On Mon, Dec 9, 2024 at 1:22 AM Dilip Kumar <dilipbal...@gmail.com> wrote:
>
> Are we planning to commit this refactoring? I think this refactoring
> makes the overall code of BitmapHeapNext() quite clean and readable.
> I haven't read all patches but 0001-0006 including 0009 makes this
> code quite clean and readable. I like the refactoring of merging of
> the shared iterator and the private iterator also.

Thanks for the feedback, Dilip. I've pushed the patches through 0006.

I've reorganized the remaining patches in attached v26.

0001 is just the refactoring to push the setup into a helper.
0002-0003 are required refactoring of the TBMIterateResult and
TBMIterator to support the read stream API.
0004 implements using the read stream API and removing the old prefetching code.
0005 removes the table_scan_bitmap_next_block() callback, as it is not
really used anymore in BitmapHeapNext() to get the next block.

I could use review feedback on all of them. 0001 should be ready to
push once I get some review.

0002 and 0003 shouldn't be committed without committing the read
stream commit because they are not improvements on their own. However,
I have an outstanding question in 0003 that I could use input on.

0004 needs another round of benchmarking.

0005 needs review once the others are dealt with.

- Melanie
From 7c73e5e868781904730cc4ea0fa62266c4fe8f4b Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Tue, 21 Jan 2025 17:36:50 -0500
Subject: [PATCH v26 1/5] Move BitmapTableScan per-scan setup into a helper

Add BitmapTableScanSetup(), a helper which contains all of the code that
must be done on every scan of the table in a bitmap table scan. This
includes scanning the index, building the bitmap, and setting up the
scan descriptors.

Much of BitmapHeapNext() code was this setup, so it made sense to put it
in a helper function.
---
 src/backend/executor/nodeBitmapHeapscan.c | 205 +++++++++++-----------
 1 file changed, 106 insertions(+), 99 deletions(-)

diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index be616683f98..92a199c1e87 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -48,6 +48,7 @@
 #include "utils/rel.h"
 #include "utils/spccache.h"
 
+static void BitmapTableScanSetup(BitmapHeapScanState *node);
 static TupleTableSlot *BitmapHeapNext(BitmapHeapScanState *node);
 static inline void BitmapDoneInitializingSharedState(ParallelBitmapHeapState *pstate);
 static inline void BitmapAdjustPrefetchIterator(BitmapHeapScanState *node);
@@ -57,6 +58,109 @@ static inline void BitmapPrefetch(BitmapHeapScanState *node,
 static bool BitmapShouldInitializeSharedState(ParallelBitmapHeapState *pstate);
 
 
+/*
+*
+ * Do the underlying index scan, build the bitmap, set up the parallel state
+ * needed for parallel workers to iterate through the bitmap, and set up the
+ * underlying table scan descriptor.
+ *
+* 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.
+*/
+static void
+BitmapTableScanSetup(BitmapHeapScanState *node)
+{
+	TBMIterator tbmiterator = {0};
+	ParallelBitmapHeapState *pstate = node->pstate;
+	dsa_area   *dsa = node->ss.ps.state->es_query_dsa;
+
+
+	if (!pstate)
+	{
+		node->tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
+
+		if (!node->tbm || !IsA(node->tbm, TIDBitmap))
+			elog(ERROR, "unrecognized result from subplan");
+	}
+	else if (BitmapShouldInitializeSharedState(pstate))
+	{
+		/*
+		 * The leader will immediately come out of the function, but others
+		 * will be blocked until leader populates the TBM and wakes them up.
+		 */
+		node->tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
+		if (!node->tbm || !IsA(node->tbm, TIDBitmap))
+			elog(ERROR, "unrecognized result from subplan");
+
+		/*
+		 * 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(node->tbm);
+
+#ifdef USE_PREFETCH
+		if (node->prefetch_maximum > 0)
+		{
+			pstate->prefetch_iterator =
+				tbm_prepare_shared_iterate(node->tbm);
+		}
+#endif							/* USE_PREFETCH */
+
+		/* We have initialized the shared state so wake up others. */
+		BitmapDoneInitializingSharedState(pstate);
+	}
+
+	tbmiterator = tbm_begin_iterate(node->tbm, dsa,
+									pstate ?
+									pstate->tbmiterator :
+									InvalidDsaPointer);
+
+#ifdef USE_PREFETCH
+	if (node->prefetch_maximum > 0)
+		node->prefetch_iterator =
+			tbm_begin_iterate(node->tbm, dsa,
+							  pstate ?
+							  pstate->prefetch_iterator :
+							  InvalidDsaPointer);
+#endif							/* USE_PREFETCH */
+
+	/*
+	 * If this is the first scan of the underlying table, create the table
+	 * scan descriptor and begin the scan.
+	 */
+	if (!node->ss.ss_currentScanDesc)
+	{
+		bool		need_tuples = false;
+
+		/*
+		 * We can potentially skip fetching heap pages if we do not need any
+		 * columns of the table, either for checking non-indexable quals or
+		 * for returning data.  This test is a bit simplistic, as it checks
+		 * the stronger condition that there's no qual or return tlist at all.
+		 * But in most cases it's probably not worth working harder than that.
+		 */
+		need_tuples = (node->ss.ps.plan->qual != NIL ||
+					   node->ss.ps.plan->targetlist != NIL);
+
+		node->ss.ss_currentScanDesc =
+			table_beginscan_bm(node->ss.ss_currentRelation,
+							   node->ss.ps.state->es_snapshot,
+							   0,
+							   NULL,
+							   need_tuples);
+	}
+
+	node->ss.ss_currentScanDesc->st.rs_tbmiterator = tbmiterator;
+	node->initialized = true;
+}
+
+
 /* ----------------------------------------------------------------
  *		BitmapHeapNext
  *
@@ -68,10 +172,8 @@ BitmapHeapNext(BitmapHeapScanState *node)
 {
 	ExprContext *econtext;
 	TableScanDesc scan;
-	TIDBitmap  *tbm;
 	TupleTableSlot *slot;
 	ParallelBitmapHeapState *pstate = node->pstate;
-	dsa_area   *dsa = node->ss.ps.state->es_query_dsa;
 
 	/*
 	 * extract necessary information from index scan node
@@ -79,110 +181,15 @@ BitmapHeapNext(BitmapHeapScanState *node)
 	econtext = node->ss.ps.ps_ExprContext;
 	slot = node->ss.ss_ScanTupleSlot;
 	scan = node->ss.ss_currentScanDesc;
-	tbm = node->tbm;
 
 	/*
 	 * 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)
 	{
-		TBMIterator tbmiterator;
-
-		if (!pstate)
-		{
-			tbm = (TIDBitmap *) MultiExecProcNode(outerPlanState(node));
-
-			if (!tbm || !IsA(tbm, TIDBitmap))
-				elog(ERROR, "unrecognized result from subplan");
-
-			node->tbm = tbm;
-		}
-		else if (BitmapShouldInitializeSharedState(pstate))
-		{
-			/*
-			 * The leader will immediately come out of the function, but
-			 * others will be blocked until leader populates the TBM and wakes
-			 * them up.
-			 */
-			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);
-			}
-#endif							/* USE_PREFETCH */
-
-			/* We have initialized the shared state so wake up others. */
-			BitmapDoneInitializingSharedState(pstate);
-		}
-
-		tbmiterator = tbm_begin_iterate(tbm, dsa,
-										pstate ?
-										pstate->tbmiterator :
-										InvalidDsaPointer);
-
-#ifdef USE_PREFETCH
-		if (node->prefetch_maximum > 0)
-			node->prefetch_iterator =
-				tbm_begin_iterate(tbm, dsa,
-								  pstate ?
-								  pstate->prefetch_iterator :
-								  InvalidDsaPointer);
-#endif							/* USE_PREFETCH */
-
-		/*
-		 * If this is the first scan of the underlying table, create the table
-		 * scan descriptor and begin the scan.
-		 */
-		if (!scan)
-		{
-			bool		need_tuples = false;
-
-			/*
-			 * We can potentially skip fetching heap pages if we do not need
-			 * any columns of the table, either for checking non-indexable
-			 * quals or for returning data.  This test is a bit simplistic, as
-			 * it checks the stronger condition that there's no qual or return
-			 * tlist at all. But in most cases it's probably not worth working
-			 * harder than that.
-			 */
-			need_tuples = (node->ss.ps.plan->qual != NIL ||
-						   node->ss.ps.plan->targetlist != NIL);
-
-			scan = table_beginscan_bm(node->ss.ss_currentRelation,
-									  node->ss.ps.state->es_snapshot,
-									  0,
-									  NULL,
-									  need_tuples);
-
-			node->ss.ss_currentScanDesc = scan;
-		}
-
-		scan->st.rs_tbmiterator = tbmiterator;
-		node->initialized = true;
-
+		BitmapTableScanSetup(node);
+		scan = node->ss.ss_currentScanDesc;
 		goto new_page;
 	}
 
-- 
2.34.1

From 19cdf4706e0ad1842ad3eb14a5c81fa16e88f976 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Wed, 22 Jan 2025 15:00:12 -0500
Subject: [PATCH v26 4/5] BitmapHeapScan uses read stream API

Make Bitmap Heap Scan use the read stream API instead of invoking
ReadBuffer() for each block indicated by the bitmap.

The read stream API handles prefetching, so remove all of the explicit
prefetching from bitmap heap scan code.

Now, heap table AM implements a read stream callback which uses the
bitmap iterator to return the next required block to the read stream
code.
---
 src/backend/access/heap/heapam.c          |  70 +++++
 src/backend/access/heap/heapam_handler.c  |  86 +++---
 src/backend/executor/nodeBitmapHeapscan.c | 355 +---------------------
 src/include/access/relscan.h              |   8 +-
 src/include/access/tableam.h              |  33 +-
 src/include/nodes/execnodes.h             |  23 +-
 6 files changed, 131 insertions(+), 444 deletions(-)

diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index b6349950294..fc4e3f807d6 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -277,6 +277,62 @@ heap_scan_stream_read_next_serial(ReadStream *stream,
 	return scan->rs_prefetch_block;
 }
 
+/*
+ * Read stream API callback for bitmap heap scans.
+ * Returns the next block the caller wants from the read stream or
+ * InvalidBlockNumber when done.
+ */
+static BlockNumber
+bitmapheap_stream_read_next(ReadStream *pgsr, void *private_data,
+							void *per_buffer_data)
+{
+	TBMIterateResult *tbmres = per_buffer_data;
+	BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) private_data;
+	HeapScanDesc hscan = (HeapScanDesc) bscan;
+	TableScanDesc sscan = &hscan->rs_base;
+
+	for (;;)
+	{
+		CHECK_FOR_INTERRUPTS();
+
+		tbm_iterate(&sscan->st.bitmap.rs_iterator, tbmres);
+
+		/* no more entries in the bitmap */
+		if (!BlockNumberIsValid(tbmres->blockno))
+			return InvalidBlockNumber;
+
+		/*
+		 * Ignore any claimed entries past what we think is the end of the
+		 * relation. It may have been extended after the start of our scan (we
+		 * only hold an AccessShareLock, and it could be inserts from this
+		 * backend).  We don't take this optimization in SERIALIZABLE
+		 * isolation though, as we need to examine all invisible tuples
+		 * reachable by the index.
+		 */
+		if (!IsolationIsSerializable() &&
+			tbmres->blockno >= hscan->rs_nblocks)
+			continue;
+
+		/*
+		 * We can skip fetching the heap page if we don't need any fields from
+		 * the heap, the bitmap entries don't need rechecking, and all tuples
+		 * on the page are visible to our transaction.
+		 */
+		if (!(sscan->rs_flags & SO_NEED_TUPLES) &&
+			!tbmres->recheck &&
+			VM_ALL_VISIBLE(sscan->rs_rd, tbmres->blockno, &bscan->rs_vmbuffer))
+		{
+			bscan->rs_empty_tuples_pending += tbmres->ntuples;
+			continue;
+		}
+
+		return tbmres->blockno;
+	}
+
+	/* not reachable */
+	Assert(false);
+}
+
 /* ----------------
  *		initscan - scan code common to heap_beginscan and heap_rescan
  * ----------------
@@ -1065,6 +1121,7 @@ heap_beginscan(Relation relation, Snapshot snapshot,
 	scan->rs_base.rs_flags = flags;
 	scan->rs_base.rs_parallel = parallel_scan;
 	scan->rs_strategy = NULL;	/* set in initscan */
+	scan->rs_cbuf = InvalidBuffer;
 
 	/*
 	 * Disable page-at-a-time mode if it's not a MVCC-safe snapshot.
@@ -1144,6 +1201,16 @@ heap_beginscan(Relation relation, Snapshot snapshot,
 														  scan,
 														  0);
 	}
+	else if (scan->rs_base.rs_flags & SO_TYPE_BITMAPSCAN)
+	{
+		scan->rs_read_stream = read_stream_begin_relation(READ_STREAM_DEFAULT,
+														  scan->rs_strategy,
+														  scan->rs_base.rs_rd,
+														  MAIN_FORKNUM,
+														  bitmapheap_stream_read_next,
+														  scan,
+														  sizeof(TBMIterateResult));
+	}
 
 
 	return (TableScanDesc) scan;
@@ -1178,7 +1245,10 @@ heap_rescan(TableScanDesc sscan, ScanKey key, bool set_params,
 	 * unpin scan buffers
 	 */
 	if (BufferIsValid(scan->rs_cbuf))
+	{
 		ReleaseBuffer(scan->rs_cbuf);
+		scan->rs_cbuf = InvalidBuffer;
+	}
 
 	if (scan->rs_base.rs_flags & SO_TYPE_BITMAPSCAN)
 	{
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bd567760f2d..eac51f5eb51 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2115,76 +2115,66 @@ heapam_estimate_rel_size(Relation rel, int32 *attr_widths,
 
 static bool
 heapam_scan_bitmap_next_block(TableScanDesc scan,
-							  BlockNumber *blockno, bool *recheck,
+							  bool *recheck,
 							  uint64 *lossy_pages, uint64 *exact_pages)
 {
 	BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) scan;
 	HeapScanDesc hscan = (HeapScanDesc) bscan;
 	BlockNumber block;
+	void	   *per_buffer_data;
 	Buffer		buffer;
 	Snapshot	snapshot;
 	int			ntup;
-	TBMIterateResult tbmres;
+	TBMIterateResult *tbmres;
 
 	Assert(scan->rs_flags & SO_TYPE_BITMAPSCAN);
+	Assert(hscan->rs_read_stream);
 
 	hscan->rs_cindex = 0;
 	hscan->rs_ntuples = 0;
 
-	*blockno = InvalidBlockNumber;
-	*recheck = true;
-
-	do
+	/* Release buffer containing previous block. */
+	if (BufferIsValid(hscan->rs_cbuf))
 	{
-		CHECK_FOR_INTERRUPTS();
+		ReleaseBuffer(hscan->rs_cbuf);
+		hscan->rs_cbuf = InvalidBuffer;
+	}
 
-		tbm_iterate(&scan->st.rs_tbmiterator, &tbmres);
+	hscan->rs_cbuf = read_stream_next_buffer(hscan->rs_read_stream, &per_buffer_data);
 
-		if (!BlockNumberIsValid(tbmres.blockno))
-			return false;
+	if (BufferIsInvalid(hscan->rs_cbuf))
+	{
+		if (BufferIsValid(bscan->rs_vmbuffer))
+		{
+			ReleaseBuffer(bscan->rs_vmbuffer);
+			bscan->rs_vmbuffer = InvalidBuffer;
+		}
 
 		/*
-		 * Ignore any claimed entries past what we think is the end of the
-		 * relation. It may have been extended after the start of our scan (we
-		 * only hold an AccessShareLock, and it could be inserts from this
-		 * backend).  We don't take this optimization in SERIALIZABLE
-		 * isolation though, as we need to examine all invisible tuples
-		 * reachable by the index.
+		 * Bitmap is exhausted. Time to emit empty tuples if relevant. We emit
+		 * all empty tuples at the end instead of emitting them per block we
+		 * skip fetching. This is necessary because the streaming read API
+		 * will only return TBMIterateResults for blocks actually fetched.
+		 * When we skip fetching a block, we keep track of how many empty
+		 * tuples to emit at the end of the BitmapHeapScan. We do not recheck
+		 * all NULL tuples.
 		 */
-	} while (!IsolationIsSerializable() &&
-			 tbmres.blockno >= hscan->rs_nblocks);
+		*recheck = false;
+		return bscan->rs_empty_tuples_pending > 0;
+	}
 
-	/* Got a valid block */
-	*blockno = tbmres.blockno;
-	*recheck = tbmres.recheck;
+	Assert(per_buffer_data);
 
-	/*
-	 * We can skip fetching the heap page if we don't need any fields from the
-	 * heap, the bitmap entries don't need rechecking, and all tuples on the
-	 * page are visible to our transaction.
-	 */
-	if (!(scan->rs_flags & SO_NEED_TUPLES) &&
-		!tbmres.recheck &&
-		VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &bscan->rs_vmbuffer))
-	{
-		/* can't be lossy in the skip_fetch case */
-		Assert(tbmres.ntuples >= 0);
-		Assert(bscan->rs_empty_tuples_pending >= 0);
+	tbmres = per_buffer_data;
 
-		bscan->rs_empty_tuples_pending += tbmres.ntuples;
+	Assert(BufferGetBlockNumber(hscan->rs_cbuf) == tbmres->blockno);
 
-		return true;
-	}
+	*recheck = tbmres->recheck;
 
-	block = tbmres.blockno;
+	hscan->rs_cblock = tbmres->blockno;
+	hscan->rs_ntuples = tbmres->ntuples;
 
-	/*
-	 * Acquire pin on the target heap page, trading in any pin we held before.
-	 */
-	hscan->rs_cbuf = ReleaseAndReadBuffer(hscan->rs_cbuf,
-										  scan->rs_rd,
-										  block);
-	hscan->rs_cblock = block;
+	block = tbmres->blockno;
 	buffer = hscan->rs_cbuf;
 	snapshot = scan->rs_snapshot;
 
@@ -2205,7 +2195,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	/*
 	 * We need two separate strategies for lossy and non-lossy cases.
 	 */
-	if (tbmres.ntuples >= 0)
+	if (tbmres->ntuples >= 0)
 	{
 		/*
 		 * Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2214,9 +2204,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 		 */
 		int			curslot;
 
-		for (curslot = 0; curslot < tbmres.ntuples; curslot++)
+		for (curslot = 0; curslot < tbmres->ntuples; curslot++)
 		{
-			OffsetNumber offnum = tbmres.offsets[curslot];
+			OffsetNumber offnum = tbmres->offsets[curslot];
 			ItemPointerData tid;
 			HeapTupleData heapTuple;
 
@@ -2266,7 +2256,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	Assert(ntup <= MaxHeapTuplesPerPage);
 	hscan->rs_ntuples = ntup;
 
-	if (tbmres.ntuples >= 0)
+	if (tbmres->ntuples >= 0)
 		(*exact_pages)++;
 	else
 		(*lossy_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index da3c76f4744..5b368a3dccc 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -51,27 +51,14 @@
 static void BitmapTableScanSetup(BitmapHeapScanState *node);
 static TupleTableSlot *BitmapHeapNext(BitmapHeapScanState *node);
 static inline void BitmapDoneInitializingSharedState(ParallelBitmapHeapState *pstate);
-static inline void BitmapAdjustPrefetchIterator(BitmapHeapScanState *node);
-static inline void BitmapAdjustPrefetchTarget(BitmapHeapScanState *node);
-static inline void BitmapPrefetch(BitmapHeapScanState *node,
-								  TableScanDesc scan);
 static bool BitmapShouldInitializeSharedState(ParallelBitmapHeapState *pstate);
 
 
 /*
-*
  * Do the underlying index scan, build the bitmap, set up the parallel state
  * needed for parallel workers to iterate through the bitmap, and set up the
  * underlying table scan descriptor.
- *
-* 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.
-*/
+ */
 static void
 BitmapTableScanSetup(BitmapHeapScanState *node)
 {
@@ -104,14 +91,6 @@ BitmapTableScanSetup(BitmapHeapScanState *node)
 		 */
 		pstate->tbmiterator = tbm_prepare_shared_iterate(node->tbm);
 
-#ifdef USE_PREFETCH
-		if (node->prefetch_maximum > 0)
-		{
-			pstate->prefetch_iterator =
-				tbm_prepare_shared_iterate(node->tbm);
-		}
-#endif							/* USE_PREFETCH */
-
 		/* We have initialized the shared state so wake up others. */
 		BitmapDoneInitializingSharedState(pstate);
 	}
@@ -121,15 +100,6 @@ BitmapTableScanSetup(BitmapHeapScanState *node)
 									pstate->tbmiterator :
 									InvalidDsaPointer);
 
-#ifdef USE_PREFETCH
-	if (node->prefetch_maximum > 0)
-		node->prefetch_iterator =
-			tbm_begin_iterate(node->tbm, dsa,
-							  pstate ?
-							  pstate->prefetch_iterator :
-							  InvalidDsaPointer);
-#endif							/* USE_PREFETCH */
-
 	/*
 	 * If this is the first scan of the underlying table, create the table
 	 * scan descriptor and begin the scan.
@@ -151,16 +121,16 @@ BitmapTableScanSetup(BitmapHeapScanState *node)
 		node->ss.ss_currentScanDesc =
 			table_beginscan_bm(node->ss.ss_currentRelation,
 							   node->ss.ps.state->es_snapshot,
+							   pstate,
 							   0,
 							   NULL,
 							   need_tuples);
 	}
 
-	node->ss.ss_currentScanDesc->st.rs_tbmiterator = tbmiterator;
+	node->ss.ss_currentScanDesc->st.bitmap.rs_iterator = tbmiterator;
 	node->initialized = true;
 }
 
-
 /* ----------------------------------------------------------------
  *		BitmapHeapNext
  *
@@ -173,7 +143,6 @@ BitmapHeapNext(BitmapHeapScanState *node)
 	ExprContext *econtext;
 	TableScanDesc scan;
 	TupleTableSlot *slot;
-	ParallelBitmapHeapState *pstate = node->pstate;
 
 	/*
 	 * extract necessary information from index scan node
@@ -200,40 +169,8 @@ BitmapHeapNext(BitmapHeapScanState *node)
 			/*
 			 * Continuing in previously obtained page.
 			 */
-
 			CHECK_FOR_INTERRUPTS();
 
-#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 */
-
-			/*
-			 * 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 we are using lossy info, we have to recheck the qual
 			 * conditions at every tuple.
@@ -253,34 +190,17 @@ BitmapHeapNext(BitmapHeapScanState *node)
 			/* OK to return this tuple */
 			return slot;
 		}
-
 new_page:
 
-		BitmapAdjustPrefetchIterator(node);
-
 		/*
 		 * Returns false if the bitmap is exhausted and there are no further
 		 * blocks we need to scan.
 		 */
-		if (!table_scan_bitmap_next_block(scan, &node->blockno,
+		if (!table_scan_bitmap_next_block(scan,
 										  &node->recheck,
 										  &node->stats.lossy_pages,
 										  &node->stats.exact_pages))
 			break;
-
-		/*
-		 * If serial, we can error out if the prefetch block doesn't stay
-		 * ahead of the current block.
-		 */
-		if (node->pstate == NULL &&
-			!tbm_exhausted(&node->prefetch_iterator) &&
-			node->prefetch_blockno < node->blockno)
-			elog(ERROR,
-				 "prefetch and main iterators are out of sync. pfblockno: %d. blockno: %d",
-				 node->prefetch_blockno, node->blockno);
-
-		/* Adjust the prefetch target */
-		BitmapAdjustPrefetchTarget(node);
 	}
 
 	/*
@@ -304,226 +224,6 @@ BitmapDoneInitializingSharedState(ParallelBitmapHeapState *pstate)
 	ConditionVariableBroadcast(&pstate->cv);
 }
 
-/*
- *	BitmapAdjustPrefetchIterator - Adjust the prefetch iterator
- *
- *	We keep track of how far the prefetch iterator is ahead of the main
- *	iterator in prefetch_pages. For each block the main iterator returns, we
- *	decrement prefetch_pages.
- */
-static inline void
-BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
-{
-#ifdef USE_PREFETCH
-	ParallelBitmapHeapState *pstate = node->pstate;
-	TBMIterateResult tbmpre;
-
-	if (pstate == NULL)
-	{
-		TBMIterator *prefetch_iterator = &node->prefetch_iterator;
-
-		if (node->prefetch_pages > 0)
-		{
-			/* The main iterator has closed the distance by one page */
-			node->prefetch_pages--;
-		}
-		else if (!tbm_exhausted(prefetch_iterator))
-		{
-			tbm_iterate(prefetch_iterator, &tbmpre);
-			node->prefetch_blockno = tbmpre.blockno;
-		}
-		return;
-	}
-
-	/*
-	 * XXX: There is a known issue with keeping the prefetch and current block
-	 * iterators in sync for parallel bitmap table scans. This can lead to
-	 * prefetching blocks that have already been read. See the discussion
-	 * here:
-	 * https://postgr.es/m/20240315211449.en2jcmdqxv5o6tlz%40alap3.anarazel.de
-	 * Note that moving the call site of BitmapAdjustPrefetchIterator()
-	 * exacerbates the effects of this bug.
-	 */
-	if (node->prefetch_maximum > 0)
-	{
-		TBMIterator *prefetch_iterator = &node->prefetch_iterator;
-
-		SpinLockAcquire(&pstate->mutex);
-		if (pstate->prefetch_pages > 0)
-		{
-			pstate->prefetch_pages--;
-			SpinLockRelease(&pstate->mutex);
-		}
-		else
-		{
-			/* Release the mutex before iterating */
-			SpinLockRelease(&pstate->mutex);
-
-			/*
-			 * In case of shared mode, we can not ensure that the current
-			 * blockno of the main iterator and that of the prefetch iterator
-			 * are same.  It's possible that whatever blockno we are
-			 * prefetching will be processed by another process.  Therefore,
-			 * we don't validate the blockno here as we do in non-parallel
-			 * case.
-			 */
-			if (!tbm_exhausted(prefetch_iterator))
-			{
-				tbm_iterate(prefetch_iterator, &tbmpre);
-				node->prefetch_blockno = tbmpre.blockno;
-			}
-		}
-	}
-#endif							/* USE_PREFETCH */
-}
-
-/*
- * BitmapAdjustPrefetchTarget - Adjust the prefetch target
- *
- * 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.
- */
-static inline void
-BitmapAdjustPrefetchTarget(BitmapHeapScanState *node)
-{
-#ifdef USE_PREFETCH
-	ParallelBitmapHeapState *pstate = node->pstate;
-
-	if (pstate == NULL)
-	{
-		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++;
-		return;
-	}
-
-	/* Do an unlocked check first to save spinlock acquisitions. */
-	if (pstate->prefetch_target < node->prefetch_maximum)
-	{
-		SpinLockAcquire(&pstate->mutex);
-		if (pstate->prefetch_target >= node->prefetch_maximum)
-			 /* don't increase any further */ ;
-		else if (pstate->prefetch_target >= node->prefetch_maximum / 2)
-			pstate->prefetch_target = node->prefetch_maximum;
-		else if (pstate->prefetch_target > 0)
-			pstate->prefetch_target *= 2;
-		else
-			pstate->prefetch_target++;
-		SpinLockRelease(&pstate->mutex);
-	}
-#endif							/* USE_PREFETCH */
-}
-
-/*
- * BitmapPrefetch - Prefetch, if prefetch_pages are behind prefetch_target
- */
-static inline void
-BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
-{
-#ifdef USE_PREFETCH
-	ParallelBitmapHeapState *pstate = node->pstate;
-
-	if (pstate == NULL)
-	{
-		TBMIterator *prefetch_iterator = &node->prefetch_iterator;
-
-		if (!tbm_exhausted(prefetch_iterator))
-		{
-			while (node->prefetch_pages < node->prefetch_target)
-			{
-				TBMIterateResult tbmpre;
-				bool		skip_fetch;
-
-				tbm_iterate(prefetch_iterator, &tbmpre);
-
-				if (!BlockNumberIsValid(tbmpre.blockno))
-				{
-					/* No more pages to prefetch */
-					tbm_end_iterate(prefetch_iterator);
-					break;
-				}
-				node->prefetch_pages++;
-				node->prefetch_blockno = tbmpre.blockno;
-
-				/*
-				 * 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?)
-				 */
-				skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) &&
-							  !tbmpre.recheck &&
-							  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)
-	{
-		TBMIterator *prefetch_iterator = &node->prefetch_iterator;
-
-		if (!tbm_exhausted(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;
-
-				tbm_iterate(prefetch_iterator, &tbmpre);
-				if (!BlockNumberIsValid(tbmpre.blockno))
-				{
-					/* No more pages to prefetch */
-					tbm_end_iterate(prefetch_iterator);
-					break;
-				}
-
-				node->prefetch_blockno = tbmpre.blockno;
-
-				/* As above, skip prefetch if we expect not to need page */
-				skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) &&
-							  !tbmpre.recheck &&
-							  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 */
-}
-
 /*
  * BitmapHeapRecheck -- access method routine to recheck a tuple in EvalPlanQual
  */
@@ -573,31 +273,19 @@ ExecReScanBitmapHeapScan(BitmapHeapScanState *node)
 		 * End iteration on iterators saved in scan descriptor if they have
 		 * not already been cleaned up.
 		 */
-		if (!tbm_exhausted(&scan->st.rs_tbmiterator))
-			tbm_end_iterate(&scan->st.rs_tbmiterator);
+		if (!tbm_exhausted(&scan->st.bitmap.rs_iterator))
+			tbm_end_iterate(&scan->st.bitmap.rs_iterator);
 
 		/* rescan to release any page pin */
 		table_rescan(node->ss.ss_currentScanDesc, NULL);
 	}
 
-	/* If we did not already clean up the prefetch iterator, do so now. */
-	if (!tbm_exhausted(&node->prefetch_iterator))
-		tbm_end_iterate(&node->prefetch_iterator);
-
 	/* release bitmaps and buffers if any */
 	if (node->tbm)
 		tbm_free(node->tbm);
-	if (node->pvmbuffer != InvalidBuffer)
-		ReleaseBuffer(node->pvmbuffer);
 	node->tbm = NULL;
 	node->initialized = false;
-	node->pvmbuffer = InvalidBuffer;
 	node->recheck = true;
-	/* Only used for serial BHS */
-	node->blockno = InvalidBlockNumber;
-	node->prefetch_blockno = InvalidBlockNumber;
-	node->prefetch_pages = 0;
-	node->prefetch_target = -1;
 
 	ExecScanReScan(&node->ss);
 
@@ -657,8 +345,8 @@ ExecEndBitmapHeapScan(BitmapHeapScanState *node)
 		 * End iteration on iterators saved in scan descriptor if they have
 		 * not already been cleaned up.
 		 */
-		if (!tbm_exhausted(&scanDesc->st.rs_tbmiterator))
-			tbm_end_iterate(&scanDesc->st.rs_tbmiterator);
+		if (!tbm_exhausted(&scanDesc->st.bitmap.rs_iterator))
+			tbm_end_iterate(&scanDesc->st.bitmap.rs_iterator);
 
 		/*
 		 * close table scan
@@ -666,17 +354,11 @@ ExecEndBitmapHeapScan(BitmapHeapScanState *node)
 		table_endscan(scanDesc);
 	}
 
-	/* If we did not already clean up the prefetch iterator, do so now. */
-	if (!tbm_exhausted(&node->prefetch_iterator))
-		tbm_end_iterate(&node->prefetch_iterator);
-
 	/*
 	 * release bitmaps and buffers if any
 	 */
 	if (node->tbm)
 		tbm_free(node->tbm);
-	if (node->pvmbuffer != InvalidBuffer)
-		ReleaseBuffer(node->pvmbuffer);
 }
 
 /* ----------------------------------------------------------------
@@ -709,18 +391,13 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
 	scanstate->ss.ps.ExecProcNode = ExecBitmapHeapScan;
 
 	scanstate->tbm = NULL;
-	scanstate->pvmbuffer = InvalidBuffer;
 
 	/* Zero the statistics counters */
 	memset(&scanstate->stats, 0, sizeof(BitmapHeapScanInstrumentation));
 
-	scanstate->prefetch_pages = 0;
-	scanstate->prefetch_target = -1;
 	scanstate->initialized = false;
 	scanstate->pstate = NULL;
 	scanstate->recheck = true;
-	scanstate->blockno = InvalidBlockNumber;
-	scanstate->prefetch_blockno = InvalidBlockNumber;
 
 	/*
 	 * Miscellaneous initialization
@@ -760,13 +437,6 @@ ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
 	scanstate->bitmapqualorig =
 		ExecInitQual(node->bitmapqualorig, (PlanState *) scanstate);
 
-	/*
-	 * Maximum number of prefetches for the tablespace if configured,
-	 * otherwise the current value of the effective_io_concurrency GUC.
-	 */
-	scanstate->prefetch_maximum =
-		get_tablespace_io_concurrency(currentRelation->rd_rel->reltablespace);
-
 	scanstate->ss.ss_currentRelation = currentRelation;
 
 	/*
@@ -870,12 +540,9 @@ ExecBitmapHeapInitializeDSM(BitmapHeapScanState *node,
 		sinstrument = (SharedBitmapHeapInstrumentation *) ptr;
 
 	pstate->tbmiterator = 0;
-	pstate->prefetch_iterator = 0;
 
 	/* Initialize the mutex */
 	SpinLockInit(&pstate->mutex);
-	pstate->prefetch_pages = 0;
-	pstate->prefetch_target = -1;
 	pstate->state = BM_INITIAL;
 
 	ConditionVariableInit(&pstate->cv);
@@ -912,17 +579,11 @@ ExecBitmapHeapReInitializeDSM(BitmapHeapScanState *node,
 		return;
 
 	pstate->state = BM_INITIAL;
-	pstate->prefetch_pages = 0;
-	pstate->prefetch_target = -1;
 
 	if (DsaPointerIsValid(pstate->tbmiterator))
 		tbm_free_shared_area(dsa, pstate->tbmiterator);
 
-	if (DsaPointerIsValid(pstate->prefetch_iterator))
-		tbm_free_shared_area(dsa, pstate->prefetch_iterator);
-
 	pstate->tbmiterator = InvalidDsaPointer;
-	pstate->prefetch_iterator = InvalidDsaPointer;
 }
 
 /* ----------------------------------------------------------------
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index dc6e0184284..934b667ad78 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -43,8 +43,12 @@ typedef struct TableScanDescData
 	 */
 	union
 	{
-		/* Iterator for Bitmap Table Scans */
-		TBMIterator rs_tbmiterator;
+		/* State for Bitmap Table Scans */
+		struct
+		{
+			struct ParallelBitmapHeapState *rs_pstate;
+			TBMIterator rs_iterator;
+		}			bitmap;
 
 		/*
 		 * Range of ItemPointers for table_scan_getnextslot_tidrange() to
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 09b9b394e0e..6a8ba3b8657 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -796,28 +796,12 @@ typedef struct TableAmRoutine
 	 * always need to be rechecked, but some non-lossy pages' tuples may also
 	 * require recheck.
 	 *
-	 * `blockno` is the current block and is set by the table AM. The table AM
-	 * is responsible for advancing the main iterator, but the bitmap table
-	 * scan code still advances the prefetch iterator. `blockno` is used by
-	 * bitmap table scan code to validate that the prefetch block stays ahead
-	 * of the current block.
-	 *
-	 * XXX: Currently this may only be implemented if the AM uses md.c as its
-	 * storage manager, and uses ItemPointer->ip_blkid in a manner that maps
-	 * blockids directly to the underlying storage. nodeBitmapHeapscan.c
-	 * performs prefetching directly using that interface.  This probably
-	 * needs to be rectified at a later point.
-	 *
-	 * XXX: Currently this may only be implemented if the AM uses the
-	 * visibilitymap, as nodeBitmapHeapscan.c unconditionally accesses it to
-	 * perform prefetching.  This probably needs to be rectified at a later
-	 * point.
+	 * Prefetching additional data from the bitmap is left to the table AM.
 	 *
 	 * Optional callback, but either both scan_bitmap_next_block and
 	 * scan_bitmap_next_tuple need to exist, or neither.
 	 */
 	bool		(*scan_bitmap_next_block) (TableScanDesc scan,
-										   BlockNumber *blockno,
 										   bool *recheck,
 										   uint64 *lossy_pages,
 										   uint64 *exact_pages);
@@ -955,15 +939,19 @@ table_beginscan_strat(Relation rel, Snapshot snapshot,
  */
 static inline TableScanDesc
 table_beginscan_bm(Relation rel, Snapshot snapshot,
+				   struct ParallelBitmapHeapState *pstate,
 				   int nkeys, struct ScanKeyData *key, bool need_tuple)
 {
+	TableScanDesc result;
 	uint32		flags = SO_TYPE_BITMAPSCAN | SO_ALLOW_PAGEMODE;
 
 	if (need_tuple)
 		flags |= SO_NEED_TUPLES;
 
-	return rel->rd_tableam->scan_begin(rel, snapshot, nkeys, key,
-									   NULL, flags);
+	result = rel->rd_tableam->scan_begin(rel, snapshot, nkeys,
+										 key, NULL, flags);
+	result->st.bitmap.rs_pstate = pstate;
+	return result;
 }
 
 /*
@@ -1965,16 +1953,11 @@ table_relation_estimate_size(Relation rel, int32 *attr_widths,
  * `recheck` is set by the table AM to indicate whether or not the tuples
  * from this block should be rechecked.
  *
- * `blockno` is the current block and is set by the table AM and is used by
- * bitmap table scan code to validate that the prefetch block stays ahead of
- * the current block.
- *
  * Note, this is an optionally implemented function, therefore should only be
  * used after verifying the presence (at plan time or such).
  */
 static inline bool
 table_scan_bitmap_next_block(TableScanDesc scan,
-							 BlockNumber *blockno,
 							 bool *recheck,
 							 uint64 *lossy_pages,
 							 uint64 *exact_pages)
@@ -1988,7 +1971,7 @@ table_scan_bitmap_next_block(TableScanDesc scan,
 		elog(ERROR, "unexpected table_scan_bitmap_next_block call during logical decoding");
 
 	return scan->rs_rd->rd_tableam->scan_bitmap_next_block(scan,
-														   blockno, recheck,
+														   recheck,
 														   lossy_pages,
 														   exact_pages);
 }
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index d0f2dca5928..3000a1ce756 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -1807,11 +1807,7 @@ typedef enum
 /* ----------------
  *	 ParallelBitmapHeapState information
  *		tbmiterator				iterator for scanning current pages
- *		prefetch_iterator		iterator for prefetching ahead of current page
- *		mutex					mutual exclusion for the prefetching variable
- *								and state
- *		prefetch_pages			# pages prefetch iterator is ahead of current
- *		prefetch_target			current target prefetch distance
+ *		mutex					mutual exclusion for state
  *		state					current state of the TIDBitmap
  *		cv						conditional wait variable
  * ----------------
@@ -1819,10 +1815,7 @@ typedef enum
 typedef struct ParallelBitmapHeapState
 {
 	dsa_pointer tbmiterator;
-	dsa_pointer prefetch_iterator;
 	slock_t		mutex;
-	int			prefetch_pages;
-	int			prefetch_target;
 	SharedBitmapState state;
 	ConditionVariable cv;
 } ParallelBitmapHeapState;
@@ -1846,18 +1839,11 @@ typedef struct SharedBitmapHeapInstrumentation
  *
  *		bitmapqualorig	   execution state for bitmapqualorig expressions
  *		tbm				   bitmap obtained from child index scan(s)
- *		pvmbuffer		   buffer for visibility-map lookups of prefetched pages
  *		stats			   execution statistics
- *		prefetch_iterator  iterator for prefetching ahead of current page
- *		prefetch_pages	   # pages prefetch iterator is ahead of current
- *		prefetch_target    current target prefetch distance
- *		prefetch_maximum   maximum value for prefetch_target
  *		initialized		   is node is ready to iterate
  *		pstate			   shared state for parallel bitmap scan
  *		sinstrument		   statistics for parallel workers
  *		recheck			   do current page's tuples need recheck
- *		blockno			   used to validate pf and current block stay in sync
- *		prefetch_blockno   used to validate pf stays ahead of current block
  * ----------------
  */
 typedef struct BitmapHeapScanState
@@ -1865,18 +1851,11 @@ typedef struct BitmapHeapScanState
 	ScanState	ss;				/* its first field is NodeTag */
 	ExprState  *bitmapqualorig;
 	TIDBitmap  *tbm;
-	Buffer		pvmbuffer;
 	BitmapHeapScanInstrumentation stats;
-	TBMIterator prefetch_iterator;
-	int			prefetch_pages;
-	int			prefetch_target;
-	int			prefetch_maximum;
 	bool		initialized;
 	ParallelBitmapHeapState *pstate;
 	SharedBitmapHeapInstrumentation *sinstrument;
 	bool		recheck;
-	BlockNumber blockno;
-	BlockNumber prefetch_blockno;
 } BitmapHeapScanState;
 
 /* ----------------
-- 
2.34.1

From cadf9b662830ac19e71b40a9a8689feee83178a2 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Fri, 17 Jan 2025 17:20:28 -0500
Subject: [PATCH v26 3/5] Separate TBM[Shared|Private]Iterator and
 TBMIterateResult

Remove the TBMIterateResult member from the TBMPrivateIterator and
TBMSharedIterator and make tbm_[shared|private_]iterate() take a
TBMIterateResult as a parameter.

This will allow multiple TBMIterateResults to exist concurrently,
allowing asynchronous use of the TIDBitmap for prefetching.

tbm_[shared|private]_iterate() now sets blockno to InvalidBlockNumber
when the bitmap is exhausted instead of returning NULL.

BitmapHeapScan callers of tbm_iterate make a TBMIterateResult locally
and pass it in.

Because GIN only needs a single TBMIterateResult, we inline the
matchResult in the GinScanEntry to avoid having to separately manage
memory for the TBMIterateResult.
---
 src/backend/access/gin/ginget.c           | 51 +++++++++------
 src/backend/access/gin/ginscan.c          |  2 +-
 src/backend/access/heap/heapam_handler.c  | 30 ++++-----
 src/backend/executor/nodeBitmapHeapscan.c | 40 ++++++------
 src/backend/nodes/tidbitmap.c             | 79 +++++++++++------------
 src/include/access/gin_private.h          |  2 +-
 src/include/nodes/tidbitmap.h             |  6 +-
 7 files changed, 111 insertions(+), 99 deletions(-)

diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 330805626ee..7cf3dd2a4b9 100644
--- a/src/backend/access/gin/ginget.c
+++ b/src/backend/access/gin/ginget.c
@@ -332,10 +332,22 @@ restartScanEntry:
 	entry->list = NULL;
 	entry->nlist = 0;
 	entry->matchBitmap = NULL;
-	entry->matchResult = NULL;
 	entry->reduceResult = false;
 	entry->predictNumberResult = 0;
 
+	/*
+	 * MTODO: is it enough to set blockno to InvalidBlockNumber? In all the
+	 * places were we previously set matchResult to NULL, I just set blockno
+	 * to InvalidBlockNumber. It seems like this should be okay because that
+	 * is usually what we check before using the matchResult members. But it
+	 * might be safer to zero out the offsets array. But that is expensive.
+	 */
+	entry->matchResult.blockno = InvalidBlockNumber;
+	entry->matchResult.ntuples = 0;
+	entry->matchResult.recheck = true;
+	memset(entry->matchResult.offsets, 0,
+		   sizeof(OffsetNumber) * MaxHeapTuplesPerPage);
+
 	/*
 	 * we should find entry, and begin scan of posting tree or just store
 	 * posting list in memory
@@ -374,6 +386,7 @@ restartScanEntry:
 			{
 				if (entry->matchIterator)
 					tbm_end_private_iterate(entry->matchIterator);
+				entry->matchResult.blockno = InvalidBlockNumber;
 				entry->matchIterator = NULL;
 				tbm_free(entry->matchBitmap);
 				entry->matchBitmap = NULL;
@@ -824,19 +837,19 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
 		{
 			/*
 			 * If we've exhausted all items on this block, move to next block
-			 * in the bitmap.
+			 * in the bitmap. tbm_private_iterate() sets matchResult->blockno
+			 * to InvalidBlockNumber when the bitmap is exhausted.
 			 */
-			while (entry->matchResult == NULL ||
-				   (entry->matchResult->ntuples >= 0 &&
-					entry->offset >= entry->matchResult->ntuples) ||
-				   entry->matchResult->blockno < advancePastBlk ||
+			while ((!BlockNumberIsValid(entry->matchResult.blockno)) ||
+				   (entry->matchResult.ntuples >= 0 &&
+					entry->offset >= entry->matchResult.ntuples) ||
+				   entry->matchResult.blockno < advancePastBlk ||
 				   (ItemPointerIsLossyPage(&advancePast) &&
-					entry->matchResult->blockno == advancePastBlk))
+					entry->matchResult.blockno == advancePastBlk))
 			{
-				entry->matchResult =
-					tbm_private_iterate(entry->matchIterator);
+				tbm_private_iterate(entry->matchIterator, &entry->matchResult);
 
-				if (entry->matchResult == NULL)
+				if (!BlockNumberIsValid(entry->matchResult.blockno))
 				{
 					ItemPointerSetInvalid(&entry->curItem);
 					tbm_end_private_iterate(entry->matchIterator);
@@ -847,7 +860,7 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
 
 				/*
 				 * Reset counter to the beginning of entry->matchResult. Note:
-				 * entry->offset is still greater than matchResult->ntuples if
+				 * entry->offset is still greater than matchResult.ntuples if
 				 * matchResult is lossy.  So, on next call we will get next
 				 * result from TIDBitmap.
 				 */
@@ -860,10 +873,10 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
 			 * We're now on the first page after advancePast which has any
 			 * items on it. If it's a lossy result, return that.
 			 */
-			if (entry->matchResult->ntuples < 0)
+			if (entry->matchResult.ntuples < 0)
 			{
 				ItemPointerSetLossyPage(&entry->curItem,
-										entry->matchResult->blockno);
+										entry->matchResult.blockno);
 
 				/*
 				 * We might as well fall out of the loop; we could not
@@ -877,27 +890,27 @@ entryGetItem(GinState *ginstate, GinScanEntry entry,
 			 * Not a lossy page. Skip over any offsets <= advancePast, and
 			 * return that.
 			 */
-			if (entry->matchResult->blockno == advancePastBlk)
+			if (entry->matchResult.blockno == advancePastBlk)
 			{
 				/*
 				 * First, do a quick check against the last offset on the
 				 * page. If that's > advancePast, so are all the other
 				 * offsets, so just go back to the top to get the next page.
 				 */
-				if (entry->matchResult->offsets[entry->matchResult->ntuples - 1] <= advancePastOff)
+				if (entry->matchResult.offsets[entry->matchResult.ntuples - 1] <= advancePastOff)
 				{
-					entry->offset = entry->matchResult->ntuples;
+					entry->offset = entry->matchResult.ntuples;
 					continue;
 				}
 
 				/* Otherwise scan to find the first item > advancePast */
-				while (entry->matchResult->offsets[entry->offset] <= advancePastOff)
+				while (entry->matchResult.offsets[entry->offset] <= advancePastOff)
 					entry->offset++;
 			}
 
 			ItemPointerSet(&entry->curItem,
-						   entry->matchResult->blockno,
-						   entry->matchResult->offsets[entry->offset]);
+						   entry->matchResult.blockno,
+						   entry->matchResult.offsets[entry->offset]);
 			entry->offset++;
 
 			/* Done unless we need to reduce the result */
diff --git a/src/backend/access/gin/ginscan.c b/src/backend/access/gin/ginscan.c
index 7d1e6615260..625140fdf25 100644
--- a/src/backend/access/gin/ginscan.c
+++ b/src/backend/access/gin/ginscan.c
@@ -106,7 +106,7 @@ ginFillScanEntry(GinScanOpaque so, OffsetNumber attnum,
 	ItemPointerSetMin(&scanEntry->curItem);
 	scanEntry->matchBitmap = NULL;
 	scanEntry->matchIterator = NULL;
-	scanEntry->matchResult = NULL;
+	scanEntry->matchResult.blockno = InvalidBlockNumber;
 	scanEntry->list = NULL;
 	scanEntry->nlist = 0;
 	scanEntry->offset = InvalidOffsetNumber;
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index a4003cf59e1..bd567760f2d 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2124,7 +2124,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	Buffer		buffer;
 	Snapshot	snapshot;
 	int			ntup;
-	TBMIterateResult *tbmres;
+	TBMIterateResult tbmres;
 
 	Assert(scan->rs_flags & SO_TYPE_BITMAPSCAN);
 
@@ -2138,9 +2138,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	{
 		CHECK_FOR_INTERRUPTS();
 
-		tbmres = tbm_iterate(&scan->st.rs_tbmiterator);
+		tbm_iterate(&scan->st.rs_tbmiterator, &tbmres);
 
-		if (tbmres == NULL)
+		if (!BlockNumberIsValid(tbmres.blockno))
 			return false;
 
 		/*
@@ -2152,11 +2152,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 		 * reachable by the index.
 		 */
 	} while (!IsolationIsSerializable() &&
-			 tbmres->blockno >= hscan->rs_nblocks);
+			 tbmres.blockno >= hscan->rs_nblocks);
 
 	/* Got a valid block */
-	*blockno = tbmres->blockno;
-	*recheck = tbmres->recheck;
+	*blockno = tbmres.blockno;
+	*recheck = tbmres.recheck;
 
 	/*
 	 * We can skip fetching the heap page if we don't need any fields from the
@@ -2164,19 +2164,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	 * page are visible to our transaction.
 	 */
 	if (!(scan->rs_flags & SO_NEED_TUPLES) &&
-		!tbmres->recheck &&
-		VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &bscan->rs_vmbuffer))
+		!tbmres.recheck &&
+		VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &bscan->rs_vmbuffer))
 	{
 		/* can't be lossy in the skip_fetch case */
-		Assert(tbmres->ntuples >= 0);
+		Assert(tbmres.ntuples >= 0);
 		Assert(bscan->rs_empty_tuples_pending >= 0);
 
-		bscan->rs_empty_tuples_pending += tbmres->ntuples;
+		bscan->rs_empty_tuples_pending += tbmres.ntuples;
 
 		return true;
 	}
 
-	block = tbmres->blockno;
+	block = tbmres.blockno;
 
 	/*
 	 * Acquire pin on the target heap page, trading in any pin we held before.
@@ -2205,7 +2205,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	/*
 	 * We need two separate strategies for lossy and non-lossy cases.
 	 */
-	if (tbmres->ntuples >= 0)
+	if (tbmres.ntuples >= 0)
 	{
 		/*
 		 * Bitmap is non-lossy, so we just look through the offsets listed in
@@ -2214,9 +2214,9 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 		 */
 		int			curslot;
 
-		for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+		for (curslot = 0; curslot < tbmres.ntuples; curslot++)
 		{
-			OffsetNumber offnum = tbmres->offsets[curslot];
+			OffsetNumber offnum = tbmres.offsets[curslot];
 			ItemPointerData tid;
 			HeapTupleData heapTuple;
 
@@ -2266,7 +2266,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	Assert(ntup <= MaxHeapTuplesPerPage);
 	hscan->rs_ntuples = ntup;
 
-	if (tbmres->ntuples >= 0)
+	if (tbmres.ntuples >= 0)
 		(*exact_pages)++;
 	else
 		(*lossy_pages)++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 92a199c1e87..da3c76f4744 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -316,7 +316,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
 {
 #ifdef USE_PREFETCH
 	ParallelBitmapHeapState *pstate = node->pstate;
-	TBMIterateResult *tbmpre;
+	TBMIterateResult tbmpre;
 
 	if (pstate == NULL)
 	{
@@ -329,9 +329,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
 		}
 		else if (!tbm_exhausted(prefetch_iterator))
 		{
-			tbmpre = tbm_iterate(prefetch_iterator);
-			node->prefetch_blockno = tbmpre ? tbmpre->blockno :
-				InvalidBlockNumber;
+			tbm_iterate(prefetch_iterator, &tbmpre);
+			node->prefetch_blockno = tbmpre.blockno;
 		}
 		return;
 	}
@@ -370,9 +369,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node)
 			 */
 			if (!tbm_exhausted(prefetch_iterator))
 			{
-				tbmpre = tbm_iterate(prefetch_iterator);
-				node->prefetch_blockno = tbmpre ? tbmpre->blockno :
-					InvalidBlockNumber;
+				tbm_iterate(prefetch_iterator, &tbmpre);
+				node->prefetch_blockno = tbmpre.blockno;
 			}
 		}
 	}
@@ -440,17 +438,19 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 		{
 			while (node->prefetch_pages < node->prefetch_target)
 			{
-				TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+				TBMIterateResult tbmpre;
 				bool		skip_fetch;
 
-				if (tbmpre == NULL)
+				tbm_iterate(prefetch_iterator, &tbmpre);
+
+				if (!BlockNumberIsValid(tbmpre.blockno))
 				{
 					/* No more pages to prefetch */
 					tbm_end_iterate(prefetch_iterator);
 					break;
 				}
 				node->prefetch_pages++;
-				node->prefetch_blockno = tbmpre->blockno;
+				node->prefetch_blockno = tbmpre.blockno;
 
 				/*
 				 * If we expect not to have to actually read this heap page,
@@ -459,13 +459,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 				 * prefetch_pages?)
 				 */
 				skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) &&
-							  !tbmpre->recheck &&
+							  !tbmpre.recheck &&
 							  VM_ALL_VISIBLE(node->ss.ss_currentRelation,
-											 tbmpre->blockno,
+											 tbmpre.blockno,
 											 &node->pvmbuffer));
 
 				if (!skip_fetch)
-					PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+					PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
 			}
 		}
 
@@ -480,7 +480,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 		{
 			while (1)
 			{
-				TBMIterateResult *tbmpre;
+				TBMIterateResult tbmpre;
 				bool		do_prefetch = false;
 				bool		skip_fetch;
 
@@ -499,25 +499,25 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 				if (!do_prefetch)
 					return;
 
-				tbmpre = tbm_iterate(prefetch_iterator);
-				if (tbmpre == NULL)
+				tbm_iterate(prefetch_iterator, &tbmpre);
+				if (!BlockNumberIsValid(tbmpre.blockno))
 				{
 					/* No more pages to prefetch */
 					tbm_end_iterate(prefetch_iterator);
 					break;
 				}
 
-				node->prefetch_blockno = tbmpre->blockno;
+				node->prefetch_blockno = tbmpre.blockno;
 
 				/* As above, skip prefetch if we expect not to need page */
 				skip_fetch = (!(scan->rs_flags & SO_NEED_TUPLES) &&
-							  !tbmpre->recheck &&
+							  !tbmpre.recheck &&
 							  VM_ALL_VISIBLE(node->ss.ss_currentRelation,
-											 tbmpre->blockno,
+											 tbmpre.blockno,
 											 &node->pvmbuffer));
 
 				if (!skip_fetch)
-					PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre->blockno);
+					PrefetchBuffer(scan->rs_rd, MAIN_FORKNUM, tbmpre.blockno);
 			}
 		}
 	}
diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index 3d38cc04cc5..40d7b9f7505 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -172,7 +172,6 @@ struct TBMPrivateIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;
 };
 
 /*
@@ -213,7 +212,6 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -948,20 +946,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
 /*
  * tbm_private_iterate - scan through next page of a TIDBitmap
  *
- * Returns a TBMIterateResult representing one page, or NULL if there are
- * no more pages to scan.  Pages are guaranteed to be delivered in numerical
- * order.  If result->ntuples < 0, then the bitmap is "lossy" and failed to
- * remember the exact tuples to look at on this page --- the caller must
- * examine all tuples on the page and check if they meet the intended
- * condition.  If result->recheck is true, only the indicated tuples need
- * be examined, but the condition must be rechecked anyway.  (For ease of
- * testing, recheck is always set true when ntuples < 0.)
+ * Caller must pass in a TBMIterateResult to be filled.
+ *
+ * Pages are guaranteed to be delivered in numerical order.  tbmres->blockno is
+ * set to InvalidBlockNumber when there are no more pages to scan. If
+ * tbmres->ntuples < 0, then the bitmap is "lossy" and failed to remember the
+ * exact tuples to look at on this page --- the caller must examine all tuples
+ * on the page and check if they meet the intended condition.  If
+ * tbmres->recheck is true, only the indicated tuples need be examined, but the
+ * condition must be rechecked anyway.  (For ease of testing, recheck is always
+ * set true when ntuples < 0.)
  */
-TBMIterateResult *
-tbm_private_iterate(TBMPrivateIterator *iterator)
+void
+tbm_private_iterate(TBMPrivateIterator *iterator, TBMIterateResult *tbmres)
 {
 	TIDBitmap  *tbm = iterator->tbm;
-	TBMIterateResult *output = &(iterator->output);
 
 	Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
 
@@ -999,11 +998,11 @@ tbm_private_iterate(TBMPrivateIterator *iterator)
 			chunk_blockno < tbm->spages[iterator->spageptr]->blockno)
 		{
 			/* Return a lossy page indicator from the chunk */
-			output->blockno = chunk_blockno;
-			output->ntuples = -1;
-			output->recheck = true;
+			tbmres->blockno = chunk_blockno;
+			tbmres->ntuples = -1;
+			tbmres->recheck = true;
 			iterator->schunkbit++;
-			return output;
+			return;
 		}
 	}
 
@@ -1019,16 +1018,16 @@ tbm_private_iterate(TBMPrivateIterator *iterator)
 			page = tbm->spages[iterator->spageptr];
 
 		/* scan bitmap to extract individual offset numbers */
-		ntuples = tbm_extract_page_tuple(page, output);
-		output->blockno = page->blockno;
-		output->ntuples = ntuples;
-		output->recheck = page->recheck;
+		ntuples = tbm_extract_page_tuple(page, tbmres);
+		tbmres->blockno = page->blockno;
+		tbmres->ntuples = ntuples;
+		tbmres->recheck = page->recheck;
 		iterator->spageptr++;
-		return output;
+		return;
 	}
 
 	/* Nothing more in the bitmap */
-	return NULL;
+	tbmres->blockno = InvalidBlockNumber;
 }
 
 /*
@@ -1038,10 +1037,9 @@ tbm_private_iterate(TBMPrivateIterator *iterator)
  *	across multiple processes.  We need to acquire the iterator LWLock,
  *	before accessing the shared members.
  */
-TBMIterateResult *
-tbm_shared_iterate(TBMSharedIterator *iterator)
+void
+tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres)
 {
-	TBMIterateResult *output = &iterator->output;
 	TBMSharedIteratorState *istate = iterator->state;
 	PagetableEntry *ptbase = NULL;
 	int		   *idxpages = NULL;
@@ -1092,13 +1090,13 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
 			chunk_blockno < ptbase[idxpages[istate->spageptr]].blockno)
 		{
 			/* Return a lossy page indicator from the chunk */
-			output->blockno = chunk_blockno;
-			output->ntuples = -1;
-			output->recheck = true;
+			tbmres->blockno = chunk_blockno;
+			tbmres->ntuples = -1;
+			tbmres->recheck = true;
 			istate->schunkbit++;
 
 			LWLockRelease(&istate->lock);
-			return output;
+			return;
 		}
 	}
 
@@ -1108,21 +1106,21 @@ tbm_shared_iterate(TBMSharedIterator *iterator)
 		int			ntuples;
 
 		/* scan bitmap to extract individual offset numbers */
-		ntuples = tbm_extract_page_tuple(page, output);
-		output->blockno = page->blockno;
-		output->ntuples = ntuples;
-		output->recheck = page->recheck;
+		ntuples = tbm_extract_page_tuple(page, tbmres);
+		tbmres->blockno = page->blockno;
+		tbmres->ntuples = ntuples;
+		tbmres->recheck = page->recheck;
 		istate->spageptr++;
 
 		LWLockRelease(&istate->lock);
 
-		return output;
+		return;
 	}
 
 	LWLockRelease(&istate->lock);
 
 	/* Nothing more in the bitmap */
-	return NULL;
+	tbmres->blockno = InvalidBlockNumber;
 }
 
 /*
@@ -1598,13 +1596,14 @@ tbm_end_iterate(TBMIterator *iterator)
 /*
  * Get the next TBMIterateResult from the shared or private bitmap iterator.
  */
-TBMIterateResult *
-tbm_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
 {
 	Assert(iterator);
+	Assert(tbmres);
 
 	if (iterator->shared)
-		return tbm_shared_iterate(iterator->i.shared_iterator);
+		return tbm_shared_iterate(iterator->i.shared_iterator, tbmres);
 	else
-		return tbm_private_iterate(iterator->i.private_iterator);
+		return tbm_private_iterate(iterator->i.private_iterator, tbmres);
 }
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index dcd1ae3fc34..a7071c4cbdc 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -353,7 +353,7 @@ typedef struct GinScanEntryData
 	/* for a partial-match or full-scan query, we accumulate all TIDs here */
 	TIDBitmap  *matchBitmap;
 	TBMPrivateIterator *matchIterator;
-	TBMIterateResult *matchResult;
+	TBMIterateResult matchResult;
 
 	/* used for Posting list and one page in Posting tree */
 	ItemPointerData *list;
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index b2e322508a2..f3956d5171e 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -86,8 +86,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
 
 extern TBMPrivateIterator *tbm_begin_private_iterate(TIDBitmap *tbm);
 extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_private_iterate(TBMPrivateIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_private_iterate(TBMPrivateIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
 extern void tbm_end_private_iterate(TBMPrivateIterator *iterator);
 extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
 extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
@@ -98,7 +98,7 @@ extern TBMIterator tbm_begin_iterate(TIDBitmap *tbm,
 									 dsa_area *dsa, dsa_pointer dsp);
 extern void tbm_end_iterate(TBMIterator *iterator);
 
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
 
 static inline bool
 tbm_exhausted(TBMIterator *iterator)
-- 
2.34.1

From 9fa10cd0ee89626e048adb4ce0c8d25a309a2d11 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Fri, 17 Jan 2025 16:42:25 -0500
Subject: [PATCH v26 2/5] Hard-code TBMIterateResult offsets array size

TIDBitmap's TBMIterateResult had a flexible sized array of tuple offsets
but the API always allocated MaxHeapTuplesPerPage OffsetNumbers.
Creating a fixed-size aray of size MaxHeapTuplesPerPage is more clear
for the API user.
---
 src/backend/nodes/tidbitmap.c | 26 +++++++-------------------
 src/include/nodes/tidbitmap.h | 12 ++++++++++--
 2 files changed, 17 insertions(+), 21 deletions(-)

diff --git a/src/backend/nodes/tidbitmap.c b/src/backend/nodes/tidbitmap.c
index af6ac64b3fc..3d38cc04cc5 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -40,7 +40,6 @@
 
 #include <limits.h>
 
-#include "access/htup_details.h"
 #include "common/hashfn.h"
 #include "common/int.h"
 #include "nodes/bitmapset.h"
@@ -48,14 +47,6 @@
 #include "storage/lwlock.h"
 #include "utils/dsa.h"
 
-/*
- * The maximum number of tuples per page is not large (typically 256 with
- * 8K pages, or 1024 with 32K pages).  So there's not much point in making
- * the per-page bitmaps variable size.  We just legislate that the size
- * is this:
- */
-#define MAX_TUPLES_PER_PAGE  MaxHeapTuplesPerPage
-
 /*
  * When we have to switch over to lossy storage, we use a data structure
  * with one bit per page, where all pages having the same number DIV
@@ -67,7 +58,7 @@
  * table, using identical data structures.  (This is because the memory
  * management for hashtables doesn't easily/efficiently allow space to be
  * transferred easily from one hashtable to another.)  Therefore it's best
- * if PAGES_PER_CHUNK is the same as MAX_TUPLES_PER_PAGE, or at least not
+ * if PAGES_PER_CHUNK is the same as MaxHeapTuplesPerPage, or at least not
  * too different.  But we also want PAGES_PER_CHUNK to be a power of 2 to
  * avoid expensive integer remainder operations.  So, define it like this:
  */
@@ -79,7 +70,7 @@
 #define BITNUM(x)	((x) % BITS_PER_BITMAPWORD)
 
 /* number of active words for an exact page: */
-#define WORDS_PER_PAGE	((MAX_TUPLES_PER_PAGE - 1) / BITS_PER_BITMAPWORD + 1)
+#define WORDS_PER_PAGE	((MaxHeapTuplesPerPage - 1) / BITS_PER_BITMAPWORD + 1)
 /* number of active words for a lossy chunk: */
 #define WORDS_PER_CHUNK  ((PAGES_PER_CHUNK - 1) / BITS_PER_BITMAPWORD + 1)
 
@@ -181,7 +172,7 @@ struct TBMPrivateIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /*
@@ -222,7 +213,7 @@ struct TBMSharedIterator
 	PTEntryArray *ptbase;		/* pagetable element array */
 	PTIterationArray *ptpages;	/* sorted exact page index list */
 	PTIterationArray *ptchunks; /* sorted lossy page index list */
-	TBMIterateResult output;	/* MUST BE LAST (because variable-size) */
+	TBMIterateResult output;
 };
 
 /* Local function prototypes */
@@ -390,7 +381,7 @@ tbm_add_tuples(TIDBitmap *tbm, const ItemPointer tids, int ntids,
 					bitnum;
 
 		/* safety check to ensure we don't overrun bit array bounds */
-		if (off < 1 || off > MAX_TUPLES_PER_PAGE)
+		if (off < 1 || off > MaxHeapTuplesPerPage)
 			elog(ERROR, "tuple offset out of range: %u", off);
 
 		/*
@@ -696,9 +687,7 @@ tbm_begin_private_iterate(TIDBitmap *tbm)
 	 * Create the TBMPrivateIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMPrivateIterator *) palloc(sizeof(TBMPrivateIterator) +
-											 MAX_TUPLES_PER_PAGE *
-											 sizeof(OffsetNumber));
+	iterator = (TBMPrivateIterator *) palloc(sizeof(TBMPrivateIterator));
 	iterator->tbm = tbm;
 
 	/*
@@ -1468,8 +1457,7 @@ tbm_attach_shared_iterate(dsa_area *dsa, dsa_pointer dp)
 	 * Create the TBMSharedIterator struct, with enough trailing space to
 	 * serve the needs of the TBMIterateResult sub-struct.
 	 */
-	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator) +
-											 MAX_TUPLES_PER_PAGE * sizeof(OffsetNumber));
+	iterator = (TBMSharedIterator *) palloc0(sizeof(TBMSharedIterator));
 
 	istate = (TBMSharedIteratorState *) dsa_get_address(dsa, dp);
 
diff --git a/src/include/nodes/tidbitmap.h b/src/include/nodes/tidbitmap.h
index fedbf69eb53..b2e322508a2 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -22,6 +22,7 @@
 #ifndef TIDBITMAP_H
 #define TIDBITMAP_H
 
+#include "access/htup_details.h"
 #include "storage/itemptr.h"
 #include "utils/dsa.h"
 
@@ -55,9 +56,16 @@ typedef struct TBMIterateResult
 {
 	BlockNumber blockno;		/* page number containing tuples */
 	int			ntuples;		/* -1 indicates lossy result */
-	bool		recheck;		/* should the tuples be rechecked? */
 	/* Note: recheck is always true if ntuples < 0 */
-	OffsetNumber offsets[FLEXIBLE_ARRAY_MEMBER];
+	bool		recheck;		/* should the tuples be rechecked? */
+
+	/*
+	 * The maximum number of tuples per page is not large (typically 256 with
+	 * 8K pages, or 1024 with 32K pages).  So there's not much point in making
+	 * the per-page bitmaps variable size.  We just legislate that the size is
+	 * this:
+	 */
+	OffsetNumber offsets[MaxHeapTuplesPerPage];
 } TBMIterateResult;
 
 /* function prototypes in nodes/tidbitmap.c */
-- 
2.34.1

From ad5a7de323d3bea2509dce52c37415cc22be7281 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplage...@gmail.com>
Date: Wed, 22 Jan 2025 15:35:17 -0500
Subject: [PATCH v26 5/5] Remove table AM callback scan_bitmap_next_block

After pushing the bitmap iterator usage into table-AM specific code (as
part of making bitmap heap scan use the read stream API),
scan_bitmap_next_block() no longer set the current blockno.

BitmapHeapNext() doesn't use the block number for anything, so there is
no reason to have a separte scan_bitmap_next_block() callback.

Now, bitmap table scan code only calls table_scan_bitmap_next_tuple().

The heap AM implementation of scan_bitmap_next_block() is now a local
helper in heapam_handler.c.
---
 src/backend/access/heap/heapam_handler.c  | 354 ++++++++++++----------
 src/backend/access/table/tableamapi.c     |   2 -
 src/backend/executor/nodeBitmapHeapscan.c |  71 ++---
 src/backend/optimizer/util/plancat.c      |   2 +-
 src/include/access/tableam.h              |  90 ++----
 5 files changed, 235 insertions(+), 284 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index eac51f5eb51..f449272a2ea 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -56,6 +56,11 @@ static bool SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 
 static BlockNumber heapam_scan_get_blocks_done(HeapScanDesc hscan);
 
+static bool BitmapHeapScanNextBlock(TableScanDesc scan,
+									bool *recheck,
+									uint64 *lossy_pages, uint64 *exact_pages);
+
+
 
 /* ------------------------------------------------------------------------
  * Slot related callbacks for heap AM
@@ -2114,189 +2119,44 @@ heapam_estimate_rel_size(Relation rel, int32 *attr_widths,
  */
 
 static bool
-heapam_scan_bitmap_next_block(TableScanDesc scan,
+heapam_scan_bitmap_next_tuple(TableScanDesc scan,
+							  TupleTableSlot *slot,
 							  bool *recheck,
-							  uint64 *lossy_pages, uint64 *exact_pages)
+							  uint64 *lossy_pages,
+							  uint64 *exact_pages)
 {
 	BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) scan;
 	HeapScanDesc hscan = (HeapScanDesc) bscan;
-	BlockNumber block;
-	void	   *per_buffer_data;
-	Buffer		buffer;
-	Snapshot	snapshot;
-	int			ntup;
-	TBMIterateResult *tbmres;
-
-	Assert(scan->rs_flags & SO_TYPE_BITMAPSCAN);
-	Assert(hscan->rs_read_stream);
-
-	hscan->rs_cindex = 0;
-	hscan->rs_ntuples = 0;
-
-	/* Release buffer containing previous block. */
-	if (BufferIsValid(hscan->rs_cbuf))
-	{
-		ReleaseBuffer(hscan->rs_cbuf);
-		hscan->rs_cbuf = InvalidBuffer;
-	}
-
-	hscan->rs_cbuf = read_stream_next_buffer(hscan->rs_read_stream, &per_buffer_data);
-
-	if (BufferIsInvalid(hscan->rs_cbuf))
-	{
-		if (BufferIsValid(bscan->rs_vmbuffer))
-		{
-			ReleaseBuffer(bscan->rs_vmbuffer);
-			bscan->rs_vmbuffer = InvalidBuffer;
-		}
-
-		/*
-		 * Bitmap is exhausted. Time to emit empty tuples if relevant. We emit
-		 * all empty tuples at the end instead of emitting them per block we
-		 * skip fetching. This is necessary because the streaming read API
-		 * will only return TBMIterateResults for blocks actually fetched.
-		 * When we skip fetching a block, we keep track of how many empty
-		 * tuples to emit at the end of the BitmapHeapScan. We do not recheck
-		 * all NULL tuples.
-		 */
-		*recheck = false;
-		return bscan->rs_empty_tuples_pending > 0;
-	}
-
-	Assert(per_buffer_data);
-
-	tbmres = per_buffer_data;
-
-	Assert(BufferGetBlockNumber(hscan->rs_cbuf) == tbmres->blockno);
-
-	*recheck = tbmres->recheck;
-
-	hscan->rs_cblock = tbmres->blockno;
-	hscan->rs_ntuples = tbmres->ntuples;
-
-	block = tbmres->blockno;
-	buffer = hscan->rs_cbuf;
-	snapshot = scan->rs_snapshot;
-
-	ntup = 0;
-
-	/*
-	 * Prune and repair fragmentation for the whole page, if possible.
-	 */
-	heap_page_prune_opt(scan->rs_rd, buffer);
-
-	/*
-	 * We must hold share lock on the buffer content while examining tuple
-	 * visibility.  Afterwards, however, the tuples we have found to be
-	 * visible are guaranteed good as long as we hold the buffer pin.
-	 */
-	LockBuffer(buffer, BUFFER_LOCK_SHARE);
+	OffsetNumber targoffset;
+	Page		page;
+	ItemId		lp;
 
 	/*
-	 * We need two separate strategies for lossy and non-lossy cases.
+	 * Out of range?  If so, nothing more to look at on this page
 	 */
-	if (tbmres->ntuples >= 0)
+	while (hscan->rs_cindex >= hscan->rs_ntuples)
 	{
 		/*
-		 * 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.
-		 */
-		int			curslot;
-
-		for (curslot = 0; curslot < tbmres->ntuples; curslot++)
-		{
-			OffsetNumber offnum = tbmres->offsets[curslot];
-			ItemPointerData tid;
-			HeapTupleData heapTuple;
-
-			ItemPointerSet(&tid, block, offnum);
-			if (heap_hot_search_buffer(&tid, scan->rs_rd, buffer, snapshot,
-									   &heapTuple, NULL, true))
-				hscan->rs_vistuples[ntup++] = ItemPointerGetOffsetNumber(&tid);
-		}
-	}
-	else
-	{
-		/*
-		 * Bitmap is lossy, so we must examine each line pointer on the page.
-		 * But we can ignore HOT chains, since we'll check each tuple anyway.
+		 * Emit empty tuples before advancing to the next block
 		 */
-		Page		page = BufferGetPage(buffer);
-		OffsetNumber maxoff = PageGetMaxOffsetNumber(page);
-		OffsetNumber offnum;
-
-		for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
+		if (bscan->rs_empty_tuples_pending > 0)
 		{
-			ItemId		lp;
-			HeapTupleData loctup;
-			bool		valid;
-
-			lp = PageGetItemId(page, offnum);
-			if (!ItemIdIsNormal(lp))
-				continue;
-			loctup.t_data = (HeapTupleHeader) PageGetItem(page, lp);
-			loctup.t_len = ItemIdGetLength(lp);
-			loctup.t_tableOid = scan->rs_rd->rd_id;
-			ItemPointerSet(&loctup.t_self, block, offnum);
-			valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
-			if (valid)
-			{
-				hscan->rs_vistuples[ntup++] = offnum;
-				PredicateLockTID(scan->rs_rd, &loctup.t_self, snapshot,
-								 HeapTupleHeaderGetXmin(loctup.t_data));
-			}
-			HeapCheckForSerializableConflictOut(valid, scan->rs_rd, &loctup,
-												buffer, snapshot);
+			/*
+			 * If we don't have to fetch the tuple, just return nulls.
+			 */
+			ExecStoreAllNullTuple(slot);
+			bscan->rs_empty_tuples_pending--;
+			return true;
 		}
-	}
-
-	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
-
-	Assert(ntup <= MaxHeapTuplesPerPage);
-	hscan->rs_ntuples = ntup;
-
-	if (tbmres->ntuples >= 0)
-		(*exact_pages)++;
-	else
-		(*lossy_pages)++;
-
-	/*
-	 * Return true to indicate that a valid block was found and the bitmap is
-	 * not exhausted. If there are no visible tuples on this page,
-	 * hscan->rs_ntuples will be 0 and heapam_scan_bitmap_next_tuple() will
-	 * return false returning control to this function to advance to the next
-	 * block in the bitmap.
-	 */
-	return true;
-}
-
-static bool
-heapam_scan_bitmap_next_tuple(TableScanDesc scan,
-							  TupleTableSlot *slot)
-{
-	BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) scan;
-	HeapScanDesc hscan = (HeapScanDesc) bscan;
-	OffsetNumber targoffset;
-	Page		page;
-	ItemId		lp;
 
-	if (bscan->rs_empty_tuples_pending > 0)
-	{
 		/*
-		 * If we don't have to fetch the tuple, just return nulls.
+		 * Returns false if the bitmap is exhausted and there are no further
+		 * blocks we need to scan.
 		 */
-		ExecStoreAllNullTuple(slot);
-		bscan->rs_empty_tuples_pending--;
-		return true;
+		if (!BitmapHeapScanNextBlock(scan, recheck, lossy_pages, exact_pages))
+			return false;
 	}
 
-	/*
-	 * Out of range?  If so, nothing more to look at on this page
-	 */
-	if (hscan->rs_cindex >= hscan->rs_ntuples)
-		return false;
-
 	targoffset = hscan->rs_vistuples[hscan->rs_cindex];
 	page = BufferGetPage(hscan->rs_cbuf);
 	lp = PageGetItemId(page, targoffset);
@@ -2603,6 +2463,167 @@ SampleHeapTupleVisible(TableScanDesc scan, Buffer buffer,
 	}
 }
 
+/*
+ * Helper function get the next block of a bitmap heap scan. Returns true when
+ * it got the next block and saved it in the scan descriptor and false when
+ * the bitmap and or relation are exhausted.
+ */
+static bool
+BitmapHeapScanNextBlock(TableScanDesc scan,
+						bool *recheck,
+						uint64 *lossy_pages, uint64 *exact_pages)
+{
+	BitmapHeapScanDesc bscan = (BitmapHeapScanDesc) scan;
+	HeapScanDesc hscan = (HeapScanDesc) bscan;
+	BlockNumber block;
+	void	   *per_buffer_data;
+	Buffer		buffer;
+	Snapshot	snapshot;
+	int			ntup;
+	TBMIterateResult *tbmres;
+
+	Assert(scan->rs_flags & SO_TYPE_BITMAPSCAN);
+	Assert(hscan->rs_read_stream);
+
+	hscan->rs_cindex = 0;
+	hscan->rs_ntuples = 0;
+
+	/* Release buffer containing previous block. */
+	if (BufferIsValid(hscan->rs_cbuf))
+	{
+		ReleaseBuffer(hscan->rs_cbuf);
+		hscan->rs_cbuf = InvalidBuffer;
+	}
+
+	hscan->rs_cbuf = read_stream_next_buffer(hscan->rs_read_stream, &per_buffer_data);
+
+	if (BufferIsInvalid(hscan->rs_cbuf))
+	{
+		if (BufferIsValid(bscan->rs_vmbuffer))
+		{
+			ReleaseBuffer(bscan->rs_vmbuffer);
+			bscan->rs_vmbuffer = InvalidBuffer;
+		}
+
+		/*
+		 * Bitmap is exhausted. Time to emit empty tuples if relevant. We emit
+		 * all empty tuples at the end instead of emitting them per block we
+		 * skip fetching. This is necessary because the streaming read API
+		 * will only return TBMIterateResults for blocks actually fetched.
+		 * When we skip fetching a block, we keep track of how many empty
+		 * tuples to emit at the end of the BitmapHeapScan. We do not recheck
+		 * all NULL tuples.
+		 */
+		*recheck = false;
+		return bscan->rs_empty_tuples_pending > 0;
+	}
+
+	Assert(per_buffer_data);
+
+	tbmres = per_buffer_data;
+
+	Assert(BufferGetBlockNumber(hscan->rs_cbuf) == tbmres->blockno);
+
+	*recheck = tbmres->recheck;
+
+	hscan->rs_cblock = tbmres->blockno;
+	hscan->rs_ntuples = tbmres->ntuples;
+
+	block = tbmres->blockno;
+	buffer = hscan->rs_cbuf;
+	snapshot = scan->rs_snapshot;
+
+	ntup = 0;
+
+	/*
+	 * Prune and repair fragmentation for the whole page, if possible.
+	 */
+	heap_page_prune_opt(scan->rs_rd, buffer);
+
+	/*
+	 * We must hold share lock on the buffer content while examining tuple
+	 * visibility.  Afterwards, however, the tuples we have found to be
+	 * visible are guaranteed good as long as we hold the buffer pin.
+	 */
+	LockBuffer(buffer, BUFFER_LOCK_SHARE);
+
+	/*
+	 * We need two separate strategies for lossy and non-lossy cases.
+	 */
+	if (tbmres->ntuples >= 0)
+	{
+		/*
+		 * 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.
+		 */
+		int			curslot;
+
+		for (curslot = 0; curslot < tbmres->ntuples; curslot++)
+		{
+			OffsetNumber offnum = tbmres->offsets[curslot];
+			ItemPointerData tid;
+			HeapTupleData heapTuple;
+
+			ItemPointerSet(&tid, block, offnum);
+			if (heap_hot_search_buffer(&tid, scan->rs_rd, buffer, snapshot,
+									   &heapTuple, NULL, true))
+				hscan->rs_vistuples[ntup++] = ItemPointerGetOffsetNumber(&tid);
+		}
+	}
+	else
+	{
+		/*
+		 * Bitmap is lossy, so we must examine each line pointer on the page.
+		 * But we can ignore HOT chains, since we'll check each tuple anyway.
+		 */
+		Page		page = BufferGetPage(buffer);
+		OffsetNumber maxoff = PageGetMaxOffsetNumber(page);
+		OffsetNumber offnum;
+
+		for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
+		{
+			ItemId		lp;
+			HeapTupleData loctup;
+			bool		valid;
+
+			lp = PageGetItemId(page, offnum);
+			if (!ItemIdIsNormal(lp))
+				continue;
+			loctup.t_data = (HeapTupleHeader) PageGetItem(page, lp);
+			loctup.t_len = ItemIdGetLength(lp);
+			loctup.t_tableOid = scan->rs_rd->rd_id;
+			ItemPointerSet(&loctup.t_self, block, offnum);
+			valid = HeapTupleSatisfiesVisibility(&loctup, snapshot, buffer);
+			if (valid)
+			{
+				hscan->rs_vistuples[ntup++] = offnum;
+				PredicateLockTID(scan->rs_rd, &loctup.t_self, snapshot,
+								 HeapTupleHeaderGetXmin(loctup.t_data));
+			}
+			HeapCheckForSerializableConflictOut(valid, scan->rs_rd, &loctup,
+												buffer, snapshot);
+		}
+	}
+
+	LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+
+	Assert(ntup <= MaxHeapTuplesPerPage);
+	hscan->rs_ntuples = ntup;
+
+	if (tbmres->ntuples >= 0)
+		(*exact_pages)++;
+	else
+		(*lossy_pages)++;
+
+	/*
+	 * Return true to indicate that a valid block was found and the bitmap is
+	 * not exhausted. If there are no visible tuples on this page,
+	 * hscan->rs_ntuples will be 0 and heapam_scan_bitmap_next_tuple() will
+	 * invoke this function again.
+	 */
+	return true;
+}
 
 /* ------------------------------------------------------------------------
  * Definition of the heap table access method.
@@ -2662,7 +2683,6 @@ static const TableAmRoutine heapam_methods = {
 
 	.relation_estimate_size = heapam_estimate_rel_size,
 
-	.scan_bitmap_next_block = heapam_scan_bitmap_next_block,
 	.scan_bitmap_next_tuple = heapam_scan_bitmap_next_tuple,
 	.scan_sample_next_block = heapam_scan_sample_next_block,
 	.scan_sample_next_tuple = heapam_scan_sample_next_tuple
diff --git a/src/backend/access/table/tableamapi.c b/src/backend/access/table/tableamapi.c
index 760a36fd2a1..56378007a81 100644
--- a/src/backend/access/table/tableamapi.c
+++ b/src/backend/access/table/tableamapi.c
@@ -92,8 +92,6 @@ GetTableAmRoutine(Oid amhandler)
 	Assert(routine->relation_estimate_size != NULL);
 
 	/* optional, but one callback implies presence of the other */
-	Assert((routine->scan_bitmap_next_block == NULL) ==
-		   (routine->scan_bitmap_next_tuple == NULL));
 	Assert(routine->scan_sample_next_block != NULL);
 	Assert(routine->scan_sample_next_tuple != NULL);
 
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 5b368a3dccc..f32a9da8efe 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -140,67 +140,44 @@ BitmapTableScanSetup(BitmapHeapScanState *node)
 static TupleTableSlot *
 BitmapHeapNext(BitmapHeapScanState *node)
 {
-	ExprContext *econtext;
-	TableScanDesc scan;
-	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;
+	ExprContext *econtext = node->ss.ps.ps_ExprContext;
+	TupleTableSlot *slot = node->ss.ss_ScanTupleSlot;
 
 	/*
 	 * If we haven't yet performed the underlying index scan, do it, and begin
 	 * the iteration over the bitmap.
 	 */
 	if (!node->initialized)
-	{
 		BitmapTableScanSetup(node);
-		scan = node->ss.ss_currentScanDesc;
-		goto new_page;
-	}
 
-	for (;;)
+	while (table_scan_bitmap_next_tuple(node->ss.ss_currentScanDesc,
+										slot, &node->recheck,
+										&node->stats.lossy_pages,
+										&node->stats.exact_pages))
 	{
-		while (table_scan_bitmap_next_tuple(scan, slot))
+		/*
+		 * Continuing in previously obtained page.
+		 */
+		CHECK_FOR_INTERRUPTS();
+
+		/*
+		 * If we are using lossy info, we have to recheck the qual conditions
+		 * at every tuple.
+		 */
+		if (node->recheck)
 		{
-			/*
-			 * Continuing in previously obtained page.
-			 */
-			CHECK_FOR_INTERRUPTS();
-
-			/*
-			 * If we are using lossy info, we have to recheck the qual
-			 * conditions at every tuple.
-			 */
-			if (node->recheck)
+			econtext->ecxt_scantuple = slot;
+			if (!ExecQualAndReset(node->bitmapqualorig, econtext))
 			{
-				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;
-				}
+				/* Fails recheck, so drop it and loop back for another */
+				InstrCountFiltered2(node, 1);
+				ExecClearTuple(slot);
+				continue;
 			}
-
-			/* OK to return this tuple */
-			return slot;
 		}
-new_page:
 
-		/*
-		 * Returns false if the bitmap is exhausted and there are no further
-		 * blocks we need to scan.
-		 */
-		if (!table_scan_bitmap_next_block(scan,
-										  &node->recheck,
-										  &node->stats.lossy_pages,
-										  &node->stats.exact_pages))
-			break;
+		/* OK to return this tuple */
+		return slot;
 	}
 
 	/*
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index 71abb01f655..0489ad36644 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -325,7 +325,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 				info->amcanparallel = amroutine->amcanparallel;
 				info->amhasgettuple = (amroutine->amgettuple != NULL);
 				info->amhasgetbitmap = amroutine->amgetbitmap != NULL &&
-					relation->rd_tableam->scan_bitmap_next_block != NULL;
+					relation->rd_tableam->scan_bitmap_next_tuple != NULL;
 				info->amcanmarkpos = (amroutine->ammarkpos != NULL &&
 									  amroutine->amrestrpos != NULL);
 				info->amcostestimate = amroutine->amcostestimate;
diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h
index 6a8ba3b8657..afdc93d1acf 100644
--- a/src/include/access/tableam.h
+++ b/src/include/access/tableam.h
@@ -779,43 +779,23 @@ typedef struct TableAmRoutine
 	 */
 
 	/*
-	 * Prepare to fetch / check / return tuples from `blockno` as part of a
-	 * bitmap table scan. `scan` was started via table_beginscan_bm(). Return
-	 * false if the bitmap is exhausted and true otherwise.
-	 *
-	 * This will typically read and pin the target block, and do the necessary
-	 * work to allow scan_bitmap_next_tuple() to return tuples (e.g. it might
-	 * make sense to perform tuple visibility checks at this time).
-	 *
-	 * `lossy_pages` and `exact_pages` are EXPLAIN counters that can be
-	 * incremented by the table AM to indicate whether or not the block's
-	 * representation in the bitmap is lossy.
+	 * Fetch the next tuple of a bitmap table scan into `slot` and return true
+	 * if a visible tuple was found, false otherwise.
 	 *
-	 * `recheck` is set by the table AM to indicate whether or not the tuples
-	 * from this block should be rechecked. Tuples from lossy pages will
-	 * always need to be rechecked, but some non-lossy pages' tuples may also
-	 * require recheck.
+	 * `lossy_pages` is incremented if the bitmap is lossy for the selected
+	 * page; otherwise, `exact_pages` is incremented. This is tracked for
+	 * display in EXPLAIN ANALYZE output.
 	 *
 	 * Prefetching additional data from the bitmap is left to the table AM.
 	 *
-	 * Optional callback, but either both scan_bitmap_next_block and
-	 * scan_bitmap_next_tuple need to exist, or neither.
+	 * This is an optional callback.
 	 */
-	bool		(*scan_bitmap_next_block) (TableScanDesc scan,
+	bool		(*scan_bitmap_next_tuple) (TableScanDesc scan,
+										   TupleTableSlot *slot,
 										   bool *recheck,
 										   uint64 *lossy_pages,
 										   uint64 *exact_pages);
 
-	/*
-	 * Fetch the next tuple of a bitmap table scan into `slot` and return true
-	 * if a visible tuple was found, false otherwise.
-	 *
-	 * Optional callback, but either both scan_bitmap_next_block and
-	 * scan_bitmap_next_tuple need to exist, or neither.
-	 */
-	bool		(*scan_bitmap_next_tuple) (TableScanDesc scan,
-										   TupleTableSlot *slot);
-
 	/*
 	 * Prepare to fetch tuples from the next block in a sample scan. Return
 	 * false if the sample scan is finished, true otherwise. `scan` was
@@ -1942,51 +1922,24 @@ table_relation_estimate_size(Relation rel, int32 *attr_widths,
  */
 
 /*
- * Prepare to fetch / check / return tuples as part of a bitmap table scan.
- * `scan` needs to have been started via table_beginscan_bm(). Returns false
- * if there are no more blocks in the bitmap, true otherwise.
- *
- * `lossy_pages` and `exact_pages` are EXPLAIN counters that can be
- * incremented by the table AM to indicate whether or not the block's
- * representation in the bitmap is lossy.
+ * Fetch / check / return tuples as part of a bitmap table scan. `scan` needs
+ * to have been started via table_beginscan_bm(). Fetch the next tuple of a
+ * bitmap table scan into `slot` and return true if a visible tuple was found,
+ * false otherwise.
  *
- * `recheck` is set by the table AM to indicate whether or not the tuples
- * from this block should be rechecked.
+ * `recheck` is set by the table AM to indicate whether or not the tuple in
+ * `slot` should be rechecked. Tuples from lossy pages will always need to be
+ * rechecked, but some non-lossy pages' tuples may also require recheck.
  *
- * Note, this is an optionally implemented function, therefore should only be
- * used after verifying the presence (at plan time or such).
+ * `lossy_pages` is incremented if the block's representation in the bitmap is
+ * lossy; otherwise, `exact_pages` is incremented.
  */
 static inline bool
-table_scan_bitmap_next_block(TableScanDesc scan,
+table_scan_bitmap_next_tuple(TableScanDesc scan,
+							 TupleTableSlot *slot,
 							 bool *recheck,
 							 uint64 *lossy_pages,
 							 uint64 *exact_pages)
-{
-	/*
-	 * We don't expect direct calls to table_scan_bitmap_next_block with valid
-	 * CheckXidAlive for catalog or regular tables.  See detailed comments in
-	 * xact.c where these variables are declared.
-	 */
-	if (unlikely(TransactionIdIsValid(CheckXidAlive) && !bsysscan))
-		elog(ERROR, "unexpected table_scan_bitmap_next_block call during logical decoding");
-
-	return scan->rs_rd->rd_tableam->scan_bitmap_next_block(scan,
-														   recheck,
-														   lossy_pages,
-														   exact_pages);
-}
-
-/*
- * Fetch the next tuple of a bitmap table scan into `slot` and return true if
- * a visible tuple was found, false otherwise.
- * table_scan_bitmap_next_block() needs to previously have selected a
- * block (i.e. returned true), and no previous
- * table_scan_bitmap_next_tuple() for the same block may have
- * returned false.
- */
-static inline bool
-table_scan_bitmap_next_tuple(TableScanDesc scan,
-							 TupleTableSlot *slot)
 {
 	/*
 	 * We don't expect direct calls to table_scan_bitmap_next_tuple with valid
@@ -1997,7 +1950,10 @@ table_scan_bitmap_next_tuple(TableScanDesc scan,
 		elog(ERROR, "unexpected table_scan_bitmap_next_tuple call during logical decoding");
 
 	return scan->rs_rd->rd_tableam->scan_bitmap_next_tuple(scan,
-														   slot);
+														   slot,
+														   recheck,
+														   lossy_pages,
+														   exact_pages);
 }
 
 /*
-- 
2.34.1

Reply via email to