/*
* Scan all items on the GiST index page identified by *pageItem, and insert
* them into the queue (or directly to output areas)
*
* scan: index scan we are executing
* pageItem: search queue item identifying an index page to scan
* myDistances: distances array associated with pageItem, or NULL at the root
* tbm: if not NULL, gistgetbitmap's output bitmap
* ntids: if not NULL, gistgetbitmap's output tuple counter
*
* If tbm/ntids aren't NULL, we are doing an amgetbitmap scan, and heap
* tuples should be reported directly into the bitmap. If they are NULL,
* we're doing a plain or ordered indexscan. For a plain indexscan, heap
* tuple TIDs are returned into so->pageData[]. For an ordered indexscan,
* heap tuple TIDs are pushed into individual search queue items.
*
* If we detect that the index page has split since we saw its downlink
* in the parent, we push its new right sibling onto the queue so the
* sibling will be processed next.
*/
static void
gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
TIDBitmap *tbm, int64 *ntids)
{
GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
Buffer buffer;
Page page;
GISTPageOpaque opaque;
OffsetNumber maxoff;
OffsetNumber i;
GISTSearchTreeItem *tmpItem = so->tmpTreeItem;
bool isNew;
MemoryContext oldcxt;
Assert(!GISTSearchItemIsHeap(*pageItem));
buffer = ReadBuffer(scan->indexRelation, pageItem->blkno);
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(scan->indexRelation, buffer);
page = BufferGetPage(buffer);
opaque = GistPageGetOpaque(page);
/*
* Check if we need to follow the rightlink. We need to follow it if the
* page was concurrently split since we visited the parent (in which case
* parentlsn < nsn), or if the system crashed after a page split but
* before the downlink was inserted into the parent.
*/
if (!XLogRecPtrIsInvalid(pageItem->data.parentlsn) &&
(GistFollowRight(page) ||
pageItem->data.parentlsn < GistPageGetNSN(page)) &&
opaque->rightlink != InvalidBlockNumber /* sanity check */ )
{
/* There was a page split, follow right link to add pages */
GISTSearchItem *item;
/* This can't happen when starting at the root */
Assert(myDistances != NULL);
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for the right sibling index page */
item = palloc(sizeof(GISTSearchItem));
item->next = NULL;
item->blkno = opaque->rightlink;
item->data.parentlsn = pageItem->data.parentlsn;
/* Insert it into the queue using same distances as for this page */
tmpItem->head = item;
tmpItem->lastHeap = NULL;
memcpy(tmpItem->distances, myDistances,
sizeof(double) * scan->numberOfOrderBys);
(void) rb_insert(so->queue, (RBNode *) tmpItem, &isNew);
MemoryContextSwitchTo(oldcxt);
}
so->nPageData = so->curPageData = 0;
/*
* check all tuples on page
*/
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
IndexTuple it = (IndexTuple) PageGetItem(page, PageGetItemId(page, i));
bool match;
bool recheck;
/*
* Must call gistindex_keytest in tempCxt, and clean up any leftover
* junk afterward.
*/
oldcxt = MemoryContextSwitchTo(so->giststate->tempCxt);
match = gistindex_keytest(scan, it, page, i, &recheck);
MemoryContextSwitchTo(oldcxt);
MemoryContextReset(so->giststate->tempCxt);
/* Ignore tuple if it doesn't match */
if (!match)
continue;
if (tbm && GistPageIsLeaf(page))
{
/*
* getbitmap scan, so just push heap tuple TIDs into the bitmap
* without worrying about ordering
*/
tbm_add_tuples(tbm, &it->t_tid, 1, recheck);
(*ntids)++;
}
else if (scan->numberOfOrderBys == 0 && GistPageIsLeaf(page))
{
/*
* Non-ordered scan, so report heap tuples in so->pageData[]
*/
so->pageData[so->nPageData].heapPtr = it->t_tid;
so->pageData[so->nPageData].recheck = recheck;
so->nPageData++;
}
else
{
/*
* Must push item into search queue. We get here for any lower
* index page, and also for heap tuples if doing an ordered
* search.
*/
GISTSearchItem *item;
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for this item */
item = palloc(sizeof(GISTSearchItem));
item->next = NULL;
if (GistPageIsLeaf(page))
{
/* Creating heap-tuple GISTSearchItem */
item->blkno = InvalidBlockNumber;
item->data.heap.heapPtr = it->t_tid;
item->data.heap.recheck = recheck;
}
else
{
/* Creating index-page GISTSearchItem */
item->blkno = ItemPointerGetBlockNumber(&it->t_tid);
/*
* LSN of current page is lsn of parent page for child. We
* only have a shared lock, so we need to get the LSN
* atomically.
*/
item->data.parentlsn = BufferGetLSNAtomic(buffer);
}
/* Insert it into the queue using new distance data */
tmpItem->head = item;
tmpItem->lastHeap = GISTSearchItemIsHeap(*item) ? item : NULL;
memcpy(tmpItem->distances, so->distances,
sizeof(double) * scan->numberOfOrderBys);
(void) rb_insert(so->queue, (RBNode *) tmpItem, &isNew);
MemoryContextSwitchTo(oldcxt);
}
}
UnlockReleaseBuffer(buffer);
}
/*
* Write a backup block if needed when we are setting a hint. Note that
* this may be called for a variety of page types, not just heaps.
*
* Callable while holding just share lock on the buffer content.
*
* We can't use the plain backup block mechanism since that relies on the
* Buffer being exclusively locked. Since some modifications (setting LSN, hint
* bits) are allowed in a sharelocked buffer that can lead to wal checksum
* failures. So instead we copy the page and insert the copied data as normal
* record data.
*
* We only need to do something if page has not yet been full page written in
* this checkpoint round. The LSN of the inserted wal record is returned if we
* had to write, InvalidXLogRecPtr otherwise.
*
* It is possible that multiple concurrent backends could attempt to write WAL
* records. In that case, multiple copies of the same block would be recorded
* in separate WAL records by different backends, though that is still OK from
* a correctness perspective.
*/
XLogRecPtr
XLogSaveBufferForHint(Buffer buffer, bool buffer_std)
{
XLogRecPtr recptr = InvalidXLogRecPtr;
XLogRecPtr lsn;
XLogRecPtr RedoRecPtr;
/*
* Ensure no checkpoint can change our view of RedoRecPtr.
*/
Assert(MyPgXact->delayChkpt);
/*
* Update RedoRecPtr so that we can make the right decision
*/
RedoRecPtr = GetRedoRecPtr();
/*
* We assume page LSN is first data on *every* page that can be passed to
* XLogInsert, whether it has the standard page layout or not. Since we're
* only holding a share-lock on the page, we must take the buffer header
* lock when we look at the LSN.
*/
lsn = BufferGetLSNAtomic(buffer);
if (lsn <= RedoRecPtr)
{
int flags;
char copied_buffer[BLCKSZ];
char *origdata = (char *) BufferGetBlock(buffer);
RelFileNode rnode;
ForkNumber forkno;
BlockNumber blkno;
/*
* Copy buffer so we don't have to worry about concurrent hint bit or
* lsn updates. We assume pd_lower/upper cannot be changed without an
* exclusive lock, so the contents bkp are not racy.
*/
if (buffer_std)
{
/* Assume we can omit data between pd_lower and pd_upper */
Page page = BufferGetPage(buffer);
uint16 lower = ((PageHeader) page)->pd_lower;
uint16 upper = ((PageHeader) page)->pd_upper;
memcpy(copied_buffer, origdata, lower);
memcpy(copied_buffer + upper, origdata + upper, BLCKSZ - upper);
}
else
memcpy(copied_buffer, origdata, BLCKSZ);
XLogBeginInsert();
flags = REGBUF_FORCE_IMAGE;
if (buffer_std)
flags |= REGBUF_STANDARD;
BufferGetTag(buffer, &rnode, &forkno, &blkno);
XLogRegisterBlock(0, &rnode, forkno, blkno, copied_buffer, flags);
recptr = XLogInsert(RM_XLOG_ID, XLOG_FPI_FOR_HINT);
}
return recptr;
}
/*
* Bulk deletion of all index entries pointing to a set of heap tuples and
* check invalid tuples left after upgrade.
* The set of target tuples is specified via a callback routine that tells
* whether any given heap tuple (identified by ItemPointer) is being deleted.
*
* Result: a palloc'd struct containing statistical info for VACUUM displays.
*/
IndexBulkDeleteResult *
gistbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback, void *callback_state)
{
Relation rel = info->index;
GistBDItem *stack,
*ptr;
/* first time through? */
if (stats == NULL)
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
/* we'll re-count the tuples each time */
stats->estimated_count = false;
stats->num_index_tuples = 0;
stack = (GistBDItem *) palloc0(sizeof(GistBDItem));
stack->blkno = GIST_ROOT_BLKNO;
while (stack)
{
Buffer buffer;
Page page;
OffsetNumber i,
maxoff;
IndexTuple idxtuple;
ItemId iid;
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, stack->blkno,
RBM_NORMAL, info->strategy);
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(rel, buffer);
page = (Page) BufferGetPage(buffer);
if (GistPageIsLeaf(page))
{
OffsetNumber todelete[MaxOffsetNumber];
int ntodelete = 0;
LockBuffer(buffer, GIST_UNLOCK);
LockBuffer(buffer, GIST_EXCLUSIVE);
page = (Page) BufferGetPage(buffer);
if (stack->blkno == GIST_ROOT_BLKNO && !GistPageIsLeaf(page))
{
/* only the root can become non-leaf during relock */
UnlockReleaseBuffer(buffer);
/* one more check */
continue;
}
/*
* check for split proceeded after look at parent, we should check
* it after relock
*/
pushStackIfSplited(page, stack);
/*
* Remove deletable tuples from page
*/
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
if (callback(&(idxtuple->t_tid), callback_state))
todelete[ntodelete++] = i;
else
stats->num_index_tuples += 1;
}
stats->tuples_removed += ntodelete;
if (ntodelete)
{
START_CRIT_SECTION();
MarkBufferDirty(buffer);
PageIndexMultiDelete(page, todelete, ntodelete);
GistMarkTuplesDeleted(page);
if (RelationNeedsWAL(rel))
{
XLogRecPtr recptr;
recptr = gistXLogUpdate(buffer,
todelete, ntodelete,
NULL, 0, InvalidBuffer);
PageSetLSN(page, recptr);
}
else
PageSetLSN(page, gistGetFakeLSN(rel));
END_CRIT_SECTION();
}
}
else
{
/* check for split proceeded after look at parent */
pushStackIfSplited(page, stack);
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
ptr = (GistBDItem *) palloc(sizeof(GistBDItem));
ptr->blkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
ptr->parentlsn = BufferGetLSNAtomic(buffer);
ptr->next = stack->next;
stack->next = ptr;
if (GistTupleIsInvalid(idxtuple))
ereport(LOG,
(errmsg("index \"%s\" contains an inner tuple marked as invalid",
RelationGetRelationName(rel)),
errdetail("This is caused by an incomplete page split at crash recovery before upgrading to PostgreSQL 9.1."),
errhint("Please REINDEX it.")));
}
}
UnlockReleaseBuffer(buffer);
ptr = stack->next;
pfree(stack);
stack = ptr;
vacuum_delay_point();
}
return stats;
}
/*
* gistkillitems() -- set LP_DEAD state for items an indexscan caller has
* told us were killed.
*
* We re-read page here, so it's important to check page LSN. If the page
* has been modified since the last read (as determined by LSN), we cannot
* flag any entries because it is possible that the old entry was vacuumed
* away and the TID was re-used by a completely different heap tuple.
*/
static void
gistkillitems(IndexScanDesc scan)
{
GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
Buffer buffer;
Page page;
OffsetNumber offnum;
ItemId iid;
int i;
bool killedsomething = false;
Assert(so->curBlkno != InvalidBlockNumber);
Assert(!XLogRecPtrIsInvalid(so->curPageLSN));
Assert(so->killedItems != NULL);
buffer = ReadBuffer(scan->indexRelation, so->curBlkno);
if (!BufferIsValid(buffer))
return;
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(scan->indexRelation, buffer);
page = BufferGetPage(buffer);
/*
* If page LSN differs it means that the page was modified since the last
* read. killedItems could be not valid so LP_DEAD hints applying is not
* safe.
*/
if (BufferGetLSNAtomic(buffer) != so->curPageLSN)
{
UnlockReleaseBuffer(buffer);
so->numKilled = 0; /* reset counter */
return;
}
Assert(GistPageIsLeaf(page));
/*
* Mark all killedItems as dead. We need no additional recheck, because,
* if page was modified, pageLSN must have changed.
*/
for (i = 0; i < so->numKilled; i++)
{
offnum = so->killedItems[i];
iid = PageGetItemId(page, offnum);
ItemIdMarkDead(iid);
killedsomething = true;
}
if (killedsomething)
{
GistMarkPageHasGarbage(page);
MarkBufferDirtyHint(buffer, true);
}
UnlockReleaseBuffer(buffer);
/*
* Always reset the scan state, so we don't look for same items on other
* pages.
*/
so->numKilled = 0;
}
/*
* Scan all items on the GiST index page identified by *pageItem, and insert
* them into the queue (or directly to output areas)
*
* scan: index scan we are executing
* pageItem: search queue item identifying an index page to scan
* myDistances: distances array associated with pageItem, or NULL at the root
* tbm: if not NULL, gistgetbitmap's output bitmap
* ntids: if not NULL, gistgetbitmap's output tuple counter
*
* If tbm/ntids aren't NULL, we are doing an amgetbitmap scan, and heap
* tuples should be reported directly into the bitmap. If they are NULL,
* we're doing a plain or ordered indexscan. For a plain indexscan, heap
* tuple TIDs are returned into so->pageData[]. For an ordered indexscan,
* heap tuple TIDs are pushed into individual search queue items. In an
* index-only scan, reconstructed index tuples are returned along with the
* TIDs.
*
* If we detect that the index page has split since we saw its downlink
* in the parent, we push its new right sibling onto the queue so the
* sibling will be processed next.
*/
static void
gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
TIDBitmap *tbm, int64 *ntids)
{
GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
GISTSTATE *giststate = so->giststate;
Relation r = scan->indexRelation;
Buffer buffer;
Page page;
GISTPageOpaque opaque;
OffsetNumber maxoff;
OffsetNumber i;
MemoryContext oldcxt;
Assert(!GISTSearchItemIsHeap(*pageItem));
buffer = ReadBuffer(scan->indexRelation, pageItem->blkno);
LockBuffer(buffer, GIST_SHARE);
PredicateLockPage(r, BufferGetBlockNumber(buffer), scan->xs_snapshot);
gistcheckpage(scan->indexRelation, buffer);
page = BufferGetPage(buffer);
TestForOldSnapshot(scan->xs_snapshot, r, page);
opaque = GistPageGetOpaque(page);
/*
* Check if we need to follow the rightlink. We need to follow it if the
* page was concurrently split since we visited the parent (in which case
* parentlsn < nsn), or if the system crashed after a page split but
* before the downlink was inserted into the parent.
*/
if (!XLogRecPtrIsInvalid(pageItem->data.parentlsn) &&
(GistFollowRight(page) ||
pageItem->data.parentlsn < GistPageGetNSN(page)) &&
opaque->rightlink != InvalidBlockNumber /* sanity check */ )
{
/* There was a page split, follow right link to add pages */
GISTSearchItem *item;
/* This can't happen when starting at the root */
Assert(myDistances != NULL);
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for the right sibling index page */
item = palloc(SizeOfGISTSearchItem(scan->numberOfOrderBys));
item->blkno = opaque->rightlink;
item->data.parentlsn = pageItem->data.parentlsn;
/* Insert it into the queue using same distances as for this page */
memcpy(item->distances, myDistances,
sizeof(double) * scan->numberOfOrderBys);
pairingheap_add(so->queue, &item->phNode);
MemoryContextSwitchTo(oldcxt);
}
so->nPageData = so->curPageData = 0;
scan->xs_hitup = NULL; /* might point into pageDataCxt */
if (so->pageDataCxt)
MemoryContextReset(so->pageDataCxt);
/*
* We save the LSN of the page as we read it, so that we know whether it
* safe to apply LP_DEAD hints to the page later. This allows us to drop
* the pin for MVCC scans, which allows vacuum to avoid blocking.
*/
so->curPageLSN = BufferGetLSNAtomic(buffer);
/*
* check all tuples on page
*/
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
ItemId iid = PageGetItemId(page, i);
IndexTuple it;
bool match;
bool recheck;
bool recheck_distances;
/*
* If the scan specifies not to return killed tuples, then we treat a
* killed tuple as not passing the qual.
*/
if (scan->ignore_killed_tuples && ItemIdIsDead(iid))
continue;
it = (IndexTuple) PageGetItem(page, iid);
/*
* Must call gistindex_keytest in tempCxt, and clean up any leftover
* junk afterward.
*/
oldcxt = MemoryContextSwitchTo(so->giststate->tempCxt);
match = gistindex_keytest(scan, it, page, i,
&recheck, &recheck_distances);
MemoryContextSwitchTo(oldcxt);
MemoryContextReset(so->giststate->tempCxt);
/* Ignore tuple if it doesn't match */
if (!match)
continue;
if (tbm && GistPageIsLeaf(page))
{
/*
* getbitmap scan, so just push heap tuple TIDs into the bitmap
* without worrying about ordering
*/
tbm_add_tuples(tbm, &it->t_tid, 1, recheck);
(*ntids)++;
}
else if (scan->numberOfOrderBys == 0 && GistPageIsLeaf(page))
{
/*
* Non-ordered scan, so report tuples in so->pageData[]
*/
so->pageData[so->nPageData].heapPtr = it->t_tid;
so->pageData[so->nPageData].recheck = recheck;
so->pageData[so->nPageData].offnum = i;
/*
* In an index-only scan, also fetch the data from the tuple. The
* reconstructed tuples are stored in pageDataCxt.
*/
if (scan->xs_want_itup)
{
oldcxt = MemoryContextSwitchTo(so->pageDataCxt);
so->pageData[so->nPageData].recontup =
gistFetchTuple(giststate, r, it);
MemoryContextSwitchTo(oldcxt);
}
so->nPageData++;
}
else
{
/*
* Must push item into search queue. We get here for any lower
* index page, and also for heap tuples if doing an ordered
* search.
*/
GISTSearchItem *item;
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for this item */
item = palloc(SizeOfGISTSearchItem(scan->numberOfOrderBys));
if (GistPageIsLeaf(page))
{
/* Creating heap-tuple GISTSearchItem */
item->blkno = InvalidBlockNumber;
item->data.heap.heapPtr = it->t_tid;
item->data.heap.recheck = recheck;
item->data.heap.recheckDistances = recheck_distances;
/*
* In an index-only scan, also fetch the data from the tuple.
*/
if (scan->xs_want_itup)
item->data.heap.recontup = gistFetchTuple(giststate, r, it);
}
else
{
/* Creating index-page GISTSearchItem */
item->blkno = ItemPointerGetBlockNumber(&it->t_tid);
/*
* LSN of current page is lsn of parent page for child. We
* only have a shared lock, so we need to get the LSN
* atomically.
*/
item->data.parentlsn = BufferGetLSNAtomic(buffer);
}
/* Insert it into the queue using new distance data */
memcpy(item->distances, so->distances,
sizeof(double) * scan->numberOfOrderBys);
pairingheap_add(so->queue, &item->phNode);
MemoryContextSwitchTo(oldcxt);
}
}
UnlockReleaseBuffer(buffer);
}
/*
* Traverse the tree to find path from root page to specified "child" block.
*
* returns a new insertion stack, starting from the parent of "child", up
* to the root. *downlinkoffnum is set to the offset of the downlink in the
* direct parent of child.
*
* To prevent deadlocks, this should lock only one page at a time.
*/
static GISTInsertStack *
gistFindPath(Relation r, BlockNumber child, OffsetNumber *downlinkoffnum)
{
Page page;
Buffer buffer;
OffsetNumber i,
maxoff;
ItemId iid;
IndexTuple idxtuple;
List *fifo;
GISTInsertStack *top,
*ptr;
BlockNumber blkno;
top = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
top->blkno = GIST_ROOT_BLKNO;
top->downlinkoffnum = InvalidOffsetNumber;
fifo = list_make1(top);
while (fifo != NIL)
{
/* Get next page to visit */
top = linitial(fifo);
fifo = list_delete_first(fifo);
buffer = ReadBuffer(r, top->blkno);
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(r, buffer);
page = (Page) BufferGetPage(buffer);
if (GistPageIsLeaf(page))
{
/*
* Because we scan the index top-down, all the rest of the pages
* in the queue must be leaf pages as well.
*/
UnlockReleaseBuffer(buffer);
break;
}
top->lsn = BufferGetLSNAtomic(buffer);
/*
* If F_FOLLOW_RIGHT is set, the page to the right doesn't have a
* downlink. This should not normally happen..
*/
if (GistFollowRight(page))
elog(ERROR, "concurrent GiST page split was incomplete");
if (top->parent && top->parent->lsn < GistPageGetNSN(page) &&
GistPageGetOpaque(page)->rightlink != InvalidBlockNumber /* sanity check */ )
{
/*
* Page was split while we looked elsewhere. We didn't see the
* downlink to the right page when we scanned the parent, so add
* it to the queue now.
*
* Put the right page ahead of the queue, so that we visit it
* next. That's important, because if this is the lowest internal
* level, just above leaves, we might already have queued up some
* leaf pages, and we assume that there can't be any non-leaf
* pages behind leaf pages.
*/
ptr = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
ptr->blkno = GistPageGetOpaque(page)->rightlink;
ptr->downlinkoffnum = InvalidOffsetNumber;
ptr->parent = top->parent;
fifo = lcons(ptr, fifo);
}
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
blkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
if (blkno == child)
{
/* Found it! */
UnlockReleaseBuffer(buffer);
*downlinkoffnum = i;
return top;
}
else
{
/* Append this child to the list of pages to visit later */
ptr = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
ptr->blkno = blkno;
ptr->downlinkoffnum = i;
ptr->parent = top;
fifo = lappend(fifo, ptr);
}
}
UnlockReleaseBuffer(buffer);
}
elog(ERROR, "failed to re-find parent of a page in index \"%s\", block %u",
RelationGetRelationName(r), child);
return NULL; /* keep compiler quiet */
}
/*
* Workhouse routine for doing insertion into a GiST index. Note that
* this routine assumes it is invoked in a short-lived memory context,
* so it does not bother releasing palloc'd allocations.
*/
void
gistdoinsert(Relation r, IndexTuple itup, Size freespace,
GISTSTATE *giststate, Relation heapRel, bool is_build)
{
ItemId iid;
IndexTuple idxtuple;
GISTInsertStack firststack;
GISTInsertStack *stack;
GISTInsertState state;
bool xlocked = false;
memset(&state, 0, sizeof(GISTInsertState));
state.freespace = freespace;
state.r = r;
state.heapRel = heapRel;
state.is_build = is_build;
/* Start from the root */
firststack.blkno = GIST_ROOT_BLKNO;
firststack.lsn = 0;
firststack.parent = NULL;
firststack.downlinkoffnum = InvalidOffsetNumber;
state.stack = stack = &firststack;
/*
* Walk down along the path of smallest penalty, updating the parent
* pointers with the key we're inserting as we go. If we crash in the
* middle, the tree is consistent, although the possible parent updates
* were a waste.
*/
for (;;)
{
if (XLogRecPtrIsInvalid(stack->lsn))
stack->buffer = ReadBuffer(state.r, stack->blkno);
/*
* Be optimistic and grab shared lock first. Swap it for an exclusive
* lock later if we need to update the page.
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_SHARE);
gistcheckpage(state.r, stack->buffer);
}
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = xlocked ?
PageGetLSN(stack->page) : BufferGetLSNAtomic(stack->buffer);
Assert(!RelationNeedsWAL(state.r) || !XLogRecPtrIsInvalid(stack->lsn));
/*
* If this page was split but the downlink was never inserted to the
* parent because the inserting backend crashed before doing that, fix
* that now.
*/
if (GistFollowRight(stack->page))
{
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
/* someone might've completed the split when we unlocked */
if (!GistFollowRight(stack->page))
continue;
}
gistfixsplit(&state, giststate);
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (stack->blkno != GIST_ROOT_BLKNO &&
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* Concurrent split detected. There's no guarantee that the
* downlink for this page is consistent with the tuple we're
* inserting anymore, so go back to parent and rechoose the best
* child.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (!GistPageIsLeaf(stack->page))
{
/*
* This is an internal page so continue to walk down the tree.
* Find the child node that has the minimum insertion penalty.
*/
BlockNumber childblkno;
IndexTuple newtup;
GISTInsertStack *item;
OffsetNumber downlinkoffnum;
/* currently, internal pages are never deleted */
Assert(!GistPageIsDeleted(stack->page));
downlinkoffnum = gistchoose(state.r, stack->page, itup, giststate);
iid = PageGetItemId(stack->page, downlinkoffnum);
idxtuple = (IndexTuple) PageGetItem(stack->page, iid);
childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
/*
* Check that it's not a leftover invalid tuple from pre-9.1
*/
if (GistTupleIsInvalid(idxtuple))
ereport(ERROR,
(errmsg("index \"%s\" contains an inner tuple marked as invalid",
RelationGetRelationName(r)),
errdetail("This is caused by an incomplete page split at crash recovery before upgrading to PostgreSQL 9.1."),
errhint("Please REINDEX it.")));
/*
* Check that the key representing the target child node is
* consistent with the key we're inserting. Update it if it's not.
*/
newtup = gistgetadjusted(state.r, idxtuple, itup, giststate);
if (newtup)
{
/*
* Swap shared lock for an exclusive one. Beware, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
if (PageGetLSN(stack->page) != stack->lsn)
{
/* the page was changed while we unlocked it, retry */
continue;
}
}
/*
* Update the tuple.
*
* We still hold the lock after gistinserttuple(), but it
* might have to split the page to make the updated tuple fit.
* In that case the updated tuple might migrate to the other
* half of the split, so we have to go back to the parent and
* descend back to the half that's a better fit for the new
* tuple.
*/
if (gistinserttuple(&state, stack, giststate, newtup,
downlinkoffnum))
{
/*
* If this was a root split, the root page continues to be
* the parent and the updated tuple went to one of the
* child pages, so we just need to retry from the root
* page.
*/
if (stack->blkno != GIST_ROOT_BLKNO)
{
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
}
continue;
}
}
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
/* descend to the chosen child */
item = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
item->blkno = childblkno;
item->parent = stack;
item->downlinkoffnum = downlinkoffnum;
state.stack = stack = item;
}
else
{
/*
* Leaf page. Insert the new key. We've already updated all the
* parents on the way down, but we might have to split the page if
* it doesn't fit. gistinserthere() will take care of that.
*/
/*
* Swap shared lock for an exclusive one. Be careful, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = PageGetLSN(stack->page);
if (stack->blkno == GIST_ROOT_BLKNO)
{
/*
* the only page that can become inner instead of leaf is
* the root page, so for root we should recheck it
*/
if (!GistPageIsLeaf(stack->page))
{
/*
* very rare situation: during unlock/lock index with
* number of pages = 1 was increased
*/
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
continue;
}
/*
* we don't need to check root split, because checking
* leaf/inner is enough to recognize split for root
*/
}
else if (GistFollowRight(stack->page) ||
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* The page was split while we momentarily unlocked the
* page. Go back to parent.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
}
/*
* The page might have been deleted after we scanned the parent
* and saw the downlink.
*/
if (GistPageIsDeleted(stack->page))
{
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
/* now state.stack->(page, buffer and blkno) points to leaf page */
gistinserttuple(&state, stack, giststate, itup,
InvalidOffsetNumber);
LockBuffer(stack->buffer, GIST_UNLOCK);
/* Release any pins we might still hold before exiting */
for (; stack; stack = stack->parent)
ReleaseBuffer(stack->buffer);
break;
}
}
}
