[Mauiusers] Maui stop by itself time to time

vaibhav agrawal agrvaibhav at gmail.com
Sat Jan 19 22:51:06 MST 2008


Hi Chi,

Have u tried the solution of enabling nscd on all the nodes?

- V
On Jan 16, 2008 9:07 PM, Craig Macdonald <craigm at dcs.gla.ac.uk> wrote:

> I had major issues with this about a year ago.
> The solution is to enabled nscd on all nodes, including the machine
> running pbs_server and the machine running maui.
>
> C
>
> Chi-Kiet Ung wrote:
> > Hello,
> >
> > We have a chronic issue with maui scheduler. Sometime, it stops by
> > itself and we have to restart maui.
> > You can find below the error messages I found in maui and torque logs.
> >
> > maui log :
> >
> > 01/14 17:17:15 MStatInitializeActiveSysUsage()
> > 01/14 17:17:15 MStatClearUsage([NONE],Active)
> > 01/14 17:17:15 ServerUpdate()
> > 01/14 17:17:15 MSysUpdateTime()
> > 01/14 17:17:15 INFO:     starting iteration 19015
> > 01/14 17:17:15 MRMGetInfo()
> > 01/14 17:17:15 MClusterClearUsage()
> > 01/14 17:17:15 MRMClusterQuery()
> > 01/14 17:17:15 MPBSClusterQuery(base,RCount,SC)
> > *01/14 17:17:15 ERROR:    cannot get node info: NULL
> >
> > *torque log :
> >
> > *01/14/2008 17:17:25;0002;PBS_Server;Req;dis_reply_write;DIS reply
> > failure, -1*
> >
> > Could you please help us to understand and to fix this issue ?
> >
> > Thank you,
> > Best regards,
> > Chi-Kiet.
> > /
> > /
> > ------------------------------------------------------------------------
> >
> > _______________________________________________
> > mauiusers mailing list
> > mauiusers at supercluster.org
> > http://www.supercluster.org/mailman/listinfo/mauiusers
> >
>
> _______________________________________________
> mauiusers mailing list
> mauiusers at supercluster.org
> http://www.supercluster.org/mailman/listinfo/mauiusers
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/mauiusers/attachments/20080120/c7038f68/attachment.html


More information about the mauiusers mailing list