[GE users] A misbehaving execution host

Sean Davis sdavis2 at mail.nih.gov
Fri May 16 18:20:55 BST 2008


    [ The following text is in the "UTF-8" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some characters may be displayed incorrectly. ]

On Fri, May 16, 2008 at 12:56 PM, Shilpi Gupta <er.guptashilpi at gmail.com> wrote:
> hi Sean,
>
> as ur execution host reports its status as "au", according to manual "a"
> means alarm nd "u" means unreachable so first of all check dat ur network
> connections r fine nd ur master host is able to reach ur execution host.
>
> and if the network is fine then check log messages in the spool/hostname
> directory of ur execution host nd from that messages file try to find out
> what the problem is.

I must have corrupted something at some point on that host.
Reinstalling using install_execd worked to fix the problem.

Thanks,
Sean

> On Fri, May 16, 2008 at 10:11 PM, Sean Davis <sdavis2 at mail.nih.gov> wrote:
>>
>> This is a pretty elementary question, I know, but I have an execution
>> host that is not reporting load average, memused, or swapused on qhost
>> (but does report memtot, swaptot, and ncpu correctly).  Also, it is
>> reporting a status "au" on qstat -f.  I have tried restarting the
>> sgeexecd, but that doesn't change things.  Can someone point me in the
>> right direction for troubleshooting this problem?
>>
>> Thanks,
>> Sean
>>
>> ---------------------------------------------------------------------
>> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
>> For additional commands, e-mail: users-help at gridengine.sunsource.net
>>
>
>

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list