[Mauiusers] Couldn`t submit any job: Cannot set hostlist

[Garrick Staples]

On Thu, Apr 13, 2006 at 10:48:41AM +0800, renyanliang alleged:
> Dear everybody:
>        Glad to meet you, I used the openpbs v2.3.16 and maui 3.2.6p14, However, anybody submitted job always couldn`t run and alway defered by maui, the shown reason is : 
>   ===========================
>   checking job 5111
>  
> job is deferred.  Reason:  RMFailure  (job cannot be started - cannot set hostlist)
> Holds:    Defer  (hold reason:  RMFailure)

Your openpbs server log may tell you why maui wasn't able to set the
job's hostlist.


> #
> # Set server attributes.
> #
> set server scheduling = True
> set server managers = liu@*

I hope you have openpbs firewalled because that means any user "liu"
anywhere in the world is your server admin.

Maui needs to also be a manager.  You need to add the username that is
running maui.


> 04/13 11:02:48 MPBSQueryMOM(rcmm6,rcmm1,Msg,SC)
> 04/13 11:02:48 ALERT:    cannot get req from MOM on node 'rcmm6' (errno: 0:5)
> 04/13 11:02:48 INFO:     MOM info for host 'rcmm6' successfully updated (Thu Apr 13 11:02:48

> 04/13 11:02:48 MPBSQueryMOM(rcmm8,rcmm1,Msg,SC) 
> 04/13 11:02:48 ALERT:    cannot get req from MOM on node 'rcmm8' (errno: 0:5)
> 04/13 11:02:48 INFO:     MOM info for host 'rcmm8' successfully updated (Thu Apr 13 11:02:48

> 04/13 11:02:48 MPBSQueryMOM(rcmm9,rcmm1,Msg,SC)
> 04/13 11:02:48 ALERT:    cannot get req from MOM on node 'rcmm9' (errno: 0:5)
> 04/13 11:02:48 INFO:     MOM info for host 'rcmm9' successfully updated (Thu Apr 13 11:02:48

Since you are using ancient OpenPBS, maui needs to directly query
pbs_mom on each node.  These nodes are rejecting connections from maui.
Is maui running as root?


-- 
Garrick Staples, Linux/HPCC Administrator
University of Southern California
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://www.supercluster.org/pipermail/mauiusers/attachments/20060413/aa86370d/attachment.bin