/*
* This function takes an already open relation and scans its pages,
* skipping those that have the corresponding visibility map bit set.
* For pages we skip, we find the free space from the free space map
* and approximate tuple_len on that basis. For the others, we count
* the exact number of dead tuples etc.
*
* This scan is loosely based on vacuumlazy.c:lazy_scan_heap(), but
* we do not try to avoid skipping single pages.
*/
static void
statapprox_heap(Relation rel, output_type *stat)
{
BlockNumber scanned,
nblocks,
blkno;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy;
TransactionId OldestXmin;
uint64 misc_count = 0;
OldestXmin = GetOldestXmin(rel, PROCARRAY_FLAGS_VACUUM);
bstrategy = GetAccessStrategy(BAS_BULKREAD);
nblocks = RelationGetNumberOfBlocks(rel);
scanned = 0;
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
Size freespace;
CHECK_FOR_INTERRUPTS();
/*
* If the page has only visible tuples, then we can find out the free
* space from the FSM and move on.
*/
if (VM_ALL_VISIBLE(rel, blkno, &vmbuffer))
{
freespace = GetRecordedFreeSpace(rel, blkno);
stat->tuple_len += BLCKSZ - freespace;
stat->free_space += freespace;
continue;
}
buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno,
RBM_NORMAL, bstrategy);
LockBuffer(buf, BUFFER_LOCK_SHARE);
page = BufferGetPage(buf);
/*
* It's not safe to call PageGetHeapFreeSpace() on new pages, so we
* treat them as being free space for our purposes.
*/
if (!PageIsNew(page))
stat->free_space += PageGetHeapFreeSpace(page);
else
stat->free_space += BLCKSZ - SizeOfPageHeaderData;
if (PageIsNew(page) || PageIsEmpty(page))
{
UnlockReleaseBuffer(buf);
continue;
}
scanned++;
/*
* Look at each tuple on the page and decide whether it's live or
* dead, then count it and its size. Unlike lazy_scan_heap, we can
* afford to ignore problems and special cases.
*/
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
HeapTupleData tuple;
itemid = PageGetItemId(page, offnum);
if (!ItemIdIsUsed(itemid) || ItemIdIsRedirected(itemid) ||
ItemIdIsDead(itemid))
{
continue;
}
Assert(ItemIdIsNormal(itemid));
ItemPointerSet(&(tuple.t_self), blkno, offnum);
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tuple.t_tableOid = RelationGetRelid(rel);
/*
* We count live and dead tuples, but we also need to add up
* others in order to feed vac_estimate_reltuples.
*/
switch (HeapTupleSatisfiesVacuum(&tuple, OldestXmin, buf))
{
case HEAPTUPLE_RECENTLY_DEAD:
misc_count++;
/* Fall through */
case HEAPTUPLE_DEAD:
stat->dead_tuple_len += tuple.t_len;
stat->dead_tuple_count++;
break;
case HEAPTUPLE_LIVE:
stat->tuple_len += tuple.t_len;
stat->tuple_count++;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
case HEAPTUPLE_DELETE_IN_PROGRESS:
misc_count++;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
}
UnlockReleaseBuffer(buf);
}
stat->table_len = (uint64) nblocks *BLCKSZ;
stat->tuple_count = vac_estimate_reltuples(rel, false, nblocks, scanned,
stat->tuple_count + misc_count);
/*
* Calculate percentages if the relation has one or more pages.
*/
if (nblocks != 0)
{
stat->scanned_percent = 100 * scanned / nblocks;
stat->tuple_percent = 100.0 * stat->tuple_len / stat->table_len;
stat->dead_tuple_percent = 100.0 * stat->dead_tuple_len / stat->table_len;
stat->free_percent = 100.0 * stat->free_space / stat->table_len;
}
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
}
/*
* Returns a list of items whose visibility map information does not match
* the status of the tuples on the page.
*
* If all_visible is passed as true, this will include all items which are
* on pages marked as all-visible in the visibility map but which do not
* seem to in fact be all-visible.
*
* If all_frozen is passed as true, this will include all items which are
* on pages marked as all-frozen but which do not seem to in fact be frozen.
*/
static corrupt_items *
collect_corrupt_items(Oid relid, bool all_visible, bool all_frozen)
{
Relation rel;
BlockNumber nblocks;
corrupt_items *items;
BlockNumber blkno;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
TransactionId OldestXmin = InvalidTransactionId;
if (all_visible)
{
/* Don't pass rel; that will fail in recovery. */
OldestXmin = GetOldestXmin(NULL, true);
}
rel = relation_open(relid, AccessShareLock);
if (rel->rd_rel->relkind != RELKIND_RELATION &&
rel->rd_rel->relkind != RELKIND_MATVIEW &&
rel->rd_rel->relkind != RELKIND_TOASTVALUE)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is not a table, materialized view, or TOAST table",
RelationGetRelationName(rel))));
nblocks = RelationGetNumberOfBlocks(rel);
/*
* Guess an initial array size. We don't expect many corrupted tuples, so
* start with a small array. This function uses the "next" field to track
* the next offset where we can store an item (which is the same thing as
* the number of items found so far) and the "count" field to track the
* number of entries allocated. We'll repurpose these fields before
* returning.
*/
items = palloc0(sizeof(corrupt_items));
items->next = 0;
items->count = 64;
items->tids = palloc(items->count * sizeof(ItemPointerData));
/* Loop over every block in the relation. */
for (blkno = 0; blkno < nblocks; ++blkno)
{
bool check_frozen = false;
bool check_visible = false;
Buffer buffer;
Page page;
OffsetNumber offnum,
maxoff;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
/* Use the visibility map to decide whether to check this page. */
if (all_frozen && VM_ALL_FROZEN(rel, blkno, &vmbuffer))
check_frozen = true;
if (all_visible && VM_ALL_VISIBLE(rel, blkno, &vmbuffer))
check_visible = true;
if (!check_visible && !check_frozen)
continue;
/* Read and lock the page. */
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
bstrategy);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
maxoff = PageGetMaxOffsetNumber(page);
/*
* The visibility map bits might have changed while we were acquiring
* the page lock. Recheck to avoid returning spurious results.
*/
if (check_frozen && !VM_ALL_FROZEN(rel, blkno, &vmbuffer))
check_frozen = false;
if (check_visible && !VM_ALL_VISIBLE(rel, blkno, &vmbuffer))
check_visible = false;
if (!check_visible && !check_frozen)
{
UnlockReleaseBuffer(buffer);
continue;
}
/* Iterate over each tuple on the page. */
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
HeapTupleData tuple;
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused or redirect line pointers are of no interest. */
if (!ItemIdIsUsed(itemid) || ItemIdIsRedirected(itemid))
continue;
/* Dead line pointers are neither all-visible nor frozen. */
if (ItemIdIsDead(itemid))
{
ItemPointerSet(&(tuple.t_self), blkno, offnum);
record_corrupt_item(items, &tuple.t_self);
continue;
}
/* Initialize a HeapTupleData structure for checks below. */
ItemPointerSet(&(tuple.t_self), blkno, offnum);
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tuple.t_tableOid = relid;
/*
* If we're checking whether the page is all-visible, we expect
* the tuple to be all-visible.
*/
if (check_visible &&
!tuple_all_visible(&tuple, OldestXmin, buffer))
{
TransactionId RecomputedOldestXmin;
/*
* Time has passed since we computed OldestXmin, so it's
* possible that this tuple is all-visible in reality even
* though it doesn't appear so based on our
* previously-computed value. Let's compute a new value so we
* can be certain whether there is a problem.
*
* From a concurrency point of view, it sort of sucks to
* retake ProcArrayLock here while we're holding the buffer
* exclusively locked, but it should be safe against
* deadlocks, because surely GetOldestXmin() should never take
* a buffer lock. And this shouldn't happen often, so it's
* worth being careful so as to avoid false positives.
*/
RecomputedOldestXmin = GetOldestXmin(NULL, true);
if (!TransactionIdPrecedes(OldestXmin, RecomputedOldestXmin))
record_corrupt_item(items, &tuple.t_self);
else
{
OldestXmin = RecomputedOldestXmin;
if (!tuple_all_visible(&tuple, OldestXmin, buffer))
record_corrupt_item(items, &tuple.t_self);
}
}
/*
* If we're checking whether the page is all-frozen, we expect the
* tuple to be in a state where it will never need freezing.
*/
if (check_frozen)
{
if (heap_tuple_needs_eventual_freeze(tuple.t_data))
record_corrupt_item(items, &tuple.t_self);
}
}
UnlockReleaseBuffer(buffer);
}
/* Clean up. */
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
relation_close(rel, AccessShareLock);
/*
* Before returning, repurpose the fields to match caller's expectations.
* next is now the next item that should be read (rather than written) and
* count is now the number of items we wrote (rather than the number we
* allocated).
*/
items->count = items->next;
items->next = 0;
return items;
}
/* ----------------------------------------------------------------
* BitmapHeapNext
*
* Retrieve next tuple from the BitmapHeapScan node's currentRelation
* ----------------------------------------------------------------
*/
static TupleTableSlot *
BitmapHeapNext(BitmapHeapScanState *node)
{
ExprContext *econtext;
HeapScanDesc scan;
TIDBitmap *tbm;
TBMIterator *tbmiterator = NULL;
TBMSharedIterator *shared_tbmiterator = NULL;
TBMIterateResult *tbmres;
OffsetNumber targoffset;
TupleTableSlot *slot;
ParallelBitmapHeapState *pstate = node->pstate;
dsa_area *dsa = node->ss.ps.state->es_query_dsa;
/*
* extract necessary information from index scan node
*/
econtext = node->ss.ps.ps_ExprContext;
slot = node->ss.ss_ScanTupleSlot;
scan = node->ss.ss_currentScanDesc;
tbm = node->tbm;
if (pstate == NULL)
tbmiterator = node->tbmiterator;
else
shared_tbmiterator = node->shared_tbmiterator;
tbmres = node->tbmres;
/*
* If we haven't yet performed the underlying index scan, do it, and begin
* the iteration over the bitmap.
*
* For prefetching, we use *two* iterators, one for the pages we are
* actually scanning and another that runs ahead of the first for
* prefetching. node->prefetch_pages tracks exactly how many pages ahead
* the prefetch iterator is. Also, node->prefetch_target tracks the
* desired prefetch distance, which starts small and increases up to the
* node->prefetch_maximum. This is to avoid doing a lot of prefetching in
* a scan that stops after a few tuples because of a LIMIT.
*/
if (!node->initialized)
{
if (!pstate)
{
tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
if (!tbm || !IsA(tbm, TIDBitmap))
elog(ERROR, "unrecognized result from subplan");
node->tbm = tbm;
node->tbmiterator = tbmiterator = tbm_begin_iterate(tbm);
node->tbmres = tbmres = NULL;
#ifdef USE_PREFETCH
if (node->prefetch_maximum > 0)
{
node->prefetch_iterator = tbm_begin_iterate(tbm);
node->prefetch_pages = 0;
node->prefetch_target = -1;
}
#endif /* USE_PREFETCH */
}
else
{
/*
* The leader will immediately come out of the function, but
* others will be blocked until leader populates the TBM and wakes
* them up.
*/
if (BitmapShouldInitializeSharedState(pstate))
{
tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
if (!tbm || !IsA(tbm, TIDBitmap))
elog(ERROR, "unrecognized result from subplan");
node->tbm = tbm;
/*
* Prepare to iterate over the TBM. This will return the
* dsa_pointer of the iterator state which will be used by
* multiple processes to iterate jointly.
*/
pstate->tbmiterator = tbm_prepare_shared_iterate(tbm);
#ifdef USE_PREFETCH
if (node->prefetch_maximum > 0)
{
pstate->prefetch_iterator =
tbm_prepare_shared_iterate(tbm);
/*
* We don't need the mutex here as we haven't yet woke up
* others.
*/
pstate->prefetch_pages = 0;
pstate->prefetch_target = -1;
}
#endif
/* We have initialized the shared state so wake up others. */
BitmapDoneInitializingSharedState(pstate);
}
/* Allocate a private iterator and attach the shared state to it */
node->shared_tbmiterator = shared_tbmiterator =
tbm_attach_shared_iterate(dsa, pstate->tbmiterator);
node->tbmres = tbmres = NULL;
#ifdef USE_PREFETCH
if (node->prefetch_maximum > 0)
{
node->shared_prefetch_iterator =
tbm_attach_shared_iterate(dsa, pstate->prefetch_iterator);
}
#endif /* USE_PREFETCH */
}
node->initialized = true;
}
for (;;)
{
Page dp;
ItemId lp;
CHECK_FOR_INTERRUPTS();
/*
* Get next page of results if needed
*/
if (tbmres == NULL)
{
if (!pstate)
node->tbmres = tbmres = tbm_iterate(tbmiterator);
else
node->tbmres = tbmres = tbm_shared_iterate(shared_tbmiterator);
if (tbmres == NULL)
{
/* no more entries in the bitmap */
break;
}
BitmapAdjustPrefetchIterator(node, tbmres);
/*
* Ignore any claimed entries past what we think is the end of the
* relation. (This is probably not necessary given that we got at
* least AccessShareLock on the table before performing any of the
* indexscans, but let's be safe.)
*/
if (tbmres->blockno >= scan->rs_nblocks)
{
node->tbmres = tbmres = NULL;
continue;
}
/*
* We can skip fetching the heap page if we don't need any fields
* from the heap, and the bitmap entries don't need rechecking,
* and all tuples on the page are visible to our transaction.
*/
node->skip_fetch = (node->can_skip_fetch &&
!tbmres->recheck &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
tbmres->blockno,
&node->vmbuffer));
if (node->skip_fetch)
{
/*
* The number of tuples on this page is put into
* scan->rs_ntuples; note we don't fill scan->rs_vistuples.
*/
scan->rs_ntuples = tbmres->ntuples;
}
else
{
/*
* Fetch the current heap page and identify candidate tuples.
*/
bitgetpage(scan, tbmres);
}
if (tbmres->ntuples >= 0)
node->exact_pages++;
else
node->lossy_pages++;
/*
* Set rs_cindex to first slot to examine
*/
scan->rs_cindex = 0;
/* Adjust the prefetch target */
BitmapAdjustPrefetchTarget(node);
}
else
{
/*
* Continuing in previously obtained page; advance rs_cindex
*/
scan->rs_cindex++;
#ifdef USE_PREFETCH
/*
* Try to prefetch at least a few pages even before we get to the
* second page if we don't stop reading after the first tuple.
*/
if (!pstate)
{
if (node->prefetch_target < node->prefetch_maximum)
node->prefetch_target++;
}
else if (pstate->prefetch_target < node->prefetch_maximum)
{
/* take spinlock while updating shared state */
SpinLockAcquire(&pstate->mutex);
if (pstate->prefetch_target < node->prefetch_maximum)
pstate->prefetch_target++;
SpinLockRelease(&pstate->mutex);
}
#endif /* USE_PREFETCH */
}
/*
* Out of range? If so, nothing more to look at on this page
*/
if (scan->rs_cindex < 0 || scan->rs_cindex >= scan->rs_ntuples)
{
node->tbmres = tbmres = NULL;
continue;
}
/*
* We issue prefetch requests *after* fetching the current page to try
* to avoid having prefetching interfere with the main I/O. Also, this
* should happen only when we have determined there is still something
* to do on the current page, else we may uselessly prefetch the same
* page we are just about to request for real.
*/
BitmapPrefetch(node, scan);
if (node->skip_fetch)
{
/*
* If we don't have to fetch the tuple, just return nulls.
*/
ExecStoreAllNullTuple(slot);
}
else
{
/*
* Okay to fetch the tuple.
*/
targoffset = scan->rs_vistuples[scan->rs_cindex];
dp = (Page) BufferGetPage(scan->rs_cbuf);
lp = PageGetItemId(dp, targoffset);
Assert(ItemIdIsNormal(lp));
scan->rs_ctup.t_data = (HeapTupleHeader) PageGetItem((Page) dp, lp);
scan->rs_ctup.t_len = ItemIdGetLength(lp);
scan->rs_ctup.t_tableOid = scan->rs_rd->rd_id;
ItemPointerSet(&scan->rs_ctup.t_self, tbmres->blockno, targoffset);
pgstat_count_heap_fetch(scan->rs_rd);
/*
* Set up the result slot to point to this tuple. Note that the
* slot acquires a pin on the buffer.
*/
ExecStoreBufferHeapTuple(&scan->rs_ctup,
slot,
scan->rs_cbuf);
/*
* If we are using lossy info, we have to recheck the qual
* conditions at every tuple.
*/
if (tbmres->recheck)
{
econtext->ecxt_scantuple = slot;
if (!ExecQualAndReset(node->bitmapqualorig, econtext))
{
/* Fails recheck, so drop it and loop back for another */
InstrCountFiltered2(node, 1);
ExecClearTuple(slot);
continue;
}
}
}
/* OK to return this tuple */
return slot;
}
/*
* if we get here it means we are at the end of the scan..
*/
return ExecClearTuple(slot);
}
/* ----------------------------------------------------------------
* IndexOnlyNext
*
* Retrieve a tuple from the IndexOnlyScan node's index.
* ----------------------------------------------------------------
*/
static TupleTableSlot *
IndexOnlyNext(IndexOnlyScanState *node)
{
EState *estate;
ExprContext *econtext;
ScanDirection direction;
IndexScanDesc scandesc;
TupleTableSlot *slot;
ItemPointer tid;
/*
* extract necessary information from index scan node
*/
estate = node->ss.ps.state;
direction = estate->es_direction;
/* flip direction if this is an overall backward scan */
if (ScanDirectionIsBackward(((IndexOnlyScan *) node->ss.ps.plan)->indexorderdir))
{
if (ScanDirectionIsForward(direction))
direction = BackwardScanDirection;
else if (ScanDirectionIsBackward(direction))
direction = ForwardScanDirection;
}
scandesc = node->ioss_ScanDesc;
econtext = node->ss.ps.ps_ExprContext;
slot = node->ss.ss_ScanTupleSlot;
if (scandesc == NULL)
{
/*
* We reach here if the index only scan is not parallel, or if we're
* serially executing an index only scan that was planned to be
* parallel.
*/
scandesc = index_beginscan(node->ss.ss_currentRelation,
node->ioss_RelationDesc,
estate->es_snapshot,
node->ioss_NumScanKeys,
node->ioss_NumOrderByKeys);
node->ioss_ScanDesc = scandesc;
/* Set it up for index-only scan */
node->ioss_ScanDesc->xs_want_itup = true;
node->ioss_VMBuffer = InvalidBuffer;
/*
* If no run-time keys to calculate or they are ready, go ahead and
* pass the scankeys to the index AM.
*/
if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
index_rescan(scandesc,
node->ioss_ScanKeys,
node->ioss_NumScanKeys,
node->ioss_OrderByKeys,
node->ioss_NumOrderByKeys);
}
/*
* OK, now that we have what we need, fetch the next tuple.
*/
while ((tid = index_getnext_tid(scandesc, direction)) != NULL)
{
HeapTuple tuple = NULL;
CHECK_FOR_INTERRUPTS();
/*
* We can skip the heap fetch if the TID references a heap page on
* which all tuples are known visible to everybody. In any case,
* we'll use the index tuple not the heap tuple as the data source.
*
* Note on Memory Ordering Effects: visibilitymap_get_status does not
* lock the visibility map buffer, and therefore the result we read
* here could be slightly stale. However, it can't be stale enough to
* matter.
*
* We need to detect clearing a VM bit due to an insert right away,
* because the tuple is present in the index page but not visible. The
* reading of the TID by this scan (using a shared lock on the index
* buffer) is serialized with the insert of the TID into the index
* (using an exclusive lock on the index buffer). Because the VM bit
* is cleared before updating the index, and locking/unlocking of the
* index page acts as a full memory barrier, we are sure to see the
* cleared bit if we see a recently-inserted TID.
*
* Deletes do not update the index page (only VACUUM will clear out
* the TID), so the clearing of the VM bit by a delete is not
* serialized with this test below, and we may see a value that is
* significantly stale. However, we don't care about the delete right
* away, because the tuple is still visible until the deleting
* transaction commits or the statement ends (if it's our
* transaction). In either case, the lock on the VM buffer will have
* been released (acting as a write barrier) after clearing the bit.
* And for us to have a snapshot that includes the deleting
* transaction (making the tuple invisible), we must have acquired
* ProcArrayLock after that time, acting as a read barrier.
*
* It's worth going through this complexity to avoid needing to lock
* the VM buffer, which could cause significant contention.
*/
if (!VM_ALL_VISIBLE(scandesc->heapRelation,
ItemPointerGetBlockNumber(tid),
&node->ioss_VMBuffer))
{
/*
* Rats, we have to visit the heap to check visibility.
*/
InstrCountTuples2(node, 1);
tuple = index_fetch_heap(scandesc);
if (tuple == NULL)
continue; /* no visible tuple, try next index entry */
/*
* Only MVCC snapshots are supported here, so there should be no
* need to keep following the HOT chain once a visible entry has
* been found. If we did want to allow that, we'd need to keep
* more state to remember not to call index_getnext_tid next time.
*/
if (scandesc->xs_continue_hot)
elog(ERROR, "non-MVCC snapshots are not supported in index-only scans");
/*
* Note: at this point we are holding a pin on the heap page, as
* recorded in scandesc->xs_cbuf. We could release that pin now,
* but it's not clear whether it's a win to do so. The next index
* entry might require a visit to the same heap page.
*/
}
/*
* Fill the scan tuple slot with data from the index. This might be
* provided in either HeapTuple or IndexTuple format. Conceivably an
* index AM might fill both fields, in which case we prefer the heap
* format, since it's probably a bit cheaper to fill a slot from.
*/
if (scandesc->xs_hitup)
{
/*
* We don't take the trouble to verify that the provided tuple has
* exactly the slot's format, but it seems worth doing a quick
* check on the number of fields.
*/
Assert(slot->tts_tupleDescriptor->natts ==
scandesc->xs_hitupdesc->natts);
ExecStoreHeapTuple(scandesc->xs_hitup, slot, false);
}
else if (scandesc->xs_itup)
StoreIndexTuple(slot, scandesc->xs_itup, scandesc->xs_itupdesc);
else
elog(ERROR, "no data returned for index-only scan");
/*
* If the index was lossy, we have to recheck the index quals.
* (Currently, this can never happen, but we should support the case
* for possible future use, eg with GiST indexes.)
*/
if (scandesc->xs_recheck)
{
econtext->ecxt_scantuple = slot;
if (!ExecQualAndReset(node->indexqual, econtext))
{
/* Fails recheck, so drop it and loop back for another */
InstrCountFiltered2(node, 1);
continue;
}
}
/*
* We don't currently support rechecking ORDER BY distances. (In
* principle, if the index can support retrieval of the originally
* indexed value, it should be able to produce an exact distance
* calculation too. So it's not clear that adding code here for
* recheck/re-sort would be worth the trouble. But we should at least
* throw an error if someone tries it.)
*/
if (scandesc->numberOfOrderBys > 0 && scandesc->xs_recheckorderby)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("lossy distance functions are not supported in index-only scans")));
/*
* Predicate locks for index-only scans must be acquired at the page
* level when the heap is not accessed, since tuple-level predicate
* locks need the tuple's xmin value. If we had to visit the tuple
* anyway, then we already have the tuple-level lock and can skip the
* page lock.
*/
if (tuple == NULL)
PredicateLockPage(scandesc->heapRelation,
ItemPointerGetBlockNumber(tid),
estate->es_snapshot);
return slot;
}
/*
* if we get here it means the index scan failed so we are at the end of
* the scan..
*/
return ExecClearTuple(slot);
}
/*
* BitmapPrefetch - Prefetch, if prefetch_pages are behind prefetch_target
*/
static inline void
BitmapPrefetch(BitmapHeapScanState *node, HeapScanDesc scan)
{
#ifdef USE_PREFETCH
ParallelBitmapHeapState *pstate = node->pstate;
if (pstate == NULL)
{
TBMIterator *prefetch_iterator = node->prefetch_iterator;
if (prefetch_iterator)
{
while (node->prefetch_pages < node->prefetch_target)
{
TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
bool skip_fetch;
if (tbmpre == NULL)
{
/* No more pages to prefetch */
tbm_end_iterate(prefetch_iterator);
node->prefetch_iterator = NULL;
break;
}
node->prefetch_pages++;
/*
* If we expect not to have to actually read this heap page,
* skip this prefetch call, but continue to run the prefetch
* logic normally. (Would it be better not to increment
* prefetch_pages?)
*
* This depends on the assumption that the index AM will
* report the same recheck flag for this future heap page as
* it did for the current heap page; which is not a certainty
* but is true in many cases.
*/
skip_fetch = (node->can_skip_fetch &&
(node->tbmres ? !node->tbmres->recheck : false) &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
tbmpre->blockno,
&node->pvmbuffer));
if (!skip_fetch)
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
}
}
return;
}
if (pstate->prefetch_pages < pstate->prefetch_target)
{
TBMSharedIterator *prefetch_iterator = node->shared_prefetch_iterator;
if (prefetch_iterator)
{
while (1)
{
TBMIterateResult *tbmpre;
bool do_prefetch = false;
bool skip_fetch;
/*
* Recheck under the mutex. If some other process has already
* done enough prefetching then we need not to do anything.
*/
SpinLockAcquire(&pstate->mutex);
if (pstate->prefetch_pages < pstate->prefetch_target)
{
pstate->prefetch_pages++;
do_prefetch = true;
}
SpinLockRelease(&pstate->mutex);
if (!do_prefetch)
return;
tbmpre = tbm_shared_iterate(prefetch_iterator);
if (tbmpre == NULL)
{
/* No more pages to prefetch */
tbm_end_shared_iterate(prefetch_iterator);
node->shared_prefetch_iterator = NULL;
break;
}
/* As above, skip prefetch if we expect not to need page */
skip_fetch = (node->can_skip_fetch &&
(node->tbmres ? !node->tbmres->recheck : false) &&
VM_ALL_VISIBLE(node->ss.ss_currentRelation,
tbmpre->blockno,
&node->pvmbuffer));
if (!skip_fetch)
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
}
}
}
#endif /* USE_PREFETCH */
}
