Maarten Litmaath wrote:
> Hi Tomas,
>
>> i am trying to install lcg-CE with MPI support and I am stuck at pbs
>> jobmanager.
>>
>> I haven't installed any MPI-related stuff yet because first I wanted to try
>> the submission of simple job. When I try to submit via lcgpbs and pbs
>> jobmanager
>> with globus-job-run the submission works fine:
>>
>> [koubat@ui2 ~]$ globus-job-run ce2.egee.cesnet.cz:2119/jobmanager-pbs -q
>> egee_dteam /bin/hostname
>> ok
>> skurut10-2.egee.cesnet.cz
>> [koubat@ui2 ~]$ globus-job-run ce2.egee.cesnet.cz:2119/jobmanager-lcgpbs -q
>> egee_dteam /bin/hostname
>> skurut10-2.egee.cesnet.cz
>>
>>
>> But when I try to submit via WMS the job is stuck in Ready state for pbs
>> jobmanager. For
>> lcgbs it works ok.
>
> Can you send the output of this command for a job sent to the pbs jobmanager:
>
> glite-wms-job-logging-info -v 2 <job-ID>
floi.ics.muni.cz is a WMS from gLite 3.1., but the same happens with WMS from gLite 3.0:
[koubat@ui2 ~]$ glite-wms-job-logging-info -v 2 https://skurut1.cesnet.cz:9000/9ND6YxVwxj9Fn8_atX-wqw
**********************************************************************
LOGGING INFORMATION:
Printing info for the Job : https://skurut1.cesnet.cz:9000/9ND6YxVwxj9Fn8_atX-wqw
---
Event: RegJob
- Arrived = Wed Jun 18 11:45:48 2008 CEST
- Host = floi.ics.muni.cz
- Ns = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Nsubjobs = 0
- Source = NetworkServer
- Src instance = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Timestamp = Wed Jun 18 11:45:48 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: RegJob
- Arrived = Wed Jun 18 11:45:48 2008 CEST
- Host = floi.ics.muni.cz
- Ns = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Nsubjobs = 0
- Source = NetworkServer
- Src instance = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Timestamp = Wed Jun 18 11:45:48 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Masaryk University/CN=floi.ics.muni.cz
---
Event: Accepted
- Arrived = Wed Jun 18 11:45:49 2008 CEST
- From = NetworkServer
- From host = ui2.farm.particle.cz
- Host = floi.ics.muni.cz
- Source = NetworkServer
- Src instance = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Timestamp = Wed Jun 18 11:45:49 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: EnQueued
- Arrived = Wed Jun 18 11:45:49 2008 CEST
- Host = floi.ics.muni.cz
- Queue = /var/glite/workload_manager/input.fl
- Result = START
- Source = NetworkServer
- Src instance = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Timestamp = Wed Jun 18 11:45:49 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: EnQueued
- Arrived = Wed Jun 18 11:45:49 2008 CEST
- Host = floi.ics.muni.cz
- Queue = /var/glite/workload_manager/input.fl
- Result = OK
- Source = NetworkServer
- Src instance = https://147.251.3.51:7443/glite_wms_wmproxy_server
- Timestamp = Wed Jun 18 11:45:49 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: DeQueued
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Host = floi.ics.muni.cz
- Queue = /var/glite/workload_manager/input.fl
- Source = WorkloadManager
- Src instance = 18317
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Match
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Dest id = ce2.egee.cesnet.cz:2119/jobmanager-pbs-egee_dteam
- Host = floi.ics.muni.cz
- Source = WorkloadManager
- Src instance = 18317
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: EnQueued
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Host = floi.ics.muni.cz
- Queue = /var/glite/jobcontrol/queue.fl
- Result = START
- Source = WorkloadManager
- Src instance = 18317
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: EnQueued
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Host = floi.ics.muni.cz
- Queue = /var/glite/jobcontrol/queue.fl
- Result = OK
- Source = WorkloadManager
- Src instance = 18317
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: DeQueued
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Host = floi.ics.muni.cz
- Local jobid = unavailable
- Queue = /var/glite/jobcontrol/queue.fl
- Source = JobController
- Src instance = unique
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Transfer
- Arrived = Wed Jun 18 11:45:50 2008 CEST
- Dest host = localhost
- Dest instance = /var/glite/logmonitor/CondorG.log/CondorG.1213601555.log
- Dest jobid = unavailable
- Destination = LogMonitor
- Host = floi.ics.muni.cz
- Reason = unavailable
- Result = START
- Source = JobController
- Src instance = unique
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Transfer
- Arrived = Wed Jun 18 11:45:51 2008 CEST
- Dest host = localhost
- Dest instance = /var/glite/logmonitor/CondorG.log/CondorG.1213601555.log
- Dest jobid = 26
- Destination = LogMonitor
- Host = floi.ics.muni.cz
- Reason = unavailable
- Result = OK
- Source = JobController
- Src instance = unique
- Timestamp = Wed Jun 18 11:45:50 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Accepted
- Arrived = Wed Jun 18 11:45:55 2008 CEST
- From = JobController
- From host = localhost
- From instance = unavailable
- Host = floi.ics.muni.cz
- Local jobid = 26
- Source = LogMonitor
- Src instance = unique
- Timestamp = Wed Jun 18 11:45:54 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Running
- Arrived = Wed Jun 18 11:46:06 2008 CEST
- Host = skurut10-2.egee.cesnet.cz
- Node = skurut10-2.egee.cesnet.cz
- Source = LRMS
- Timestamp = Wed Jun 18 11:46:06 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: Transfer
- Arrived = Wed Jun 18 11:46:07 2008 CEST
- Dest host = ce2.egee.cesnet.cz:2119/jobmanager-pbs
- Dest instance = /var/glite/logmonitor/CondorG.log/CondorG.1213601555.log
- Dest jobid = unavailable
- Destination = LRMS
- Host = floi.ics.muni.cz
- Reason = Job successfully submitted to Globus
- Result = OK
- Source = LogMonitor
- Src instance = unique
- Timestamp = Wed Jun 18 11:46:07 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: Running
- Arrived = Wed Jun 18 11:46:07 2008 CEST
- Host = floi.ics.muni.cz
- Node = gt2 ce2.egee.cesnet.cz:2119/jobmanager-pbs
- Source = LogMonitor
- Src instance = unique
- Timestamp = Wed Jun 18 11:46:07 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba/CN=proxy/CN=proxy
---
Event: ReallyRunning
- Arrived = Wed Jun 18 11:46:08 2008 CEST
- Host = skurut10-2.egee.cesnet.cz
- Source = LRMS
- Timestamp = Wed Jun 18 11:46:08 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: ResourceUsage
- Arrived = Wed Jun 18 11:48:08 2008 CEST
- Host = skurut10-2.egee.cesnet.cz
- Source = LRMS
- Timestamp = Wed Jun 18 11:48:08 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
---
Event: Done
- Arrived = Wed Jun 18 11:48:10 2008 CEST
- Exit code = 0
- Host = skurut10-2.egee.cesnet.cz
- Source = LRMS
- Status code = OK
- Timestamp = Wed Jun 18 11:48:10 2008 CEST
- User = /DC=cz/DC=cesnet-ca/O=Institute of Physics of the Academy of Sciences of the CR/CN=Tomas Kouba
**********************************************************************
--
Tomas Kouba
Institute of Physics, Academy of sciences of the Czech Republic
|