/*
* _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, bool vacuum_full)
{
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;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
// Fetch gp_persistent_relation_node information that will be added to XLOG record.
RelationFetchGpRelationNodeForXLog(rel);
/*
* 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,
&lbuf, BT_READ);
/* don't need a pin on that either */
_bt_relbuf(rel, lbuf);
/*
* If we are trying to delete an interior page, _bt_search did
* more than we needed. Locate the stack item pointing to our
* parent level.
*/
ilevel = 0;
for (;;)
{
if (stack == NULL)
elog(ERROR, "not enough stack items");
if (ilevel == targetlevel)
break;
stack = stack->bts_parent;
ilevel++;
}
}
else
{
/*
* During WAL recovery, we can't use _bt_search (for one reason,
* it might invoke user-defined comparison functions that expect
* facilities not available in recovery mode). Instead, just set
* up a dummy stack pointing to the left end of the parent tree
* level, from which _bt_getstackbuf will walk right to the parent
* page. Painful, but we don't care too much about performance in
* this scenario.
*/
pbuf = _bt_get_endpoint(rel, targetlevel + 1, false);
stack = (BTStack) palloc(sizeof(BTStackData));
stack->bts_blkno = BufferGetBlockNumber(pbuf);
stack->bts_offset = InvalidOffsetNumber;
/* bts_btentry will be initialized below */
stack->bts_parent = NULL;
_bt_relbuf(rel, pbuf);
}
}
/*
* We cannot delete a page that is the rightmost child of its immediate
* parent, unless it is the only child --- in which case the parent has to
* be deleted too, and the same condition applies recursively to it. We
* have to check this condition all the way up before trying to delete. We
* don't need to re-test when deleting a non-leaf page, though.
*/
if (targetlevel == 0 &&
!_bt_parent_deletion_safe(rel, target, stack))
return 0;
/*
* We have to lock the pages we need to modify in the standard order:
* moving right, then up. Else we will deadlock against other writers.
*
* So, we need to find and write-lock the current left sibling of the
* target page. The sibling that was current a moment ago could have
* split, so we may have to move right. This search could fail if either
* the sibling or the target page was deleted by someone else meanwhile;
* if so, give up. (Right now, that should never happen, since page
* deletion is only done in VACUUM and there shouldn't be multiple VACUUMs
* concurrently on the same table.)
*/
if (leftsib != P_NONE)
{
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
while (P_ISDELETED(opaque) || opaque->btpo_next != target)
{
/* step right one page */
leftsib = opaque->btpo_next;
_bt_relbuf(rel, lbuf);
if (leftsib == P_NONE)
{
elog(LOG, "no left sibling (concurrent deletion?) in \"%s\"",
RelationGetRelationName(rel));
return 0;
}
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
}
else
lbuf = InvalidBuffer;
/*
* Next write-lock the target page itself. It should be okay to take just
* a write lock not a superexclusive lock, since no scans would stop on an
* empty page.
*/
buf = _bt_getbuf(rel, target, BT_WRITE);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* Check page is still empty etc, else abandon deletion. The empty check
* is necessary since someone else might have inserted into it while we
* didn't have it locked; the others are just for paranoia's sake.
*/
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
if (opaque->btpo_prev != leftsib)
elog(ERROR, "left link changed unexpectedly in block %u of index \"%s\"",
target, RelationGetRelationName(rel));
/*
* And next write-lock the (current) right sibling.
*/
rightsib = opaque->btpo_next;
rbuf = _bt_getbuf(rel, rightsib, BT_WRITE);
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (opaque->btpo_prev != target)
elog(ERROR, "right sibling's left-link doesn't match: "
"block %u links to %u instead of expected %u in index \"%s\"",
rightsib, opaque->btpo_prev, target,
RelationGetRelationName(rel));
/*
* Next find and write-lock the current parent of the target page. This is
* essentially the same as the corresponding step of splitting.
*/
ItemPointerSet(&(stack->bts_btentry.t_tid), target, P_HIKEY);
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
elog(ERROR, "failed to re-find parent key in index \"%s\" for deletion target page %u",
RelationGetRelationName(rel), target);
parent = stack->bts_blkno;
poffset = stack->bts_offset;
/*
* If the target is the rightmost child of its parent, then we can't
* delete, unless it's also the only child --- in which case the parent
* changes to half-dead status. The "can't delete" case should have been
* detected by _bt_parent_deletion_safe, so complain if we see it now.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
maxoff = PageGetMaxOffsetNumber(page);
parent_half_dead = false;
parent_one_child = false;
if (poffset >= maxoff)
{
if (poffset == P_FIRSTDATAKEY(opaque))
parent_half_dead = true;
else
elog(ERROR, "failed to delete rightmost child %u of block %u in index \"%s\"",
target, parent, RelationGetRelationName(rel));
}
else
{
/* Will there be exactly one child left in this parent? */
if (OffsetNumberNext(P_FIRSTDATAKEY(opaque)) == maxoff)
parent_one_child = true;
}
/*
* If we are deleting the next-to-last page on the target's level, then
* the rightsib is a candidate to become the new fast root. (In theory, it
* might be possible to push the fast root even further down, but the odds
* of doing so are slim, and the locking considerations daunting.)
*
* We don't support handling this in the case where the parent is becoming
* half-dead, even though it theoretically could occur.
*
* We can safely acquire a lock on the metapage here --- see comments for
* _bt_newroot().
*/
if (leftsib == P_NONE && !parent_half_dead)
{
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo.level == targetlevel);
if (P_RIGHTMOST(opaque))
{
/* rightsib will be the only one left on the level */
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_WRITE);
metapg = BufferGetPage(metabuf);
metad = BTPageGetMeta(metapg);
/*
* The expected case here is btm_fastlevel == targetlevel+1; if
* the fastlevel is <= targetlevel, something is wrong, and we
* choose to overwrite it to fix it.
*/
if (metad->btm_fastlevel > targetlevel + 1)
{
/* no update wanted */
_bt_relbuf(rel, metabuf);
metabuf = InvalidBuffer;
}
}
}
/*
* Check that the parent-page index items we're about to delete/overwrite
* contain what we expect. This can fail if the index has become
* corrupt for some reason. We want to throw any error before entering
* the critical section --- otherwise it'd be a PANIC.
*
* The test on the target item is just an Assert because _bt_getstackbuf
* should have guaranteed it has the expected contents. The test on the
* next-child downlink is known to sometimes fail in the field, though.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
#ifdef USE_ASSERT_CHECKING
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
Assert(ItemPointerGetBlockNumber(&(itup->t_tid)) == target);
#endif
if (!parent_half_dead)
{
OffsetNumber nextoffset;
nextoffset = OffsetNumberNext(poffset);
itemid = PageGetItemId(page, nextoffset);
itup = (IndexTuple) PageGetItem(page, itemid);
if (ItemPointerGetBlockNumber(&(itup->t_tid)) != rightsib)
elog(ERROR, "right sibling %u of block %u is not next child %u of block %u in index \"%s\"",
rightsib, target, ItemPointerGetBlockNumber(&(itup->t_tid)),
parent, RelationGetRelationName(rel));
}
/*
* Here we begin doing the deletion.
*/
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/*
* Update parent. The normal case is a tad tricky because we want to
* delete the target's downlink and the *following* key. Easiest way is
* to copy the right sibling's downlink over the target downlink, and then
* delete the following item.
*/
if (parent_half_dead)
{
PageIndexTupleDelete(page, poffset);
opaque->btpo_flags |= BTP_HALF_DEAD;
}
else
{
OffsetNumber nextoffset;
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
PageIndexTupleDelete(page, nextoffset);
}
/*
* Update siblings' side-links. Note the target page's side-links will
* continue to point to the siblings. Asserts here are just rechecking
* things we already verified above.
*/
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_next == target);
opaque->btpo_next = rightsib;
}
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_prev == target);
opaque->btpo_prev = leftsib;
rightsib_empty = (P_FIRSTDATAKEY(opaque) > PageGetMaxOffsetNumber(page));
/*
* Mark the page itself deleted. It can be recycled when all current
* transactions are gone; or immediately if we're doing VACUUM FULL.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags &= ~BTP_HALF_DEAD;
opaque->btpo_flags |= BTP_DELETED;
opaque->btpo.xact =
vacuum_full ? FrozenTransactionId : ReadNewTransactionId();
/* And update the metapage, if needed */
if (BufferIsValid(metabuf))
{
metad->btm_fastroot = rightsib;
metad->btm_fastlevel = targetlevel;
MarkBufferDirty(metabuf);
}
/* Must mark buffers dirty before XLogInsert */
MarkBufferDirty(pbuf);
MarkBufferDirty(rbuf);
MarkBufferDirty(buf);
if (BufferIsValid(lbuf))
MarkBufferDirty(lbuf);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete_page xlrec;
xl_btree_metadata xlmeta;
uint8 xlinfo;
XLogRecPtr recptr;
XLogRecData rdata[5];
XLogRecData *nextrdata;
xl_btreetid_set(&(xlrec.target), rel, parent, poffset);
xlrec.deadblk = target;
xlrec.leftblk = leftsib;
xlrec.rightblk = rightsib;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeDeletePage;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = nextrdata = &(rdata[1]);
if (BufferIsValid(metabuf))
{
xlmeta.root = metad->btm_root;
xlmeta.level = metad->btm_level;
xlmeta.fastroot = metad->btm_fastroot;
xlmeta.fastlevel = metad->btm_fastlevel;
nextrdata->data = (char *) &xlmeta;
nextrdata->len = sizeof(xl_btree_metadata);
nextrdata->buffer = InvalidBuffer;
nextrdata->next = nextrdata + 1;
nextrdata++;
xlinfo = XLOG_BTREE_DELETE_PAGE_META;
}
else if (parent_half_dead)
xlinfo = XLOG_BTREE_DELETE_PAGE_HALF;
else
xlinfo = XLOG_BTREE_DELETE_PAGE;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->next = nextrdata + 1;
nextrdata->buffer = pbuf;
nextrdata->buffer_std = true;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = rbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
if (BufferIsValid(lbuf))
{
nextrdata->next = nextrdata + 1;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = lbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
}
recptr = XLogInsert(RM_BTREE_ID, xlinfo, rdata);
if (BufferIsValid(metabuf))
{
PageSetLSN(metapg, recptr);
PageSetTLI(metapg, ThisTimeLineID);
}
page = BufferGetPage(pbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(rbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(buf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
END_CRIT_SECTION();
/* release metapage; send out relcache inval if metapage changed */
if (BufferIsValid(metabuf))
{
CacheInvalidateRelcache(rel);
_bt_relbuf(rel, metabuf);
}
/* can always release leftsib immediately */
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
/*
* If parent became half dead, recurse to delete it. Otherwise, if right
* sibling is empty and is now the last child of the parent, recurse to
* try to delete it. (These cases cannot apply at the same time, though
* the second case might itself recurse to the first.)
*
* When recursing to parent, we hold the lock on the target page until
* done. This delays any insertions into the keyspace that was just
* effectively reassigned to the parent's right sibling. If we allowed
* that, and there were enough such insertions before we finish deleting
* the parent, page splits within that keyspace could lead to inserting
* out-of-order keys into the grandparent level. It is thought that that
* wouldn't have any serious consequences, but it still seems like a
* pretty bad idea.
*/
if (parent_half_dead)
{
/* recursive call will release pbuf */
_bt_relbuf(rel, rbuf);
result = _bt_pagedel(rel, pbuf, stack->bts_parent, vacuum_full) + 1;
_bt_relbuf(rel, buf);
}
else if (parent_one_child && rightsib_empty)
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
/* recursive call will release rbuf */
result = _bt_pagedel(rel, rbuf, stack, vacuum_full) + 1;
}
else
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
_bt_relbuf(rel, rbuf);
result = 1;
}
return result;
}
/*
* _bt_first() -- Find the first item in a scan.
*
* We need to be clever about the type of scan, the operation it's
* performing, and the tree ordering. We find the
* first item in the tree that satisfies the qualification
* associated with the scan descriptor. On exit, the page containing
* the current index tuple is read locked and pinned, and the scan's
* opaque data entry is updated to include the buffer.
*/
bool
_bt_first(IndexScanDesc scan, ScanDirection dir)
{
Relation rel = scan->indexRelation;
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Buffer buf;
Page page;
BTStack stack;
OffsetNumber offnum;
BTItem btitem;
IndexTuple itup;
ItemPointer current;
BlockNumber blkno;
StrategyNumber strat;
bool res;
int32 result;
bool scanFromEnd;
bool continuescan;
ScanKey scankeys = NULL;
int keysCount = 0;
int *nKeyIs = NULL;
int i,
j;
StrategyNumber strat_total;
/*
* Order the scan keys in our canonical fashion and eliminate any
* redundant keys.
*/
_bt_orderkeys(scan);
/*
* Quit now if _bt_orderkeys() discovered that the scan keys can never
* be satisfied (eg, x == 1 AND x > 2).
*/
if (!so->qual_ok)
return false;
/*
* Examine the scan keys to discover where we need to start the scan.
*/
scanFromEnd = false;
strat_total = BTEqualStrategyNumber;
if (so->numberOfKeys > 0)
{
nKeyIs = (int *) palloc(so->numberOfKeys * sizeof(int));
for (i = 0; i < so->numberOfKeys; i++)
{
AttrNumber attno = so->keyData[i].sk_attno;
/* ignore keys for already-determined attrs */
if (attno <= keysCount)
continue;
/* if we didn't find a boundary for the preceding attr, quit */
if (attno > keysCount + 1)
break;
strat = _bt_getstrat(rel, attno,
so->keyData[i].sk_procedure);
/*
* Can we use this key as a starting boundary for this attr?
*
* We can use multiple keys if they look like, say, = >= = but we
* have to stop after accepting a > or < boundary.
*/
if (strat == strat_total ||
strat == BTEqualStrategyNumber)
nKeyIs[keysCount++] = i;
else if (ScanDirectionIsBackward(dir) &&
(strat == BTLessStrategyNumber ||
strat == BTLessEqualStrategyNumber))
{
nKeyIs[keysCount++] = i;
strat_total = strat;
if (strat == BTLessStrategyNumber)
break;
}
else if (ScanDirectionIsForward(dir) &&
(strat == BTGreaterStrategyNumber ||
strat == BTGreaterEqualStrategyNumber))
{
nKeyIs[keysCount++] = i;
strat_total = strat;
if (strat == BTGreaterStrategyNumber)
break;
}
}
if (keysCount == 0)
scanFromEnd = true;
}
else
scanFromEnd = true;
/* if we just need to walk down one edge of the tree, do that */
if (scanFromEnd)
{
if (nKeyIs)
pfree(nKeyIs);
return _bt_endpoint(scan, dir);
}
/*
* We want to start the scan somewhere within the index. Set up a
* scankey we can use to search for the correct starting point.
*/
scankeys = (ScanKey) palloc(keysCount * sizeof(ScanKeyData));
for (i = 0; i < keysCount; i++)
{
FmgrInfo *procinfo;
j = nKeyIs[i];
/*
* _bt_orderkeys disallows it, but it's place to add some code
* later
*/
if (so->keyData[j].sk_flags & SK_ISNULL)
{
pfree(nKeyIs);
pfree(scankeys);
elog(ERROR, "btree doesn't support is(not)null, yet");
return false;
}
procinfo = index_getprocinfo(rel, i + 1, BTORDER_PROC);
ScanKeyEntryInitializeWithInfo(scankeys + i,
so->keyData[j].sk_flags,
i + 1,
procinfo,
CurrentMemoryContext,
so->keyData[j].sk_argument);
}
if (nKeyIs)
pfree(nKeyIs);
current = &(scan->currentItemData);
/*
* Use the manufactured scan key to descend the tree and position
* ourselves on the target leaf page.
*/
stack = _bt_search(rel, keysCount, scankeys, &buf, BT_READ);
/* don't need to keep the stack around... */
_bt_freestack(stack);
if (!BufferIsValid(buf))
{
/* Only get here if index is completely empty */
ItemPointerSetInvalid(current);
so->btso_curbuf = InvalidBuffer;
pfree(scankeys);
return false;
}
/* remember which buffer we have pinned */
so->btso_curbuf = buf;
blkno = BufferGetBlockNumber(buf);
page = BufferGetPage(buf);
/* position to the precise item on the page */
offnum = _bt_binsrch(rel, buf, keysCount, scankeys);
ItemPointerSet(current, blkno, offnum);
/*
* At this point 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.
*
* We could step forward in the latter case, but that'd be a waste of
* time if we want to scan backwards. So, it's now time to examine
* the scan strategy to find the exact place to start the scan.
*
* Note: if _bt_step fails (meaning we fell off the end of the index in
* one direction or the other), we either return false (no matches) or
* call _bt_endpoint() to set up a scan starting at that index
* endpoint, as appropriate for the desired scan type.
*
* it's yet other place to add some code later for is(not)null ...
*/
switch (strat_total)
{
case BTLessStrategyNumber:
/*
* Back up one to arrive at last item < scankey
*/
if (!_bt_step(scan, &buf, BackwardScanDirection))
{
pfree(scankeys);
return false;
}
break;
case BTLessEqualStrategyNumber:
/*
* We need to find the last item <= scankey, so step forward
* till we find one > scankey, then step back one.
*/
if (offnum > PageGetMaxOffsetNumber(page))
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return _bt_endpoint(scan, dir);
}
}
for (;;)
{
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
result = _bt_compare(rel, keysCount, scankeys, page, offnum);
if (result < 0)
break;
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return _bt_endpoint(scan, dir);
}
}
if (!_bt_step(scan, &buf, BackwardScanDirection))
{
pfree(scankeys);
return false;
}
break;
case BTEqualStrategyNumber:
/*
* Make sure we are on the first equal item; might have to
* step forward if currently at end of page.
*/
if (offnum > PageGetMaxOffsetNumber(page))
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return false;
}
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
}
result = _bt_compare(rel, keysCount, scankeys, page, offnum);
if (result != 0)
goto nomatches; /* no equal items! */
/*
* If a backward scan was specified, need to start with last
* equal item not first one.
*/
if (ScanDirectionIsBackward(dir))
{
do
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return _bt_endpoint(scan, dir);
}
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
result = _bt_compare(rel, keysCount, scankeys, page, offnum);
} while (result == 0);
if (!_bt_step(scan, &buf, BackwardScanDirection))
elog(ERROR, "equal items disappeared?");
}
break;
case BTGreaterEqualStrategyNumber:
/*
* We want the first item >= scankey, which is where we are...
* unless we're not anywhere at all...
*/
if (offnum > PageGetMaxOffsetNumber(page))
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return false;
}
}
break;
case BTGreaterStrategyNumber:
/*
* We want the first item > scankey, so make sure we are on an
* item and then step over any equal items.
*/
if (offnum > PageGetMaxOffsetNumber(page))
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return false;
}
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
}
result = _bt_compare(rel, keysCount, scankeys, page, offnum);
while (result == 0)
{
if (!_bt_step(scan, &buf, ForwardScanDirection))
{
pfree(scankeys);
return false;
}
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
result = _bt_compare(rel, keysCount, scankeys, page, offnum);
}
break;
}
/* okay, current item pointer for the scan is right */
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(buf);
btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
itup = &btitem->bti_itup;
/* is the first item actually acceptable? */
if (_bt_checkkeys(scan, itup, dir, &continuescan))
{
/* yes, return it */
scan->xs_ctup.t_self = itup->t_tid;
res = true;
}
else if (continuescan)
{
/* no, but there might be another one that is */
res = _bt_next(scan, dir);
}
else
{
/* no tuples in the index match this scan key */
nomatches:
ItemPointerSetInvalid(current);
so->btso_curbuf = InvalidBuffer;
_bt_relbuf(rel, buf);
res = false;
}
pfree(scankeys);
return res;
}
/*
* _bt_first() -- Find the first item in a scan.
*
* We need to be clever about the direction of scan, the search
* conditions, and the tree ordering. We find the first item (or,
* if backwards scan, the last item) in the tree that satisfies the
* qualifications in the scan key. On success exit, the page containing
* the current index tuple is pinned but not locked, and data about
* the matching tuple(s) on the page has been loaded into so->currPos.
* scan->xs_ctup.t_self is set to the heap TID of the current tuple,
* and if requested, scan->xs_itup points to a copy of the index tuple.
*
* If there are no matching items in the index, we return FALSE, with no
* pins or locks held.
*
* Note that scan->keyData[], and the so->keyData[] scankey built from it,
* are both search-type scankeys (see nbtree/README for more about this).
* Within this routine, we build a temporary insertion-type scankey to use
* in locating the scan start position.
*/
bool
_bt_first(IndexScanDesc scan, ScanDirection dir)
{
Relation rel = scan->indexRelation;
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Buffer buf;
BTStack stack;
OffsetNumber offnum;
StrategyNumber strat;
bool nextkey;
bool goback;
ScanKey startKeys[INDEX_MAX_KEYS];
ScanKeyData scankeys[INDEX_MAX_KEYS];
ScanKeyData notnullkeys[INDEX_MAX_KEYS];
int keysCount = 0;
int i;
StrategyNumber strat_total;
BTScanPosItem *currItem;
pgstat_count_index_scan(rel);
/*
* Examine the scan keys and eliminate any redundant keys; also mark the
* keys that must be matched to continue the scan.
*/
_bt_preprocess_keys(scan);
/*
* Quit now if _bt_preprocess_keys() discovered that the scan keys can
* never be satisfied (eg, x == 1 AND x > 2).
*/
if (!so->qual_ok)
return false;
/*----------
* Examine the scan keys to discover where we need to start the scan.
*
* We want to identify the keys that can be used as starting boundaries;
* these are =, >, or >= keys for a forward scan or =, <, <= keys for
* a backwards scan. We can use keys for multiple attributes so long as
* the prior attributes had only =, >= (resp. =, <=) keys. Once we accept
* a > or < boundary or find an attribute with no boundary (which can be
* thought of as the same as "> -infinity"), we can't use keys for any
* attributes to its right, because it would break our simplistic notion
* of what initial positioning strategy to use.
*
* When the scan keys include cross-type operators, _bt_preprocess_keys
* may not be able to eliminate redundant keys; in such cases we will
* arbitrarily pick a usable one for each attribute. This is correct
* but possibly not optimal behavior. (For example, with keys like
* "x >= 4 AND x >= 5" we would elect to scan starting at x=4 when
* x=5 would be more efficient.) Since the situation only arises given
* a poorly-worded query plus an incomplete opfamily, live with it.
*
* When both equality and inequality keys appear for a single attribute
* (again, only possible when cross-type operators appear), we *must*
* select one of the equality keys for the starting point, because
* _bt_checkkeys() will stop the scan as soon as an equality qual fails.
* For example, if we have keys like "x >= 4 AND x = 10" and we elect to
* start at x=4, we will fail and stop before reaching x=10. If multiple
* equality quals survive preprocessing, however, it doesn't matter which
* one we use --- by definition, they are either redundant or
* contradictory.
*
* Any regular (not SK_SEARCHNULL) key implies a NOT NULL qualifier.
* If the index stores nulls at the end of the index we'll be starting
* from, and we have no boundary key for the column (which means the key
* we deduced NOT NULL from is an inequality key that constrains the other
* end of the index), then we cons up an explicit SK_SEARCHNOTNULL key to
* use as a boundary key. If we didn't do this, we might find ourselves
* traversing a lot of null entries at the start of the scan.
*
* In this loop, row-comparison keys are treated the same as keys on their
* first (leftmost) columns. We'll add on lower-order columns of the row
* comparison below, if possible.
*
* The selected scan keys (at most one per index column) are remembered by
* storing their addresses into the local startKeys[] array.
*----------
*/
strat_total = BTEqualStrategyNumber;
if (so->numberOfKeys > 0)
{
AttrNumber curattr;
ScanKey chosen;
ScanKey impliesNN;
ScanKey cur;
/*
* chosen is the so-far-chosen key for the current attribute, if any.
* We don't cast the decision in stone until we reach keys for the
* next attribute.
*/
curattr = 1;
chosen = NULL;
/* Also remember any scankey that implies a NOT NULL constraint */
impliesNN = NULL;
/*
* Loop iterates from 0 to numberOfKeys inclusive; we use the last
* pass to handle after-last-key processing. Actual exit from the
* loop is at one of the "break" statements below.
*/
for (cur = so->keyData, i = 0;; cur++, i++)
{
if (i >= so->numberOfKeys || cur->sk_attno != curattr)
{
/*
* Done looking at keys for curattr. If we didn't find a
* usable boundary key, see if we can deduce a NOT NULL key.
*/
if (chosen == NULL && impliesNN != NULL &&
((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
ScanDirectionIsForward(dir) :
ScanDirectionIsBackward(dir)))
{
/* Yes, so build the key in notnullkeys[keysCount] */
chosen = ¬nullkeys[keysCount];
ScanKeyEntryInitialize(chosen,
(SK_SEARCHNOTNULL | SK_ISNULL |
(impliesNN->sk_flags &
(SK_BT_DESC | SK_BT_NULLS_FIRST))),
curattr,
((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
BTGreaterStrategyNumber :
BTLessStrategyNumber),
InvalidOid,
InvalidOid,
InvalidOid,
(Datum) 0);
}
/*
* If we still didn't find a usable boundary key, quit; else
* save the boundary key pointer in startKeys.
*/
if (chosen == NULL)
break;
startKeys[keysCount++] = chosen;
/*
* Adjust strat_total, and quit if we have stored a > or <
* key.
*/
strat = chosen->sk_strategy;
if (strat != BTEqualStrategyNumber)
{
strat_total = strat;
if (strat == BTGreaterStrategyNumber ||
strat == BTLessStrategyNumber)
break;
}
/*
* Done if that was the last attribute, or if next key is not
* in sequence (implying no boundary key is available for the
* next attribute).
*/
if (i >= so->numberOfKeys ||
cur->sk_attno != curattr + 1)
break;
/*
* Reset for next attr.
*/
curattr = cur->sk_attno;
chosen = NULL;
impliesNN = NULL;
}
/*
* Can we use this key as a starting boundary for this attr?
*
* If not, does it imply a NOT NULL constraint? (Because
* SK_SEARCHNULL keys are always assigned BTEqualStrategyNumber,
* *any* inequality key works for that; we need not test.)
*/
switch (cur->sk_strategy)
{
case BTLessStrategyNumber:
case BTLessEqualStrategyNumber:
if (chosen == NULL)
{
if (ScanDirectionIsBackward(dir))
chosen = cur;
else
impliesNN = cur;
}
break;
case BTEqualStrategyNumber:
/* override any non-equality choice */
chosen = cur;
break;
case BTGreaterEqualStrategyNumber:
case BTGreaterStrategyNumber:
if (chosen == NULL)
{
if (ScanDirectionIsForward(dir))
chosen = cur;
else
impliesNN = cur;
}
break;
}
}
}
/*
* If we found no usable boundary keys, we have to start from one end of
* the tree. Walk down that edge to the first or last key, and scan from
* there.
*/
if (keysCount == 0)
return _bt_endpoint(scan, dir);
/*
* We want to start the scan somewhere within the index. Set up an
* insertion scankey we can use to search for the boundary point we
* identified above. The insertion scankey is built in the local
* scankeys[] array, using the keys identified by startKeys[].
*/
Assert(keysCount <= INDEX_MAX_KEYS);
for (i = 0; i < keysCount; i++)
{
ScanKey cur = startKeys[i];
Assert(cur->sk_attno == i + 1);
if (cur->sk_flags & SK_ROW_HEADER)
{
/*
* Row comparison header: look to the first row member instead.
*
* The member scankeys are already in insertion format (ie, they
* have sk_func = 3-way-comparison function), but we have to watch
* out for nulls, which _bt_preprocess_keys didn't check. A null
* in the first row member makes the condition unmatchable, just
* like qual_ok = false.
*/
ScanKey subkey = (ScanKey) DatumGetPointer(cur->sk_argument);
Assert(subkey->sk_flags & SK_ROW_MEMBER);
if (subkey->sk_flags & SK_ISNULL)
return false;
memcpy(scankeys + i, subkey, sizeof(ScanKeyData));
/*
* If the row comparison is the last positioning key we accepted,
* try to add additional keys from the lower-order row members.
* (If we accepted independent conditions on additional index
* columns, we use those instead --- doesn't seem worth trying to
* determine which is more restrictive.) Note that this is OK
* even if the row comparison is of ">" or "<" type, because the
* condition applied to all but the last row member is effectively
* ">=" or "<=", and so the extra keys don't break the positioning
* scheme. But, by the same token, if we aren't able to use all
* the row members, then the part of the row comparison that we
* did use has to be treated as just a ">=" or "<=" condition, and
* so we'd better adjust strat_total accordingly.
*/
if (i == keysCount - 1)
{
bool used_all_subkeys = false;
Assert(!(subkey->sk_flags & SK_ROW_END));
for (;;)
{
subkey++;
Assert(subkey->sk_flags & SK_ROW_MEMBER);
if (subkey->sk_attno != keysCount + 1)
break; /* out-of-sequence, can't use it */
if (subkey->sk_strategy != cur->sk_strategy)
break; /* wrong direction, can't use it */
if (subkey->sk_flags & SK_ISNULL)
break; /* can't use null keys */
Assert(keysCount < INDEX_MAX_KEYS);
memcpy(scankeys + keysCount, subkey, sizeof(ScanKeyData));
keysCount++;
if (subkey->sk_flags & SK_ROW_END)
{
used_all_subkeys = true;
break;
}
}
if (!used_all_subkeys)
{
switch (strat_total)
{
case BTLessStrategyNumber:
strat_total = BTLessEqualStrategyNumber;
break;
case BTGreaterStrategyNumber:
strat_total = BTGreaterEqualStrategyNumber;
break;
}
}
break; /* done with outer loop */
}
}
else
{
/*
* Ordinary comparison key. Transform the search-style scan key
* to an insertion scan key by replacing the sk_func with the
* appropriate btree comparison function.
*
* If scankey operator is not a cross-type comparison, we can use
* the cached comparison function; otherwise gotta look it up in
* the catalogs. (That can't lead to infinite recursion, since no
* indexscan initiated by syscache lookup will use cross-data-type
* operators.)
*
* We support the convention that sk_subtype == InvalidOid means
* the opclass input type; this is a hack to simplify life for
* ScanKeyInit().
*/
if (cur->sk_subtype == rel->rd_opcintype[i] ||
cur->sk_subtype == InvalidOid)
{
FmgrInfo *procinfo;
procinfo = index_getprocinfo(rel, cur->sk_attno, BTORDER_PROC);
ScanKeyEntryInitializeWithInfo(scankeys + i,
cur->sk_flags,
cur->sk_attno,
InvalidStrategy,
cur->sk_subtype,
cur->sk_collation,
procinfo,
cur->sk_argument);
}
else
{
RegProcedure cmp_proc;
cmp_proc = get_opfamily_proc(rel->rd_opfamily[i],
rel->rd_opcintype[i],
cur->sk_subtype,
BTORDER_PROC);
if (!RegProcedureIsValid(cmp_proc))
elog(ERROR, "missing support function %d(%u,%u) for attribute %d of index \"%s\"",
BTORDER_PROC, rel->rd_opcintype[i], cur->sk_subtype,
cur->sk_attno, RelationGetRelationName(rel));
ScanKeyEntryInitialize(scankeys + i,
cur->sk_flags,
cur->sk_attno,
InvalidStrategy,
cur->sk_subtype,
cur->sk_collation,
cmp_proc,
cur->sk_argument);
}
}
}
/*----------
* Examine the selected initial-positioning strategy to determine exactly
* where we need to start the scan, and set flag variables to control the
* code below.
*
* If nextkey = false, _bt_search and _bt_binsrch will locate the first
* item >= scan key. If nextkey = true, they will locate the first
* item > scan key.
*
* If goback = true, we will then step back one item, while if
* goback = false, we will start the scan on the located item.
*----------
*/
switch (strat_total)
{
case BTLessStrategyNumber:
/*
* Find first item >= scankey, then back up one to arrive at last
* item < scankey. (Note: this positioning strategy is only used
* for a backward scan, so that is always the correct starting
* position.)
*/
nextkey = false;
goback = true;
break;
case BTLessEqualStrategyNumber:
/*
* Find first item > scankey, then back up one to arrive at last
* item <= scankey. (Note: this positioning strategy is only used
* for a backward scan, so that is always the correct starting
* position.)
*/
nextkey = true;
goback = true;
break;
case BTEqualStrategyNumber:
/*
* If a backward scan was specified, need to start with last equal
* item not first one.
*/
if (ScanDirectionIsBackward(dir))
{
/*
* This is the same as the <= strategy. We will check at the
* end whether the found item is actually =.
*/
nextkey = true;
goback = true;
}
else
{
/*
* This is the same as the >= strategy. We will check at the
* end whether the found item is actually =.
*/
nextkey = false;
goback = false;
}
break;
case BTGreaterEqualStrategyNumber:
/*
* Find first item >= scankey. (This is only used for forward
* scans.)
*/
nextkey = false;
goback = false;
break;
case BTGreaterStrategyNumber:
/*
* 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;
}
/*
* _bt_pagedel() -- Delete a page from the b-tree.
*
* 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 read-locked. This lock and
* pin will be dropped before exiting.
*
* Returns the number of pages successfully deleted (zero on failure; could
* be more than one if parent blocks were deleted).
*
* 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, bool vacuum_full)
{
BlockNumber target,
leftsib,
rightsib,
parent;
OffsetNumber poffset,
maxoff;
uint32 targetlevel,
ilevel;
ItemId itemid;
BTItem targetkey,
btitem;
ScanKey itup_scankey;
BTStack stack;
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))
{
_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 = CopyBTItem((BTItem) PageGetItem(page, itemid));
/*
* We need to get an approximate pointer to the page's parent page. 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). To avoid deadlocks, we'd
* better drop the target page lock first.
*/
_bt_relbuf(rel, buf);
/* we need a scan key to do our search, so build one */
itup_scankey = _bt_mkscankey(rel, &(targetkey->bti_itup));
/* find the leftmost leaf page containing this key */
stack = _bt_search(rel, rel->rd_rel->relnatts, itup_scankey, false,
&lbuf, BT_READ);
/* don't need a pin on that either */
_bt_relbuf(rel, lbuf);
/*
* If we are trying to delete an interior page, _bt_search did more than
* we needed. Locate the stack item pointing to our parent level.
*/
ilevel = 0;
for (;;)
{
if (stack == NULL)
elog(ERROR, "not enough stack items");
if (ilevel == targetlevel)
break;
stack = stack->bts_parent;
ilevel++;
}
/*
* We have to lock the pages we need to modify in the standard order:
* moving right, then up. Else we will deadlock against other writers.
*
* So, we need to find and write-lock the current left sibling of the
* target page. The sibling that was current a moment ago could have
* split, so we may have to move right. This search could fail if either
* the sibling or the target page was deleted by someone else meanwhile;
* if so, give up. (Right now, that should never happen, since page
* deletion is only done in VACUUM and there shouldn't be multiple VACUUMs
* concurrently on the same table.)
*/
if (leftsib != P_NONE)
{
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
while (P_ISDELETED(opaque) || opaque->btpo_next != target)
{
/* step right one page */
leftsib = opaque->btpo_next;
_bt_relbuf(rel, lbuf);
if (leftsib == P_NONE)
{
elog(LOG, "no left sibling (concurrent deletion?) in \"%s\"",
RelationGetRelationName(rel));
return 0;
}
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
}
else
lbuf = InvalidBuffer;
/*
* Next write-lock the target page itself. It should be okay to take just
* a write lock not a superexclusive lock, since no scans would stop on an
* empty page.
*/
buf = _bt_getbuf(rel, target, BT_WRITE);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* Check page is still empty etc, else abandon deletion. The empty check
* is necessary since someone else might have inserted into it while we
* didn't have it locked; the others are just for paranoia's sake.
*/
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
if (opaque->btpo_prev != leftsib)
elog(ERROR, "left link changed unexpectedly in block %u of \"%s\"",
target, RelationGetRelationName(rel));
/*
* And next write-lock the (current) right sibling.
*/
rightsib = opaque->btpo_next;
rbuf = _bt_getbuf(rel, rightsib, BT_WRITE);
/*
* Next find and write-lock the current parent of the target page. This is
* essentially the same as the corresponding step of splitting. However,
* it's possible for the search to fail (for reasons explained in README).
* If that happens, we recover by searching the whole parent level, which
* is a tad inefficient but doesn't happen often enough to be a problem.
*/
ItemPointerSet(&(stack->bts_btitem.bti_itup.t_tid),
target, P_HIKEY);
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
{
/* Find the leftmost page in the parent level */
pbuf = _bt_get_endpoint(rel, opaque->btpo.level + 1, false);
stack->bts_blkno = BufferGetBlockNumber(pbuf);
stack->bts_offset = InvalidOffsetNumber;
_bt_relbuf(rel, pbuf);
/* and repeat search from there */
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
elog(ERROR, "failed to re-find parent key in \"%s\" for deletion target page %u",
RelationGetRelationName(rel), target);
}
parent = stack->bts_blkno;
poffset = stack->bts_offset;
/*
* If the target is the rightmost child of its parent, then we can't
* delete, unless it's also the only child --- in which case the parent
* changes to half-dead status.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
maxoff = PageGetMaxOffsetNumber(page);
parent_half_dead = false;
parent_one_child = false;
if (poffset >= maxoff)
{
if (poffset == P_FIRSTDATAKEY(opaque))
parent_half_dead = true;
else
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, rbuf);
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
}
else
{
/* Will there be exactly one child left in this parent? */
if (OffsetNumberNext(P_FIRSTDATAKEY(opaque)) == maxoff)
parent_one_child = true;
}
/*
* If we are deleting the next-to-last page on the target's level, then
* the rightsib is a candidate to become the new fast root. (In theory, it
* might be possible to push the fast root even further down, but the odds
* of doing so are slim, and the locking considerations daunting.)
*
* We can safely acquire a lock on the metapage here --- see comments for
* _bt_newroot().
*/
if (leftsib == P_NONE)
{
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo.level == targetlevel);
if (P_RIGHTMOST(opaque))
{
/* rightsib will be the only one left on the level */
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_WRITE);
metapg = BufferGetPage(metabuf);
metad = BTPageGetMeta(metapg);
/*
* The expected case here is btm_fastlevel == targetlevel+1; if
* the fastlevel is <= targetlevel, something is wrong, and we
* choose to overwrite it to fix it.
*/
if (metad->btm_fastlevel > targetlevel + 1)
{
/* no update wanted */
_bt_relbuf(rel, metabuf);
metabuf = InvalidBuffer;
}
}
}
/*
* Here we begin doing the deletion.
*/
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/*
* Update parent. The normal case is a tad tricky because we want to
* delete the target's downlink and the *following* key. Easiest way is
* to copy the right sibling's downlink over the target downlink, and then
* delete the following item.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (parent_half_dead)
{
PageIndexTupleDelete(page, poffset);
opaque->btpo_flags |= BTP_HALF_DEAD;
}
else
{
OffsetNumber nextoffset;
itemid = PageGetItemId(page, poffset);
btitem = (BTItem) PageGetItem(page, itemid);
Assert(ItemPointerGetBlockNumber(&(btitem->bti_itup.t_tid)) == target);
ItemPointerSet(&(btitem->bti_itup.t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
/* This part is just for double-checking */
itemid = PageGetItemId(page, nextoffset);
btitem = (BTItem) PageGetItem(page, itemid);
if (ItemPointerGetBlockNumber(&(btitem->bti_itup.t_tid)) != rightsib)
elog(PANIC, "right sibling is not next child in \"%s\"",
RelationGetRelationName(rel));
PageIndexTupleDelete(page, nextoffset);
}
/*
* Update siblings' side-links. Note the target page's side-links will
* continue to point to the siblings.
*/
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_next == target);
opaque->btpo_next = rightsib;
}
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_prev == target);
opaque->btpo_prev = leftsib;
rightsib_empty = (P_FIRSTDATAKEY(opaque) > PageGetMaxOffsetNumber(page));
/*
* Mark the page itself deleted. It can be recycled when all current
* transactions are gone; or immediately if we're doing VACUUM FULL.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags |= BTP_DELETED;
opaque->btpo.xact =
vacuum_full ? FrozenTransactionId : ReadNewTransactionId();
/* And update the metapage, if needed */
if (BufferIsValid(metabuf))
{
metad->btm_fastroot = rightsib;
metad->btm_fastlevel = targetlevel;
}
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete_page xlrec;
xl_btree_metadata xlmeta;
uint8 xlinfo;
XLogRecPtr recptr;
XLogRecData rdata[5];
XLogRecData *nextrdata;
xlrec.target.node = rel->rd_node;
ItemPointerSet(&(xlrec.target.tid), parent, poffset);
xlrec.deadblk = target;
xlrec.leftblk = leftsib;
xlrec.rightblk = rightsib;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeDeletePage;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = nextrdata = &(rdata[1]);
if (BufferIsValid(metabuf))
{
xlmeta.root = metad->btm_root;
xlmeta.level = metad->btm_level;
xlmeta.fastroot = metad->btm_fastroot;
xlmeta.fastlevel = metad->btm_fastlevel;
nextrdata->data = (char *) &xlmeta;
nextrdata->len = sizeof(xl_btree_metadata);
nextrdata->buffer = InvalidBuffer;
nextrdata->next = nextrdata + 1;
nextrdata++;
xlinfo = XLOG_BTREE_DELETE_PAGE_META;
}
else
xlinfo = XLOG_BTREE_DELETE_PAGE;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->next = nextrdata + 1;
nextrdata->buffer = pbuf;
nextrdata->buffer_std = true;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = rbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
if (BufferIsValid(lbuf))
{
nextrdata->next = nextrdata + 1;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = lbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
}
recptr = XLogInsert(RM_BTREE_ID, xlinfo, rdata);
if (BufferIsValid(metabuf))
{
PageSetLSN(metapg, recptr);
PageSetTLI(metapg, ThisTimeLineID);
}
page = BufferGetPage(pbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(rbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(buf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
END_CRIT_SECTION();
/* Write and release buffers */
if (BufferIsValid(metabuf))
_bt_wrtbuf(rel, metabuf);
_bt_wrtbuf(rel, pbuf);
_bt_wrtbuf(rel, rbuf);
_bt_wrtbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_wrtbuf(rel, lbuf);
/*
* If parent became half dead, recurse to try to delete it. Otherwise, if
* right sibling is empty and is now the last child of the parent, recurse
* to try to delete it. (These cases cannot apply at the same time,
* though the second case might itself recurse to the first.)
*/
if (parent_half_dead)
{
buf = _bt_getbuf(rel, parent, BT_READ);
return _bt_pagedel(rel, buf, vacuum_full) + 1;
}
if (parent_one_child && rightsib_empty)
{
buf = _bt_getbuf(rel, rightsib, BT_READ);
return _bt_pagedel(rel, buf, vacuum_full) + 1;
}
return 1;
}
