v2-0001-Track-invalidation_reason-in-pg_replication_slots.patch

From 26c5b7762abc8fd92df0376ec68c81d7064891fb Mon Sep 17 00:00:00 2001
From: Bharath Rupireddy <bharath.rupireddyforpostgres@gmail.com>
Date: Fri, 26 Jan 2024 18:11:01 +0000
Subject: [PATCH v2] Track invalidation_reason in pg_replication_slots

Currently the reason for replication slot invalidation is not
tracked in pg_replication_slots. A recent commit 007693f2a added
conflict_reason to show the reasons for slot invalidation, but
only for logical slots. This commit renames conflict_reason to
invalidation_reason, and adds the support to show invalidation
reasons for both physical and logical slots.
---
 doc/src/sgml/system-views.sgml                | 11 +++---
 src/backend/catalog/system_views.sql          |  2 +-
 src/backend/replication/slotfuncs.c           | 37 ++++++++-----------
 src/bin/pg_upgrade/info.c                     |  4 +-
 src/include/catalog/pg_proc.dat               |  2 +-
 .../t/035_standby_logical_decoding.pl         | 32 ++++++++--------
 src/test/regress/expected/rules.out           |  4 +-
 7 files changed, 44 insertions(+), 48 deletions(-)

diff --git a/doc/src/sgml/system-views.sgml b/doc/src/sgml/system-views.sgml
index dd468b31ea..c61312793c 100644
--- a/doc/src/sgml/system-views.sgml
+++ b/doc/src/sgml/system-views.sgml
@@ -2525,13 +2525,14 @@ SELECT * FROM pg_locks pl LEFT JOIN pg_prepared_xacts ppx
 
      <row>
       <entry role="catalog_table_entry"><para role="column_definition">
-       <structfield>conflict_reason</structfield> <type>text</type>
+       <structfield>invalidation_reason</structfield> <type>text</type>
       </para>
       <para>
-       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:
+       The reason for the slot's invalidation. <literal>NULL</literal> if the
+       slot is currently actively being used. The non-NULL values indicate that
+       the slot is marked as invalidated. In case of logical slots, it
+       represents the reason for the logical slot's conflict with recovery.
+       Possible values are:
        <itemizedlist spacing="compact">
         <listitem>
          <para>
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index c62aa0074a..d78077b936 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.conflict_reason,
+            L.invalidation_reason,
             L.failover
     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 eb685089b3..e53aeb37c9 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -407,28 +407,23 @@ pg_get_replication_slots(PG_FUNCTION_ARGS)
 
 		values[i++] = BoolGetDatum(slot_contents.data.two_phase);
 
-		if (slot_contents.data.database == InvalidOid)
-			nulls[i++] = true;
-		else
+		switch (slot_contents.data.invalidated)
 		{
-			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;
-			}
+			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;
 		}
 
 		values[i++] = BoolGetDatum(slot_contents.data.failover);
diff --git a/src/bin/pg_upgrade/info.c b/src/bin/pg_upgrade/info.c
index 183c2f84eb..9683c91d4a 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, failover, "
-							"%s as caught_up, conflict_reason IS NOT NULL as invalid "
+							"%s as caught_up, invalidation_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 conflict_reason IS NOT NULL THEN FALSE "
+							"(CASE WHEN invalidation_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/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 29af4ce65d..de1115baa0 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11129,7 +11129,7 @@
   proargtypes => '',
   proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,text,bool}',
   proargmodes => '{o,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,conflict_reason,failover}',
+  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,invalidation_reason,failover}',
   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 cebfa52d0f..f2c58a8a06 100644
--- a/src/test/recovery/t/035_standby_logical_decoding.pl
+++ b/src/test/recovery/t/035_standby_logical_decoding.pl
@@ -168,7 +168,7 @@ sub change_hot_standby_feedback_and_wait_for_xmins
 	}
 }
 
-# Check conflict_reason in pg_replication_slots.
+# Check invalidation_reason in pg_replication_slots.
 sub check_slots_conflict_reason
 {
 	my ($slot_prefix, $reason) = @_;
@@ -178,15 +178,15 @@ sub check_slots_conflict_reason
 
 	$res = $node_standby->safe_psql(
 		'postgres', qq(
-			 select conflict_reason from pg_replication_slots where slot_name = '$active_slot';));
+			 select invalidation_reason from pg_replication_slots where slot_name = '$active_slot';));
 
-	is($res, "$reason", "$active_slot conflict_reason is $reason");
+	is($res, "$reason", "$active_slot invalidation_reason is $reason");
 
 	$res = $node_standby->safe_psql(
 		'postgres', qq(
-			 select conflict_reason from pg_replication_slots where slot_name = '$inactive_slot';));
+			 select invalidation_reason from pg_replication_slots where slot_name = '$inactive_slot';));
 
-	is($res, "$reason", "$inactive_slot conflict_reason is $reason");
+	is($res, "$reason", "$inactive_slot invalidation_reason is $reason");
 }
 
 # Drop the slots, re-create them, change hot_standby_feedback,
@@ -293,13 +293,13 @@ $node_primary->safe_psql('testdb',
 	qq[SELECT * FROM pg_create_physical_replication_slot('$primary_slotname');]
 );
 
-# Check conflict_reason is NULL for physical slot
+# Check invalidation_reason is NULL for physical slot
 $res = $node_primary->safe_psql(
 	'postgres', qq[
-		 SELECT conflict_reason is null FROM pg_replication_slots where slot_name = '$primary_slotname';]
+		 SELECT invalidation_reason is null FROM pg_replication_slots where slot_name = '$primary_slotname';]
 );
 
-is($res, 't', "Physical slot reports conflict_reason as NULL");
+is($res, 't', "Physical slot reports invalidation_reason as NULL");
 
 my $backup_name = 'b1';
 $node_primary->backup($backup_name);
@@ -512,7 +512,7 @@ $node_primary->wait_for_replay_catchup($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 conflict_reason is 'rows_removed' in pg_replication_slots
+# Verify invalidation_reason is 'rows_removed' in pg_replication_slots
 check_slots_conflict_reason('vacuum_full_', 'rows_removed');
 
 $handle =
@@ -531,7 +531,7 @@ change_hot_standby_feedback_and_wait_for_xmins(1, 1);
 ##################################################
 $node_standby->restart;
 
-# Verify conflict_reason is retained across a restart.
+# Verify invalidation_reason is retained across a restart.
 check_slots_conflict_reason('vacuum_full_', 'rows_removed');
 
 ##################################################
@@ -540,7 +540,7 @@ check_slots_conflict_reason('vacuum_full_', 'rows_removed');
 
 # 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 conflict_reason is not null;"
+	"SELECT restart_lsn from pg_replication_slots WHERE slot_name = 'vacuum_full_activeslot' and invalidation_reason is not null;"
 );
 
 chomp($restart_lsn);
@@ -591,7 +591,7 @@ $node_primary->wait_for_replay_catchup($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 conflict_reason is 'rows_removed' in pg_replication_slots
+# Verify invalidation_reason is 'rows_removed' in pg_replication_slots
 check_slots_conflict_reason('row_removal_', 'rows_removed');
 
 $handle =
@@ -627,7 +627,7 @@ $node_primary->wait_for_replay_catchup($node_standby);
 check_for_invalidation('shared_row_removal_', $logstart,
 	'with vacuum on pg_authid');
 
-# Verify conflict_reason is 'rows_removed' in pg_replication_slots
+# Verify invalidation_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,
@@ -680,7 +680,7 @@ ok( $node_standby->poll_query_until(
 is( $node_standby->safe_psql(
 		'postgres',
 		q[select bool_or(conflicting) from
-		  (select conflict_reason is not NULL as conflicting
+		  (select invalidation_reason is not NULL as conflicting
 		   from pg_replication_slots WHERE slot_type = 'logical')]),
 	'f',
 	'Logical slots are reported as non conflicting');
@@ -719,7 +719,7 @@ $node_primary->wait_for_replay_catchup($node_standby);
 # Check invalidation in the logfile and in pg_stat_database_conflicts
 check_for_invalidation('pruning_', $logstart, 'with on-access pruning');
 
-# Verify conflict_reason is 'rows_removed' in pg_replication_slots
+# Verify invalidation_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);
@@ -763,7 +763,7 @@ $node_primary->wait_for_replay_catchup($node_standby);
 # Check invalidation in the logfile and in pg_stat_database_conflicts
 check_for_invalidation('wal_level_', $logstart, 'due to wal_level');
 
-# Verify conflict_reason is 'wal_level_insufficient' in pg_replication_slots
+# Verify invalidation_reason is 'wal_level_insufficient' in pg_replication_slots
 check_slots_conflict_reason('wal_level_', 'wal_level_insufficient');
 
 $handle =
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index abc944e8b8..022f9bccb0 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1473,9 +1473,9 @@ pg_replication_slots| SELECT l.slot_name,
     l.wal_status,
     l.safe_wal_size,
     l.two_phase,
-    l.conflict_reason,
+    l.invalidation_reason,
     l.failover
-   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, failover)
+   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, invalidation_reason, failover)
      LEFT JOIN pg_database d ON ((l.datoid = d.oid)));
 pg_roles| SELECT pg_authid.rolname,
     pg_authid.rolsuper,
-- 
2.34.1