Пример #1
0
/*
 * buffer must be pinned and locked by caller
 */
void
gistnewroot(Relation r, Buffer buffer, IndexTuple *itup, int len, ItemPointer key)
{
	Page		page;

	Assert(BufferGetBlockNumber(buffer) == GIST_ROOT_BLKNO);
	page = BufferGetPage(buffer);

	START_CRIT_SECTION();

	GISTInitBuffer(buffer, 0);
	gistfillbuffer(r, page, itup, len, FirstOffsetNumber);

	MarkBufferDirty(buffer);

	if (!r->rd_istemp)
	{
		XLogRecPtr	recptr;
		XLogRecData *rdata;

		rdata = formUpdateRdata(r, buffer,
								NULL, 0,
								itup, len, key);

		recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_NEW_ROOT, rdata);
		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}
	else
		PageSetLSN(page, XLogRecPtrForTemp);

	END_CRIT_SECTION();
}
Пример #2
0
static void
gistRedoPageSplitRecord(XLogReaderState *record)
{
	XLogRecPtr	lsn = record->EndRecPtr;
	gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
	Buffer		firstbuffer = InvalidBuffer;
	Buffer		buffer;
	Page		page;
	int			i;
	bool		isrootsplit = false;

	/*
	 * 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 < xldata->npage; i++)
	{
		int			flags;
		char	   *data;
		Size		datalen;
		int			num;
		BlockNumber blkno;
		IndexTuple *tuples;

		XLogRecGetBlockTag(record, i + 1, NULL, NULL, &blkno);
		if (blkno == GIST_ROOT_BLKNO)
		{
			Assert(i == 0);
			isrootsplit = true;
		}

		buffer = XLogInitBufferForRedo(record, i + 1);
		page = (Page) BufferGetPage(buffer);
		data = XLogRecGetBlockData(record, i + 1, &datalen);

		tuples = decodePageSplitRecord(data, datalen, &num);

		/* ok, clear buffer */
		if (xldata->origleaf && blkno != GIST_ROOT_BLKNO)
			flags = F_LEAF;
		else
			flags = 0;
		GISTInitBuffer(buffer, flags);

		/* and fill it */
		gistfillbuffer(page, tuples, num, FirstOffsetNumber);

		if (blkno == GIST_ROOT_BLKNO)
		{
			GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
			GistPageSetNSN(page, xldata->orignsn);
			GistClearFollowRight(page);
		}
		else
		{
			if (i < xldata->npage - 1)
			{
				BlockNumber nextblkno;

				XLogRecGetBlockTag(record, i + 2, NULL, NULL, &nextblkno);
				GistPageGetOpaque(page)->rightlink = nextblkno;
			}
			else
				GistPageGetOpaque(page)->rightlink = xldata->origrlink;
			GistPageSetNSN(page, xldata->orignsn);
			if (i < xldata->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 (XLogRecHasBlockRef(record, 0))
		gistRedoClearFollowRight(record, 0);

	/* Finally, release lock on the first page */
	UnlockReleaseBuffer(firstbuffer);
}
Пример #3
0
/*
 * Place tuples from 'itup' to 'buffer'. If 'oldoffnum' is valid, the tuple
 * at that offset is atomically removed along with inserting the new tuples.
 * This is used to replace a tuple with a new one.
 *
 * If 'leftchildbuf' is valid, we're inserting the downlink for the page
 * to the right of 'leftchildbuf', or updating the downlink for 'leftchildbuf'.
 * F_FOLLOW_RIGHT flag on 'leftchildbuf' is cleared and NSN is set.
 *
 * If 'markfollowright' is true and the page is split, the left child is
 * marked with F_FOLLOW_RIGHT flag. That is the normal case. During buffered
 * index build, however, there is no concurrent access and the page splitting
 * is done in a slightly simpler fashion, and false is passed.
 *
 * If there is not enough room on the page, it is split. All the split
 * pages are kept pinned and locked and returned in *splitinfo, the caller
 * is responsible for inserting the downlinks for them. However, if
 * 'buffer' is the root page and it needs to be split, gistplacetopage()
 * performs the split as one atomic operation, and *splitinfo is set to NIL.
 * In that case, we continue to hold the root page locked, and the child
 * pages are released; note that new tuple(s) are *not* on the root page
 * but in one of the new child pages.
 *
 * If 'newblkno' is not NULL, returns the block number of page the first
 * new/updated tuple was inserted to. Usually it's the given page, but could
 * be its right sibling if the page was split.
 *
 * Returns 'true' if the page was split, 'false' otherwise.
 */
bool
gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate,
				Buffer buffer,
				IndexTuple *itup, int ntup, OffsetNumber oldoffnum,
				BlockNumber *newblkno,
				Buffer leftchildbuf,
				List **splitinfo,
				bool markfollowright)
{
	BlockNumber blkno = BufferGetBlockNumber(buffer);
	Page		page = BufferGetPage(buffer);
	bool		is_leaf = (GistPageIsLeaf(page)) ? true : false;
	XLogRecPtr	recptr;
	int			i;
	bool		is_split;

	/*
	 * Refuse to modify a page that's incompletely split. This should not
	 * happen because we finish any incomplete splits while we walk down the
	 * tree. However, it's remotely possible that another concurrent inserter
	 * splits a parent page, and errors out before completing the split. We
	 * will just throw an error in that case, and leave any split we had in
	 * progress unfinished too. The next insert that comes along will clean up
	 * the mess.
	 */
	if (GistFollowRight(page))
		elog(ERROR, "concurrent GiST page split was incomplete");

	*splitinfo = NIL;

	/*
	 * if isupdate, 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.
	 */
	is_split = gistnospace(page, itup, ntup, oldoffnum, freespace);
	if (is_split)
	{
		/* no space for insertion */
		IndexTuple *itvec;
		int			tlen;
		SplitedPageLayout *dist = NULL,
				   *ptr;
		BlockNumber oldrlink = InvalidBlockNumber;
		GistNSN		oldnsn = 0;
		SplitedPageLayout rootpg;
		bool		is_rootsplit;

		is_rootsplit = (blkno == GIST_ROOT_BLKNO);

		/*
		 * Form index tuples vector to split. If we're replacing an old tuple,
		 * remove the old version from the vector.
		 */
		itvec = gistextractpage(page, &tlen);
		if (OffsetNumberIsValid(oldoffnum))
		{
			/* on inner page we should remove old tuple */
			int			pos = oldoffnum - FirstOffsetNumber;

			tlen--;
			if (pos != tlen)
				memmove(itvec + pos, itvec + pos + 1, sizeof(IndexTuple) * (tlen - pos));
		}
		itvec = gistjoinvector(itvec, &tlen, itup, ntup);
		dist = gistSplit(rel, page, itvec, tlen, giststate);

		/*
		 * Set up pages to work with. Allocate new buffers for all but the
		 * leftmost page. The original page becomes the new leftmost page, and
		 * is just replaced with the new contents.
		 *
		 * For a root-split, allocate new buffers for all child pages, the
		 * original page is overwritten with new root page containing
		 * downlinks to the new child pages.
		 */
		ptr = dist;
		if (!is_rootsplit)
		{
			/* save old rightlink and NSN */
			oldrlink = GistPageGetOpaque(page)->rightlink;
			oldnsn = GistPageGetNSN(page);

			dist->buffer = buffer;
			dist->block.blkno = BufferGetBlockNumber(buffer);
			dist->page = PageGetTempPageCopySpecial(BufferGetPage(buffer));

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

			ptr = ptr->next;
		}
		for (; ptr; ptr = ptr->next)
		{
			/* Allocate new page */
			ptr->buffer = gistNewBuffer(rel);
			GISTInitBuffer(ptr->buffer, (is_leaf) ? F_LEAF : 0);
			ptr->page = BufferGetPage(ptr->buffer);
			ptr->block.blkno = BufferGetBlockNumber(ptr->buffer);
		}

		/*
		 * Now that we know which blocks the new pages go to, set up downlink
		 * tuples to point to them.
		 */
		for (ptr = dist; ptr; ptr = ptr->next)
		{
			ItemPointerSetBlockNumber(&(ptr->itup->t_tid), ptr->block.blkno);
			GistTupleSetValid(ptr->itup);
		}

		/*
		 * If this is a root split, we construct the new root page with the
		 * downlinks here directly, instead of requiring the caller to insert
		 * them. Add the new root page to the list along with the child pages.
		 */
		if (is_rootsplit)
		{
			IndexTuple *downlinks;
			int			ndownlinks = 0;
			int			i;

			rootpg.buffer = buffer;
			rootpg.page = PageGetTempPageCopySpecial(BufferGetPage(rootpg.buffer));
			GistPageGetOpaque(rootpg.page)->flags = 0;

			/* Prepare a vector of all the downlinks */
			for (ptr = dist; ptr; ptr = ptr->next)
				ndownlinks++;
			downlinks = palloc(sizeof(IndexTuple) * ndownlinks);
			for (i = 0, ptr = dist; ptr; ptr = ptr->next)
				downlinks[i++] = ptr->itup;

			rootpg.block.blkno = GIST_ROOT_BLKNO;
			rootpg.block.num = ndownlinks;
			rootpg.list = gistfillitupvec(downlinks, ndownlinks,
										  &(rootpg.lenlist));
			rootpg.itup = NULL;

			rootpg.next = dist;
			dist = &rootpg;
		}
		else
		{
			/* Prepare split-info to be returned to caller */
			for (ptr = dist; ptr; ptr = ptr->next)
			{
				GISTPageSplitInfo *si = palloc(sizeof(GISTPageSplitInfo));

				si->buf = ptr->buffer;
				si->downlink = ptr->itup;
				*splitinfo = lappend(*splitinfo, si);
			}
		}

		/*
		 * Fill all pages. All the pages are new, ie. freshly allocated empty
		 * pages, or a temporary copy of the old page.
		 */
		for (ptr = dist; ptr; ptr = ptr->next)
		{
			char	   *data = (char *) (ptr->list);

			for (i = 0; i < ptr->block.num; i++)
			{
				IndexTuple	thistup = (IndexTuple) data;

				if (PageAddItem(ptr->page, (Item) data, IndexTupleSize(thistup), i + FirstOffsetNumber, false, false) == InvalidOffsetNumber)
					elog(ERROR, "failed to add item to index page in \"%s\"", RelationGetRelationName(rel));

				/*
				 * If this is the first inserted/updated tuple, let the caller
				 * know which page it landed on.
				 */
				if (newblkno && ItemPointerEquals(&thistup->t_tid, &(*itup)->t_tid))
					*newblkno = ptr->block.blkno;

				data += IndexTupleSize(thistup);
			}

			/* Set up rightlinks */
			if (ptr->next && ptr->block.blkno != GIST_ROOT_BLKNO)
				GistPageGetOpaque(ptr->page)->rightlink =
					ptr->next->block.blkno;
			else
				GistPageGetOpaque(ptr->page)->rightlink = oldrlink;

			/*
			 * Mark the all but the right-most page with the follow-right
			 * flag. It will be cleared as soon as the downlink is inserted
			 * into the parent, but this ensures that if we error out before
			 * that, the index is still consistent. (in buffering build mode,
			 * any error will abort the index build anyway, so this is not
			 * needed.)
			 */
			if (ptr->next && !is_rootsplit && markfollowright)
				GistMarkFollowRight(ptr->page);
			else
				GistClearFollowRight(ptr->page);

			/*
			 * Copy the NSN of the original page to all pages. The
			 * F_FOLLOW_RIGHT flags ensure that scans will follow the
			 * rightlinks until the downlinks are inserted.
			 */
			GistPageSetNSN(ptr->page, oldnsn);
		}

		START_CRIT_SECTION();

		/*
		 * Must mark buffers dirty before XLogInsert, even though we'll still
		 * be changing their opaque fields below.
		 */
		for (ptr = dist; ptr; ptr = ptr->next)
			MarkBufferDirty(ptr->buffer);
		if (BufferIsValid(leftchildbuf))
			MarkBufferDirty(leftchildbuf);

		/*
		 * The first page in the chain was a temporary working copy meant to
		 * replace the old page. Copy it over the old page.
		 */
		PageRestoreTempPage(dist->page, BufferGetPage(dist->buffer));
		dist->page = BufferGetPage(dist->buffer);

		/* Write the WAL record */
		if (RelationNeedsWAL(rel))
			recptr = gistXLogSplit(rel->rd_node, blkno, is_leaf,
								   dist, oldrlink, oldnsn, leftchildbuf,
								   markfollowright);
		else
			recptr = gistGetFakeLSN(rel);

		for (ptr = dist; ptr; ptr = ptr->next)
		{
			PageSetLSN(ptr->page, recptr);
		}

		/*
		 * Return the new child buffers to the caller.
		 *
		 * If this was a root split, we've already inserted the downlink
		 * pointers, in the form of a new root page. Therefore we can release
		 * all the new buffers, and keep just the root page locked.
		 */
		if (is_rootsplit)
		{
			for (ptr = dist->next; ptr; ptr = ptr->next)
				UnlockReleaseBuffer(ptr->buffer);
		}
	}
	else
	{
		/*
		 * Enough space. We also get here if ntuples==0.
		 */
		START_CRIT_SECTION();

		if (OffsetNumberIsValid(oldoffnum))
			PageIndexTupleDelete(page, oldoffnum);
		gistfillbuffer(page, itup, ntup, InvalidOffsetNumber);

		MarkBufferDirty(buffer);

		if (BufferIsValid(leftchildbuf))
			MarkBufferDirty(leftchildbuf);

		if (RelationNeedsWAL(rel))
		{
			OffsetNumber ndeloffs = 0,
						deloffs[1];

			if (OffsetNumberIsValid(oldoffnum))
			{
				deloffs[0] = oldoffnum;
				ndeloffs = 1;
			}

			recptr = gistXLogUpdate(rel->rd_node, buffer,
									deloffs, ndeloffs, itup, ntup,
									leftchildbuf);

			PageSetLSN(page, recptr);
		}
		else
		{
			recptr = gistGetFakeLSN(rel);
			PageSetLSN(page, recptr);
		}

		if (newblkno)
			*newblkno = blkno;
	}

	/*
	 * If we inserted the downlink for a child page, set NSN and clear
	 * F_FOLLOW_RIGHT flag on the left child, so that concurrent scans know to
	 * follow the rightlink if and only if they looked at the parent page
	 * before we inserted the downlink.
	 *
	 * Note that we do this *after* writing the WAL record. That means that
	 * the possible full page image in the WAL record does not include these
	 * changes, and they must be replayed even if the page is restored from
	 * the full page image. There's a chicken-and-egg problem: if we updated
	 * the child pages first, we wouldn't know the recptr of the WAL record
	 * we're about to write.
	 */
	if (BufferIsValid(leftchildbuf))
	{
		Page		leftpg = BufferGetPage(leftchildbuf);

		GistPageSetNSN(leftpg, recptr);
		GistClearFollowRight(leftpg);

		PageSetLSN(leftpg, recptr);
	}

	END_CRIT_SECTION();

	return is_split;
}
Пример #4
0
static ArrayTuple
gistVacuumUpdate(GistVacuum *gv, BlockNumber blkno, bool needunion)
{
	ArrayTuple	res = {NULL, 0, false};
	Buffer		buffer;
	Page		page,
				tempPage = NULL;
	OffsetNumber i,
				maxoff;
	ItemId		iid;
	int			lenaddon = 4,
				curlenaddon = 0,
				nOffToDelete = 0,
				nBlkToDelete = 0;
	IndexTuple	idxtuple,
			   *addon = NULL;
	bool		needwrite = false;
	OffsetNumber offToDelete[MaxOffsetNumber];
	BlockNumber blkToDelete[MaxOffsetNumber];
	ItemPointerData *completed = NULL;
	int			ncompleted = 0,
				lencompleted = 16;

	vacuum_delay_point();

	buffer = ReadBufferWithStrategy(gv->index, blkno, gv->strategy);
	LockBuffer(buffer, GIST_EXCLUSIVE);
	gistcheckpage(gv->index, buffer);
	page = (Page) BufferGetPage(buffer);
	maxoff = PageGetMaxOffsetNumber(page);

	if (GistPageIsLeaf(page))
	{
		if (GistTuplesDeleted(page))
			needunion = needwrite = true;
	}
	else
	{
		completed = (ItemPointerData *) palloc(sizeof(ItemPointerData) * lencompleted);
		addon = (IndexTuple *) palloc(sizeof(IndexTuple) * lenaddon);

		/* get copy of page to work */
		tempPage = GistPageGetCopyPage(page);

		for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
		{
			ArrayTuple	chldtuple;
			bool		needchildunion;

			iid = PageGetItemId(tempPage, i);
			idxtuple = (IndexTuple) PageGetItem(tempPage, iid);
			needchildunion = (GistTupleIsInvalid(idxtuple)) ? true : false;

			if (needchildunion)
				elog(DEBUG2, "gistVacuumUpdate: need union for block %u",
					 ItemPointerGetBlockNumber(&(idxtuple->t_tid)));

			chldtuple = gistVacuumUpdate(gv, ItemPointerGetBlockNumber(&(idxtuple->t_tid)),
										 needchildunion);
			if (chldtuple.ituplen || chldtuple.emptypage)
			{
				/* update tuple or/and inserts new */
				if (chldtuple.emptypage)
					blkToDelete[nBlkToDelete++] = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
				offToDelete[nOffToDelete++] = i;
				PageIndexTupleDelete(tempPage, i);
				i--;
				maxoff--;
				needwrite = needunion = true;

				if (chldtuple.ituplen)
				{

					Assert(chldtuple.emptypage == false);
					while (curlenaddon + chldtuple.ituplen >= lenaddon)
					{
						lenaddon *= 2;
						addon = (IndexTuple *) repalloc(addon, sizeof(IndexTuple) * lenaddon);
					}

					memcpy(addon + curlenaddon, chldtuple.itup, chldtuple.ituplen * sizeof(IndexTuple));

					curlenaddon += chldtuple.ituplen;

					if (chldtuple.ituplen > 1)
					{
						/*
						 * child was split, so we need mark completion
						 * insert(split)
						 */
						int			j;

						while (ncompleted + chldtuple.ituplen > lencompleted)
						{
							lencompleted *= 2;
							completed = (ItemPointerData *) repalloc(completed, sizeof(ItemPointerData) * lencompleted);
						}
						for (j = 0; j < chldtuple.ituplen; j++)
						{
							ItemPointerCopy(&(chldtuple.itup[j]->t_tid), completed + ncompleted);
							ncompleted++;
						}
					}
					pfree(chldtuple.itup);
				}
			}
		}

		Assert(maxoff == PageGetMaxOffsetNumber(tempPage));

		if (curlenaddon)
		{
			/* insert updated tuples */
			if (gistnospace(tempPage, addon, curlenaddon, InvalidOffsetNumber, 0))
			{
				/* there is no space on page to insert tuples */
				res = vacuumSplitPage(gv, tempPage, buffer, addon, curlenaddon);
				tempPage = NULL;	/* vacuumSplitPage() free tempPage */
				needwrite = needunion = false;	/* gistSplit already forms
												 * unions and writes pages */
			}
			else
				/* enough free space */
				gistfillbuffer(gv->index, tempPage, addon, curlenaddon, InvalidOffsetNumber);
		}
	}

	/*
	 * If page is empty, we should remove pointer to it before deleting page
	 * (except root)
	 */

	if (blkno != GIST_ROOT_BLKNO && (PageIsEmpty(page) || (tempPage && PageIsEmpty(tempPage))))
	{
		/*
		 * New version of page is empty, so leave it unchanged, upper call
		 * will mark our page as deleted. In case of page split we never will
		 * be here...
		 *
		 * If page was empty it can't become non-empty during processing
		 */
		res.emptypage = true;
		UnlockReleaseBuffer(buffer);
	}
	else
	{
		/* write page and remove its childs if it need */

		START_CRIT_SECTION();

		if (tempPage && needwrite)
		{
			PageRestoreTempPage(tempPage, page);
			tempPage = NULL;
		}

		/* Empty index */
		if (PageIsEmpty(page) && blkno == GIST_ROOT_BLKNO)
		{
			needwrite = true;
			GistPageSetLeaf(page);
		}


		if (needwrite)
		{
			MarkBufferDirty(buffer);
			GistClearTuplesDeleted(page);

			if (!gv->index->rd_istemp)
			{
				XLogRecData *rdata;
				XLogRecPtr	recptr;
				char	   *xlinfo;

				rdata = formUpdateRdata(gv->index->rd_node, buffer,
										offToDelete, nOffToDelete,
										addon, curlenaddon, NULL);
				xlinfo = rdata->next->data;

				recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_UPDATE, rdata);
				PageSetLSN(page, recptr);
				PageSetTLI(page, ThisTimeLineID);

				pfree(xlinfo);
				pfree(rdata);
			}
			else
				PageSetLSN(page, XLogRecPtrForTemp);
		}

		END_CRIT_SECTION();

		if (needunion && !PageIsEmpty(page))
		{
			res.itup = (IndexTuple *) palloc(sizeof(IndexTuple));
			res.ituplen = 1;
			res.itup[0] = PageMakeUnionKey(gv, buffer);
		}

		UnlockReleaseBuffer(buffer);

		/* delete empty children, now we havn't any links to pointed subtrees */
		for (i = 0; i < nBlkToDelete; i++)
			gistDeleteSubtree(gv, blkToDelete[i]);

		if (ncompleted && !gv->index->rd_istemp)
			gistxlogInsertCompletion(gv->index->rd_node, completed, ncompleted);
	}


	for (i = 0; i < curlenaddon; i++)
		pfree(addon[i]);
	if (addon)
		pfree(addon);
	if (completed)
		pfree(completed);
	if (tempPage)
		pfree(tempPage);

	return res;
}
Пример #5
0
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++;
		}

		/* saves old rightlink */
		if (state->stack->blkno != GIST_ROOT_BLKNO)
			rrlink = GistPageGetOpaque(dist->page)->rightlink;

		START_CRIT_SECTION();

		/*
		 * must mark buffers dirty before XLogInsert, even though we'll still
		 * be changing their opaque fields below. set up right links.
		 */
		for (ptr = dist; ptr; ptr = ptr->next)
		{
			MarkBufferDirty(ptr->buffer);
			GistPageGetOpaque(ptr->page)->rightlink = (ptr->next) ?
				ptr->next->block.blkno : rrlink;
		}

		/* restore splitted non-root page */
		if (state->stack->blkno != GIST_ROOT_BLKNO)
		{
			PageRestoreTempPage(dist->page, BufferGetPage(dist->buffer));
			dist->page = BufferGetPage(dist->buffer);
		}

		if (!state->r->rd_istemp)
		{
			XLogRecPtr	recptr;
			XLogRecData *rdata;

			rdata = formSplitRdata(state->r, state->stack->blkno,
								   is_leaf, &(state->key), dist);

			recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_SPLIT, rdata);

			for (ptr = dist; ptr; ptr = ptr->next)
			{
				PageSetLSN(ptr->page, recptr);
				PageSetTLI(ptr->page, ThisTimeLineID);
			}
		}
		else
		{
			for (ptr = dist; ptr; ptr = ptr->next)
			{
				PageSetLSN(ptr->page, XLogRecPtrForTemp);
			}
		}

		/* set up NSN */
		oldnsn = GistPageGetOpaque(dist->page)->nsn;
		if (state->stack->blkno == GIST_ROOT_BLKNO)
			/* if root split we should put initial value */
			oldnsn = PageGetLSN(dist->page);

		for (ptr = dist; ptr; ptr = ptr->next)
		{
			/* only for last set oldnsn */
			GistPageGetOpaque(ptr->page)->nsn = (ptr->next) ?
				PageGetLSN(ptr->page) : oldnsn;
		}

		/*
		 * release buffers, if it was a root split then release all buffers
		 * because we create all buffers
		 */
		ptr = (state->stack->blkno == GIST_ROOT_BLKNO) ? dist : dist->next;
		for (; ptr; ptr = ptr->next)
			UnlockReleaseBuffer(ptr->buffer);

		if (state->stack->blkno == GIST_ROOT_BLKNO)
		{
			gistnewroot(state->r, state->stack->buffer, state->itup, state->ituplen, &(state->key));
			state->needInsertComplete = false;
		}

		END_CRIT_SECTION();
	}
	else
	{
		/* enough space */
		START_CRIT_SECTION();

		if (!is_leaf)
			PageIndexTupleDelete(state->stack->page, state->stack->childoffnum);
		gistfillbuffer(state->r, state->stack->page, state->itup, state->ituplen, InvalidOffsetNumber);

		MarkBufferDirty(state->stack->buffer);

		if (!state->r->rd_istemp)
		{
			OffsetNumber noffs = 0,
						offs[1];
			XLogRecPtr	recptr;
			XLogRecData *rdata;

			if (!is_leaf)
			{
				/* only on inner page we should delete previous version */
				offs[0] = state->stack->childoffnum;
				noffs = 1;
			}

			rdata = formUpdateRdata(state->r, state->stack->buffer,
									offs, noffs,
									state->itup, state->ituplen,
									&(state->key));

			recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_UPDATE, rdata);
			PageSetLSN(state->stack->page, recptr);
			PageSetTLI(state->stack->page, ThisTimeLineID);
		}
		else
			PageSetLSN(state->stack->page, XLogRecPtrForTemp);

		if (state->stack->blkno == GIST_ROOT_BLKNO)
			state->needInsertComplete = false;

		END_CRIT_SECTION();

		if (state->ituplen > 1)
		{						/* previous is_splitted==true */

			/*
			 * child was splited, so we must form union for insertion in
			 * parent
			 */
			IndexTuple	newtup = gistunion(state->r, state->itup, state->ituplen, giststate);

			ItemPointerSetBlockNumber(&(newtup->t_tid), state->stack->blkno);
			state->itup[0] = newtup;
			state->ituplen = 1;
		}
		else if (is_leaf)
		{
			/*
			 * itup[0] store key to adjust parent, we set it to valid to
			 * correct check by GistTupleIsInvalid macro in gistgetadjusted()
			 */
			ItemPointerSetBlockNumber(&(state->itup[0]->t_tid), state->stack->blkno);
			GistTupleSetValid(state->itup[0]);
		}
	}
	return is_splitted;
}
Пример #6
0
static void
gistRedoPageSplitRecord(XLogRecPtr lsn, XLogRecord *record)
{
	gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
	PageSplitRecord xlrec;
	Buffer		buffer;
	Page		page;
	int			i;
	bool		isrootsplit = false;

	if (BlockNumberIsValid(xldata->leftchild))
		gistRedoClearFollowRight(xldata->node, lsn, xldata->leftchild);
	decodePageSplitRecord(&xlrec, record);

	/* 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;
			GistPageGetOpaque(page)->nsn = 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;
			GistPageGetOpaque(page)->nsn = xldata->orignsn;
			if (i < xlrec.data->npage - 1 && !isrootsplit)
				GistMarkFollowRight(page);
			else
				GistClearFollowRight(page);
		}

		PageSetLSN(page, lsn);
		PageSetTLI(page, ThisTimeLineID);
		MarkBufferDirty(buffer);
		UnlockReleaseBuffer(buffer);
	}
}
Пример #7
0
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);
}