diff mbox series

[v2] io_uring: unlock sqd->lock before sq thread release CPU

Message ID 20230525082626.577862-1-wenwen.chen@samsung.com (mailing list archive)
State New
Headers show
Series [v2] io_uring: unlock sqd->lock before sq thread release CPU | expand

Commit Message

Wenwen Chen May 25, 2023, 8:26 a.m. UTC 
The sq thread actively releases CPU resources by calling the
cond_resched() and schedule() interfaces when it is idle. Therefore,
more resources are available for other threads to run.

There exists a problem in sq thread: it does not unlock sqd->lock before
releasing CPU resources every time. This makes other threads pending on
sqd->lock for a long time. For example, the following interfaces all
require sqd->lock: io_sq_offload_create(), io_register_iowq_max_workers()
and io_ring_exit_work().

Before the sq thread releases CPU resources, unlocking sqd->lock will
provide the user a better experience because it can respond quickly to
user requests.

Signed-off-by: Kanchan Joshi<joshi.k@samsung.com>
Signed-off-by: Wenwen Chen<wenwen.chen@samsung.com>
---
 V1 -> V2: Make sqd lock shuffle dependent on the need to reschedule
 io_uring/sqpoll.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

Comments

Jens Axboe May 25, 2023, 3:30 p.m. UTC | #1 
On Thu, 25 May 2023 16:26:26 +0800, Wenwen Chen wrote:
> The sq thread actively releases CPU resources by calling the
> cond_resched() and schedule() interfaces when it is idle. Therefore,
> more resources are available for other threads to run.
> 
> There exists a problem in sq thread: it does not unlock sqd->lock before
> releasing CPU resources every time. This makes other threads pending on
> sqd->lock for a long time. For example, the following interfaces all
> require sqd->lock: io_sq_offload_create(), io_register_iowq_max_workers()
> and io_ring_exit_work().
> 
> [...]

Applied, thanks!

[1/1] io_uring: unlock sqd->lock before sq thread release CPU
      commit: 533ab73f5b5c95dcb4152b52d5482abcc824c690

Best regards,
diff mbox series

Patch

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 9db4bc1f521a..5e329e3cd470 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -255,9 +255,13 @@  static int io_sq_thread(void *data)
 			sqt_spin = true;
 
 		if (sqt_spin || !time_after(jiffies, timeout)) {
-			cond_resched();
 			if (sqt_spin)
 				timeout = jiffies + sqd->sq_thread_idle;
+			if (unlikely(need_resched())) {
+				mutex_unlock(&sqd->lock);
+				cond_resched();
+				mutex_lock(&sqd->lock);
+			}
 			continue;
 		}