Hi,
> 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
Hmm, it's not matching my binary. I rebuilt the packages a few times this
afternoon (as various bugs where fixed), so maybe you got one of the
older ones. Can you just fire up gdb on your end and send a backtrace?
> i'd like to ask a few other questions if you dont mind:
> how is redundany or failover for the mds handled?
If you start multiple cmds instances, the standby will take over (replay
log, reconnect to clients) if the first one fails. The failed instance
will need to be restarted at some point, so you might want to put it in
your machine's startup sequence, and/or set 'restart on core dump = yes'
for the mds.
> why only one entry in the sample config?
No reason.. it's just a sample :)
> how much should i expext it to be working?
Clustered mds isn't working, and the snapshots haven't been tested with
some of the recent changes, but for basic fs usage it should be
pretty stable. There are some lingering issues with the mds restarting
that have to be sorted out, but it will mostly work.
> the kernel client was stalled several times while
> copying directories in my test setup.
When the kernel is doing its async data writeback, metadata is also
flushed back to the mds, which makes the progress of other mds operations
stall.
> btw what's that sudo option for that you mentioned below?
It's obsolete, actually... it doesn't do anything.
> thanks for your help!
No problem. You can also find me in #ceph on irc.oftc.net.. that's
often faster.
sage
>
> 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: #xlh...@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: #xlh...@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
>
>
------------------------------------------------------------------------------
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
