[GE users] Re: [Fwd: Re: [GE users] cannot run because no access to pe]

Bo Chu beowulfnewbee at gmail.com
Wed Dec 3 17:06:02 GMT 2008


Thanks Rayson,
According to queue_conf
" The  formerly supported types parallel and checkpointing are not allowed  
anymore.
        A queue instance is implicitly of type parallel/checkpointing if  
there is a  par-
        allel  environment or a checkpointing interface specified for this  
queue instance
        in pe_list/ckpt_list"

So, I implicitly specify the pe with MPI, this is what my queue config  
looks like. Still getting this
cannot run because no access to pe "MPI"
cannot run in PE "MPI" because it only offers 0 slots

Any suggestion? Thanks
# qconf -sq node1-4
qname                 node1-4
hostlist              @x86_64
seq_no                0
load_thresholds       np_load_avg=1.75
suspend_thresholds    NONE
nsuspend              1
suspend_interval      00:05:00
priority              0
min_cpu_interval      00:05:00
processors            UNDEFINED
qtype                 BATCH INTERACTIVE
ckpt_list             NONE
pe_list               MPI make
rerun                 FALSE
slots                 8
tmpdir                /tmp
shell                 /bin/sh
prolog                NONE
epilog                NONE
shell_start_mode      unix_behavior
starter_method        NONE
suspend_method        NONE
resume_method         NONE
terminate_method      NONE
notify                00:00:60
owner_list            NONE
user_lists            NONE
xuser_lists           NONE
subordinate_list      NONE
complex_values        NONE
projects              NONE
xprojects             NONE
calendar              NONE
initial_state         enabled
s_rt                  INFINITY
h_rt                  INFINITY
s_cpu                 INFINITY
h_cpu                 INFINITY
s_fsize               INFINITY
h_fsize               INFINITY
s_data                INFINITY
h_data                INFINITY
s_stack               INFINITY
h_stack               INFINITY
s_core                INFINITY
h_core                INFINITY
s_rss                 INFINITY
h_rss                 INFINITY
s_vmem                INFINITY
h_vmem                INFINITY


> Rayson
>
>
> On 12/2/08, Bo <beowulfnewbee at gmail.com> wrote:
>> I'm having problem running the parallel job. I'm not sure if some
>> misconfiguration since I'm new to SGE.
>> My test job submitted ok but when I do qstat I got this error
>> cannot run because no access to pe "mpich1"
>> cannot run in PE because it only offer 0 slots
>> or...something like this. I need to run again later today if you want
>> the exact output.
>> My job stays in qw stat and never got dispatched.
>> Please let me know what to check and start troubleshooting this. My guts
>> tells me the parallel environment is not set up right  ( or the queue
>> even)
>> All hosts appear to be up and no error state. Nothing is running on the
>> cluster (it's a 4 nodes cluster with centos 5.2)
>> Thanks for the help
>> Bo
>>
>> ------------------------------------------------------
>>
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=90763
>>
>> To unsubscribe from this discussion, e-mail: [
> users-unsubscribe at gridengine.sunsource.net].
>>
>
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=90790
>
> To unsubscribe from this discussion, e-mail: [
> users-unsubscribe at gridengine.sunsource.net].
> --
> Viet Phan
> Aspen Systems, Inc.
> support at aspsys.com
> Phone: 303-431-4606 Ext. 111
> Fax: 303-431-7196
> http://www.aspsys.com
>
>



-- 
Using Opera's revolutionary e-mail client: http://www.opera.com/mail/

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=90913

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



More information about the gridengine-users mailing list