[GE users] question about queues and limitations to specific nodes

reuti reuti at staff.uni-marburg.de
Fri May 14 10:13:02 BST 2010


Am 13.05.2010 um 23:12 schrieb gragghia:

> Yes, you can use the "-w" option to qsub.  This will throw an error to 
> the user if the job is won't be able to run (without a configuration 
> change).  We add a line "-w e" to our site sge_request file in order to 
> make this behavior the default for all users.

Correct, this will work.

But:

It shouldn't be necessary to specify queues at all in your `qsub`command, as this is Torque-style job submission. In SGE you request resources like:

- time
- memory
- software licenses
- parallel environments

and SGE will select an appropriate queue for your job. Especially if you have already setup "user_lists" on a queue or host level, SGE will do the right thing automatically. Setting up "user_lists" for queues and request the queues also in the `qsub` command is superfluous.

-- Reuti


>> qw state and does not run - this is great!  Is there some way that I can
>> have the job return and error to the user that this was the reason why
>> the job did not run - wrong queue?
>> Thanks.
>> 
>> gragghia wrote:
>> 
>>> To only allow certain users use of the IB machines, I would make them a
>>> cluster queue and then only set the "allow" list.  Explicitly added the
>>> "deny" list is not needed.
>>> 
>>> How is the file /opt/mpdd_tmp/hydra.hosts being created?  If it is
>>> dynamic, you should cat the contents of this file out to ensure that it
>>> contains the correct hosts.  You may also want to execute "qstat -g t"
>>> within the batch script to show what SGE thinks it is allocating to you.
>>> 
>>> If you provide the output for "qconf -sq ib.q" and "qconf -sq
>>> ethernet.q" it will help a lot in determining the source of the problem.
>>> 
>>> - Gerald
>>> 
>>> 
>>> On 5/12/2010 4:28 PM, jnorris wrote:
>>> 
>>> 
>>>> Hello to all,
>>>> 
>>>> Here is the situation:
>>>> 
>>>> I have 66 nodes total in my cluster - I need to allow select users to
>>>> access the first 8 nodes and all users access the remaining nodes.
>>>> 
>>>> The first 8 nodes I put into a queue ib.q and the rest in ethernet.q  I
>>>> set the exclude user list on IB to all of the user lists of those that
>>>> should not be allowed and the user list to the users that are allowed.
>>>> With ethernet.q  I have all user list in users and NONE for exclude users.
>>>> 
>>>> Then I did some testing with a simple hello script that keeps track of
>>>> what node its running on and prints the message:
>>>> 
>>>> Hello from process 0 on c1
>>>> Hello from process 1 on c2
>>>> Hello from process 2 on c3
>>>> Hello from process 3 on c4
>>>> Hello from process 4 on c5
>>>> Hello from process 5 on c6
>>>> Hello from process 6 on c7
>>>> Hello from process 7 on c8
>>>> 
>>>> 
>>>> I set the #$ -q ethernet.q  in the script and set the run as:
>>>> 
>>>> mpiexec.hydra  -f /opt/mpdd_tmp/hydra.hosts  -n 10 ./hello
>>>> 
>>>> The out put above is what I obtain.  Ok here are my questions:
>>>> 
>>>> 1)  is this the best way to do this? - I am real newbie to sge
>>>> 2)  by the scenario above and considering that c1-c8 are the nodes that
>>>> should not be in this output - what am I doing wrong?
>>>> 
>>>> Thank beforehand for any and all help.
>>>> 
>>>> 
>>>> 
>>>> 
>>>> 
>>>> 
>>> 
>>> 
>> 
> 
> -- 
> Gerald Ragghianti
> 
> Newton HPC Program http://newton.utk.edu/
> Office of Information Technology
>   Research Computing Support
>   Professional Technical Services
> 
> The University of Tennessee
> 2309 Kingston Pike
> Knoxville, TN 37996
> Phone: 865-974-2448
> 
> /-------------------------------------\
> | One Contact       OIT: 865-974-9900 |
> | Many Solutions         help.utk.edu |
> \-------------------------------------/
> 
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=257213
> 
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=257255

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list