From 007693f2a3ac2ac19affcb03ad43cdb36ccff5b5 Mon Sep 17 00:00:00 2001 From: Amit Kapila Date: Thu, 4 Jan 2024 08:21:51 +0530 Subject: [PATCH] Track conflict_reason in pg_replication_slots. This patch changes the existing 'conflicting' field to 'conflict_reason' in pg_replication_slots. This new field indicates the reason for the logical slot's conflict with recovery. It is always NULL for physical slots, as well as for logical slots which are not invalidated. The non-NULL values indicate that the slot is marked as invalidated. Possible values are: wal_removed = required WAL has been removed. rows_removed = required rows have been removed. wal_level_insufficient = the primary doesn't have a wal_level sufficient to perform logical decoding. The existing users of 'conflicting' column can get the same answer by using 'conflict_reason' IS NOT NULL. Author: Shveta Malik Reviewed-by: Amit Kapila, Bertrand Drouvot, Michael Paquier Discussion: https://postgr.es/m/ZYOE8IguqTbp-seF@paquier.xyz --- doc/src/sgml/system-views.sgml | 29 +++++++- src/backend/catalog/system_views.sql | 2 +- src/backend/replication/slotfuncs.c | 22 ++++-- src/bin/pg_upgrade/info.c | 4 +- src/include/catalog/catversion.h | 2 +- src/include/catalog/pg_proc.dat | 4 +- .../t/035_standby_logical_decoding.pl | 72 ++++++++++--------- src/test/regress/expected/rules.out | 4 +- 8 files changed, 90 insertions(+), 49 deletions(-) diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml index 0ef1745631..72d01fc624 100644 --- a/doc/src/sgml/system-views.sgml +++ b/doc/src/sgml/system-views.sgml @@ -2525,11 +2525,34 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx - conflicting bool + conflict_reason text - True if this logical slot conflicted with recovery (and so is now - invalidated). Always NULL for physical slots. + The reason for the logical slot's conflict with recovery. It is always + NULL for physical slots, as well as for logical slots which are not + invalidated. The non-NULL values indicate that the slot is marked + as invalidated. Possible values are: + + + + wal_removed means that the required WAL has been + removed. + + + + + rows_removed means that the required rows have + been removed. + + + + + wal_level_insufficient means that the + primary doesn't have a sufficient to + perform logical decoding. + + + diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 4899b5e0f0..e43e36f5ac 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1023,7 +1023,7 @@ CREATE VIEW pg_replication_slots AS L.wal_status, L.safe_wal_size, L.two_phase, - L.conflicting + L.conflict_reason FROM pg_get_replication_slots() AS L LEFT JOIN pg_database D ON (L.datoid = D.oid); diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c index 47e104782c..cad35dce7f 100644 --- a/src/backend/replication/slotfuncs.c +++ b/src/backend/replication/slotfuncs.c @@ -406,10 +406,24 @@ pg_get_replication_slots(PG_FUNCTION_ARGS) nulls[i++] = true; else { - if (slot_contents.data.invalidated != RS_INVAL_NONE) - values[i++] = BoolGetDatum(true); - else - values[i++] = BoolGetDatum(false); + switch (slot_contents.data.invalidated) + { + case RS_INVAL_NONE: + nulls[i++] = true; + break; + + case RS_INVAL_WAL_REMOVED: + values[i++] = CStringGetTextDatum("wal_removed"); + break; + + case RS_INVAL_HORIZON: + values[i++] = CStringGetTextDatum("rows_removed"); + break; + + case RS_INVAL_WAL_LEVEL: + values[i++] = CStringGetTextDatum("wal_level_insufficient"); + break; + } } Assert(i == PG_GET_REPLICATION_SLOTS_COLS); diff --git a/src/bin/pg_upgrade/info.c b/src/bin/pg_upgrade/info.c index c52501c8fb..190dd53a42 100644 --- a/src/bin/pg_upgrade/info.c +++ b/src/bin/pg_upgrade/info.c @@ -667,13 +667,13 @@ get_old_cluster_logical_slot_infos(DbInfo *dbinfo, bool live_check) * removed. */ res = executeQueryOrDie(conn, "SELECT slot_name, plugin, two_phase, " - "%s as caught_up, conflicting as invalid " + "%s as caught_up, conflict_reason IS NOT NULL as invalid " "FROM pg_catalog.pg_replication_slots " "WHERE slot_type = 'logical' AND " "database = current_database() AND " "temporary IS FALSE;", live_check ? "FALSE" : - "(CASE WHEN conflicting THEN FALSE " + "(CASE WHEN conflict_reason IS NOT NULL THEN FALSE " "ELSE (SELECT pg_catalog.binary_upgrade_logical_slot_has_caught_up(slot_name)) " "END)"); diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h index 6bbe0f1af1..686667a0f8 100644 --- a/src/include/catalog/catversion.h +++ b/src/include/catalog/catversion.h @@ -57,6 +57,6 @@ */ /* yyyymmddN */ -#define CATALOG_VERSION_NO 202401021 +#define CATALOG_VERSION_NO 202401041 #endif diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 14b1dfacab..7979392776 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11115,9 +11115,9 @@ proname => 'pg_get_replication_slots', prorows => '10', proisstrict => 'f', proretset => 't', provolatile => 's', prorettype => 'record', proargtypes => '', - proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,bool}', + proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text}', proargmodes => '{o,o,o,o,o,o,o,o,o,o,o,o,o,o,o}', - proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflicting}', + proargnames => '{slot_name,plugin,slot_type,datoid,temporary,active,active_pid,xmin,catalog_xmin,restart_lsn,confirmed_flush_lsn,wal_status,safe_wal_size,two_phase,conflict_reason}', prosrc => 'pg_get_replication_slots' }, { oid => '3786', descr => 'set up a logical replication slot', proname => 'pg_create_logical_replication_slot', provolatile => 'v', diff --git a/src/test/recovery/t/035_standby_logical_decoding.pl b/src/test/recovery/t/035_standby_logical_decoding.pl index 3231538418..8bc39a5f03 100644 --- a/src/test/recovery/t/035_standby_logical_decoding.pl +++ b/src/test/recovery/t/035_standby_logical_decoding.pl @@ -168,27 +168,25 @@ sub change_hot_standby_feedback_and_wait_for_xmins } } -# Check conflicting status in pg_replication_slots. -sub check_slots_conflicting_status +# Check conflict_reason in pg_replication_slots. +sub check_slots_conflict_reason { - my ($conflicting) = @_; + my ($slot_prefix, $reason) = @_; - if ($conflicting) - { - $res = $node_standby->safe_psql( - 'postgres', qq( - select bool_and(conflicting) from pg_replication_slots;)); + my $active_slot = $slot_prefix . 'activeslot'; + my $inactive_slot = $slot_prefix . 'inactiveslot'; - is($res, 't', "Logical slots are reported as conflicting"); - } - else - { - $res = $node_standby->safe_psql( - 'postgres', qq( - select bool_or(conflicting) from pg_replication_slots;)); + $res = $node_standby->safe_psql( + 'postgres', qq( + select conflict_reason from pg_replication_slots where slot_name = '$active_slot';)); - is($res, 'f', "Logical slots are reported as non conflicting"); - } + is($res, "$reason", "$active_slot conflict_reason is $reason"); + + $res = $node_standby->safe_psql( + 'postgres', qq( + select conflict_reason from pg_replication_slots where slot_name = '$inactive_slot';)); + + is($res, "$reason", "$inactive_slot conflict_reason is $reason"); } # Drop the slots, re-create them, change hot_standby_feedback, @@ -260,13 +258,13 @@ $node_primary->safe_psql('testdb', qq[SELECT * FROM pg_create_physical_replication_slot('$primary_slotname');] ); -# Check conflicting is NULL for physical slot +# Check conflict_reason is NULL for physical slot $res = $node_primary->safe_psql( 'postgres', qq[ - SELECT conflicting is null FROM pg_replication_slots where slot_name = '$primary_slotname';] + SELECT conflict_reason is null FROM pg_replication_slots where slot_name = '$primary_slotname';] ); -is($res, 't', "Physical slot reports conflicting as NULL"); +is($res, 't', "Physical slot reports conflict_reason as NULL"); my $backup_name = 'b1'; $node_primary->backup($backup_name); @@ -483,8 +481,8 @@ $node_primary->wait_for_replay_catchup($node_standby); # Check invalidation in the logfile and in pg_stat_database_conflicts check_for_invalidation('vacuum_full_', 1, 'with vacuum FULL on pg_class'); -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is 'rows_removed' in pg_replication_slots +check_slots_conflict_reason('vacuum_full_', 'rows_removed'); $handle = make_slot_active($node_standby, 'vacuum_full_', 0, \$stdout, \$stderr); @@ -502,8 +500,8 @@ change_hot_standby_feedback_and_wait_for_xmins(1, 1); ################################################## $node_standby->restart; -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is retained across a restart. +check_slots_conflict_reason('vacuum_full_', 'rows_removed'); ################################################## # Verify that invalidated logical slots do not lead to retaining WAL. @@ -511,7 +509,7 @@ check_slots_conflicting_status(1); # Get the restart_lsn from an invalidated slot my $restart_lsn = $node_standby->safe_psql('postgres', - "SELECT restart_lsn from pg_replication_slots WHERE slot_name = 'vacuum_full_activeslot' and conflicting is true;" + "SELECT restart_lsn from pg_replication_slots WHERE slot_name = 'vacuum_full_activeslot' and conflict_reason is not null;" ); chomp($restart_lsn); @@ -565,8 +563,8 @@ $node_primary->wait_for_replay_catchup($node_standby); # Check invalidation in the logfile and in pg_stat_database_conflicts check_for_invalidation('row_removal_', $logstart, 'with vacuum on pg_class'); -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is 'rows_removed' in pg_replication_slots +check_slots_conflict_reason('row_removal_', 'rows_removed'); $handle = make_slot_active($node_standby, 'row_removal_', 0, \$stdout, \$stderr); @@ -604,8 +602,8 @@ $node_primary->wait_for_replay_catchup($node_standby); check_for_invalidation('shared_row_removal_', $logstart, 'with vacuum on pg_authid'); -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is 'rows_removed' in pg_replication_slots +check_slots_conflict_reason('shared_row_removal_', 'rows_removed'); $handle = make_slot_active($node_standby, 'shared_row_removal_', 0, \$stdout, \$stderr); @@ -657,7 +655,13 @@ ok( $node_standby->poll_query_until( ) or die "Timed out waiting confl_active_logicalslot to be updated"; # Verify slots are reported as non conflicting in pg_replication_slots -check_slots_conflicting_status(0); +is( $node_standby->safe_psql( + 'postgres', + q[select bool_or(conflicting) from + (select conflict_reason is not NULL as conflicting + from pg_replication_slots WHERE slot_type = 'logical')]), + 'f', + 'Logical slots are reported as non conflicting'); # Turn hot_standby_feedback back on change_hot_standby_feedback_and_wait_for_xmins(1, 0); @@ -693,8 +697,8 @@ $node_primary->wait_for_replay_catchup($node_standby); # Check invalidation in the logfile and in pg_stat_database_conflicts check_for_invalidation('pruning_', $logstart, 'with on-access pruning'); -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is 'rows_removed' in pg_replication_slots +check_slots_conflict_reason('pruning_', 'rows_removed'); $handle = make_slot_active($node_standby, 'pruning_', 0, \$stdout, \$stderr); @@ -737,8 +741,8 @@ $node_primary->wait_for_replay_catchup($node_standby); # Check invalidation in the logfile and in pg_stat_database_conflicts check_for_invalidation('wal_level_', $logstart, 'due to wal_level'); -# Verify slots are reported as conflicting in pg_replication_slots -check_slots_conflicting_status(1); +# Verify conflict_reason is 'wal_level_insufficient' in pg_replication_slots +check_slots_conflict_reason('wal_level_', 'wal_level_insufficient'); $handle = make_slot_active($node_standby, 'wal_level_', 0, \$stdout, \$stderr); diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index f645e8486b..d878a971df 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -1473,8 +1473,8 @@ pg_replication_slots| SELECT l.slot_name, l.wal_status, l.safe_wal_size, l.two_phase, - l.conflicting - FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflicting) + l.conflict_reason + FROM (pg_get_replication_slots() l(slot_name, plugin, slot_type, datoid, temporary, active, active_pid, xmin, catalog_xmin, restart_lsn, confirmed_flush_lsn, wal_status, safe_wal_size, two_phase, conflict_reason) LEFT JOIN pg_database d ON ((l.datoid = d.oid))); pg_roles| SELECT pg_authid.rolname, pg_authid.rolsuper,