agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH va1 2/2] Mega-WIP: Optimized out/send path for printtup
203+ messages / 2 participants
[nested] [flat]

* [PATCH va1 2/2] Mega-WIP: Optimized out/send path for printtup
@ 2026-05-06 15:44 Andres Freund <[email protected]>
  0 siblings, 0 replies; 203+ messages in thread

From: Andres Freund @ 2026-05-06 15:44 UTC (permalink / raw)

Discussion: https://postgr.es/m/[email protected]
---
 src/include/nodes/miscnodes.h        | 12 +++++
 src/backend/access/common/printtup.c | 35 +++++++++++--
 src/backend/utils/adt/int.c          | 73 +++++++++++++++++++++++++---
 src/backend/utils/adt/varlena.c      | 40 ++++++++++++++-
 4 files changed, 148 insertions(+), 12 deletions(-)

diff --git a/src/include/nodes/miscnodes.h b/src/include/nodes/miscnodes.h
index ec833001ab0..b3c189a5c0c 100644
--- a/src/include/nodes/miscnodes.h
+++ b/src/include/nodes/miscnodes.h
@@ -54,4 +54,16 @@ typedef struct ErrorSaveContext
 	((escontext) != NULL && IsA(escontext, ErrorSaveContext) && \
 	 ((ErrorSaveContext *) (escontext))->error_occurred)
 
+
+/*
+ * Type optionally passed to input/receive/output/send functions that allows
+ * those functions to opt into more efficient ways of performing their work
+ * (mainly reducing allocations & copies).
+ */
+typedef struct InOutContext
+{
+	NodeTag		type;
+	StringInfo	buf;
+} InOutContext;
+
 #endif							/* MISCNODES_H */
diff --git a/src/backend/access/common/printtup.c b/src/backend/access/common/printtup.c
index 6fa93a6798a..2e3eb8f56d3 100644
--- a/src/backend/access/common/printtup.c
+++ b/src/backend/access/common/printtup.c
@@ -63,6 +63,7 @@ typedef struct
 	int			nattrs;
 	PrinttupAttrInfo *myinfo;	/* Cached info about each attr */
 	StringInfoData buf;			/* output buffer (*not* in tmpcontext) */
+	InOutContext inout;			/* FunctionCallInfo->context data */
 	MemoryContext tmpcontext;	/* Memory context for per-row workspace */
 } DR_printtup;
 
@@ -142,6 +143,9 @@ printtup_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 								  FetchPortalTargetList(portal),
 								  portal->formats);
 
+	myState->inout.type = T_InOutContext;
+	myState->inout.buf = &myState->buf;
+
 	/* ----------------
 	 * We could set up the derived attr info at this time, but we postpone it
 	 * until the first call of printtup, for 2 reasons:
@@ -297,6 +301,15 @@ printtup_prepare_info(DR_printtup *myState, TupleDesc typeinfo, int numAttrs)
 		/* both out and send funcs have one argument */
 		thisState->outstate = palloc0(SizeForFunctionCallInfo(1));
 		thisState->outstate->flinfo = &thisState->finfo;
+
+		/*
+		 * The idea here is that output functions can optionally use more
+		 * efficient paths if they see that the context is InOutContext, by
+		 * directly appending correctly formatted output into the output
+		 * buffer.
+		 */
+		thisState->outstate->context = (Node *) &myState->inout;
+		thisState->outstate->nargs = 1;
 	}
 }
 
@@ -369,7 +382,13 @@ printtup(TupleTableSlot *slot, DestReceiver *self)
 
 			outputstr = DatumGetCString(FunctionCallInvoke(thisState->outstate));
 			Assert(!thisState->outstate->isnull);
-			pq_sendcountedtext(buf, outputstr, strlen(outputstr));
+
+			/*
+			 * If outputstr == NULL, the output function directly appended a
+			 * correctly formatted message.
+			 */
+			if (outputstr)
+				pq_sendcountedtext(buf, outputstr, strlen(outputstr));
 		}
 		else
 		{
@@ -378,9 +397,17 @@ printtup(TupleTableSlot *slot, DestReceiver *self)
 
 			outputbytes = DatumGetByteaP(FunctionCallInvoke(thisState->outstate));
 			Assert(!thisState->outstate->isnull);
-			pq_sendint32(buf, VARSIZE(outputbytes) - VARHDRSZ);
-			pq_sendbytes(buf, VARDATA(outputbytes),
-						 VARSIZE(outputbytes) - VARHDRSZ);
+
+			/*
+			 * If outputbytes == NULL, the send function directly appended a
+			 * correctly formatted message.
+			 */
+			if (outputbytes)
+			{
+				pq_sendint32(buf, VARSIZE(outputbytes) - VARHDRSZ);
+				pq_sendbytes(buf, VARDATA(outputbytes),
+							 VARSIZE(outputbytes) - VARHDRSZ);
+			}
 		}
 	}
 
diff --git a/src/backend/utils/adt/int.c b/src/backend/utils/adt/int.c
index 4c894a49d5d..1b7b5b5246c 100644
--- a/src/backend/utils/adt/int.c
+++ b/src/backend/utils/adt/int.c
@@ -327,10 +327,54 @@ Datum
 int4out(PG_FUNCTION_ARGS)
 {
 	int32		arg1 = PG_GETARG_INT32(0);
-	char	   *result = (char *) palloc(12);	/* sign, 10 digits, '\0' */
+	int			maxlen = 12;	/* sign, 10 digits, '\0' */
 
-	pg_ltoa(arg1, result);
-	PG_RETURN_CSTRING(result);
+	if (fcinfo->context && IsA(fcinfo->context, InOutContext))
+	{
+		/*
+		 * Optimized path for output functions called as part of a larger
+		 * ouput.
+		 *
+		 * FIXME: A good chunk of this should obviously be in helper
+		 * functions.
+		 */
+		InOutContext *inout = castNode(InOutContext, fcinfo->context);
+		StringInfo	buf = inout->buf;
+		int			prev_buflen;
+		int			len;
+		uint32		len_net;
+
+		/* reserve space for length and the max string length */
+		enlargeStringInfo(buf, sizeof(uint32) + maxlen);
+
+		/* reserve space for length, to be filled out later */
+		prev_buflen = buf->len;
+		buf->len += sizeof(uint32);
+
+		/*
+		 * Construct string directly in buffer, we don't have to care about
+		 * encoding conversions, because we assume that every encoding
+		 * embodies ascii (XXX: Is that actually true with client encodings?).
+		 */
+		len = pg_ltoa(arg1, buf->data + buf->len);
+		buf->len += len;
+
+		/* update the previously reserved length */
+		len_net = pg_hton32(len);
+		memcpy(&buf->data[prev_buflen], &len_net, sizeof(uint32));
+
+		PG_RETURN_VOID();
+	}
+	else
+	{
+		/*
+		 * Fallback path called in any other context.
+		 */
+		char	   *result = (char *) palloc(maxlen);
+
+		pg_ltoa(arg1, result);
+		PG_RETURN_CSTRING(result);
+	}
 }
 
 /*
@@ -351,11 +395,26 @@ Datum
 int4send(PG_FUNCTION_ARGS)
 {
 	int32		arg1 = PG_GETARG_INT32(0);
-	StringInfoData buf;
 
-	pq_begintypsend(&buf);
-	pq_sendint32(&buf, arg1);
-	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
+	if (fcinfo->context && IsA(fcinfo->context, InOutContext))
+	{
+		InOutContext *inout = castNode(InOutContext, fcinfo->context);
+
+		/* length of data */
+		pq_sendint32(inout->buf, 4);
+		/* data itself */
+		pq_sendint32(inout->buf, arg1);
+
+		PG_RETURN_VOID();
+	}
+	else
+	{
+		StringInfoData buf;
+
+		pq_begintypsend(&buf);
+		pq_sendint32(&buf, arg1);
+		PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
+	}
 }
 
 
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index c0ff51bd2fc..09913bc01f5 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -290,7 +290,45 @@ textout(PG_FUNCTION_ARGS)
 {
 	Datum		txt = PG_GETARG_DATUM(0);
 
-	PG_RETURN_CSTRING(TextDatumGetCString(txt));
+	if (fcinfo->context && IsA(fcinfo->context, InOutContext))
+	{
+		StringInfo	buf = castNode(InOutContext, fcinfo->context)->buf;
+		text	   *tunpacked = pg_detoast_datum_packed(DatumGetPointer(txt));
+		int			len = VARSIZE_ANY_EXHDR(tunpacked);
+		char	   *data = VARDATA_ANY(tunpacked);
+		char	   *data_converted;
+		size_t		data_len;
+
+		/*
+		 * Convert text output to the right encoding.  For efficiency, this
+		 * should really happen directly into buf. For that we would have to
+		 * reserve space for the length first and fill it out after
+		 * conversion.
+		 *
+		 * FIXME: Obviously we would need helpers for this too.
+		 */
+		data_converted = pg_server_to_client(data, len);
+
+		if (data == data_converted)
+			data_len = len;
+		else
+			data_len = strlen(data_converted);
+
+		/* length */
+		pq_sendint32(buf, data_len);
+
+		/* actual data */
+		appendBinaryStringInfoNT(buf, data_converted, data_len);
+
+		if (tunpacked != DatumGetPointer(txt))
+			pfree(tunpacked);
+
+		PG_RETURN_VOID();
+	}
+	else
+	{
+		PG_RETURN_CSTRING(TextDatumGetCString(txt));
+	}
 }
 
 /*
-- 
2.46.0.519.g2e7b89e038


--benhmb75h34eqzc4--





^ permalink  raw  reply  [nested|flat] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ 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; 203+ 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] 203+ messages in thread