C++ BufferGetBlockNumber函数代码示例

/*
 * Build an SP-GiST index.
 */
Datum
spgbuild(PG_FUNCTION_ARGS)
{
	Relation	heap = (Relation) PG_GETARG_POINTER(0);
	Relation	index = (Relation) PG_GETARG_POINTER(1);
	IndexInfo  *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
	IndexBuildResult *result;
	double		reltuples;
	SpGistBuildState buildstate;
	Buffer		metabuffer,
				rootbuffer;

	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/*
	 * Initialize the meta page and root page
	 */
	metabuffer = SpGistNewBuffer(index);
	rootbuffer = SpGistNewBuffer(index);

	Assert(BufferGetBlockNumber(metabuffer) == SPGIST_METAPAGE_BLKNO);
	Assert(BufferGetBlockNumber(rootbuffer) == SPGIST_HEAD_BLKNO);

	START_CRIT_SECTION();

	SpGistInitMetapage(BufferGetPage(metabuffer));
	MarkBufferDirty(metabuffer);
	SpGistInitBuffer(rootbuffer, SPGIST_LEAF);
	MarkBufferDirty(rootbuffer);

	if (RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;
		XLogRecData rdata;

		/* WAL data is just the relfilenode */
		rdata.data = (char *) &(index->rd_node);
		rdata.len = sizeof(RelFileNode);
		rdata.buffer = InvalidBuffer;
		rdata.next = NULL;

		recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_CREATE_INDEX, &rdata);

		PageSetLSN(BufferGetPage(metabuffer), recptr);
		PageSetTLI(BufferGetPage(metabuffer), ThisTimeLineID);
		PageSetLSN(BufferGetPage(rootbuffer), recptr);
		PageSetTLI(BufferGetPage(rootbuffer), ThisTimeLineID);
	}

	END_CRIT_SECTION();

	UnlockReleaseBuffer(metabuffer);
	UnlockReleaseBuffer(rootbuffer);

	/*
	 * Now insert all the heap data into the index
	 */
	initSpGistState(&buildstate.spgstate, index);
	buildstate.spgstate.isBuild = true;

	buildstate.tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
											"SP-GiST build temporary context",
											  ALLOCSET_DEFAULT_MINSIZE,
											  ALLOCSET_DEFAULT_INITSIZE,
											  ALLOCSET_DEFAULT_MAXSIZE);

	reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
								   spgistBuildCallback, (void *) &buildstate);

	MemoryContextDelete(buildstate.tmpCtx);

	SpGistUpdateMetaPage(index);

	result = (IndexBuildResult *) palloc0(sizeof(IndexBuildResult));
	result->heap_tuples = result->index_tuples = reltuples;

	PG_RETURN_POINTER(result);
}

/*
 * Write WAL record of a page split.
 */
XLogRecPtr
gistXLogSplit(RelFileNode node, BlockNumber blkno, bool page_is_leaf,
			  SplitedPageLayout *dist,
			  BlockNumber origrlink, GistNSN orignsn,
			  Buffer leftchildbuf)
{
	XLogRecData *rdata;
	gistxlogPageSplit xlrec;
	SplitedPageLayout *ptr;
	int			npage = 0,
				cur;
	XLogRecPtr	recptr;

	for (ptr = dist; ptr; ptr = ptr->next)
		npage++;

	rdata = (XLogRecData *) palloc(sizeof(XLogRecData) * (npage * 2 + 2));

	xlrec.node = node;
	xlrec.origblkno = blkno;
	xlrec.origrlink = origrlink;
	xlrec.orignsn = orignsn;
	xlrec.origleaf = page_is_leaf;
	xlrec.npage = (uint16) npage;
	xlrec.leftchild =
		BufferIsValid(leftchildbuf) ? BufferGetBlockNumber(leftchildbuf) : InvalidBlockNumber;

	rdata[0].data = (char *) &xlrec;
	rdata[0].len = sizeof(gistxlogPageSplit);
	rdata[0].buffer = InvalidBuffer;

	cur = 1;

	/*
	 * Include a full page image of the child buf. (only necessary if a
	 * checkpoint happened since the child page was split)
	 */
	if (BufferIsValid(leftchildbuf))
	{
		rdata[cur - 1].next = &(rdata[cur]);
		rdata[cur].data = NULL;
		rdata[cur].len = 0;
		rdata[cur].buffer = leftchildbuf;
		rdata[cur].buffer_std = true;
		cur++;
	}

	for (ptr = dist; ptr; ptr = ptr->next)
	{
		rdata[cur - 1].next = &(rdata[cur]);
		rdata[cur].buffer = InvalidBuffer;
		rdata[cur].data = (char *) &(ptr->block);
		rdata[cur].len = sizeof(gistxlogPage);
		cur++;

		rdata[cur - 1].next = &(rdata[cur]);
		rdata[cur].buffer = InvalidBuffer;
		rdata[cur].data = (char *) (ptr->list);
		rdata[cur].len = ptr->lenlist;
		cur++;
	}
	rdata[cur - 1].next = NULL;

	recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_SPLIT, rdata);

	pfree(rdata);
	return recptr;
}

//.........这里部分代码省略.........

				/*
				 * During Hot Standby we currently assume that
				 * XLOG_BTREE_VACUUM records do not produce conflicts. That is
				 * only true as long as the callback function depends only
				 * upon whether the index tuple refers to heap tuples removed
				 * in the initial heap scan. When vacuum starts it derives a
				 * value of OldestXmin. Backends taking later snapshots could
				 * have a RecentGlobalXmin with a later xid than the vacuum's
				 * OldestXmin, so it is possible that row versions deleted
				 * after OldestXmin could be marked as killed by other
				 * backends. The callback function *could* look at the index
				 * tuple state in isolation and decide to delete the index
				 * tuple, though currently it does not. If it ever did, we
				 * would need to reconsider whether XLOG_BTREE_VACUUM records
				 * should cause conflicts. If they did cause conflicts they
				 * would be fairly harsh conflicts, since we haven't yet
				 * worked out a way to pass a useful value for
				 * latestRemovedXid on the XLOG_BTREE_VACUUM records. This
				 * applies to *any* type of index that marks index tuples as
				 * killed.
				 */
				if (callback(htup, callback_state))
					deletable[ndeletable++] = offnum;
			}
		}

		/*
		 * Apply any needed deletes.  We issue just one _bt_delitems() call
		 * per page, so as to minimize WAL traffic.
		 */
		if (ndeletable > 0)
		{
			BlockNumber lastBlockVacuumed = BufferGetBlockNumber(buf);

			_bt_delitems_vacuum(rel, buf, deletable, ndeletable, vstate->lastBlockVacuumed);

			/*
			 * Keep track of the block number of the lastBlockVacuumed, so we
			 * can scan those blocks as well during WAL replay. This then
			 * provides concurrency protection and allows btrees to be used
			 * while in recovery.
			 */
			if (lastBlockVacuumed > vstate->lastBlockVacuumed)
				vstate->lastBlockVacuumed = lastBlockVacuumed;

			stats->tuples_removed += ndeletable;
			/* must recompute maxoff */
			maxoff = PageGetMaxOffsetNumber(page);
		}
		else
		{
			/*
			 * If the page has been split during this vacuum cycle, it seems
			 * worth expending a write to clear btpo_cycleid even if we don't
			 * have any deletions to do.  (If we do, _bt_delitems takes care
			 * of this.)  This ensures we won't process the page again.
			 *
			 * We treat this like a hint-bit update because there's no need to
			 * WAL-log it.
			 */
			if (vstate->cycleid != 0 &&
				opaque->btpo_cycleid == vstate->cycleid)
			{
				opaque->btpo_cycleid = 0;
				SetBufferCommitInfoNeedsSave(buf);

/*
 * _bt_pagedel() -- Delete a page from the b-tree, if legal to do so.
 *
 * This action unlinks the page from the b-tree structure, removing all
 * pointers leading to it --- but not touching its own left and right links.
 * The page cannot be physically reclaimed right away, since other processes
 * may currently be trying to follow links leading to the page; they have to
 * be allowed to use its right-link to recover.  See nbtree/README.
 *
 * On entry, the target buffer must be pinned and locked (either read or write
 * lock is OK).  This lock and pin will be dropped before exiting.
 *
 * The "stack" argument can be a search stack leading (approximately) to the
 * target page, or NULL --- outside callers typically pass NULL since they
 * have not done such a search, but internal recursion cases pass the stack
 * to avoid duplicated search effort.
 *
 * Returns the number of pages successfully deleted (zero if page cannot
 * be deleted now; could be more than one if parent pages were deleted too).
 *
 * NOTE: this leaks memory.  Rather than trying to clean up everything
 * carefully, it's better to run it in a temp context that can be reset
 * frequently.
 */
int
_bt_pagedel(Relation rel, Buffer buf, BTStack stack)
{
	int			result;
	BlockNumber target,
				leftsib,
				rightsib,
				parent;
	OffsetNumber poffset,
				maxoff;
	uint32		targetlevel,
				ilevel;
	ItemId		itemid;
	IndexTuple	targetkey,
				itup;
	ScanKey		itup_scankey;
	Buffer		lbuf,
				rbuf,
				pbuf;
	bool		parent_half_dead;
	bool		parent_one_child;
	bool		rightsib_empty;
	Buffer		metabuf = InvalidBuffer;
	Page		metapg = NULL;
	BTMetaPageData *metad = NULL;
	Page		page;
	BTPageOpaque opaque;

	/*
	 * We can never delete rightmost pages nor root pages.	While at it, check
	 * that page is not already deleted and is empty.
	 */
	page = BufferGetPage(buf);
	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
	if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
		P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
	{
		/* Should never fail to delete a half-dead page */
		Assert(!P_ISHALFDEAD(opaque));

		_bt_relbuf(rel, buf);
		return 0;
	}

	/*
	 * Save info about page, including a copy of its high key (it must have
	 * one, being non-rightmost).
	 */
	target = BufferGetBlockNumber(buf);
	targetlevel = opaque->btpo.level;
	leftsib = opaque->btpo_prev;
	itemid = PageGetItemId(page, P_HIKEY);
	targetkey = CopyIndexTuple((IndexTuple) PageGetItem(page, itemid));

	/*
	 * To avoid deadlocks, we'd better drop the target page lock before going
	 * further.
	 */
	_bt_relbuf(rel, buf);

	/*
	 * We need an approximate pointer to the page's parent page.  We use the
	 * standard search mechanism to search for the page's high key; this will
	 * give us a link to either the current parent or someplace to its left
	 * (if there are multiple equal high keys).  In recursion cases, the
	 * caller already generated a search stack and we can just re-use that
	 * work.
	 */
	if (stack == NULL)
	{
		if (!InRecovery)
		{
			/* we need an insertion scan key to do our search, so build one */
			itup_scankey = _bt_mkscankey(rel, targetkey);
			/* find the leftmost leaf page containing this key */
			stack = _bt_search(rel, rel->rd_rel->relnatts, itup_scankey, false,
//.........这里部分代码省略.........

/*
 *	_bt_getroot() -- Get the root page of the btree.
 *
 *		Since the root page can move around the btree file, we have to read
 *		its location from the metadata page, and then read the root page
 *		itself.  If no root page exists yet, we have to create one.  The
 *		standard class of race conditions exists here; I think I covered
 *		them all in the Hopi Indian rain dance of lock requests below.
 *
 *		The access type parameter (BT_READ or BT_WRITE) controls whether
 *		a new root page will be created or not.  If access = BT_READ,
 *		and no root page exists, we just return InvalidBuffer.	For
 *		BT_WRITE, we try to create the root page if it doesn't exist.
 *		NOTE that the returned root page will have only a read lock set
 *		on it even if access = BT_WRITE!
 *
 *		The returned page is not necessarily the true root --- it could be
 *		a "fast root" (a page that is alone in its level due to deletions).
 *		Also, if the root page is split while we are "in flight" to it,
 *		what we will return is the old root, which is now just the leftmost
 *		page on a probably-not-very-wide level.  For most purposes this is
 *		as good as or better than the true root, so we do not bother to
 *		insist on finding the true root.  We do, however, guarantee to
 *		return a live (not deleted or half-dead) page.
 *
 *		On successful return, the root page is pinned and read-locked.
 *		The metadata page is not locked or pinned on exit.
 */
Buffer
_bt_getroot(Relation rel, int access)
{
	Buffer		metabuf;
	Page		metapg;
	BTPageOpaque metaopaque;
	Buffer		rootbuf;
	Page		rootpage;
	BTPageOpaque rootopaque;
	BlockNumber rootblkno;
	uint32		rootlevel;
	BTMetaPageData *metad;

	metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_READ);
	metapg = BufferGetPage(metabuf);
	metaopaque = (BTPageOpaque) PageGetSpecialPointer(metapg);
	metad = BTPageGetMeta(metapg);

	/* sanity-check the metapage */
	if (!(metaopaque->btpo_flags & BTP_META) ||
		metad->btm_magic != BTREE_MAGIC)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("index \"%s\" is not a btree",
						RelationGetRelationName(rel))));

	if (metad->btm_version != BTREE_VERSION)
		ereport(ERROR,
				(errcode(ERRCODE_INDEX_CORRUPTED),
				 errmsg("version mismatch in index \"%s\": file version %d, code version %d",
						RelationGetRelationName(rel),
						metad->btm_version, BTREE_VERSION)));

	/* if no root page initialized yet, do it */
	if (metad->btm_root == P_NONE)
	{
		/* If access = BT_READ, caller doesn't want us to create root yet */
		if (access == BT_READ)
		{
			_bt_relbuf(rel, metabuf);
			return InvalidBuffer;
		}

		/* trade in our read lock for a write lock */
		LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
		LockBuffer(metabuf, BT_WRITE);

		/*
		 * Race condition:	if someone else initialized the metadata between
		 * the time we released the read lock and acquired the write lock, we
		 * must avoid doing it again.
		 */
		if (metad->btm_root != P_NONE)
		{
			/*
			 * Metadata initialized by someone else.  In order to guarantee no
			 * deadlocks, we have to release the metadata page and start all
			 * over again.	(Is that really true? But it's hardly worth trying
			 * to optimize this case.)
			 */
			_bt_relbuf(rel, metabuf);
			return _bt_getroot(rel, access);
		}

		/*
		 * Get, initialize, write, and leave a lock of the appropriate type on
		 * the new root page.  Since this is the first page in the tree, it's
		 * a leaf as well as the root.
		 */
		rootbuf = _bt_getbuf(rel, P_NEW, BT_WRITE);
		rootblkno = BufferGetBlockNumber(rootbuf);
		rootpage = BufferGetPage(rootbuf);
//.........这里部分代码省略.........

/*
 * Routine to build an index.  Basically calls insert over and over.
 *
 * XXX: it would be nice to implement some sort of bulk-loading
 * algorithm, but it is not clear how to do that.
 */
Datum
gistbuild(PG_FUNCTION_ARGS)
{
	Relation	heap = (Relation) PG_GETARG_POINTER(0);
	Relation	index = (Relation) PG_GETARG_POINTER(1);
	IndexInfo  *indexInfo = (IndexInfo *) PG_GETARG_POINTER(2);
	IndexBuildResult *result;
	double		reltuples;
	GISTBuildState buildstate;
	Buffer		buffer;
	Page		page;

	/*
	 * We expect to be called exactly once for any index relation. If that's
	 * not the case, big trouble's what we have.
	 */
	if (RelationGetNumberOfBlocks(index) != 0)
		elog(ERROR, "index \"%s\" already contains data",
			 RelationGetRelationName(index));

	/* no locking is needed */
	initGISTstate(&buildstate.giststate, index);

	/* initialize the root page */
	buffer = gistNewBuffer(index);
	Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
	page = BufferGetPage(buffer);

	START_CRIT_SECTION();

	GISTInitBuffer(buffer, F_LEAF);

	MarkBufferDirty(buffer);

	if (RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;
		XLogRecData rdata;

		rdata.data = (char *) &(index->rd_node);
		rdata.len = sizeof(RelFileNode);
		rdata.buffer = InvalidBuffer;
		rdata.next = NULL;

		recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_CREATE_INDEX, &rdata);
		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}
	else
		PageSetLSN(page, GetXLogRecPtrForTemp());

	UnlockReleaseBuffer(buffer);

	END_CRIT_SECTION();

	/* build the index */
	buildstate.numindexattrs = indexInfo->ii_NumIndexAttrs;
	buildstate.indtuples = 0;

	/*
	 * create a temporary memory context that is reset once for each tuple
	 * inserted into the index
	 */
	buildstate.tmpCtx = createTempGistContext();

	/* do the heap scan */
	reltuples = IndexBuildHeapScan(heap, index, indexInfo, true,
								   gistbuildCallback, (void *) &buildstate);

	/* okay, all heap tuples are indexed */
	MemoryContextDelete(buildstate.tmpCtx);

	freeGISTstate(&buildstate.giststate);

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

	result->heap_tuples = reltuples;
	result->index_tuples = buildstate.indtuples;

	PG_RETURN_POINTER(result);
}

void
_bt_delitems_delete(Relation rel, Buffer buf,
					OffsetNumber *itemnos, int nitems, Relation heapRel)
{
	Page		page = BufferGetPage(buf);
	BTPageOpaque opaque;

	Assert(nitems > 0);

	/* No ereport(ERROR) until changes are logged */
	START_CRIT_SECTION();

	/* Fix the page */
	PageIndexMultiDelete(page, itemnos, nitems);

	/*
	 * We can clear the vacuum cycle ID since this page has certainly been
	 * processed by the current vacuum scan.
	 */
	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
	opaque->btpo_cycleid = 0;

	/*
	 * Mark the page as not containing any LP_DEAD items.  This is not
	 * certainly true (there might be some that have recently been marked, but
	 * weren't included in our target-item list), but it will almost always be
	 * true and it doesn't seem worth an additional page scan to check it.
	 * Remember that BTP_HAS_GARBAGE is only a hint anyway.
	 */
	opaque->btpo_flags &= ~BTP_HAS_GARBAGE;

	MarkBufferDirty(buf);

	/* XLOG stuff */
	if (RelationNeedsWAL(rel))
	{
		XLogRecPtr	recptr;
		XLogRecData rdata[3];

		xl_btree_delete xlrec_delete;

		xlrec_delete.node = rel->rd_node;
		xlrec_delete.hnode = heapRel->rd_node;
		xlrec_delete.block = BufferGetBlockNumber(buf);
		xlrec_delete.nitems = nitems;

		rdata[0].data = (char *) &xlrec_delete;
		rdata[0].len = SizeOfBtreeDelete;
		rdata[0].buffer = InvalidBuffer;
		rdata[0].next = &(rdata[1]);

		/*
		 * We need the target-offsets array whether or not we store the to
		 * allow us to find the latestRemovedXid on a standby server.
		 */
		rdata[1].data = (char *) itemnos;
		rdata[1].len = nitems * sizeof(OffsetNumber);
		rdata[1].buffer = InvalidBuffer;
		rdata[1].next = &(rdata[2]);

		rdata[2].data = NULL;
		rdata[2].len = 0;
		rdata[2].buffer = buf;
		rdata[2].buffer_std = true;
		rdata[2].next = NULL;

		recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_DELETE, rdata);

		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}

	END_CRIT_SECTION();
}

/*
 *	_bt_endpoint() -- Find the first or last page in the index, and scan
 * from there to the first key satisfying all the quals.
 *
 * This is used by _bt_first() to set up a scan when we've determined
 * that the scan must start at the beginning or end of the index (for
 * a forward or backward scan respectively).  Exit conditions are the
 * same as for _bt_first().
 */
static bool
_bt_endpoint(IndexScanDesc scan, ScanDirection dir)
{
	Relation	rel = scan->indexRelation;
	BTScanOpaque so = (BTScanOpaque) scan->opaque;
	Buffer		buf;
	Page		page;
	BTPageOpaque opaque;
	OffsetNumber start;
	BTScanPosItem *currItem;

	/*
	 * Scan down to the leftmost or rightmost leaf page.  This is a simplified
	 * version of _bt_search().  We don't maintain a stack since we know we
	 * won't need it.
	 */
	buf = _bt_get_endpoint(rel, 0, ScanDirectionIsBackward(dir));

	if (!BufferIsValid(buf))
	{
		/*
		 * Empty index. Lock the whole relation, as nothing finer to lock
		 * exists.
		 */
		PredicateLockRelation(rel, scan->xs_snapshot);
		so->currPos.buf = InvalidBuffer;
		return false;
	}

	PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot);
	page = BufferGetPage(buf);
	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
	Assert(P_ISLEAF(opaque));

	if (ScanDirectionIsForward(dir))
	{
		/* There could be dead pages to the left, so not this: */
		/* Assert(P_LEFTMOST(opaque)); */

		start = P_FIRSTDATAKEY(opaque);
	}
	else if (ScanDirectionIsBackward(dir))
	{
		Assert(P_RIGHTMOST(opaque));

		start = PageGetMaxOffsetNumber(page);
	}
	else
	{
		elog(ERROR, "invalid scan direction: %d", (int) dir);
		start = 0;				/* keep compiler quiet */
	}

	/* remember which buffer we have pinned */
	so->currPos.buf = buf;

	/* initialize moreLeft/moreRight appropriately for scan direction */
	if (ScanDirectionIsForward(dir))
	{
		so->currPos.moreLeft = false;
		so->currPos.moreRight = true;
	}
	else
	{
		so->currPos.moreLeft = true;
		so->currPos.moreRight = false;
	}
	so->numKilled = 0;			/* just paranoia */
	so->markItemIndex = -1;		/* ditto */

	/*
	 * Now load data from the first page of the scan.
	 */
	if (!_bt_readpage(scan, dir, start))
	{
		/*
		 * There's no actually-matching data on this page.  Try to advance to
		 * the next page.  Return false if there's no matching data at all.
		 */
		if (!_bt_steppage(scan, dir))
			return false;
	}

	/* Drop the lock, but not pin, on the current page */
	LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);

	/* OK, itemIndex says what to return */
	currItem = &so->currPos.items[so->currPos.itemIndex];
	scan->xs_ctup.t_self = currItem->heapTid;
	if (scan->xs_want_itup)
		scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
//.........这里部分代码省略.........

//.........这里部分代码省略.........
			 * Find first item > scankey.  (This is only used for forward
			 * scans.)
			 */
			nextkey = true;
			goback = false;
			break;

		default:
			/* can't get here, but keep compiler quiet */
			elog(ERROR, "unrecognized strat_total: %d", (int) strat_total);
			return false;
	}

	/*
	 * Use the manufactured insertion scan key to descend the tree and
	 * position ourselves on the target leaf page.
	 */
	stack = _bt_search(rel, keysCount, scankeys, nextkey, &buf, BT_READ);

	/* don't need to keep the stack around... */
	_bt_freestack(stack);

	/* remember which buffer we have pinned, if any */
	so->currPos.buf = buf;

	if (!BufferIsValid(buf))
	{
		/*
		 * We only get here if the index is completely empty. Lock relation
		 * because nothing finer to lock exists.
		 */
		PredicateLockRelation(rel, scan->xs_snapshot);
		return false;
	}
	else
		PredicateLockPage(rel, BufferGetBlockNumber(buf),
						  scan->xs_snapshot);

	/* initialize moreLeft/moreRight appropriately for scan direction */
	if (ScanDirectionIsForward(dir))
	{
		so->currPos.moreLeft = false;
		so->currPos.moreRight = true;
	}
	else
	{
		so->currPos.moreLeft = true;
		so->currPos.moreRight = false;
	}
	so->numKilled = 0;			/* just paranoia */
	so->markItemIndex = -1;		/* ditto */

	/* position to the precise item on the page */
	offnum = _bt_binsrch(rel, buf, keysCount, scankeys, nextkey);

	/*
	 * If nextkey = false, we are positioned at the first item >= scan key, or
	 * possibly at the end of a page on which all the existing items are less
	 * than the scan key and we know that everything on later pages is greater
	 * than or equal to scan key.
	 *
	 * If nextkey = true, we are positioned at the first item > scan key, or
	 * possibly at the end of a page on which all the existing items are less
	 * than or equal to the scan key and we know that everything on later
	 * pages is greater than scan key.
	 *
	 * The actually desired starting point is either this item or the prior
	 * one, or in the end-of-page case it's the first item on the next page or
	 * the last item on this page.	Adjust the starting offset if needed. (If
	 * this results in an offset before the first item or after the last one,
	 * _bt_readpage will report no items found, and then we'll step to the
	 * next page as needed.)
	 */
	if (goback)
		offnum = OffsetNumberPrev(offnum);

	/*
	 * Now load data from the first page of the scan.
	 */
	if (!_bt_readpage(scan, dir, offnum))
	{
		/*
		 * There's no actually-matching data on this page.  Try to advance to
		 * the next page.  Return false if there's no matching data at all.
		 */
		if (!_bt_steppage(scan, dir))
			return false;
	}

	/* Drop the lock, but not pin, on the current page */
	LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);

	/* OK, itemIndex says what to return */
	currItem = &so->currPos.items[so->currPos.itemIndex];
	scan->xs_ctup.t_self = currItem->heapTid;
	if (scan->xs_want_itup)
		scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);

	return true;
}

//.........这里部分代码省略.........
	{
		/* bump pin on current buffer for assignment to mark buffer */
		IncrBufferRefCount(so->currPos.buf);
		memcpy(&so->markPos, &so->currPos,
			   offsetof(BTScanPosData, items[1]) +
			   so->currPos.lastItem * sizeof(BTScanPosItem));
		if (so->markTuples)
			memcpy(so->markTuples, so->currTuples,
				   so->currPos.nextTupleOffset);
		so->markPos.itemIndex = so->markItemIndex;
		so->markItemIndex = -1;
	}

	rel = scan->indexRelation;

	if (ScanDirectionIsForward(dir))
	{
		/* Walk right to the next page with data */
		/* We must rely on the previously saved nextPage link! */
		BlockNumber blkno = so->currPos.nextPage;

		/* Remember we left a page with data */
		so->currPos.moreLeft = true;

		for (;;)
		{
			/* release the previous buffer */
			_bt_relbuf(rel, so->currPos.buf);
			so->currPos.buf = InvalidBuffer;
			/* if we're at end of scan, give up */
			if (blkno == P_NONE || !so->currPos.moreRight)
				return false;
			/* check for interrupts while we're not holding any buffer lock */
			CHECK_FOR_INTERRUPTS();
			/* step right one page */
			so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
			/* check for deleted page */
			page = BufferGetPage(so->currPos.buf);
			opaque = (BTPageOpaque) PageGetSpecialPointer(page);
			if (!P_IGNORE(opaque))
			{
				PredicateLockPage(rel, blkno, scan->xs_snapshot);
				/* see if there are any matches on this page */
				/* note that this will clear moreRight if we can stop */
				if (_bt_readpage(scan, dir, P_FIRSTDATAKEY(opaque)))
					break;
			}
			/* nope, keep going */
			blkno = opaque->btpo_next;
		}
	}
	else
	{
		/* Remember we left a page with data */
		so->currPos.moreRight = true;

		/*
		 * Walk left to the next page with data.  This is much more complex
		 * than the walk-right case because of the possibility that the page
		 * to our left splits while we are in flight to it, plus the
		 * possibility that the page we were on gets deleted after we leave
		 * it.	See nbtree/README for details.
		 */
		for (;;)
		{
			/* Done if we know there are no matching keys to the left */
			if (!so->currPos.moreLeft)
			{
				_bt_relbuf(rel, so->currPos.buf);
				so->currPos.buf = InvalidBuffer;
				return false;
			}

			/* Step to next physical page */
			so->currPos.buf = _bt_walk_left(rel, so->currPos.buf);

			/* if we're physically at end of index, return failure */
			if (so->currPos.buf == InvalidBuffer)
				return false;

			/*
			 * Okay, we managed to move left to a non-deleted page. Done if
			 * it's not half-dead and contains matching tuples. Else loop back
			 * and do it all again.
			 */
			page = BufferGetPage(so->currPos.buf);
			opaque = (BTPageOpaque) PageGetSpecialPointer(page);
			if (!P_IGNORE(opaque))
			{
				PredicateLockPage(rel, BufferGetBlockNumber(so->currPos.buf), scan->xs_snapshot);
				/* see if there are any matches on this page */
				/* note that this will clear moreLeft if we can stop */
				if (_bt_readpage(scan, dir, PageGetMaxOffsetNumber(page)))
					break;
			}
		}
	}

	return true;
}

/*
 * _bt_walk_left() -- step left one page, if possible
 *
 * The given buffer must be pinned and read-locked.  This will be dropped
 * before stepping left.  On return, we have pin and read lock on the
 * returned page, instead.
 *
 * Returns InvalidBuffer if there is no page to the left (no lock is held
 * in that case).
 *
 * When working on a non-leaf level, it is possible for the returned page
 * to be half-dead; the caller should check that condition and step left
 * again if it's important.
 */
static Buffer
_bt_walk_left(Relation rel, Buffer buf)
{
	Page		page;
	BTPageOpaque opaque;

	page = BufferGetPage(buf);
	opaque = (BTPageOpaque) PageGetSpecialPointer(page);

	for (;;)
	{
		BlockNumber obknum;
		BlockNumber lblkno;
		BlockNumber blkno;
		int			tries;

		/* if we're at end of tree, release buf and return failure */
		if (P_LEFTMOST(opaque))
		{
			_bt_relbuf(rel, buf);
			break;
		}
		/* remember original page we are stepping left from */
		obknum = BufferGetBlockNumber(buf);
		/* step left */
		blkno = lblkno = opaque->btpo_prev;
		_bt_relbuf(rel, buf);
		/* check for interrupts while we're not holding any buffer lock */
		CHECK_FOR_INTERRUPTS();
		buf = _bt_getbuf(rel, blkno, BT_READ);
		page = BufferGetPage(buf);
		opaque = (BTPageOpaque) PageGetSpecialPointer(page);

		/*
		 * If this isn't the page we want, walk right till we find what we
		 * want --- but go no more than four hops (an arbitrary limit). If we
		 * don't find the correct page by then, the most likely bet is that
		 * the original page got deleted and isn't in the sibling chain at all
		 * anymore, not that its left sibling got split more than four times.
		 *
		 * Note that it is correct to test P_ISDELETED not P_IGNORE here,
		 * because half-dead pages are still in the sibling chain.	Caller
		 * must reject half-dead pages if wanted.
		 */
		tries = 0;
		for (;;)
		{
			if (!P_ISDELETED(opaque) && opaque->btpo_next == obknum)
			{
				/* Found desired page, return it */
				return buf;
			}
			if (P_RIGHTMOST(opaque) || ++tries > 4)
				break;
			blkno = opaque->btpo_next;
			buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
			page = BufferGetPage(buf);
			opaque = (BTPageOpaque) PageGetSpecialPointer(page);
		}

		/* Return to the original page to see what's up */
		buf = _bt_relandgetbuf(rel, buf, obknum, BT_READ);
		page = BufferGetPage(buf);
		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
		if (P_ISDELETED(opaque))
		{
			/*
			 * It was deleted.	Move right to first nondeleted page (there
			 * must be one); that is the page that has acquired the deleted
			 * one's keyspace, so stepping left from it will take us where we
			 * want to be.
			 */
			for (;;)
			{
				if (P_RIGHTMOST(opaque))
					elog(ERROR, "fell off the end of index \"%s\"",
						 RelationGetRelationName(rel));
				blkno = opaque->btpo_next;
				buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
				page = BufferGetPage(buf);
				opaque = (BTPageOpaque) PageGetSpecialPointer(page);
				if (!P_ISDELETED(opaque))
					break;
			}

			/*
//.........这里部分代码省略.........

/*
 *	_hash_freeovflpage() -
 *
 *	Remove this overflow page from its bucket's chain, and mark the page as
 *	free.  On entry, ovflbuf is write-locked; it is released before exiting.
 *
 *	Add the tuples (itups) to wbuf in this function.  We could do that in the
 *	caller as well, but the advantage of doing it here is we can easily write
 *	the WAL for XLOG_HASH_SQUEEZE_PAGE operation.  Addition of tuples and
 *	removal of overflow page has to done as an atomic operation, otherwise
 *	during replay on standby users might find duplicate records.
 *
 *	Since this function is invoked in VACUUM, we provide an access strategy
 *	parameter that controls fetches of the bucket pages.
 *
 *	Returns the block number of the page that followed the given page
 *	in the bucket, or InvalidBlockNumber if no following page.
 *
 *	NB: caller must not hold lock on metapage, nor on page, that's next to
 *	ovflbuf in the bucket chain.  We don't acquire the lock on page that's
 *	prior to ovflbuf in chain if it is same as wbuf because the caller already
 *	has a lock on same.
 */
BlockNumber
_hash_freeovflpage(Relation rel, Buffer bucketbuf, Buffer ovflbuf,
				   Buffer wbuf, IndexTuple *itups, OffsetNumber *itup_offsets,
				   Size *tups_size, uint16 nitups,
				   BufferAccessStrategy bstrategy)
{
	HashMetaPage metap;
	Buffer		metabuf;
	Buffer		mapbuf;
	BlockNumber ovflblkno;
	BlockNumber prevblkno;
	BlockNumber blkno;
	BlockNumber nextblkno;
	BlockNumber writeblkno;
	HashPageOpaque ovflopaque;
	Page		ovflpage;
	Page		mappage;
	uint32	   *freep;
	uint32		ovflbitno;
	int32		bitmappage,
				bitmapbit;
	Bucket		bucket PG_USED_FOR_ASSERTS_ONLY;
	Buffer		prevbuf = InvalidBuffer;
	Buffer		nextbuf = InvalidBuffer;
	bool		update_metap = false;

	/* Get information from the doomed page */
	_hash_checkpage(rel, ovflbuf, LH_OVERFLOW_PAGE);
	ovflblkno = BufferGetBlockNumber(ovflbuf);
	ovflpage = BufferGetPage(ovflbuf);
	ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
	nextblkno = ovflopaque->hasho_nextblkno;
	prevblkno = ovflopaque->hasho_prevblkno;
	writeblkno = BufferGetBlockNumber(wbuf);
	bucket = ovflopaque->hasho_bucket;

	/*
	 * Fix up the bucket chain.  this is a doubly-linked list, so we must fix
	 * up the bucket chain members behind and ahead of the overflow page being
	 * deleted.  Concurrency issues are avoided by using lock chaining as
	 * described atop hashbucketcleanup.
	 */
	if (BlockNumberIsValid(prevblkno))
	{
		if (prevblkno == writeblkno)
			prevbuf = wbuf;
		else
			prevbuf = _hash_getbuf_with_strategy(rel,
												 prevblkno,
												 HASH_WRITE,
												 LH_BUCKET_PAGE | LH_OVERFLOW_PAGE,
												 bstrategy);
	}
	if (BlockNumberIsValid(nextblkno))
		nextbuf = _hash_getbuf_with_strategy(rel,
											 nextblkno,
											 HASH_WRITE,
											 LH_OVERFLOW_PAGE,
											 bstrategy);

	/* Note: bstrategy is intentionally not used for metapage and bitmap */

	/* Read the metapage so we can determine which bitmap page to use */
	metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
	metap = HashPageGetMeta(BufferGetPage(metabuf));

	/* Identify which bit to set */
	ovflbitno = _hash_ovflblkno_to_bitno(metap, ovflblkno);

	bitmappage = ovflbitno >> BMPG_SHIFT(metap);
	bitmapbit = ovflbitno & BMPG_MASK(metap);

	if (bitmappage >= metap->hashm_nmaps)
		elog(ERROR, "invalid overflow bit number %u", ovflbitno);
	blkno = metap->hashm_mapp[bitmappage];

	/* Release metapage lock while we access the bitmap page */
//.........这里部分代码省略.........

//.........这里部分代码省略.........
	 * and other on new overflow page) since there cannot be anyone else
	 * contending for access to ovflbuf.
	 */
	ovflbuf = _hash_getnewbuf(rel, blkno, MAIN_FORKNUM);

found:

	/*
	 * Do the update.  No ereport(ERROR) until changes are logged. We want to
	 * log the changes for bitmap page and overflow page together to avoid
	 * loss of pages in case the new page is added.
	 */
	START_CRIT_SECTION();

	if (page_found)
	{
		Assert(BufferIsValid(mapbuf));

		/* mark page "in use" in the bitmap */
		SETBIT(freep, bitmap_page_bit);
		MarkBufferDirty(mapbuf);
	}
	else
	{
		/* update the count to indicate new overflow page is added */
		metap->hashm_spares[splitnum]++;

		if (BufferIsValid(newmapbuf))
		{
			_hash_initbitmapbuffer(newmapbuf, metap->hashm_bmsize, false);
			MarkBufferDirty(newmapbuf);

			/* add the new bitmap page to the metapage's list of bitmaps */
			metap->hashm_mapp[metap->hashm_nmaps] = BufferGetBlockNumber(newmapbuf);
			metap->hashm_nmaps++;
			metap->hashm_spares[splitnum]++;
		}

		MarkBufferDirty(metabuf);

		/*
		 * for new overflow page, we don't need to explicitly set the bit in
		 * bitmap page, as by default that will be set to "in use".
		 */
	}

	/*
	 * Adjust hashm_firstfree to avoid redundant searches.  But don't risk
	 * changing it if someone moved it while we were searching bitmap pages.
	 */
	if (metap->hashm_firstfree == orig_firstfree)
	{
		metap->hashm_firstfree = bit + 1;
		MarkBufferDirty(metabuf);
	}

	/* initialize new overflow page */
	ovflpage = BufferGetPage(ovflbuf);
	ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
	ovflopaque->hasho_prevblkno = BufferGetBlockNumber(buf);
	ovflopaque->hasho_nextblkno = InvalidBlockNumber;
	ovflopaque->hasho_bucket = pageopaque->hasho_bucket;
	ovflopaque->hasho_flag = LH_OVERFLOW_PAGE;
	ovflopaque->hasho_page_id = HASHO_PAGE_ID;

	MarkBufferDirty(ovflbuf);

//.........这里部分代码省略.........
			case HEAPTUPLE_LIVE:
			case HEAPTUPLE_INSERT_IN_PROGRESS:

				/*
				 * If we wanted to optimize for aborts, we might consider
				 * marking the page prunable when we see INSERT_IN_PROGRESS.
				 * But we don't.  See related decisions about when to mark the
				 * page prunable in heapam.c.
				 */
				break;

			default:
				elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
				break;
		}

		/*
		 * Remember the last DEAD tuple seen.  We will advance past
		 * RECENTLY_DEAD tuples just in case there's a DEAD one after them;
		 * but we can't advance past anything else.  (XXX is it really worth
		 * continuing to scan beyond RECENTLY_DEAD?  The case where we will
		 * find another DEAD tuple is a fairly unusual corner case.)
		 */
		if (tupdead)
		{
			latestdead = offnum;
			HeapTupleHeaderAdvanceLatestRemovedXid(htup,
												 &prstate->latestRemovedXid);
		}
		else if (!recent_dead)
			break;

		/*
		 * If the tuple is not HOT-updated, then we are at the end of this
		 * HOT-update chain.
		 */
		if (!HeapTupleHeaderIsHotUpdated(htup))
			break;

		/*
		 * Advance to next chain member.
		 */
		Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
			   BufferGetBlockNumber(buffer));
		offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
		priorXmax = HeapTupleHeaderGetUpdateXid(htup);
	}

	/*
	 * If we found a DEAD tuple in the chain, adjust the HOT chain so that all
	 * the DEAD tuples at the start of the chain are removed and the root line
	 * pointer is appropriately redirected.
	 */
	if (OffsetNumberIsValid(latestdead))
	{
		/*
		 * Mark as unused each intermediate item that we are able to remove
		 * from the chain.
		 *
		 * When the previous item is the last dead tuple seen, we are at the
		 * right candidate for redirection.
		 */
		for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
		{
			heap_prune_record_unused(prstate, chainitems[i]);
			ndeleted++;
		}

		/*
		 * If the root entry had been a normal tuple, we are deleting it, so
		 * count it in the result.	But changing a redirect (even to DEAD
		 * state) doesn't count.
		 */
		if (ItemIdIsNormal(rootlp))
			ndeleted++;

		/*
		 * If the DEAD tuple is at the end of the chain, the entire chain is
		 * dead and the root line pointer can be marked dead.  Otherwise just
		 * redirect the root to the correct chain member.
		 */
		if (i >= nchain)
			heap_prune_record_dead(prstate, rootoffnum);
		else
			heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
	}
	else if (nchain < 2 && ItemIdIsRedirected(rootlp))
	{
		/*
		 * We found a redirect item that doesn't point to a valid follow-on
		 * item.  This can happen if the loop in heap_page_prune caused us to
		 * visit the dead successor of a redirect item before visiting the
		 * redirect item.  We can clean up by setting the redirect item to
		 * DEAD state.
		 */
		heap_prune_record_dead(prstate, rootoffnum);
	}

	return ndeleted;
}

static bool
gistplacetopage(GISTInsertState *state, GISTSTATE *giststate)
{
	bool		is_splitted = false;
	bool		is_leaf = (GistPageIsLeaf(state->stack->page)) ? true : false;

	MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;

	/*
	 * if (!is_leaf) remove old key: This node's key has been modified, either
	 * because a child split occurred or because we needed to adjust our key
	 * for an insert in a child node. Therefore, remove the old version of
	 * this node's key.
	 *
	 * for WAL replay, in the non-split case we handle this by setting up a
	 * one-element todelete array; in the split case, it's handled implicitly
	 * because the tuple vector passed to gistSplit won't include this tuple.
	 *
	 * XXX: If we want to change fillfactors between node and leaf, fillfactor
	 * = (is_leaf ? state->leaf_fillfactor : state->node_fillfactor)
	 */
	if (gistnospace(state->stack->page, state->itup, state->ituplen,
					is_leaf ? InvalidOffsetNumber : state->stack->childoffnum,
					state->freespace))
	{
		/* no space for insertion */
		IndexTuple *itvec;
		int			tlen;
		SplitedPageLayout *dist = NULL,
				   *ptr;
		BlockNumber rrlink = InvalidBlockNumber;
		GistNSN		oldnsn;

		is_splitted = true;

		/*
		 * Form index tuples vector to split: remove old tuple if t's needed
		 * and add new tuples to vector
		 */
		itvec = gistextractpage(state->stack->page, &tlen);
		if (!is_leaf)
		{
			/* on inner page we should remove old tuple */
			int			pos = state->stack->childoffnum - FirstOffsetNumber;

			tlen--;
			if (pos != tlen)
				memmove(itvec + pos, itvec + pos + 1, sizeof(IndexTuple) * (tlen - pos));
		}
		itvec = gistjoinvector(itvec, &tlen, state->itup, state->ituplen);
		dist = gistSplit(state->r, state->stack->page, itvec, tlen, giststate);

		state->itup = (IndexTuple *) palloc(sizeof(IndexTuple) * tlen);
		state->ituplen = 0;

		if (state->stack->blkno != GIST_ROOT_BLKNO)
		{
			/*
			 * if non-root split then we should not allocate new buffer, but
			 * we must create temporary page to operate
			 */
			dist->buffer = state->stack->buffer;
			dist->page = PageGetTempPage(BufferGetPage(dist->buffer), sizeof(GISTPageOpaqueData));

			/* clean all flags except F_LEAF */
			GistPageGetOpaque(dist->page)->flags = (is_leaf) ? F_LEAF : 0;
		}

		/* make new pages and fills them */
		for (ptr = dist; ptr; ptr = ptr->next)
		{
			int			i;
			char	   *data;

			/* get new page */
			if (ptr->buffer == InvalidBuffer)
			{
				ptr->buffer = gistNewBuffer(state->r);
				GISTInitBuffer(ptr->buffer, (is_leaf) ? F_LEAF : 0);
				ptr->page = BufferGetPage(ptr->buffer);
			}
			ptr->block.blkno = BufferGetBlockNumber(ptr->buffer);

			/*
			 * fill page, we can do it because all these pages are new
			 * (ie not linked in tree or masked by temp page
			 */
			data = (char *) (ptr->list);
			for (i = 0; i < ptr->block.num; i++)
			{
				if (PageAddItem(ptr->page, (Item) data, IndexTupleSize((IndexTuple) data), i + FirstOffsetNumber, LP_USED) == InvalidOffsetNumber)
					elog(ERROR, "failed to add item to index page in \"%s\"", RelationGetRelationName(state->r));
				data += IndexTupleSize((IndexTuple) data);
			}

			/* set up ItemPointer and remember it for parent */
			ItemPointerSetBlockNumber(&(ptr->itup->t_tid), ptr->block.blkno);
			state->itup[state->ituplen] = ptr->itup;
			state->ituplen++;
		}
//.........这里部分代码省略.........