From: Stefan Priebe - Profihost AG <s.priebe-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
To: Kent Overstreet <kmo-PEzghdH756F8UrSeD/g0lQ@public.gmane.org>
Cc: Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: bcache: Fix a writeback performance regression
Date: Tue, 20 Aug 2013 10:01:07 +0200 [thread overview]
Message-ID: <52132243.8050803@profihost.ag> (raw)
In-Reply-To: <20130819222718.GA32104@kmo-pixel>
Am 20.08.2013 00:27, schrieb Kent Overstreet:
> On Mon, Aug 19, 2013 at 12:09:24AM +0200, Stefan Priebe wrote:
>>
>> Vanilla 3.10.7 + bcache: Fix a writeback performance regression
>>
>> http://pastebin.com/raw.php?i=LXZk4cMH
>
> Whoops, at first I thought this was the same bug as one I'd already been
> chasing down that had been a harmless bug - turns out I didn't look
> closely enough at the backtrace.
>
> What happened is background writeback is deadlocking, because for some
> reason the workqueue it's running out of is a singlethreaded workqueue,
> so as soon as it decides to queue enough writeback bios that it has to
> sleep on that semaphore (which often won't happen due to the PD
> controller based ratelimiting) - boom, deadlock.
>
> Here's the fixup patch I just tested and am applying:
thanks, this works fine. The only issue i still have, is that the
dirty_date value starts at 0 and goes to a negative value after reboot.
Greets,
Stefan
WARNING: multiple messages have this Message-ID (diff)
From: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
To: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-kernel@vger.kernel.org, linux-bcache@vger.kernel.org
Subject: Re: bcache: Fix a writeback performance regression
Date: Tue, 20 Aug 2013 10:01:07 +0200 [thread overview]
Message-ID: <52132243.8050803@profihost.ag> (raw)
In-Reply-To: <20130819222718.GA32104@kmo-pixel>
Am 20.08.2013 00:27, schrieb Kent Overstreet:
> On Mon, Aug 19, 2013 at 12:09:24AM +0200, Stefan Priebe wrote:
>>
>> Vanilla 3.10.7 + bcache: Fix a writeback performance regression
>>
>> http://pastebin.com/raw.php?i=LXZk4cMH
>
> Whoops, at first I thought this was the same bug as one I'd already been
> chasing down that had been a harmless bug - turns out I didn't look
> closely enough at the backtrace.
>
> What happened is background writeback is deadlocking, because for some
> reason the workqueue it's running out of is a singlethreaded workqueue,
> so as soon as it decides to queue enough writeback bios that it has to
> sleep on that semaphore (which often won't happen due to the PD
> controller based ratelimiting) - boom, deadlock.
>
> Here's the fixup patch I just tested and am applying:
thanks, this works fine. The only issue i still have, is that the
dirty_date value starts at 0 and goes to a negative value after reboot.
Greets,
Stefan
next prev parent reply other threads:[~2013-08-20 8:01 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-14 22:59 [GIT PULL] bcache fixes for 3.11 Kent Overstreet
2013-08-14 22:59 ` Kent Overstreet
2013-08-15 6:43 ` Stefan Priebe - Profihost AG
2013-08-15 6:43 ` Stefan Priebe - Profihost AG
2013-08-15 7:07 ` Kent Overstreet
[not found] ` <520C788A.1060208-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-16 10:11 ` Stefan Priebe - Profihost AG
2013-08-16 10:11 ` Stefan Priebe - Profihost AG
[not found] ` <520DFAB4.1050402-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-18 22:09 ` bcache: Fix a writeback performance regression Stefan Priebe
2013-08-18 22:09 ` Stefan Priebe
2013-08-19 22:27 ` Kent Overstreet
2013-08-19 22:27 ` Kent Overstreet
2013-08-20 8:01 ` Stefan Priebe - Profihost AG [this message]
2013-08-20 8:01 ` Stefan Priebe - Profihost AG
[not found] ` <52132243.8050803-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-20 8:07 ` Stefan Priebe - Profihost AG
2013-08-20 8:07 ` Stefan Priebe - Profihost AG
2013-08-21 21:10 ` Kent Overstreet
[not found] ` <521323D1.1070503-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-21 23:47 ` Kent Overstreet
2013-08-21 23:47 ` Kent Overstreet
[not found] ` <20130821234715.GA4630-jC9Py7bek1znysI04z7BkA@public.gmane.org>
2013-08-22 5:25 ` Stefan Priebe
2013-08-22 5:25 ` Stefan Priebe
2013-08-22 5:27 ` Stefan Priebe
2013-08-22 5:27 ` Stefan Priebe
2013-08-22 5:43 ` Kent Overstreet
2013-08-22 5:59 ` Stefan Priebe
[not found] ` <5215A8A8.90900-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-22 6:02 ` Kent Overstreet
2013-08-22 6:02 ` Kent Overstreet
2013-08-22 7:32 ` Stefan Priebe - Profihost AG
2013-08-22 7:32 ` Stefan Priebe - Profihost AG
[not found] ` <5215BEA4.6040101-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-22 7:42 ` Kent Overstreet
2013-08-22 7:42 ` Kent Overstreet
2013-08-26 19:21 ` Stefan Priebe
2013-08-26 19:21 ` Stefan Priebe
[not found] ` <521BAACB.4070003-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-28 3:37 ` kernel neophyte
2013-08-28 3:37 ` kernel neophyte
[not found] ` <CAFkUHxeAUvv-nhSZSDRVwdm8SoNhHD8oSBKqDYnEO3bNAKLG6w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-08-28 6:05 ` Kent Overstreet
2013-08-28 6:05 ` Kent Overstreet
2013-08-28 18:12 ` kernel neophyte
[not found] ` <CAFkUHxeryKu2VdgBTBWBHTnzzZ=aapUgLd22+7cQnFOXF4r_2g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-08-28 18:38 ` Stefan Priebe - Profihost AG
2013-08-28 18:38 ` Stefan Priebe - Profihost AG
2013-08-28 18:47 ` kernel neophyte
[not found] ` <CAFkUHxcu+0Qv64_4gEGbMk5YaBkm1r7pdw4-JTamiCqy=SMUPg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-08-28 19:20 ` Stefan Priebe
2013-08-28 19:20 ` Stefan Priebe
[not found] ` <521E4D87.8020705-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-28 20:12 ` kernel neophyte
2013-08-28 20:12 ` kernel neophyte
[not found] ` <CAFkUHxfn8fn09d8xnhVyySOTkn_8r_5O8aqCCf=GmMr6m7nOmA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-08-28 20:15 ` Stefan Priebe
2013-08-28 20:15 ` Stefan Priebe
[not found] ` <521E5A69.30408-2Lf/h1ldwEHR5kwTpVNS9A@public.gmane.org>
2013-08-28 22:45 ` kernel neophyte
2013-08-28 22:45 ` kernel neophyte
2013-08-29 18:52 ` Stefan Priebe
2013-08-29 18:52 ` Stefan Priebe
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=52132243.8050803@profihost.ag \
--to=s.priebe-2lf/h1ldwehr5kwtpvns9a@public.gmane.org \
--cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
--cc=kmo-PEzghdH756F8UrSeD/g0lQ@public.gmane.org \
--cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.