Hi,

Am 30.12.2013 um 22:21 schrieb Eric Kaufmann:

> I have set up a new queue on GE 6.2u5.
> 
> When I submit a job it just sits in the qw state. Below is the error message.
> 
>  cannot run in PE "gauss" because it only offers 0 slots
> 
> Here is the configuration for queue. I removed the names of the hosts.
> 
> qname                 std
> hostlist              

a) is the desired host in the hostlist or any hostgroup?

> 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               gauss make
> rerun                 FALSE
> slots                 32,

b) has this host in question the correct amount of slots defined?

c) is there any additional slot limit in the exechost definition?

Unfortunately the error message "because it only offers 0 slots" can have 
several reasons, and it's sometimes not easy to get to the root of it.

What is the output of:

$ qalter -w v <job_id>

$ qalter -w p <job_id>

for the waiting job?

d) Is there any memory defined/requested by h_vmem / virtual_free on an 
exechost level and a defined default value in the complex definition.

-- Reuti


> tmpdir                /tmp
> shell                 /bin/csh
> prolog                NONE
> epilog                NONE
> shell_start_mode      posix_compliant
> starter_method        NONE
> suspend_method        NONE
> resume_method         NONE
> terminate_method      NONE
> notify                60
> owner_list            NONE
> user_lists            NONE
> xuser_lists           NONE
> subordinate_list      NONE
> complex_values        NONE
> projects              NONE
> xprojects             NONE
> calendar              NONE
> initial_state         default
> 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
> 
> Here is the configuration of the pe:
> 
> pe_name            gauss
> slots              999
> user_lists         NONE
> xuser_lists        NONE
> start_proc_args    /bin/true
> stop_proc_args     /bin/true
> allocation_rule    $fill_up
> control_slaves     FALSE
> job_is_first_task  FALSE
> urgency_slots      min
> accounting_summary TRUE
> 
> The job I am submitting request 4 processors on an 8 processor machine. There 
> are no other jobs running on the cluster at this time. I have looked around 
> and did change the allocation_rule to $fill_up. Didn't seem to help though.
> 
> -- 
> Eric Kaufmann |  Application Support Analyst -  Advanced Technology Group | 
> Saint Louis University | 314-977-2257 | [email protected] 
> 
> _______________________________________________
> users mailing list
> [email protected]
> https://gridengine.org/mailman/listinfo/users


_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users

Reply via email to