Re: [Condor-users] Problem in running mpi program

["Dennis Hsu" <dennis.hsu@xxxxxxxxx>]

ï

The messages are:

 

[dennis@grid examples]$ condor_q -analyze

 

-- Submitter: grid.ancad.com : <192.168.10.244:32773> : grid.ancad.com
 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD
---
109.000:  Run analysis summary.  Of 4 machines,
      3 are rejected by your job's requirements
      0 reject your job because of their own requirements
      0 match, but are serving users with a better priority in the pool
      0 match, match, but reject the job for unknown reasons
      0 match, but will not currently preempt their existing job
      1 are available to run your job

 

WARNING: Analysis is meaningless for MPI universe jobs.

 

1 jobs; 1 idle, 0 running, 0 held

 

Dennis

What condor_analyze condor_q -analyze says ?????

On Thu, 2005-04-14 at 07:43, Dennis Hsu wrote:

Hi, John

I reboot all machines and re-submit the MPI job. But it still does not work.
I add the following lines in condor_config.local:

-------------------------------------------------------------
DedicatedScheduler = "DedicatedScheduler@xxxxxxxxxxxxxx"
START          = True
SUSPEND        = False
CONTINUE       = True
PREEMPT        = False
KILL           = False
WANT_SUSPEND   = False
WANT_VACATE    = False
RANK           = Scheduler =?= $(DedicatedScheduler)
MPI_CONDOR_RSH_PATH = $(SBIN)
STARTD_EXPRS = $(STARTD_EXPRS), DedicatedScheduler


-----------------------------------------------------------------
1.) In dedicated scheduler:
DAEMON_LIST = MASTER, STARTD, SCHEDD, NEGOTIATOR, COLLECTOR

2.) Others just activate MASTER and STARTD daemons
DAEMON_LIST = MASTER, STARTD