Allow locking updated tuples in tuple_update() and tuple_delete()

Currently, in read committed transaction isolation mode (default), we have the
following sequence of actions when tuple_update()/tuple_delete() finds
the tuple updated by the concurrent transaction.

1. Attempt to update/delete tuple with tuple_update()/tuple_delete(), which
   returns TM_Updated.
2. Lock tuple with tuple_lock().
3. Re-evaluate plan qual (recheck if we still need to update/delete and
   calculate the new tuple for update).
4. Second attempt to update/delete tuple with tuple_update()/tuple_delete().
   This attempt should be successful, since the tuple was previously locked.

This commit eliminates step 2 by taking the lock during the first
tuple_update()/tuple_delete() call.  The heap table access method saves some
effort by checking the updated tuple once instead of twice.  Future
undo-based table access methods, which will start from the latest row version,
can immediately place a lock there.

Also, this commit makes tuple_update()/tuple_delete() optionally save the old
tuple into the dedicated slot.  That saves efforts on re-fetching tuples in
certain cases.

The code in nodeModifyTable.c is simplified by removing the nested switch/case.

Discussion: https://postgr.es/m/CAPpHfdua-YFw3XTprfutzGp28xXLigFtzNbuFY8yPhqeq6X5kg%40mail.gmail.com
Reviewed-by: Aleksander Alekseev, Pavel Borisov, Vignesh C, Mason Sharp
Reviewed-by: Andres Freund, Chris Travers

1 files changed, 15 insertions, 40 deletions

diff --git a/src/backend/commands/trigger.c b/src/backend/commands/trigger.c
index 35eb7180f7e..3309b4ebd2d 100644
--- a/src/backend/commands/trigger.c
+++ b/src/backend/commands/trigger.c
@@ -2773,8 +2773,8 @@ ExecBRDeleteTriggers(EState *estate, EPQState *epqstate,
 void
 ExecARDeleteTriggers(EState *estate,
 					 ResultRelInfo *relinfo,
-					 ItemPointer tupleid,
 					 HeapTuple fdw_trigtuple,
+					 TupleTableSlot *slot,
 					 TransitionCaptureState *transition_capture,
 					 bool is_crosspart_update)
 {
@@ -2783,20 +2783,11 @@ ExecARDeleteTriggers(EState *estate,
 	if ((trigdesc && trigdesc->trig_delete_after_row) ||
 		(transition_capture && transition_capture->tcs_delete_old_table))
 	{
-		TupleTableSlot *slot = ExecGetTriggerOldSlot(estate, relinfo);
-
-		Assert(HeapTupleIsValid(fdw_trigtuple) ^ ItemPointerIsValid(tupleid));
-		if (fdw_trigtuple == NULL)
-			GetTupleForTrigger(estate,
-							   NULL,
-							   relinfo,
-							   tupleid,
-							   LockTupleExclusive,
-							   slot,
-							   NULL,
-							   NULL,
-							   NULL);
-		else
+		/*
+		 * Put the FDW old tuple to the slot.  Otherwise, caller is expected
+		 * to have old tuple alredy fetched to the slot.
+		 */
+		if (fdw_trigtuple != NULL)
 			ExecForceStoreHeapTuple(fdw_trigtuple, slot, false);
 
 		AfterTriggerSaveEvent(estate, relinfo, NULL, NULL,
@@ -3087,18 +3078,17 @@ ExecBRUpdateTriggers(EState *estate, EPQState *epqstate,
  * Note: 'src_partinfo' and 'dst_partinfo', when non-NULL, refer to the source
  * and destination partitions, respectively, of a cross-partition update of
  * the root partitioned table mentioned in the query, given by 'relinfo'.
- * 'tupleid' in that case refers to the ctid of the "old" tuple in the source
- * partition, and 'newslot' contains the "new" tuple in the destination
- * partition.  This interface allows to support the requirements of
- * ExecCrossPartitionUpdateForeignKey(); is_crosspart_update must be true in
- * that case.
+ * 'oldslot' contains the "old" tuple in the source partition, and 'newslot'
+ * contains the "new" tuple in the destination partition.  This interface
+ * allows to support the requirements of ExecCrossPartitionUpdateForeignKey();
+ * is_crosspart_update must be true in that case.
  */
 void
 ExecARUpdateTriggers(EState *estate, ResultRelInfo *relinfo,
 					 ResultRelInfo *src_partinfo,
 					 ResultRelInfo *dst_partinfo,
-					 ItemPointer tupleid,
 					 HeapTuple fdw_trigtuple,
+					 TupleTableSlot *oldslot,
 					 TupleTableSlot *newslot,
 					 List *recheckIndexes,
 					 TransitionCaptureState *transition_capture,
@@ -3117,29 +3107,14 @@ ExecARUpdateTriggers(EState *estate, ResultRelInfo *relinfo,
 		 * separately for DELETE and INSERT to capture transition table rows.
 		 * In such case, either old tuple or new tuple can be NULL.
 		 */
-		TupleTableSlot *oldslot;
-		ResultRelInfo *tupsrc;
-
 		Assert((src_partinfo != NULL && dst_partinfo != NULL) ||
 			   !is_crosspart_update);
 
-		tupsrc = src_partinfo ? src_partinfo : relinfo;
-		oldslot = ExecGetTriggerOldSlot(estate, tupsrc);
-
-		if (fdw_trigtuple == NULL && ItemPointerIsValid(tupleid))
-			GetTupleForTrigger(estate,
-							   NULL,
-							   tupsrc,
-							   tupleid,
-							   LockTupleExclusive,
-							   oldslot,
-							   NULL,
-							   NULL,
-							   NULL);
-		else if (fdw_trigtuple != NULL)
+		if (fdw_trigtuple != NULL)
+		{
+			Assert(oldslot);
 			ExecForceStoreHeapTuple(fdw_trigtuple, oldslot, false);
-		else
-			ExecClearTuple(oldslot);
+		}
 
 		AfterTriggerSaveEvent(estate, relinfo,
 							  src_partinfo, dst_partinfo,