From: Eric Sandeen <sandeen@sandeen.net>
To: 符永涛 <yongtaofu@gmail.com>
Cc: Brian Foster <bfoster@redhat.com>, "xfs@oss.sgi.com" <xfs@oss.sgi.com>
Subject: Re: xfs_iunlink_remove: xfs_inotobp() returned error 22 -- debugging
Date: Fri, 19 Apr 2013 20:40:57 -0700 [thread overview]
Message-ID: <51720E49.9020001@sandeen.net> (raw)
In-Reply-To: <CADFMGuL05J+b=bv5jAneLT451eQFNNz2RNHQHccBOjqWsE68Kw@mail.gmail.com>
On 4/19/13 7:51 PM, 符永涛 wrote:
> After change mount option to sync shutdown still happens, and I got a trace again, the inode 0x1c57d is abnormal.
since this is a race on namespace operations, I wouldn't have expected sync to matter.
> https://docs.google.com/file/d/0B7n2C4T5tfNCYW1jNWhBbXBYakE/edit?usp=sharing
> I have a question if the problem is hard to reproduce why I got 8 times in a week only in a test cluster with 8 node?
> What's the problem?
you must have something unique in your environment, and we don't know what it is.
To gather more information, can you also turn on tracepoints for:
xfs_rename
xfs_create
xfs_link
xfs_remove
in addition to xfs_iunlink and xfs_iunlink_remove,
and we'll see what that tells us.
There are many paths that manipulate the di_nlink count, and something is racing, but we don't yet know what two callchains they are.
The above are all the callers that manipulate the link count, so they will yield more information about who is manipulating the counts.
Thanks,
-Eric
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
next prev parent reply other threads:[~2013-04-20 3:41 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-15 23:14 xfs_iunlink_remove: xfs_inotobp() returned error 22 -- debugging Brian Foster
2013-04-16 16:24 ` Dave Chinner
2013-04-16 17:18 ` Brian Foster
2013-04-17 1:04 ` 符永涛
2013-04-17 1:35 ` 符永涛
2013-04-17 3:15 ` 符永涛
2013-04-17 3:48 ` 符永涛
2013-04-17 4:28 ` Eric Sandeen
2013-04-18 1:30 ` 符永涛
2013-04-18 6:45 ` 符永涛
2013-04-18 8:25 ` 符永涛
2013-04-18 11:41 ` Brian Foster
2013-04-18 15:23 ` 符永涛
2013-04-18 16:40 ` 符永涛
2013-04-18 17:03 ` Eric Sandeen
2013-04-18 18:35 ` Eric Sandeen
2013-04-18 20:59 ` Brian Foster
2013-04-19 6:40 ` 符永涛
2013-04-19 11:41 ` 符永涛
2013-04-19 14:59 ` Eric Sandeen
2013-04-19 15:13 ` 符永涛
2013-04-19 15:18 ` 符永涛
2013-04-19 16:16 ` Eric Sandeen
2013-04-19 16:47 ` 符永涛
2013-04-19 17:00 ` 符永涛
2013-04-19 17:04 ` Eric Sandeen
2013-04-19 17:08 ` 符永涛
2013-04-19 17:17 ` 符永涛
2013-04-20 0:03 ` 符永涛
2013-04-20 1:15 ` 符永涛
2013-04-20 2:51 ` 符永涛
2013-04-20 3:40 ` Eric Sandeen [this message]
2013-04-20 4:03 ` 符永涛
2013-04-20 4:11 ` 符永涛
2013-04-20 4:20 ` Eric Sandeen
2013-04-20 4:27 ` 符永涛
2013-04-20 10:10 ` 符永涛
2013-04-20 11:38 ` Brian Foster
2013-04-20 11:52 ` 符永涛
2013-04-20 12:58 ` Brian Foster
2013-04-20 13:12 ` 符永涛
2013-04-20 15:36 ` Eric Sandeen
[not found] ` <5172B73C.6000900@sandeen.net>
2013-04-20 23:52 ` 符永涛
2013-04-22 19:59 ` Eric Sandeen
2013-04-23 0:08 ` Dave Chinner
2013-04-23 0:52 ` Eric Sandeen
2013-04-23 1:31 ` 符永涛
2013-04-24 9:02 ` Dave Chinner
2013-04-24 10:21 ` 符永涛
2013-04-25 0:48 ` 符永涛
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=51720E49.9020001@sandeen.net \
--to=sandeen@sandeen.net \
--cc=bfoster@redhat.com \
--cc=xfs@oss.sgi.com \
--cc=yongtaofu@gmail.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