summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorWenwen Chen <wenwen.chen@samsung.com>2023-05-25 16:26:26 +0800
committerJens Axboe <axboe@kernel.dk>2023-05-25 09:30:13 -0600
commit533ab73f5b5c95dcb4152b52d5482abcc824c690 (patch)
tree8214f20ed59dc84edeef2f7cf54c7b218c9b3cd4
parent293007b033418c8c9d1b35d68dec49a500750fde (diff)
downloadlwn-533ab73f5b5c95dcb4152b52d5482abcc824c690.tar.gz
lwn-533ab73f5b5c95dcb4152b52d5482abcc824c690.zip
io_uring: unlock sqd->lock before sq thread release CPU
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> Link: https://lore.kernel.org/r/20230525082626.577862-1-wenwen.chen@samsung.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--io_uring/sqpoll.c6
1 files changed, 5 insertions, 1 deletions
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;
}