PostgreSQL源码学习--删除数据#0

以一条delete from test where a = 123;的SQL语句为例，跟踪删除数据的代码逻辑。（PG版本为12.2）

删除数据主要的函数是heap_delete。查看调用栈：

#0  heap_delete (relation=0x7f67ac24ca28, tid=0x7fff92b2c8ba, cid=0, 
    crosscheck=0x0, wait=true, tmfd=0x7fff92b2c7d0, changingPart=false)
    at heapam.c:2447
#1  0x00000000004d3bb7 in heapam_tuple_delete (relation=0x7f67ac24ca28, 
    tid=0x7fff92b2c8ba, cid=0, snapshot=0x2e37060, crosscheck=0x0, wait=true, 
    tmfd=0x7fff92b2c7d0, changingPart=false) at heapam_handler.c:314
#2  0x00000000006dac91 in table_tuple_delete (rel=0x7f67ac24ca28, 
    tid=0x7fff92b2c8ba, cid=0, snapshot=0x2e37060, crosscheck=0x0, wait=true, 
    tmfd=0x7fff92b2c7d0, changingPart=false)
    at ../../../src/include/access/tableam.h:1230
#3  0x00000000006dbfcb in ExecDelete (mtstate=0x2dcd1f0, 
    tupleid=0x7fff92b2c8ba, oldtuple=0x0, planSlot=0x2dce5c8, 
    epqstate=0x2dcd2e8, estate=0x2dcce70, processReturning=true, 
    canSetTag=true, changingPart=false, tupleDeleted=0x0, epqreturnslot=0x0)
    at nodeModifyTable.c:768
#4  0x00000000006de016 in ExecModifyTable (pstate=0x2dcd1f0)
    at nodeModifyTable.c:2226

//src/include/access/heapam.h

extern TM_Result heap_delete(Relation relation, ItemPointer tid,
					 CommandId cid, Snapshot crosscheck, bool wait,
					 struct TM_FailureData *tmfd, bool changingPart);

TransactionId xid = GetCurrentTransactionId();

Assert(ItemPointerIsValid(tid));


if (IsInParallelMode())
	ereport(ERROR,
			(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
			 errmsg("cannot delete tuples during a parallel operation")));


block = ItemPointerGetBlockNumber(tid);
buffer = ReadBuffer(relation, block);
page = BufferGetPage(buffer);


if (PageIsAllVisible(page))
	visibilitymap_pin(relation, block, &vmbuffer);

LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);


if (vmbuffer == InvalidBuffer && PageIsAllVisible(page))
{
	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
	visibilitymap_pin(relation, block, &vmbuffer);
	LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}


lp = PageGetItemId(page, ItemPointerGetOffsetNumber(tid));
	Assert(ItemIdIsNormal(lp));


tp.t_tableOid = RelationGetRelid(relation);
tp.t_data = (HeapTupleHeader) PageGetItem(page, lp);
tp.t_len = ItemIdGetLength(lp);
tp.t_self = *tid;


l1:


result = HeapTupleSatisfiesUpdate(&tp, cid, buffer);


if (result == TM_Invisible)
{
	UnlockReleaseBuffer(buffer);
	ereport(ERROR,
			(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
			 errmsg("attempted to delete invisible tuple")));
}

else if (result == TM_BeingModified && wait)
{
	
	xwait = HeapTupleHeaderGetRawXmax(tp.t_data);
	infomask = tp.t_data->t_infomask;
	
	
	if (infomask & HEAP_XMAX_IS_MULTI)
	{
		
		if (DoesMultiXactIdConflict((MultiXactId) xwait, infomask,
						LockTupleExclusive, ¤t_is_member))
		{
			
			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
			
			
			if (!current_is_member)
				heap_acquire_tuplock(relation, &(tp.t_self), LockTupleExclusive,
							 LockWaitBlock, &have_tuple_lock);
			
			
			MultiXactIdWait((MultiXactId) xwait, MultiXactStatusUpdate, infomask,
							relation, &(tp.t_self), XLTW_Delete,
							NULL);
			LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
			
			
			if (xmax_infomask_changed(tp.t_data->t_infomask, infomask) ||
				!TransactionIdEquals(HeapTupleHeaderGetRawXmax(tp.t_data),
							 xwait))
				goto l1;
		}
	}
	
	else if (!TransactionIdIsCurrentTransactionId(xwait))
	{
		
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		heap_acquire_tuplock(relation, &(tp.t_self), LockTupleExclusive,
						 LockWaitBlock, &have_tuple_lock);
		XactLockTableWait(xwait, relation, &(tp.t_self), XLTW_Delete);
		LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
		
		
		if (xmax_infomask_changed(tp.t_data->t_infomask, infomask) ||
			!TransactionIdEquals(HeapTupleHeaderGetRawXmax(tp.t_data),
							 xwait))
			goto l1;
		
		
		UpdateXmaxHintBits(tp.t_data, buffer, xwait);
	}
	
	
	if ((tp.t_data->t_infomask & HEAP_XMAX_INVALID) ||
		HEAP_XMAX_IS_LOCKED_ONLY(tp.t_data->t_infomask) ||
		HeapTupleHeaderIsOnlyLocked(tp.t_data))
		result = TM_Ok;
	else if (!ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid) ||
			 HeapTupleHeaderIndicatesMovedPartitions(tp.t_data))
		result = TM_Updated;
	else
		result = TM_Deleted;
}


if (crosscheck != InvalidSnapshot && result == TM_Ok)
{
	if (!HeapTupleSatisfiesVisibility(&tp, crosscheck, buffer))
		result = TM_Updated;
}


if (result != TM_Ok)
{
	Assert(result == TM_SelfModified ||
		   result == TM_Updated ||
		   result == TM_Deleted ||
		   result == TM_BeingModified);
	Assert(!(tp.t_data->t_infomask & HEAP_XMAX_INVALID));
	Assert(result != TM_Updated ||
		   !ItemPointerEquals(&tp.t_self, &tp.t_data->t_ctid));
	tmfd->ctid = tp.t_data->t_ctid;
	tmfd->xmax = HeapTupleHeaderGetUpdateXid(tp.t_data);
	if (result == TM_SelfModified)
		tmfd->cmax = HeapTupleHeaderGetCmax(tp.t_data);
	else
		tmfd->cmax = InvalidCommandId;
	UnlockReleaseBuffer(buffer);
	if (have_tuple_lock)
		UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive);
	if (vmbuffer != InvalidBuffer)
		ReleaseBuffer(vmbuffer);
	return result;
}


CheckForSerializableConflictIn(relation, &tp, buffer);


HeapTupleHeaderAdjustCmax(tp.t_data, &cid, &iscombo);


old_key_tuple = ExtractReplicaIdentity(relation, &tp, true, &old_key_copied);


MultiXactIdSetOldestMember();


compute_new_xmax_infomask(HeapTupleHeaderGetRawXmax(tp.t_data),
					  tp.t_data->t_infomask, tp.t_data->t_infomask2,
					  xid, LockTupleExclusive, true,
					  &new_xmax, &new_infomask, &new_infomask2);


START_CRIT_SECTION();


PageSetPrunable(page, xid);


if (PageIsAllVisible(page))
{
	all_visible_cleared = true;
	PageClearAllVisible(page);
	visibilitymap_clear(relation, BufferGetBlockNumber(buffer),
					vmbuffer, VISIBILITYMAP_VALID_BITS);
}


tp.t_data->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED);
tp.t_data->t_infomask2 &= ~HEAP_KEYS_UPDATED;
tp.t_data->t_infomask |= new_infomask;
tp.t_data->t_infomask2 |= new_infomask2;
HeapTupleHeaderClearHotUpdated(tp.t_data);
HeapTupleHeaderSetXmax(tp.t_data, new_xmax);
HeapTupleHeaderSetCmax(tp.t_data, cid, iscombo);

tp.t_data->t_ctid = tp.t_self;


if (changingPart)
	HeapTupleHeaderSetMovedPartitions(tp.t_data);


MarkBufferDirty(buffer);


if (RelationNeedsWAL(relation))
{
	
	if (RelationIsAccessibleInLogicalDecoding(relation))
		log_heap_new_cid(relation, &tp);
	
	xlrec.flags = 0;
	if (all_visible_cleared)
		xlrec.flags |= XLH_DELETE_ALL_VISIBLE_CLEARED;
	if (changingPart)
		xlrec.flags |= XLH_DELETE_IS_PARTITION_MOVE;
	xlrec.infobits_set = compute_infobits(tp.t_data->t_infomask,
										  tp.t_data->t_infomask2);
	xlrec.offnum = ItemPointerGetOffsetNumber(&tp.t_self);
	xlrec.xmax = new_xmax;
	
	if (old_key_tuple != NULL)
	{
		if (relation->rd_rel->relreplident == REPLICA_IDENTITY_FULL)
			xlrec.flags |= XLH_DELETE_CONTAINS_OLD_TUPLE;
		else
			xlrec.flags |= XLH_DELETE_CONTAINS_OLD_KEY;
	}
	
	
	XLogBeginInsert();
	XLogRegisterData((char *) &xlrec, SizeOfHeapDelete);
	
	XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
	
	
	if (old_key_tuple != NULL)
	{
		xlhdr.t_infomask2 = old_key_tuple->t_data->t_infomask2;
		xlhdr.t_infomask = old_key_tuple->t_data->t_infomask;
		xlhdr.t_hoff = old_key_tuple->t_data->t_hoff;
		
		XLogRegisterData((char *) &xlhdr, SizeOfHeapHeader);
		XLogRegisterData((char *) old_key_tuple->t_data
						 + SizeofHeapTupleHeader,
						 old_key_tuple->t_len
						 - SizeofHeapTupleHeader);
	}

	
	XLogSetRecordFlags(XLOG_INCLUDE_ORIGIN);

	
	recptr = XLogInsert(RM_HEAP_ID, XLOG_HEAP_DELETE);

	
	PageSetLSN(page, recptr);
}

END_CRIT_SECTION();


LockBuffer(buffer, BUFFER_LOCK_UNLOCK);

if (vmbuffer != InvalidBuffer)
		ReleaseBuffer(vmbuffer);


if (relation->rd_rel->relkind != RELKIND_RELATION &&
	relation->rd_rel->relkind != RELKIND_MATVIEW)
{
	
	Assert(!HeapTupleHasExternal(&tp));
}
else if (HeapTupleHasExternal(&tp))
	toast_delete(relation, &tp, false);


CacheInvalidateHeapTuple(relation, &tp, NULL);


ReleaseBuffer(buffer);


if (have_tuple_lock)
	UnlockTupleTuplock(relation, &(tp.t_self), LockTupleExclusive);


pgstat_count_heap_delete(relation);


if (old_key_tuple != NULL && old_key_copied)
	heap_freetuple(old_key_tuple);

return TM_Ok;