Esempio n. 1
0
/* ----------------------------------------------------------------
 *		BitmapHeapNext
 *
 *		Retrieve next tuple from the BitmapHeapScan node's currentRelation
 * ----------------------------------------------------------------
 */
static TupleTableSlot *
BitmapHeapNext(BitmapHeapScanState *node)
{
	ExprContext *econtext;
	HeapScanDesc scan;
	TIDBitmap  *tbm;
	TBMIterator *tbmiterator;
	TBMIterateResult *tbmres;

#ifdef USE_PREFETCH
	TBMIterator *prefetch_iterator;
#endif
	OffsetNumber targoffset;
	TupleTableSlot *slot;

	/*
	 * 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;
	tbmiterator = node->tbmiterator;
	tbmres = node->tbmres;
#ifdef USE_PREFETCH
	prefetch_iterator = node->prefetch_iterator;
#endif

	/*
	 * 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 (tbm == NULL)
	{
		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 = prefetch_iterator = tbm_begin_iterate(tbm);
			node->prefetch_pages = 0;
			node->prefetch_target = -1;
		}
#endif   /* USE_PREFETCH */
	}

	for (;;)
	{
		Page		dp;
		ItemId		lp;

		/*
		 * Get next page of results if needed
		 */
		if (tbmres == NULL)
		{
			node->tbmres = tbmres = tbm_iterate(tbmiterator);
			if (tbmres == NULL)
			{
				/* no more entries in the bitmap */
				break;
			}

#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");
			}
#endif   /* USE_PREFETCH */

			/*
			 * 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;
			}

			/*
			 * 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;

#ifdef USE_PREFETCH

			/*
			 * 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.
			 */
			if (node->prefetch_target >= node->prefetch_maximum)
				 /* don't increase any further */ ;
			else if (node->prefetch_target >= node->prefetch_maximum / 2)
				node->prefetch_target = node->prefetch_maximum;
			else if (node->prefetch_target > 0)
				node->prefetch_target *= 2;
			else
				node->prefetch_target++;
#endif   /* USE_PREFETCH */
		}
		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 (node->prefetch_target < node->prefetch_maximum)
				node->prefetch_target++;
#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;
		}

#ifdef USE_PREFETCH

		/*
		 * 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.
		 */
		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);
			}
		}
#endif   /* USE_PREFETCH */

		/*
		 * Okay to fetch the tuple
		 */
		targoffset = scan->rs_vistuples[scan->rs_cindex];
		dp = BufferGetPage(scan->rs_cbuf, NULL, NULL, BGP_NO_SNAPSHOT_TEST);
		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.
		 */
		ExecStoreTuple(&scan->rs_ctup,
					   slot,
					   scan->rs_cbuf,
					   false);

		/*
		 * If we are using lossy info, we have to recheck the qual conditions
		 * at every tuple.
		 */
		if (tbmres->recheck)
		{
			econtext->ecxt_scantuple = slot;
			ResetExprContext(econtext);

			if (!ExecQual(node->bitmapqualorig, econtext, false))
			{
				/* 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);
}
/* ----------------------------------------------------------------
 *		BitmapHeapNext
 *
 *		Retrieve next tuple from the BitmapHeapScan node's currentRelation
 * ----------------------------------------------------------------
 */
static TupleTableSlot *
BitmapHeapNext(BitmapHeapScanState *node)
{
	EState	   *estate;
	ExprContext *econtext;
	HeapScanDesc scan;
	Index		scanrelid;
	TIDBitmap  *tbm;
	TBMIterateResult *tbmres;
	OffsetNumber targoffset;
	TupleTableSlot *slot;

	/*
	 * extract necessary information from index scan node
	 */
	estate = node->ss.ps.state;
	econtext = node->ss.ps.ps_ExprContext;
	slot = node->ss.ss_ScanTupleSlot;
	scan = node->ss.ss_currentScanDesc;
	scanrelid = ((BitmapHeapScan *) node->ss.ps.plan)->scan.scanrelid;
	tbm = node->tbm;
	tbmres = node->tbmres;

	/*
	 * Check if we are evaluating PlanQual for tuple of this relation.
	 * Additional checking is not good, but no other way for now. We could
	 * introduce new nodes for this case and handle IndexScan --> NewNode
	 * switching in Init/ReScan plan...
	 */
	if (estate->es_evTuple != NULL &&
		estate->es_evTuple[scanrelid - 1] != NULL)
	{
		if (estate->es_evTupleNull[scanrelid - 1])
			return ExecClearTuple(slot);

		ExecStoreTuple(estate->es_evTuple[scanrelid - 1],
					   slot, InvalidBuffer, false);

		/* Does the tuple meet the original qual conditions? */
		econtext->ecxt_scantuple = slot;

		ResetExprContext(econtext);

		if (!ExecQual(node->bitmapqualorig, econtext, false))
			ExecClearTuple(slot);		/* would not be returned by scan */

		/* Flag for the next call that no more tuples */
		estate->es_evTupleNull[scanrelid - 1] = true;

		return slot;
	}

	/*
	 * If we haven't yet performed the underlying index scan, do it, and
	 * prepare the bitmap to be iterated over.
	 */
	if (tbm == NULL)
	{
		tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));

		if (!tbm || !IsA(tbm, TIDBitmap))
			elog(ERROR, "unrecognized result from subplan");

		node->tbm = tbm;
		node->tbmres = tbmres = NULL;

		tbm_begin_iterate(tbm);
	}

	for (;;)
	{
		Page		dp;
		ItemId		lp;

		/*
		 * Get next page of results if needed
		 */
		if (tbmres == NULL)
		{
			node->tbmres = tbmres = tbm_iterate(tbm);
			if (tbmres == NULL)
			{
				/* no more entries in the bitmap */
				break;
			}

			/*
			 * 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;
			}

			/*
			 * Fetch the current heap page and identify candidate tuples.
			 */
			bitgetpage(scan, tbmres);

			/*
			 * Set rs_cindex to first slot to examine
			 */
			scan->rs_cindex = 0;
		}
		else
		{
			/*
			 * Continuing in previously obtained page; advance rs_cindex
			 */
			scan->rs_cindex++;
		}

		/*
		 * 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;
		}

		/*
		 * Okay to fetch the tuple
		 */
		targoffset = scan->rs_vistuples[scan->rs_cindex];
		dp = (Page) BufferGetPage(scan->rs_cbuf);
		lp = PageGetItemId(dp, targoffset);
		Assert(ItemIdIsUsed(lp));

		scan->rs_ctup.t_data = (HeapTupleHeader) PageGetItem((Page) dp, lp);
		scan->rs_ctup.t_len = ItemIdGetLength(lp);
		ItemPointerSet(&scan->rs_ctup.t_self, tbmres->blockno, targoffset);

		pgstat_count_heap_fetch(&scan->rs_pgstat_info);

		/*
		 * Set up the result slot to point to this tuple. Note that the slot
		 * acquires a pin on the buffer.
		 */
		ExecStoreTuple(&scan->rs_ctup,
					   slot,
					   scan->rs_cbuf,
					   false);

		/*
		 * If we are using lossy info, we have to recheck the qual conditions
		 * at every tuple.
		 */
		if (tbmres->ntuples < 0)
		{
			econtext->ecxt_scantuple = slot;
			ResetExprContext(econtext);

			if (!ExecQual(node->bitmapqualorig, econtext, false))
			{
				/* Fails recheck, so drop it and loop back for another */
				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);
}
/* ----------------------------------------------------------------
 *		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;
			}

			/*
			 * 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);

		/*
		 * 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.
		 */
		ExecStoreTuple(&scan->rs_ctup,
					   slot,
					   scan->rs_cbuf,
					   false);

		/*
		 * If we are using lossy info, we have to recheck the qual conditions
		 * at every tuple.
		 */
		if (tbmres->recheck)
		{
			econtext->ecxt_scantuple = slot;
			ResetExprContext(econtext);

			if (!ExecQual(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);
}
/*
 * 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);

				if (tbmpre == NULL)
				{
					/* No more pages to prefetch */
					tbm_end_iterate(prefetch_iterator);
					node->prefetch_iterator = NULL;
					break;
				}
				node->prefetch_pages++;
				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;

				/*
				 * 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;
				}

				PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
			}
		}
	}
#endif							/* USE_PREFETCH */
}
Esempio n. 5
0
/* ----------------------------------------------------------------
 *		BitmapHeapNext
 *
 *		Retrieve next tuple from the BitmapHeapScan node's currentRelation
 * ----------------------------------------------------------------
 */
static TupleTableSlot *
BitmapHeapNext(BitmapHeapScanState *node)
{
	EState	   *estate;
	ExprContext *econtext;
	HeapScanDesc scandesc;
	Index		scanrelid;
	TIDBitmap  *tbm;
	TBMIterateResult *tbmres;
	OffsetNumber targoffset;
	TupleTableSlot *slot;

	OnDiskBitmapWords *odbm;
	ODBMIterateResult *odbmres;
	bool inmem = false;

	/*
	 * extract necessary information from index scan node
	 */
	estate = node->ss.ps.state;
	econtext = node->ss.ps.ps_ExprContext;
	slot = node->ss.ss_ScanTupleSlot;
	scandesc = node->ss.ss_currentScanDesc;
	scanrelid = ((BitmapHeapScan *) node->ss.ps.plan)->scan.scanrelid;
	tbm = node->tbm;
	tbmres = node->tbmres;
	odbm = node->odbm;
	odbmres = node->odbmres;

	/*
	 * Clear any reference to the previously returned tuple.  The idea here is
	 * to not have the tuple slot be the last holder of a pin on that tuple's
	 * buffer; if it is, we'll need a separate visit to the bufmgr to release
	 * the buffer.	By clearing here, we get to have the release done by
	 * ReleaseAndReadBuffer, below.
	 */
	ExecClearTuple(slot);

	/*
	 * Check if we are evaluating PlanQual for tuple of this relation.
	 * Additional checking is not good, but no other way for now. We could
	 * introduce new nodes for this case and handle IndexScan --> NewNode
	 * switching in Init/ReScan plan...
	 */
	if (estate->es_evTuple != NULL &&
		estate->es_evTuple[scanrelid - 1] != NULL)
	{
		if (estate->es_evTupleNull[scanrelid - 1])
			return slot;		/* return empty slot */

		ExecStoreTuple(estate->es_evTuple[scanrelid - 1],
					   slot, InvalidBuffer, false);

		/* Does the tuple meet the original qual conditions? */
		econtext->ecxt_scantuple = slot;

		ResetExprContext(econtext);

		if (!ExecQual(node->bitmapqualorig, econtext, false))
			ExecClearTuple(slot);		/* would not be returned by scan */

		/* Flag for the next call that no more tuples */
		estate->es_evTupleNull[scanrelid - 1] = true;

		return slot;
	}

	/* check if this requires in-mem bitmap scan or on-disk bitmap index. */
	inmem = ((BitmapHeapScan*)(((PlanState*)node)->plan))->inmem;

	/*
	 * If the underline indexes are on disk bitmap indexes
	 */
	if (!inmem) {
		uint64	nextTid = 0;

		if (odbm == NULL)
		{
			odbm = odbm_create(ODBM_MAX_WORDS);
			node->odbm = odbm;
		}

		if (odbmres == NULL)
		{
			odbmres = odbm_res_create(odbm);
			node->odbmres = odbmres;
		}

		for (;;)
		{
			/* If we have used up the words from previous scan, or 
				we haven't scan the underlying index scan for wrods yet,
				then do it.
			 */
			if (odbm->numOfWords == 0 &&
				odbmres->nextTidLoc >= odbmres->numOfTids)
			{

				Plan* outerPlan = (((PlanState*)node)->lefttree)->plan;
				odbm_set_bitmaptype(outerPlan, false);

				odbm->firstTid = odbmres->nextTid;
				odbm->startNo = 0;
				odbm_set_child_resultnode(((PlanState*)node)->lefttree,
										  odbm);
				odbm = (OnDiskBitmapWords *)
					MultiExecProcNode(outerPlanState(node));

				if (!odbm || !IsA(odbm, OnDiskBitmapWords))
					elog(ERROR, "unrecognized result from subplan");

				odbm_begin_iterate(node->odbm, node->odbmres);
			}

			/* If we can not find more words, then this scan is over. */
			if (odbm == NULL ||
				(odbm->numOfWords == 0 && 
				 odbmres->nextTidLoc >= odbmres->numOfTids))
				return ExecClearTuple(slot);

			nextTid = odbm_findnexttid(odbm, odbmres);

			if (nextTid == 0)
				continue;

			ItemPointerSet(&scandesc->rs_ctup.t_self,
							(nextTid-1)/MaxNumHeapTuples,
							((nextTid-1)%MaxNumHeapTuples)+1);
			/* fetch the heap tuple and see if it matches the snapshot. */
			if (heap_release_fetch(scandesc->rs_rd,
								   scandesc->rs_snapshot,
								   &scandesc->rs_ctup,
								   &scandesc->rs_cbuf,
								   true,
								   &scandesc->rs_pgstat_info))
			{
				/*
			 	* Set up the result slot to point to this tuple.
				 * Note that the slot acquires a pin on the buffer.
				 */
				ExecStoreTuple(&scandesc->rs_ctup,
							   slot,
							   scandesc->rs_cbuf,
							   false);

			
				/* return this tuple */
				return slot;
			}
		}
	}

	/*
	 * If we haven't yet performed the underlying index scan, do it, and
	 * prepare the bitmap to be iterated over.
	 */
	if (tbm == NULL)
	{
		tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));

		if (!tbm || !IsA(tbm, TIDBitmap))
			elog(ERROR, "unrecognized result from subplan");

		node->tbm = tbm;
		node->tbmres = tbmres = NULL;

		tbm_begin_iterate(tbm);
	}

	for (;;)
	{
		/*
		 * Get next page of results if needed
		 */
		if (tbmres == NULL)
		{
			node->tbmres = tbmres = tbm_iterate(tbm);
			if (tbmres == NULL)
			{
				/* no more entries in the bitmap */
				break;
			}

			/*
			 * Ignore any claimed entries past what we think is the end of the
			 * relation.  (This is probably not necessary given that we got
			 * AccessShareLock before performing any of the indexscans, but
			 * let's be safe.)
			 */
			if (tbmres->blockno >= scandesc->rs_nblocks)
			{
				node->tbmres = tbmres = NULL;
				continue;
			}

			/*
			 * Acquire pin on the current heap page.  We'll hold the pin until
			 * done looking at the page.  We trade in any pin we held before.
			 */
			scandesc->rs_cbuf = ReleaseAndReadBuffer(scandesc->rs_cbuf,
													 scandesc->rs_rd,
													 tbmres->blockno);

			/*
			 * Determine how many entries we need to look at on this page. If
			 * the bitmap is lossy then we need to look at each physical item
			 * pointer; otherwise we just look through the offsets listed in
			 * tbmres.
			 */
			if (tbmres->ntuples >= 0)
			{
				/* non-lossy case */
				node->minslot = 0;
				node->maxslot = tbmres->ntuples - 1;
			}
			else
			{
				/* lossy case */
				Page		dp;

				LockBuffer(scandesc->rs_cbuf, BUFFER_LOCK_SHARE);
				dp = (Page) BufferGetPage(scandesc->rs_cbuf);

				node->minslot = FirstOffsetNumber;
				node->maxslot = PageGetMaxOffsetNumber(dp);

				LockBuffer(scandesc->rs_cbuf, BUFFER_LOCK_UNLOCK);
			}

			/*
			 * Set curslot to first slot to examine
			 */
			node->curslot = node->minslot;
		}
		else
		{
			/*
			 * Continuing in previously obtained page; advance curslot
			 */
			node->curslot++;
		}

		/*
		 * Out of range?  If so, nothing more to look at on this page
		 */
		if (node->curslot < node->minslot || node->curslot > node->maxslot)
		{
			node->tbmres = tbmres = NULL;
			continue;
		}

		/*
		 * Okay to try to fetch the tuple
		 */
		if (tbmres->ntuples >= 0)
		{
			/* non-lossy case */
			targoffset = tbmres->offsets[node->curslot];
		}
		else
		{
			/* lossy case */
			targoffset = (OffsetNumber) node->curslot;
		}

		ItemPointerSet(&scandesc->rs_ctup.t_self, tbmres->blockno, targoffset);

		/*
		 * Fetch the heap tuple and see if it matches the snapshot. We use
		 * heap_release_fetch to avoid useless bufmgr traffic.
		 */
		if (heap_release_fetch(scandesc->rs_rd,
							   scandesc->rs_snapshot,
							   &scandesc->rs_ctup,
							   &scandesc->rs_cbuf,
							   true,
							   &scandesc->rs_pgstat_info))
		{
			/*
			 * Set up the result slot to point to this tuple. Note that the
			 * slot acquires a pin on the buffer.
			 */
			ExecStoreTuple(&scandesc->rs_ctup,
						   slot,
						   scandesc->rs_cbuf,
						   false);

			/*
			 * If we are using lossy info, we have to recheck the qual
			 * conditions at every tuple.
			 */
			if (tbmres->ntuples < 0)
			{
				econtext->ecxt_scantuple = slot;
				ResetExprContext(econtext);

				if (!ExecQual(node->bitmapqualorig, econtext, false))
				{
					/* Fails recheck, so drop it and loop back for another */
					ExecClearTuple(slot);
					continue;
				}
			}

			/* OK to return this tuple */
			return slot;
		}

		/*
		 * Failed the snap, so loop back and try again.
		 */
	}

	/*
	 * if we get here it means we are at the end of the scan..
	 */
	return ExecClearTuple(slot);
}
Esempio n. 6
0
/*
 * 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 */
}