name); @@ -536,9 +540,13 @@ 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. + * + * If check_for_invalidation is true, the slot is checked for invalidation + * based on replication_slot_inactive_timeout GUC and an error is raised after making the slot ours. */ void -ReplicationSlotAcquire(const char *name, bool nowait) +ReplicationSlotAcquire(const char *name, bool nowait, + bool check_for_invalidation) { ReplicationSlot *s; int active_pid; @@ -616,6 +624,41 @@ retry: /* We made this slot active, so it's ours now. */ MyReplicationSlot = s; + /* + * Check if the given slot can be invalidated based on its inactive + * timeout. If yes, persist the invalidated state to disk and then error + * out. We do this only after making the slot ours to avoid anyone else + * acquiring it while we check for its invalidation. + */ + if (check_for_invalidation) + { + /* The slot is ours by now */ + Assert(s->active_pid == MyProcPid); + + /* + * Well, the slot is not yet ours really unless we check for the + * invalidation below. + */ + s->active_pid = 0; + if (InvalidateReplicationSlotForInactiveTimeout(s, true, true)) + { + /* + * If the slot has been invalidated, recalculate the resource + * limits. + */ + ReplicationSlotsComputeRequiredXmin(false); + ReplicationSlotsComputeRequiredLSN(); + + /* Might need it for slot clean up on error, so restore it */ + s->active_pid = MyProcPid; + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("cannot acquire invalidated replication slot \"%s\"", + NameStr(MyReplicationSlot->data.name)))); + } + s->active_pid = MyProcPid; + } + /* * The call to pgstat_acquire_replslot() protects against stats for a * different slot, from before a restart or such, being present during @@ -790,7 +833,7 @@ 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 @@ -813,7 +856,7 @@ ReplicationSlotAlter(const char *name, bool failover) { Assert(MyReplicationSlot == NULL); - ReplicationSlotAcquire(name, false); + ReplicationSlotAcquire(name, false, true); if (SlotIsPhysical(MyReplicationSlot)) ereport(ERROR, @@ -1515,6 +1558,9 @@ ReportSlotInvalidation(ReplicationSlotInvalidationCause cause, case RS_INVAL_WAL_LEVEL: appendStringInfoString(&err_detail, _("Logical decoding on standby requires wal_level >= logical on the primary server.")); break; + case RS_INVAL_INACTIVE_TIMEOUT: + appendStringInfoString(&err_detail, _("The slot has been inactive for more than the time specified by replication_slot_inactive_timeout parameter.")); + break; case RS_INVAL_NONE: pg_unreachable(); } @@ -1628,6 +1674,10 @@ InvalidatePossiblyObsoleteSlot(ReplicationSlotInvalidationCause cause, if (SlotIsLogical(s)) invalidation_cause = cause; break; + case RS_INVAL_INACTIVE_TIMEOUT: + if (InvalidateReplicationSlotForInactiveTimeout(s, false, false)) + invalidation_cause = cause; + break; case RS_INVAL_NONE: pg_unreachable(); } @@ -1781,6 +1831,7 @@ InvalidatePossiblyObsoleteSlot(ReplicationSlotInvalidationCause cause, * - RS_INVAL_HORIZON: requires a snapshot <= the given horizon in the given * db; dboid may be InvalidOid for shared relations * - RS_INVAL_WAL_LEVEL: is logical + * - RS_INVAL_INACTIVE_TIMEOUT: inactive slot timeout occurs * * NB - this runs as part of checkpoint, so avoid raising errors if possible. */ @@ -1832,6 +1883,103 @@ restart: return invalidated; } +/* + * Invalidate given slot based on replication_slot_inactive_timeout GUC. + * + * Returns true if the slot has got invalidated. + * + * NB - this function also runs as part of checkpoint, so avoid raising errors + * if possible. + */ +bool +InvalidateReplicationSlotForInactiveTimeout(ReplicationSlot *slot, + bool need_locks, + bool persist_state) +{ + if (!InvalidateSlotForInactiveTimeout(slot, need_locks)) + return false; + + Assert(slot->active_pid == 0); + + SpinLockAcquire(&slot->mutex); + slot->data.invalidated = RS_INVAL_INACTIVE_TIMEOUT; + + /* Make sure the invalidated state persists across server restart */ + slot->just_dirtied = true; + slot->dirty = true; + SpinLockRelease(&slot->mutex); + + if (persist_state) + { + char path[MAXPGPATH]; + + sprintf(path, "pg_replslot/%s", NameStr(slot->data.name)); + SaveSlotToPath(slot, path, ERROR); + } + + ReportSlotInvalidation(RS_INVAL_INACTIVE_TIMEOUT, false, 0, + slot->data.name, InvalidXLogRecPtr, + InvalidXLogRecPtr, InvalidTransactionId); + + return true; +} + +/* + * Helper for InvalidateReplicationSlotForInactiveTimeout + */ +static bool +InvalidateSlotForInactiveTimeout(ReplicationSlot *slot, bool need_locks) +{ + ReplicationSlotInvalidationCause inavidation_cause = RS_INVAL_NONE; + + if (slot->inactive_since == 0 || + replication_slot_inactive_timeout == 0) + return false; + + /* + * Do not invalidate the slots which are currently being synced from the + * primary to the standby. + */ + if (RecoveryInProgress() && slot->data.synced) + return false; + + if (need_locks) + { + LWLockAcquire(ReplicationSlotControlLock, LW_SHARED); + SpinLockAcquire(&slot->mutex); + } + + Assert(LWLockHeldByMeInMode(ReplicationSlotControlLock, LW_SHARED)); + + /* + * Check if the slot needs to be invalidated due to + * replication_slot_inactive_timeout GUC. We do this with the spinlock + * held to avoid race conditions -- for example the restart_lsn could move + * forward, or the slot could be dropped. + */ + if (slot->inactive_since > 0 && + replication_slot_inactive_timeout > 0) + { + TimestampTz now; + + /* inactive_since is only tracked for inactive slots */ + Assert(slot->active_pid == 0); + + now = GetCurrentTimestamp(); + if (TimestampDifferenceExceeds(slot->inactive_since, now, + replication_slot_inactive_timeout * 1000)) + inavidation_cause = RS_INVAL_INACTIVE_TIMEOUT; + } + + if (need_locks) + { + SpinLockRelease(&slot->mutex); + LWLockRelease(ReplicationSlotControlLock); + } + + return (inavidation_cause == RS_INVAL_INACTIVE_TIMEOUT); +} + /* * Flush all replication slots to disk. * @@ -1844,6 +1992,7 @@ void CheckPointReplicationSlots(bool is_shutdown) { int i; + bool invalidated = false; elog(DEBUG1, "performing replication slot checkpoint"); @@ -1867,6 +2016,13 @@ CheckPointReplicationSlots(bool is_shutdown) /* save the slot to disk, locking is handled in SaveSlotToPath() */ sprintf(path, "pg_replslot/%s", NameStr(s->data.name)); + /* + * Here's an opportunity to invalidate inactive replication slots + * based on timeout, so let's do it. + */ + if (InvalidateReplicationSlotForInactiveTimeout(s, true, false)) + invalidated = true; + /* * Slot's data is not flushed each time the confirmed_flush LSN is * updated as that could lead to frequent writes. However, we decide @@ -1893,6 +2049,13 @@ CheckPointReplicationSlots(bool is_shutdown) SaveSlotToPath(s, path, LOG); } LWLockRelease(ReplicationSlotAllocationLock); + + /* If the slot has been invalidated, recalculate the resource limits */ + if (invalidated) + { + ReplicationSlotsComputeRequiredXmin(false); + ReplicationSlotsComputeRequiredLSN(); + } } /* diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index da57177c25..677c0bf0a2 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -651,7 +651,7 @@ 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 bc40c454de..96eeb8b7d2 100644 --- a/src/backend/replication/walsender.c +++ b/src/backend/replication/walsender.c @@ -846,7 +846,7 @@ 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), @@ -1459,7 +1459,7 @@ 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 c54b08fe18..82956d58d3 100644 --- a/src/backend/utils/adt/pg_upgrade_support.c +++ b/src/backend/utils/adt/pg_upgrade_support.c @@ -299,7 +299,7 @@ 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/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index 1e71e7db4a..c97a2d83a7 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -2954,6 +2954,18 @@ struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"replication_slot_inactive_timeout", PGC_SIGHUP, REPLICATION_SENDING, + gettext_noop("Sets the amount of time to wait before invalidating an " + "inactive replication slot."), + NULL, + GUC_UNIT_S + }, + &replication_slot_inactive_timeout, + 0, 0, INT_MAX, + NULL, NULL, NULL + }, + { {"commit_delay", PGC_SUSET, WAL_SETTINGS, gettext_noop("Sets the delay in microseconds between transaction commit and " diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 2244ee52f7..622cdf503d 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -334,6 +334,7 @@ #wal_sender_timeout = 60s # in milliseconds; 0 disables #track_commit_timestamp = off # collect timestamp of transaction commit # (change requires restart) +#replication_slot_inactive_timeout = 0 # in seconds; 0 disables # - Primary Server - diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h index 7b937d1a0c..cd98ab5112 100644 --- a/src/include/replication/slot.h +++ b/src/include/replication/slot.h @@ -53,6 +53,8 @@ typedef enum ReplicationSlotInvalidationCause RS_INVAL_HORIZON, /* wal_level insufficient for slot */ RS_INVAL_WAL_LEVEL, + /* inactive slot timeout has occurred */ + RS_INVAL_INACTIVE_TIMEOUT, } ReplicationSlotInvalidationCause; extern PGDLLIMPORT const char *const SlotInvalidationCauses[]; @@ -230,6 +232,7 @@ extern PGDLLIMPORT ReplicationSlot *MyReplicationSlot; /* GUCs */ extern PGDLLIMPORT int max_replication_slots; extern PGDLLIMPORT char *standby_slot_names; +extern PGDLLIMPORT int replication_slot_inactive_timeout; /* shmem initialization functions */ extern Size ReplicationSlotsShmemSize(void); @@ -245,7 +248,8 @@ extern void ReplicationSlotDrop(const char *name, bool nowait); extern void ReplicationSlotDropAcquired(void); extern void ReplicationSlotAlter(const char *name, bool failover); -extern void ReplicationSlotAcquire(const char *name, bool nowait); +extern void ReplicationSlotAcquire(const char *name, bool nowait, + bool check_for_invalidation); extern void ReplicationSlotRelease(void); extern void ReplicationSlotCleanup(void); extern void ReplicationSlotSave(void); @@ -264,6 +268,9 @@ extern bool InvalidateObsoleteReplicationSlots(ReplicationSlotInvalidationCause XLogSegNo oldestSegno, Oid dboid, TransactionId snapshotConflictHorizon); +extern bool InvalidateReplicationSlotForInactiveTimeout(ReplicationSlot *slot, + bool need_locks, + bool persist_state); extern ReplicationSlot *SearchNamedReplicationSlot(const char *name, bool need_lock); extern int ReplicationSlotIndex(ReplicationSlot *slot); extern bool ReplicationSlotName(int index, Name name); diff --git a/src/test/recovery/meson.build b/src/test/recovery/meson.build index b1eb77b1ec..708a2a3798 100644 --- a/src/test/recovery/meson.build +++ b/src/test/recovery/meson.build @@ -51,6 +51,7 @@ tests += { 't/040_standby_failover_slots_sync.pl', 't/041_checkpoint_at_promote.pl', 't/042_low_level_backup.pl', + 't/050_invalidate_slots.pl', ], }, } diff --git a/src/test/recovery/t/050_invalidate_slots.pl b/src/test/recovery/t/050_invalidate_slots.pl new file mode 100644 index 0000000000..cf233c5513 --- /dev/null +++ b/src/test/recovery/t/050_invalidate_slots.pl @@ -0,0 +1,278 @@ +# Copyright (c) 2024, 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; +use Time::HiRes qw(usleep); + +# ============================================================================= +# Testcase start: Invalidate streaming standby's slot as well as logical +# failover slot on primary due to inactive timeout GUC. Also, check the logical +# failover slot synced on to the standby doesn't invalidate the slot on its own, +# but gets the invalidated state from the remote slot on the primary. + +# Initialize primary node +my $primary = PostgreSQL::Test::Cluster->new('primary'); +$primary->init(allows_streaming => 'logical'); + +# Avoid checkpoint during the test, otherwise, the test can get unpredictable +$primary->append_conf( + 'postgresql.conf', q{ +checkpoint_timeout = 1h +autovacuum = off +}); +$primary->start; + +# Take backup +my $backup_name = 'my_backup'; +$primary->backup($backup_name); + +# Create a standby linking to the primary using the replication slot +my $standby1 = PostgreSQL::Test::Cluster->new('standby1'); +$standby1->init_from_backup($primary, $backup_name, has_streaming => 1); + +my $connstr_1 = $primary->connstr; +$standby1->append_conf( + 'postgresql.conf', qq( +hot_standby_feedback = on +primary_slot_name = 'sb1_slot' +primary_conninfo = '$connstr_1 dbname=postgres' +)); + +# Create sync slot on the primary +$primary->psql('postgres', + q{SELECT pg_create_logical_replication_slot('lsub1_sync_slot', 'test_decoding', false, false, true);} +); + +$primary->safe_psql( + 'postgres', qq[ + SELECT pg_create_physical_replication_slot(slot_name := 'sb1_slot'); +]); + +$standby1->start; + +my $standby1_logstart = -s $standby1->logfile; + +# Wait until standby has replayed enough data +$primary->wait_for_catchup($standby1); + +# Synchronize the primary server slots to the standby. +$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();"); + +# Confirm that the logical failover slot is created on the standby and is +# flagged as 'synced'. +is( $standby1->safe_psql( + 'postgres', + q{SELECT count(*) = 1 FROM pg_replication_slots + WHERE slot_name = 'lsub1_sync_slot' AND synced AND NOT temporary;} + ), + "t", + 'logical slot has synced as true on standby'); + +my $logstart = -s $primary->logfile; + +# Set timeout so that the next checkpoint will invalidate the inactive +# replication slot. +$primary->safe_psql( + 'postgres', qq[ + ALTER SYSTEM SET replication_slot_inactive_timeout TO '2s'; +]); +$primary->reload; + +# Wait for the logical failover slot to become inactive on the primary. Note +# that nobody has acquired that slot yet, so due to inactive timeout setting +# above it must get invalidated. +wait_for_slot_invalidation($primary, 'lsub1_sync_slot', $logstart); + +# Set timeout on the standby also to check the synced slots don't get +# invalidated due to timeout on the standby. +$standby1->safe_psql( + 'postgres', qq[ + ALTER SYSTEM SET replication_slot_inactive_timeout TO '2s'; +]); +$standby1->reload; + +# Now, sync the logical failover slot from the remote slot on the primary. +# Note that the remote slot has already been invalidated due to inactive +# timeout. Now, the standby must also see it as invalidated. +$standby1->safe_psql('postgres', "SELECT pg_sync_replication_slots();"); + +# Wait for the inactive replication slot to be invalidated. +$standby1->poll_query_until( + 'postgres', qq[ + SELECT COUNT(slot_name) = 1 FROM pg_replication_slots + WHERE slot_name = 'lsub1_sync_slot' AND + invalidation_reason = 'inactive_timeout'; +]) + or die + "Timed out while waiting for replication slot lsub1_sync_slot invalidation to be synced on standby"; + +# Synced slot mustn't get invalidated on the standby, it must sync invalidation +# from the primary. So, we must not see the slot's invalidation message in server +# log. +ok( !$standby1->log_contains( + "invalidating obsolete replication slot \"lsub1_sync_slot\"", + $standby1_logstart), + 'check that syned slot has not been invalidated on the standby'); + +# Stop standby to make the standby's replication slot on the primary inactive +$standby1->stop; + +# Wait for the standby's replication slot to become inactive +wait_for_slot_invalidation($primary, 'sb1_slot', $logstart); + +# Testcase end: Invalidate streaming standby's slot as well as logical failover +# slot on primary due to inactive timeout GUC. Also, check the logical failover +# slot synced on to the standby doesn't invalidate the slot on its own, but +# gets the invalidated state from the remote slot on the primary. +# ============================================================================= + +# ============================================================================= +# Testcase start: Invalidate logical subscriber's slot due to inactive timeout +# GUC. + +my $publisher = $primary; + +# Prepare for the next test +$publisher->safe_psql( + 'postgres', qq[ + ALTER SYSTEM SET replication_slot_inactive_timeout TO '0'; +]); +$publisher->reload; + +# Create subscriber node +my $subscriber = PostgreSQL::Test::Cluster->new('sub'); +$subscriber->init; +$subscriber->start; + +# Create tables +$publisher->safe_psql('postgres', "CREATE TABLE test_tbl (id int)"); +$subscriber->safe_psql('postgres', "CREATE TABLE test_tbl (id int)"); + +# Insert some data +$subscriber->safe_psql('postgres', + "INSERT INTO test_tbl VALUES (generate_series(1, 5));"); + +# Setup logical replication +my $publisher_connstr = $publisher->connstr . ' dbname=postgres'; +$publisher->safe_psql('postgres', "CREATE PUBLICATION pub FOR ALL TABLES"); +$publisher->safe_psql( + 'postgres', qq[ + SELECT pg_create_logical_replication_slot(slot_name := 'lsub1_slot', plugin := 'pgoutput'); +]); + +$subscriber->safe_psql('postgres', + "CREATE SUBSCRIPTION sub CONNECTION '$publisher_connstr' PUBLICATION pub WITH (slot_name = 'lsub1_slot', create_slot = false)" +); + +$subscriber->wait_for_subscription_sync($publisher, 'sub'); + +my $result = + $subscriber->safe_psql('postgres', "SELECT count(*) FROM test_tbl"); + +is($result, qq(5), "check initial copy was done"); + +# Prepare for the next test +$publisher->safe_psql( + 'postgres', qq[ + ALTER SYSTEM SET replication_slot_inactive_timeout TO '2s'; +]); +$publisher->reload; + +$logstart = -s $publisher->logfile; + +# Stop subscriber to make the replication slot on publisher inactive +$subscriber->stop; + +# Wait for the replication slot to become inactive and then invalidated due to +# timeout. +wait_for_slot_invalidation($publisher, 'lsub1_slot', $logstart); + +# Testcase end: Invalidate logical subscriber's slot due to inactive timeout +# GUC. +# ============================================================================= + +# ============================================================================= +# Start: Helper functions used for this test file + +sub wait_for_slot_invalidation +{ + my ($node, $slot_name, $offset) = @_; + my $name = $node->name; + + # Wait for the replication slot to become inactive + $node->poll_query_until( + 'postgres', qq[ + SELECT COUNT(slot_name) = 1 FROM pg_replication_slots + WHERE slot_name = '$slot_name' AND active = 'f'; + ]) + or die + "Timed out while waiting for replication slot to become inactive"; + + # Wait for the replication slot info to be updated + $node->poll_query_until( + 'postgres', qq[ + SELECT COUNT(slot_name) = 1 FROM pg_replication_slots + WHERE inactive_since IS NOT NULL + AND slot_name = '$slot_name' AND active = 'f'; + ]) + or die + "Timed out while waiting for info of replication slot $slot_name to be updated on node $name"; + + check_for_slot_invalidation_in_server_log($node, $slot_name, $offset); + + # Wait for the inactive replication slot to be invalidated. + $node->poll_query_until( + 'postgres', qq[ + SELECT COUNT(slot_name) = 1 FROM pg_replication_slots + WHERE slot_name = '$slot_name' AND + invalidation_reason = 'inactive_timeout'; + ]) + or die + "Timed out while waiting for inactive replication slot $slot_name to be invalidated on node $name"; + + # Check that the invalidated slot cannot be acquired + my ($result, $stdout, $stderr); + + ($result, $stdout, $stderr) = $primary->psql( + 'postgres', qq[ + SELECT pg_replication_slot_advance('$slot_name', '0/1'); + ]); + + ok( $stderr =~ /cannot acquire invalidated replication slot "$slot_name"/, + "detected error upon trying to acquire invalidated slot $slot_name on node $name" + ) + or die + "could not detect error upon trying to acquire invalidated slot $slot_name"; +} + +# Check for invalidation of slot in server log. +sub check_for_slot_invalidation_in_server_log +{ + my ($node, $slot_name, $offset) = @_; + my $invalidated = 0; + + for (my $i = 0; $i < 10 * $PostgreSQL::Test::Utils::timeout_default; $i++) + { + $node->safe_psql('postgres', "CHECKPOINT"); + if ($node->log_contains( + "invalidating obsolete replication slot \"$slot_name\"", + $offset)) + { + $invalidated = 1; + last; + } + usleep(100_000); + } + ok($invalidated, + "check that slot $slot_name invalidation has been logged"); +} + +# ============================================================================= +# End: Helper functions used for this test file + +done_testing(); -- 2.34.1