2005-04-20 00:35:18 +02:00
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
*
|
|
|
|
* nodeBitmapHeapscan.c
|
|
|
|
* Routines to support bitmapped scans of relations
|
|
|
|
*
|
|
|
|
* NOTE: it is critical that this plan type only be used with MVCC-compliant
|
Use an MVCC snapshot, rather than SnapshotNow, for catalog scans.
SnapshotNow scans have the undesirable property that, in the face of
concurrent updates, the scan can fail to see either the old or the new
versions of the row. In many cases, we work around this by requiring
DDL operations to hold AccessExclusiveLock on the object being
modified; in some cases, the existing locking is inadequate and random
failures occur as a result. This commit doesn't change anything
related to locking, but will hopefully pave the way to allowing lock
strength reductions in the future.
The major issue has held us back from making this change in the past
is that taking an MVCC snapshot is significantly more expensive than
using a static special snapshot such as SnapshotNow. However, testing
of various worst-case scenarios reveals that this problem is not
severe except under fairly extreme workloads. To mitigate those
problems, we avoid retaking the MVCC snapshot for each new scan;
instead, we take a new snapshot only when invalidation messages have
been processed. The catcache machinery already requires that
invalidation messages be sent before releasing the related heavyweight
lock; else other backends might rely on locally-cached data rather
than scanning the catalog at all. Thus, making snapshot reuse
dependent on the same guarantees shouldn't break anything that wasn't
already subtly broken.
Patch by me. Review by Michael Paquier and Andres Freund.
2013-07-02 15:47:01 +02:00
|
|
|
* snapshots (ie, regular snapshots, not SnapshotAny or one of the other
|
2014-05-06 18:12:18 +02:00
|
|
|
* special snapshots). The reason is that since index and heap scans are
|
2005-04-20 00:35:18 +02:00
|
|
|
* decoupled, there can be no assurance that the index tuple prompting a
|
|
|
|
* visit to a particular heap TID still exists when the visit is made.
|
|
|
|
* Therefore the tuple might not exist anymore either (which is OK because
|
|
|
|
* heap_fetch will cope) --- but worse, the tuple slot could have been
|
|
|
|
* re-used for a newer tuple. With an MVCC snapshot the newer tuple is
|
Use an MVCC snapshot, rather than SnapshotNow, for catalog scans.
SnapshotNow scans have the undesirable property that, in the face of
concurrent updates, the scan can fail to see either the old or the new
versions of the row. In many cases, we work around this by requiring
DDL operations to hold AccessExclusiveLock on the object being
modified; in some cases, the existing locking is inadequate and random
failures occur as a result. This commit doesn't change anything
related to locking, but will hopefully pave the way to allowing lock
strength reductions in the future.
The major issue has held us back from making this change in the past
is that taking an MVCC snapshot is significantly more expensive than
using a static special snapshot such as SnapshotNow. However, testing
of various worst-case scenarios reveals that this problem is not
severe except under fairly extreme workloads. To mitigate those
problems, we avoid retaking the MVCC snapshot for each new scan;
instead, we take a new snapshot only when invalidation messages have
been processed. The catcache machinery already requires that
invalidation messages be sent before releasing the related heavyweight
lock; else other backends might rely on locally-cached data rather
than scanning the catalog at all. Thus, making snapshot reuse
dependent on the same guarantees shouldn't break anything that wasn't
already subtly broken.
Patch by me. Review by Michael Paquier and Andres Freund.
2013-07-02 15:47:01 +02:00
|
|
|
* certain to fail the time qual and so it will not be mistakenly returned,
|
|
|
|
* but with anything else we might return a tuple that doesn't meet the
|
|
|
|
* required index qual conditions.
|
2005-04-20 00:35:18 +02:00
|
|
|
*
|
|
|
|
*
|
2016-01-02 19:33:40 +01:00
|
|
|
* Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
|
2005-04-20 00:35:18 +02:00
|
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
|
|
*
|
|
|
|
*
|
|
|
|
* IDENTIFICATION
|
2010-09-20 22:08:53 +02:00
|
|
|
* src/backend/executor/nodeBitmapHeapscan.c
|
2005-04-20 00:35:18 +02:00
|
|
|
*
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
/*
|
|
|
|
* INTERFACE ROUTINES
|
|
|
|
* ExecBitmapHeapScan scans a relation using bitmap info
|
|
|
|
* ExecBitmapHeapNext workhorse for above
|
|
|
|
* ExecInitBitmapHeapScan creates and initializes state info.
|
2010-07-12 19:01:06 +02:00
|
|
|
* ExecReScanBitmapHeapScan prepares to rescan the plan.
|
2005-04-20 00:35:18 +02:00
|
|
|
* ExecEndBitmapHeapScan releases all storage.
|
|
|
|
*/
|
|
|
|
#include "postgres.h"
|
|
|
|
|
2008-06-19 02:46:06 +02:00
|
|
|
#include "access/relscan.h"
|
2008-09-11 16:01:10 +02:00
|
|
|
#include "access/transam.h"
|
2005-04-20 00:35:18 +02:00
|
|
|
#include "executor/execdebug.h"
|
|
|
|
#include "executor/nodeBitmapHeapscan.h"
|
2005-10-06 04:29:23 +02:00
|
|
|
#include "pgstat.h"
|
2008-05-12 02:00:54 +02:00
|
|
|
#include "storage/bufmgr.h"
|
2011-06-29 20:40:27 +02:00
|
|
|
#include "storage/predicate.h"
|
2005-05-06 19:24:55 +02:00
|
|
|
#include "utils/memutils.h"
|
2011-02-23 18:18:09 +01:00
|
|
|
#include "utils/rel.h"
|
2015-09-08 17:51:42 +02:00
|
|
|
#include "utils/spccache.h"
|
2008-03-26 19:48:59 +01:00
|
|
|
#include "utils/snapmgr.h"
|
2008-03-26 22:10:39 +01:00
|
|
|
#include "utils/tqual.h"
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
|
|
|
|
static TupleTableSlot *BitmapHeapNext(BitmapHeapScanState *node);
|
2005-11-26 04:03:07 +01:00
|
|
|
static void bitgetpage(HeapScanDesc scan, TBMIterateResult *tbmres);
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
* BitmapHeapNext
|
|
|
|
*
|
|
|
|
* Retrieve next tuple from the BitmapHeapScan node's currentRelation
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
static TupleTableSlot *
|
|
|
|
BitmapHeapNext(BitmapHeapScanState *node)
|
|
|
|
{
|
|
|
|
ExprContext *econtext;
|
2005-11-26 04:03:07 +01:00
|
|
|
HeapScanDesc scan;
|
2005-04-20 00:35:18 +02:00
|
|
|
TIDBitmap *tbm;
|
2009-01-10 22:08:36 +01:00
|
|
|
TBMIterator *tbmiterator;
|
2005-04-20 00:35:18 +02:00
|
|
|
TBMIterateResult *tbmres;
|
2012-06-10 21:20:04 +02:00
|
|
|
|
2011-12-11 00:15:15 +01:00
|
|
|
#ifdef USE_PREFETCH
|
2009-01-12 06:10:45 +01:00
|
|
|
TBMIterator *prefetch_iterator;
|
2011-12-11 00:15:15 +01:00
|
|
|
#endif
|
2005-04-20 00:35:18 +02:00
|
|
|
OffsetNumber targoffset;
|
|
|
|
TupleTableSlot *slot;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* extract necessary information from index scan node
|
|
|
|
*/
|
|
|
|
econtext = node->ss.ps.ps_ExprContext;
|
|
|
|
slot = node->ss.ss_ScanTupleSlot;
|
2005-11-26 04:03:07 +01:00
|
|
|
scan = node->ss.ss_currentScanDesc;
|
2005-04-20 00:35:18 +02:00
|
|
|
tbm = node->tbm;
|
2009-01-10 22:08:36 +01:00
|
|
|
tbmiterator = node->tbmiterator;
|
2005-04-20 00:35:18 +02:00
|
|
|
tbmres = node->tbmres;
|
2011-12-11 00:15:15 +01:00
|
|
|
#ifdef USE_PREFETCH
|
2009-01-12 06:10:45 +01:00
|
|
|
prefetch_iterator = node->prefetch_iterator;
|
2011-12-11 00:15:15 +01:00
|
|
|
#endif
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
/*
|
2009-06-11 16:49:15 +02:00
|
|
|
* If we haven't yet performed the underlying index scan, do it, and begin
|
|
|
|
* the iteration over the bitmap.
|
2009-01-12 06:10:45 +01:00
|
|
|
*
|
|
|
|
* For prefetching, we use *two* iterators, one for the pages we are
|
|
|
|
* actually scanning and another that runs ahead of the first for
|
2009-06-11 16:49:15 +02:00
|
|
|
* 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
|
2015-09-08 17:51:42 +02:00
|
|
|
* 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.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
|
|
|
if (tbm == NULL)
|
|
|
|
{
|
|
|
|
tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
|
|
|
|
|
|
|
|
if (!tbm || !IsA(tbm, TIDBitmap))
|
|
|
|
elog(ERROR, "unrecognized result from subplan");
|
|
|
|
|
|
|
|
node->tbm = tbm;
|
2009-01-10 22:08:36 +01:00
|
|
|
node->tbmiterator = tbmiterator = tbm_begin_iterate(tbm);
|
2005-04-20 00:35:18 +02:00
|
|
|
node->tbmres = tbmres = NULL;
|
2009-01-12 06:10:45 +01:00
|
|
|
|
|
|
|
#ifdef USE_PREFETCH
|
2015-09-08 17:51:42 +02:00
|
|
|
if (node->prefetch_maximum > 0)
|
2009-01-12 06:10:45 +01:00
|
|
|
{
|
|
|
|
node->prefetch_iterator = prefetch_iterator = tbm_begin_iterate(tbm);
|
|
|
|
node->prefetch_pages = 0;
|
|
|
|
node->prefetch_target = -1;
|
|
|
|
}
|
2009-06-11 16:49:15 +02:00
|
|
|
#endif /* USE_PREFETCH */
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
for (;;)
|
|
|
|
{
|
2005-11-26 04:03:07 +01:00
|
|
|
Page dp;
|
|
|
|
ItemId lp;
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
|
|
|
* Get next page of results if needed
|
|
|
|
*/
|
|
|
|
if (tbmres == NULL)
|
|
|
|
{
|
2009-01-10 22:08:36 +01:00
|
|
|
node->tbmres = tbmres = tbm_iterate(tbmiterator);
|
2005-04-20 00:35:18 +02:00
|
|
|
if (tbmres == NULL)
|
|
|
|
{
|
|
|
|
/* no more entries in the bitmap */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2009-01-12 06:10:45 +01:00
|
|
|
#ifdef USE_PREFETCH
|
|
|
|
if (node->prefetch_pages > 0)
|
|
|
|
{
|
|
|
|
/* The main iterator has closed the distance by one page */
|
|
|
|
node->prefetch_pages--;
|
|
|
|
}
|
|
|
|
else if (prefetch_iterator)
|
|
|
|
{
|
|
|
|
/* Do not let the prefetch iterator get behind the main one */
|
|
|
|
TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
|
|
|
|
|
|
|
|
if (tbmpre == NULL || tbmpre->blockno != tbmres->blockno)
|
|
|
|
elog(ERROR, "prefetch and main iterators are out of sync");
|
|
|
|
}
|
2009-06-11 16:49:15 +02:00
|
|
|
#endif /* USE_PREFETCH */
|
2009-01-12 06:10:45 +01:00
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
2005-10-15 04:49:52 +02:00
|
|
|
* Ignore any claimed entries past what we think is the end of the
|
2005-12-02 21:03:42 +01:00
|
|
|
* 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.)
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2005-11-26 04:03:07 +01:00
|
|
|
if (tbmres->blockno >= scan->rs_nblocks)
|
2005-04-20 00:35:18 +02:00
|
|
|
{
|
|
|
|
node->tbmres = tbmres = NULL;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2005-11-26 04:03:07 +01:00
|
|
|
* Fetch the current heap page and identify candidate tuples.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2005-11-26 04:03:07 +01:00
|
|
|
bitgetpage(scan, tbmres);
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2014-01-13 20:42:16 +01:00
|
|
|
if (tbmres->ntuples >= 0)
|
|
|
|
node->exact_pages++;
|
|
|
|
else
|
|
|
|
node->lossy_pages++;
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
2005-11-26 04:03:07 +01:00
|
|
|
* Set rs_cindex to first slot to examine
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2005-11-26 04:03:07 +01:00
|
|
|
scan->rs_cindex = 0;
|
2009-01-12 06:10:45 +01:00
|
|
|
|
|
|
|
#ifdef USE_PREFETCH
|
2009-06-11 16:49:15 +02:00
|
|
|
|
2009-01-12 06:10:45 +01:00
|
|
|
/*
|
2009-06-11 16:49:15 +02:00
|
|
|
* Increase prefetch target if it's not yet at the max. Note that
|
|
|
|
* we will increase it to zero after fetching the very first
|
|
|
|
* page/tuple, then to one after the second tuple is fetched, then
|
|
|
|
* it doubles as later pages are fetched.
|
2009-01-12 06:10:45 +01:00
|
|
|
*/
|
2015-09-08 17:51:42 +02:00
|
|
|
if (node->prefetch_target >= node->prefetch_maximum)
|
2009-06-11 16:49:15 +02:00
|
|
|
/* don't increase any further */ ;
|
2015-09-08 17:51:42 +02:00
|
|
|
else if (node->prefetch_target >= node->prefetch_maximum / 2)
|
|
|
|
node->prefetch_target = node->prefetch_maximum;
|
2009-01-12 06:10:45 +01:00
|
|
|
else if (node->prefetch_target > 0)
|
|
|
|
node->prefetch_target *= 2;
|
|
|
|
else
|
|
|
|
node->prefetch_target++;
|
2009-06-11 16:49:15 +02:00
|
|
|
#endif /* USE_PREFETCH */
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
/*
|
2005-11-26 04:03:07 +01:00
|
|
|
* Continuing in previously obtained page; advance rs_cindex
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2005-11-26 04:03:07 +01:00
|
|
|
scan->rs_cindex++;
|
2009-01-12 06:10:45 +01:00
|
|
|
|
|
|
|
#ifdef USE_PREFETCH
|
2009-06-11 16:49:15 +02:00
|
|
|
|
2009-01-12 06:10:45 +01:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2015-09-08 17:51:42 +02:00
|
|
|
if (node->prefetch_target < node->prefetch_maximum)
|
2009-01-12 06:10:45 +01:00
|
|
|
node->prefetch_target++;
|
2009-06-11 16:49:15 +02:00
|
|
|
#endif /* USE_PREFETCH */
|
2009-01-12 06:10:45 +01:00
|
|
|
}
|
|
|
|
|
2009-01-12 17:00:41 +01:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2009-01-12 06:10:45 +01:00
|
|
|
#ifdef USE_PREFETCH
|
2009-06-11 16:49:15 +02:00
|
|
|
|
2009-01-12 06:10:45 +01:00
|
|
|
/*
|
2009-06-11 16:49:15 +02:00
|
|
|
* 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.
|
2009-01-12 06:10:45 +01:00
|
|
|
*/
|
|
|
|
if (prefetch_iterator)
|
|
|
|
{
|
|
|
|
while (node->prefetch_pages < node->prefetch_target)
|
|
|
|
{
|
|
|
|
TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
|
|
|
|
|
|
|
|
if (tbmpre == NULL)
|
|
|
|
{
|
|
|
|
/* No more pages to prefetch */
|
|
|
|
tbm_end_iterate(prefetch_iterator);
|
|
|
|
node->prefetch_iterator = prefetch_iterator = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
node->prefetch_pages++;
|
|
|
|
PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
|
|
|
|
}
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
2009-06-11 16:49:15 +02:00
|
|
|
#endif /* USE_PREFETCH */
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
/*
|
2005-11-26 04:03:07 +01:00
|
|
|
* Okay to fetch the tuple
|
|
|
|
*/
|
|
|
|
targoffset = scan->rs_vistuples[scan->rs_cindex];
|
|
|
|
dp = (Page) BufferGetPage(scan->rs_cbuf);
|
|
|
|
lp = PageGetItemId(dp, targoffset);
|
2007-09-13 00:10:26 +02:00
|
|
|
Assert(ItemIdIsNormal(lp));
|
2005-11-26 04:03:07 +01:00
|
|
|
|
|
|
|
scan->rs_ctup.t_data = (HeapTupleHeader) PageGetItem((Page) dp, lp);
|
|
|
|
scan->rs_ctup.t_len = ItemIdGetLength(lp);
|
2013-07-22 19:26:33 +02:00
|
|
|
scan->rs_ctup.t_tableOid = scan->rs_rd->rd_id;
|
2005-11-26 04:03:07 +01:00
|
|
|
ItemPointerSet(&scan->rs_ctup.t_self, tbmres->blockno, targoffset);
|
|
|
|
|
2007-05-27 05:50:39 +02:00
|
|
|
pgstat_count_heap_fetch(scan->rs_rd);
|
2005-11-26 04:03:07 +01:00
|
|
|
|
|
|
|
/*
|
2006-10-04 02:30:14 +02:00
|
|
|
* Set up the result slot to point to this tuple. Note that the slot
|
|
|
|
* acquires a pin on the buffer.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2005-11-26 04:03:07 +01:00
|
|
|
ExecStoreTuple(&scan->rs_ctup,
|
|
|
|
slot,
|
|
|
|
scan->rs_cbuf,
|
|
|
|
false);
|
|
|
|
|
|
|
|
/*
|
2006-10-04 02:30:14 +02:00
|
|
|
* If we are using lossy info, we have to recheck the qual conditions
|
|
|
|
* at every tuple.
|
2005-11-26 04:03:07 +01:00
|
|
|
*/
|
2008-04-11 00:25:26 +02:00
|
|
|
if (tbmres->recheck)
|
2005-11-26 04:03:07 +01:00
|
|
|
{
|
|
|
|
econtext->ecxt_scantuple = slot;
|
|
|
|
ResetExprContext(econtext);
|
|
|
|
|
|
|
|
if (!ExecQual(node->bitmapqualorig, econtext, false))
|
|
|
|
{
|
|
|
|
/* Fails recheck, so drop it and loop back for another */
|
2011-09-22 17:29:18 +02:00
|
|
|
InstrCountFiltered2(node, 1);
|
2005-11-26 04:03:07 +01:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* bitgetpage - subroutine for BitmapHeapNext()
|
|
|
|
*
|
|
|
|
* This routine reads and pins the specified page of the relation, then
|
|
|
|
* builds an array indicating which tuples on the page are both potentially
|
|
|
|
* interesting according to the bitmap, and visible according to the snapshot.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
bitgetpage(HeapScanDesc scan, TBMIterateResult *tbmres)
|
|
|
|
{
|
2006-10-04 02:30:14 +02:00
|
|
|
BlockNumber page = tbmres->blockno;
|
2005-11-26 04:03:07 +01:00
|
|
|
Buffer buffer;
|
|
|
|
Snapshot snapshot;
|
|
|
|
int ntup;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Acquire pin on the target heap page, trading in any pin we held before.
|
|
|
|
*/
|
|
|
|
Assert(page < scan->rs_nblocks);
|
|
|
|
|
|
|
|
scan->rs_cbuf = ReleaseAndReadBuffer(scan->rs_cbuf,
|
|
|
|
scan->rs_rd,
|
|
|
|
page);
|
|
|
|
buffer = scan->rs_cbuf;
|
|
|
|
snapshot = scan->rs_snapshot;
|
|
|
|
|
2007-09-20 19:56:33 +02:00
|
|
|
ntup = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Prune and repair fragmentation for the whole page, if possible.
|
|
|
|
*/
|
Introduce logical decoding.
This feature, building on previous commits, allows the write-ahead log
stream to be decoded into a series of logical changes; that is,
inserts, updates, and deletes and the transactions which contain them.
It is capable of handling decoding even across changes to the schema
of the effected tables. The output format is controlled by a
so-called "output plugin"; an example is included. To make use of
this in a real replication system, the output plugin will need to be
modified to produce output in the format appropriate to that system,
and to perform filtering.
Currently, information can be extracted from the logical decoding
system only via SQL; future commits will add the ability to stream
changes via walsender.
Andres Freund, with review and other contributions from many other
people, including Álvaro Herrera, Abhijit Menon-Sen, Peter Gheogegan,
Kevin Grittner, Robert Haas, Heikki Linnakangas, Fujii Masao, Abhijit
Menon-Sen, Michael Paquier, Simon Riggs, Craig Ringer, and Steve
Singer.
2014-03-03 22:32:18 +01:00
|
|
|
heap_page_prune_opt(scan->rs_rd, buffer);
|
2007-09-20 19:56:33 +02:00
|
|
|
|
2005-11-26 04:03:07 +01:00
|
|
|
/*
|
2006-10-04 02:30:14 +02:00
|
|
|
* We must hold share lock on the buffer content while examining tuple
|
2014-05-06 18:12:18 +02:00
|
|
|
* visibility. Afterwards, however, the tuples we have found to be
|
2006-10-04 02:30:14 +02:00
|
|
|
* visible are guaranteed good as long as we hold the buffer pin.
|
2005-11-26 04:03:07 +01:00
|
|
|
*/
|
|
|
|
LockBuffer(buffer, BUFFER_LOCK_SHARE);
|
|
|
|
|
|
|
|
/*
|
2007-09-20 19:56:33 +02:00
|
|
|
* We need two separate strategies for lossy and non-lossy cases.
|
2005-11-26 04:03:07 +01:00
|
|
|
*/
|
|
|
|
if (tbmres->ntuples >= 0)
|
|
|
|
{
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
2007-09-20 19:56:33 +02:00
|
|
|
* Bitmap is non-lossy, so we just look through the offsets listed in
|
|
|
|
* tbmres; but we have to follow any HOT chain starting at each such
|
|
|
|
* offset.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2007-11-15 22:14:46 +01:00
|
|
|
int curslot;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2007-09-20 19:56:33 +02:00
|
|
|
for (curslot = 0; curslot < tbmres->ntuples; curslot++)
|
|
|
|
{
|
|
|
|
OffsetNumber offnum = tbmres->offsets[curslot];
|
|
|
|
ItemPointerData tid;
|
2012-06-10 21:20:04 +02:00
|
|
|
HeapTupleData heapTuple;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2007-09-20 19:56:33 +02:00
|
|
|
ItemPointerSet(&tid, page, offnum);
|
2011-06-27 16:27:17 +02:00
|
|
|
if (heap_hot_search_buffer(&tid, scan->rs_rd, buffer, snapshot,
|
|
|
|
&heapTuple, NULL, true))
|
2007-09-20 19:56:33 +02:00
|
|
|
scan->rs_vistuples[ntup++] = ItemPointerGetOffsetNumber(&tid);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2005-11-26 04:03:07 +01:00
|
|
|
/*
|
2007-09-20 19:56:33 +02:00
|
|
|
* Bitmap is lossy, so we must examine each item pointer on the page.
|
|
|
|
* But we can ignore HOT chains, since we'll check each tuple anyway.
|
2005-11-26 04:03:07 +01:00
|
|
|
*/
|
2007-09-20 19:56:33 +02:00
|
|
|
Page dp = (Page) BufferGetPage(buffer);
|
|
|
|
OffsetNumber maxoff = PageGetMaxOffsetNumber(dp);
|
|
|
|
OffsetNumber offnum;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2008-05-13 17:44:08 +02:00
|
|
|
for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
|
2007-09-20 19:56:33 +02:00
|
|
|
{
|
|
|
|
ItemId lp;
|
|
|
|
HeapTupleData loctup;
|
2011-06-29 20:40:27 +02:00
|
|
|
bool valid;
|
2005-11-26 04:03:07 +01:00
|
|
|
|
2007-09-20 19:56:33 +02:00
|
|
|
lp = PageGetItemId(dp, offnum);
|
|
|
|
if (!ItemIdIsNormal(lp))
|
|
|
|
continue;
|
|
|
|
loctup.t_data = (HeapTupleHeader) PageGetItem((Page) dp, lp);
|
|
|
|
loctup.t_len = ItemIdGetLength(lp);
|
2011-06-29 20:40:27 +02:00
|
|
|
loctup.t_tableOid = scan->rs_rd->rd_id;
|
|
|
|
ItemPointerSet(&loctup.t_self, page, offnum);
|
|
|
|
valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
|
|
|
|
if (valid)
|
|
|
|
{
|
2007-09-20 19:56:33 +02:00
|
|
|
scan->rs_vistuples[ntup++] = offnum;
|
2011-06-29 20:40:27 +02:00
|
|
|
PredicateLockTuple(scan->rs_rd, &loctup, snapshot);
|
|
|
|
}
|
|
|
|
CheckForSerializableConflictOut(valid, scan->rs_rd, &loctup,
|
|
|
|
buffer, snapshot);
|
2007-09-20 19:56:33 +02:00
|
|
|
}
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
2005-11-26 04:03:07 +01:00
|
|
|
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
|
|
|
|
|
|
|
|
Assert(ntup <= MaxHeapTuplesPerPage);
|
|
|
|
scan->rs_ntuples = ntup;
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
Re-implement EvalPlanQual processing to improve its performance and eliminate
a lot of strange behaviors that occurred in join cases. We now identify the
"current" row for every joined relation in UPDATE, DELETE, and SELECT FOR
UPDATE/SHARE queries. If an EvalPlanQual recheck is necessary, we jam the
appropriate row into each scan node in the rechecking plan, forcing it to emit
only that one row. The former behavior could rescan the whole of each joined
relation for each recheck, which was terrible for performance, and what's much
worse could result in duplicated output tuples.
Also, the original implementation of EvalPlanQual could not re-use the recheck
execution tree --- it had to go through a full executor init and shutdown for
every row to be tested. To avoid this overhead, I've associated a special
runtime Param with each LockRows or ModifyTable plan node, and arranged to
make every scan node below such a node depend on that Param. Thus, by
signaling a change in that Param, the EPQ machinery can just rescan the
already-built test plan.
This patch also adds a prohibition on set-returning functions in the
targetlist of SELECT FOR UPDATE/SHARE. This is needed to avoid the
duplicate-output-tuple problem. It seems fairly reasonable since the
other restrictions on SELECT FOR UPDATE are meant to ensure that there
is a unique correspondence between source tuples and result tuples,
which an output SRF destroys as much as anything else does.
2009-10-26 03:26:45 +01:00
|
|
|
/*
|
|
|
|
* BitmapHeapRecheck -- access method routine to recheck a tuple in EvalPlanQual
|
|
|
|
*/
|
|
|
|
static bool
|
|
|
|
BitmapHeapRecheck(BitmapHeapScanState *node, TupleTableSlot *slot)
|
|
|
|
{
|
|
|
|
ExprContext *econtext;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* extract necessary information from index scan node
|
|
|
|
*/
|
|
|
|
econtext = node->ss.ps.ps_ExprContext;
|
|
|
|
|
|
|
|
/* Does the tuple meet the original qual conditions? */
|
|
|
|
econtext->ecxt_scantuple = slot;
|
|
|
|
|
|
|
|
ResetExprContext(econtext);
|
|
|
|
|
|
|
|
return ExecQual(node->bitmapqualorig, econtext, false);
|
|
|
|
}
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
* ExecBitmapHeapScan(node)
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
TupleTableSlot *
|
|
|
|
ExecBitmapHeapScan(BitmapHeapScanState *node)
|
|
|
|
{
|
Re-implement EvalPlanQual processing to improve its performance and eliminate
a lot of strange behaviors that occurred in join cases. We now identify the
"current" row for every joined relation in UPDATE, DELETE, and SELECT FOR
UPDATE/SHARE queries. If an EvalPlanQual recheck is necessary, we jam the
appropriate row into each scan node in the rechecking plan, forcing it to emit
only that one row. The former behavior could rescan the whole of each joined
relation for each recheck, which was terrible for performance, and what's much
worse could result in duplicated output tuples.
Also, the original implementation of EvalPlanQual could not re-use the recheck
execution tree --- it had to go through a full executor init and shutdown for
every row to be tested. To avoid this overhead, I've associated a special
runtime Param with each LockRows or ModifyTable plan node, and arranged to
make every scan node below such a node depend on that Param. Thus, by
signaling a change in that Param, the EPQ machinery can just rescan the
already-built test plan.
This patch also adds a prohibition on set-returning functions in the
targetlist of SELECT FOR UPDATE/SHARE. This is needed to avoid the
duplicate-output-tuple problem. It seems fairly reasonable since the
other restrictions on SELECT FOR UPDATE are meant to ensure that there
is a unique correspondence between source tuples and result tuples,
which an output SRF destroys as much as anything else does.
2009-10-26 03:26:45 +01:00
|
|
|
return ExecScan(&node->ss,
|
|
|
|
(ExecScanAccessMtd) BitmapHeapNext,
|
|
|
|
(ExecScanRecheckMtd) BitmapHeapRecheck);
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
2010-07-12 19:01:06 +02:00
|
|
|
* ExecReScanBitmapHeapScan(node)
|
2005-04-20 00:35:18 +02:00
|
|
|
* ----------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
void
|
2010-07-12 19:01:06 +02:00
|
|
|
ExecReScanBitmapHeapScan(BitmapHeapScanState *node)
|
2005-04-20 00:35:18 +02:00
|
|
|
{
|
2015-05-24 03:35:49 +02:00
|
|
|
PlanState *outerPlan = outerPlanState(node);
|
2015-05-04 22:13:07 +02:00
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/* rescan to release any page pin */
|
|
|
|
heap_rescan(node->ss.ss_currentScanDesc, NULL);
|
|
|
|
|
2009-01-10 22:08:36 +01:00
|
|
|
if (node->tbmiterator)
|
|
|
|
tbm_end_iterate(node->tbmiterator);
|
2009-01-12 06:10:45 +01:00
|
|
|
if (node->prefetch_iterator)
|
|
|
|
tbm_end_iterate(node->prefetch_iterator);
|
2005-04-20 00:35:18 +02:00
|
|
|
if (node->tbm)
|
|
|
|
tbm_free(node->tbm);
|
|
|
|
node->tbm = NULL;
|
2009-01-10 22:08:36 +01:00
|
|
|
node->tbmiterator = NULL;
|
2005-04-20 00:35:18 +02:00
|
|
|
node->tbmres = NULL;
|
2009-01-12 06:10:45 +01:00
|
|
|
node->prefetch_iterator = NULL;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
Re-implement EvalPlanQual processing to improve its performance and eliminate
a lot of strange behaviors that occurred in join cases. We now identify the
"current" row for every joined relation in UPDATE, DELETE, and SELECT FOR
UPDATE/SHARE queries. If an EvalPlanQual recheck is necessary, we jam the
appropriate row into each scan node in the rechecking plan, forcing it to emit
only that one row. The former behavior could rescan the whole of each joined
relation for each recheck, which was terrible for performance, and what's much
worse could result in duplicated output tuples.
Also, the original implementation of EvalPlanQual could not re-use the recheck
execution tree --- it had to go through a full executor init and shutdown for
every row to be tested. To avoid this overhead, I've associated a special
runtime Param with each LockRows or ModifyTable plan node, and arranged to
make every scan node below such a node depend on that Param. Thus, by
signaling a change in that Param, the EPQ machinery can just rescan the
already-built test plan.
This patch also adds a prohibition on set-returning functions in the
targetlist of SELECT FOR UPDATE/SHARE. This is needed to avoid the
duplicate-output-tuple problem. It seems fairly reasonable since the
other restrictions on SELECT FOR UPDATE are meant to ensure that there
is a unique correspondence between source tuples and result tuples,
which an output SRF destroys as much as anything else does.
2009-10-26 03:26:45 +01:00
|
|
|
ExecScanReScan(&node->ss);
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
2010-07-12 19:01:06 +02:00
|
|
|
* if chgParam of subnode is not null then plan will be re-scanned by
|
|
|
|
* first ExecProcNode.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2015-05-04 22:13:07 +02:00
|
|
|
if (outerPlan->chgParam == NULL)
|
|
|
|
ExecReScan(outerPlan);
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
* ExecEndBitmapHeapScan
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
void
|
|
|
|
ExecEndBitmapHeapScan(BitmapHeapScanState *node)
|
|
|
|
{
|
|
|
|
Relation relation;
|
|
|
|
HeapScanDesc scanDesc;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* extract information from the node
|
|
|
|
*/
|
|
|
|
relation = node->ss.ss_currentRelation;
|
|
|
|
scanDesc = node->ss.ss_currentScanDesc;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Free the exprcontext
|
|
|
|
*/
|
|
|
|
ExecFreeExprContext(&node->ss.ps);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* clear out tuple table slots
|
|
|
|
*/
|
|
|
|
ExecClearTuple(node->ss.ps.ps_ResultTupleSlot);
|
|
|
|
ExecClearTuple(node->ss.ss_ScanTupleSlot);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* close down subplans
|
|
|
|
*/
|
|
|
|
ExecEndNode(outerPlanState(node));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* release bitmap if any
|
|
|
|
*/
|
2009-01-10 22:08:36 +01:00
|
|
|
if (node->tbmiterator)
|
|
|
|
tbm_end_iterate(node->tbmiterator);
|
2009-01-12 06:10:45 +01:00
|
|
|
if (node->prefetch_iterator)
|
|
|
|
tbm_end_iterate(node->prefetch_iterator);
|
2005-04-20 00:35:18 +02:00
|
|
|
if (node->tbm)
|
|
|
|
tbm_free(node->tbm);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* close heap scan
|
|
|
|
*/
|
|
|
|
heap_endscan(scanDesc);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* close the heap relation.
|
|
|
|
*/
|
2005-12-02 21:03:42 +01:00
|
|
|
ExecCloseScanRelation(relation);
|
2005-04-20 00:35:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* ----------------------------------------------------------------
|
|
|
|
* ExecInitBitmapHeapScan
|
|
|
|
*
|
|
|
|
* Initializes the scan's state information.
|
|
|
|
* ----------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
BitmapHeapScanState *
|
2006-02-28 05:10:28 +01:00
|
|
|
ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
|
2005-04-20 00:35:18 +02:00
|
|
|
{
|
|
|
|
BitmapHeapScanState *scanstate;
|
|
|
|
Relation currentRelation;
|
2015-09-08 17:51:42 +02:00
|
|
|
int io_concurrency;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2006-02-28 05:10:28 +01:00
|
|
|
/* check for unsupported flags */
|
|
|
|
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
|
|
|
|
|
2005-11-26 04:03:07 +01:00
|
|
|
/*
|
2006-10-04 02:30:14 +02:00
|
|
|
* Assert caller didn't ask for an unsafe snapshot --- see comments at
|
|
|
|
* head of file.
|
2005-11-26 04:03:07 +01:00
|
|
|
*/
|
|
|
|
Assert(IsMVCCSnapshot(estate->es_snapshot));
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
|
|
|
* create state structure
|
|
|
|
*/
|
|
|
|
scanstate = makeNode(BitmapHeapScanState);
|
|
|
|
scanstate->ss.ps.plan = (Plan *) node;
|
|
|
|
scanstate->ss.ps.state = estate;
|
|
|
|
|
|
|
|
scanstate->tbm = NULL;
|
2009-01-10 22:08:36 +01:00
|
|
|
scanstate->tbmiterator = NULL;
|
2005-04-20 00:35:18 +02:00
|
|
|
scanstate->tbmres = NULL;
|
2014-01-13 20:42:16 +01:00
|
|
|
scanstate->exact_pages = 0;
|
|
|
|
scanstate->lossy_pages = 0;
|
2009-01-12 06:10:45 +01:00
|
|
|
scanstate->prefetch_iterator = NULL;
|
|
|
|
scanstate->prefetch_pages = 0;
|
|
|
|
scanstate->prefetch_target = 0;
|
2015-09-08 17:51:42 +02:00
|
|
|
/* may be updated below */
|
|
|
|
scanstate->prefetch_maximum = target_prefetch_pages;
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Miscellaneous initialization
|
|
|
|
*
|
|
|
|
* create expression context for node
|
|
|
|
*/
|
|
|
|
ExecAssignExprContext(estate, &scanstate->ss.ps);
|
|
|
|
|
2006-12-26 20:26:46 +01:00
|
|
|
scanstate->ss.ps.ps_TupFromTlist = false;
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
|
|
|
* initialize child expressions
|
|
|
|
*/
|
|
|
|
scanstate->ss.ps.targetlist = (List *)
|
|
|
|
ExecInitExpr((Expr *) node->scan.plan.targetlist,
|
|
|
|
(PlanState *) scanstate);
|
|
|
|
scanstate->ss.ps.qual = (List *)
|
|
|
|
ExecInitExpr((Expr *) node->scan.plan.qual,
|
|
|
|
(PlanState *) scanstate);
|
|
|
|
scanstate->bitmapqualorig = (List *)
|
|
|
|
ExecInitExpr((Expr *) node->bitmapqualorig,
|
|
|
|
(PlanState *) scanstate);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* tuple table initialization
|
|
|
|
*/
|
|
|
|
ExecInitResultTupleSlot(estate, &scanstate->ss.ps);
|
|
|
|
ExecInitScanTupleSlot(estate, &scanstate->ss);
|
|
|
|
|
|
|
|
/*
|
2005-12-02 21:03:42 +01:00
|
|
|
* open the base relation and acquire appropriate lock on it.
|
2005-04-20 00:35:18 +02:00
|
|
|
*/
|
2013-04-27 23:48:57 +02:00
|
|
|
currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags);
|
2005-04-20 00:35:18 +02:00
|
|
|
|
2015-09-08 17:51:42 +02:00
|
|
|
/*
|
|
|
|
* Determine the maximum for prefetch_target. If the tablespace has a
|
|
|
|
* specific IO concurrency set, use that to compute the corresponding
|
|
|
|
* maximum value; otherwise, we already initialized to the value computed
|
|
|
|
* by the GUC machinery.
|
|
|
|
*/
|
|
|
|
io_concurrency =
|
|
|
|
get_tablespace_io_concurrency(currentRelation->rd_rel->reltablespace);
|
|
|
|
if (io_concurrency != effective_io_concurrency)
|
|
|
|
{
|
|
|
|
double maximum;
|
|
|
|
|
|
|
|
if (ComputeIoConcurrency(io_concurrency, &maximum))
|
|
|
|
scanstate->prefetch_maximum = rint(maximum);
|
|
|
|
}
|
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
scanstate->ss.ss_currentRelation = currentRelation;
|
|
|
|
|
|
|
|
/*
|
2005-10-15 04:49:52 +02:00
|
|
|
* Even though we aren't going to do a conventional seqscan, it is useful
|
2007-06-09 20:49:55 +02:00
|
|
|
* to create a HeapScanDesc --- most of the fields in it are usable.
|
2005-10-06 04:29:23 +02:00
|
|
|
*/
|
2007-06-09 20:49:55 +02:00
|
|
|
scanstate->ss.ss_currentScanDesc = heap_beginscan_bm(currentRelation,
|
|
|
|
estate->es_snapshot,
|
|
|
|
0,
|
|
|
|
NULL);
|
2005-10-06 04:29:23 +02:00
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
|
|
|
* get the scan type from the relation descriptor.
|
|
|
|
*/
|
2006-06-16 20:42:24 +02:00
|
|
|
ExecAssignScanType(&scanstate->ss, RelationGetDescr(currentRelation));
|
2005-04-20 00:35:18 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Initialize result tuple type and projection info.
|
|
|
|
*/
|
|
|
|
ExecAssignResultTypeFromTL(&scanstate->ss.ps);
|
|
|
|
ExecAssignScanProjectionInfo(&scanstate->ss);
|
|
|
|
|
2005-12-02 02:29:55 +01:00
|
|
|
/*
|
|
|
|
* initialize child nodes
|
|
|
|
*
|
|
|
|
* We do this last because the child nodes will open indexscans on our
|
2006-10-04 02:30:14 +02:00
|
|
|
* relation's indexes, and we want to be sure we have acquired a lock on
|
|
|
|
* the relation first.
|
2005-12-02 02:29:55 +01:00
|
|
|
*/
|
2006-02-28 05:10:28 +01:00
|
|
|
outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags);
|
2005-12-02 02:29:55 +01:00
|
|
|
|
2005-04-20 00:35:18 +02:00
|
|
|
/*
|
|
|
|
* all done.
|
|
|
|
*/
|
|
|
|
return scanstate;
|
|
|
|
}
|