[RFC PATCH 8/8] io_uring: Do not set iowait before sleeping

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Setting in_iowait was introduced in commit
8a796565cec3 ("io_uring: Use io_schedule* in cqring wait")
to tackle a perf regression that was caused by menu taking iowait into
account for synchronous IO and thus not selecting deeper states like in
the io_uring counterpart.
That behaviour is gone, so the workaround can be removed.

Signed-off-by: Christian Loehle <christian.loehle@xxxxxxx>
---
 io_uring/io_uring.c | 17 -----------------
 1 file changed, 17 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 3942db160f18..c819d40bdcf0 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2341,15 +2341,6 @@ 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)
@@ -2367,19 +2358,11 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	if (unlikely(io_should_wake(iowq)))
 		return 0;
 
-	/*
-	 * 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.
-	 */
-	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;
-	current->in_iowait = 0;
 	return ret;
 }
 
-- 
2.34.1





[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux