static void
killtuple(Relation r, GISTScanOpaque so, ItemPointer iptr)
{
MIRROREDLOCK_BUFMGR_DECLARE;
Page p;
OffsetNumber offset;
// -------- MirroredLock ----------
MIRROREDLOCK_BUFMGR_LOCK;
LockBuffer(so->curbuf, GIST_SHARE);
gistcheckpage(r, so->curbuf);
p = (Page) BufferGetPage(so->curbuf);
if (XLByteEQ(so->stack->lsn, PageGetLSN(p)))
{
/* page unchanged, so all is simple */
offset = ItemPointerGetOffsetNumber(iptr);
ItemIdMarkDead(PageGetItemId(p, offset));
SetBufferCommitInfoNeedsSave(so->curbuf);
}
else
{
OffsetNumber maxoff = PageGetMaxOffsetNumber(p);
for (offset = FirstOffsetNumber; offset <= maxoff; offset = OffsetNumberNext(offset))
{
IndexTuple ituple = (IndexTuple) PageGetItem(p, PageGetItemId(p, offset));
if (ItemPointerEquals(&(ituple->t_tid), iptr))
{
/* found */
ItemIdMarkDead(PageGetItemId(p, offset));
SetBufferCommitInfoNeedsSave(so->curbuf);
break;
}
}
}
LockBuffer(so->curbuf, GIST_UNLOCK);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
}
/*
* SetHintBits()
*
* Set commit/abort hint bits on a tuple, if appropriate at this time.
*
* It is only safe to set a transaction-committed hint bit if we know the
* transaction's commit record has been flushed to disk. We cannot change
* the LSN of the page here because we may hold only a share lock on the
* buffer, so we can't use the LSN to interlock this; we have to just refrain
* from setting the hint bit until some future re-examination of the tuple.
*
* We can always set hint bits when marking a transaction aborted. (Some
* code in heapam.c relies on that!)
*
* Also, if we are cleaning up HEAP_MOVED_IN or HEAP_MOVED_OFF entries, then
* we can always set the hint bits, since VACUUM FULL always uses synchronous
* commits and doesn't move tuples that weren't previously hinted. (This is
* not known by this subroutine, but is applied by its callers.)
*
* Normal commits may be asynchronous, so for those we need to get the LSN
* of the transaction and then check whether this is flushed.
*
* The caller should pass xid as the XID of the transaction to check, or
* InvalidTransactionId if no check is needed.
*/
static inline void
SetHintBits(HeapTupleHeader tuple, Buffer buffer,
uint16 infomask, TransactionId xid)
{
if (TransactionIdIsValid(xid))
{
/* NB: xid must be known committed here! */
XLogRecPtr commitLSN = TransactionIdGetCommitLSN(xid);
if (XLogNeedsFlush(commitLSN))
return; /* not flushed yet, so don't set hint */
}
tuple->t_infomask |= infomask;
SetBufferCommitInfoNeedsSave(buffer);
}
Datum
rtgettuple(PG_FUNCTION_ARGS)
{
IndexScanDesc s = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanDirection dir = (ScanDirection) PG_GETARG_INT32(1);
RTreeScanOpaque so = (RTreeScanOpaque) s->opaque;
Page page;
OffsetNumber offnum;
/*
* If we've already produced a tuple and the executor has informed us that
* it should be marked "killed", do so now.
*/
if (s->kill_prior_tuple && ItemPointerIsValid(&(s->currentItemData)))
{
offnum = ItemPointerGetOffsetNumber(&(s->currentItemData));
page = BufferGetPage(so->curbuf);
PageGetItemId(page, offnum)->lp_flags |= LP_DELETE;
SetBufferCommitInfoNeedsSave(so->curbuf);
}
/*
* Get the next tuple that matches the search key; if asked to skip killed
* tuples, find the first non-killed tuple that matches. Return as soon as
* we've run out of matches or we've found an acceptable match.
*/
for (;;)
{
bool res = rtnext(s, dir);
if (res && s->ignore_killed_tuples)
{
offnum = ItemPointerGetOffsetNumber(&(s->currentItemData));
page = BufferGetPage(so->curbuf);
if (ItemIdDeleted(PageGetItemId(page, offnum)))
continue;
}
PG_RETURN_BOOL(res);
}
}
/*
* lazy_scan_heap() -- scan an open heap relation
*
* This routine sets commit status bits, builds lists of dead tuples
* and pages with free space, and calculates statistics on the number
* of live tuples in the heap. When done, or when we run low on space
* for dead-tuple TIDs, invoke vacuuming of indexes and heap.
*
* If there are no indexes then we just vacuum each dirty page as we
* process it, since there's no point in gathering many tuples.
*/
static void
lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats,
Relation *Irel, int nindexes, bool scan_all)
{
BlockNumber nblocks,
blkno;
HeapTupleData tuple;
char *relname;
BlockNumber empty_pages,
vacuumed_pages;
double num_tuples,
tups_vacuumed,
nkeep,
nunused;
IndexBulkDeleteResult **indstats;
int i;
PGRUsage ru0;
Buffer vmbuffer = InvalidBuffer;
BlockNumber next_not_all_visible_block;
bool skipping_all_visible_blocks;
pg_rusage_init(&ru0);
relname = RelationGetRelationName(onerel);
ereport(elevel,
(errmsg("vacuuming \"%s.%s\"",
get_namespace_name(RelationGetNamespace(onerel)),
relname)));
empty_pages = vacuumed_pages = 0;
num_tuples = tups_vacuumed = nkeep = nunused = 0;
indstats = (IndexBulkDeleteResult **)
palloc0(nindexes * sizeof(IndexBulkDeleteResult *));
nblocks = RelationGetNumberOfBlocks(onerel);
vacrelstats->rel_pages = nblocks;
vacrelstats->scanned_pages = 0;
vacrelstats->nonempty_pages = 0;
vacrelstats->latestRemovedXid = InvalidTransactionId;
lazy_space_alloc(vacrelstats, nblocks);
/*
* We want to skip pages that don't require vacuuming according to the
* visibility map, but only when we can skip at least SKIP_PAGES_THRESHOLD
* consecutive pages. Since we're reading sequentially, the OS should be
* doing readahead for us, so there's no gain in skipping a page now and
* then; that's likely to disable readahead and so be counterproductive.
* Also, skipping even a single page means that we can't update
* relfrozenxid, so we only want to do it if we can skip a goodly number
* of pages.
*
* Before entering the main loop, establish the invariant that
* next_not_all_visible_block is the next block number >= blkno that's not
* all-visible according to the visibility map, or nblocks if there's no
* such block. Also, we set up the skipping_all_visible_blocks flag,
* which is needed because we need hysteresis in the decision: once we've
* started skipping blocks, we may as well skip everything up to the next
* not-all-visible block.
*
* Note: if scan_all is true, we won't actually skip any pages; but we
* maintain next_not_all_visible_block anyway, so as to set up the
* all_visible_according_to_vm flag correctly for each page.
*/
for (next_not_all_visible_block = 0;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block, &vmbuffer))
break;
vacuum_delay_point();
}
if (next_not_all_visible_block >= SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
bool tupgone,
hastup;
int prev_dead_count;
OffsetNumber frozen[MaxOffsetNumber];
int nfrozen;
Size freespace;
bool all_visible_according_to_vm;
bool all_visible;
bool has_dead_tuples;
if (blkno == next_not_all_visible_block)
{
/* Time to advance next_not_all_visible_block */
for (next_not_all_visible_block++;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block,
&vmbuffer))
break;
vacuum_delay_point();
}
/*
* We know we can't skip the current block. But set up
* skipping_all_visible_blocks to do the right thing at the
* following blocks.
*/
if (next_not_all_visible_block - blkno > SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
all_visible_according_to_vm = false;
}
else
{
/* Current block is all-visible */
if (skipping_all_visible_blocks && !scan_all)
continue;
all_visible_according_to_vm = true;
}
vacuum_delay_point();
vacrelstats->scanned_pages++;
/*
* If we are close to overrunning the available space for dead-tuple
* TIDs, pause and do a cycle of vacuuming before we tackle this page.
*/
if ((vacrelstats->max_dead_tuples - vacrelstats->num_dead_tuples) < MaxHeapTuplesPerPage &&
vacrelstats->num_dead_tuples > 0)
{
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacrelstats->num_index_scans++;
}
buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
RBM_NORMAL, vac_strategy);
/* We need buffer cleanup lock so that we can prune HOT chains. */
LockBufferForCleanup(buf);
page = BufferGetPage(buf);
if (PageIsNew(page))
{
/*
* An all-zeroes page could be left over if a backend extends the
* relation but crashes before initializing the page. Reclaim such
* pages for use.
*
* We have to be careful here because we could be looking at a
* page that someone has just added to the relation and not yet
* been able to initialize (see RelationGetBufferForTuple). To
* protect against that, release the buffer lock, grab the
* relation extension lock momentarily, and re-lock the buffer. If
* the page is still uninitialized by then, it must be left over
* from a crashed backend, and we can initialize it.
*
* We don't really need the relation lock when this is a new or
* temp relation, but it's probably not worth the code space to
* check that, since this surely isn't a critical path.
*
* Note: the comparable code in vacuum.c need not worry because
* it's got exclusive lock on the whole relation.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockRelationForExtension(onerel, ExclusiveLock);
UnlockRelationForExtension(onerel, ExclusiveLock);
LockBufferForCleanup(buf);
if (PageIsNew(page))
{
ereport(WARNING,
(errmsg("relation \"%s\" page %u is uninitialized --- fixing",
relname, blkno)));
PageInit(page, BufferGetPageSize(buf), 0);
empty_pages++;
}
freespace = PageGetHeapFreeSpace(page);
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
if (PageIsEmpty(page))
{
empty_pages++;
freespace = PageGetHeapFreeSpace(page);
if (!PageIsAllVisible(page))
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
/*
* Prune all HOT-update chains in this page.
*
* We count tuples removed by the pruning step as removed by VACUUM.
*/
tups_vacuumed += heap_page_prune(onerel, buf, OldestXmin, false,
&vacrelstats->latestRemovedXid);
/*
* Now scan the page to collect vacuumable items and check for tuples
* requiring freezing.
*/
all_visible = true;
has_dead_tuples = false;
nfrozen = 0;
hastup = false;
prev_dead_count = vacrelstats->num_dead_tuples;
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused items require no processing, but we count 'em */
if (!ItemIdIsUsed(itemid))
{
nunused += 1;
continue;
}
/* Redirect items mustn't be touched */
if (ItemIdIsRedirected(itemid))
{
hastup = true; /* this page won't be truncatable */
continue;
}
ItemPointerSet(&(tuple.t_self), blkno, offnum);
/*
* DEAD item pointers are to be vacuumed normally; but we don't
* count them in tups_vacuumed, else we'd be double-counting (at
* least in the common case where heap_page_prune() just freed up
* a non-HOT tuple).
*/
if (ItemIdIsDead(itemid))
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
all_visible = false;
continue;
}
Assert(ItemIdIsNormal(itemid));
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tupgone = false;
switch (HeapTupleSatisfiesVacuum(tuple.t_data, OldestXmin, buf))
{
case HEAPTUPLE_DEAD:
/*
* Ordinarily, DEAD tuples would have been removed by
* heap_page_prune(), but it's possible that the tuple
* state changed since heap_page_prune() looked. In
* particular an INSERT_IN_PROGRESS tuple could have
* changed to DEAD if the inserter aborted. So this
* cannot be considered an error condition.
*
* If the tuple is HOT-updated then it must only be
* removed by a prune operation; so we keep it just as if
* it were RECENTLY_DEAD. Also, if it's a heap-only
* tuple, we choose to keep it, because it'll be a lot
* cheaper to get rid of it in the next pruning pass than
* to treat it like an indexed tuple.
*/
if (HeapTupleIsHotUpdated(&tuple) ||
HeapTupleIsHeapOnly(&tuple))
nkeep += 1;
else
tupgone = true; /* we can delete the tuple */
all_visible = false;
break;
case HEAPTUPLE_LIVE:
/* Tuple is good --- but let's do some validity checks */
if (onerel->rd_rel->relhasoids &&
!OidIsValid(HeapTupleGetOid(&tuple)))
elog(WARNING, "relation \"%s\" TID %u/%u: OID is invalid",
relname, blkno, offnum);
/*
* Is the tuple definitely visible to all transactions?
*
* NB: Like with per-tuple hint bits, we can't set the
* PD_ALL_VISIBLE flag if the inserter committed
* asynchronously. See SetHintBits for more info. Check
* that the HEAP_XMIN_COMMITTED hint bit is set because of
* that.
*/
if (all_visible)
{
TransactionId xmin;
if (!(tuple.t_data->t_infomask & HEAP_XMIN_COMMITTED))
{
all_visible = false;
break;
}
/*
* The inserter definitely committed. But is it old
* enough that everyone sees it as committed?
*/
xmin = HeapTupleHeaderGetXmin(tuple.t_data);
if (!TransactionIdPrecedes(xmin, OldestXmin))
{
all_visible = false;
break;
}
}
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must not remove it
* from relation.
*/
nkeep += 1;
all_visible = false;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (tupgone)
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
HeapTupleHeaderAdvanceLatestRemovedXid(tuple.t_data,
&vacrelstats->latestRemovedXid);
tups_vacuumed += 1;
has_dead_tuples = true;
}
else
{
num_tuples += 1;
hastup = true;
/*
* Each non-removable tuple must be checked to see if it needs
* freezing. Note we already have exclusive buffer lock.
*/
if (heap_freeze_tuple(tuple.t_data, FreezeLimit,
InvalidBuffer))
frozen[nfrozen++] = offnum;
}
} /* scan along page */
/*
* If we froze any tuples, mark the buffer dirty, and write a WAL
* record recording the changes. We must log the changes to be
* crash-safe against future truncation of CLOG.
*/
if (nfrozen > 0)
{
MarkBufferDirty(buf);
if (RelationNeedsWAL(onerel))
{
XLogRecPtr recptr;
recptr = log_heap_freeze(onerel, buf, FreezeLimit,
frozen, nfrozen);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
/*
* If there are no indexes then we can vacuum the page right now
* instead of doing a second scan.
*/
if (nindexes == 0 &&
vacrelstats->num_dead_tuples > 0)
{
/* Remove tuples from heap */
lazy_vacuum_page(onerel, blkno, buf, 0, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacuumed_pages++;
}
freespace = PageGetHeapFreeSpace(page);
/* Update the all-visible flag on the page */
if (!PageIsAllVisible(page) && all_visible)
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
/*
* It's possible for the value returned by GetOldestXmin() to move
* backwards, so it's not wrong for us to see tuples that appear to
* not be visible to everyone yet, while PD_ALL_VISIBLE is already
* set. The real safe xmin value never moves backwards, but
* GetOldestXmin() is conservative and sometimes returns a value
* that's unnecessarily small, so if we see that contradiction it just
* means that the tuples that we think are not visible to everyone yet
* actually are, and the PD_ALL_VISIBLE flag is correct.
*
* There should never be dead tuples on a page with PD_ALL_VISIBLE
* set, however.
*/
else if (PageIsAllVisible(page) && has_dead_tuples)
{
elog(WARNING, "page containing dead tuples is marked as all-visible in relation \"%s\" page %u",
relname, blkno);
PageClearAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
/*
* Normally, we would drop the lock on the heap page before
* updating the visibility map, but since this case shouldn't
* happen anyway, don't worry about that.
*/
visibilitymap_clear(onerel, blkno);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm && all_visible)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(buf);
/* Remember the location of the last page with nonremovable tuples */
if (hastup)
vacrelstats->nonempty_pages = blkno + 1;
/*
* If we remembered any tuples for deletion, then the page will be
* visited again by lazy_vacuum_heap, which will compute and record
* its post-compaction free space. If not, then we're done with this
* page, so remember its free space as-is. (This path will always be
* taken if there are no indexes.)
*/
if (vacrelstats->num_dead_tuples == prev_dead_count)
RecordPageWithFreeSpace(onerel, blkno, freespace);
}
/* save stats for use later */
vacrelstats->scanned_tuples = num_tuples;
vacrelstats->tuples_deleted = tups_vacuumed;
/* now we can compute the new value for pg_class.reltuples */
vacrelstats->new_rel_tuples = vac_estimate_reltuples(onerel, false,
nblocks,
vacrelstats->scanned_pages,
num_tuples);
/* If any tuples need to be deleted, perform final vacuum cycle */
/* XXX put a threshold on min number of tuples here? */
if (vacrelstats->num_dead_tuples > 0)
{
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
vacrelstats->num_index_scans++;
}
/* Release the pin on the visibility map page */
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
/* Do post-vacuum cleanup and statistics update for each index */
for (i = 0; i < nindexes; i++)
lazy_cleanup_index(Irel[i], indstats[i], vacrelstats);
/* If no indexes, make log report that lazy_vacuum_heap would've made */
if (vacuumed_pages)
ereport(elevel,
(errmsg("\"%s\": removed %.0f row versions in %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, vacuumed_pages)));
ereport(elevel,
(errmsg("\"%s\": found %.0f removable, %.0f nonremovable row versions in %u out of %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, num_tuples,
vacrelstats->scanned_pages, nblocks),
errdetail("%.0f dead row versions cannot be removed yet.\n"
"There were %.0f unused item pointers.\n"
"%u pages are entirely empty.\n"
"%s.",
nkeep,
nunused,
empty_pages,
pg_rusage_show(&ru0))));
}
/*
* 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_killitems - set LP_DEAD state for items an indexscan caller has
* told us were killed
*
* scan->so contains information about the current page and killed tuples
* thereon (generally, this should only be called if so->numKilled > 0).
*
* The caller must have pin on so->currPos.buf, but may or may not have
* read-lock, as indicated by haveLock. Note that we assume read-lock
* is sufficient for setting LP_DEAD status (which is only a hint).
*
* We match items by heap TID before assuming they are the right ones to
* delete. We cope with cases where items have moved right due to insertions.
* If an item has moved off the current page due to a split, we'll fail to
* find it and do nothing (this is not an error case --- we assume the item
* will eventually get marked in a future indexscan). Note that because we
* hold pin on the target page continuously from initially reading the items
* until applying this function, VACUUM cannot have deleted any items from
* the page, and so there is no need to search left from the recorded offset.
* (This observation also guarantees that the item is still the right one
* to delete, which might otherwise be questionable since heap TIDs can get
* recycled.)
*/
void
_bt_killitems(IndexScanDesc scan, bool haveLock)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Page page;
BTPageOpaque opaque;
OffsetNumber minoff;
OffsetNumber maxoff;
int i;
bool killedsomething = false;
Assert(BufferIsValid(so->currPos.buf));
if (!haveLock)
LockBuffer(so->currPos.buf, BT_READ);
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
for (i = 0; i < so->numKilled; i++)
{
int itemIndex = so->killedItems[i];
BTScanPosItem *kitem = &so->currPos.items[itemIndex];
OffsetNumber offnum = kitem->indexOffset;
Assert(itemIndex >= so->currPos.firstItem &&
itemIndex <= so->currPos.lastItem);
if (offnum < minoff)
continue; /* pure paranoia */
while (offnum <= maxoff)
{
ItemId iid = PageGetItemId(page, offnum);
IndexTuple ituple = (IndexTuple) PageGetItem(page, iid);
if (ItemPointerEquals(&ituple->t_tid, &kitem->heapTid))
{
/* found the item */
ItemIdMarkDead(iid);
killedsomething = true;
break; /* out of inner search loop */
}
offnum = OffsetNumberNext(offnum);
}
}
/*
* Since this can be redone later if needed, it's treated the same as a
* commit-hint-bit status update for heap tuples: we mark the buffer dirty
* but don't make a WAL log entry.
*
* Whenever we mark anything LP_DEAD, we also set the page's
* BTP_HAS_GARBAGE flag, which is likewise just a hint.
*/
if (killedsomething)
{
opaque->btpo_flags |= BTP_HAS_GARBAGE;
SetBufferCommitInfoNeedsSave(so->currPos.buf);
}
if (!haveLock)
LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);
/*
* Always reset the scan state, so we don't look for same items on other
* pages.
*/
so->numKilled = 0;
}
/*
* hashgettuple() -- Get the next tuple in the scan.
*/
Datum
hashgettuple(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanDirection dir = (ScanDirection) PG_GETARG_INT32(1);
HashScanOpaque so = (HashScanOpaque) scan->opaque;
Relation rel = scan->indexRelation;
Buffer buf;
Page page;
OffsetNumber offnum;
ItemPointer current;
bool res;
/* Hash indexes are always lossy since we store only the hash code */
scan->xs_recheck = true;
/*
* We hold pin but not lock on current buffer while outside the hash AM.
* Reacquire the read lock here.
*/
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_NOLOCK, HASH_READ);
/*
* If we've already initialized this scan, we can just advance it in the
* appropriate direction. If we haven't done so yet, we call a routine to
* get the first item in the scan.
*/
current = &(so->hashso_curpos);
if (ItemPointerIsValid(current))
{
/*
* An insertion into the current index page could have happened while
* we didn't have read lock on it. Re-find our position by looking
* for the TID we previously returned. (Because we hold share lock on
* the bucket, no deletions or splits could have occurred; therefore
* we can expect that the TID still exists in the current index page,
* at an offset >= where we were.)
*/
OffsetNumber maxoffnum;
buf = so->hashso_curbuf;
Assert(BufferIsValid(buf));
page = BufferGetPage(buf);
maxoffnum = PageGetMaxOffsetNumber(page);
for (offnum = ItemPointerGetOffsetNumber(current);
offnum <= maxoffnum;
offnum = OffsetNumberNext(offnum))
{
IndexTuple itup;
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
if (ItemPointerEquals(&(so->hashso_heappos), &(itup->t_tid)))
break;
}
if (offnum > maxoffnum)
elog(ERROR, "failed to re-find scan position within index \"%s\"",
RelationGetRelationName(rel));
ItemPointerSetOffsetNumber(current, offnum);
/*
* Check to see if we should kill the previously-fetched tuple.
*/
if (scan->kill_prior_tuple)
{
/*
* Yes, so mark it by setting the LP_DEAD state in the item flags.
*/
ItemIdMarkDead(PageGetItemId(page, offnum));
/*
* Since this can be redone later if needed, it's treated the same
* as a commit-hint-bit status update for heap tuples: we mark the
* buffer dirty but don't make a WAL log entry.
*/
SetBufferCommitInfoNeedsSave(buf);
}
/*
* Now continue the scan.
*/
res = _hash_next(scan, dir);
}
else
res = _hash_first(scan, dir);
/*
* Skip killed tuples if asked to.
*/
if (scan->ignore_killed_tuples)
{
while (res)
{
offnum = ItemPointerGetOffsetNumber(current);
page = BufferGetPage(so->hashso_curbuf);
if (!ItemIdIsDead(PageGetItemId(page, offnum)))
break;
res = _hash_next(scan, dir);
}
}
/* Release read lock on current buffer, but keep it pinned */
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_READ, HASH_NOLOCK);
/* Return current heap TID on success */
scan->xs_ctup.t_self = so->hashso_heappos;
PG_RETURN_BOOL(res);
}
/*
* 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;
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);
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).
*/
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;
}
}
/* If the page is in use, update lastUsedPage */
if (!_bt_page_recyclable(page) && vstate->lastUsedPage < blkno)
vstate->lastUsedPage = blkno;
/* 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);
/*
* 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)
{
BlockNumber lastBlockVacuumed = BufferGetBlockNumber(buf);
_bt_delitems_vacuum(rel, buf, deletable, ndeletable,
vstate->lastBlockVacuumed);
/*
* Keep track of the block number of the lastBlockVacuumed, so we
* can scan those blocks as well during WAL replay. This then
* provides concurrency protection and allows btrees to be used
* while in recovery.
*/
if (lastBlockVacuumed > vstate->lastBlockVacuumed)
vstate->lastBlockVacuumed = lastBlockVacuumed;
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;
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);
/* 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;
}
}
/*
* hashgettuple() -- Get the next tuple in the scan.
*/
Datum
hashgettuple(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanDirection dir = (ScanDirection) PG_GETARG_INT32(1);
HashScanOpaque so = (HashScanOpaque) scan->opaque;
Relation rel = scan->indexRelation;
Page page;
OffsetNumber offnum;
bool res;
/*
* We hold pin but not lock on current buffer while outside the hash AM.
* Reacquire the read lock here.
*/
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_NOLOCK, HASH_READ);
/*
* If we've already initialized this scan, we can just advance it in the
* appropriate direction. If we haven't done so yet, we call a routine to
* get the first item in the scan.
*/
if (ItemPointerIsValid(&(scan->currentItemData)))
{
/*
* Check to see if we should kill the previously-fetched tuple.
*/
if (scan->kill_prior_tuple)
{
/*
* Yes, so mark it by setting the LP_DELETE bit in the item flags.
*/
offnum = ItemPointerGetOffsetNumber(&(scan->currentItemData));
page = BufferGetPage(so->hashso_curbuf);
PageGetItemId(page, offnum)->lp_flags |= LP_DELETE;
/*
* Since this can be redone later if needed, it's treated the same
* as a commit-hint-bit status update for heap tuples: we mark the
* buffer dirty but don't make a WAL log entry.
*/
SetBufferCommitInfoNeedsSave(so->hashso_curbuf);
}
/*
* Now continue the scan.
*/
res = _hash_next(scan, dir);
}
else
res = _hash_first(scan, dir);
/*
* Skip killed tuples if asked to.
*/
if (scan->ignore_killed_tuples)
{
while (res)
{
offnum = ItemPointerGetOffsetNumber(&(scan->currentItemData));
page = BufferGetPage(so->hashso_curbuf);
if (!ItemIdDeleted(PageGetItemId(page, offnum)))
break;
res = _hash_next(scan, dir);
}
}
/* Release read lock on current buffer, but keep it pinned */
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_READ, HASH_NOLOCK);
PG_RETURN_BOOL(res);
}
/*
* pgstattuple_real
*
* The real work occurs here
*/
static Datum
pgstattuple_real(Relation rel)
{
HeapScanDesc scan;
HeapTuple tuple;
BlockNumber nblocks;
BlockNumber block = 0; /* next block to count free space in */
BlockNumber tupblock;
Buffer buffer;
uint64 table_len;
uint64 tuple_len = 0;
uint64 dead_tuple_len = 0;
uint64 tuple_count = 0;
uint64 dead_tuple_count = 0;
double tuple_percent;
double dead_tuple_percent;
uint64 free_space = 0; /* free/reusable space in bytes */
double free_percent; /* free/reusable space in % */
TupleDesc tupdesc;
TupleTableSlot *slot;
AttInMetadata *attinmeta;
char **values;
int i;
Datum result;
/*
* Build a tuple description for a pgstattupe_type tuple
*/
tupdesc = RelationNameGetTupleDesc(DUMMY_TUPLE);
/* allocate a slot for a tuple with this tupdesc */
slot = TupleDescGetSlot(tupdesc);
/*
* Generate attribute metadata needed later to produce tuples from raw
* C strings
*/
attinmeta = TupleDescGetAttInMetadata(tupdesc);
nblocks = RelationGetNumberOfBlocks(rel);
scan = heap_beginscan(rel, SnapshotAny, 0, NULL);
/* scan the relation */
while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
uint16 sv_infomask;
sv_infomask = tuple->t_data->t_infomask;
if (HeapTupleSatisfiesNow(tuple->t_data))
{
tuple_len += tuple->t_len;
tuple_count++;
}
else
{
dead_tuple_len += tuple->t_len;
dead_tuple_count++;
}
if (sv_infomask != tuple->t_data->t_infomask)
SetBufferCommitInfoNeedsSave(scan->rs_cbuf);
/*
* To avoid physically reading the table twice, try to do the
* free-space scan in parallel with the heap scan. However,
* heap_getnext may find no tuples on a given page, so we cannot
* simply examine the pages returned by the heap scan.
*/
tupblock = BlockIdGetBlockNumber(&tuple->t_self.ip_blkid);
while (block <= tupblock)
{
buffer = ReadBuffer(rel, block);
free_space += PageGetFreeSpace((Page) BufferGetPage(buffer));
ReleaseBuffer(buffer);
block++;
}
}
heap_endscan(scan);
while (block < nblocks)
{
buffer = ReadBuffer(rel, block);
free_space += PageGetFreeSpace((Page) BufferGetPage(buffer));
ReleaseBuffer(buffer);
block++;
}
heap_close(rel, AccessShareLock);
table_len = (uint64) nblocks *BLCKSZ;
if (nblocks == 0)
{
tuple_percent = 0.0;
dead_tuple_percent = 0.0;
free_percent = 0.0;
}
else
{
tuple_percent = (double) tuple_len *100.0 / table_len;
dead_tuple_percent = (double) dead_tuple_len *100.0 / table_len;
free_percent = (double) free_space *100.0 / table_len;
}
/*
* Prepare a values array for storage in our slot. This should be an
* array of C strings which will be processed later by the appropriate
* "in" functions.
*/
values = (char **) palloc(NCOLUMNS * sizeof(char *));
for (i = 0; i < NCOLUMNS; i++)
values[i] = (char *) palloc(NCHARS * sizeof(char));
i = 0;
snprintf(values[i++], NCHARS, INT64_FORMAT, table_len);
snprintf(values[i++], NCHARS, INT64_FORMAT, tuple_count);
snprintf(values[i++], NCHARS, INT64_FORMAT, tuple_len);
snprintf(values[i++], NCHARS, "%.2f", tuple_percent);
snprintf(values[i++], NCHARS, INT64_FORMAT, dead_tuple_count);
snprintf(values[i++], NCHARS, INT64_FORMAT, dead_tuple_len);
snprintf(values[i++], NCHARS, "%.2f", dead_tuple_percent);
snprintf(values[i++], NCHARS, INT64_FORMAT, free_space);
snprintf(values[i++], NCHARS, "%.2f", free_percent);
/* build a tuple */
tuple = BuildTupleFromCStrings(attinmeta, values);
/* make the tuple into a datum */
result = TupleGetDatum(slot, tuple);
/* Clean up */
for (i = 0; i < NCOLUMNS; i++)
pfree(values[i]);
pfree(values);
return (result);
}
/*
* Prune and repair fragmentation in the specified page.
*
* Caller must have pin and buffer cleanup lock on the page.
*
* OldestXmin is the cutoff XID used to distinguish whether tuples are DEAD
* or RECENTLY_DEAD (see HeapTupleSatisfiesVacuum).
*
* If report_stats is true then we send the number of reclaimed heap-only
* tuples to pgstats. (This must be FALSE during vacuum, since vacuum will
* send its own new total to pgstats, and we don't want this delta applied
* on top of that.)
*
* Returns the number of tuples deleted from the page and sets
* latestRemovedXid.
*/
int
heap_page_prune(Relation relation, Buffer buffer, TransactionId OldestXmin,
bool report_stats, TransactionId *latestRemovedXid)
{
int ndeleted = 0;
Page page = BufferGetPage(buffer);
OffsetNumber offnum,
maxoff;
PruneState prstate;
/*
* Our strategy is to scan the page and make lists of items to change,
* then apply the changes within a critical section. This keeps as much
* logic as possible out of the critical section, and also ensures that
* WAL replay will work the same as the normal case.
*
* First, initialize the new pd_prune_xid value to zero (indicating no
* prunable tuples). If we find any tuples which may soon become
* prunable, we will save the lowest relevant XID in new_prune_xid. Also
* initialize the rest of our working state.
*/
prstate.new_prune_xid = InvalidTransactionId;
prstate.latestRemovedXid = *latestRemovedXid;
prstate.nredirected = prstate.ndead = prstate.nunused = 0;
memset(prstate.marked, 0, sizeof(prstate.marked));
/* Scan the page */
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
/* Ignore items already processed as part of an earlier chain */
if (prstate.marked[offnum])
continue;
/* Nothing to do if slot is empty or already dead */
itemid = PageGetItemId(page, offnum);
if (!ItemIdIsUsed(itemid) || ItemIdIsDead(itemid))
continue;
/* Process this item or chain of items */
ndeleted += heap_prune_chain(relation, buffer, offnum,
OldestXmin,
&prstate);
}
/* Any error while applying the changes is critical */
START_CRIT_SECTION();
/* Have we found any prunable items? */
if (prstate.nredirected > 0 || prstate.ndead > 0 || prstate.nunused > 0)
{
/*
* Apply the planned item changes, then repair page fragmentation, and
* update the page's hint bit about whether it has free line pointers.
*/
heap_page_prune_execute(buffer,
prstate.redirected, prstate.nredirected,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused);
/*
* Update the page's pd_prune_xid field to either zero, or the lowest
* XID of any soon-prunable tuple.
*/
((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
/*
* Also clear the "page is full" flag, since there's no point in
* repeating the prune/defrag process until something else happens to
* the page.
*/
PageClearFull(page);
MarkBufferDirty(buffer);
/*
* Emit a WAL HEAP_CLEAN record showing what we did
*/
if (RelationNeedsWAL(relation))
{
XLogRecPtr recptr;
recptr = log_heap_clean(relation, buffer,
prstate.redirected, prstate.nredirected,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused,
prstate.latestRemovedXid);
PageSetLSN(BufferGetPage(buffer), recptr);
PageSetTLI(BufferGetPage(buffer), ThisTimeLineID);
}
}
else
{
/*
* If we didn't prune anything, but have found a new value for the
* pd_prune_xid field, update it and mark the buffer dirty. This is
* treated as a non-WAL-logged hint.
*
* Also clear the "page is full" flag if it is set, since there's no
* point in repeating the prune/defrag process until something else
* happens to the page.
*/
if (((PageHeader) page)->pd_prune_xid != prstate.new_prune_xid ||
PageIsFull(page))
{
((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
PageClearFull(page);
SetBufferCommitInfoNeedsSave(buffer);
}
}
END_CRIT_SECTION();
/*
* If requested, report the number of tuples reclaimed to pgstats. This is
* ndeleted minus ndead, because we don't want to count a now-DEAD root
* item as a deletion for this purpose.
*/
if (report_stats && ndeleted > prstate.ndead)
pgstat_update_heap_dead_tuples(relation, ndeleted - prstate.ndead);
*latestRemovedXid = prstate.latestRemovedXid;
/*
* XXX Should we update the FSM information of this page ?
*
* There are two schools of thought here. We may not want to update FSM
* information so that the page is not used for unrelated UPDATEs/INSERTs
* and any free space in this page will remain available for further
* UPDATEs in *this* page, thus improving chances for doing HOT updates.
*
* But for a large table and where a page does not receive further UPDATEs
* for a long time, we might waste this space by not updating the FSM
* information. The relation may get extended and fragmented further.
*
* One possibility is to leave "fillfactor" worth of space in this page
* and update FSM with the remaining space.
*
* In any case, the current FSM implementation doesn't accept
* one-page-at-a-time updates, so this is all academic for now.
*/
return ndeleted;
}
/* ----------------
* index_getnext - get the next heap tuple from a scan
*
* The result is the next heap tuple satisfying the scan keys and the
* snapshot, or NULL if no more matching tuples exist. On success,
* the buffer containing the heap tuple is pinned (the pin will be dropped
* at the next index_getnext or index_endscan). The index TID corresponding
* to the heap tuple can be obtained if needed from scan->currentItemData.
* ----------------
*/
HeapTuple
index_getnext(IndexScanDesc scan, ScanDirection direction)
{
HeapTuple heapTuple = &scan->xs_ctup;
SCAN_CHECKS;
/* Release any previously held pin */
if (BufferIsValid(scan->xs_cbuf))
{
ReleaseBuffer(scan->xs_cbuf);
scan->xs_cbuf = InvalidBuffer;
}
/*
* If we already got a tuple and it must be unique, there's no need to
* make the index AM look through any additional tuples. (This can
* save a useful amount of work in scenarios where there are many dead
* tuples due to heavy update activity.)
*
* To do this we must keep track of the logical scan position
* (before/on/after tuple). Also, we have to be sure to release scan
* resources before returning NULL; if we fail to do so then a
* multi-index scan can easily run the system out of free buffers. We
* can release index-level resources fairly cheaply by calling
* index_rescan. This means there are two persistent states as far as
* the index AM is concerned: on-tuple and rescanned. If we are
* actually asked to re-fetch the single tuple, we have to go through
* a fresh indexscan startup, which penalizes that (infrequent) case.
*/
if (scan->keys_are_unique && scan->got_tuple)
{
int new_tuple_pos = scan->unique_tuple_pos;
if (ScanDirectionIsForward(direction))
{
if (new_tuple_pos <= 0)
new_tuple_pos++;
}
else
{
if (new_tuple_pos >= 0)
new_tuple_pos--;
}
if (new_tuple_pos == 0)
{
/*
* We are moving onto the unique tuple from having been off
* it. We just fall through and let the index AM do the work.
* Note we should get the right answer regardless of scan
* direction.
*/
scan->unique_tuple_pos = 0; /* need to update position */
}
else
{
/*
* Moving off the tuple; must do amrescan to release
* index-level pins before we return NULL. Since index_rescan
* will reset my state, must save and restore...
*/
int unique_tuple_mark = scan->unique_tuple_mark;
index_rescan(scan, NULL /* no change to key */ );
scan->keys_are_unique = true;
scan->got_tuple = true;
scan->unique_tuple_pos = new_tuple_pos;
scan->unique_tuple_mark = unique_tuple_mark;
return NULL;
}
}
/* just make sure this is false... */
scan->kill_prior_tuple = false;
for (;;)
{
bool found;
uint16 sv_infomask;
pgstat_count_index_scan(&scan->xs_pgstat_info);
/*
* The AM's gettuple proc finds the next tuple matching the scan
* keys. index_beginscan already set up fn_getnext.
*/
found = DatumGetBool(FunctionCall2(&scan->fn_getnext,
PointerGetDatum(scan),
Int32GetDatum(direction)));
/* Reset kill flag immediately for safety */
scan->kill_prior_tuple = false;
if (!found)
return NULL; /* failure exit */
/*
* Fetch the heap tuple and see if it matches the snapshot.
*/
if (heap_fetch(scan->heapRelation, scan->xs_snapshot,
heapTuple, &scan->xs_cbuf, true,
&scan->xs_pgstat_info))
break;
/* Skip if no tuple at this location */
if (heapTuple->t_data == NULL)
continue; /* should we raise an error instead? */
/*
* If we can't see it, maybe no one else can either. Check to see
* if the tuple is dead to all transactions. If so, signal the
* index AM to not return it on future indexscans.
*
* We told heap_fetch to keep a pin on the buffer, so we can
* re-access the tuple here. But we must re-lock the buffer
* first. Also, it's just barely possible for an update of hint
* bits to occur here.
*/
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
sv_infomask = heapTuple->t_data->t_infomask;
if (HeapTupleSatisfiesVacuum(heapTuple->t_data, RecentGlobalXmin) ==
HEAPTUPLE_DEAD)
scan->kill_prior_tuple = true;
if (sv_infomask != heapTuple->t_data->t_infomask)
SetBufferCommitInfoNeedsSave(scan->xs_cbuf);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(scan->xs_cbuf);
scan->xs_cbuf = InvalidBuffer;
}
/* Success exit */
scan->got_tuple = true;
/*
* If we just fetched a known-unique tuple, then subsequent calls will
* go through the short-circuit code above. unique_tuple_pos has been
* initialized to 0, which is the correct state ("on row").
*/
pgstat_count_index_getnext(&scan->xs_pgstat_info);
return heapTuple;
}
/*
* IndexBuildHeapScan - scan the heap relation to find tuples to be indexed
*
* This is called back from an access-method-specific index build procedure
* after the AM has done whatever setup it needs. The parent heap relation
* is scanned to find tuples that should be entered into the index. Each
* such tuple is passed to the AM's callback routine, which does the right
* things to add it to the new index. After we return, the AM's index
* build procedure does whatever cleanup is needed; in particular, it should
* close the heap and index relations.
*
* The total count of heap tuples is returned. This is for updating pg_class
* statistics. (It's annoying not to be able to do that here, but we can't
* do it until after the relation is closed.) Note that the index AM itself
* must keep track of the number of index tuples; we don't do so here because
* the AM might reject some of the tuples for its own reasons, such as being
* unable to store NULLs.
*/
double
IndexBuildHeapScan(Relation heapRelation,
Relation indexRelation,
IndexInfo *indexInfo,
IndexBuildCallback callback,
void *callback_state)
{
HeapScanDesc scan;
HeapTuple heapTuple;
TupleDesc heapDescriptor;
Datum attdata[INDEX_MAX_KEYS];
char nulls[INDEX_MAX_KEYS];
double reltuples;
List *predicate;
TupleTable tupleTable;
TupleTableSlot *slot;
EState *estate;
ExprContext *econtext;
Snapshot snapshot;
TransactionId OldestXmin;
/*
* sanity checks
*/
Assert(OidIsValid(indexRelation->rd_rel->relam));
heapDescriptor = RelationGetDescr(heapRelation);
/*
* Need an EState for evaluation of index expressions and
* partial-index predicates.
*/
estate = CreateExecutorState();
econtext = GetPerTupleExprContext(estate);
/*
* If this is a predicate (partial) index, we will need to evaluate
* the predicate using ExecQual, which requires the current tuple to
* be in a slot of a TupleTable. Likewise if there are any
* expressions.
*/
if (indexInfo->ii_Predicate != NIL || indexInfo->ii_Expressions != NIL)
{
tupleTable = ExecCreateTupleTable(1);
slot = ExecAllocTableSlot(tupleTable);
ExecSetSlotDescriptor(slot, heapDescriptor, false);
/* Arrange for econtext's scan tuple to be the tuple under test */
econtext->ecxt_scantuple = slot;
/* Set up execution state for predicate. */
predicate = (List *)
ExecPrepareExpr((Expr *) indexInfo->ii_Predicate,
estate);
}
else
{
tupleTable = NULL;
slot = NULL;
predicate = NIL;
}
/*
* Ok, begin our scan of the base relation. We use SnapshotAny
* because we must retrieve all tuples and do our own time qual
* checks.
*/
if (IsBootstrapProcessingMode())
{
snapshot = SnapshotNow;
OldestXmin = InvalidTransactionId;
}
else
{
snapshot = SnapshotAny;
OldestXmin = GetOldestXmin(heapRelation->rd_rel->relisshared);
}
scan = heap_beginscan(heapRelation, /* relation */
snapshot, /* seeself */
0, /* number of keys */
(ScanKey) NULL); /* scan key */
reltuples = 0;
/*
* Scan all tuples in the base relation.
*/
while ((heapTuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
bool tupleIsAlive;
CHECK_FOR_INTERRUPTS();
if (snapshot == SnapshotAny)
{
/* do our own time qual check */
bool indexIt;
uint16 sv_infomask;
/*
* HeapTupleSatisfiesVacuum may update tuple's hint status
* bits. We could possibly get away with not locking the
* buffer here, since caller should hold ShareLock on the
* relation, but let's be conservative about it.
*/
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
sv_infomask = heapTuple->t_data->t_infomask;
switch (HeapTupleSatisfiesVacuum(heapTuple->t_data, OldestXmin))
{
case HEAPTUPLE_DEAD:
indexIt = false;
tupleIsAlive = false;
break;
case HEAPTUPLE_LIVE:
indexIt = true;
tupleIsAlive = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must index it
* anyway to keep VACUUM from complaining.
*/
indexIt = true;
tupleIsAlive = false;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* Since caller should hold ShareLock or better, we
* should not see any tuples inserted by open
* transactions --- unless it's our own transaction.
* (Consider INSERT followed by CREATE INDEX within a
* transaction.) An exception occurs when reindexing
* a system catalog, because we often release lock on
* system catalogs before committing.
*/
if (!TransactionIdIsCurrentTransactionId(
HeapTupleHeaderGetXmin(heapTuple->t_data))
&& !IsSystemRelation(heapRelation))
elog(ERROR, "concurrent insert in progress");
indexIt = true;
tupleIsAlive = true;
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* Since caller should hold ShareLock or better, we
* should not see any tuples deleted by open
* transactions --- unless it's our own transaction.
* (Consider DELETE followed by CREATE INDEX within a
* transaction.) An exception occurs when reindexing
* a system catalog, because we often release lock on
* system catalogs before committing.
*/
if (!TransactionIdIsCurrentTransactionId(
HeapTupleHeaderGetXmax(heapTuple->t_data))
&& !IsSystemRelation(heapRelation))
elog(ERROR, "concurrent delete in progress");
indexIt = true;
tupleIsAlive = false;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
indexIt = tupleIsAlive = false; /* keep compiler quiet */
break;
}
/* check for hint-bit update by HeapTupleSatisfiesVacuum */
if (sv_infomask != heapTuple->t_data->t_infomask)
SetBufferCommitInfoNeedsSave(scan->rs_cbuf);
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
if (!indexIt)
continue;
}
else
{
/* heap_getnext did the time qual check */
tupleIsAlive = true;
}
reltuples += 1;
MemoryContextReset(econtext->ecxt_per_tuple_memory);
/* Set up for predicate or expression evaluation */
if (slot)
ExecStoreTuple(heapTuple, slot, InvalidBuffer, false);
/*
* In a partial index, discard tuples that don't satisfy the
* predicate. We can also discard recently-dead tuples, since
* VACUUM doesn't complain about tuple count mismatch for partial
* indexes.
*/
if (predicate != NIL)
{
if (!tupleIsAlive)
continue;
if (!ExecQual(predicate, econtext, false))
continue;
}
/*
* For the current heap tuple, extract all the attributes we use
* in this index, and note which are null. This also performs
* evaluation of any expressions needed.
*/
FormIndexDatum(indexInfo,
heapTuple,
heapDescriptor,
estate,
attdata,
nulls);
/*
* You'd think we should go ahead and build the index tuple here,
* but some index AMs want to do further processing on the data
* first. So pass the attdata and nulls arrays, instead.
*/
/* Call the AM's callback routine to process the tuple */
callback(indexRelation, heapTuple, attdata, nulls, tupleIsAlive,
callback_state);
}
heap_endscan(scan);
if (tupleTable)
ExecDropTupleTable(tupleTable, true);
FreeExecutorState(estate);
/* These may have been pointing to the now-gone estate */
indexInfo->ii_ExpressionsState = NIL;
indexInfo->ii_PredicateState = NIL;
return reltuples;
}