From: Carlos Carvalho <carlos@fisica.ufpr.br>
To: linux-raid@vger.kernel.org
Subject: Re: problem with recovered array
Date: Tue, 31 Oct 2023 00:21:15 -0300 [thread overview]
Message-ID: <ZUByq7Wg-KFcXctW@fisica.ufpr.br> (raw)
In-Reply-To: <CAAMCDecjCJz3qPve-54wpd_eX3dTgLYrMVupX6i3JNfBq2mNPw@mail.gmail.com>
Roger Heflin (rogerheflin@gmail.com) wrote on Mon, Oct 30, 2023 at 01:14:49PM -03:
> look at SAR -d output for all the disks in the raid6. It may be a
> disk issue (though I suspect not given the 100% cpu show in raid).
>
> Clearly something very expensive/deadlockish is happening because of
> the raid having to rebuild the data from the missing disk, not sure
> what could be wrong with it.
This is very similar to what I complained some 3 months ago. For me it happens
with an array in normal state. sar shows no disk activity yet there are no
writes to the array (reads happen normally) and the flushd thread uses 100%
cpu.
For the latest 6.5.* I can reliably reproduce it with
% xzcat linux-6.5.tar.xz | tar x -f -
This leaves the machine with ~1.5GB of dirty pages (as reported by
/proc/meminfo) that it never manages to write to the array. I've waited for
several hours to no avail. After a reboot the kernel tree had only about 220MB
instead of ~1.5GB...
next prev parent reply other threads:[~2023-10-31 3:29 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-30 13:35 problem with recovered array eyal
2023-10-30 16:14 ` Roger Heflin
2023-10-31 2:35 ` eyal
2023-10-31 2:50 ` eyal
2023-10-31 3:21 ` Carlos Carvalho [this message]
2023-10-31 6:25 ` eyal
2023-10-31 9:29 ` eyal
2023-10-31 10:24 ` Roger Heflin
2023-10-31 21:40 ` eyal
2023-11-01 10:30 ` Roger Heflin
2023-11-01 13:08 ` eyal
2023-11-01 14:29 ` Roger Heflin
2023-11-02 8:34 ` Johannes Truschnigg
2023-11-02 11:27 ` eyal
2023-11-02 11:57 ` Roger Heflin
2023-11-02 13:05 ` eyal
2023-11-02 17:05 ` Roger Heflin
2023-11-02 23:23 ` eyal
2023-11-03 12:08 ` Roger Heflin
2023-11-02 12:29 ` eyal
2023-11-02 12:46 ` Reindl Harald
2023-11-03 14:16 ` Carlos Carvalho
2023-11-03 14:32 ` Dirty page flushing regression in 6.5.x vs 6.1.x Roman Mamedov
2023-11-03 15:57 ` problem with recovered array Roger Heflin
2023-11-03 22:38 ` eyal
2023-11-04 0:48 ` eyal
2023-11-04 1:01 ` Roger Heflin
2023-11-04 10:04 ` eyal
2023-10-31 12:39 ` Carlos Carvalho
2023-10-31 14:19 ` Roger Heflin
2023-10-31 19:20 ` Carlos Carvalho
2023-10-31 21:44 ` problem with recovered array [more details] eyal
2023-10-31 22:00 ` eyal
2023-11-01 4:31 ` [now urgent] problem with recovered array eyal
2023-11-01 6:44 ` eyal
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=ZUByq7Wg-KFcXctW@fisica.ufpr.br \
--to=carlos@fisica.ufpr.br \
--cc=linux-raid@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox