All of lore.kernel.org
 help / color / mirror / Atom feed
From: Fyodor Ustinov <ufm@ufm.su>
To: Gregory Farnum <gregory.farnum@dreamhost.com>
Cc: ceph-devel@vger.kernel.org
Subject: Re: My favorite question
Date: Wed, 27 Jul 2011 13:05:05 +0300	[thread overview]
Message-ID: <4E2FE2D1.8040902@ufm.su> (raw)
In-Reply-To: <CAF3hT9CtaCi8S56+hGpU0mn-tH1WJob081J4Bb0_Z7asPZcXdA@mail.gmail.com>

On 07/27/2011 01:24 AM, Gregory Farnum wrote:
> Hmm, I'm afraid I can't see anything useful in these logs right now --
> just confusion!
>
> The only thing I can think of that might provide useful information
> now is to turn off osd5, update its config file to have heavy
> debugging information (debug osd = 20, at a minimum), and then start
> the OSD back up again. Then we can see if pg 0.256 is still having any
> issues (it is in the logs you sent me).
>
> If not I'll have to mark this as "Can't reproduce" and hope we see it
> again from somebody with higher log levels on. :(
> -Greg

I started manual scrubbing on osd5 and got next message:

2011-07-27 11:38:30.360812   log 2011-07-27 11:38:28.540559 osd5 
10.5.51.145:6803/19737 2842 : [ERR] 0.256 scrub stat mismatch, got 
2196/2196 objects, 0/0 clones, 9046200695/9046200817 bytes, 
8834197/8834197 kb.
2011-07-27 11:38:30.360812   log 2011-07-27 11:38:28.540571 osd5 
10.5.51.145:6803/19737 2843 : [ERR] 0.256 scrub 1 errors

"Hmmm" I said to myself.

stop osd5
fsck -fy /dev/sdb1

And got:

Inode 230558734, i_blocks is 8, should be 16.  Fix? yes
Inode 230559279, i_blocks is 8208, should be 8200.  Fix? yes
Inode 230559410, i_blocks is 40, should be 32.  Fix? yes
Inode 230559527, i_blocks is 24, should be 32.  Fix? yes
Inode 231342174, i_blocks is 40, should be 32.  Fix? yes
Inode 231342209, i_blocks is 24, should be 32.  Fix? yes

Ups. Familiar message. :(

I login to different node and got the same.

Greg, I think to catch any errors no sense. 2.6.39 have broken ext4. I 
will try 3.0.0 (or 3.1.0) and tell about result.

WBR,
     Fyodor.

  reply	other threads:[~2011-07-27 10:05 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-19 11:03 My favorite question Fyodor Ustinov
2011-07-19 14:29 ` Sage Weil
2011-07-19 14:32   ` Fyodor Ustinov
2011-07-22 15:27   ` Fyodor Ustinov
2011-07-25 20:54     ` Gregory Farnum
2011-07-25 21:16       ` Fyodor Ustinov
2011-07-25 22:55         ` Gregory Farnum
2011-07-26  0:05           ` Fyodor Ustinov
2011-07-26 18:07             ` Gregory Farnum
2011-07-26 18:37               ` Fyodor Ustinov
2011-07-26 18:40                 ` Gregory Farnum
2011-07-26 19:19                   ` Fyodor Ustinov
2011-07-26 22:24                     ` Gregory Farnum
2011-07-27 10:05                       ` Fyodor Ustinov [this message]
2011-07-27 15:57                         ` Gregory Farnum

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=4E2FE2D1.8040902@ufm.su \
    --to=ufm@ufm.su \
    --cc=ceph-devel@vger.kernel.org \
    --cc=gregory.farnum@dreamhost.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 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.