v2-0011-Separate-TBM-Shared-Iterator-and-TBMIterateResult.patch

From b0417f661ffab18058a392327370eb8690b49c38 Mon Sep 17 00:00:00 2001
From: Melanie Plageman <melanieplageman@gmail.com>
Date: Thu, 15 Feb 2024 21:23:41 -0500
Subject: [PATCH v2 11/13] Separate TBM[Shared]Iterator and TBMIterateResult

Remove the TBMIterateResult from the TBMIterator and TBMSharedIterator
and have tbm_[shared_]iterate() take a TBMIterateResult as a parameter.

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

tbm_[shared]_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, inline the matchResult
in the GinScanEntry to avoid having to separately manage memory for the
TBMIterateResult.
---
 src/backend/access/gin/ginget.c           | 48 +++++++++------
 src/backend/access/gin/ginscan.c          |  2 +-
 src/backend/access/heap/heapam_handler.c  | 32 +++++-----
 src/backend/executor/nodeBitmapHeapscan.c | 33 +++++-----
 src/backend/nodes/tidbitmap.c             | 73 ++++++++++++-----------
 src/include/access/gin_private.h          |  2 +-
 src/include/nodes/tidbitmap.h             |  4 +-
 7 files changed, 107 insertions(+), 87 deletions(-)

diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
index 0b4f2ebadb6..831941271c4 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_iterate(entry->matchIterator);
+				entry->matchResult.blockno = InvalidBlockNumber;
 				entry->matchIterator = NULL;
 				tbm_free(entry->matchBitmap);
 				entry->matchBitmap = NULL;
@@ -823,18 +836,19 @@ 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_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_iterate(entry->matchIterator);
+				tbm_iterate(entry->matchIterator, &entry->matchResult);
 
-				if (entry->matchResult == NULL)
+				if (!BlockNumberIsValid(entry->matchResult.blockno))
 				{
 					ItemPointerSetInvalid(&entry->curItem);
 					tbm_end_iterate(entry->matchIterator);
@@ -858,10 +872,10 @@ 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
@@ -875,27 +889,27 @@ 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 af24d38544e..033d5253394 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 c8da3def645..ba6793a749c 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -2121,7 +2121,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	Buffer		buffer;
 	Snapshot	snapshot;
 	int			ntup;
-	TBMIterateResult *tbmres;
+	TBMIterateResult tbmres;
 
 	hscan->rs_cindex = 0;
 	hscan->rs_ntuples = 0;
@@ -2134,11 +2134,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 		CHECK_FOR_INTERRUPTS();
 
 		if (scan->shared_tbmiterator)
-			tbmres = tbm_shared_iterate(scan->shared_tbmiterator);
+			tbm_shared_iterate(scan->shared_tbmiterator, &tbmres);
 		else
-			tbmres = tbm_iterate(scan->tbmiterator);
+			tbm_iterate(scan->tbmiterator, &tbmres);
 
-		if (tbmres == NULL)
+		if (!BlockNumberIsValid(tbmres.blockno))
 		{
 			/* no more entries in the bitmap */
 			Assert(hscan->rs_empty_tuples_pending == 0);
@@ -2153,11 +2153,11 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 		 * isolation though, as we need to examine all invisible tuples
 		 * reachable by the index.
 		 */
-	} while (!IsolationIsSerializable() && tbmres->blockno >= hscan->rs_nblocks);
+	} while (!IsolationIsSerializable() && 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
@@ -2165,19 +2165,19 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	 * the page are visible to our transaction.
 	 */
 	if (scan->rs_flags & SO_CAN_SKIP_FETCH &&
-		!tbmres->recheck &&
-		VM_ALL_VISIBLE(scan->rs_rd, tbmres->blockno, &hscan->rs_vmbuffer))
+		!tbmres.recheck &&
+		VM_ALL_VISIBLE(scan->rs_rd, tbmres.blockno, &hscan->rs_vmbuffer))
 	{
 		/* can't be lossy in the skip_fetch case */
-		Assert(tbmres->ntuples >= 0);
+		Assert(tbmres.ntuples >= 0);
 		Assert(hscan->rs_empty_tuples_pending >= 0);
 
-		hscan->rs_empty_tuples_pending += tbmres->ntuples;
+		hscan->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.
@@ -2206,7 +2206,7 @@ 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
@@ -2215,9 +2215,9 @@ 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;
 
@@ -2270,7 +2270,7 @@ heapam_scan_bitmap_next_block(TableScanDesc scan,
 	/* Only count exact and lossy pages with visible tuples */
 	if (ntup > 0)
 	{
-		if (tbmres->ntuples >= 0)
+		if (tbmres.ntuples >= 0)
 			scan->exact_pages++;
 		else
 			scan->lossy_pages++;
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index ae837785116..284641fa8ea 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -340,9 +340,10 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node,
 		else if (prefetch_iterator)
 		{
 			/* Do not let the prefetch iterator get behind the main one */
-			TBMIterateResult *tbmpre = tbm_iterate(prefetch_iterator);
+			TBMIterateResult tbmpre;
+			tbm_iterate(prefetch_iterator, &tbmpre);
 
-			if (tbmpre == NULL || tbmpre->blockno != blockno)
+			if (!BlockNumberIsValid(tbmpre.blockno) || tbmpre.blockno != blockno)
 				elog(ERROR, "prefetch and main iterators are out of sync");
 		}
 		return;
@@ -360,6 +361,8 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node,
 		}
 		else
 		{
+			TBMIterateResult tbmpre;
+
 			/* Release the mutex before iterating */
 			SpinLockRelease(&pstate->mutex);
 
@@ -372,7 +375,7 @@ BitmapAdjustPrefetchIterator(BitmapHeapScanState *node,
 			 * case.
 			 */
 			if (prefetch_iterator)
-				tbm_shared_iterate(prefetch_iterator);
+				tbm_shared_iterate(prefetch_iterator, &tbmpre);
 		}
 	}
 #endif							/* USE_PREFETCH */
@@ -439,10 +442,12 @@ 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);
@@ -464,13 +469,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 				 */
 
 				skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
-							  !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);
 			}
 		}
 
@@ -485,7 +490,7 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 		{
 			while (1)
 			{
-				TBMIterateResult *tbmpre;
+				TBMIterateResult tbmpre;
 				bool		do_prefetch = false;
 				bool		skip_fetch;
 
@@ -504,8 +509,8 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 				if (!do_prefetch)
 					return;
 
-				tbmpre = tbm_shared_iterate(prefetch_iterator);
-				if (tbmpre == NULL)
+				tbm_shared_iterate(prefetch_iterator, &tbmpre);
+				if (!BlockNumberIsValid(tbmpre.blockno))
 				{
 					/* No more pages to prefetch */
 					tbm_end_shared_iterate(prefetch_iterator);
@@ -515,13 +520,13 @@ BitmapPrefetch(BitmapHeapScanState *node, TableScanDesc scan)
 
 				/* As above, skip prefetch if we expect not to need page */
 				skip_fetch = (scan->rs_flags & SO_CAN_SKIP_FETCH &&
-							  !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 f711c056143..b4dcb1cbb88 100644
--- a/src/backend/nodes/tidbitmap.c
+++ b/src/backend/nodes/tidbitmap.c
@@ -171,7 +171,6 @@ struct TBMIterator
 	int			spageptr;		/* next spages index */
 	int			schunkptr;		/* next schunks index */
 	int			schunkbit;		/* next bit to check in current schunk */
-	TBMIterateResult output;
 };
 
 /*
@@ -212,7 +211,6 @@ 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) */
 };
 
 /* Local function prototypes */
@@ -943,20 +941,21 @@ tbm_advance_schunkbit(PagetableEntry *chunk, int *schunkbitp)
 /*
  * tbm_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_iterate(TBMIterator *iterator)
+void
+tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres)
 {
 	TIDBitmap  *tbm = iterator->tbm;
-	TBMIterateResult *output = &(iterator->output);
 
 	Assert(tbm->iterating == TBM_ITERATING_PRIVATE);
 
@@ -984,6 +983,7 @@ tbm_iterate(TBMIterator *iterator)
 	 * If both chunk and per-page data remain, must output the numerically
 	 * earlier page.
 	 */
+	Assert(tbmres);
 	if (iterator->schunkptr < tbm->nchunks)
 	{
 		PagetableEntry *chunk = tbm->schunks[iterator->schunkptr];
@@ -994,11 +994,11 @@ tbm_iterate(TBMIterator *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;
 		}
 	}
 
@@ -1014,16 +1014,17 @@ tbm_iterate(TBMIterator *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;
+	return;
 }
 
 /*
@@ -1033,10 +1034,9 @@ tbm_iterate(TBMIterator *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;
@@ -1087,13 +1087,13 @@ 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;
 		}
 	}
 
@@ -1103,21 +1103,22 @@ 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;
+	return;
 }
 
 /*
diff --git a/src/include/access/gin_private.h b/src/include/access/gin_private.h
index 51d0c74a6b0..e423d92b41c 100644
--- a/src/include/access/gin_private.h
+++ b/src/include/access/gin_private.h
@@ -352,7 +352,7 @@ typedef struct GinScanEntryData
 	/* for a partial-match or full-scan query, we accumulate all TIDs here */
 	TIDBitmap  *matchBitmap;
 	TBMIterator *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 432fae52962..f000c1af28f 100644
--- a/src/include/nodes/tidbitmap.h
+++ b/src/include/nodes/tidbitmap.h
@@ -72,8 +72,8 @@ extern bool tbm_is_empty(const TIDBitmap *tbm);
 
 extern TBMIterator *tbm_begin_iterate(TIDBitmap *tbm);
 extern dsa_pointer tbm_prepare_shared_iterate(TIDBitmap *tbm);
-extern TBMIterateResult *tbm_iterate(TBMIterator *iterator);
-extern TBMIterateResult *tbm_shared_iterate(TBMSharedIterator *iterator);
+extern void tbm_iterate(TBMIterator *iterator, TBMIterateResult *tbmres);
+extern void tbm_shared_iterate(TBMSharedIterator *iterator, TBMIterateResult *tbmres);
 extern void tbm_end_iterate(TBMIterator *iterator);
 extern void tbm_end_shared_iterate(TBMSharedIterator *iterator);
 extern TBMSharedIterator *tbm_attach_shared_iterate(dsa_area *dsa,
-- 
2.37.2