[prev in list] [next in list] [prev in thread] [next in thread] 

List:       ceph-devel
Subject:    Re: [ceph-devel] cmds crashes with floating point exception
From:       Jürgen_Herrmann <Juergen.Herrmann () XLhost ! de>
Date:       2009-05-11 21:45:47
Message-ID: 58b4f21ab86251d538a3aae29df4eb2d.squirrel () xlhost ! de
[Download RAW message or body]

On Mon, May 11, 2009 20:00, Sage Weil wrote:
> Hi,
>
> Unfortunately, the binaries in the package were stripped, so the core
> isn't terribly helpful.  I've uploaded a new 0.8 (unstable) package that
> isn't stripped.  I hope you're using amd64/x86_64?  The i386 packages are
> a bit out of date (I don't have a machine to build them at the moment.)
>
> Can you try with the latest (amd64) package, and/or build from source?
>
> Also, I've updated the sample ceph.conf to remove rare options and be a
> bit more informative.
>
> Thanks!
> sage
>
ok, now the bug occurrs from time to time. i installed latest 0.8
debian unstable packages.
please see the core at http://t5.by/.downloads/cephcores/core2.bz2

i'd like to ask a few other questions if you dont mind:
how is redundany or failover for the mds handled? why only one
entry in the sample config? how much should i expext it to be
working? the kernel client was stalled several times while
copying directories in my test setup.

btw what's that sudo option for that you mentioned below?

thanks for your help!

best regards,
jürgen
>
>
>> cluster config:
>> [global]
>>         restart on core dump = true
>
> That is what was making things restart.  It's now off by default.
>
>>         pid file = /var/run/ceph/$name.pid
>> [mon]
>>         mon data = /home/ceph_mon_$id
>> [mon0]
>>         host = app-ha1
>>         mon addr = 10.0.85.101:6789
>> [mon1]
>>         host = app-ha2
>>         mon addr = 10.0.85.102:6789
>> [mon2]
>>         host = app-ha3
>>         mon addr = 10.0.85.103:6789
>> [mds]
>> [mds.app-ha1]
>>         host = app-ha1
>> [osd]
>>         sudo = true
>
> Normally not needed.
>
>> [osd0]
>>         host = app-ha1
>>         osd data = /mnt/hda2
>>         osd journal = /dev/umema
>
> Only useful if you have an NVRAM card.
>
>> [osd1]
>>         host = app-ha2
>>         osd data = /mnt/hda2
>>         osd journal = /dev/umema
>> [group everyone]
>>         addr = 10.0.0.0/8
>> [mount /]
>>         allow = %everyone
>>
>> when i startup my machines in the order given in the cluster config,
>> everything is fine. if i then restart app-ha1, cmds crashes with the
>> following error msg:
>> cmds[##pid##] trap divide error ip:6112ee sp:41a9a720 error:0 in cmds[400000+2c2000]
>> /usr/bin/crun: line21:  ##pid## Floating point exception(core dumped)
>> /usr/bin/cmds cumped core, restarting in 5 seconds...
>>
>> and this continues to show up every 5s, so cmds seems to crash instantly.
>> i uploaded a core dump here: http://t5.by/.downloads/cephcores/core.bz2
>>
>> can i provide anything else to help with this possible bug?
>>
>> best regards,
>> jürgen herrmann
>> --
>> >> XLhost.de - eXperts in Linux hosting ® <<
>>
>> XLhost.de GmbH
>> Jürgen Herrmann, Geschäftsführer
>> Boelckestrasse 21, 93051 Regensburg, Germany
>>
>> Geschäftsführer: Volker Geith, Jürgen Herrmann
>> Registriert unter: HRB9918
>> Umsatzsteuer-Identifikationsnummer: DE245931218
>>
>> Fon:  +49 (0)700 XLHOSTDE [0700 95467833]
>> Fax:  +49 (0)700 XLHOSTDE [0700 95467833]
>>
>> WEB:  http://www.XLhost.de
>> IRC:  #XLhost@irc.quakenet.org
>>
>>
>> ------------------------------------------------------------------------------
>> The NEW KODAK i700 Series Scanners deliver under ANY circumstances! Your
>> production scanning environment may not be a perfect world - but thanks to
>> Kodak, there's a perfect scanner to get the job done! With the NEW KODAK i700
>> Series Scanner you'll get full speed at 300 dpi even with all image
>> processing features enabled. http://p.sf.net/sfu/kodak-com
>> _______________________________________________
>> Ceph-devel mailing list
>> Ceph-devel@lists.sourceforge.net
>> https://lists.sourceforge.net/lists/listinfo/ceph-devel
>>
>>


--
>> XLhost.de - eXperts in Linux hosting ® <<

XLhost.de GmbH
Jürgen Herrmann, Geschäftsführer
Boelckestrasse 21, 93051 Regensburg, Germany

Geschäftsführer: Volker Geith, Jürgen Herrmann
Registriert unter: HRB9918
Umsatzsteuer-Identifikationsnummer: DE245931218

Fon:  +49 (0)700 XLHOSTDE [0700 95467833]
Fax:  +49 (0)700 XLHOSTDE [0700 95467833]

WEB:  http://www.XLhost.de
IRC:  #XLhost@irc.quakenet.org


------------------------------------------------------------------------------
The NEW KODAK i700 Series Scanners deliver under ANY circumstances! Your
production scanning environment may not be a perfect world - but thanks to
Kodak, there's a perfect scanner to get the job done! With the NEW KODAK i700
Series Scanner you'll get full speed at 300 dpi even with all image 
processing features enabled. http://p.sf.net/sfu/kodak-com
_______________________________________________
Ceph-devel mailing list
Ceph-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ceph-devel


[prev in list] [next in list] [prev in thread] [next in thread]