C++ UnlockRelationForExtension函数代码示例

/*
 * Ensure that the visibility map fork is at least vm_nblocks long, extending
 * it if necessary with zeroed pages.
 */
static void
vm_extend(Relation rel, BlockNumber vm_nblocks)
{
	BlockNumber vm_nblocks_now;
	Page		pg;

	pg = (Page) palloc(BLCKSZ);
	PageInit(pg, BLCKSZ, 0);

	/*
	 * We use the relation extension lock to lock out other backends trying to
	 * extend the visibility map at the same time. It also locks out extension
	 * of the main fork, unnecessarily, but extending the visibility map
	 * happens seldom enough that it doesn't seem worthwhile to have a
	 * separate lock tag type for it.
	 *
	 * Note that another backend might have extended or created the relation
	 * by the time we get the lock.
	 */
	LockRelationForExtension(rel, ExclusiveLock);

	/* Might have to re-open if a cache flush happened */
	RelationOpenSmgr(rel);

	/*
	 * Create the file first if it doesn't exist.  If smgr_vm_nblocks is
	 * positive then it must exist, no need for an smgrexists call.
	 */
	if ((rel->rd_smgr->smgr_vm_nblocks == 0 ||
		 rel->rd_smgr->smgr_vm_nblocks == InvalidBlockNumber) &&
		!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
		smgrcreate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, false);

	vm_nblocks_now = smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM);

	/* Now extend the file */
	while (vm_nblocks_now < vm_nblocks)
	{
		smgrextend(rel->rd_smgr, VISIBILITYMAP_FORKNUM, vm_nblocks_now,
				   (char *) pg, false);
		vm_nblocks_now++;
	}

	/*
	 * Send a shared-inval message to force other backends to close any smgr
	 * references they may have for this rel, which we are about to change.
	 * This is a useful optimization because it means that backends don't have
	 * to keep checking for creation or extension of the file, which happens
	 * infrequently.
	 */
	CacheInvalidateSmgr(rel->rd_smgr->smgr_rnode);

	/* Update local cache with the up-to-date size */
	rel->rd_smgr->smgr_vm_nblocks = vm_nblocks_now;

	UnlockRelationForExtension(rel, ExclusiveLock);

	pfree(pg);
}

/*
 * Allocate a new page (either by recycling, or by extending the index file).
 *
 * The returned buffer is already pinned and exclusive-locked.
 * Caller is responsible for initializing the page by calling SpGistInitBuffer.
 */
Buffer
SpGistNewBuffer(Relation index)
{
	Buffer		buffer;
	bool		needLock;

	/* First, try to get a page from FSM */
	for (;;)
	{
		BlockNumber blkno = GetFreeIndexPage(index);

		if (blkno == InvalidBlockNumber)
			break;				/* nothing known to FSM */

		/*
		 * The fixed pages shouldn't ever be listed in FSM, but just in case
		 * one is, ignore it.
		 */
		if (SpGistBlockIsFixed(blkno))
			continue;

		buffer = ReadBuffer(index, blkno);

		/*
		 * We have to guard against the possibility that someone else already
		 * recycled this page; the buffer may be locked if so.
		 */
		if (ConditionalLockBuffer(buffer))
		{
			Page		page = BufferGetPage(buffer);

			if (PageIsNew(page))
				return buffer;	/* OK to use, if never initialized */

			if (SpGistPageIsDeleted(page) || PageIsEmpty(page))
				return buffer;	/* OK to use */

			LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		}

		/* Can't use it, so release buffer and try again */
		ReleaseBuffer(buffer);
	}

	/* Must extend the file */
	needLock = !RELATION_IS_LOCAL(index);
	if (needLock)
		LockRelationForExtension(index, ExclusiveLock);

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

	if (needLock)
		UnlockRelationForExtension(index, ExclusiveLock);

	return buffer;
}

/*
 * Allocate a new page (either by recycling, or by extending the index file)
 *
 * The returned buffer is already pinned and exclusive-locked
 *
 * Caller is responsible for initializing the page by calling GISTInitBuffer
 */
Buffer
gistNewBuffer(Relation r)
{
	Buffer		buffer;
	bool		needLock;

	MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;

	/* First, try to get a page from FSM */
	for (;;)
	{
		BlockNumber blkno = GetFreeIndexPage(&r->rd_node);

		if (blkno == InvalidBlockNumber)
			break;				/* nothing left in FSM */

		buffer = ReadBuffer(r, blkno);

		/*
		 * We have to guard against the possibility that someone else already
		 * recycled this page; the buffer may be locked if so.
		 */
		if (ConditionalLockBuffer(buffer))
		{
			Page		page = BufferGetPage(buffer);

			if (PageIsNew(page))
				return buffer;	/* OK to use, if never initialized */

			gistcheckpage(r, buffer);

			if (GistPageIsDeleted(page))
				return buffer;	/* OK to use */

			LockBuffer(buffer, GIST_UNLOCK);
		}

		/* Can't use it, so release buffer and try again */
		ReleaseBuffer(buffer);
	}

	/* Must extend the file */
	needLock = !RELATION_IS_LOCAL(r);

	if (needLock)
		LockRelationForExtension(r, ExclusiveLock);

	buffer = ReadBuffer(r, P_NEW);
	LockBuffer(buffer, GIST_EXCLUSIVE);

	if (needLock)
		UnlockRelationForExtension(r, ExclusiveLock);

	return buffer;
}

/*
 * Ensure that the FSM fork is at least fsm_nblocks long, extending
 * it if necessary with empty pages. And by empty, I mean pages filled
 * with zeros, meaning there's no free space.
 */
static void
fsm_extend(Relation rel, BlockNumber fsm_nblocks)
{
	BlockNumber fsm_nblocks_now;
	Page		pg;

	pg = (Page) palloc(BLCKSZ);
	PageInit(pg, BLCKSZ, 0);

	/*
	 * We use the relation extension lock to lock out other backends trying to
	 * extend the FSM at the same time. It also locks out extension of the
	 * main fork, unnecessarily, but extending the FSM happens seldom enough
	 * that it doesn't seem worthwhile to have a separate lock tag type for
	 * it.
	 *
	 * Note that another backend might have extended or created the relation
	 * by the time we get the lock.
	 */
	LockRelationForExtension(rel, ExclusiveLock);

	/* Might have to re-open if a cache flush happened */
	RelationOpenSmgr(rel);

	/*
	 * Create the FSM file first if it doesn't exist.  If smgr_fsm_nblocks is
	 * positive then it must exist, no need for an smgrexists call.
	 */
	if ((rel->rd_smgr->smgr_fsm_nblocks == 0 ||
		 rel->rd_smgr->smgr_fsm_nblocks == InvalidBlockNumber) &&
		!smgrexists(rel->rd_smgr, FSM_FORKNUM))
		smgrcreate(rel->rd_smgr, FSM_FORKNUM, false);

	fsm_nblocks_now = smgrnblocks(rel->rd_smgr, FSM_FORKNUM);

	while (fsm_nblocks_now < fsm_nblocks)
	{
		PageSetChecksumInplace(pg, fsm_nblocks_now);

		smgrextend(rel->rd_smgr, FSM_FORKNUM, fsm_nblocks_now,
				   (char *) pg, false);
		fsm_nblocks_now++;
	}

	/* Update local cache with the up-to-date size */
	rel->rd_smgr->smgr_fsm_nblocks = fsm_nblocks_now;

	UnlockRelationForExtension(rel, ExclusiveLock);

	pfree(pg);
}

Buffer
GinNewBuffer(Relation index)
{
	Buffer		buffer;
	bool		needLock;

	/* First, try to get a page from FSM */
	for (;;)
	{
		BlockNumber blkno = GetFreeIndexPage(index);

		if (blkno == InvalidBlockNumber)
			break;

		buffer = ReadBuffer(index, blkno);

		/*
		 * We have to guard against the possibility that someone else already
		 * recycled this page; the buffer may be locked if so.
		 */
		if (ConditionalLockBuffer(buffer))
		{
			Page		page = BufferGetPage(buffer);

			if (PageIsNew(page))
				return buffer;	/* OK to use, if never initialized */

			if (GinPageIsDeleted(page))
				return buffer;	/* OK to use */

			LockBuffer(buffer, GIN_UNLOCK);
		}

		/* Can't use it, so release buffer and try again */
		ReleaseBuffer(buffer);
	}

	/* Must extend the file */
	needLock = !RELATION_IS_LOCAL(index);
	if (needLock)
		LockRelationForExtension(index, ExclusiveLock);

	buffer = ReadBuffer(index, P_NEW);
	LockBuffer(buffer, GIN_EXCLUSIVE);

	if (needLock)
		UnlockRelationForExtension(index, ExclusiveLock);

	return buffer;
}

/*
 * _bitmap_getbuf() -- return the buffer for the given block number and
 * 					   the access method.
 */
Buffer
_bitmap_getbuf(Relation rel, BlockNumber blkno, int access)
{
	Buffer buf;

	MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;

	if (blkno != P_NEW)
	{
		buf = ReadBuffer(rel, blkno);
		if (access != BM_NOLOCK)
			LockBuffer(buf, access);
	}

	else
	{
		bool		needLock;

		Assert(access == BM_WRITE);

		/*
		 * Extend the relation by one page.
		 *
		 * We have to use a lock to ensure no one else is extending the rel at
		 * the same time, else we will both try to initialize the same new
		 * page.  We can skip locking for new or temp relations, however,
		 * since no one else could be accessing them.
		 */
		needLock = !RELATION_IS_LOCAL(rel);

		if (needLock)
			LockRelationForExtension(rel, ExclusiveLock);

		buf = ReadBuffer(rel, P_NEW);

		/* Acquire buffer lock on new page */
		LockBuffer(buf, BM_WRITE);

		/*
		 * Release the file-extension lock; it's now OK for someone else to
		 * extend the relation some more.
		 */
		if (needLock)
			UnlockRelationForExtension(rel, ExclusiveLock);
	}

	return buf;
}

/*
 * Ensure that the visibility map fork is at least vm_nblocks long, extending
 * it if necessary with zeroed pages.
 */
static void
vm_extend(Relation rel, BlockNumber vm_nblocks)
{
	BlockNumber vm_nblocks_now;
	Page		pg;

	pg = (Page) palloc(BLCKSZ);
	PageInit(pg, BLCKSZ, 0);

	/*
	 * We use the relation extension lock to lock out other backends trying to
	 * extend the visibility map at the same time. It also locks out extension
	 * of the main fork, unnecessarily, but extending the visibility map
	 * happens seldom enough that it doesn't seem worthwhile to have a
	 * separate lock tag type for it.
	 *
	 * Note that another backend might have extended or created the relation
	 * before we get the lock.
	 */
	LockRelationForExtension(rel, ExclusiveLock);

	/* Create the file first if it doesn't exist */
	if ((rel->rd_vm_nblocks == 0 || rel->rd_vm_nblocks == InvalidBlockNumber)
		&& !smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
	{
		smgrcreate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, false);
		vm_nblocks_now = 0;
	}
	else
		vm_nblocks_now = smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM);

	while (vm_nblocks_now < vm_nblocks)
	{
		smgrextend(rel->rd_smgr, VISIBILITYMAP_FORKNUM, vm_nblocks_now,
				   (char *) pg, rel->rd_istemp);
		vm_nblocks_now++;
	}

	UnlockRelationForExtension(rel, ExclusiveLock);

	pfree(pg);

	/* Update the relcache with the up-to-date size */
	if (!InRecovery)
		CacheInvalidateRelcache(rel);
	rel->rd_vm_nblocks = vm_nblocks_now;
}

/*
 * Given a BRIN index page, initialize it if necessary, and record it into the
 * FSM if necessary.  Return value is true if the FSM itself needs "vacuuming".
 * The main use for this is when, during vacuuming, an uninitialized page is
 * found, which could be the result of relation extension followed by a crash
 * before the page can be used.
 */
bool
brin_page_cleanup(Relation idxrel, Buffer buf)
{
	Page		page = BufferGetPage(buf);
	Size		freespace;

	/*
	 * If a page was left uninitialized, initialize it now; also record it in
	 * FSM.
	 *
	 * Somebody else might be extending the relation concurrently.  To avoid
	 * re-initializing the page before they can grab the buffer lock, we
	 * acquire the extension lock momentarily.  Since they hold the extension
	 * lock from before getting the page and after its been initialized, we're
	 * sure to see their initialization.
	 */
	if (PageIsNew(page))
	{
		LockRelationForExtension(idxrel, ShareLock);
		UnlockRelationForExtension(idxrel, ShareLock);

		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
		if (PageIsNew(page))
		{
			brin_initialize_empty_new_buffer(idxrel, buf);
			LockBuffer(buf, BUFFER_LOCK_UNLOCK);
			return true;
		}
		LockBuffer(buf, BUFFER_LOCK_UNLOCK);
	}

	/* Nothing to be done for non-regular index pages */
	if (BRIN_IS_META_PAGE(BufferGetPage(buf)) ||
		BRIN_IS_REVMAP_PAGE(BufferGetPage(buf)))
		return false;

	/* Measure free space and record it */
	freespace = br_page_get_freespace(page);
	if (freespace > GetRecordedFreeSpace(idxrel, BufferGetBlockNumber(buf)))
	{
		RecordPageWithFreeSpace(idxrel, BufferGetBlockNumber(buf), freespace);
		return true;
	}

	return false;
}

/*
 * pgstat_index -- returns live/dead tuples info in a generic index
 */
static Datum
pgstat_index(Relation rel, BlockNumber start, pgstat_page pagefn,
			 FunctionCallInfo fcinfo)
{
	BlockNumber nblocks;
	BlockNumber blkno;
	BufferAccessStrategy bstrategy;
	pgstattuple_type stat = {0};

	/* prepare access strategy for this index */
	bstrategy = GetAccessStrategy(BAS_BULKREAD);

	blkno = start;
	for (;;)
	{
		/* Get the current relation length */
		LockRelationForExtension(rel, ExclusiveLock);
		nblocks = RelationGetNumberOfBlocks(rel);
		UnlockRelationForExtension(rel, ExclusiveLock);

		/* Quit if we've scanned the whole relation */
		if (blkno >= nblocks)
		{
			stat.table_len = (uint64) nblocks *BLCKSZ;

			break;
		}

		for (; blkno < nblocks; blkno++)
		{
			CHECK_FOR_INTERRUPTS();

			pagefn(&stat, rel, blkno, bstrategy);
		}
	}

	relation_close(rel, AccessShareLock);

	return build_pgstattuple_type(&stat, fcinfo);
}

Datum
gistvacuumcleanup(PG_FUNCTION_ARGS)
{
	IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
	GistBulkDeleteResult *stats = (GistBulkDeleteResult *) PG_GETARG_POINTER(1);
	Relation	rel = info->index;
	BlockNumber npages,
				blkno;
	BlockNumber totFreePages,
				nFreePages,
			   *freePages,
				maxFreePages;
	BlockNumber lastBlock = GIST_ROOT_BLKNO,
				lastFilledBlock = GIST_ROOT_BLKNO;
	bool		needLock;

	/* Set up all-zero stats if gistbulkdelete wasn't called */
	if (stats == NULL)
	{
		stats = (GistBulkDeleteResult *) palloc0(sizeof(GistBulkDeleteResult));
		/* use heap's tuple count */
		Assert(info->num_heap_tuples >= 0);
		stats->std.num_index_tuples = info->num_heap_tuples;

		/*
		 * 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?
		 */
	}

	/* gistVacuumUpdate may cause hard work */
	if (info->vacuum_full)
	{
		GistVacuum	gv;
		ArrayTuple	res;

		/* note: vacuum.c already acquired AccessExclusiveLock on index */

		gv.index = rel;
		initGISTstate(&(gv.giststate), rel);
		gv.opCtx = createTempGistContext();
		gv.result = stats;
		gv.strategy = info->strategy;

		/* walk through the entire index for update tuples */
		res = gistVacuumUpdate(&gv, GIST_ROOT_BLKNO, false);
		/* cleanup */
		if (res.itup)
		{
			int			i;

			for (i = 0; i < res.ituplen; i++)
				pfree(res.itup[i]);
			pfree(res.itup);
		}
		freeGISTstate(&(gv.giststate));
		MemoryContextDelete(gv.opCtx);
	}
	else if (stats->needFullVacuum)
		ereport(NOTICE,
				(errmsg("index \"%s\" needs VACUUM FULL or REINDEX to finish crash recovery",
						RelationGetRelationName(rel))));

	/*
	 * If vacuum full, we already have exclusive lock on the index. Otherwise,
	 * need lock unless it's local to this backend.
	 */
	if (info->vacuum_full)
		needLock = false;
	else
		needLock = !RELATION_IS_LOCAL(rel);

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

	maxFreePages = npages;
	if (maxFreePages > MaxFSMPages)
		maxFreePages = MaxFSMPages;

	totFreePages = nFreePages = 0;
	freePages = (BlockNumber *) palloc(sizeof(BlockNumber) * maxFreePages);

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

		vacuum_delay_point();

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

		if (PageIsNew(page) || GistPageIsDeleted(page))
		{
			if (nFreePages < maxFreePages)
//.........这里部分代码省略.........

//.........这里部分代码省略.........
		 * code above.
		 */
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		if (otherBuffer == InvalidBuffer)
			ReleaseBuffer(buffer);
		else if (otherBlock != targetBlock)
		{
			LockBuffer(otherBuffer, BUFFER_LOCK_UNLOCK);
			ReleaseBuffer(buffer);
		}

		/* Without FSM, always fall out of the loop and extend */
		if (!use_fsm)
			break;

		/*
		 * Update FSM as to condition of this page, and ask for another page
		 * to try.
		 */
		targetBlock = RecordAndGetPageWithFreeSpace(relation,
													targetBlock,
													pageFreeSpace,
													len + saveFreeSpace);
	}

	/*
	 * Have to extend the relation.
	 *
	 * We have to use a lock to ensure no one else is extending the rel at the
	 * same time, else we will both try to initialize the same new page.  We
	 * can skip locking for new or temp relations, however, since no one else
	 * could be accessing them.
	 */
	needLock = !RELATION_IS_LOCAL(relation);

	if (needLock)
		LockRelationForExtension(relation, ExclusiveLock);

	/*
	 * XXX This does an lseek - rather expensive - but at the moment it is the
	 * only way to accurately determine how many blocks are in a relation.	Is
	 * it worth keeping an accurate file length in shared memory someplace,
	 * rather than relying on the kernel to do it for us?
	 */
	buffer = ReadBufferBI(relation, P_NEW, bistate);

	/*
	 * We can be certain that locking the otherBuffer first is OK, since it
	 * must have a lower page number.
	 */
	if (otherBuffer != InvalidBuffer)
		LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);

	/*
	 * Now acquire lock on the new page.
	 */
	LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

	/*
	 * Release the file-extension lock; it's now OK for someone else to extend
	 * the relation some more.	Note that we cannot release this lock before
	 * we have buffer lock on the new page, or we risk a race condition
	 * against vacuumlazy.c --- see comments therein.
	 */
	if (needLock)
		UnlockRelationForExtension(relation, ExclusiveLock);

	/*
	 * We need to initialize the empty new page.  Double-check that it really
	 * is empty (this should never happen, but if it does we don't want to
	 * risk wiping out valid data).
	 */
	page = BufferGetPage(buffer);

	if (!PageIsNew(page))
		elog(ERROR, "page %u of relation \"%s\" should be empty but is not",
			 BufferGetBlockNumber(buffer),
			 RelationGetRelationName(relation));

	PageInit(page, BufferGetPageSize(buffer), 0);

	if (len > PageGetHeapFreeSpace(page))
	{
		/* We should not get here given the test at the top */
		elog(PANIC, "tuple is too big: size %lu", (unsigned long) len);
	}

	/*
	 * Remember the new page as our target for future insertions.
	 *
	 * XXX should we enter the new page into the free space map immediately,
	 * or just keep it for this backend's exclusive use in the short run
	 * (until VACUUM sees it)?	Seems to depend on whether you expect the
	 * current backend to make more insertions or not, which is probably a
	 * good bet most of the time.  So for now, don't add it to FSM yet.
	 */
	RelationSetTargetBlock(relation, BufferGetBlockNumber(buffer));

	return buffer;
}

/*
 * VACUUM cleanup: update FSM
 */
Datum
gistvacuumcleanup(PG_FUNCTION_ARGS)
{
	IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
	GistBulkDeleteResult *stats = (GistBulkDeleteResult *) PG_GETARG_POINTER(1);
	Relation	rel = info->index;
	BlockNumber npages,
				blkno;
	BlockNumber totFreePages;
	BlockNumber lastBlock = GIST_ROOT_BLKNO,
				lastFilledBlock = GIST_ROOT_BLKNO;
	bool		needLock;

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

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

	if (stats->needReindex)
		ereport(NOTICE,
				(errmsg("index \"%s\" needs VACUUM FULL or REINDEX to finish crash recovery",
						RelationGetRelationName(rel))));

	/*
	 * 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);
		}
		else
			lastFilledBlock = blkno;
		UnlockReleaseBuffer(buffer);
	}
	lastBlock = npages - 1;

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

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

	PG_RETURN_POINTER(stats);
}

/*
 * btvacuumscan --- scan the index for VACUUMing purposes
 *
 * This combines the functions of looking for leaf tuples that are deletable
 * according to the vacuum callback, looking for empty pages that can be
 * deleted, and looking for old deleted pages that can be recycled.  Both
 * btbulkdelete and btvacuumcleanup invoke this (the latter only if no
 * btbulkdelete call occurred).
 *
 * The caller is responsible for initially allocating/zeroing a stats struct
 * and for obtaining a vacuum cycle ID if necessary.
 */
static void
btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
			 IndexBulkDeleteCallback callback, void *callback_state,
			 BTCycleId cycleid)
{
	Relation	rel = info->index;
	BTVacState	vstate;
	BlockNumber num_pages;
	BlockNumber blkno;
	bool		needLock;

	/*
	 * Reset counts that will be incremented during the scan; needed in case
	 * of multiple scans during a single VACUUM command
	 */
	stats->estimated_count = false;
	stats->num_index_tuples = 0;
	stats->pages_deleted = 0;

	/* Set up info to pass down to btvacuumpage */
	vstate.info = info;
	vstate.stats = stats;
	vstate.callback = callback;
	vstate.callback_state = callback_state;
	vstate.cycleid = cycleid;
	vstate.lastBlockVacuumed = BTREE_METAPAGE;	/* Initialise at first block */
	vstate.lastBlockLocked = BTREE_METAPAGE;
	vstate.totFreePages = 0;

	/* Create a temporary memory context to run _bt_pagedel in */
	vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
												  "_bt_pagedel",
												  ALLOCSET_DEFAULT_SIZES);

	/*
	 * The outer loop iterates over all index pages except the metapage, in
	 * physical order (we hope the kernel will cooperate in providing
	 * read-ahead for speed).  It is critical that we visit all leaf pages,
	 * including ones added after we start the scan, else we might fail to
	 * delete some deletable tuples.  Hence, we must repeatedly check the
	 * relation length.  We must acquire the relation-extension lock while
	 * doing so to avoid a race condition: if someone else is extending the
	 * relation, there is a window where bufmgr/smgr have created a new
	 * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
	 * we manage to scan such a page here, we'll improperly assume it can be
	 * recycled.  Taking the lock synchronizes things enough to prevent a
	 * problem: either num_pages won't include the new page, or _bt_getbuf
	 * already has write lock on the buffer and it will be fully initialized
	 * before we can examine it.  (See also vacuumlazy.c, which has the same
	 * issue.)	Also, we need not worry if a page is added immediately after
	 * we look; the page splitting code already has write-lock on the left
	 * page before it adds a right page, so we must already have processed any
	 * tuples due to be moved into such a page.
	 *
	 * We can skip locking for new or temp relations, however, since no one
	 * else could be accessing them.
	 */
	needLock = !RELATION_IS_LOCAL(rel);

	blkno = BTREE_METAPAGE + 1;
	for (;;)
	{
		/* Get the current relation length */
		if (needLock)
			LockRelationForExtension(rel, ExclusiveLock);
		num_pages = RelationGetNumberOfBlocks(rel);
		if (needLock)
			UnlockRelationForExtension(rel, ExclusiveLock);

		/* Quit if we've scanned the whole relation */
		if (blkno >= num_pages)
			break;
		/* Iterate over pages, then loop back to recheck length */
		for (; blkno < num_pages; blkno++)
		{
			btvacuumpage(&vstate, blkno, blkno);
		}
	}

	/*
	 * Check to see if we need to issue one final WAL record for this index,
	 * which may be needed for correctness on a hot standby node when non-MVCC
	 * index scans could take place.
	 *
	 * If the WAL is replayed in hot standby, the replay process needs to get
	 * cleanup locks on all index leaf pages, just as we've been doing here.
	 * However, we won't issue any WAL records about pages that have no items
	 * to be deleted.  For pages between pages we've vacuumed, the replay code
//.........这里部分代码省略.........

//.........这里部分代码省略.........
	if (blkno != P_NEW)
	{
		/* Read an existing block of the relation */
		buf = ReadBuffer(rel, blkno);
		LockBuffer(buf, access);
		_bt_checkpage(rel, buf);
	}
	else
	{
		bool		needLock;
		Page		page;

		Assert(access == BT_WRITE);

		/*
		 * First see if the FSM knows of any free pages.
		 *
		 * We can't trust the FSM's report unreservedly; we have to check that
		 * the page is still free.	(For example, an already-free page could
		 * have been re-used between the time the last VACUUM scanned it and
		 * the time the VACUUM made its FSM updates.)
		 *
		 * In fact, it's worse than that: we can't even assume that it's safe
		 * to take a lock on the reported page.  If somebody else has a lock
		 * on it, or even worse our own caller does, we could deadlock.  (The
		 * own-caller scenario is actually not improbable. Consider an index
		 * on a serial or timestamp column.  Nearly all splits will be at the
		 * rightmost page, so it's entirely likely that _bt_split will call us
		 * while holding a lock on the page most recently acquired from FSM. A
		 * VACUUM running concurrently with the previous split could well have
		 * placed that page back in FSM.)
		 *
		 * To get around that, we ask for only a conditional lock on the
		 * reported page.  If we fail, then someone else is using the page,
		 * and we may reasonably assume it's not free.  (If we happen to be
		 * wrong, the worst consequence is the page will be lost to use till
		 * the next VACUUM, which is no big problem.)
		 */
		for (;;)
		{
			blkno = GetFreeIndexPage(&rel->rd_node);
			if (blkno == InvalidBlockNumber)
				break;
			buf = ReadBuffer(rel, blkno);
			if (ConditionalLockBuffer(buf))
			{
				page = BufferGetPage(buf);
				if (_bt_page_recyclable(page))
				{
					/* Okay to use page.  Re-initialize and return it */
					_bt_pageinit(page, BufferGetPageSize(buf));
					return buf;
				}
				elog(DEBUG2, "FSM returned nonrecyclable page");
				_bt_relbuf(rel, buf);
			}
			else
			{
				elog(DEBUG2, "FSM returned nonlockable page");
				/* couldn't get lock, so just drop pin */
				ReleaseBuffer(buf);
			}
		}

		/*
		 * Extend the relation by one page.
		 *
		 * We have to use a lock to ensure no one else is extending the rel at
		 * the same time, else we will both try to initialize the same new
		 * page.  We can skip locking for new or temp relations, however,
		 * since no one else could be accessing them.
		 */
		needLock = !RELATION_IS_LOCAL(rel);

		if (needLock)
			LockRelationForExtension(rel, ExclusiveLock);

		buf = ReadBuffer(rel, P_NEW);

		/* Acquire buffer lock on new page */
		LockBuffer(buf, BT_WRITE);

		/*
		 * Release the file-extension lock; it's now OK for someone else to
		 * extend the relation some more.  Note that we cannot release this
		 * lock before we have buffer lock on the new page, or we risk a race
		 * condition against btvacuumscan --- see comments therein.
		 */
		if (needLock)
			UnlockRelationForExtension(rel, ExclusiveLock);

		/* Initialize the new page before returning it */
		page = BufferGetPage(buf);
		Assert(PageIsNew((PageHeader) page));
		_bt_pageinit(page, BufferGetPageSize(buf));
	}

	/* ref count and lock type are correct */
	return buf;
}

//.........这里部分代码省略.........
		 * code above.
		 */
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		if (otherBuffer == InvalidBuffer)
			ReleaseBuffer(buffer);
		else if (otherBlock != targetBlock)
		{
			LockBuffer(otherBuffer, BUFFER_LOCK_UNLOCK);
			ReleaseBuffer(buffer);
		}

		/* Without FSM, always fall out of the loop and extend */
		if (!use_fsm)
			break;

		/*
		 * Update FSM as to condition of this page, and ask for another page
		 * to try.
		 */
		targetBlock = RecordAndGetPageWithFreeSpace(&relation->rd_node,
													targetBlock,
													pageFreeSpace,
													len + saveFreeSpace);
	}

	/*
	 * Have to extend the relation.
	 *
	 * We have to use a lock to ensure no one else is extending the rel at the
	 * same time, else we will both try to initialize the same new page.  We
	 * can skip locking for new or temp relations, however, since no one else
	 * could be accessing them.
	 */
	needLock = !RELATION_IS_LOCAL(relation);

	if (needLock)
		LockRelationForExtension(relation, ExclusiveLock);

	/*
	 * XXX This does an lseek - rather expensive - but at the moment it is the
	 * only way to accurately determine how many blocks are in a relation.	Is
	 * it worth keeping an accurate file length in shared memory someplace,
	 * rather than relying on the kernel to do it for us?
	 */
	buffer = ReadBuffer(relation, P_NEW);

	/*
	 * We can be certain that locking the otherBuffer first is OK, since it
	 * must have a lower page number.
	 */
	if (otherBuffer != InvalidBuffer)
		LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);

	/*
	 * Now acquire lock on the new page.
	 */
	LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

	/*
	 * Release the file-extension lock; it's now OK for someone else to extend
	 * the relation some more.	Note that we cannot release this lock before
	 * we have buffer lock on the new page, or we risk a race condition
	 * against vacuumlazy.c --- see comments therein.
	 */
	if (needLock)
		UnlockRelationForExtension(relation, ExclusiveLock);

	/*
	 * We need to initialize the empty new page.  Double-check that it really
	 * is empty (this should never happen, but if it does we don't want to
	 * risk wiping out valid data).
	 */
	pageHeader = (Page) BufferGetPage(buffer);

	if (!PageIsNew((PageHeader) pageHeader))
		elog(ERROR, "page %u of relation \"%s\" should be empty but is not",
			 BufferGetBlockNumber(buffer),
			 RelationGetRelationName(relation));

	PageInit(pageHeader, BufferGetPageSize(buffer), 0);

	if (len > PageGetFreeSpace(pageHeader))
	{
		/* We should not get here given the test at the top */
		elog(PANIC, "tuple is too big: size %lu", (unsigned long) len);
	}

	/*
	 * Remember the new page as our target for future insertions.
	 *
	 * XXX should we enter the new page into the free space map immediately,
	 * or just keep it for this backend's exclusive use in the short run
	 * (until VACUUM sees it)?	Seems to depend on whether you expect the
	 * current backend to make more insertions or not, which is probably a
	 * good bet most of the time.  So for now, don't add it to FSM yet.
	 */
	relation->rd_targblock = BufferGetBlockNumber(buffer);

	return buffer;
}