C++ UnlockReleaseBuffer函数代码示例

static void
btree_xlog_vacuum(XLogReaderState *record)
{
	XLogRecPtr	lsn = record->EndRecPtr;
	xl_btree_vacuum *xlrec = (xl_btree_vacuum *) XLogRecGetData(record);
	Buffer		buffer;
	Page		page;
	BTPageOpaque opaque;

	/*
	 * If queries might be active then we need to ensure every leaf page is
	 * unpinned between the lastBlockVacuumed and the current block, if there
	 * are any.  This prevents replay of the VACUUM from reaching the stage of
	 * removing heap tuples while there could still be indexscans "in flight"
	 * to those particular tuples for those scans which could be confused by
	 * finding new___ tuples at the old TID locations (see nbtree/README).
	 *
	 * It might be worth checking if there are actually any backends running;
	 * if not, we could just skip this.
	 *
	 * Since VACUUM can visit leaf pages out-of-order, it might issue records
	 * with lastBlockVacuumed >= block; that's not an error, it just means
	 * nothing to do now.
	 *
	 * Note: since we touch all pages in the range, we will lock non-leaf
	 * pages, and also any empty (all-zero) pages that may be in the index. It
	 * doesn't seem worth the complexity to avoid that.  But it's important
	 * that HotStandbyActiveInReplay() will not return true if the database
	 * isn't yet consistent; so we need not fear reading still-corrupt blocks
	 * here during crash recovery.
	 */
	if (HotStandbyActiveInReplay())
	{
		RelFileNode thisrnode;
		BlockNumber thisblkno;
		BlockNumber blkno;

		XLogRecGetBlockTag(record, 0, &thisrnode, NULL, &thisblkno);

		for (blkno = xlrec->lastBlockVacuumed + 1; blkno < thisblkno; blkno++)
		{
			/*
			 * We use RBM_NORMAL_NO_LOG mode because it's not an error
			 * condition to see all-zero pages.  The original btvacuumpage
			 * scan would have skipped over all-zero pages, noting them in FSM
			 * but not bothering to initialize them just yet; so we mustn't
			 * throw an error here.  (We could skip acquiring the cleanup lock
			 * if PageIsNew, but it's probably not worth the cycles to test.)
			 *
			 * XXX we don't actually need to read the block, we just need to
			 * confirm it is unpinned. If we had a special call into the
			 * buffer manager we could optimise this so that if the block is
			 * not in shared_buffers we confirm it as unpinned.
			 */
			buffer = XLogReadBufferExtended(thisrnode, MAIN_FORKNUM, blkno,
											RBM_NORMAL_NO_LOG);
			if (BufferIsValid(buffer))
			{
				LockBufferForCleanup(buffer);
				UnlockReleaseBuffer(buffer);
			}
		}
	}

	/*
	 * Like in btvacuumpage(), we need to take a cleanup lock on every leaf
	 * page. See nbtree/README for details.
	 */
	if (XLogReadBufferForRedoExtended(record, 0, RBM_NORMAL, true, &buffer)
		== BLK_NEEDS_REDO)
	{
		char	   *ptr;
		Size		len;

		ptr = XLogRecGetBlockData(record, 0, &len);

		page = (Page) BufferGetPage(buffer);

		if (len > 0)
		{
			OffsetNumber *unused;
			OffsetNumber *unend;

			unused = (OffsetNumber *) ptr;
			unend = (OffsetNumber *) ((char *) ptr + len);

			if ((unend - unused) > 0)
				PageIndexMultiDelete(page, unused, unend - unused);
		}

		/*
		 * Mark the page as not containing any LP_DEAD items --- see comments
		 * in _bt_delitems_vacuum().
		 */
		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
		opaque->btpo_flags &= ~BTP_HAS_GARBAGE;

		PageSetLSN(page, lsn);
		MarkBufferDirty(buffer);
	}
//.........这里部分代码省略.........

static void
spgRedoMoveLeafs(XLogRecPtr lsn, XLogRecord *record)
{
	char	   *ptr = XLogRecGetData(record);
	spgxlogMoveLeafs *xldata = (spgxlogMoveLeafs *) ptr;
	SpGistState state;
	OffsetNumber *toDelete;
	OffsetNumber *toInsert;
	int			nInsert;
	Buffer		buffer;
	Page		page;

	fillFakeState(&state, xldata->stateSrc);

	nInsert = xldata->replaceDead ? 1 : xldata->nMoves + 1;

	ptr += MAXALIGN(sizeof(spgxlogMoveLeafs));
	toDelete = (OffsetNumber *) ptr;
	ptr += MAXALIGN(sizeof(OffsetNumber) * xldata->nMoves);
	toInsert = (OffsetNumber *) ptr;
	ptr += MAXALIGN(sizeof(OffsetNumber) * nInsert);

	/* now ptr points to the list of leaf tuples */

	/* Insert tuples on the dest page (do first, so redirect is valid) */
	if (!(record->xl_info & XLR_BKP_BLOCK_2))
	{
		buffer = XLogReadBuffer(xldata->node, xldata->blknoDst,
								xldata->newPage);
		if (BufferIsValid(buffer))
		{
			page = BufferGetPage(buffer);

			if (xldata->newPage)
				SpGistInitBuffer(buffer, SPGIST_LEAF);

			if (!XLByteLE(lsn, PageGetLSN(page)))
			{
				int			i;

				for (i = 0; i < nInsert; i++)
				{
					SpGistLeafTuple lt = (SpGistLeafTuple) ptr;

					addOrReplaceTuple(page, (Item) lt, lt->size, toInsert[i]);
					ptr += lt->size;
				}

				PageSetLSN(page, lsn);
				PageSetTLI(page, ThisTimeLineID);
				MarkBufferDirty(buffer);
			}
			UnlockReleaseBuffer(buffer);
		}
	}

	/* Delete tuples from the source page, inserting a redirection pointer */
	if (!(record->xl_info & XLR_BKP_BLOCK_1))
	{
		buffer = XLogReadBuffer(xldata->node, xldata->blknoSrc, false);
		if (BufferIsValid(buffer))
		{
			page = BufferGetPage(buffer);
			if (!XLByteLE(lsn, PageGetLSN(page)))
			{
				spgPageIndexMultiDelete(&state, page, toDelete, xldata->nMoves,
										state.isBuild ? SPGIST_PLACEHOLDER : SPGIST_REDIRECT,
										SPGIST_PLACEHOLDER,
										xldata->blknoDst,
										toInsert[nInsert - 1]);

				PageSetLSN(page, lsn);
				PageSetTLI(page, ThisTimeLineID);
				MarkBufferDirty(buffer);
			}
			UnlockReleaseBuffer(buffer);
		}
	}

	/* And update the parent downlink */
	if (!(record->xl_info & XLR_BKP_BLOCK_3))
	{
		buffer = XLogReadBuffer(xldata->node, xldata->blknoParent, false);
		if (BufferIsValid(buffer))
		{
			page = BufferGetPage(buffer);
			if (!XLByteLE(lsn, PageGetLSN(page)))
			{
				SpGistInnerTuple tuple;

				tuple = (SpGistInnerTuple) PageGetItem(page,
													   PageGetItemId(page, xldata->offnumParent));

				spgUpdateNodeLink(tuple, xldata->nodeI,
								  xldata->blknoDst, toInsert[nInsert - 1]);

				PageSetLSN(page, lsn);
				PageSetTLI(page, ThisTimeLineID);
				MarkBufferDirty(buffer);
			}
//.........这里部分代码省略.........

static void
spgRedoSplitTuple(XLogRecPtr lsn, XLogRecord *record)
{
	char	   *ptr = XLogRecGetData(record);
	spgxlogSplitTuple *xldata = (spgxlogSplitTuple *) ptr;
	SpGistInnerTuple prefixTuple;
	SpGistInnerTuple postfixTuple;
	Buffer		buffer;
	Page		page;

	/* we assume this is adequately aligned */
	ptr += sizeof(spgxlogSplitTuple);
	prefixTuple = (SpGistInnerTuple) ptr;
	ptr += prefixTuple->size;
	postfixTuple = (SpGistInnerTuple) ptr;

	/* insert postfix tuple first to avoid dangling link */
	if (xldata->blknoPostfix != xldata->blknoPrefix &&
		!(record->xl_info & XLR_BKP_BLOCK_2))
	{
		buffer = XLogReadBuffer(xldata->node, xldata->blknoPostfix,
								xldata->newPage);
		if (BufferIsValid(buffer))
		{
			page = BufferGetPage(buffer);

			if (xldata->newPage)
				SpGistInitBuffer(buffer, 0);

			if (!XLByteLE(lsn, PageGetLSN(page)))
			{
				addOrReplaceTuple(page, (Item) postfixTuple,
								  postfixTuple->size, xldata->offnumPostfix);

				PageSetLSN(page, lsn);
				PageSetTLI(page, ThisTimeLineID);
				MarkBufferDirty(buffer);
			}
			UnlockReleaseBuffer(buffer);
		}
	}

	/* now handle the original page */
	if (!(record->xl_info & XLR_BKP_BLOCK_1))
	{
		buffer = XLogReadBuffer(xldata->node, xldata->blknoPrefix, false);
		if (BufferIsValid(buffer))
		{
			page = BufferGetPage(buffer);
			if (!XLByteLE(lsn, PageGetLSN(page)))
			{
				PageIndexTupleDelete(page, xldata->offnumPrefix);
				if (PageAddItem(page, (Item) prefixTuple, prefixTuple->size,
								xldata->offnumPrefix, false, false) != xldata->offnumPrefix)
					elog(ERROR, "failed to add item of size %u to SPGiST index page",
						 prefixTuple->size);

				if (xldata->blknoPostfix == xldata->blknoPrefix)
					addOrReplaceTuple(page, (Item) postfixTuple,
									  postfixTuple->size,
									  xldata->offnumPostfix);

				PageSetLSN(page, lsn);
				PageSetTLI(page, ThisTimeLineID);
				MarkBufferDirty(buffer);
			}
			UnlockReleaseBuffer(buffer);
		}
	}
}

static void
gistRedoPageSplitRecord(XLogRecPtr lsn, XLogRecord *record)
{
	gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
	PageSplitRecord xlrec;
	Buffer		firstbuffer = InvalidBuffer;
	Buffer		buffer;
	Page		page;
	int			i;
	bool		isrootsplit = false;

	decodePageSplitRecord(&xlrec, record);

	/*
	 * We must hold lock on the first-listed page throughout the action,
	 * including while updating the left child page (if any).  We can unlock
	 * remaining pages in the list as soon as they've been written, because
	 * there is no path for concurrent queries to reach those pages without
	 * first visiting the first-listed page.
	 */

	/* loop around all pages */
	for (i = 0; i < xlrec.data->npage; i++)
	{
		NewPage    *newpage = xlrec.page + i;
		int			flags;

		if (newpage->header->blkno == GIST_ROOT_BLKNO)
		{
			Assert(i == 0);
			isrootsplit = true;
		}

		buffer = XLogReadBuffer(xlrec.data->node, newpage->header->blkno, true);
		Assert(BufferIsValid(buffer));
		page = (Page) BufferGetPage(buffer);

		/* ok, clear buffer */
		if (xlrec.data->origleaf && newpage->header->blkno != GIST_ROOT_BLKNO)
			flags = F_LEAF;
		else
			flags = 0;
		GISTInitBuffer(buffer, flags);

		/* and fill it */
		gistfillbuffer(page, newpage->itup, newpage->header->num, FirstOffsetNumber);

		if (newpage->header->blkno == GIST_ROOT_BLKNO)
		{
			GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
			GistPageSetNSN(page, xldata->orignsn);
			GistClearFollowRight(page);
		}
		else
		{
			if (i < xlrec.data->npage - 1)
				GistPageGetOpaque(page)->rightlink = xlrec.page[i + 1].header->blkno;
			else
				GistPageGetOpaque(page)->rightlink = xldata->origrlink;
			GistPageSetNSN(page, xldata->orignsn);
			if (i < xlrec.data->npage - 1 && !isrootsplit &&
				xldata->markfollowright)
				GistMarkFollowRight(page);
			else
				GistClearFollowRight(page);
		}

		PageSetLSN(page, lsn);
		MarkBufferDirty(buffer);

		if (i == 0)
			firstbuffer = buffer;
		else
			UnlockReleaseBuffer(buffer);
	}

	/* Fix follow-right data on left child page, if any */
	if (BlockNumberIsValid(xldata->leftchild))
		gistRedoClearFollowRight(lsn, record, 0,
								 xldata->node, xldata->leftchild);

	/* Finally, release lock on the first page */
	UnlockReleaseBuffer(firstbuffer);
}

/*
 * brinbuild() -- build a new BRIN index.
 */
IndexBuildResult *
brinbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
	IndexBuildResult *result;
	double		reltuples;
	double		idxtuples;
	BrinRevmap *revmap;
	BrinBuildState *state;
	Buffer		meta;
	BlockNumber pagesPerRange;

	/*
	 * We expect to be called exactly once for any index relation.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/*
	 * Critical section not required, because on error the creation of the
	 * whole relation will be rolled back.
	 */

	meta = ReadBuffer(index, P_NEW);
	Assert(BufferGetBlockNumber(meta) == BRIN_METAPAGE_BLKNO);
	LockBuffer(meta, BUFFER_LOCK_EXCLUSIVE);

	brin_metapage_init(BufferGetPage(meta), BrinGetPagesPerRange(index),
					   BRIN_CURRENT_VERSION);
	MarkBufferDirty(meta);

	if (RelationNeedsWAL(index))
	{
		xl_brin_createidx xlrec;
		XLogRecPtr	recptr;
		Page		page;

		xlrec.version = BRIN_CURRENT_VERSION;
		xlrec.pagesPerRange = BrinGetPagesPerRange(index);

		XLogBeginInsert();
		XLogRegisterData((char *) &xlrec, SizeOfBrinCreateIdx);
		XLogRegisterBuffer(0, meta, REGBUF_WILL_INIT);

		recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_CREATE_INDEX);

		page = BufferGetPage(meta);
		PageSetLSN(page, recptr);
	}

	UnlockReleaseBuffer(meta);

	/*
	 * Initialize our state, including the deformed tuple state.
	 */
	revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
	state = initialize_brin_buildstate(index, revmap, pagesPerRange);

	/*
	 * Now scan the relation.  No syncscan allowed here because we want the
	 * heap blocks in physical order.
	 */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo, false,
								   brinbuildCallback, (void *) state);

	/* process the final batch */
	form_and_insert_tuple(state);

	/* release resources */
	idxtuples = state->bs_numtuples;
	brinRevmapTerminate(state->bs_rmAccess);
	terminate_brin_buildstate(state);

	/*
	 * Return statistics
	 */
	result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));

	result->heap_tuples = reltuples;
	result->index_tuples = idxtuples;

	return result;
}

/*
 * Insert new tuple to the bloom index.
 */
bool
blinsert(Relation index, Datum *values, bool *isnull,
		 ItemPointer ht_ctid, Relation heapRel,
		 IndexUniqueCheck checkUnique,
		 IndexInfo *indexInfo)
{
	BloomState	blstate;
	BloomTuple *itup;
	MemoryContext oldCtx;
	MemoryContext insertCtx;
	BloomMetaPageData *metaData;
	Buffer		buffer,
				metaBuffer;
	Page		page,
				metaPage;
	BlockNumber blkno = InvalidBlockNumber;
	OffsetNumber nStart;
	GenericXLogState *state;

	insertCtx = AllocSetContextCreate(CurrentMemoryContext,
									  "Bloom insert temporary context",
									  ALLOCSET_DEFAULT_SIZES);

	oldCtx = MemoryContextSwitchTo(insertCtx);

	initBloomState(&blstate, index);
	itup = BloomFormTuple(&blstate, ht_ctid, values, isnull);

	/*
	 * At first, try to insert new tuple to the first page in notFullPage
	 * array.  If successful, we don't need to modify the meta page.
	 */
	metaBuffer = ReadBuffer(index, BLOOM_METAPAGE_BLKNO);
	LockBuffer(metaBuffer, BUFFER_LOCK_SHARE);
	metaData = BloomPageGetMeta(BufferGetPage(metaBuffer));

	if (metaData->nEnd > metaData->nStart)
	{
		Page		page;

		blkno = metaData->notFullPage[metaData->nStart];
		Assert(blkno != InvalidBlockNumber);

		/* Don't hold metabuffer lock while doing insert */
		LockBuffer(metaBuffer, BUFFER_LOCK_UNLOCK);

		buffer = ReadBuffer(index, blkno);
		LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

		state = GenericXLogStart(index);
		page = GenericXLogRegisterBuffer(state, buffer, 0);

		/*
		 * We might have found a page that was recently deleted by VACUUM.  If
		 * so, we can reuse it, but we must reinitialize it.
		 */
		if (PageIsNew(page) || BloomPageIsDeleted(page))
			BloomInitPage(page, 0);

		if (BloomPageAddItem(&blstate, page, itup))
		{
			/* Success!  Apply the change, clean up, and exit */
			GenericXLogFinish(state);
			UnlockReleaseBuffer(buffer);
			ReleaseBuffer(metaBuffer);
			MemoryContextSwitchTo(oldCtx);
			MemoryContextDelete(insertCtx);
			return false;
		}

		/* Didn't fit, must try other pages */
		GenericXLogAbort(state);
		UnlockReleaseBuffer(buffer);
	}
	else
	{
		/* No entries in notFullPage */
		LockBuffer(metaBuffer, BUFFER_LOCK_UNLOCK);
	}

	/*
	 * Try other pages in notFullPage array.  We will have to change nStart in
	 * metapage.  Thus, grab exclusive lock on metapage.
	 */
	LockBuffer(metaBuffer, BUFFER_LOCK_EXCLUSIVE);

	/* nStart might have changed while we didn't have lock */
	nStart = metaData->nStart;

	/* Skip first page if we already tried it above */
	if (nStart < metaData->nEnd &&
		blkno == metaData->notFullPage[nStart])
		nStart++;

	/*
	 * This loop iterates for each page we try from the notFullPage array, and
	 * will also initialize a GenericXLogState for the fallback case of having
//.........这里部分代码省略.........

/*
 * Get a buffer of the type and parity specified by flags, having at least
 * as much free space as indicated by needSpace.  We use the lastUsedPages
 * cache to assign the same buffer previously requested when possible.
 * The returned buffer is already pinned and exclusive-locked.
 *
 * *isNew is set true if the page was initialized here, false if it was
 * already valid.
 */
Buffer
SpGistGetBuffer(Relation index, int flags, int needSpace, bool *isNew)
{
	SpGistCache *cache = spgGetCache(index);
	SpGistLastUsedPage *lup;

	/* Bail out if even an empty page wouldn't meet the demand */
	if (needSpace > SPGIST_PAGE_CAPACITY)
		elog(ERROR, "desired SPGiST tuple size is too big");

	/*
	 * If possible, increase the space request to include relation's
	 * fillfactor.  This ensures that when we add unrelated tuples to a page,
	 * we try to keep 100-fillfactor% available for adding tuples that are
	 * related to the ones already on it.  But fillfactor mustn't cause an
	 * error for requests that would otherwise be legal.
	 */
	needSpace += RelationGetTargetPageFreeSpace(index,
												SPGIST_DEFAULT_FILLFACTOR);
	needSpace = Min(needSpace, SPGIST_PAGE_CAPACITY);

	/* Get the cache entry for this flags setting */
	lup = GET_LUP(cache, flags);

	/* If we have nothing cached, just turn it over to allocNewBuffer */
	if (lup->blkno == InvalidBlockNumber)
	{
		*isNew = true;
		return allocNewBuffer(index, flags);
	}

	/* fixed pages should never be in cache */
	Assert(!SpGistBlockIsFixed(lup->blkno));

	/* If cached freeSpace isn't enough, don't bother looking at the page */
	if (lup->freeSpace >= needSpace)
	{
		Buffer		buffer;
		Page		page;

		buffer = ReadBuffer(index, lup->blkno);

		if (!ConditionalLockBuffer(buffer))
		{
			/*
			 * buffer is locked by another process, so return a new buffer
			 */
			ReleaseBuffer(buffer);
			*isNew = true;
			return allocNewBuffer(index, flags);
		}

		page = BufferGetPage(buffer);

		if (PageIsNew(page) || SpGistPageIsDeleted(page) || PageIsEmpty(page))
		{
			/* OK to initialize the page */
			uint16		pageflags = 0;

			if (GBUF_REQ_LEAF(flags))
				pageflags |= SPGIST_LEAF;
			if (GBUF_REQ_NULLS(flags))
				pageflags |= SPGIST_NULLS;
			SpGistInitBuffer(buffer, pageflags);
			lup->freeSpace = PageGetExactFreeSpace(page) - needSpace;
			*isNew = true;
			return buffer;
		}

		/*
		 * Check that page is of right type and has enough space.  We must
		 * recheck this since our cache isn't necessarily up to date.
		 */
		if ((GBUF_REQ_LEAF(flags) ? SpGistPageIsLeaf(page) : !SpGistPageIsLeaf(page)) &&
			(GBUF_REQ_NULLS(flags) ? SpGistPageStoresNulls(page) : !SpGistPageStoresNulls(page)))
		{
			int			freeSpace = PageGetExactFreeSpace(page);

			if (freeSpace >= needSpace)
			{
				/* Success, update freespace info and return the buffer */
				lup->freeSpace = freeSpace - needSpace;
				*isNew = false;
				return buffer;
			}
		}

		/*
		 * fallback to allocation of new buffer
		 */
		UnlockReleaseBuffer(buffer);
//.........这里部分代码省略.........

/*
 * Bulk deletion of all index entries pointing to a set of heap tuples and
 * check invalid tuples left after upgrade.
 * The set of target tuples is specified via a callback routine that tells
 * whether any given heap tuple (identified by ItemPointer) is being deleted.
 *
 * Result: a palloc'd struct containing statistical info for VACUUM displays.
 */
IndexBulkDeleteResult *
gistbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
			   IndexBulkDeleteCallback callback, void *callback_state)
{
	Relation	rel = info->index;
	GistBDItem *stack,
			   *ptr;

	/* first time through? */
	if (stats == NULL)
		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
	/* we'll re-count the tuples each time */
	stats->estimated_count = false;
	stats->num_index_tuples = 0;

	stack = (GistBDItem *) palloc0(sizeof(GistBDItem));
	stack->blkno = GIST_ROOT_BLKNO;

	while (stack)
	{
		Buffer		buffer;
		Page		page;
		OffsetNumber i,
					maxoff;
		IndexTuple	idxtuple;
		ItemId		iid;

		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, stack->blkno,
									RBM_NORMAL, info->strategy);
		LockBuffer(buffer, GIST_SHARE);
		gistcheckpage(rel, buffer);
		page = (Page) BufferGetPage(buffer);

		if (GistPageIsLeaf(page))
		{
			OffsetNumber todelete[MaxOffsetNumber];
			int			ntodelete = 0;

			LockBuffer(buffer, GIST_UNLOCK);
			LockBuffer(buffer, GIST_EXCLUSIVE);

			page = (Page) BufferGetPage(buffer);
			if (stack->blkno == GIST_ROOT_BLKNO && !GistPageIsLeaf(page))
			{
				/* only the root can become non-leaf during relock */
				UnlockReleaseBuffer(buffer);
				/* one more check */
				continue;
			}

			/*
			 * check for split proceeded after look at parent, we should check
			 * it after relock
			 */
			pushStackIfSplited(page, stack);

			/*
			 * Remove deletable tuples from page
			 */

			maxoff = PageGetMaxOffsetNumber(page);

			for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
			{
				iid = PageGetItemId(page, i);
				idxtuple = (IndexTuple) PageGetItem(page, iid);

				if (callback(&(idxtuple->t_tid), callback_state))
					todelete[ntodelete++] = i;
				else
					stats->num_index_tuples += 1;
			}

			stats->tuples_removed += ntodelete;

			if (ntodelete)
			{
				START_CRIT_SECTION();

				MarkBufferDirty(buffer);

				PageIndexMultiDelete(page, todelete, ntodelete);
				GistMarkTuplesDeleted(page);

				if (RelationNeedsWAL(rel))
				{
					XLogRecPtr	recptr;

					recptr = gistXLogUpdate(rel->rd_node, buffer,
											todelete, ntodelete,
											NULL, 0, InvalidBuffer);
					PageSetLSN(page, recptr);
//.........这里部分代码省略.........

/*
 * VACUUM cleanup: update FSM
 */
IndexBulkDeleteResult *
gistvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
{
	Relation	rel = info->index;
	BlockNumber npages,
				blkno;
	BlockNumber totFreePages;
	bool		needLock;

	/* No-op in ANALYZE ONLY mode */
	if (info->analyze_only)
		return stats;

	/* Set up all-zero stats if gistbulkdelete wasn't called */
	if (stats == NULL)
	{
		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
		/* use heap's tuple count */
		stats->num_index_tuples = info->num_heap_tuples;
		stats->estimated_count = info->estimated_count;

		/*
		 * XXX the above is wrong if index is partial.  Would it be OK to just
		 * return NULL, or is there work we must do below?
		 */
	}

	/*
	 * Need lock unless it's local to this backend.
	 */
	needLock = !RELATION_IS_LOCAL(rel);

	/* try to find deleted pages */
	if (needLock)
		LockRelationForExtension(rel, ExclusiveLock);
	npages = RelationGetNumberOfBlocks(rel);
	if (needLock)
		UnlockRelationForExtension(rel, ExclusiveLock);

	totFreePages = 0;
	for (blkno = GIST_ROOT_BLKNO + 1; blkno < npages; blkno++)
	{
		Buffer		buffer;
		Page		page;

		vacuum_delay_point();

		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
									info->strategy);
		LockBuffer(buffer, GIST_SHARE);
		page = (Page) BufferGetPage(buffer);

		if (PageIsNew(page) || GistPageIsDeleted(page))
		{
			totFreePages++;
			RecordFreeIndexPage(rel, blkno);
		}
		UnlockReleaseBuffer(buffer);
	}

	/* Finally, vacuum the FSM */
	IndexFreeSpaceMapVacuum(info->index);

	/* return statistics */
	stats->pages_free = totFreePages;
	if (needLock)
		LockRelationForExtension(rel, ExclusiveLock);
	stats->num_pages = RelationGetNumberOfBlocks(rel);
	if (needLock)
		UnlockRelationForExtension(rel, ExclusiveLock);

	return stats;
}

/*
 * Rescan end pages to verify that they are (still) empty of tuples.
 *
 * Returns number of nondeletable pages (last nonempty page + 1).
 */
static BlockNumber
count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats)
{
	BlockNumber blkno;
	instr_time	starttime;
	instr_time	currenttime;
	instr_time	elapsed;

	/* Initialize the starttime if we check for conflicting lock requests */
	INSTR_TIME_SET_CURRENT(starttime);

	/* Strange coding of loop control is needed because blkno is unsigned */
	blkno = vacrelstats->rel_pages;
	while (blkno > vacrelstats->nonempty_pages)
	{
		Buffer		buf;
		Page		page;
		OffsetNumber offnum,
					maxoff;
		bool		hastup;

		/*
		 * Check if another process requests a lock on our relation. We are
		 * holding an AccessExclusiveLock here, so they will be waiting. We
		 * only do this in autovacuum_truncate_lock_check millisecond
		 * intervals, and we only check if that interval has elapsed once
		 * every 32 blocks to keep the number of system calls and actual
		 * shared lock table lookups to a minimum.
		 */
		if ((blkno % 32) == 0)
		{
			INSTR_TIME_SET_CURRENT(currenttime);
			elapsed = currenttime;
			INSTR_TIME_SUBTRACT(elapsed, starttime);
			if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
				>= AUTOVACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
			{
				if (LockHasWaitersRelation(onerel, AccessExclusiveLock))
				{
					ereport(elevel,
							(errmsg("\"%s\": suspending truncate "
									"due to conflicting lock request",
									RelationGetRelationName(onerel))));

					vacrelstats->lock_waiter_detected = true;
					return blkno;
				}
				starttime = currenttime;
			}
		}

		/*
		 * We don't insert a vacuum delay point here, because we have an
		 * exclusive lock on the table which we want to hold for as short a
		 * time as possible.  We still need to check for interrupts however.
		 */
		CHECK_FOR_INTERRUPTS();

		blkno--;

		buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
								 RBM_NORMAL, vac_strategy);

		/* In this phase we only need shared access to the buffer */
		LockBuffer(buf, BUFFER_LOCK_SHARE);

		page = BufferGetPage(buf);

		if (PageIsNew(page) || PageIsEmpty(page))
		{
			/* PageIsNew probably shouldn't happen... */
			UnlockReleaseBuffer(buf);
			continue;
		}

		hastup = false;
		maxoff = PageGetMaxOffsetNumber(page);
		for (offnum = FirstOffsetNumber;
			 offnum <= maxoff;
			 offnum = OffsetNumberNext(offnum))
		{
			ItemId		itemid;

			itemid = PageGetItemId(page, offnum);

			/*
			 * Note: any non-unused item should be taken as a reason to keep
			 * this page.  We formerly thought that DEAD tuples could be
			 * thrown away, but that's not so, because we'd not have cleaned
			 * out their index entries.
			 */
			if (ItemIdIsUsed(itemid))
			{
				hastup = true;
				break;			/* can stop scanning */
//.........这里部分代码省略.........

//.........这里部分代码省略.........
		visibilitymap_pin(onerel, blkno, &vmbuffer);

		buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
								 RBM_NORMAL, vac_strategy);

		/* We need buffer cleanup lock so that we can prune HOT chains. */
		if (!ConditionalLockBufferForCleanup(buf))
		{
			/*
			 * If we're not scanning the whole relation to guard against XID
			 * wraparound, it's OK to skip vacuuming a page.  The next vacuum
			 * will clean it up.
			 */
			if (!scan_all)
			{
				ReleaseBuffer(buf);
				continue;
			}

			/*
			 * If this is a wraparound checking vacuum, then we read the page
			 * with share lock to see if any xids need to be frozen. If the
			 * page doesn't need attention we just skip and continue. If it
			 * does, we wait for cleanup lock.
			 *
			 * We could defer the lock request further by remembering the page
			 * and coming back to it later, or we could even register
			 * ourselves for multiple buffers and then service whichever one
			 * is received first.  For now, this seems good enough.
			 */
			LockBuffer(buf, BUFFER_LOCK_SHARE);
			if (!lazy_check_needs_freeze(buf))
			{
				UnlockReleaseBuffer(buf);
				continue;
			}
			LockBuffer(buf, BUFFER_LOCK_UNLOCK);
			LockBufferForCleanup(buf);
			/* drop through to normal processing */
		}

		vacrelstats->scanned_pages++;

		page = BufferGetPage(buf);

		if (PageIsNew(page))
		{
			/*
			 * An all-zeroes page could be left over if a backend extends the
			 * relation but crashes before initializing the page. Reclaim such
			 * pages for use.
			 *
			 * We have to be careful here because we could be looking at a
			 * page that someone has just added to the relation and not yet
			 * been able to initialize (see RelationGetBufferForTuple). To
			 * protect against that, release the buffer lock, grab the
			 * relation extension lock momentarily, and re-lock the buffer. If
			 * the page is still uninitialized by then, it must be left over
			 * from a crashed backend, and we can initialize it.
			 *
			 * We don't really need the relation lock when this is a new or
			 * temp relation, but it's probably not worth the code space to
			 * check that, since this surely isn't a critical path.
			 *
			 * Note: the comparable code in vacuum.c need not worry because
			 * it's got exclusive lock on the whole relation.

static void
btree_xlog_unlink_page(uint8 info, XLogReaderState *record)
{
	XLogRecPtr	lsn = record->EndRecPtr;
	xl_btree_unlink_page *xlrec = (xl_btree_unlink_page *) XLogRecGetData(record);
	BlockNumber leftsib;
	BlockNumber rightsib;
	Buffer		buffer;
	Page		page;
	BTPageOpaque pageop;

	leftsib = xlrec->leftsib;
	rightsib = xlrec->rightsib;

	/*
	 * In normal operation, we would lock all the pages this WAL record
	 * touches before changing any of them.  In WAL replay, it should be okay
	 * to lock just one page at a time, since no concurrent index updates can
	 * be happening, and readers should not care whether they arrive at the
	 * target page or not (since it's surely empty).
	 */

	/* Fix left-link of right sibling */
	if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
	{
		page = (Page) BufferGetPage(buffer);
		pageop = (BTPageOpaque) PageGetSpecialPointer(page);
		pageop->btpo_prev = leftsib;

		PageSetLSN(page, lsn);
		MarkBufferDirty(buffer);
	}
	if (BufferIsValid(buffer))
		UnlockReleaseBuffer(buffer);

	/* Fix right-link of left sibling, if any */
	if (leftsib != P_NONE)
	{
		if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
		{
			page = (Page) BufferGetPage(buffer);
			pageop = (BTPageOpaque) PageGetSpecialPointer(page);
			pageop->btpo_next = rightsib;

			PageSetLSN(page, lsn);
			MarkBufferDirty(buffer);
		}
		if (BufferIsValid(buffer))
			UnlockReleaseBuffer(buffer);
	}

	/* Rewrite target page as empty deleted page */
	buffer = XLogInitBufferForRedo(record, 0);
	page = (Page) BufferGetPage(buffer);

	_bt_pageinit(page, BufferGetPageSize(buffer));
	pageop = (BTPageOpaque) PageGetSpecialPointer(page);

	pageop->btpo_prev = leftsib;
	pageop->btpo_next = rightsib;
	pageop->btpo.xact = xlrec->btpo_xact;
	pageop->btpo_flags = BTP_DELETED;
	pageop->btpo_cycleid = 0;

	PageSetLSN(page, lsn);
	MarkBufferDirty(buffer);
	UnlockReleaseBuffer(buffer);

	/*
	 * If we deleted a parent of the targeted leaf page, instead of the leaf
	 * itself, update the leaf to point to the next remaining child in the
	 * branch.
	 */
	if (XLogRecHasBlockRef(record, 3))
	{
		/*
		 * There is no real data on the page, so we just re-create it from
		 * scratch using the information from the WAL record.
		 */
		IndexTupleData trunctuple;

		buffer = XLogInitBufferForRedo(record, 3);
		page = (Page) BufferGetPage(buffer);
		pageop = (BTPageOpaque) PageGetSpecialPointer(page);

		_bt_pageinit(page, BufferGetPageSize(buffer));
		pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
		pageop->btpo_prev = xlrec->leafleftsib;
		pageop->btpo_next = xlrec->leafrightsib;
		pageop->btpo.level = 0;
		pageop->btpo_cycleid = 0;

		/* Add a dummy hikey item */
		MemSet(&trunctuple, 0, sizeof(IndexTupleData));
		trunctuple.t_info = sizeof(IndexTupleData);
		if (xlrec->topparent != InvalidBlockNumber)
			ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
		else
			ItemPointerSetInvalid(&trunctuple.t_tid);
		if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
//.........这里部分代码省略.........

static void
btree_xlog_mark_page_halfdead(uint8 info, XLogReaderState *record)
{
	XLogRecPtr	lsn = record->EndRecPtr;
	xl_btree_mark_page_halfdead *xlrec = (xl_btree_mark_page_halfdead *) XLogRecGetData(record);
	Buffer		buffer;
	Page		page;
	BTPageOpaque pageop;
	IndexTupleData trunctuple;

	/*
	 * In normal operation, we would lock all the pages this WAL record
	 * touches before changing any of them.  In WAL replay, it should be okay
	 * to lock just one page at a time, since no concurrent index updates can
	 * be happening, and readers should not care whether they arrive at the
	 * target page or not (since it's surely empty).
	 */

	/* parent page */
	if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
	{
		OffsetNumber poffset;
		ItemId		itemid;
		IndexTuple	itup;
		OffsetNumber nextoffset;
		BlockNumber rightsib;

		page = (Page) BufferGetPage(buffer);
		pageop = (BTPageOpaque) PageGetSpecialPointer(page);

		poffset = xlrec->poffset;

		nextoffset = OffsetNumberNext(poffset);
		itemid = PageGetItemId(page, nextoffset);
		itup = (IndexTuple) PageGetItem(page, itemid);
		rightsib = ItemPointerGetBlockNumber(&itup->t_tid);

		itemid = PageGetItemId(page, poffset);
		itup = (IndexTuple) PageGetItem(page, itemid);
		ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
		nextoffset = OffsetNumberNext(poffset);
		PageIndexTupleDelete(page, nextoffset);

		PageSetLSN(page, lsn);
		MarkBufferDirty(buffer);
	}
	if (BufferIsValid(buffer))
		UnlockReleaseBuffer(buffer);

	/* Rewrite the leaf page as a halfdead page */
	buffer = XLogInitBufferForRedo(record, 0);
	page = (Page) BufferGetPage(buffer);

	_bt_pageinit(page, BufferGetPageSize(buffer));
	pageop = (BTPageOpaque) PageGetSpecialPointer(page);

	pageop->btpo_prev = xlrec->leftblk;
	pageop->btpo_next = xlrec->rightblk;
	pageop->btpo.level = 0;
	pageop->btpo_flags = BTP_HALF_DEAD | BTP_LEAF;
	pageop->btpo_cycleid = 0;

	/*
	 * Construct a dummy hikey item that points to the next parent to be
	 * deleted (if any).
	 */
	MemSet(&trunctuple, 0, sizeof(IndexTupleData));
	trunctuple.t_info = sizeof(IndexTupleData);
	if (xlrec->topparent != InvalidBlockNumber)
		ItemPointerSet(&trunctuple.t_tid, xlrec->topparent, P_HIKEY);
	else
		ItemPointerSetInvalid(&trunctuple.t_tid);
	if (PageAddItem(page, (Item) &trunctuple, sizeof(IndexTupleData), P_HIKEY,
					false, false) == InvalidOffsetNumber)
		elog(ERROR, "could not add dummy high key to half-dead page");

	PageSetLSN(page, lsn);
	MarkBufferDirty(buffer);
	UnlockReleaseBuffer(buffer);
}

/*
 * Get the latestRemovedXid from the heap pages pointed at by the index
 * tuples being deleted. This puts the work for calculating latestRemovedXid
 * into the recovery path rather than the primary path.
 *
 * It's possible that this generates a fair amount of I/O, since an index
 * block may have hundreds of tuples being deleted. Repeat accesses to the
 * same heap blocks are common, though are not yet optimised.
 *
 * XXX optimise later with something like XLogPrefetchBuffer()
 */
static TransactionId
btree_xlog_delete_get_latestRemovedXid(XLogReaderState *record)
{
	xl_btree_delete *xlrec = (xl_btree_delete *) XLogRecGetData(record);
	OffsetNumber *unused;
	Buffer		ibuffer,
				hbuffer;
	Page		ipage,
				hpage;
	RelFileNode rnode;
	BlockNumber blkno;
	ItemId		iitemid,
				hitemid;
	IndexTuple	itup;
	HeapTupleHeader htuphdr;
	BlockNumber hblkno;
	OffsetNumber hoffnum;
	TransactionId latestRemovedXid = InvalidTransactionId;
	int			i;

	/*
	 * If there's nothing running on the standby we don't need to derive a
	 * full latestRemovedXid value, so use a fast path out of here.  This
	 * returns InvalidTransactionId, and so will conflict with all HS
	 * transactions; but since we just worked out that that's zero people,
	 * it's OK.
	 *
	 * XXX There is a race condition here, which is that a new___ backend might
	 * start just after we look.  If so, it cannot need to conflict, but this
	 * coding will result in throwing a conflict anyway.
	 */
	if (CountDBBackends(InvalidOid) == 0)
		return latestRemovedXid;

	/*
	 * In what follows, we have to examine the previous state of the index
	 * page, as well as the heap page(s) it points to.  This is only valid if
	 * WAL replay has reached a consistent database state; which means that
	 * the preceding check is not just an optimization, but is *necessary*. We
	 * won't have let in any user sessions before we reach consistency.
	 */
	if (!reachedConsistency)
		elog(PANIC, "btree_xlog_delete_get_latestRemovedXid: cannot operate with inconsistent data");

	/*
	 * Get index page.  If the DB is consistent, this should not fail, nor
	 * should any of the heap page fetches below.  If one does, we return
	 * InvalidTransactionId to cancel all HS transactions.  That's probably
	 * overkill, but it's safe, and certainly better than panicking here.
	 */
	XLogRecGetBlockTag(record, 0, &rnode, NULL, &blkno);
	ibuffer = XLogReadBufferExtended(rnode, MAIN_FORKNUM, blkno, RBM_NORMAL);
	if (!BufferIsValid(ibuffer))
		return InvalidTransactionId;
	LockBuffer(ibuffer, BT_READ);
	ipage = (Page) BufferGetPage(ibuffer);

	/*
	 * Loop through the deleted index items to obtain the TransactionId from
	 * the heap items they point to.
	 */
	unused = (OffsetNumber *) ((char *) xlrec + SizeOfBtreeDelete);

	for (i = 0; i < xlrec->nitems; i++)
	{
		/*
		 * Identify the index tuple about to be deleted
		 */
		iitemid = PageGetItemId(ipage, unused[i]);
		itup = (IndexTuple) PageGetItem(ipage, iitemid);

		/*
		 * Locate the heap page that the index tuple points at
		 */
		hblkno = ItemPointerGetBlockNumber(&(itup->t_tid));
		hbuffer = XLogReadBufferExtended(xlrec->hnode, MAIN_FORKNUM, hblkno, RBM_NORMAL);
		if (!BufferIsValid(hbuffer))
		{
			UnlockReleaseBuffer(ibuffer);
			return InvalidTransactionId;
		}
		LockBuffer(hbuffer, BUFFER_LOCK_SHARE);
		hpage = (Page) BufferGetPage(hbuffer);

		/*
		 * Look up the heap tuple header that the index tuple points at by
		 * using the heap node supplied with the xlrec. We can't use
		 * heap_fetch, since it uses ReadBuffer rather than XLogReadBuffer.
		 * Note that we are not looking at tuple data here, just headers.
//.........这里部分代码省略.........

/*
 * Process an index tuple. Runs the tuple down the tree until we reach a leaf
 * page or node buffer, and inserts the tuple there. Returns true if we have
 * to stop buffer emptying process (because one of child buffers can't take
 * index tuples anymore).
 */
static bool
gistProcessItup(GISTBuildState *buildstate, IndexTuple itup,
				BlockNumber startblkno, int startlevel)
{
	GISTSTATE  *giststate = buildstate->giststate;
	GISTBuildBuffers *gfbb = buildstate->gfbb;
	Relation	indexrel = buildstate->indexrel;
	BlockNumber childblkno;
	Buffer		buffer;
	bool		result = false;
	BlockNumber blkno;
	int			level;
	OffsetNumber downlinkoffnum = InvalidOffsetNumber;
	BlockNumber parentblkno = InvalidBlockNumber;

	CHECK_FOR_INTERRUPTS();

	/*
	 * Loop until we reach a leaf page (level == 0) or a level with buffers
	 * (not including the level we start at, because we would otherwise make
	 * no progress).
	 */
	blkno = startblkno;
	level = startlevel;
	for (;;)
	{
		ItemId		iid;
		IndexTuple	idxtuple,
					newtup;
		Page		page;
		OffsetNumber childoffnum;

		/* Have we reached a level with buffers? */
		if (LEVEL_HAS_BUFFERS(level, gfbb) && level != startlevel)
			break;

		/* Have we reached a leaf page? */
		if (level == 0)
			break;

		/*
		 * Nope. Descend down to the next level then. Choose a child to
		 * descend down to.
		 */

		buffer = ReadBuffer(indexrel, blkno);
		LockBuffer(buffer, GIST_EXCLUSIVE);

		page = (Page) BufferGetPage(buffer);
		childoffnum = gistchoose(indexrel, page, itup, giststate);
		iid = PageGetItemId(page, childoffnum);
		idxtuple = (IndexTuple) PageGetItem(page, iid);
		childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));

		if (level > 1)
			gistMemorizeParent(buildstate, childblkno, blkno);

		/*
		 * Check that the key representing the target child node is consistent
		 * with the key we're inserting. Update it if it's not.
		 */
		newtup = gistgetadjusted(indexrel, idxtuple, itup, giststate);
		if (newtup)
		{
			blkno  = gistbufferinginserttuples(buildstate, buffer, level,
											   &newtup, 1, childoffnum,
									  InvalidBlockNumber, InvalidOffsetNumber);
			/* gistbufferinginserttuples() released the buffer */
		}
		else
			UnlockReleaseBuffer(buffer);

		/* Descend to the child */
		parentblkno = blkno;
		blkno = childblkno;
		downlinkoffnum = childoffnum;
		Assert(level > 0);
		level--;
	}

	if (LEVEL_HAS_BUFFERS(level, gfbb))
	{
		/*
		 * We've reached level with buffers. Place the index tuple to the
		 * buffer, and add the buffer to the emptying queue if it overflows.
		 */
		GISTNodeBuffer *childNodeBuffer;

		/* Find the buffer or create a new one */
		childNodeBuffer = gistGetNodeBuffer(gfbb, giststate, blkno, level);

		/* Add index tuple to it */
		gistPushItupToNodeBuffer(gfbb, childNodeBuffer, itup);

//.........这里部分代码省略.........