----- Original Message -----
From: "Dave Chinner" <david@xxxxxxxxxxxxx>
To: "Janos Haar" <janos.haar@xxxxxxxxxxxx>
Cc: <xiyou.wangcong@xxxxxxxxx>; <linux-kernel@xxxxxxxxxxxxxxx>;
<kamezawa.hiroyu@xxxxxxxxxxxxxx>; <linux-mm@xxxxxxxxx>; <xfs@xxxxxxxxxxx>;
Sent: Thursday, April 15, 2010 11:23 AM
Subject: Re: Kernel crash in xfs_iflush_cluster (was Somebody take a look
On Thu, Apr 15, 2010 at 09:00:49AM +0200, Janos Haar wrote:
The corruption + crash reproduced. (unfortunately)
Apr 14 01:06:33 alfa kernel: XFS mounting filesystem sdb2
This was the point of the xfs_repair more times.
OK, the inodes that are corrupted are different, so there's still
something funky going on here. I still would suggest replacing the
RAID controller to rule that out as the cause.
This was not a cheap card and i can't replace, because have only one, and
the owner decided allready about i need to replace the entire server @
I have only 2 day to get useful debug information when the server is online.
This is bad too for testing, becasue the workload will disappear, and we
need to figure out something to reproduce the problem offline...
FWIW, do you have any other servers with similar h/w, s/w and
workloads? If so, are they seeing problems?
This is a web based game, wich generates a loooot of small files on the
corrupted filesystem, and as far as i see, the corruption happens only @
writing, but not when reading.
Because i can copy multiple times big gz files across the partitions, and
compare, and test for crc, and there is a cron-tester wich tests 12GB gz
files hourly but can't find any problem, this shows me, the corruption only
happens when writing, and not on the content, but on the FS.
This scores the RAID card problem more lower, am i right? :-)
Additionally in the last 3 days i have tried 2 times to cp -aR the entire
partition to another, and both times the corruption appears ON THE SOURCE
and finally the kernel crashed.
step 1. repair
step 2 run the game (files generated...)
step 3 start copy partition's data in background
step 4 corruption reported by kernel
step 5 kernel crashed during write
Can this be a race between read and write?
Btw i have 2 server with this game, the difference are these:
- The game's language
- The HW's structure similar, but totally different branded all the parts,
except the Intel CPU. :-)
- The workload is lower on the stable server
- The stable server is not selected for replace. :-)
The important matches:
- The base OS is FC6 on both
- The actual kernel on the stable server is 220.127.116.11
(This kernel starts to crash @ the beginnig of Marc. month on which we are
- The FS and the internal structure is the same
Can you recompile the kernel with CONFIG_XFS_DEBUG enabled and
reboot into it before you repair and remount the filesystem again?
Yes, of course!
I will do it now, we have 2 days left to get useful infos....
(i.e. so that we know that we have started with a clean filesystem
and the debug kernel) I'm hoping that this will catch the corruption
much sooner, perhaps before it gets to disk. Note that this will
cause the machine to panic when corruption is detected, and it is
much,much more careful about checking in memory structures so there
is a CPU overhead involved as well.
not a problem.