[PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.

agora inbox for pgsql-hackers@postgresql.org  
help / color / mirror / Atom feed

[PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
218+ messages / 1 participants
[nested] [flat]

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

* [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables.
@ 2026-09-08 17:40  Nathan Bossart <nathan@postgresql.org>
  0 siblings, 0 replies; 218+ messages in thread

From: Nathan Bossart @ 2026-09-08 17:40 UTC (permalink / raw)

Currently, currentWorker and workersFinished are ints protected by a
spinlock.  By converting them to atomic variables, we can remove the
spinlock.  Note that worker_freeze_result_tape() also stores the
worker's tape metadata in shared memory within the spinlock's
critical section, but each worker writes only its own slot, and the
fetch-and-add that follows provides the barrier that the leader
depends on when it reads the tapes.
---
 src/backend/utils/sort/tuplesort.c | 30 ++++++++----------------------
 1 file changed, 8 insertions(+), 22 deletions(-)

diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index f67651483f8..37c40763ee0 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -104,6 +104,7 @@
 #include "commands/tablespace.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "port/atomics.h"
 #include "port/pg_bitutils.h"
 #include "storage/shmem.h"
 #include "utils/guc.h"
@@ -340,9 +341,6 @@ struct Tuplesortstate
  */
 struct Sharedsort
 {
-	/* mutex protects all fields prior to tapes */
-	slock_t		mutex;
-
 	/*
 	 * currentWorker generates ordinal identifier numbers for parallel sort
 	 * workers.  These start from 0, and are always gapless.
@@ -351,8 +349,8 @@ struct Sharedsort
 	 * is equal to state.nParticipants within the leader, leader is ready to
 	 * merge worker runs.
 	 */
-	int			currentWorker;
-	int			workersFinished;
+	pg_atomic_uint32 currentWorker;
+	pg_atomic_uint32 workersFinished;
 
 	/* Temporary file space */
 	SharedFileSet fileset;
@@ -3254,9 +3252,8 @@ tuplesort_initialize_shared(Sharedsort *shared, int nWorkers, dsm_segment *seg)
 
 	Assert(nWorkers > 0);
 
-	SpinLockInit(&shared->mutex);
-	shared->currentWorker = 0;
-	shared->workersFinished = 0;
+	pg_atomic_init_u32(&shared->currentWorker, 0);
+	pg_atomic_init_u32(&shared->workersFinished, 0);
 	SharedFileSetInit(&shared->fileset, seg);
 	shared->nTapes = nWorkers;
 	for (i = 0; i < nWorkers; i++)
@@ -3293,16 +3290,9 @@ tuplesort_attach_shared(Sharedsort *shared, dsm_segment *seg)
 static int
 worker_get_identifier(Tuplesortstate *state)
 {
-	Sharedsort *shared = state->shared;
-	int			worker;
-
 	Assert(WORKER(state));
 
-	SpinLockAcquire(&shared->mutex);
-	worker = shared->currentWorker++;
-	SpinLockRelease(&shared->mutex);
-
-	return worker;
+	return pg_atomic_fetch_add_u32(&state->shared->currentWorker, 1);
 }
 
 /*
@@ -3344,10 +3334,8 @@ worker_freeze_result_tape(Tuplesortstate *state)
 	LogicalTapeFreeze(state->result_tape, &output);
 
 	/* Store properties of output tape, and update finished worker count */
-	SpinLockAcquire(&shared->mutex);
 	shared->tapes[state->worker] = output;
-	shared->workersFinished++;
-	SpinLockRelease(&shared->mutex);
+	pg_atomic_fetch_add_u32(&shared->workersFinished, 1);
 }
 
 /*
@@ -3389,9 +3377,7 @@ leader_takeover_tapes(Tuplesortstate *state)
 	Assert(LEADER(state));
 	Assert(nParticipants >= 1);
 
-	SpinLockAcquire(&shared->mutex);
-	workersFinished = shared->workersFinished;
-	SpinLockRelease(&shared->mutex);
+	workersFinished = pg_atomic_read_membarrier_u32(&shared->workersFinished);
 
 	if (nParticipants != workersFinished)
 		elog(ERROR, "cannot take over tapes before all workers finish");
-- 
2.55.0


--hwKv7DgSDwjNaYBK
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename=v3-0006-Convert-SharedFileSet-refcnt-to-an-atomic-variabl.patch



^ permalink  raw  reply  [nested|flat] 218+ messages in thread

end of thread, other threads:[~2026-09-08 17:40 UTC | newest]

Thread overview: 218+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>
2026-09-08 17:40 [PATCH v3 5/6] Convert Sharedsort's worker counters to atomic variables. Nathan Bossart <nathan@postgresql.org>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox