Add slotsync_skip_reason column to pg_replication_slots view.

Introduce a new column, slotsync_skip_reason, in the pg_replication_slots
view. This column records the reason why the last slot synchronization was
skipped. It is primarily relevant for logical replication slots on standby
servers where the 'synced' field is true. The value is NULL when
synchronization succeeds.

Author: Shlok Kyal <shlok.kyal.oss@gmail.com>
Reviewed-by: shveta malik <shveta.malik@gmail.com>
Reviewed-by: Hayato Kuroda <kuroda.hayato@fujitsu.com>
Reviewed-by: Ashutosh Sharma <ashu.coek88@gmail.com>
Reviewed-by: Hou Zhijie <houzj.fnst@fujitsu.com>
Reviewed-by: Amit Kapila <amit.kapila16@gmail.com>
Discussion: https://postgr.es/m/CAE9k0PkhfKrTEAsGz4DjOhEj1nQ+hbQVfvWUxNacD38ibW3a1g@mail.gmail.com

3 files changed, 34 insertions, 4 deletions

diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index ee642e5510d..70320aa0cfb 100644
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -57,6 +57,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202511251
+#define CATALOG_VERSION_NO	202511281
 
 #endif
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 66431940700..66af2d96d67 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -11519,9 +11519,9 @@
   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,pg_lsn,timestamptz,bool,text,bool,bool}',
-  proargmodes => '{o,o,o,o,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,two_phase_at,inactive_since,conflicting,invalidation_reason,failover,synced}',
+  proallargtypes => '{name,name,text,oid,bool,bool,int4,xid,xid,pg_lsn,pg_lsn,text,int8,bool,pg_lsn,timestamptz,bool,text,bool,bool,text}',
+  proargmodes => '{o,o,o,o,o,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,two_phase_at,inactive_since,conflicting,invalidation_reason,failover,synced,slotsync_skip_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/include/replication/slot.h b/src/include/replication/slot.h
index 09c69f83d57..28251d86638 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -72,6 +72,24 @@ typedef enum ReplicationSlotInvalidationCause
 #define	RS_INVAL_MAX_CAUSES 4
 
 /*
+ * When the slot synchronization worker is running, or when
+ * pg_sync_replication_slots is executed, slot synchronization may be
+ * skipped. This enum defines the possible reasons for skipping slot
+ * synchronization.
+ */
+typedef enum SlotSyncSkipReason
+{
+	SS_SKIP_NONE,				/* No skip */
+	SS_SKIP_WAL_NOT_FLUSHED,	/* Standby did not flush the wal corresponding
+								 * to confirmed flush of remote slot */
+	SS_SKIP_WAL_OR_ROWS_REMOVED,	/* Remote slot is behind; required WAL or
+									 * rows may be removed or at risk */
+	SS_SKIP_NO_CONSISTENT_SNAPSHOT, /* Standby could not build a consistent
+									 * snapshot */
+	SS_SKIP_INVALID				/* Local slot is invalid */
+} SlotSyncSkipReason;
+
+/*
  * On-Disk data of a replication slot, preserved across restarts.
  */
 typedef struct ReplicationSlotPersistentData
@@ -249,6 +267,18 @@ typedef struct ReplicationSlot
 	 */
 	XLogRecPtr	last_saved_restart_lsn;
 
+	/*
+	 * Reason for the most recent slot synchronization skip.
+	 *
+	 * Slot sync skips can occur for both temporary and persistent replication
+	 * slots. They are more common for temporary slots, but persistent slots
+	 * may also skip synchronization in rare cases (e.g.,
+	 * SS_SKIP_WAL_NOT_FLUSHED or SS_SKIP_WAL_OR_ROWS_REMOVED).
+	 *
+	 * Since, temporary slots are dropped after server restart, persisting
+	 * slotsync_skip_reason provides no practical benefit.
+	 */
+	SlotSyncSkipReason slotsync_skip_reason;
 } ReplicationSlot;
 
 #define SlotIsPhysical(slot) ((slot)->data.database == InvalidOid)