[torqueusers] PBS_NODEFILE incomplete

[Christopher Samuel]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi Scott,

On 21/12/10 16:44, Scott Hazelhurst wrote:


> 2. checkjob -v --------------------------------------------------
> 
> 
> checking job 5766 (RM job '5766.cream-ce.core.wits.ac.za')
> 
[..]
> Allocated Nodes:
> [n05.core.wits.ac.za:8][n04.core.wits.ac.za:8]

So Maui has got everything right by the look of it.

> 3. Result of qstat -f

[...]
>     exec_host = 
> n04.core.wits.ac.za/7+n04.core.wits.ac.za/6+n04.core.wits.ac.z
> a/5+n04.core.wits.ac.za/4+n04.core.wits.ac.za/3+n04.core.wits.ac.za/2+
>         n04.core.wits.ac.za/1+n04.core.wits.ac.za/0

Awooga - exec_host hasn't been set correctly to match
what Maui thinks it should be!  Do you have any errors
in your Maui logs or pbs_server logs corresponding to
this job ?

> 4. Output of PBS_NODES
> 
[...]

That's not actually wrong in the sense that it agrees with
where the pbs_server thinks the job should be running, but
that's not where Maui thinks it should be.

I'd guess a communication error between Maui and Torque,
though your Torque version is pretty old...

I notice that you're running a very old version of Maui,
there have been 4 more snapshot releases since that one
plus an entire new version (3.3) - any chance you could
try with a newer one in case it's been fixed since then ?

cheers,
Chris
- -- 
 Christopher Samuel - Senior Systems Administrator
 VLSCI - Victorian Life Sciences Computational Initiative
 Email: samuel at unimelb.edu.au Phone: +61 (0)3 903 55545
         http://www.vlsci.unimelb.edu.au/

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/

iEYEARECAAYFAk0RL94ACgkQO2KABBYQAh8gUgCfQ7uOkG0xZDIUb6KDhYvktgNQ
QO8AoIqIys16uGGrblBQRp6w00fyOV3I
=Ct1F
-----END PGP SIGNATURE-----