/*
 * Make sure that SUBTRANS has room for a newly-allocated XID.
 *
 * NB: this is called while holding XidGenLock.  We want it to be very fast
 * most of the time; even when it's not so fast, no actual I/O need happen
 * unless we're forced to write out a dirty subtrans page to make room
 * in shared memory.
 */
void
ExtendSUBTRANS(TransactionId newestXact)
{
	int			pageno;

	/*
	 * Caller must have already taken mirrored lock shared.
	 */

	/*
	 * No work except at first XID of a page.  But beware: just after
	 * wraparound, the first XID of page zero is FirstNormalTransactionId.
	 */
	if (TransactionIdToEntry(newestXact) != 0 &&
		!TransactionIdEquals(newestXact, FirstNormalTransactionId))
		return;

	pageno = TransactionIdToPage(newestXact);

	LWLockAcquire(SubtransControlLock, LW_EXCLUSIVE);

	/* Zero the page */
	ZeroSUBTRANSPage(pageno);

	LWLockRelease(SubtransControlLock);
}

/*
 *		XactLockTableWait
 *
 * Wait for the specified transaction to commit or abort.
 */
void
XactLockTableWait(TransactionId xid)
{
	LOCKTAG		tag;
	TransactionId myxid = GetCurrentTransactionId();

	Assert(!TransactionIdEquals(xid, myxid));

	MemSet(&tag, 0, sizeof(tag));
	tag.relId = XactLockTableId;
	tag.dbId = InvalidOid;
	tag.objId.xid = xid;

	if (!LockAcquire(LockTableId, &tag, myxid,
					 ShareLock, false))
		elog(ERROR, "LockAcquire failed");

	LockRelease(LockTableId, &tag, myxid, ShareLock);

	/*
	 * Transaction was committed/aborted/crashed - we have to update
	 * pg_clog if transaction is still marked as running.
	 */
	if (!TransactionIdDidCommit(xid) && !TransactionIdDidAbort(xid))
		TransactionIdAbort(xid);
}

/*
 * TransactionIdGetCommitLSN
 *
 * This function returns an LSN that is late enough to be able
 * to guarantee that if we flush up to the LSN returned then we
 * will have flushed the transaction's commit record to disk.
 *
 * The result is not necessarily the exact LSN of the transaction's
 * commit record!  For example, for long-past transactions (those whose
 * clog pages already migrated to disk), we'll return InvalidXLogRecPtr.
 * Also, because we group transactions on the same clog page to conserve
 * storage, we might return the LSN of a later transaction that falls into
 * the same group.
 */
XLogRecPtr
TransactionIdGetCommitLSN(TransactionId xid)
{
	XLogRecPtr	result;

	/*
	 * Currently, all uses of this function are for xids that were just
	 * reported to be committed by TransactionLogFetch, so we expect that
	 * checking TransactionLogFetch's cache will usually succeed and avoid an
	 * extra trip to shared memory.
	 */
	if (TransactionIdEquals(xid, cachedFetchXid))
		return cachedCommitLSN;

	/* Special XIDs are always known committed */
	if (!TransactionIdIsNormal(xid))
		return InvalidXLogRecPtr;

	/*
	 * Get the transaction status.
	 */
	(void) TransactionIdGetStatus(xid, &result);

	return result;
}

/*
 * Make sure that CommitTs has room for a newly-allocated XID.
 *
 * NB: this is called while holding XidGenLock.  We want it to be very fast
 * most of the time; even when it's not so fast, no actual I/O need happen
 * unless we're forced to write out a dirty CommitTs or xlog page to make room
 * in shared memory.
 *
 * NB: the current implementation relies on track_commit_timestamp being
 * PGC_POSTMASTER.
 */
void
ExtendCommitTs(TransactionId newestXact)
{
	int			pageno;

	/*
	 * Nothing to do if module not enabled.  Note we do an unlocked read of
	 * the flag here, which is okay because this routine is only called from
	 * GetNewTransactionId, which is never called in a standby.
	 */
	Assert(!InRecovery);
	if (!commitTsShared->commitTsActive)
		return;

	/*
	 * No work except at first XID of a page.  But beware: just after
	 * wraparound, the first XID of page zero is FirstNormalTransactionId.
	 */
	if (TransactionIdToCTsEntry(newestXact) != 0 &&
		!TransactionIdEquals(newestXact, FirstNormalTransactionId))
		return;

	pageno = TransactionIdToCTsPage(newestXact);

	LWLockAcquire(CommitTsControlLock, LW_EXCLUSIVE);

	/* Zero the page and make an XLOG entry about it */
	ZeroCommitTsPage(pageno, !InRecovery);

	LWLockRelease(CommitTsControlLock);
}

/*
 * TransactionIdIsInProgress -- is given transaction running by some backend
 */
bool
TransactionIdIsInProgress(TransactionId xid)
{
	bool		result = false;
	SISeg	   *segP = shmInvalBuffer;
	ProcState  *stateP = segP->procState;
	int			index;

	LWLockAcquire(SInvalLock, LW_SHARED);

	for (index = 0; index < segP->lastBackend; index++)
	{
		SHMEM_OFFSET pOffset = stateP[index].procStruct;

		if (pOffset != INVALID_OFFSET)
		{
			PGPROC	   *proc = (PGPROC *) MAKE_PTR(pOffset);

			/* Fetch xid just once - see GetNewTransactionId */
			TransactionId pxid = proc->xid;

			if (TransactionIdEquals(pxid, xid))
			{
				result = true;
				break;
			}
		}
	}

	LWLockRelease(SInvalLock);

	return result;
}

/*
 * Make sure that SUBTRANS has room for a newly-allocated XID.
 *
 * NB: this is called while holding XidGenLock.  We want it to be very fast
 * most of the time; even when it's not so fast, no actual I/O need happen
 * unless we're forced to write out a dirty subtrans page to make room
 * in shared memory.
 */
void
ExtendSUBTRANS(TransactionId newestXact)
{
	int			pageno;

	/*
	 * No work except at first XID of a page.  But beware: just after
	 * wraparound, the first XID of page zero is FirstNormalTransactionId.
	 */
#ifdef PGXC  /* PGXC_COORD || PGXC_DATANODE */
	/* 
	 * In PGXC, it may be that a node is not involved in a transaction,
	 * and therefore will be skipped, so we need to detect this by using
	 * the latest_page_number instead of the pg index.
	 *
	 * Also, there is a special case of when transactions wrap-around that
	 * we need to detect.
	 */
	pageno = TransactionIdToPage(newestXact);

	/* 
	 * The first condition makes sure we did not wrap around 
	 * The second checks if we are still using the same page.
	 * Note that this value can change and we are not holding a lock, 
	 * so we repeat the check below. We do it this way instead of 
	 * grabbing the lock to avoid lock contention.
	 */
	if (SubTransCtl->shared->latest_page_number - pageno <= SUBTRANS_WRAP_CHECK_DELTA 
			&& pageno <= SubTransCtl->shared->latest_page_number)
		return;
#else
	if (TransactionIdToEntry(newestXact) != 0 &&
		!TransactionIdEquals(newestXact, FirstNormalTransactionId))
		return;

	pageno = TransactionIdToPage(newestXact);
#endif

	LWLockAcquire(SubtransControlLock, LW_EXCLUSIVE);

#ifdef PGXC
	/*
	 * We repeat the check.  Another process may have written 
	 * out the page already and advanced the latest_page_number
	 * while we were waiting for the lock.
	 */
	if (SubTransCtl->shared->latest_page_number - pageno <= SUBTRANS_WRAP_CHECK_DELTA 
			&& pageno <= SubTransCtl->shared->latest_page_number)
	{
		LWLockRelease(SubtransControlLock);
		return;
	}
#endif

	/* Zero the page */
	ZeroSUBTRANSPage(pageno);

	LWLockRelease(SubtransControlLock);
}

/*
 *		xideq			- are two xids equal?
 */
Datum
xideq(PG_FUNCTION_ARGS)
{
    TransactionId xid1 = PG_GETARG_TRANSACTIONID(0);
    TransactionId xid2 = PG_GETARG_TRANSACTIONID(1);

    PG_RETURN_BOOL(TransactionIdEquals(xid1, xid2));
}

/*
 * TransactionLogFetch --- fetch commit status of specified transaction id
 */
static XidStatus
TransactionLogFetch(TransactionId transactionId)
{
	XidStatus	xidstatus;
	XLogRecPtr	xidlsn;

	/*
	 * Before going to the commit log manager, check our single item cache to
	 * see if we didn't just check the transaction status a moment ago.
	 */
	if (TransactionIdEquals(transactionId, cachedFetchXid))
		return cachedFetchXidStatus;

	/*
	 * Also, check to see if the transaction ID is a permanent one.
	 */
	if (!TransactionIdIsNormal(transactionId))
	{
		if (TransactionIdEquals(transactionId, BootstrapTransactionId))
			return TRANSACTION_STATUS_COMMITTED;
		if (TransactionIdEquals(transactionId, FrozenTransactionId))
			return TRANSACTION_STATUS_COMMITTED;
		return TRANSACTION_STATUS_ABORTED;
	}

	/*
	 * Get the transaction status.
	 */
	xidstatus = TransactionIdGetStatus(transactionId, &xidlsn);

	/*
	 * Cache it, but DO NOT cache status for unfinished or sub-committed
	 * transactions!  We only cache status that is guaranteed not to change.
	 */
	if (xidstatus != TRANSACTION_STATUS_IN_PROGRESS &&
		xidstatus != TRANSACTION_STATUS_SUB_COMMITTED)
	{
		cachedFetchXid = transactionId;
		cachedFetchXidStatus = xidstatus;
		cachedCommitLSN = xidlsn;
	}

	return xidstatus;
}

/*
 * TransactionIdIsKnownCompleted
 *		True iff transaction associated with the identifier is currently
 *		known to have either committed or aborted.
 *
 * This does NOT look into pg_clog but merely probes our local cache
 * (and so it's not named TransactionIdDidComplete, which would be the
 * appropriate name for a function that worked that way).  The intended
 * use is just to short-circuit TransactionIdIsInProgress calls when doing
 * repeated tqual.c checks for the same XID.  If this isn't extremely fast
 * then it will be counterproductive.
 *
 * Note:
 *		Assumes transaction identifier is valid.
 */
bool
TransactionIdIsKnownCompleted(TransactionId transactionId)
{
	if (TransactionIdEquals(transactionId, cachedFetchXid))
	{
		/* If it's in the cache at all, it must be completed. */
		return true;
	}

	return false;
}

/*
 *	TransactionIdIsCurrentTransactionId
 *
 *	During bootstrap, we cheat and say "it's not my transaction ID" even though
 *	it is.	Along with transam.c's cheat to say that the bootstrap XID is
 *	already committed, this causes the tqual.c routines to see previously
 *	inserted tuples as committed, which is what we need during bootstrap.
 */
bool
TransactionIdIsCurrentTransactionId(TransactionId xid)
{
	TransactionState s = CurrentTransactionState;

	if (AMI_OVERRIDE)
	{
		Assert(xid == BootstrapTransactionId);
		return false;
	}

	return TransactionIdEquals(xid, s->transactionIdData);
}

/*
 * TransactionIdIsKnownCompleted
 *		True iff transaction associated with the identifier is currently
 *		known to have either committed or aborted.
 *
 * This does NOT look into pg_clog but merely probes our local cache
 * (and so it's not named TransactionIdDidComplete, which would be the
 * appropriate name for a function that worked that way).  The intended
 * use is just to short-circuit TransactionIdIsInProgress calls when doing
 * repeated tqual.c checks for the same XID.  If this isn't extremely fast
 * then it will be counterproductive.
 *
 * Note:
 *		Assumes transaction identifier is valid.
 */
bool
TransactionIdIsKnownCompleted(TransactionId transactionId)
{
	if (TransactionIdEquals(transactionId, cachedFetchXid))
	{
#ifdef PGXC
		syncGXID_GTM((GlobalTransactionId)transactionId);
#endif
		/* If it's in the cache at all, it must be completed. */
		return true;
	}

	return false;
}

/*
 *		XactLockTableWait
 *
 * Wait for the specified transaction to commit or abort.  If an operation
 * is specified, an error context callback is set up.  If 'oper' is passed as
 * None, no error context callback is set up.
 *
 * Note that this does the right thing for subtransactions: if we wait on a
 * subtransaction, we will exit as soon as it aborts or its top parent commits.
 * It takes some extra work to ensure this, because to save on shared memory
 * the XID lock of a subtransaction is released when it ends, whether
 * successfully or unsuccessfully.  So we have to check if it's "still running"
 * and if so wait for its parent.
 */
void
XactLockTableWait(TransactionId xid, Relation rel, ItemPointer ctid,
				  XLTW_Oper oper)
{
	LOCKTAG		tag;
	XactLockTableWaitInfo info;
	ErrorContextCallback callback;

	/*
	 * If an operation is specified, set up our verbose error context
	 * callback.
	 */
	if (oper != XLTW_None)
	{
		Assert(RelationIsValid(rel));
		Assert(ItemPointerIsValid(ctid));

		info.rel = rel;
		info.ctid = ctid;
		info.oper = oper;

		callback.callback = XactLockTableWaitErrorCb;
		callback.arg = &info;
		callback.previous = error_context_stack;
		error_context_stack = &callback;
	}

	for (;;)
	{
		Assert(TransactionIdIsValid(xid));
		Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));

		SET_LOCKTAG_TRANSACTION(tag, xid);

		(void) LockAcquire(&tag, ShareLock, false, false);

		LockRelease(&tag, ShareLock, false);

		if (!TransactionIdIsInProgress(xid))
			break;
		xid = SubTransGetParent(xid);
	}

	if (oper != XLTW_None)
		error_context_stack = callback.previous;
}

/*
 * Check if specified heap tuple was inserted by given
 * xaction/command and return
 *
 * - -1 if not
 * - 0	if there is no tuple at all
 * - 1	if yes
 */
int
XLogIsOwnerOfTuple(RelFileNode hnode, ItemPointer iptr,
				   TransactionId xid, CommandId cid)
{
	Relation	reln;
	Buffer		buffer;
	Page		page;
	ItemId		lp;
	HeapTupleHeader htup;

	reln = XLogOpenRelation(false, RM_HEAP_ID, hnode);
	if (!RelationIsValid(reln))
		return (0);

	buffer = ReadBuffer(reln, ItemPointerGetBlockNumber(iptr));
	if (!BufferIsValid(buffer))
		return (0);

	LockBuffer(buffer, BUFFER_LOCK_SHARE);
	page = (Page) BufferGetPage(buffer);
	if (PageIsNew((PageHeader) page) ||
		ItemPointerGetOffsetNumber(iptr) > PageGetMaxOffsetNumber(page))
	{
		UnlockAndReleaseBuffer(buffer);
		return (0);
	}
	lp = PageGetItemId(page, ItemPointerGetOffsetNumber(iptr));
	if (!ItemIdIsUsed(lp) || ItemIdDeleted(lp))
	{
		UnlockAndReleaseBuffer(buffer);
		return (0);
	}

	htup = (HeapTupleHeader) PageGetItem(page, lp);

	Assert(PageGetSUI(page) == ThisStartUpID);
	if (!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), xid) ||
		HeapTupleHeaderGetCmin(htup) != cid)
	{
		UnlockAndReleaseBuffer(buffer);
		return (-1);
	}

	UnlockAndReleaseBuffer(buffer);
	return (1);
}

/*
 *		XactLockTableWait
 *
 * Wait for the specified transaction to commit or abort.
 *
 * Note that this does the right thing for subtransactions: if we wait on a
 * subtransaction, we will exit as soon as it aborts or its top parent commits.
 * It takes some extra work to ensure this, because to save on shared memory
 * the XID lock of a subtransaction is released when it ends, whether
 * successfully or unsuccessfully.	So we have to check if it's "still running"
 * and if so wait for its parent.
 */
void
XactLockTableWait(TransactionId xid)
{
	LOCKTAG		tag;

	for (;;)
	{
		Assert(TransactionIdIsValid(xid));
		Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));

		SET_LOCKTAG_TRANSACTION(tag, xid);

		(void) LockAcquire(&tag, ShareLock, false, false);

		LockRelease(&tag, ShareLock, false);

		if (!TransactionIdIsInProgress(xid))
			break;
		xid = SubTransGetParent(xid);
	}
}

/*
 *		ConditionalXactLockTableWait
 *
 * As above, but only lock if we can get the lock without blocking.
 * Returns TRUE if the lock was acquired.
 */
bool
ConditionalXactLockTableWait(TransactionId xid)
{
	LOCKTAG		tag;

	for (;;)
	{
		Assert(TransactionIdIsValid(xid));
		Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));

		SET_LOCKTAG_TRANSACTION(tag, xid);

		if (LockAcquire(&tag, ShareLock, false, true) == LOCKACQUIRE_NOT_AVAIL)
			return false;

		LockRelease(&tag, ShareLock, false);

		if (!TransactionIdIsInProgress(xid))
			break;
		xid = SubTransGetParent(xid);
	}

	return true;
}

/*
 * Make sure that DistributedLog has room for a newly-allocated XID.
 *
 * NB: this is called while holding XidGenLock.  We want it to be very fast
 * most of the time; even when it's not so fast, no actual I/O need happen
 * unless we're forced to write out a dirty DistributedLog or xlog page
 * to make room in shared memory.
 */
void
DistributedLog_Extend(TransactionId newestXact)
{
	MIRRORED_LOCK_DECLARE;

	int			page;

	/*
	 * No work except at first XID of a page.  But beware: just after
	 * wraparound, the first XID of page zero is FirstNormalTransactionId.
	 */
	if (TransactionIdToEntry(newestXact) != 0 &&
		!TransactionIdEquals(newestXact, FirstNormalTransactionId))
		return;

	page = TransactionIdToPage(newestXact);

	elog((Debug_print_full_dtm ? LOG : DEBUG5),
		 "DistributedLog_Extend page %d",
		 page);

	MIRRORED_LOCK;

	LWLockAcquire(DistributedLogControlLock, LW_EXCLUSIVE);

	/* Zero the page and make an XLOG entry about it */
	DistributedLog_ZeroPage(page, true);

	LWLockRelease(DistributedLogControlLock);

	MIRRORED_UNLOCK;
	
	elog((Debug_print_full_dtm ? LOG : DEBUG5), 
		 "DistributedLog_Extend with newest local xid = %d to page = %d",
		 newestXact, page);
}

/*
 * PrescanPreparedTransactions
 *
 * Scan the pg_twophase directory and determine the range of valid XIDs
 * present.  This is run during database startup, after we have completed
 * reading WAL.  ShmemVariableCache->nextXid has been set to one more than
 * the highest XID for which evidence exists in WAL.
 *
 * We throw away any prepared xacts with main XID beyond nextXid --- if any
 * are present, it suggests that the DBA has done a PITR recovery to an
 * earlier point in time without cleaning out pg_twophase.	We dare not
 * try to recover such prepared xacts since they likely depend on database
 * state that doesn't exist now.
 *
 * However, we will advance nextXid beyond any subxact XIDs belonging to
 * valid prepared xacts.  We need to do this since subxact commit doesn't
 * write a WAL entry, and so there might be no evidence in WAL of those
 * subxact XIDs.
 *
 * Our other responsibility is to determine and return the oldest valid XID
 * among the prepared xacts (if none, return ShmemVariableCache->nextXid).
 * This is needed to synchronize pg_subtrans startup properly.
 */
TransactionId
PrescanPreparedTransactions(void)
{
	TransactionId origNextXid = ShmemVariableCache->nextXid;
	TransactionId result = origNextXid;
	DIR		   *cldir;
	struct dirent *clde;

	cldir = AllocateDir(TWOPHASE_DIR);
	while ((clde = ReadDir(cldir, TWOPHASE_DIR)) != NULL)
	{
		if (strlen(clde->d_name) == 8 &&
			strspn(clde->d_name, "0123456789ABCDEF") == 8)
		{
			TransactionId xid;
			char	   *buf;
			TwoPhaseFileHeader *hdr;
			TransactionId *subxids;
			int			i;

			xid = (TransactionId) strtoul(clde->d_name, NULL, 16);

			/* Reject XID if too new */
			if (TransactionIdFollowsOrEquals(xid, origNextXid))
			{
				ereport(WARNING,
						(errmsg("removing future two-phase state file \"%s\"",
								clde->d_name)));
				RemoveTwoPhaseFile(xid, true);
				continue;
			}

			/*
			 * Note: we can't check if already processed because clog
			 * subsystem isn't up yet.
			 */

			/* Read and validate file */
			buf = ReadTwoPhaseFile(xid);
			if (buf == NULL)
			{
				ereport(WARNING,
					  (errmsg("removing corrupt two-phase state file \"%s\"",
							  clde->d_name)));
				RemoveTwoPhaseFile(xid, true);
				continue;
			}

			/* Deconstruct header */
			hdr = (TwoPhaseFileHeader *) buf;
			if (!TransactionIdEquals(hdr->xid, xid))
			{
				ereport(WARNING,
					  (errmsg("removing corrupt two-phase state file \"%s\"",
							  clde->d_name)));
				RemoveTwoPhaseFile(xid, true);
				pfree(buf);
				continue;
			}

			/*
			 * OK, we think this file is valid.  Incorporate xid into the
			 * running-minimum result.
			 */
			if (TransactionIdPrecedes(xid, result))
				result = xid;

			/*
			 * Examine subtransaction XIDs ... they should all follow main
			 * XID, and they may force us to advance nextXid.
			 */
			subxids = (TransactionId *)
				(buf + MAXALIGN(sizeof(TwoPhaseFileHeader)));
			for (i = 0; i < hdr->nsubxacts; i++)
			{
				TransactionId subxid = subxids[i];

//.........这里部分代码省略.........

//.........这里部分代码省略.........
		{
			/* We are satisfying it with an unused buffer */
		}

		/* Now the found B1 CDB gets the buffer and is moved to T2 */
		cdb_found->buf_id = buf->buf_id;
		STRAT_LIST_REMOVE(cdb_found);
		STRAT_MRU_INSERT(cdb_found, STRAT_LIST_T2);
	}
	else
	{
		/*
		 * This was a complete cache miss, so we need to create a new CDB.
		 * We use a free one if available, else reclaim the tail end of B1.
		 */
		if (StrategyControl->listUnusedCDB >= 0)
		{
			cdb_found = &StrategyCDB[StrategyControl->listUnusedCDB];
			StrategyControl->listUnusedCDB = cdb_found->next;
		}
		else
		{
			/* Can't fail because we have more CDBs than buffers... */
			if (B1_LENGTH == 0)
				elog(PANIC, "StrategyReplaceBuffer: out of CDBs");
			cdb_found = &StrategyCDB[StrategyControl->listHead[STRAT_LIST_B1]];

			BufTableDelete(&(cdb_found->buf_tag));
			STRAT_LIST_REMOVE(cdb_found);
		}

		/* Set the CDB's buf_tag and insert it into the hash table */
		cdb_found->buf_tag = *newTag;
		BufTableInsert(&(cdb_found->buf_tag), (cdb_found - StrategyCDB));

		if (cdb_replace_index >= 0)
		{
			/*
			 * The buffer was formerly in a T list, move its CDB to the
			 * appropriate list: B1 if T1, else discard it, as above
			 */
			cdb_replace = &StrategyCDB[cdb_replace_index];

			Assert(cdb_replace->list == STRAT_LIST_T1 ||
				   cdb_replace->list == STRAT_LIST_T2);
			Assert(cdb_replace->buf_id == buf->buf_id);
			Assert(BUFFERTAGS_EQUAL(cdb_replace->buf_tag, buf->tag));

			if (cdb_replace->list == STRAT_LIST_T1)
			{
				STRAT_LIST_REMOVE(cdb_replace);
				STRAT_MRU_INSERT(cdb_replace, STRAT_LIST_B1);
			}
			else
			{
				BufTableDelete(&(cdb_replace->buf_tag));
				STRAT_LIST_REMOVE(cdb_replace);
				cdb_replace->next = StrategyControl->listUnusedCDB;
				StrategyControl->listUnusedCDB = cdb_replace_index;
			}
			/* And clear its block reference */
			cdb_replace->buf_id = -1;
		}
		else
		{
			/* We are satisfying it with an unused buffer */
		}

		/* Assign the buffer id to the new CDB */
		cdb_found->buf_id = buf->buf_id;

		/*
		 * Specialized VACUUM optimization. If this complete cache miss
		 * happened because vacuum needed the page, we place it at the LRU
		 * position of T1; normally it goes at the MRU position.
		 */
		if (strategy_hint_vacuum)
		{
			if (TransactionIdEquals(strategy_vacuum_xid,
									GetTopTransactionId()))
				STRAT_LRU_INSERT(cdb_found, STRAT_LIST_T1);
			else
			{
				/* VACUUM must have been aborted by error, reset flag */
				strategy_hint_vacuum = false;
				STRAT_MRU_INSERT(cdb_found, STRAT_LIST_T1);
			}
		}
		else
			STRAT_MRU_INSERT(cdb_found, STRAT_LIST_T1);

		/*
		 * Remember the Xid when this buffer went onto T1 to avoid a
		 * single UPDATE promoting a newcomer straight into T2. Also
		 * remember if it was loaded for VACUUM.
		 */
		cdb_found->t1_xid = GetTopTransactionId();
		cdb_found->t1_vacuum = strategy_hint_vacuum;
	}
}

/*
 * For all items in this page, find their respective root line pointers.
 * If item k is part of a HOT-chain with root at item j, then we set
 * root_offsets[k - 1] = j.
 *
 * The passed-in root_offsets array must have MaxHeapTuplesPerPage entries.
 * We zero out all unused entries.
 *
 * The function must be called with at least share lock on the buffer, to
 * prevent concurrent prune operations.
 *
 * Note: The information collected here is valid only as long as the caller
 * holds a pin on the buffer. Once pin is released, a tuple might be pruned
 * and reused by a completely unrelated tuple.
 */
void
heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
{
	OffsetNumber offnum,
				maxoff;

	MemSet(root_offsets, 0, MaxHeapTuplesPerPage * sizeof(OffsetNumber));

	maxoff = PageGetMaxOffsetNumber(page);
	for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
	{
		ItemId		lp = PageGetItemId(page, offnum);
		HeapTupleHeader htup;
		OffsetNumber nextoffnum;
		TransactionId priorXmax;

		/* skip unused and dead items */
		if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
			continue;

		if (ItemIdIsNormal(lp))
		{
			htup = (HeapTupleHeader) PageGetItem(page, lp);

			/*
			 * Check if this tuple is part of a HOT-chain rooted at some other
			 * tuple. If so, skip it for now; we'll process it when we find
			 * its root.
			 */
			if (HeapTupleHeaderIsHeapOnly(htup))
				continue;

			/*
			 * This is either a plain tuple or the root of a HOT-chain.
			 * Remember it in the mapping.
			 */
			root_offsets[offnum - 1] = offnum;

			/* If it's not the start of a HOT-chain, we're done with it */
			if (!HeapTupleHeaderIsHotUpdated(htup))
				continue;

			/* Set up to scan the HOT-chain */
			nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
			priorXmax = HeapTupleHeaderGetXmax(htup);
		}
		else
		{
			/* Must be a redirect item. We do not set its root_offsets entry */
			Assert(ItemIdIsRedirected(lp));
			/* Set up to scan the HOT-chain */
			nextoffnum = ItemIdGetRedirect(lp);
			priorXmax = InvalidTransactionId;
		}

		/*
		 * Now follow the HOT-chain and collect other tuples in the chain.
		 *
		 * Note: Even though this is a nested loop, the complexity of the
		 * function is O(N) because a tuple in the page should be visited not
		 * more than twice, once in the outer loop and once in HOT-chain
		 * chases.
		 */
		for (;;)
		{
			lp = PageGetItemId(page, nextoffnum);

			/* Check for broken chains */
			if (!ItemIdIsNormal(lp))
				break;

			htup = (HeapTupleHeader) PageGetItem(page, lp);

			if (TransactionIdIsValid(priorXmax) &&
				!TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
				break;

			/* Remember the root line pointer for this item */
			root_offsets[nextoffnum - 1] = offnum;

			/* Advance to next chain member, if any */
			if (!HeapTupleHeaderIsHotUpdated(htup))
				break;

			nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
//.........这里部分代码省略.........

/*
 * XidInMVCCSnapshot
 *		Is the given XID still-in-progress according to the snapshot?
 *
 * Note: GetSnapshotData never stores either top xid or subxids of our own
 * backend into a snapshot, so these xids will not be reported as "running"
 * by this function.  This is OK for current uses, because we actually only
 * apply this for known-committed XIDs.
 */
static bool
XidInMVCCSnapshot(TransactionId xid, Snapshot snapshot)
{
	uint32		i;

	/*
	 * Make a quick range check to eliminate most XIDs without looking at the
	 * xip arrays.  Note that this is OK even if we convert a subxact XID to
	 * its parent below, because a subxact with XID < xmin has surely also got
	 * a parent with XID < xmin, while one with XID >= xmax must belong to a
	 * parent that was not yet committed at the time of this snapshot.
	 */

	/* Any xid < xmin is not in-progress */
	if (TransactionIdPrecedes(xid, snapshot->xmin))
		return false;
	/* Any xid >= xmax is in-progress */
	if (TransactionIdFollowsOrEquals(xid, snapshot->xmax))
		return true;

	/*
	 * Snapshot information is stored slightly differently in snapshots taken
	 * during recovery.
	 */
	if (!snapshot->takenDuringRecovery)
	{
		/*
		 * If the snapshot contains full subxact data, the fastest way to
		 * check things is just to compare the given XID against both subxact
		 * XIDs and top-level XIDs.  If the snapshot overflowed, we have to
		 * use pg_subtrans to convert a subxact XID to its parent XID, but
		 * then we need only look at top-level XIDs not subxacts.
		 */
		if (!snapshot->suboverflowed)
		{
			/* full data, so search subxip */
			int32		j;

			for (j = 0; j < snapshot->subxcnt; j++)
			{
				if (TransactionIdEquals(xid, snapshot->subxip[j]))
					return true;
			}

			/* not there, fall through to search xip[] */
		}
		else
		{
			/* overflowed, so convert xid to top-level */
			xid = SubTransGetTopmostTransaction(xid);

			/*
			 * If xid was indeed a subxact, we might now have an xid < xmin,
			 * so recheck to avoid an array scan.  No point in rechecking
			 * xmax.
			 */
			if (TransactionIdPrecedes(xid, snapshot->xmin))
				return false;
		}

		for (i = 0; i < snapshot->xcnt; i++)
		{
			if (TransactionIdEquals(xid, snapshot->xip[i]))
				return true;
		}
	}
	else
	{
		int32		j;

		/*
		 * In recovery we store all xids in the subxact array because it is by
		 * far the bigger array, and we mostly don't know which xids are
		 * top-level and which are subxacts. The xip array is empty.
		 *
		 * We start by searching subtrans, if we overflowed.
		 */
		if (snapshot->suboverflowed)
		{
			/* overflowed, so convert xid to top-level */
			xid = SubTransGetTopmostTransaction(xid);

			/*
			 * If xid was indeed a subxact, we might now have an xid < xmin,
			 * so recheck to avoid an array scan.  No point in rechecking
			 * xmax.
			 */
			if (TransactionIdPrecedes(xid, snapshot->xmin))
				return false;
		}

//.........这里部分代码省略.........