Message-ID: <3D1AEFB0.3070609@conet.cz>
Date: Thu, 27 Jun 2002 12:57:52 +0200
From: Libor Vanek <libor@conet.cz>
User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.1a) Gecko/20020611
MIME-Version: 1.0
To: Seth Mos <knuffie@xs4all.nl>
CC: linux-xfs@oss.sgi.com
Subject: Re: XFS corruption!
References: <4.3.2.7.2.20020627090504.03c4f4a0@pop.xs4all.nl>
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit
Sender: owner-linux-xfs@oss.sgi.com
Precedence: bulk

>
>
>> Hi,
>> we are selling Linux file servers and we wanted to use XFS. Our 
>> internal tests passed OK but when we installed first server at 
>> customer and migrated data an error occured (usually after copying 
>> 60-100 GB). In /var/log/messages we saw this messages:
>
> One of the developers better comment on those messages.


I also think so thats why I post my message here.

>> We tried migrating 160 GB of data using "cp -a" (over NFS), scp and 
>> rsync from old server using RH7.0 (ext2) - all resulted in this.
>> The system is running software RAID5 (10x60GB), 1 GHz Celeron, 128 MB 
>> RAM, standard RH7.3 with SGI XFS modified installation CD.
>> When we rebooted system everything seems OK (nothing lost) but after 
>> copying few more MB the same error occurs.
>> We have built up 2 VERY same machines from same system image and both 
>> behave the very same so I think that it's some software failure.
>
> It sounds like it. Did you build this filesystem with any special mkfs 
> options?
> What IDE controllers are you using? Did you use the 2.4.18 kernel that 
> came on the installer disk or is this a selfcompiled version or even a 
> CVS checkout?

I used default 2.4.18-4-XFS-1.1 and also custom build (same version) - 
no difference.

>> I have stress tested system with doing lot of "dd if=/dev/md0 
>> of=/raid/tmp bs=10MB count=100" and recursive directories (about 50 
>> levels deep) and nothing similar occured. Only when copying data over 
>> network from the old system.
>
> Weird. I frequently have to copy large amounts of data over the 
> network and it works fine so I suspect that something in your 
> filesystem is not right and causing it to fail again as soon as you 
> try to copy to it again.

Now I remember I had also tried to do this "dd" over NFS between the two 
same machines also whithout any corruption. Very strange.

> Can you check/repair the filesystem and see if it appears again?

I can - it does the same but sooner (not after copying tens of GB but 
after copying GBs). As it is production system (from which I'm copying) 
my tests are very limited.

-- 

S pozdravem,
Libor Vanek

Kontakt:
+-------------------------------------+
| Email:    libor@conet.cz            |
| ICQ:      124529939                 |
| WWW:      http://www.discobolos.net |
| Tel/fax:  05/4122 5091, 6293, 6003  |
| Mobil:    0603 536 946              |
+-------------------------------------+