summaryrefslogtreecommitdiff
path: root/io_uring/io_uring.c
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2023-07-24 20:28:17 +0300
committerJens Axboe <axboe@kernel.dk>2023-07-24 20:44:35 +0300
commit7b72d661f1f2f950ab8c12de7e2bc48bdac8ed69 (patch)
tree7e1831c46bf4f4065dba29f192440b2a89586c11 /io_uring/io_uring.c
parent07e981137f17e5275b6fa5fd0c28b0ddb4519702 (diff)
downloadlinux-7b72d661f1f2f950ab8c12de7e2bc48bdac8ed69.tar.xz
io_uring: gate iowait schedule on having pending requests
A previous commit made all cqring waits marked as iowait, as a way to improve performance for short schedules with pending IO. However, for use cases that have a special reaper thread that does nothing but wait on events on the ring, this causes a cosmetic issue where we know have one core marked as being "busy" with 100% iowait. While this isn't a grave issue, it is confusing to users. Rather than always mark us as being in iowait, gate setting of current->in_iowait to 1 by whether or not the waiting task has pending requests. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/io-uring/CAMEGJJ2RxopfNQ7GNLhr7X9=bHXKo+G5OOe0LUq=+UgLXsv1Xg@mail.gmail.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=217699 Link: https://bugzilla.kernel.org/show_bug.cgi?id=217700 Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name> Reported-by: Phil Elwell <phil@raspberrypi.com> Tested-by: Andres Freund <andres@anarazel.de> Fixes: 8a796565cec3 ("io_uring: Use io_schedule* in cqring wait") Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring/io_uring.c')
-rw-r--r--io_uring/io_uring.c23
1 files changed, 17 insertions, 6 deletions
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 89a611541bc4..f4591b912ea8 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2493,11 +2493,20 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
return 0;
}
+static bool current_pending_io(void)
+{
+ struct io_uring_task *tctx = current->io_uring;
+
+ if (!tctx)
+ return false;
+ return percpu_counter_read_positive(&tctx->inflight);
+}
+
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq)
{
- int token, ret;
+ int io_wait, ret;
if (unlikely(READ_ONCE(ctx->check_cq)))
return 1;
@@ -2511,17 +2520,19 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
return 0;
/*
- * Use io_schedule_prepare/finish, so cpufreq can take into account
- * that the task is waiting for IO - turns out to be important for low
- * QD IO.
+ * Mark us as being in io_wait if we have pending requests, so cpufreq
+ * can take into account that the task is waiting for IO - turns out
+ * to be important for low QD IO.
*/
- token = io_schedule_prepare();
+ io_wait = current->in_iowait;
+ if (current_pending_io())
+ current->in_iowait = 1;
ret = 0;
if (iowq->timeout == KTIME_MAX)
schedule();
else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS))
ret = -ETIME;
- io_schedule_finish(token);
+ current->in_iowait = io_wait;
return ret;
}