[Mauiusers] maui/torque communication problem using qsub -l nodes=x:ppn=y, y > 1

Matthias Schoepfer mschoepf at techfak.uni-bielefeld.de
Wed Mar 3 05:59:38 MST 2010


Hi!

I am experiencing the following problem when using torque/maui.

When I request

qsub -l nodes=5:ppn=8 script.sh

maui will reserve 5 nodes, but my program is eventually only executed on
one node, and also the PBS_NODEFILE is wrong (as it only mentions one
node). The job is an OpenMPI job.

When I request

qsub -l nodes=1:ppn=1 script.sh

I will correctly get 5 nodes with one process each and a correct
PBS_NODEFILE.

What am I missing? Here are some log etc:

We have 16 nodes with 8 cores each, JOBNODEMATCHPOLICY is on EXACTNODE.


maui.log with nodes=5:ppn=8:

03/03 12:56:27 INFO:     128 feasible tasks found for job 1475:0 in
partition DEFAULT (40 Needed)
03/03 12:56:27 MJobGetINL(1475,FNL,INL,DEFAULT,NodeCount,TaskCount)
03/03 12:56:27
MNodeSelectIdleTasks(1475,0,SrcNL,IdleMNL,TC,NC,NMap,RCount,RejReason)
03/03 12:56:27 INFO:     64(0) tasks/8(0) nodes found for job 1475 in
MJobSelectMNL
03/03 12:56:27 MJobNLDistribute(1475,SrcMNL,DstMNL)
03/03 12:56:27 INFO:     resources found for job 1475 tasks: 64+0 of 40
 nodes: 8+0 of 0
03/03 12:56:27
MJobAllocMNL(1475,MFeasibleList,NodeMap,NULL,LASTAVAILABLE,1267617387)
03/03 12:56:27 INFO:     tasks located for job 1475:  40 of 40 required
(24 feasible)
03/03 12:56:27 INFO:     allocated MNode[000]x8 'node07' to 1475:0
03/03 12:56:27 INFO:     allocated MNode[001]x8 'node06' to 1475:0
03/03 12:56:27 INFO:     allocated MNode[002]x8 'node05' to 1475:0
03/03 12:56:27 INFO:     allocated MNode[003]x8 'node04' to 1475:0
03/03 12:56:27 INFO:     allocated MNode[004]x8 'node03' to 1475:0
03/03 12:56:27 MJobStart(1475)
03/03 12:56:27 MJobDistributeTasks(1475,0,NodeList,TaskMap)
03/03 12:56:27 INFO:     5 node(s)/40 task(s) added to 1475:0
03/03 12:56:27 INFO:     MNode[000] 'node07'(x8) added to job '1475'
03/03 12:56:27 INFO:     MNode[001] 'node06'(x8) added to job '1475'
03/03 12:56:27 INFO:     MNode[002] 'node05'(x8) added to job '1475'
03/03 12:56:27 INFO:     MNode[003] 'node04'(x8) added to job '1475'
03/03 12:56:27 INFO:     MNode[004] 'node03'(x8) added to job '1475'
03/03 12:56:27 MAMAllocJReserve(1475,RIndex,ErrMsg)
03/03 12:56:27 MRMJobStart(1475,Msg,SC)
03/03 12:56:27 MPBSJobStart(1475,0,Msg,SC)
03/03 12:56:27 MPBSJobModify(1475,Resource_List,Resource,node03:ppn=8)
03/03 12:56:27 MPBSJobModify(1475,Resource_List,Resource,5:ppn=8)
03/03 12:56:27 INFO:     job '1475' successfully started
03/03 12:56:27 MQueueAddAJob(1475)
03/03 12:56:27 MStatUpdateActiveJobUsage(1475)
03/03 12:56:27 MPolicyAdjustUsage(NULL,1475,NULL,active,NULL,[ALL],1,NULL)
03/03 12:56:27 MResJCreate(1475,MNodeList,00:00:00,ActiveJob,Res)
03/03 12:56:27 MResAdjustDRes(1475,FALSE)
03/03 12:56:27 MPolicyAdjustUsage(NULL,1475,NULL,idle,PU,[ALL],-1,NULL)
03/03 12:56:27 MPolicyAdjustUsage(NULL,1475,NULL,idle,NULL,[ALL],-1,NULL)
03/03 12:56:27 MJobAddToNL(1475,NULL)
03/03 12:56:27 INFO:     node node07 added to job 1475.  PSlot: [short 8:8]
03/03 12:56:27 INFO:     node node06 added to job 1475.  PSlot: [short 8:8]
03/03 12:56:27 INFO:     node node05 added to job 1475.  PSlot: [short 8:8]
03/03 12:56:27 INFO:     node node04 added to job 1475.  PSlot: [short 8:8]
03/03 12:56:27 INFO:     node node03 added to job 1475.  PSlot: [short 8:8]
03/03 12:56:27 INFO:     starting job '1475'
03/03 12:56:37 INFO:     active PBS job 1475 has been removed from the
queue.  assuming successful completion
03/03 12:56:37 MJobProcessCompleted(1475)
03/03 12:56:37 MAMAllocJDebit(A,1475,SC,ErrMsg)
03/03 12:56:37 MJobWriteStats(1475)
03/03 12:56:37 MJobToTString(1475,230,Buf,65536)
03/03 12:56:37 INFO:     job stats written for '1475'
03/03 12:56:37 INFO:     job '              1475' completed.  QueueTime:
     1  RunTime:     10  Accuracy:  0.03  XFactor:  0.00
03/03 12:56:37 INFO:     job '1475' completed  X: 0.000382  T: 10  PS:
400  A: 0.000347
03/03 12:56:37 MJobSendFB(1475)
03/03 12:56:37 INFO:     job usage sent for job '1475'

pbs_server.log with nodes=5:ppn=8:
03/03/2010 12:56:26;0008;PBS_Server;Job;1475.macabeo;ready to commit job
03/03/2010 12:56:26;0008;PBS_Server;Job;1475.macabeo;ready to commit job
completed
03/03/2010 12:56:26;0008;PBS_Server;Job;1475.macabeo;committing job
03/03/2010 12:56:26;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from TRANSIT-TRANSICM to QUEUED-QUEUED (1-10)
03/03/2010 12:56:26;0100;PBS_Server;Job;1475.macabeo;enqueuing into
medium, state 1 hop 1
03/03/2010 12:56:26;0008;PBS_Server;Job;1475.macabeo;Job Queued at
request of mschoepf at macabeo, owner = mschoepf at macabeo, job name =
mpitest, queue = medium
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;attr Resource_List
modified
03/03/2010 12:56:27;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from QUEUED-QUEUED to QUEUED-QUEUED (1-10)
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;Job Modified at
request of root at macabeo
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocating nodes for
job 1475.macabeo with node expression 'node03:ppn=8'
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/0 to job 1475.macabeo (nsnfree=8)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/1 to job 1475.macabeo (nsnfree=7)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/2 to job 1475.macabeo (nsnfree=6)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/3 to job 1475.macabeo (nsnfree=5)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/4 to job 1475.macabeo (nsnfree=4)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/5 to job 1475.macabeo (nsnfree=3)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/6 to job 1475.macabeo (nsnfree=2)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;allocated node
node03/7 to job 1475.macabeo (nsnfree=1)
03/03/2010 12:56:27;0040;PBS_Server;Req;set_nodes;job 1475.macabeo
allocated 8 nodes
(nodelist=node03/7+node03/6+node03/5+node03/4+node03/3+node03/2+node03/1+node03/0)
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;Job Run at request
of root at macabeo
03/03/2010 12:56:27;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from QUEUED-QUEUED to RUNNING-PRERUN (4-40)
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;forking in send_job
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;send_job child job
pid is 28449
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;entering post_sendmom
03/03/2010 12:56:27;0002;PBS_Server;Job;1475.macabeo;child reported
success for job after 0 seconds (dest=node03), rc=0
03/03/2010 12:56:27;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from RUNNING-PRERUN to RUNNING-RUNNING (4-42)
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;attr Resource_List
modified
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;Job Modified at
request of root at macabeo
03/03/2010 12:56:27;0008;PBS_Server;Job;1475.macabeo;attr session_id
modified
03/03/2010 12:56:27;000d;PBS_Server;Job;1475.macabeo;sending 'b' mail
for job 1475.macabeo to mschoepf at macabeo (---)
03/03/2010 12:56:36;0009;PBS_Server;Job;1475.macabeo;obit received
03/03/2010 12:56:36;0009;PBS_Server;Job;1475.macabeo;obit received -
updating final job usage info
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;attr resources_used
modified
03/03/2010 12:56:36;0009;PBS_Server;Job;1475.macabeo;job exit status 0
handled
03/03/2010 12:56:36;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from RUNNING-RUNNING to EXITING-EXITING
(5-50)
03/03/2010 12:56:36;000d;PBS_Server;Job;1475.macabeo;sending 'e' mail
for job 1475.macabeo to mschoepf at macabeo (Exit_status=0
03/03/2010 12:56:36;0010;PBS_Server;Job;1475.macabeo;Exit_status=0
resources_used.cput=00:00:05 resources_used.mem=14792kb
resources_used.vmem=161676kb resources_used.walltime=00:00:09
03/03/2010 12:56:36;0009;PBS_Server;Job;1475.macabeo;on_job_exit task
assigned to job
03/03/2010 12:56:36;0009;PBS_Server;Job;1475.macabeo;req_jobobit completed
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_EXITING
03/03/2010 12:56:36;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from EXITING-EXITING to EXITING-STAGEOUT
(5-51)
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_STAGEOUT
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;about to copy
stdout/stderr/stageout files
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_STAGEOUT
03/03/2010 12:56:36;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from EXITING-STAGEOUT to EXITING-STAGEDEL
(5-52)
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_STAGEDEL
03/03/2010 12:56:36;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from EXITING-STAGEDEL to EXITING-EXITED
(5-53)
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_EXITED
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing nodes for job
1475.macabeo
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/0
from job 1475.macabeo (nsnfree=0)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/1
from job 1475.macabeo (nsnfree=1)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/2
from job 1475.macabeo (nsnfree=2)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/3
from job 1475.macabeo (nsnfree=3)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/4
from job 1475.macabeo (nsnfree=4)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/5
from job 1475.macabeo (nsnfree=5)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/6
from job 1475.macabeo (nsnfree=6)
03/03/2010 12:56:36;0040;PBS_Server;Req;free_nodes;freeing node node03/7
from job 1475.macabeo (nsnfree=7)
03/03/2010 12:56:36;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1475.macabeo state from EXITING-EXITED to COMPLETE-COMPLETE
(6-59)
03/03/2010 12:56:36;0008;PBS_Server;Job;1475.macabeo;JOB_SUBSTATE_COMPLETE
03/03/2010 12:56:36;0100;PBS_Server;Job;1475.macabeo;dequeuing from
medium, state COMPLETE
03/03/2010 12:56:36;0080;PBS_Server;Job;1475.macabeo;removed job script
03/03/2010 12:56:36;0080;PBS_Server;Job;1475.macabeo;removed job file
03/03/2010 13:42:32;0008;PBS_Server;Job;1669.macabeo;send_job child job
pid is 1475
03/03/2010 13:42:32;0040;PBS_Server;Req;next_task;DISPATCH Task
WORK_Deferred_Cmp type 6, wt_event 1475, wt_aux 0


maui log for nodes=5:ppn=1

03/03 13:57:04 INFO:     node node03 has joblist '0/1786.macabeo'
03/03 13:57:04 INFO:     job 1786 adds 1 processors per task to node
node03 (1)
03/03 13:57:04 INFO:     node node04 has joblist '0/1786.macabeo'
03/03 13:57:04 INFO:     job 1786 adds 1 processors per task to node
node04 (1)
03/03 13:57:04 INFO:     node node05 has joblist '0/1786.macabeo'
03/03 13:57:04 INFO:     job 1786 adds 1 processors per task to node
node05 (1)
03/03 13:57:04 INFO:     node node06 has joblist '0/1786.macabeo'
03/03 13:57:04 INFO:     job 1786 adds 1 processors per task to node
node06 (1)
03/03 13:57:04 INFO:     node node07 has joblist '0/1786.macabeo'
03/03 13:57:04 INFO:     job 1786 adds 1 processors per task to node
node07 (1)
03/03 13:57:04 MPBSJobUpdate(1786,1786.macabeo,TaskList,0)
03/03 13:57:04 INFO:     job 1786 starttime: 1267621021 (00:00:03)
presenttime: 1267621024  wclimit: 28800  mtime: 1267621021  etime:
1267621021  walltime: 0  state: Running
03/03 13:57:04 MQueueAddAJob(1786)
03/03 13:57:04 MStatUpdateActiveJobUsage(1786)
03/03 13:57:04 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:04 MResDestroy(1786)
03/03 13:57:04 MResChargeAllocation(1786,2)
03/03 13:57:04 MResAdjustDRes(1786,TRUE)
03/03 13:57:04 MResJCreate(1786,MNodeList,-00:00:03,ActiveJob,Res)
03/03 13:57:04 MResAdjustDRes(1786,FALSE)
03/03 13:57:04 MJobAddToNL(1786,NULL)
03/03 13:57:04 INFO:     node node07 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:04 INFO:     node node06 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:04 INFO:     node node05 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:04 INFO:     node node04 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:04 INFO:     node node03 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:04 INFO:     job '1786' Priority:        1
03/03 13:57:04 MPolicyAdjustUsage(NULL,1786,NULL,active,PU,[ALL],1,NULL)
03/03 13:57:04 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:04 INFO:     job '1786' Priority:        1
03/03 13:57:05 INFO:     node node03 has joblist '0/1786.macabeo'
03/03 13:57:05 INFO:     job 1786 adds 1 processors per task to node
node03 (1)
03/03 13:57:05 INFO:     node node04 has joblist '0/1786.macabeo'
03/03 13:57:05 INFO:     job 1786 adds 1 processors per task to node
node04 (1)
03/03 13:57:05 INFO:     node node05 has joblist '0/1786.macabeo'
03/03 13:57:05 INFO:     job 1786 adds 1 processors per task to node
node05 (1)
03/03 13:57:05 INFO:     node node06 has joblist '0/1786.macabeo'
03/03 13:57:05 INFO:     job 1786 adds 1 processors per task to node
node06 (1)
03/03 13:57:05 INFO:     node node07 has joblist '0/1786.macabeo'
03/03 13:57:05 INFO:     job 1786 adds 1 processors per task to node
node07 (1)
03/03 13:57:06 MPBSJobUpdate(1786,1786.macabeo,TaskList,0)
03/03 13:57:06 INFO:     job 1786 starttime: 1267621021 (00:00:04)
presenttime: 1267621025  wclimit: 28800  mtime: 1267621021  etime:
1267621021  walltime: 0  state: Running
03/03 13:57:06 MQueueAddAJob(1786)
03/03 13:57:06 MStatUpdateActiveJobUsage(1786)
03/03 13:57:06 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:06 MResDestroy(1786)
03/03 13:57:06 MResChargeAllocation(1786,2)
03/03 13:57:06 MResAdjustDRes(1786,TRUE)
03/03 13:57:06 MResJCreate(1786,MNodeList,-00:00:04,ActiveJob,Res)
03/03 13:57:06 MResAdjustDRes(1786,FALSE)
03/03 13:57:06 MJobAddToNL(1786,NULL)
03/03 13:57:06 INFO:     node node07 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:06 INFO:     node node06 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:06 INFO:     node node05 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:06 INFO:     node node04 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:06 INFO:     node node03 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:06 INFO:     job '1786' Priority:        1
03/03 13:57:06 MPolicyAdjustUsage(NULL,1786,NULL,active,PU,[ALL],1,NULL)
03/03 13:57:06 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:06 INFO:     job '1786' Priority:        1
03/03 13:57:07 INFO:     node node03 has joblist '0/1786.macabeo'
03/03 13:57:07 INFO:     job 1786 adds 1 processors per task to node
node03 (1)
03/03 13:57:07 INFO:     node node04 has joblist '0/1786.macabeo'
03/03 13:57:07 INFO:     job 1786 adds 1 processors per task to node
node04 (1)
03/03 13:57:07 INFO:     node node05 has joblist '0/1786.macabeo'
03/03 13:57:07 INFO:     job 1786 adds 1 processors per task to node
node05 (1)
03/03 13:57:07 INFO:     node node06 has joblist '0/1786.macabeo'
03/03 13:57:07 INFO:     job 1786 adds 1 processors per task to node
node06 (1)
03/03 13:57:07 INFO:     node node07 has joblist '0/1786.macabeo'
03/03 13:57:07 INFO:     job 1786 adds 1 processors per task to node
node07 (1)
03/03 13:57:07 MPBSJobUpdate(1786,1786.macabeo,TaskList,0)
03/03 13:57:07 INFO:     job 1786 starttime: 1267621021 (00:00:06)
presenttime: 1267621027  wclimit: 28800  mtime: 1267621021  etime:
1267621021  walltime: 0  state: Running
03/03 13:57:07 MQueueAddAJob(1786)
03/03 13:57:07 MStatUpdateActiveJobUsage(1786)
03/03 13:57:07 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:07 MResDestroy(1786)
03/03 13:57:07 MResChargeAllocation(1786,2)
03/03 13:57:07 MResAdjustDRes(1786,TRUE)
03/03 13:57:07 MResJCreate(1786,MNodeList,-00:00:06,ActiveJob,Res)
03/03 13:57:07 MResAdjustDRes(1786,FALSE)
03/03 13:57:07 MJobAddToNL(1786,NULL)
03/03 13:57:07 INFO:     node node07 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:07 INFO:     node node06 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:07 INFO:     node node05 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:07 INFO:     node node04 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:07 INFO:     node node03 added to job 1786.  PSlot: [short 8:8]
03/03 13:57:07 INFO:     job '1786' Priority:        1
03/03 13:57:07 MPolicyAdjustUsage(NULL,1786,NULL,active,PU,[ALL],1,NULL)
03/03 13:57:07 MPolicyAdjustUsage(NULL,1786,NULL,active,NULL,[ALL],1,NULL)
03/03 13:57:07 INFO:     job '1786' Priority:        1


pbs_server.log for nodes=5:ppn=1

03/03/2010 13:04:25;0040;PBS_Server;Req;next_task;DISPATCH Task #2 type
1, wt_event 1267617865, wt_aux 0
03/03/2010 13:04:25;0040;PBS_Server;Req;dispatch_task;handling work task
type 1, wt_event 1267617865, wt_aux 0
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;ready to commit job
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;ready to commit job
completed
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;committing job
03/03/2010 13:57:01;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1786.macabeo state from TRANSIT-TRANSICM to QUEUED-QUEUED (1-10)
03/03/2010 13:57:01;0100;PBS_Server;Job;1786.macabeo;enqueuing into
medium, state 1 hop 1
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;Job Queued at
request of mschoepf at macabeo, owner = mschoepf at macabeo, job name =
mpitest, queue = medium
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;attr Resource_List
modified
03/03/2010 13:57:01;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1786.macabeo state from QUEUED-QUEUED to QUEUED-QUEUED (1-10)
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;Job Modified at
request of root at macabeo
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocating nodes for
job 1786.macabeo with node expression 'node07+node06+node05+node04+node03'
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocated node
node03/0 to job 1786.macabeo (nsnfree=8)
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocated node
node04/0 to job 1786.macabeo (nsnfree=8)
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocated node
node05/0 to job 1786.macabeo (nsnfree=8)
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocated node
node06/0 to job 1786.macabeo (nsnfree=8)
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;allocated node
node07/0 to job 1786.macabeo (nsnfree=8)
03/03/2010 13:57:01;0040;PBS_Server;Req;set_nodes;job 1786.macabeo
allocated 5 nodes (nodelist=node07/0+node06/0+node05/0+node04/0+node03/0)
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;Job Run at request
of root at macabeo
03/03/2010 13:57:01;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1786.macabeo state from QUEUED-QUEUED to RUNNING-PRERUN (4-40)
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;forking in send_job
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;send_job child job
pid is 3834
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;entering post_sendmom
03/03/2010 13:57:01;0002;PBS_Server;Job;1786.macabeo;child reported
success for job after 0 seconds (dest=node07), rc=0
03/03/2010 13:57:01;0001;PBS_Server;Svr;PBS_Server;svr_setjobstate:
setting job 1786.macabeo state from RUNNING-PRERUN to RUNNING-RUNNING (4-42)
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;attr Resource_List
modified
03/03/2010 13:57:01;0008;PBS_Server;Job;1786.macabeo;Job Modified at
request of root at macabeo

-- 

MfG  Matthias Schoepfer

email:mschoepf at techfak.uni-bielefeld.de, PGP-Key auf Anfrage

	      		       --- Werbung ---
				Math Problems?
                                     Call
                   0190-((10x)(13i)²)-(sin(xy)(log(y)))³


More information about the mauiusers mailing list