This is a note to let you know that I've just added the patch titled
io_uring: gate iowait schedule on having pending requests
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
io_uring-gate-iowait-schedule-on-having-pending-requests.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From bca63954fe0022a9c0dc06b94f68271c956875b2 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@xxxxxxxxx>
Date: Tue, 1 Aug 2023 08:39:47 -0600
Subject: io_uring: gate iowait schedule on having pending requests
From: Jens Axboe <axboe@xxxxxxxxx>
Commit 7b72d661f1f2f950ab8c12de7e2bc48bdac8ed69 upstream.
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@xxxxxxxxxxxxxxx
Link: https://lore.kernel.org/io-uring/CAMEGJJ2RxopfNQ7GNLhr7X9=bHXKo+G5OOe0LUq=+UgLXsv1Xg@xxxxxxxxxxxxxx/
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@xxxxxxxxxxxxxx>
Reported-by: Phil Elwell <phil@xxxxxxxxxxxxxxx>
Tested-by: Andres Freund <andres@xxxxxxxxxxx>
Fixes: 8a796565cec3 ("io_uring: Use io_schedule* in cqring wait")
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
io_uring/io_uring.c | 23 +++++++++++++++++------
1 file changed, 17 insertions(+), 6 deletions(-)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -7631,12 +7631,21 @@ static int io_run_task_work_sig(void)
return -EINTR;
}
+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,
ktime_t *timeout)
{
- int token, ret;
+ int io_wait, ret;
/* make sure we run task_work before checking for signals */
ret = io_run_task_work_sig();
@@ -7647,15 +7656,17 @@ static inline int io_cqring_wait_schedul
return 1;
/*
- * 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 = 1;
if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
ret = -ETIME;
- io_schedule_finish(token);
+ current->in_iowait = io_wait;
return ret;
}
Patches currently in stable-queue which might be from axboe@xxxxxxxxx are
queue-5.10/block-fix-a-source-code-comment-in-include-uapi-linu.patch
queue-5.10/io_uring-don-t-audit-the-capability-check-in-io_urin.patch
queue-5.10/s390-dasd-fix-hanging-device-after-quiesce-resume.patch
queue-5.10/io_uring-gate-iowait-schedule-on-having-pending-requests.patch
queue-5.10/io_uring-treat-eagain-for-req_f_nowait-as-final-for-io-wq.patch
