Hi All,

I am having the same problem on the PBS HDF5 test.  First the test failed
and the next tests (MPIC & LAM) fail due "Not enough free nodes".  So far
I found that the 30 seconds default timeout on pbs_test is too short for
my 10 node cluster to finish the HDF5 test.  When the timeout is completed
the job is supposed to be deleted using 'qdel' but that isn't happening. 
When the other test is going to start (MPICH and LAM) they just failed at
check_free_nodes because all nodes are still busy with the HDF5 test. That
is what gives the "Not enough free nodes" error.  I could arrange the
timeout, but I noticed that the timeout value should be increased
depending on the node count.  Why the tests took more time if I add more
nodes?  Is this suppose to happen or something is wrong in my
configuration?

Thanks,

Freddy

> Is /home mounted on all nodes?  Looks like PBS is failing...
>
>          Jeremy
>
> At 02:06 PM 7/18/2003 -0500, Brandi Winfrey wrote:
>>I did a qstat.  While the FAILED messages were showing up, the message
>> was  as follows:
>>
>>Job id          Name            User            Time Use S Queue
>>-------------   ------------    ------------    -------- - -----
>>3.master        shelltest       oscartst               O E workq
>>
>>
>>as soon as the test said "...Hit enter to exit...", I did a qstat and
>> there was nothing left showing.
>>
>>Brandi
>>
>>_________________________________________________________________ Help
>> STOP SPAM with the new MSN 8 and get 2 months FREE*
>>http://join.msn.com/?page=features/junkmail
>>
>>
>>
>>-------------------------------------------------------
>>This SF.net email is sponsored by: VM Ware
>>With VMware you can run multiple operating systems on a single machine.
>> WITHOUT REBOOTING! Mix Linux / Windows / Novell virtual machines at the
>> same time. Free trial click here: http://www.vmware.com/wl/offer/345/0
>> _______________________________________________
>>Oscar-users mailing list
>>[EMAIL PROTECTED]
>>https://lists.sourceforge.net/lists/listinfo/oscar-users
>
>
>
> -------------------------------------------------------
> This SF.net email is sponsored by: VM Ware
> With VMware you can run multiple operating systems on a single machine.
> WITHOUT REBOOTING! Mix Linux / Windows / Novell virtual machines at the
> same time. Free trial click here: http://www.vmware.com/wl/offer/345/0
> _______________________________________________
> Oscar-users mailing list
> [EMAIL PROTECTED]
> https://lists.sourceforge.net/lists/listinfo/oscar-users





-------------------------------------------------------
This SF.net email is sponsored by: VM Ware
With VMware you can run multiple operating systems on a single machine.
WITHOUT REBOOTING! Mix Linux / Windows / Novell virtual machines at the
same time. Free trial click here: http://www.vmware.com/wl/offer/345/0
_______________________________________________
Oscar-users mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/oscar-users

Reply via email to