aboutsummaryrefslogtreecommitdiff
path: root/src/backend/storage/aio
diff options
context:
space:
mode:
Diffstat (limited to 'src/backend/storage/aio')
-rw-r--r--src/backend/storage/aio/aio.c27
-rw-r--r--src/backend/storage/aio/aio_callback.c7
-rw-r--r--src/backend/storage/aio/method_io_uring.c8
-rw-r--r--src/backend/storage/aio/method_worker.c7
4 files changed, 39 insertions, 10 deletions
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c
index c64d815ebd1..3643f27ad6e 100644
--- a/src/backend/storage/aio/aio.c
+++ b/src/backend/storage/aio/aio.c
@@ -556,6 +556,13 @@ bool
pgaio_io_was_recycled(PgAioHandle *ioh, uint64 ref_generation, PgAioHandleState *state)
{
*state = ioh->state;
+
+ /*
+ * Ensure that we don't see an earlier state of the handle than ioh->state
+ * due to compiler or CPU reordering. This protects both ->generation as
+ * directly used here, and other fields in the handle accessed in the
+ * caller if the handle was not reused.
+ */
pg_read_barrier();
return ioh->generation != ref_generation;
@@ -752,7 +759,7 @@ pgaio_io_wait_for_free(void)
{
int reclaimed = 0;
- pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %d in-flight, %d idle IOs",
+ pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs",
pgaio_my_backend->num_staged_ios,
dclist_count(&pgaio_my_backend->in_flight_ios),
dclist_count(&pgaio_my_backend->idle_ios));
@@ -773,7 +780,12 @@ pgaio_io_wait_for_free(void)
* Note that no interrupts are processed between the state check
* and the call to reclaim - that's important as otherwise an
* interrupt could have already reclaimed the handle.
+ *
+ * Need to ensure that there's no reordering, in the more common
+ * paths, where we wait for IO, that's done by
+ * pgaio_io_was_recycled().
*/
+ pg_read_barrier();
pgaio_io_reclaim(ioh);
reclaimed++;
}
@@ -797,7 +809,7 @@ pgaio_io_wait_for_free(void)
if (dclist_count(&pgaio_my_backend->in_flight_ios) == 0)
ereport(ERROR,
errmsg_internal("no free IOs despite no in-flight IOs"),
- errdetail_internal("%d pending, %d in-flight, %d idle IOs",
+ errdetail_internal("%d pending, %u in-flight, %u idle IOs",
pgaio_my_backend->num_staged_ios,
dclist_count(&pgaio_my_backend->in_flight_ios),
dclist_count(&pgaio_my_backend->idle_ios)));
@@ -828,7 +840,7 @@ pgaio_io_wait_for_free(void)
case PGAIO_HS_COMPLETED_IO:
case PGAIO_HS_SUBMITTED:
pgaio_debug_io(DEBUG2, ioh,
- "waiting for free io with %d in flight",
+ "waiting for free io with %u in flight",
dclist_count(&pgaio_my_backend->in_flight_ios));
/*
@@ -852,7 +864,12 @@ pgaio_io_wait_for_free(void)
* check and the call to reclaim - that's important as
* otherwise an interrupt could have already reclaimed the
* handle.
+ *
+ * Need to ensure that there's no reordering, in the more
+ * common paths, where we wait for IO, that's done by
+ * pgaio_io_was_recycled().
*/
+ pg_read_barrier();
pgaio_io_reclaim(ioh);
break;
}
@@ -1252,7 +1269,7 @@ pgaio_closing_fd(int fd)
break;
pgaio_debug_io(DEBUG2, ioh,
- "waiting for IO before FD %d gets closed, %d in-flight IOs",
+ "waiting for IO before FD %d gets closed, %u in-flight IOs",
fd, dclist_count(&pgaio_my_backend->in_flight_ios));
/* see comment in pgaio_io_wait_for_free() about raciness */
@@ -1288,7 +1305,7 @@ pgaio_shutdown(int code, Datum arg)
uint64 generation = ioh->generation;
pgaio_debug_io(DEBUG2, ioh,
- "waiting for IO to complete during shutdown, %d in-flight IOs",
+ "waiting for IO to complete during shutdown, %u in-flight IOs",
dclist_count(&pgaio_my_backend->in_flight_ios));
/* see comment in pgaio_io_wait_for_free() about raciness */
diff --git a/src/backend/storage/aio/aio_callback.c b/src/backend/storage/aio/aio_callback.c
index 0ad9795bb7e..03c9bba0802 100644
--- a/src/backend/storage/aio/aio_callback.c
+++ b/src/backend/storage/aio/aio_callback.c
@@ -256,6 +256,9 @@ pgaio_io_call_complete_shared(PgAioHandle *ioh)
pgaio_result_status_string(result.status),
result.id, result.error_data, result.result);
result = ce->cb->complete_shared(ioh, result, cb_data);
+
+ /* the callback should never transition to unknown */
+ Assert(result.status != PGAIO_RS_UNKNOWN);
}
ioh->distilled_result = result;
@@ -290,6 +293,7 @@ pgaio_io_call_complete_local(PgAioHandle *ioh)
/* start with distilled result from shared callback */
result = ioh->distilled_result;
+ Assert(result.status != PGAIO_RS_UNKNOWN);
for (int i = ioh->num_callbacks; i > 0; i--)
{
@@ -306,6 +310,9 @@ pgaio_io_call_complete_local(PgAioHandle *ioh)
pgaio_result_status_string(result.status),
result.id, result.error_data, result.result);
result = ce->cb->complete_local(ioh, result, cb_data);
+
+ /* the callback should never transition to unknown */
+ Assert(result.status != PGAIO_RS_UNKNOWN);
}
/*
diff --git a/src/backend/storage/aio/method_io_uring.c b/src/backend/storage/aio/method_io_uring.c
index c719ba2727a..b78048328e1 100644
--- a/src/backend/storage/aio/method_io_uring.c
+++ b/src/backend/storage/aio/method_io_uring.c
@@ -126,7 +126,7 @@ pgaio_uring_shmem_size(void)
static void
pgaio_uring_shmem_init(bool first_time)
{
- int TotalProcs = MaxBackends + NUM_AUXILIARY_PROCS - MAX_IO_WORKERS;
+ int TotalProcs = pgaio_uring_procs();
bool found;
pgaio_uring_contexts = (PgAioUringContext *)
@@ -400,9 +400,9 @@ pgaio_uring_wait_one(PgAioHandle *ioh, uint64 ref_generation)
while (true)
{
pgaio_debug_io(DEBUG3, ioh,
- "wait_one io_gen: %llu, ref_gen: %llu, cycle %d",
- (long long unsigned) ioh->generation,
- (long long unsigned) ref_generation,
+ "wait_one io_gen: %" PRIu64 ", ref_gen: %" PRIu64 ", cycle %d",
+ ioh->generation,
+ ref_generation,
waited);
if (pgaio_io_was_recycled(ioh, ref_generation, &state) ||
diff --git a/src/backend/storage/aio/method_worker.c b/src/backend/storage/aio/method_worker.c
index 743cccc2acd..36be179678d 100644
--- a/src/backend/storage/aio/method_worker.c
+++ b/src/backend/storage/aio/method_worker.c
@@ -461,7 +461,12 @@ IoWorkerMain(const void *startup_data, size_t startup_data_len)
int nwakeups = 0;
int worker;
- /* Try to get a job to do. */
+ /*
+ * Try to get a job to do.
+ *
+ * The lwlock acquisition also provides the necessary memory barrier
+ * to ensure that we don't see an outdated data in the handle.
+ */
LWLockAcquire(AioWorkerSubmissionQueueLock, LW_EXCLUSIVE);
if ((io_index = pgaio_worker_submission_queue_consume()) == UINT32_MAX)
{
generated by cgit v1.2.3 (git 2.25.1) at 2025-07-07 11:45:59 +0000