public inbox for linux-block@vger.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Hugh Dickins <hughd@google.com>
Cc: Keith Busch <kbusch@kernel.org>,
	linux-block@vger.kernel.org, Liu Song <liusong@linux.alibaba.com>,
	Hillf Danton <hdanton@sina.com>, Jan Kara <jack@suse.cz>,
	linux-kernel@vger.kernel.org, Yu Kuai <yukuai1@huaweicloud.com>
Subject: Re: [PATCH next v3] sbitmap: fix lockup while swapping
Date: Thu, 29 Sep 2022 17:58:41 -0600	[thread overview]
Message-ID: <166449592135.4485.5114483552637281957.b4-ty@kernel.dk> (raw)
In-Reply-To: <9c2038a7-cdc5-5ee-854c-fbc6168bf16@google.com>

On Thu, 29 Sep 2022 12:50:12 -0700 (PDT), Hugh Dickins wrote:
> Commit 4acb83417cad ("sbitmap: fix batched wait_cnt accounting")
> is a big improvement: without it, I had to revert to before commit
> 040b83fcecfb ("sbitmap: fix possible io hung due to lost wakeup")
> to avoid the high system time and freezes which that had introduced.
> 
> Now okay on the NVME laptop, but 4acb83417cad is a disaster for heavy
> swapping (kernel builds in low memory) on another: soon locking up in
> sbitmap_queue_wake_up() (into which __sbq_wake_up() is inlined), cycling
> around with waitqueue_active() but wait_cnt 0 .  Here is a backtrace,
> showing the common pattern of outer sbitmap_queue_wake_up() interrupted
> before setting wait_cnt 0 back to wake_batch (in some cases other CPUs
> are idle, in other cases they're spinning for a lock in dd_bio_merge()):
> 
> [...]

Applied, thanks!

[1/1] sbitmap: fix lockup while swapping
      commit: 30514bd2dd4e86a3ecfd6a93a3eadf7b9ea164a0

Best regards,
-- 
Jens Axboe



  parent reply	other threads:[~2022-09-29 23:58 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-18 21:10 [PATCH next] sbitmap: fix lockup while swapping Hugh Dickins
2022-09-19 21:22 ` Keith Busch
2022-09-19 23:01   ` Hugh Dickins
2022-09-21 16:40     ` Jan Kara
2022-09-23 14:43       ` Jan Kara
2022-09-23 15:13         ` Keith Busch
2022-09-23 16:16         ` Hugh Dickins
2022-09-23 19:07           ` Keith Busch
2022-09-23 21:29             ` Hugh Dickins
2022-09-23 23:15               ` Hugh Dickins
2022-09-26 11:44                 ` Jan Kara
2022-09-26 14:08                   ` Yu Kuai
2022-09-27  3:39                   ` Hugh Dickins
2022-09-27 10:31                     ` Jan Kara
2022-09-28  3:56                       ` Hugh Dickins
2022-09-28  3:59                         ` [PATCH next v2] " Hugh Dickins
2022-09-28  4:07                           ` Hugh Dickins
2022-09-29  8:39                             ` Jan Kara
2022-09-29 19:50                               ` [PATCH next v3] " Hugh Dickins
2022-09-29 19:56                                 ` Keith Busch
2022-09-29 23:58                                 ` Jens Axboe [this message]
     [not found]               ` <20220924023047.1410-1-hdanton@sina.com>
2022-09-27  4:02                 ` [PATCH next] " Hugh Dickins

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 \
    --in-reply-to=166449592135.4485.5114483552637281957.b4-ty@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=hdanton@sina.com \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=liusong@linux.alibaba.com \
    --cc=yukuai1@huaweicloud.com \
    /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