/*
* 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;
}
static void
btree_xlog_split(bool onleft, bool isroot, XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record);
bool isleaf = (xlrec->level == 0);
Buffer lbuf;
Buffer rbuf;
Page rpage;
BTPageOpaque ropaque;
char *datapos;
Size datalen;
Item left_hikey = NULL;
Size left_hikeysz = 0;
BlockNumber leftsib;
BlockNumber rightsib;
BlockNumber rnext;
XLogRecGetBlockTag(record, 0, NULL, NULL, &leftsib);
XLogRecGetBlockTag(record, 1, NULL, NULL, &rightsib);
if (!XLogRecGetBlockTag(record, 2, NULL, NULL, &rnext))
rnext = P_NONE;
/*
* Clear the incomplete split flag on the left sibling of the child page
* this is a downlink for. (Like in btree_xlog_insert, this can be done
* before locking the other pages)
*/
if (!isleaf)
_bt_clear_incomplete_split(record, 3);
/* Reconstruct right (new) sibling page from scratch */
rbuf = XLogInitBufferForRedo(record, 1);
datapos = XLogRecGetBlockData(record, 1, &datalen);
rpage = (Page) BufferGetPage(rbuf);
_bt_pageinit(rpage, BufferGetPageSize(rbuf));
ropaque = (BTPageOpaque) PageGetSpecialPointer(rpage);
ropaque->btpo_prev = leftsib;
ropaque->btpo_next = rnext;
ropaque->btpo.level = xlrec->level;
ropaque->btpo_flags = isleaf ? BTP_LEAF : 0;
ropaque->btpo_cycleid = 0;
_bt_restore_page(rpage, datapos, datalen);
/*
* On leaf level, the high key of the left page is equal to the first key
* on the right page.
*/
if (isleaf)
{
ItemId hiItemId = PageGetItemId(rpage, P_FIRSTDATAKEY(ropaque));
left_hikey = PageGetItem(rpage, hiItemId);
left_hikeysz = ItemIdGetLength(hiItemId);
}
PageSetLSN(rpage, lsn);
MarkBufferDirty(rbuf);
/* don't release the buffer yet; we touch right page's first item below */
/* Now reconstruct left (original) sibling page */
if (XLogReadBufferForRedo(record, 0, &lbuf) == BLK_NEEDS_REDO)
{
/*
* To retain the same physical order of the tuples that they had, we
* initialize a temporary empty page for the left page and add all the
* items to that in item number order. This mirrors how _bt_split()
* works. It's not strictly required to retain the same physical
* order, as long as the items are in the correct item number order,
* but it helps debugging. See also _bt_restore_page(), which does
* the same for the right page.
*/
Page lpage = (Page) BufferGetPage(lbuf);
BTPageOpaque lopaque = (BTPageOpaque) PageGetSpecialPointer(lpage);
OffsetNumber off;
Item newitem = NULL;
Size newitemsz = 0;
Page newlpage;
OffsetNumber leftoff;
datapos = XLogRecGetBlockData(record, 0, &datalen);
if (onleft)
{
newitem = (Item) datapos;
newitemsz = MAXALIGN(IndexTupleSize(newitem));
datapos += newitemsz;
datalen -= newitemsz;
}
/* Extract left hikey and its size (assuming 16-bit alignment) */
if (!isleaf)
{
left_hikey = (Item) datapos;
left_hikeysz = MAXALIGN(IndexTupleSize(left_hikey));
datapos += left_hikeysz;
datalen -= left_hikeysz;
}
Assert(datalen == 0);
newlpage = PageGetTempPageCopySpecial(lpage);
/* Set high key */
leftoff = P_HIKEY;
if (PageAddItem(newlpage, left_hikey, left_hikeysz,
P_HIKEY, false, false) == InvalidOffsetNumber)
elog(PANIC, "failed to add high key to left page after split");
leftoff = OffsetNumberNext(leftoff);
for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstright; off++)
{
ItemId itemid;
Size itemsz;
Item item;
/* add the new item if it was inserted on left page */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
itemid = PageGetItemId(lpage, off);
itemsz = ItemIdGetLength(itemid);
item = PageGetItem(lpage, itemid);
if (PageAddItem(newlpage, item, itemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add old item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
/* cope with possibility that newitem goes at the end */
if (onleft && off == xlrec->newitemoff)
{
if (PageAddItem(newlpage, newitem, newitemsz, leftoff,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add new item to left page after split");
leftoff = OffsetNumberNext(leftoff);
}
PageRestoreTempPage(newlpage, lpage);
/* Fix opaque fields */
lopaque->btpo_flags = BTP_INCOMPLETE_SPLIT;
if (isleaf)
lopaque->btpo_flags |= BTP_LEAF;
lopaque->btpo_next = rightsib;
lopaque->btpo_cycleid = 0;
PageSetLSN(lpage, lsn);
MarkBufferDirty(lbuf);
}
/* We no longer need the buffers */
if (BufferIsValid(lbuf))
UnlockReleaseBuffer(lbuf);
UnlockReleaseBuffer(rbuf);
/*
* Fix left-link of the page to the right of the new right sibling.
*
* Note: in normal operation, we do this while still holding lock on the
* two split pages. However, that's not necessary for correctness in WAL
* replay, because no other index update can be in progress, and readers
* will cope properly when following an obsolete left-link.
*/
if (rnext != P_NONE)
{
Buffer buffer;
if (XLogReadBufferForRedo(record, 2, &buffer) == BLK_NEEDS_REDO)
{
Page page = (Page) BufferGetPage(buffer);
BTPageOpaque pageop = (BTPageOpaque) PageGetSpecialPointer(page);
pageop->btpo_prev = rightsib;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
}
