public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: Sebastian Andrzej Siewior <[email protected]>
Cc: [email protected], [email protected],
	[email protected], Ingo Molnar <[email protected]>,
	Juri Lelli <[email protected]>,
	Vincent Guittot <[email protected]>,
	Dietmar Eggemann <[email protected]>,
	Steven Rostedt <[email protected]>,
	Ben Segall <[email protected]>, Mel Gorman <[email protected]>,
	Thomas Gleixner <[email protected]>
Subject: Re: [PATCH v2] io_wq: Make io_wqe::lock a raw_spinlock_t
Date: Tue, 1 Sep 2020 08:17:54 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On 9/1/20 2:41 AM, Sebastian Andrzej Siewior wrote:
> During a context switch the scheduler invokes wq_worker_sleeping() with
> disabled preemption. Disabling preemption is needed because it protects
> access to `worker->sleeping'. As an optimisation it avoids invoking
> schedule() within the schedule path as part of possible wake up (thus
> preempt_enable_no_resched() afterwards).
> 
> The io-wq has been added to the mix in the same section with disabled
> preemption. This breaks on PREEMPT_RT because io_wq_worker_sleeping()
> acquires a spinlock_t. Also within the schedule() the spinlock_t must be
> acquired after tsk_is_pi_blocked() otherwise it will block on the
> sleeping lock again while scheduling out.
> 
> While playing with `io_uring-bench' I didn't notice a significant
> latency spike after converting io_wqe::lock to a raw_spinlock_t. The
> latency was more or less the same.
> 
> In order to keep the spinlock_t it would have to be moved after the
> tsk_is_pi_blocked() check which would introduce a branch instruction
> into the hot path.
> 
> The lock is used to maintain the `work_list' and wakes one task up at
> most.
> Should io_wqe_cancel_pending_work() cause latency spikes, while
> searching for a specific item, then it would need to drop the lock
> during iterations.
> revert_creds() is also invoked under the lock. According to debug
> cred::non_rcu is 0. Otherwise it should be moved outside of the locked
> section because put_cred_rcu()->free_uid() acquires a sleeping lock.
> 
> Convert io_wqe::lock to a raw_spinlock_t.c

Thanks, I've applied this for 5.10.

-- 
Jens Axboe


  reply	other threads:[~2020-09-01 14:39 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-19 12:37 [RFC PATCH] sched: Invoke io_wq_worker_sleeping() with enabled preemption Sebastian Andrzej Siewior
2020-08-19 13:15 ` peterz
2020-08-19 13:18   ` Jens Axboe
2020-08-19 19:44     ` [PATCH] io_wq: Make io_wqe::lock a raw_spinlock_t Sebastian Andrzej Siewior
2020-09-01  8:41       ` [PATCH v2] " Sebastian Andrzej Siewior
2020-09-01 14:17         ` Jens Axboe [this message]
2020-08-19 13:33   ` [RFC PATCH] sched: Invoke io_wq_worker_sleeping() with enabled preemption Sebastian Andrzej Siewior
2020-08-19 14:21     ` peterz
2020-08-19 19:55       ` [PATCH 1/2] sched: Bring the PF_IO_WORKER and PF_WQ_WORKER bits closer together Sebastian Andrzej Siewior
2020-08-19 20:00         ` [PATCH 2/2] sched: Cache task_struct::flags in sched_submit_work() Sebastian Andrzej Siewior
2020-08-19 20:11           ` Peter Zijlstra
2020-09-07 12:58         ` [PATCH 1/2] sched: Bring the PF_IO_WORKER and PF_WQ_WORKER bits closer together Will Deacon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox