/*
* _bt_relandgetbuf() -- release a locked buffer and get another one.
*
* This is equivalent to _bt_relbuf followed by _bt_getbuf, with the
* exception that blkno may not be P_NEW. Also, if obuf is InvalidBuffer
* then it reduces to just _bt_getbuf; allowing this case simplifies some
* callers.
*
* The original motivation for using this was to avoid two entries to the
* bufmgr when one would do. However, now it's mainly just a notational
* convenience. The only case where it saves work over _bt_relbuf/_bt_getbuf
* is when the target page is the same one already in the buffer.
*/
Buffer
_bt_relandgetbuf(Relation rel, Buffer obuf, BlockNumber blkno, int access)
{
Buffer buf;
Assert(blkno != P_NEW);
if (BufferIsValid(obuf))
LockBuffer(obuf, BUFFER_LOCK_UNLOCK);
buf = ReleaseAndReadBuffer(obuf, rel, blkno);
LockBuffer(buf, access);
_bt_checkpage(rel, buf);
return buf;
}
/*
* btvacuumscan --- scan the index for VACUUMing purposes
*
* This combines the functions of looking for leaf tuples that are deletable
* according to the vacuum callback, looking for empty pages that can be
* deleted, and looking for old deleted pages that can be recycled. Both
* btbulkdelete and btvacuumcleanup invoke this (the latter only if no
* btbulkdelete call occurred).
*
* The caller is responsible for initially allocating/zeroing a stats struct
* and for obtaining a vacuum cycle ID if necessary.
*/
static void
btvacuumscan(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback, void *callback_state,
BTCycleId cycleid)
{
Relation rel = info->index;
BTVacState vstate;
BlockNumber num_pages;
BlockNumber blkno;
bool needLock;
/*
* Reset counts that will be incremented during the scan; needed in case
* of multiple scans during a single VACUUM command
*/
stats->estimated_count = false;
stats->num_index_tuples = 0;
stats->pages_deleted = 0;
/* Set up info to pass down to btvacuumpage */
vstate.info = info;
vstate.stats = stats;
vstate.callback = callback;
vstate.callback_state = callback_state;
vstate.cycleid = cycleid;
vstate.lastBlockVacuumed = BTREE_METAPAGE; /* Initialise at first block */
vstate.lastBlockLocked = BTREE_METAPAGE;
vstate.totFreePages = 0;
/* Create a temporary memory context to run _bt_pagedel in */
vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
"_bt_pagedel",
ALLOCSET_DEFAULT_SIZES);
/*
* The outer loop iterates over all index pages except the metapage, in
* physical order (we hope the kernel will cooperate in providing
* read-ahead for speed). It is critical that we visit all leaf pages,
* including ones added after we start the scan, else we might fail to
* delete some deletable tuples. Hence, we must repeatedly check the
* relation length. We must acquire the relation-extension lock while
* doing so to avoid a race condition: if someone else is extending the
* relation, there is a window where bufmgr/smgr have created a new
* all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
* we manage to scan such a page here, we'll improperly assume it can be
* recycled. Taking the lock synchronizes things enough to prevent a
* problem: either num_pages won't include the new page, or _bt_getbuf
* already has write lock on the buffer and it will be fully initialized
* before we can examine it. (See also vacuumlazy.c, which has the same
* issue.) Also, we need not worry if a page is added immediately after
* we look; the page splitting code already has write-lock on the left
* page before it adds a right page, so we must already have processed any
* tuples due to be moved into such a page.
*
* We can skip locking for new or temp relations, however, since no one
* else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
blkno = BTREE_METAPAGE + 1;
for (;;)
{
/* Get the current relation length */
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
num_pages = RelationGetNumberOfBlocks(rel);
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Quit if we've scanned the whole relation */
if (blkno >= num_pages)
break;
/* Iterate over pages, then loop back to recheck length */
for (; blkno < num_pages; blkno++)
{
btvacuumpage(&vstate, blkno, blkno);
}
}
/*
* Check to see if we need to issue one final WAL record for this index,
* which may be needed for correctness on a hot standby node when non-MVCC
* index scans could take place.
*
* If the WAL is replayed in hot standby, the replay process needs to get
* cleanup locks on all index leaf pages, just as we've been doing here.
* However, we won't issue any WAL records about pages that have no items
* to be deleted. For pages between pages we've vacuumed, the replay code
* will take locks under the direction of the lastBlockVacuumed fields in
* the XLOG_BTREE_VACUUM WAL records. To cover pages after the last one
* we vacuum, we need to issue a dummy XLOG_BTREE_VACUUM WAL record
* against the last leaf page in the index, if that one wasn't vacuumed.
*/
if (XLogStandbyInfoActive() &&
vstate.lastBlockVacuumed < vstate.lastBlockLocked)
{
Buffer buf;
/*
* The page should be valid, but we can't use _bt_getbuf() because we
* want to use a nondefault buffer access strategy. Since we aren't
* going to delete any items, getting cleanup lock again is probably
* overkill, but for consistency do that anyway.
*/
buf = ReadBufferExtended(rel, MAIN_FORKNUM, vstate.lastBlockLocked,
RBM_NORMAL, info->strategy);
LockBufferForCleanup(buf);
_bt_checkpage(rel, buf);
_bt_delitems_vacuum(rel, buf, NULL, 0, vstate.lastBlockVacuumed);
_bt_relbuf(rel, buf);
}
MemoryContextDelete(vstate.pagedelcontext);
/* update statistics */
stats->num_pages = num_pages;
stats->pages_free = vstate.totFreePages;
}
/*
* 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;
}
}
/*
* For a newly inserted heap tid, check if an entry with this tid
* already exists in a unique index. If it does, abort the inserting
* transaction.
*/
static void
_bt_validate_tid(Relation irel, ItemPointer h_tid)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber blkno;
BlockNumber num_pages;
Buffer buf;
Page page;
BTPageOpaque opaque;
IndexTuple itup;
OffsetNumber maxoff,
minoff,
offnum;
elog(DEBUG1, "validating tid (%d,%d) for index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
RelationGetRelationName(irel));
blkno = BTREE_METAPAGE + 1;
num_pages = RelationGetNumberOfBlocks(irel);
MIRROREDLOCK_BUFMGR_LOCK;
for (; blkno < num_pages; blkno++)
{
buf = ReadBuffer(irel, blkno);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!PageIsNew(page))
_bt_checkpage(irel, buf);
if (P_ISLEAF(opaque))
{
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
itup = (IndexTuple) PageGetItem(page,
PageGetItemId(page, offnum));
if (ItemPointerEquals(&itup->t_tid, h_tid))
{
Form_pg_attribute key_att = RelationGetDescr(irel)->attrs[0];
Oid key = InvalidOid;
bool isnull;
if (key_att->atttypid == OIDOID)
{
key = DatumGetInt32(
index_getattr(itup, 1, RelationGetDescr(irel), &isnull));
elog(ERROR, "found tid (%d,%d), %s (%d) already in index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
NameStr(key_att->attname), key, RelationGetRelationName(irel));
}
else
{
elog(ERROR, "found tid (%d,%d) already in index (%s)",
ItemPointerGetBlockNumber(h_tid), ItemPointerGetOffsetNumber(h_tid),
RelationGetRelationName(irel));
}
}
}
}
ReleaseBuffer(buf);
}
MIRROREDLOCK_BUFMGR_UNLOCK;
}
/*
* Post vacuum, iterate over all entries in index, check if the h_tid
* of each entry exists and is not dead. For specific system tables,
* also ensure that the key in index entry matches the corresponding
* attribute in the heap tuple.
*/
void
_bt_validate_vacuum(Relation irel, Relation hrel, TransactionId oldest_xmin)
{
MIRROREDLOCK_BUFMGR_DECLARE;
BlockNumber blkno;
BlockNumber num_pages;
Buffer ibuf = InvalidBuffer;
Buffer hbuf = InvalidBuffer;
Page ipage;
BTPageOpaque opaque;
IndexTuple itup;
HeapTupleData htup;
OffsetNumber maxoff,
minoff,
offnum;
Oid ioid,
hoid;
bool isnull;
blkno = BTREE_METAPAGE + 1;
num_pages = RelationGetNumberOfBlocks(irel);
elog(LOG, "btvalidatevacuum: index %s, heap %s",
RelationGetRelationName(irel), RelationGetRelationName(hrel));
MIRROREDLOCK_BUFMGR_LOCK;
for (; blkno < num_pages; blkno++)
{
ibuf = ReadBuffer(irel, blkno);
ipage = BufferGetPage(ibuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(ipage);
if (!PageIsNew(ipage))
_bt_checkpage(irel, ibuf);
if (P_ISLEAF(opaque))
{
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(ipage);
for (offnum = minoff;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
itup = (IndexTuple) PageGetItem(ipage,
PageGetItemId(ipage, offnum));
ItemPointerCopy(&itup->t_tid, &htup.t_self);
/*
* TODO: construct a tid bitmap based on index tids
* and fetch heap tids in order afterwards. That will
* also allow validating if a heap tid appears twice
* in a unique index.
*/
if (!heap_release_fetch(hrel, SnapshotAny, &htup,
&hbuf, true, NULL))
{
elog(ERROR, "btvalidatevacuum: tid (%d,%d) from index %s "
"not found in heap %s",
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel),
RelationGetRelationName(hrel));
}
switch (HeapTupleSatisfiesVacuum(hrel, htup.t_data, oldest_xmin, hbuf))
{
case HEAPTUPLE_RECENTLY_DEAD:
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* these tuples are considered alive by vacuum */
break;
case HEAPTUPLE_DEAD:
elog(ERROR, "btvalidatevacuum: vacuum did not remove "
"dead tuple (%d,%d) from heap %s and index %s",
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(hrel),
RelationGetRelationName(irel));
break;
default:
elog(ERROR, "btvalidatevacuum: invalid visibility");
break;
}
switch(RelationGetRelid(irel))
{
case DatabaseOidIndexId:
case TypeOidIndexId:
case ClassOidIndexId:
case ConstraintOidIndexId:
hoid = HeapTupleGetOid(&htup);
ioid = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
if (hoid != ioid)
{
elog(ERROR,
"btvalidatevacuum: index oid(%d) != heap oid(%d)"
" tuple (%d,%d) index %s", ioid, hoid,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
break;
case GpRelationNodeOidIndexId:
hoid = heap_getattr(&htup, 1, RelationGetDescr(hrel), &isnull);
ioid = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
if (hoid != ioid)
{
elog(ERROR,
"btvalidatevacuum: index oid(%d) != heap oid(%d)"
" tuple (%d,%d) index %s", ioid, hoid,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
int4 hsegno = heap_getattr(&htup, 2, RelationGetDescr(hrel), &isnull);
int4 isegno = index_getattr(itup, 2, RelationGetDescr(irel), &isnull);
if (isegno != hsegno)
{
elog(ERROR,
"btvalidatevacuum: index segno(%d) != heap segno(%d)"
" tuple (%d,%d) index %s", isegno, hsegno,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
break;
default:
break;
}
if (RelationGetNamespace(irel) == PG_AOSEGMENT_NAMESPACE)
{
int4 isegno = index_getattr(itup, 1, RelationGetDescr(irel), &isnull);
int4 hsegno = heap_getattr(&htup, 1, RelationGetDescr(hrel), &isnull);
if (isegno != hsegno)
{
elog(ERROR,
"btvalidatevacuum: index segno(%d) != heap segno(%d)"
" tuple (%d,%d) index %s", isegno, hsegno,
ItemPointerGetBlockNumber(&itup->t_tid),
ItemPointerGetOffsetNumber(&itup->t_tid),
RelationGetRelationName(irel));
}
}
}
}
if (BufferIsValid(ibuf))
ReleaseBuffer(ibuf);
}
if (BufferIsValid(hbuf))
ReleaseBuffer(hbuf);
MIRROREDLOCK_BUFMGR_UNLOCK;
}
/*
* 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;
}
}
/*
* _bt_getbuf() -- Get a buffer by block number for read or write.
*
* blkno == P_NEW means to get an unallocated index page. The page
* will be initialized before returning it.
*
* When this routine returns, the appropriate lock is set on the
* requested buffer and its reference count has been incremented
* (ie, the buffer is "locked and pinned"). Also, we apply
* _bt_checkpage to sanity-check the page (except in P_NEW case).
*/
Buffer
_bt_getbuf(Relation rel, BlockNumber blkno, int access)
{
Buffer buf;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
if (blkno != P_NEW)
{
/* Read an existing block of the relation */
buf = ReadBuffer(rel, blkno);
LockBuffer(buf, access);
_bt_checkpage(rel, buf);
}
else
{
bool needLock;
Page page;
Assert(access == BT_WRITE);
/*
* First see if the FSM knows of any free pages.
*
* We can't trust the FSM's report unreservedly; we have to check that
* the page is still free. (For example, an already-free page could
* have been re-used between the time the last VACUUM scanned it and
* the time the VACUUM made its FSM updates.)
*
* In fact, it's worse than that: we can't even assume that it's safe
* to take a lock on the reported page. If somebody else has a lock
* on it, or even worse our own caller does, we could deadlock. (The
* own-caller scenario is actually not improbable. Consider an index
* on a serial or timestamp column. Nearly all splits will be at the
* rightmost page, so it's entirely likely that _bt_split will call us
* while holding a lock on the page most recently acquired from FSM. A
* VACUUM running concurrently with the previous split could well have
* placed that page back in FSM.)
*
* To get around that, we ask for only a conditional lock on the
* reported page. If we fail, then someone else is using the page,
* and we may reasonably assume it's not free. (If we happen to be
* wrong, the worst consequence is the page will be lost to use till
* the next VACUUM, which is no big problem.)
*/
for (;;)
{
blkno = GetFreeIndexPage(&rel->rd_node);
if (blkno == InvalidBlockNumber)
break;
buf = ReadBuffer(rel, blkno);
if (ConditionalLockBuffer(buf))
{
page = BufferGetPage(buf);
if (_bt_page_recyclable(page))
{
/* Okay to use page. Re-initialize and return it */
_bt_pageinit(page, BufferGetPageSize(buf));
return buf;
}
elog(DEBUG2, "FSM returned nonrecyclable page");
_bt_relbuf(rel, buf);
}
else
{
elog(DEBUG2, "FSM returned nonlockable page");
/* couldn't get lock, so just drop pin */
ReleaseBuffer(buf);
}
}
/*
* Extend the relation by one page.
*
* We have to use a lock to ensure no one else is extending the rel at
* the same time, else we will both try to initialize the same new
* page. We can skip locking for new or temp relations, however,
* since no one else could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(rel);
if (needLock)
LockRelationForExtension(rel, ExclusiveLock);
buf = ReadBuffer(rel, P_NEW);
/* Acquire buffer lock on new page */
LockBuffer(buf, BT_WRITE);
/*
* Release the file-extension lock; it's now OK for someone else to
* extend the relation some more. Note that we cannot release this
* lock before we have buffer lock on the new page, or we risk a race
* condition against btvacuumscan --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(rel, ExclusiveLock);
/* Initialize the new page before returning it */
page = BufferGetPage(buf);
Assert(PageIsNew((PageHeader) page));
_bt_pageinit(page, BufferGetPageSize(buf));
}
/* ref count and lock type are correct */
return buf;
}
