agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v52 10/10] CheckLogicalDecodingRequirements: be specific about which GUC is limiting
374+ messages / 2 participants
[nested] [flat]

* [PATCH v52 10/10] CheckLogicalDecodingRequirements: be specific about which GUC is limiting
@ 2026-04-03 19:01  Álvaro Herrera <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

From: Álvaro Herrera @ 2026-04-03 19:01 UTC (permalink / raw)

---
 src/backend/commands/repack_worker.c           |  3 ++-
 src/backend/replication/logical/logical.c      |  8 +++++---
 src/backend/replication/logical/logicalfuncs.c |  2 +-
 src/backend/replication/slot.c                 | 18 ++++++++++++------
 src/backend/replication/slotfuncs.c            | 11 ++++++-----
 src/backend/replication/walsender.c            |  5 +++--
 src/include/replication/logical.h              |  3 ++-
 src/include/replication/slot.h                 |  2 +-
 8 files changed, 32 insertions(+), 20 deletions(-)

diff --git a/src/backend/commands/repack_worker.c b/src/backend/commands/repack_worker.c
index 610592a05b0..ca827223845 100644
--- a/src/backend/commands/repack_worker.c
+++ b/src/backend/commands/repack_worker.c
@@ -224,7 +224,7 @@ repack_setup_logical_decoding(Oid relid)
 	 * Make sure we can use logical decoding.
 	 */
 	CheckSlotPermissions();
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(true);
 
 	/*
 	 * A single backend should not execute multiple REPACK commands at a time,
@@ -252,6 +252,7 @@ repack_setup_logical_decoding(Oid relid)
 	ctx = CreateInitDecodingContext(REPL_PLUGIN_NAME,
 									NIL,
 									true,
+									true,
 									InvalidXLogRecPtr,
 									XL_ROUTINE(.page_read = read_local_xlog_page,
 											   .segment_open = wal_segment_open,
diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index f20a0fe70ad..a08aece5731 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -108,9 +108,9 @@ static void LoadOutputPlugin(OutputPluginCallbacks *callbacks, const char *plugi
  * decoding.
  */
 void
-CheckLogicalDecodingRequirements(void)
+CheckLogicalDecodingRequirements(bool repack)
 {
-	CheckSlotRequirements();
+	CheckSlotRequirements(repack);
 
 	/*
 	 * NB: Adding a new requirement likely means that RestoreSlotFromDisk()
@@ -305,6 +305,7 @@ StartupDecodingContext(List *output_plugin_options,
  * output_plugin_options -- contains options passed to the output plugin
  * need_full_snapshot -- if true, must obtain a snapshot able to read all
  *		tables; if false, one that can read only catalogs is acceptable.
+ * for_repack -- if true, we're going to be decoding for REPACK.
  * restart_lsn -- if given as invalid, it's this routine's responsibility to
  *		mark WAL as reserved by setting a convenient restart_lsn for the slot.
  *		Otherwise, we set for decoding to start from the given LSN without
@@ -325,6 +326,7 @@ LogicalDecodingContext *
 CreateInitDecodingContext(const char *plugin,
 						  List *output_plugin_options,
 						  bool need_full_snapshot,
+						  bool for_repack,
 						  XLogRecPtr restart_lsn,
 						  XLogReaderRoutine *xl_routine,
 						  LogicalOutputPluginWriterPrepareWrite prepare_write,
@@ -341,7 +343,7 @@ CreateInitDecodingContext(const char *plugin,
 	 * On a standby, this check is also required while creating the slot.
 	 * Check the comments in the function.
 	 */
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(for_repack);
 
 	/* shorter lines... */
 	slot = MyReplicationSlot;
diff --git a/src/backend/replication/logical/logicalfuncs.c b/src/backend/replication/logical/logicalfuncs.c
index 9760818941d..512013b0ef0 100644
--- a/src/backend/replication/logical/logicalfuncs.c
+++ b/src/backend/replication/logical/logicalfuncs.c
@@ -115,7 +115,7 @@ pg_logical_slot_get_changes_guts(FunctionCallInfo fcinfo, bool confirm, bool bin
 
 	CheckSlotPermissions();
 
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	if (PG_ARGISNULL(0))
 		ereport(ERROR,
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 2c6c6773ad2..13004ed547a 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -1669,19 +1669,25 @@ CheckLogicalSlotExists(void)
  * slots.
  */
 void
-CheckSlotRequirements(void)
+CheckSlotRequirements(bool repack)
 {
+	int		limit;
+
 	/*
 	 * NB: Adding a new requirement likely means that RestoreSlotFromDisk()
 	 * needs the same check.
 	 */
 
-	/* XXX we should be able to check exactly which type of slot we need */
-	if (max_replication_slots + max_repack_replication_slots == 0)
+	if (repack)
+		limit = max_repack_replication_slots;
+	else
+		limit = max_replication_slots;
+
+	if (limit == 0)
 		ereport(ERROR,
-				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
-				 errmsg("replication slots can only be used if \"%s\" > 0 or \"%s\" > 0",
-						"max_replication_slots", "max_repack_replication_slots")));
+				errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
+				errmsg("replication slots can only be used if \"%s\" > 0",
+					   repack ? "max_repack_replication_slots" : "max_replication_slots"));
 
 	if (wal_level < WAL_LEVEL_REPLICA)
 		ereport(ERROR,
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index 78dd3c4ea66..16fbd383735 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -90,7 +90,7 @@ pg_create_physical_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckSlotRequirements();
+	CheckSlotRequirements(false);
 
 	create_physical_replication_slot(NameStr(*name),
 									 immediately_reserve,
@@ -164,6 +164,7 @@ create_logical_replication_slot(char *name, char *plugin,
 	 */
 	ctx = CreateInitDecodingContext(plugin, NIL,
 									false,	/* just catalogs is OK */
+									false,	/* not repack */
 									restart_lsn,
 									XL_ROUTINE(.page_read = read_local_xlog_page,
 											   .segment_open = wal_segment_open,
@@ -203,7 +204,7 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	create_logical_replication_slot(NameStr(*name),
 									NameStr(*plugin),
@@ -240,7 +241,7 @@ pg_drop_replication_slot(PG_FUNCTION_ARGS)
 
 	CheckSlotPermissions();
 
-	CheckSlotRequirements();
+	CheckSlotRequirements(false);
 
 	ReplicationSlotDrop(NameStr(*name), true);
 
@@ -648,9 +649,9 @@ copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
 	CheckSlotPermissions();
 
 	if (logical_slot)
-		CheckLogicalDecodingRequirements();
+		CheckLogicalDecodingRequirements(false);
 	else
-		CheckSlotRequirements();
+		CheckSlotRequirements(false);
 
 	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 75ef3419a15..9d7d675fa96 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -1240,7 +1240,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 
 		Assert(cmd->kind == REPLICATION_KIND_LOGICAL);
 
-		CheckLogicalDecodingRequirements();
+		CheckLogicalDecodingRequirements(false);
 
 		/*
 		 * Initially create persistent slot as ephemeral - that allows us to
@@ -1309,6 +1309,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 		Assert(IsLogicalDecodingEnabled());
 
 		ctx = CreateInitDecodingContext(cmd->plugin, NIL, need_full_snapshot,
+										false,
 										InvalidXLogRecPtr,
 										XL_ROUTINE(.page_read = logical_read_xlog_page,
 												   .segment_open = WalSndSegmentOpen,
@@ -1466,7 +1467,7 @@ StartLogicalReplication(StartReplicationCmd *cmd)
 	QueryCompletion qc;
 
 	/* make sure that our requirements are still fulfilled */
-	CheckLogicalDecodingRequirements();
+	CheckLogicalDecodingRequirements(false);
 
 	Assert(!MyReplicationSlot);
 
diff --git a/src/include/replication/logical.h b/src/include/replication/logical.h
index bc9d4ece672..bc075b16741 100644
--- a/src/include/replication/logical.h
+++ b/src/include/replication/logical.h
@@ -115,11 +115,12 @@ typedef struct LogicalDecodingContext
 } LogicalDecodingContext;
 
 
-extern void CheckLogicalDecodingRequirements(void);
+extern void CheckLogicalDecodingRequirements(bool repack);
 
 extern LogicalDecodingContext *CreateInitDecodingContext(const char *plugin,
 														 List *output_plugin_options,
 														 bool need_full_snapshot,
+														 bool for_repack,
 														 XLogRecPtr restart_lsn,
 														 XLogReaderRoutine *xl_routine,
 														 LogicalOutputPluginWriterPrepareWrite prepare_write,
diff --git a/src/include/replication/slot.h b/src/include/replication/slot.h
index c316a01a807..489af7d8d6c 100644
--- a/src/include/replication/slot.h
+++ b/src/include/replication/slot.h
@@ -378,7 +378,7 @@ extern void ReplicationSlotDropAtPubNode(WalReceiverConn *wrconn, char *slotname
 extern void StartupReplicationSlots(void);
 extern void CheckPointReplicationSlots(bool is_shutdown);
 
-extern void CheckSlotRequirements(void);
+extern void CheckSlotRequirements(bool repack);
 extern void CheckSlotPermissions(void);
 extern ReplicationSlotInvalidationCause
 			GetSlotInvalidationCause(const char *cause_name);
-- 
2.47.3


--gp2pyozrd5pweboh--





^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ messages in thread

* [PATCH v2 8/9] convert ParallelBlockTableScanDescData->phs_{start,num}block to atomics
@ 2026-07-09 20:21  Nathan Bossart <[email protected]>
  0 siblings, 0 replies; 374+ messages in thread

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

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

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


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



^ permalink  raw  reply  [nested|flat] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ 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; 374+ 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] 374+ messages in thread