/*
* _bt_page_recyclable() -- Is an existing page recyclable?
*
* This exists to make sure _bt_getbuf and btvacuumscan have the same
* policy about whether a page is safe to re-use.
*/
bool
_bt_page_recyclable(Page page)
{
BTPageOpaque opaque;
TransactionId cutoff;
/*
* It's possible to find an all-zeroes page in an index --- for example, a
* backend might successfully extend the relation one page and then crash
* before it is able to make a WAL entry for adding the page. If we find a
* zeroed page then reclaim it.
*/
if (PageIsNew(page))
return true;
/*
* Otherwise, recycle if deleted and too old to have any processes
* interested in it. If we are generating records for Hot Standby
* defer page recycling until RecentGlobalXmin to respect user
* controls specified by vacuum_defer_cleanup_age or hot_standby_feedback.
*/
if (XLogStandbyInfoActive())
cutoff = RecentGlobalXmin;
else
cutoff = RecentXmin;
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISDELETED(opaque) &&
TransactionIdPrecedesOrEquals(opaque->btpo.xact, cutoff))
return true;
return false;
}
/*
* Mask a btree page before performing consistency checks on it.
*/
void
btree_mask(char *pagedata, BlockNumber blkno)
{
Page page = (Page) pagedata;
BTPageOpaque maskopaq;
mask_page_lsn_and_checksum(page);
mask_page_hint_bits(page);
mask_unused_space(page);
maskopaq = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISDELETED(maskopaq))
{
/*
* Mask page content on a DELETED page since it will be re-initialized
* during replay. See btree_xlog_unlink_page() for details.
*/
mask_page_content(page);
}
else if (P_ISLEAF(maskopaq))
{
/*
* In btree leaf pages, it is possible to modify the LP_FLAGS without
* emitting any WAL record. Hence, mask the line pointer flags. See
* _bt_killitems(), _bt_check_unique() for details.
*/
mask_lp_flags(page);
}
/*
* BTP_HAS_GARBAGE is just an un-logged hint bit. So, mask it. See
* _bt_killitems(), _bt_check_unique() for details.
*/
maskopaq->btpo_flags &= ~BTP_HAS_GARBAGE;
/*
* During replay of a btree page split, we don't set the BTP_SPLIT_END
* flag of the right sibling and initialize the cycle_id to 0 for the same
* page. See btree_xlog_split() for details.
*/
maskopaq->btpo_flags &= ~BTP_SPLIT_END;
maskopaq->btpo_cycleid = 0;
}
/*
* _bt_page_recyclable() -- Is an existing page recyclable?
*
* This exists to make sure _bt_getbuf and btvacuumscan have the same
* policy about whether a page is safe to re-use.
*/
bool
_bt_page_recyclable(Page page)
{
BTPageOpaque opaque;
/*
* It's possible to find an all-zeroes page in an index --- for example, a
* backend might successfully extend the relation one page and then crash
* before it is able to make a WAL entry for adding the page. If we find a
* zeroed page then reclaim it.
*/
if (PageIsNew(page))
return true;
/*
* Otherwise, recycle if deleted and too old to have any processes
* interested in it.
*/
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISDELETED(opaque) &&
TransactionIdPrecedes(opaque->btpo.xact, RecentGlobalXmin))
return true;
return false;
}
/*
* _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_walk_left() -- step left one page, if possible
*
* The given buffer must be pinned and read-locked. This will be dropped
* before stepping left. On return, we have pin and read lock on the
* returned page, instead.
*
* Returns InvalidBuffer if there is no page to the left (no lock is held
* in that case).
*
* When working on a non-leaf level, it is possible for the returned page
* to be half-dead; the caller should check that condition and step left
* again if it's important.
*/
static Buffer
_bt_walk_left(Relation rel, Buffer buf)
{
Page page;
BTPageOpaque opaque;
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
for (;;)
{
BlockNumber obknum;
BlockNumber lblkno;
BlockNumber blkno;
int tries;
/* if we're at end of tree, release buf and return failure */
if (P_LEFTMOST(opaque))
{
_bt_relbuf(rel, buf);
break;
}
/* remember original page we are stepping left from */
obknum = BufferGetBlockNumber(buf);
/* step left */
blkno = lblkno = opaque->btpo_prev;
_bt_relbuf(rel, buf);
/* check for interrupts while we're not holding any buffer lock */
CHECK_FOR_INTERRUPTS();
buf = _bt_getbuf(rel, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* If this isn't the page we want, walk right till we find what we
* want --- but go no more than four hops (an arbitrary limit). If we
* don't find the correct page by then, the most likely bet is that
* the original page got deleted and isn't in the sibling chain at all
* anymore, not that its left sibling got split more than four times.
*
* Note that it is correct to test P_ISDELETED not P_IGNORE here,
* because half-dead pages are still in the sibling chain. Caller
* must reject half-dead pages if wanted.
*/
tries = 0;
for (;;)
{
if (!P_ISDELETED(opaque) && opaque->btpo_next == obknum)
{
/* Found desired page, return it */
return buf;
}
if (P_RIGHTMOST(opaque) || ++tries > 4)
break;
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/* Return to the original page to see what's up */
buf = _bt_relandgetbuf(rel, buf, obknum, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISDELETED(opaque))
{
/*
* It was deleted. Move right to first nondeleted page (there
* must be one); that is the page that has acquired the deleted
* one's keyspace, so stepping left from it will take us where we
* want to be.
*/
for (;;)
{
if (P_RIGHTMOST(opaque))
elog(ERROR, "fell off the end of index \"%s\"",
RelationGetRelationName(rel));
blkno = opaque->btpo_next;
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_ISDELETED(opaque))
break;
}
/*
* Now return to top of loop, resetting obknum to point to this
* nondeleted page, and try again.
*/
}
else
{
/*
* It wasn't deleted; the explanation had better be that the page
* to the left got split or deleted. Without this check, we'd go
* into an infinite loop if there's anything wrong.
*/
if (opaque->btpo_prev == lblkno)
elog(ERROR, "could not find left sibling of block %u in index \"%s\"",
obknum, RelationGetRelationName(rel));
/* Okay to try again with new lblkno value */
}
}
return InvalidBuffer;
}
static Datum
pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo)
{
Datum result;
BlockNumber nblocks;
BlockNumber blkno;
BTIndexStat indexStat;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
/*
* Read metapage
*/
{
Buffer buffer = ReadBufferExtended(rel, MAIN_FORKNUM, 0, RBM_NORMAL, bstrategy);
Page page = BufferGetPage(buffer);
BTMetaPageData *metad = BTPageGetMeta(page);
indexStat.version = metad->btm_version;
indexStat.level = metad->btm_level;
indexStat.root_blkno = metad->btm_root;
ReleaseBuffer(buffer);
}
/* -- init counters -- */
indexStat.internal_pages = 0;
indexStat.leaf_pages = 0;
indexStat.empty_pages = 0;
indexStat.deleted_pages = 0;
indexStat.max_avail = 0;
indexStat.free_space = 0;
indexStat.fragments = 0;
/*
* Scan all blocks except the metapage
*/
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buffer;
Page page;
BTPageOpaque opaque;
CHECK_FOR_INTERRUPTS();
/* Read and lock buffer */
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/* Determine page type, and update totals */
if (P_ISDELETED(opaque))
indexStat.deleted_pages++;
else if (P_IGNORE(opaque))
indexStat.empty_pages++; /* this is the "half dead" state */
else if (P_ISLEAF(opaque))
{
int max_avail;
max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
indexStat.max_avail += max_avail;
indexStat.free_space += PageGetFreeSpace(page);
indexStat.leaf_pages++;
/*
* If the next leaf is on an earlier block, it means a
* fragmentation.
*/
if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
indexStat.fragments++;
}
else
indexStat.internal_pages++;
/* Unlock and release buffer */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
relation_close(rel, AccessShareLock);
/*----------------------------
* Build a result tuple
*----------------------------
*/
{
TupleDesc tupleDesc;
int j;
char *values[10];
HeapTuple tuple;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
j = 0;
values[j++] = psprintf("%d", indexStat.version);
values[j++] = psprintf("%d", indexStat.level);
values[j++] = psprintf(INT64_FORMAT,
(1 + /* include the metapage in index_size */
indexStat.leaf_pages +
indexStat.internal_pages +
indexStat.deleted_pages +
indexStat.empty_pages) * BLCKSZ);
values[j++] = psprintf("%u", indexStat.root_blkno);
values[j++] = psprintf(INT64_FORMAT, indexStat.internal_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.leaf_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.empty_pages);
values[j++] = psprintf(INT64_FORMAT, indexStat.deleted_pages);
if (indexStat.max_avail > 0)
values[j++] = psprintf("%.2f",
100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
else
values[j++] = pstrdup("NaN");
if (indexStat.leaf_pages > 0)
values[j++] = psprintf("%.2f",
(double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
else
values[j++] = pstrdup("NaN");
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
values);
result = HeapTupleGetDatum(tuple);
}
return result;
}
/* -------------------------------------------------
* GetBTPageStatistics()
*
* Collect statistics of single b-tree page
* -------------------------------------------------
*/
static void
GetBTPageStatistics(block_t blkno, buf_id_t buffer, BTPageStat *stat)
{
page_p page = BUF_PAGE(buffer);
struct page_hdr * phdr = (struct page_hdr *) page;
item_id_t maxoff = PAGE_MAX_ITEM_ID(page);
struct bt_page_opaque * opaque = (struct bt_page_opaque *) PAGE_SPECIAL_PTR(page);
int item_size = 0;
int off;
stat->blkno = blkno;
stat->max_avail = BLK_SZ - (BLK_SZ - phdr->pd_special + PAGE_HDR_SZ);
stat->dead_items = stat->live_items = 0;
stat->page_size = PAGE_SZ(page);
/* page type (flags) */
if (P_ISDELETED(opaque))
{
stat->type = 'd';
stat->btpo.xact = opaque->btpo.xact;
return;
}
else if (P_IGNORE(opaque))
stat->type = 'e';
else if (P_ISLEAF(opaque))
stat->type = 'l';
else if (P_ISROOT(opaque))
stat->type = 'r';
else
stat->type = 'i';
/* btpage opaque data */
stat->btpo_prev = opaque->btpo_prev;
stat->btpo_next = opaque->btpo_next;
stat->btpo.level = opaque->btpo.level;
stat->btpo_flags = opaque->btpo_flags;
stat->btpo_cycleid = opaque->btpo_cycleid;
/* count live and dead tuples, and free space */
for (off = FIRST_ITEM_ID; off <= maxoff; off++)
{
struct index_tuple * itup;
struct item_id * id = PAGE_ITEM_ID(page, off);
itup = (struct index_tuple *) PAGE_GET_ITEM(page, id);
item_size += INDEX_TUPLE_SZ(itup);
if (!ITEMID_DEAD(id))
stat->live_items++;
else
stat->dead_items++;
}
stat->free_size = page_free_space(page);
if ((stat->live_items + stat->dead_items) > 0)
stat->avg_item_size = item_size / (stat->live_items + stat->dead_items);
else
stat->avg_item_size = 0;
}
datum_t
bt_page_items(PG_FUNC_ARGS)
{
text *relname = ARG_TEXT_P(0);
uint32 blkno = ARG_UINT32(1);
datum_t result;
char *values[6];
struct heap_tuple * tuple;
struct fcall_ctx *fctx;
struct mctx * mctx;
struct user_args *uargs;
if (!superuser())
ereport(ERROR,
(errcode(E_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pageinspect functions"))));
if (SRF_IS_FIRSTCALL())
{
range_var_n *relrv;
struct relation * rel;
buf_id_t buffer;
struct bt_page_opaque * opaque;
struct tuple * tupleDesc;
fctx = SRF_FIRSTCALL_INIT();
relrv = nl_to_range_var(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, ACCESS_SHR_LOCK);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
REL_NAME(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the
* owning session's local buffers.
*/
if (REL_IS_OTHER_TMP(rel))
ereport(ERROR,
(errcode(E_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
if (blkno == 0)
elog(ERROR, "block 0 is a meta page");
CHECK_RELATION_BLOCK_RANGE(rel, blkno);
buffer = read_buf(rel, blkno);
/*
* We copy the page into local storage to avoid holding pin on the
* buffer longer than we must, and possibly failing to release it at
* all if the calling query doesn't fetch all rows.
*/
mctx = mctx_switch(fctx->multi_call_memory_ctx);
uargs = palloc(sizeof(struct user_args));
uargs->page = palloc(BLK_SZ);
memcpy(uargs->page, BUF_PAGE(buffer), BLK_SZ);
release_buf(buffer);
relation_close(rel, ACCESS_SHR_LOCK);
uargs->offset = FIRST_ITEM_ID;
opaque = (struct bt_page_opaque *) PAGE_SPECIAL_PTR(uargs->page);
if (P_ISDELETED(opaque))
elog(NOTICE, "page is deleted");
fctx->max_calls = PAGE_MAX_ITEM_ID(uargs->page);
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc);
fctx->user_fctx = uargs;
mctx_switch(mctx);
}
fctx = SRF_PERCALL_SETUP();
uargs = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
struct item_id * id;
struct index_tuple * itup;
int j;
int off;
int dlen;
char *dump;
char *ptr;
id = PAGE_ITEM_ID(uargs->page, uargs->offset);
if (!ITEMID_VALID(id))
elog(ERROR, "invalid ItemId");
itup = (struct index_tuple *) PAGE_GET_ITEM(uargs->page, id);
j = 0;
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", uargs->offset);
values[j] = palloc(32);
snprintf(values[j++], 32, "(%u,%u)",
BLK_ID_TO_BLK_NR(&(itup->t_tid.ip_blkid)),
itup->t_tid.ip_posid);
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", (int) INDEX_TUPLE_SZ(itup));
values[j] = palloc(32);
snprintf(values[j++], 32, "%c", INDEX_TUPLE_HAS_NULLS(itup) ? 't' : 'f');
values[j] = palloc(32);
snprintf(values[j++], 32, "%c", INDEX_TUPLE_HAS_VAR(itup) ? 't' : 'f');
ptr = (char *) itup + INDEX_TUPLE_DATA_OFFSET(itup->t_info);
dlen = INDEX_TUPLE_SZ(itup) - INDEX_TUPLE_DATA_OFFSET(itup->t_info);
dump = pzalloc(dlen * 3 + 1);
values[j] = dump;
for (off = 0; off < dlen; off++)
{
if (off > 0)
*dump++ = ' ';
sprintf(dump, "%02x", *(ptr + off) & 0xff);
dump += 2;
}
tuple = build_tuple_from_cstrings(fctx->attinmeta, values);
result = HeapTupleGetDatum(tuple);
uargs->offset = uargs->offset + 1;
SRF_RETURN_NEXT(fctx, result);
}
else
{
pfree(uargs->page);
pfree(uargs);
SRF_RETURN_DONE(fctx);
}
}
/* ------------------------------------------------------
* pgstatindex()
*
* Usage: SELECT * FROM pgstatindex('t1_pkey');
* ------------------------------------------------------
*/
Datum
pgstatindex(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_P(0);
Relation rel;
RangeVar *relrv;
Datum result;
BlockNumber nblocks;
BlockNumber blkno;
BTIndexStat indexStat;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pgstattuple functions"))));
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the owning
* session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
/*
* Read metapage
*/
{
Buffer buffer = ReadBuffer(rel, 0);
Page page = BufferGetPage(buffer);
BTMetaPageData *metad = BTPageGetMeta(page);
indexStat.version = metad->btm_version;
indexStat.level = metad->btm_level;
indexStat.root_blkno = metad->btm_root;
ReleaseBuffer(buffer);
}
/* -- init counters -- */
indexStat.root_pages = 0;
indexStat.internal_pages = 0;
indexStat.leaf_pages = 0;
indexStat.empty_pages = 0;
indexStat.deleted_pages = 0;
indexStat.max_avail = 0;
indexStat.free_space = 0;
indexStat.fragments = 0;
/*
* Scan all blocks except the metapage
*/
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 1; blkno < nblocks; blkno++)
{
Buffer buffer;
Page page;
BTPageOpaque opaque;
/* Read and lock buffer */
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/* Determine page type, and update totals */
if (P_ISLEAF(opaque))
{
int max_avail;
max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
indexStat.max_avail += max_avail;
indexStat.free_space += PageGetFreeSpace(page);
indexStat.leaf_pages++;
/*
* If the next leaf is on an earlier block, it means a
* fragmentation.
*/
if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
indexStat.fragments++;
}
else if (P_ISDELETED(opaque))
indexStat.deleted_pages++;
else if (P_IGNORE(opaque))
indexStat.empty_pages++;
else if (P_ISROOT(opaque))
indexStat.root_pages++;
else
indexStat.internal_pages++;
/* Unlock and release buffer */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
relation_close(rel, AccessShareLock);
/*----------------------------
* Build a result tuple
*----------------------------
*/
{
TupleDesc tupleDesc;
int j;
char *values[10];
HeapTuple tuple;
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
j = 0;
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", indexStat.version);
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", indexStat.level);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT,
(indexStat.root_pages +
indexStat.leaf_pages +
indexStat.internal_pages +
indexStat.deleted_pages +
indexStat.empty_pages) * BLCKSZ);
values[j] = palloc(32);
snprintf(values[j++], 32, "%u", indexStat.root_blkno);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.internal_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.leaf_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.empty_pages);
values[j] = palloc(32);
snprintf(values[j++], 32, INT64_FORMAT, indexStat.deleted_pages);
values[j] = palloc(32);
if (indexStat.max_avail > 0)
snprintf(values[j++], 32, "%.2f",
100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
else
snprintf(values[j++], 32, "NaN");
values[j] = palloc(32);
if (indexStat.leaf_pages > 0)
snprintf(values[j++], 32, "%.2f",
(double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
else
snprintf(values[j++], 32, "NaN");
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
values);
result = HeapTupleGetDatum(tuple);
}
PG_RETURN_DATUM(result);
}
Datum
bt_page_items_bytea(PG_FUNCTION_ARGS)
{
bytea *raw_page = PG_GETARG_BYTEA_P(0);
Datum result;
FuncCallContext *fctx;
struct user_args *uargs;
int raw_page_size;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pageinspect functions"))));
if (SRF_IS_FIRSTCALL())
{
BTPageOpaque opaque;
MemoryContext mctx;
TupleDesc tupleDesc;
raw_page_size = VARSIZE(raw_page) - VARHDRSZ;
if (raw_page_size < SizeOfPageHeaderData)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("input page too small (%d bytes)", raw_page_size)));
fctx = SRF_FIRSTCALL_INIT();
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
uargs = palloc(sizeof(struct user_args));
uargs->page = VARDATA(raw_page);
uargs->offset = FirstOffsetNumber;
opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page);
if (P_ISMETA(opaque))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("block is a meta page")));
if (P_ISDELETED(opaque))
elog(NOTICE, "page is deleted");
fctx->max_calls = PageGetMaxOffsetNumber(uargs->page);
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc);
fctx->user_fctx = uargs;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
uargs = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
result = bt_page_print_tuples(fctx, uargs->page, uargs->offset);
uargs->offset++;
SRF_RETURN_NEXT(fctx, result);
}
else
{
pfree(uargs);
SRF_RETURN_DONE(fctx);
}
}
/*-------------------------------------------------------
* bt_page_items()
*
* Get IndexTupleData set in a btree page
*
* Usage: SELECT * FROM bt_page_items('t1_pkey', 1);
*-------------------------------------------------------
*/
Datum
bt_page_items(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_PP(0);
uint32 blkno = PG_GETARG_UINT32(1);
Datum result;
FuncCallContext *fctx;
MemoryContext mctx;
struct user_args *uargs;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pageinspect functions"))));
if (SRF_IS_FIRSTCALL())
{
RangeVar *relrv;
Relation rel;
Buffer buffer;
BTPageOpaque opaque;
TupleDesc tupleDesc;
fctx = SRF_FIRSTCALL_INIT();
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the
* owning session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
if (blkno == 0)
elog(ERROR, "block 0 is a meta page");
CHECK_RELATION_BLOCK_RANGE(rel, blkno);
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
/*
* We copy the page into local storage to avoid holding pin on the
* buffer longer than we must, and possibly failing to release it at
* all if the calling query doesn't fetch all rows.
*/
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
uargs = palloc(sizeof(struct user_args));
uargs->page = palloc(BLCKSZ);
memcpy(uargs->page, BufferGetPage(buffer), BLCKSZ);
UnlockReleaseBuffer(buffer);
relation_close(rel, AccessShareLock);
uargs->offset = FirstOffsetNumber;
opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page);
if (P_ISDELETED(opaque))
elog(NOTICE, "page is deleted");
fctx->max_calls = PageGetMaxOffsetNumber(uargs->page);
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc);
fctx->user_fctx = uargs;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
uargs = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
result = bt_page_print_tuples(fctx, uargs->page, uargs->offset);
uargs->offset++;
SRF_RETURN_NEXT(fctx, result);
}
else
{
pfree(uargs->page);
pfree(uargs);
SRF_RETURN_DONE(fctx);
}
}
Datum
bt_page_items(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_P(0);
uint32 blkno = PG_GETARG_UINT32(1);
Datum result;
char *values[6];
HeapTuple tuple;
FuncCallContext *fctx;
MemoryContext mctx;
struct user_args *uargs;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pageinspect functions"))));
if (SRF_IS_FIRSTCALL())
{
RangeVar *relrv;
Relation rel;
Buffer buffer;
BTPageOpaque opaque;
TupleDesc tupleDesc;
fctx = SRF_FIRSTCALL_INIT();
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
rel = relation_openrv(relrv, AccessShareLock);
if (!IS_INDEX(rel) || !IS_BTREE(rel))
elog(ERROR, "relation \"%s\" is not a btree index",
RelationGetRelationName(rel));
/*
* Reject attempts to read non-local temporary relations; we would be
* likely to get wrong data since we have no visibility into the
* owning session's local buffers.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot access temporary tables of other sessions")));
if (blkno == 0)
elog(ERROR, "block 0 is a meta page");
CHECK_RELATION_BLOCK_RANGE(rel, blkno);
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
/*
* We copy the page into local storage to avoid holding pin on the
* buffer longer than we must, and possibly failing to release it at
* all if the calling query doesn't fetch all rows.
*/
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
uargs = palloc(sizeof(struct user_args));
uargs->page = palloc(BLCKSZ);
memcpy(uargs->page, BufferGetPage(buffer), BLCKSZ);
UnlockReleaseBuffer(buffer);
relation_close(rel, AccessShareLock);
uargs->offset = FirstOffsetNumber;
opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page);
if (P_ISDELETED(opaque))
elog(NOTICE, "page is deleted");
fctx->max_calls = PageGetMaxOffsetNumber(uargs->page);
/* Build a tuple descriptor for our result type */
if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
fctx->attinmeta = TupleDescGetAttInMetadata(tupleDesc);
fctx->user_fctx = uargs;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
uargs = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
ItemId id;
IndexTuple itup;
int j;
int off;
int dlen;
char *dump;
char *ptr;
id = PageGetItemId(uargs->page, uargs->offset);
if (!ItemIdIsValid(id))
elog(ERROR, "invalid ItemId");
itup = (IndexTuple) PageGetItem(uargs->page, id);
j = 0;
values[j++] = psprintf("%d", uargs->offset);
values[j++] = psprintf("(%u,%u)",
BlockIdGetBlockNumber(&(itup->t_tid.ip_blkid)),
itup->t_tid.ip_posid);
values[j++] = psprintf("%d", (int) IndexTupleSize(itup));
values[j++] = psprintf("%c", IndexTupleHasNulls(itup) ? 't' : 'f');
values[j++] = psprintf("%c", IndexTupleHasVarwidths(itup) ? 't' : 'f');
ptr = (char *) itup + IndexInfoFindDataOffset(itup->t_info);
dlen = IndexTupleSize(itup) - IndexInfoFindDataOffset(itup->t_info);
dump = palloc0(dlen * 3 + 1);
values[j] = dump;
for (off = 0; off < dlen; off++)
{
if (off > 0)
*dump++ = ' ';
sprintf(dump, "%02x", *(ptr + off) & 0xff);
dump += 2;
}
tuple = BuildTupleFromCStrings(fctx->attinmeta, values);
result = HeapTupleGetDatum(tuple);
uargs->offset = uargs->offset + 1;
SRF_RETURN_NEXT(fctx, result);
}
else
{
pfree(uargs->page);
pfree(uargs);
SRF_RETURN_DONE(fctx);
}
}
Datum
bt_page_items(PG_FUNCTION_ARGS)
{
text *relname = PG_GETARG_TEXT_P(0);
uint32 blkno = PG_GETARG_UINT32(1);
RangeVar *relrv;
Datum result;
char *values[BTPAGEITEMS_NCOLUMNS];
BTPageOpaque opaque;
HeapTuple tuple;
ItemId id;
FuncCallContext *fctx;
MemoryContext mctx;
struct user_args *uargs = NULL;
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to use pgstattuple functions"))));
if (blkno == 0)
elog(ERROR, "Block 0 is a meta page.");
if (SRF_IS_FIRSTCALL())
{
fctx = SRF_FIRSTCALL_INIT();
mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
uargs = palloc(sizeof(struct user_args));
uargs->tupd = RelationNameGetTupleDesc(BTPAGEITEMS_TYPE);
uargs->offset = FirstOffsetNumber;
relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
uargs->rel = relation_openrv(relrv, AccessShareLock);
CHECK_RELATION_BLOCK_RANGE(uargs->rel, blkno);
uargs->buffer = ReadBuffer(uargs->rel, blkno);
if (!IS_INDEX(uargs->rel) || !IS_BTREE(uargs->rel))
elog(ERROR, "bt_page_items() can be used only on b-tree index.");
uargs->page = BufferGetPage(uargs->buffer);
opaque = (BTPageOpaque) PageGetSpecialPointer(uargs->page);
if (P_ISDELETED(opaque))
elog(NOTICE, "bt_page_items(): this page is deleted.");
fctx->max_calls = PageGetMaxOffsetNumber(uargs->page);
fctx->user_fctx = uargs;
MemoryContextSwitchTo(mctx);
}
fctx = SRF_PERCALL_SETUP();
uargs = fctx->user_fctx;
if (fctx->call_cntr < fctx->max_calls)
{
IndexTuple itup;
id = PageGetItemId(uargs->page, uargs->offset);
if (!ItemIdIsValid(id))
elog(ERROR, "Invalid ItemId.");
itup = (IndexTuple) PageGetItem(uargs->page, id);
{
int j = 0;
BlockNumber blkno = BlockIdGetBlockNumber(&(itup->t_tid.ip_blkid));
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", uargs->offset);
values[j] = palloc(32);
snprintf(values[j++], 32, "(%u,%u)", blkno, itup->t_tid.ip_posid);
values[j] = palloc(32);
snprintf(values[j++], 32, "%d", (int) IndexTupleSize(itup));
values[j] = palloc(32);
snprintf(values[j++], 32, "%c", IndexTupleHasNulls(itup) ? 't' : 'f');
values[j] = palloc(32);
snprintf(values[j++], 32, "%c", IndexTupleHasVarwidths(itup) ? 't' : 'f');
{
int off;
char *dump;
char *ptr = (char *) itup + IndexInfoFindDataOffset(itup->t_info);
dump = palloc(IndexTupleSize(itup) * 3);
memset(dump, 0, IndexTupleSize(itup) * 3);
for (off = 0;
off < IndexTupleSize(itup) - IndexInfoFindDataOffset(itup->t_info);
off++)
{
if (dump[0] == '\0')
sprintf(dump, "%02x", *(ptr + off) & 0xff);
else
{
char buf[4];
sprintf(buf, " %02x", *(ptr + off) & 0xff);
strcat(dump, buf);
}
}
values[j] = dump;
}
tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(uargs->tupd), values);
result = TupleGetDatum(TupleDescGetSlot(uargs->tupd), tuple);
}
uargs->offset = uargs->offset + 1;
SRF_RETURN_NEXT(fctx, result);
}
else
{
ReleaseBuffer(uargs->buffer);
relation_close(uargs->rel, AccessShareLock);
SRF_RETURN_DONE(fctx);
}
}
/*
* _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;
}
/*
* btvacuumpage --- VACUUM one page
*
* This processes a single page for btvacuumscan(). In some cases we
* must go back and re-examine previously-scanned pages; this routine
* recurses when necessary to handle that case.
*
* blkno is the page to process. orig_blkno is the highest block number
* reached by the outer btvacuumscan loop (the same as blkno, unless we
* are recursing to re-examine a previous page).
*/
static void
btvacuumpage(BTVacState *vstate, BlockNumber blkno, BlockNumber orig_blkno)
{
MIRROREDLOCK_BUFMGR_DECLARE;
IndexVacuumInfo *info = vstate->info;
IndexBulkDeleteResult *stats = vstate->stats;
IndexBulkDeleteCallback callback = vstate->callback;
void *callback_state = vstate->callback_state;
Relation rel = info->index;
bool delete_now;
BlockNumber recurse_to;
Buffer buf;
Page page;
BTPageOpaque opaque;
restart:
delete_now = false;
recurse_to = P_NONE;
/* call vacuum_delay_point while not holding any buffer lock */
vacuum_delay_point();
/*
* We can't use _bt_getbuf() here because it always applies
* _bt_checkpage(), which will barf on an all-zero page. We want to
* recycle all-zero pages, not fail. Also, we want to use a nondefault
* buffer access strategy.
*/
// -------- MirroredLock ----------
MIRROREDLOCK_BUFMGR_LOCK;
buf = ReadBufferWithStrategy(rel, blkno, info->strategy);
LockBuffer(buf, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!PageIsNew(page))
_bt_checkpage(rel, buf);
/*
* If we are recursing, the only case we want to do anything with is a
* live leaf page having the current vacuum cycle ID. Any other state
* implies we already saw the page (eg, deleted it as being empty). In
* particular, we don't want to risk adding it to freePages twice.
*/
if (blkno != orig_blkno)
{
if (_bt_page_recyclable(page) ||
P_IGNORE(opaque) ||
!P_ISLEAF(opaque) ||
opaque->btpo_cycleid != vstate->cycleid)
{
_bt_relbuf(rel, buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return;
}
}
/* Page is valid, see what to do with it */
if (_bt_page_recyclable(page))
{
/* Okay to recycle this page */
if (vstate->nFreePages < vstate->maxFreePages)
vstate->freePages[vstate->nFreePages++] = blkno;
vstate->totFreePages++;
stats->pages_deleted++;
}
else if (P_ISDELETED(opaque))
{
/* Already deleted, but can't recycle yet */
stats->pages_deleted++;
}
else if (P_ISHALFDEAD(opaque))
{
/* Half-dead, try to delete */
delete_now = true;
}
else if (P_ISLEAF(opaque))
{
OffsetNumber deletable[MaxOffsetNumber];
int ndeletable;
OffsetNumber offnum,
minoff,
maxoff;
/*
* Trade in the initial read lock for a super-exclusive write lock on
* this page. We must get such a lock on every leaf page over the
* course of the vacuum scan, whether or not it actually contains any
* deletable tuples --- see nbtree/README.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBufferForCleanup(buf);
/*
* Check whether we need to recurse back to earlier pages. What we
* are concerned about is a page split that happened since we started
* the vacuum scan. If the split moved some tuples to a lower page
* then we might have missed 'em. If so, set up for tail recursion.
* (Must do this before possibly clearing btpo_cycleid below!)
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid &&
!(opaque->btpo_flags & BTP_SPLIT_END) &&
!P_RIGHTMOST(opaque) &&
opaque->btpo_next < orig_blkno)
recurse_to = opaque->btpo_next;
/*
* Scan over all items to see which ones need deleted according to the
* callback function.
*/
ndeletable = 0;
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
if (callback)
{
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
IndexTuple itup;
ItemPointer htup;
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
htup = &(itup->t_tid);
if (callback(htup, callback_state))
deletable[ndeletable++] = offnum;
}
}
/*
* Apply any needed deletes. We issue just one _bt_delitems() call
* per page, so as to minimize WAL traffic.
*/
if (ndeletable > 0)
{
_bt_delitems(rel, buf, deletable, ndeletable, true);
stats->tuples_removed += ndeletable;
/* must recompute maxoff */
maxoff = PageGetMaxOffsetNumber(page);
}
else
{
/*
* If the page has been split during this vacuum cycle, it seems
* worth expending a write to clear btpo_cycleid even if we don't
* have any deletions to do. (If we do, _bt_delitems takes care
* of this.) This ensures we won't process the page again.
*
* We treat this like a hint-bit update because there's no need to
* WAL-log it.
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid)
{
opaque->btpo_cycleid = 0;
SetBufferCommitInfoNeedsSave(buf);
}
}
/*
* If it's now empty, try to delete; else count the live tuples. We
* don't delete when recursing, though, to avoid putting entries into
* freePages out-of-order (doesn't seem worth any extra code to handle
* the case).
*/
if (minoff > maxoff)
delete_now = (blkno == orig_blkno);
else
stats->num_index_tuples += maxoff - minoff + 1;
}
if (delete_now)
{
MemoryContext oldcontext;
int ndel;
/* Run pagedel in a temp context to avoid memory leakage */
MemoryContextReset(vstate->pagedelcontext);
oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);
ndel = _bt_pagedel(rel, buf, NULL, info->vacuum_full);
/* count only this page, else may double-count parent */
if (ndel)
stats->pages_deleted++;
/*
* During VACUUM FULL it's okay to recycle deleted pages immediately,
* since there can be no other transactions scanning the index. Note
* that we will only recycle the current page and not any parent pages
* that _bt_pagedel might have recursed to; this seems reasonable in
* the name of simplicity. (Trying to do otherwise would mean we'd
* have to sort the list of recyclable pages we're building.)
*/
if (ndel && info->vacuum_full)
{
if (vstate->nFreePages < vstate->maxFreePages)
vstate->freePages[vstate->nFreePages++] = blkno;
vstate->totFreePages++;
}
MemoryContextSwitchTo(oldcontext);
/* pagedel released buffer, so we shouldn't */
}
else
_bt_relbuf(rel, buf);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
/*
* This is really tail recursion, but if the compiler is too stupid to
* optimize it as such, we'd eat an uncomfortably large amount of stack
* space per recursion level (due to the deletable[] array). A failure is
* improbable since the number of levels isn't likely to be large ... but
* just in case, let's hand-optimize into a loop.
*/
if (recurse_to != P_NONE)
{
blkno = recurse_to;
goto restart;
}
}
/* -------------------------------------------------
* GetBTPageStatistics()
*
* Collect statistics of single b-tree page
* -------------------------------------------------
*/
static void
GetBTPageStatistics(BlockNumber blkno, Buffer buffer, BTPageStat *stat)
{
Page page = BufferGetPage(buffer);
PageHeader phdr = (PageHeader) page;
OffsetNumber maxoff = PageGetMaxOffsetNumber(page);
BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page);
int item_size = 0;
int off;
stat->blkno = blkno;
stat->max_avail = BLCKSZ - (BLCKSZ - phdr->pd_special + SizeOfPageHeaderData);
stat->dead_items = stat->live_items = 0;
stat->page_size = PageGetPageSize(page);
/* page type (flags) */
if (P_ISDELETED(opaque))
{
stat->type = 'd';
stat->btpo.xact = opaque->btpo.xact;
return;
}
else if (P_IGNORE(opaque))
stat->type = 'e';
else if (P_ISLEAF(opaque))
stat->type = 'l';
else if (P_ISROOT(opaque))
stat->type = 'r';
else
stat->type = 'i';
/* btpage opaque data */
stat->btpo_prev = opaque->btpo_prev;
stat->btpo_next = opaque->btpo_next;
stat->btpo.level = opaque->btpo.level;
stat->btpo_flags = opaque->btpo_flags;
stat->btpo_cycleid = opaque->btpo_cycleid;
/* count live and dead tuples, and free space */
for (off = FirstOffsetNumber; off <= maxoff; off++)
{
IndexTuple itup;
ItemId id = PageGetItemId(page, off);
itup = (IndexTuple) PageGetItem(page, id);
item_size += IndexTupleSize(itup);
if (!ItemIdIsDead(id))
stat->live_items++;
else
stat->dead_items++;
}
stat->free_size = PageGetFreeSpace(page);
if ((stat->live_items + stat->dead_items) > 0)
stat->avg_item_size = item_size / (stat->live_items + stat->dead_items);
else
stat->avg_item_size = 0;
}
/*
* btvacuumpage --- VACUUM one page
*
* This processes a single page for btvacuumscan(). In some cases we
* must go back and re-examine previously-scanned pages; this routine
* recurses when necessary to handle that case.
*
* blkno is the page to process. orig_blkno is the highest block number
* reached by the outer btvacuumscan loop (the same as blkno, unless we
* are recursing to re-examine a previous page).
*/
static void
btvacuumpage(BTVacState *vstate, BlockNumber blkno, BlockNumber orig_blkno)
{
IndexVacuumInfo *info = vstate->info;
IndexBulkDeleteResult *stats = vstate->stats;
IndexBulkDeleteCallback callback = vstate->callback;
void *callback_state = vstate->callback_state;
Relation rel = info->index;
bool delete_now;
BlockNumber recurse_to;
Buffer buf;
Page page;
BTPageOpaque opaque = NULL;
restart:
delete_now = false;
recurse_to = P_NONE;
/* call vacuum_delay_point while not holding any buffer lock */
vacuum_delay_point();
/*
* We can't use _bt_getbuf() here because it always applies
* _bt_checkpage(), which will barf on an all-zero page. We want to
* recycle all-zero pages, not fail. Also, we want to use a nondefault
* buffer access strategy.
*/
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
info->strategy);
LockBuffer(buf, BT_READ);
page = BufferGetPage(buf);
if (!PageIsNew(page))
{
_bt_checkpage(rel, buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/*
* If we are recursing, the only case we want to do anything with is a
* live leaf page having the current vacuum cycle ID. Any other state
* implies we already saw the page (eg, deleted it as being empty).
*/
if (blkno != orig_blkno)
{
if (_bt_page_recyclable(page) ||
P_IGNORE(opaque) ||
!P_ISLEAF(opaque) ||
opaque->btpo_cycleid != vstate->cycleid)
{
_bt_relbuf(rel, buf);
return;
}
}
/* Page is valid, see what to do with it */
if (_bt_page_recyclable(page))
{
/* Okay to recycle this page */
RecordFreeIndexPage(rel, blkno);
vstate->totFreePages++;
stats->pages_deleted++;
}
else if (P_ISDELETED(opaque))
{
/* Already deleted, but can't recycle yet */
stats->pages_deleted++;
}
else if (P_ISHALFDEAD(opaque))
{
/* Half-dead, try to delete */
delete_now = true;
}
else if (P_ISLEAF(opaque))
{
OffsetNumber deletable[MaxOffsetNumber];
int ndeletable;
OffsetNumber offnum,
minoff,
maxoff;
/*
* Trade in the initial read lock for a super-exclusive write lock on
* this page. We must get such a lock on every leaf page over the
* course of the vacuum scan, whether or not it actually contains any
* deletable tuples --- see nbtree/README.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBufferForCleanup(buf);
/*
* Remember highest leaf page number we've taken cleanup lock on; see
* notes in btvacuumscan
*/
if (blkno > vstate->lastBlockLocked)
vstate->lastBlockLocked = blkno;
/*
* Check whether we need to recurse back to earlier pages. What we
* are concerned about is a page split that happened since we started
* the vacuum scan. If the split moved some tuples to a lower page
* then we might have missed 'em. If so, set up for tail recursion.
* (Must do this before possibly clearing btpo_cycleid below!)
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid &&
!(opaque->btpo_flags & BTP_SPLIT_END) &&
!P_RIGHTMOST(opaque) &&
opaque->btpo_next < orig_blkno)
recurse_to = opaque->btpo_next;
/*
* Scan over all items to see which ones need deleted according to the
* callback function.
*/
ndeletable = 0;
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
if (callback)
{
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
IndexTuple itup;
ItemPointer htup;
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
htup = &(itup->t_tid);
/*
* During Hot Standby we currently assume that
* XLOG_BTREE_VACUUM records do not produce conflicts. That is
* only true as long as the callback function depends only
* upon whether the index tuple refers to heap tuples removed
* in the initial heap scan. When vacuum starts it derives a
* value of OldestXmin. Backends taking later snapshots could
* have a RecentGlobalXmin with a later xid than the vacuum's
* OldestXmin, so it is possible that row versions deleted
* after OldestXmin could be marked as killed by other
* backends. The callback function *could* look at the index
* tuple state in isolation and decide to delete the index
* tuple, though currently it does not. If it ever did, we
* would need to reconsider whether XLOG_BTREE_VACUUM records
* should cause conflicts. If they did cause conflicts they
* would be fairly harsh conflicts, since we haven't yet
* worked out a way to pass a useful value for
* latestRemovedXid on the XLOG_BTREE_VACUUM records. This
* applies to *any* type of index that marks index tuples as
* killed.
*/
if (callback(htup, callback_state))
deletable[ndeletable++] = offnum;
}
}
/*
* Apply any needed deletes. We issue just one _bt_delitems_vacuum()
* call per page, so as to minimize WAL traffic.
*/
if (ndeletable > 0)
{
/*
* Notice that the issued XLOG_BTREE_VACUUM WAL record includes
* all information to the replay code to allow it to get a cleanup
* lock on all pages between the previous lastBlockVacuumed and
* this page. This ensures that WAL replay locks all leaf pages at
* some point, which is important should non-MVCC scans be
* requested. This is currently unused on standby, but we record
* it anyway, so that the WAL contains the required information.
*
* Since we can visit leaf pages out-of-order when recursing,
* replay might end up locking such pages an extra time, but it
* doesn't seem worth the amount of bookkeeping it'd take to avoid
* that.
*/
_bt_delitems_vacuum(rel, buf, deletable, ndeletable,
vstate->lastBlockVacuumed);
/*
* Remember highest leaf page number we've issued a
* XLOG_BTREE_VACUUM WAL record for.
*/
if (blkno > vstate->lastBlockVacuumed)
vstate->lastBlockVacuumed = blkno;
stats->tuples_removed += ndeletable;
/* must recompute maxoff */
maxoff = PageGetMaxOffsetNumber(page);
}
else
{
/*
* If the page has been split during this vacuum cycle, it seems
* worth expending a write to clear btpo_cycleid even if we don't
* have any deletions to do. (If we do, _bt_delitems_vacuum takes
* care of this.) This ensures we won't process the page again.
*
* We treat this like a hint-bit update because there's no need to
* WAL-log it.
*/
if (vstate->cycleid != 0 &&
opaque->btpo_cycleid == vstate->cycleid)
{
opaque->btpo_cycleid = 0;
MarkBufferDirtyHint(buf, true);
}
}
/*
* If it's now empty, try to delete; else count the live tuples. We
* don't delete when recursing, though, to avoid putting entries into
* freePages out-of-order (doesn't seem worth any extra code to handle
* the case).
*/
if (minoff > maxoff)
delete_now = (blkno == orig_blkno);
else
stats->num_index_tuples += maxoff - minoff + 1;
}
if (delete_now)
{
MemoryContext oldcontext;
int ndel;
/* Run pagedel in a temp context to avoid memory leakage */
MemoryContextReset(vstate->pagedelcontext);
oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);
ndel = _bt_pagedel(rel, buf);
/* count only this page, else may double-count parent */
if (ndel)
stats->pages_deleted++;
MemoryContextSwitchTo(oldcontext);
/* pagedel released buffer, so we shouldn't */
}
else
_bt_relbuf(rel, buf);
/*
* This is really tail recursion, but if the compiler is too stupid to
* optimize it as such, we'd eat an uncomfortably large amount of stack
* space per recursion level (due to the deletable[] array). A failure is
* improbable since the number of levels isn't likely to be large ... but
* just in case, let's hand-optimize into a loop.
*/
if (recurse_to != P_NONE)
{
blkno = recurse_to;
goto restart;
}
}
uint32 check_index_page(Relation rel, PageHeader header, char *buffer, int block) {
uint32 nerrs = 0;
BTPageOpaque opaque = NULL;
/* check basic page header */
nerrs += check_page_header(header, block);
/* (block==0) means it's a meta-page, otherwise it's a regular index-page */
if (block == BTREE_METAPAGE) {
BTMetaPageData * mpdata = BTPageGetMeta(buffer);
ereport(DEBUG2, (errmsg("[%d] is a meta-page [magic=%d, version=%d]", block, mpdata->btm_magic, mpdata->btm_version)));
if (mpdata->btm_magic != BTREE_MAGIC) {
ereport(WARNING,(errmsg("[%d] metapage contains invalid magic number %d (should be %d)", block, mpdata->btm_magic, BTREE_MAGIC)));
nerrs++;
}
if (mpdata->btm_version != BTREE_VERSION) {
ereport(WARNING,(errmsg("[%d] metapage contains invalid version %d (should be %d)", block, mpdata->btm_version, BTREE_VERSION)));
nerrs++;
}
/* FIXME Check that the btm_root/btm_fastroot is between 1 and number of index blocks */
/* FIXME Check that the btm_level/btm_fastlevel is equal to the level fo the root block */
} else {
opaque = (BTPageOpaque)(buffer + header->pd_special);
/* check there's enough space for index-relevant data */
if (header->pd_special > BLCKSZ - sizeof(BTPageOpaque)) {
ereport(WARNING,
(errmsg("[%d] there's not enough special space for index data (%d > %d)",
block,
(int) sizeof(BTPageOpaque),
BLCKSZ - header->pd_special)));
nerrs++;
}
/*
* if the page is a leaf page, then level needs to be 0. Otherwise,
* it should be > 0. Deleted pages don't have a level, the level
* field is interleaved with an xid.
*/
if (!P_ISDELETED(opaque))
{
if (P_ISLEAF(opaque))
{
if (opaque-> btpo.level != 0) {
ereport(WARNING,
(errmsg("[%d] is leaf page, but level %d is not zero",
block, opaque->btpo.level)));
nerrs++;
}
}
else
{
if (opaque-> btpo.level == 0) {
ereport(WARNING,
(errmsg("[%d] is a non-leaf page, but level is zero",
block)));
nerrs++;
}
}
}
}
return nerrs;
}
