agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v2 4/4] xml2: Avoid libxml leaks in pgxml_xpath() error paths
324+ messages / 2 participants
[nested] [flat]

* [PATCH v2 4/4] xml2: Avoid libxml leaks in pgxml_xpath() error paths
@ 2026-06-01 22:41 Andrey Chernyy <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Andrey Chernyy @ 2026-06-01 22:41 UTC (permalink / raw)

pgxml_xpath() builds an xpath_workspace before returning it to
callers.  If an ERROR is thrown before the function returns, callers
have not received the workspace pointer yet and cannot run
cleanup_workspace().

Add local error cleanup for the partially built workspace and the
compiled XPath expression.  Also check xmlXPathNewContext() before
dereferencing the returned context.
---
 contrib/xml2/xpath.c | 51 +++++++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/contrib/xml2/xpath.c b/contrib/xml2/xpath.c
index 9fe75cb5ff4..283bb51178d 100644
--- a/contrib/xml2/xpath.c
+++ b/contrib/xml2/xpath.c
@@ -497,36 +497,49 @@ static xpath_workspace *
 pgxml_xpath(text *document, xmlChar *xpath, PgXmlErrorContext *xmlerrcxt)
 {
 	int32		docsize = VARSIZE_ANY_EXHDR(document);
-	xmlXPathCompExprPtr comppath;
+	xmlXPathCompExprPtr volatile comppath = NULL;
 	xpath_workspace *workspace = palloc0_object(xpath_workspace);
 
 	workspace->doctree = NULL;
 	workspace->ctxt = NULL;
 	workspace->res = NULL;
 
-	workspace->doctree = xmlReadMemory((char *) VARDATA_ANY(document),
-									   docsize, NULL, NULL,
-									   XML_PARSE_NOENT);
-	if (workspace->doctree != NULL)
+	PG_TRY();
 	{
-		workspace->ctxt = xmlXPathNewContext(workspace->doctree);
-		workspace->ctxt->node = xmlDocGetRootElement(workspace->doctree);
-
-		/* compile the path */
-		comppath = xmlXPathCtxtCompile(workspace->ctxt, xpath);
-		if (comppath == NULL || pg_xml_error_occurred(xmlerrcxt))
+		workspace->doctree = xmlReadMemory((char *) VARDATA_ANY(document),
+										   docsize, NULL, NULL,
+										   XML_PARSE_NOENT);
+		if (workspace->doctree != NULL)
 		{
-			if (comppath != NULL)
-				xmlXPathFreeCompExpr(comppath);
-			xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_ARGUMENT_FOR_XQUERY,
-						"XPath Syntax Error");
-		}
+			workspace->ctxt = xmlXPathNewContext(workspace->doctree);
+			if (workspace->ctxt == NULL)
+				xml_ereport(xmlerrcxt, ERROR, ERRCODE_OUT_OF_MEMORY,
+							"could not allocate XPath context");
 
-		/* Now evaluate the path expression. */
-		workspace->res = xmlXPathCompiledEval(comppath, workspace->ctxt);
+			workspace->ctxt->node = xmlDocGetRootElement(workspace->doctree);
+
+			/* compile the path */
+			comppath = xmlXPathCtxtCompile(workspace->ctxt, xpath);
+			if (comppath == NULL || pg_xml_error_occurred(xmlerrcxt))
+				xml_ereport(xmlerrcxt, ERROR, ERRCODE_INVALID_ARGUMENT_FOR_XQUERY,
+							"XPath Syntax Error");
+
+			/* Now evaluate the path expression. */
+			workspace->res = xmlXPathCompiledEval(comppath, workspace->ctxt);
+
+			xmlXPathFreeCompExpr(comppath);
+			comppath = NULL;
+		}
+	}
+	PG_CATCH();
+	{
+		if (comppath != NULL)
+			xmlXPathFreeCompExpr(comppath);
+		cleanup_workspace(workspace);
 
-		xmlXPathFreeCompExpr(comppath);
+		PG_RE_THROW();
 	}
+	PG_END_TRY();
 
 	return workspace;
 }
-- 
2.54.0


--MP_/LMSk9=uMhuQ1QiIJDarDO8G--






^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Xf36GNcW+0xZNily
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v2-0009-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread

* [PATCH v1 7/8] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21 Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 324+ messages in thread

From: Nathan Bossart @ 2026-07-09 20:21 UTC (permalink / raw)

---
 src/backend/access/heap/heapam_handler.c |  2 +-
 src/backend/access/table/tableam.c       | 59 +++++++++++-------------
 src/include/access/relscan.h             |  8 ++--
 3 files changed, 31 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c
index bf87430cf01..0f24a132564 100644
--- a/src/backend/access/heap/heapam_handler.c
+++ b/src/backend/access/heap/heapam_handler.c
@@ -1965,7 +1965,7 @@ heapam_scan_get_blocks_done(HeapScanDesc hscan)
 	if (hscan->rs_base.rs_parallel != NULL)
 	{
 		bpscan = (ParallelBlockTableScanDesc) hscan->rs_base.rs_parallel;
-		startblock = bpscan->phs_startblock;
+		startblock = pg_atomic_read_u32(&bpscan->phs_startblock);
 	}
 	else
 		startblock = hscan->rs_startblock;
diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c
index 68ff0966f1c..f2038ea9205 100644
--- a/src/backend/access/table/tableam.c
+++ b/src/backend/access/table/tableam.c
@@ -421,9 +421,8 @@ table_block_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan)
 	bpscan->base.phs_syncscan = synchronize_seqscans &&
 		!RelationUsesLocalBuffers(rel) &&
 		bpscan->phs_nblocks > NBuffers / 4;
-	SpinLockInit(&bpscan->phs_mutex);
-	bpscan->phs_startblock = InvalidBlockNumber;
-	bpscan->phs_numblock = InvalidBlockNumber;
+	pg_atomic_init_u32(&bpscan->phs_startblock, InvalidBlockNumber);
+	pg_atomic_init_u32(&bpscan->phs_numblock, InvalidBlockNumber);
 	pg_atomic_init_u64(&bpscan->phs_nallocated, 0);
 
 	return sizeof(ParallelBlockTableScanDescData);
@@ -459,25 +458,22 @@ table_block_parallelscan_startblock_init(Relation rel,
 	StaticAssertDecl(MaxBlockNumber <= 0xFFFFFFFE,
 					 "pg_nextpower2_32 may be too small for non-standard BlockNumber width");
 
-	BlockNumber sync_startpage = InvalidBlockNumber;
 	BlockNumber scan_nblocks;
 
 	/* Reset the state we use for controlling allocation size. */
 	memset(pbscanwork, 0, sizeof(*pbscanwork));
 
-retry:
-	/* Grab the spinlock. */
-	SpinLockAcquire(&pbscan->phs_mutex);
-
 	/*
 	 * When the caller specified a limit on the number of blocks to scan, set
 	 * that in the ParallelBlockTableScanDesc, if it's not been done by
 	 * another worker already.
 	 */
-	if (numblocks != InvalidBlockNumber &&
-		pbscan->phs_numblock == InvalidBlockNumber)
+	if (numblocks != InvalidBlockNumber)
 	{
-		pbscan->phs_numblock = numblocks;
+		uint32		expected = InvalidBlockNumber;
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_numblock, &expected,
+									   numblocks);
 	}
 
 	/*
@@ -485,36 +481,35 @@ retry:
 	 * so now.  If a startblock was specified, start there, otherwise if this
 	 * is not a synchronized scan, we just start at block 0, but if it is a
 	 * synchronized scan, we must get the starting position from the
-	 * synchronized scan machinery.  We can't hold the spinlock while doing
-	 * that, though, so release the spinlock, get the information we need, and
-	 * retry.  If nobody else has initialized the scan in the meantime, we'll
-	 * fill in the value we fetched on the second time through.
+	 * synchronized scan machinery.
+	 *
+	 * If another worker initializes phs_startblock concurrently, just use
+	 * their value.
 	 */
-	if (pbscan->phs_startblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_startblock) == InvalidBlockNumber)
 	{
+		BlockNumber newstartblock;
+		uint32		expected = InvalidBlockNumber;
+
 		if (startblock != InvalidBlockNumber)
-			pbscan->phs_startblock = startblock;
+			newstartblock = startblock;
 		else if (!pbscan->base.phs_syncscan)
-			pbscan->phs_startblock = 0;
-		else if (sync_startpage != InvalidBlockNumber)
-			pbscan->phs_startblock = sync_startpage;
+			newstartblock = 0;
 		else
-		{
-			SpinLockRelease(&pbscan->phs_mutex);
-			sync_startpage = ss_get_location(rel, pbscan->phs_nblocks);
-			goto retry;
-		}
+			newstartblock = ss_get_location(rel, pbscan->phs_nblocks);
+
+		pg_atomic_compare_exchange_u32(&pbscan->phs_startblock, &expected,
+									   newstartblock);
 	}
-	SpinLockRelease(&pbscan->phs_mutex);
 
 	/*
 	 * Figure out how many blocks we're going to scan; either all of them, or
 	 * just phs_numblock's worth, if a limit has been imposed.
 	 */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * We determine the chunk size based on scan_nblocks.  First we split
@@ -595,10 +590,10 @@ table_block_parallelscan_nextpage(Relation rel,
 	 */
 
 	/* First, figure out how many blocks we're planning on scanning */
-	if (pbscan->phs_numblock == InvalidBlockNumber)
+	if (pg_atomic_read_u32(&pbscan->phs_numblock) == InvalidBlockNumber)
 		scan_nblocks = pbscan->phs_nblocks;
 	else
-		scan_nblocks = pbscan->phs_numblock;
+		scan_nblocks = pg_atomic_read_u32(&pbscan->phs_numblock);
 
 	/*
 	 * Now check if we have any remaining blocks in a previous chunk for this
@@ -644,7 +639,7 @@ table_block_parallelscan_nextpage(Relation rel,
 	if (nallocated >= scan_nblocks)
 		page = InvalidBlockNumber;	/* all blocks have been allocated */
 	else
-		page = (nallocated + pbscan->phs_startblock) % pbscan->phs_nblocks;
+		page = (nallocated + pg_atomic_read_u32(&pbscan->phs_startblock)) % pbscan->phs_nblocks;
 
 	/*
 	 * Report scan location.  Normally, we report the current page number.
@@ -658,7 +653,7 @@ table_block_parallelscan_nextpage(Relation rel,
 		if (page != InvalidBlockNumber)
 			ss_report_location(rel, page);
 		else if (nallocated == pbscan->phs_nblocks)
-			ss_report_location(rel, pbscan->phs_startblock);
+			ss_report_location(rel, pg_atomic_read_u32(&pbscan->phs_startblock));
 	}
 
 	return page;
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 2ea06a67a63..2305d0159f3 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -19,7 +19,6 @@
 #include "nodes/tidbitmap.h"
 #include "port/atomics.h"
 #include "storage/relfilelocator.h"
-#include "storage/spin.h"
 #include "utils/relcache.h"
 
 
@@ -99,10 +98,9 @@ typedef struct ParallelBlockTableScanDescData
 	ParallelTableScanDescData base;
 
 	BlockNumber phs_nblocks;	/* # blocks in relation at start of scan */
-	slock_t		phs_mutex;		/* mutual exclusion for setting startblock */
-	BlockNumber phs_startblock; /* starting block number */
-	BlockNumber phs_numblock;	/* # blocks to scan, or InvalidBlockNumber if
-								 * no limit */
+	pg_atomic_uint32 phs_startblock;	/* starting block number */
+	pg_atomic_uint32 phs_numblock;	/* # blocks to scan, or InvalidBlockNumber
+									 * if no limit */
 	pg_atomic_uint64 phs_nallocated;	/* number of blocks allocated to
 										 * workers so far. */
 }			ParallelBlockTableScanDescData;
-- 
2.50.1 (Apple Git-155)


--Ot5x3ffkWEuxilWO
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v1-0008-convert-FastPathStrongRelationLocks-to-atomics.patch



^ permalink  raw  reply  [nested|flat] 324+ messages in thread