User Tools

Site Tools


cluster:134

Warning: Undefined array key -1 in /usr/share/dokuwiki/inc/html.php on line 1458

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
cluster:134 [2014/08/20 10:26]
hmeij [High Throughput]
cluster:134 [2014/08/22 09:05] (current)
hmeij [MPI]
Line 101: Line 101:
  
 [[https://computing.llnl.gov/linux/slurm/high_throughput.html]] [[https://computing.llnl.gov/linux/slurm/high_throughput.html]]
 +
 +Vanilla out of the box with these changes
  
   * MaxJobCount=120000   * MaxJobCount=120000
Line 152: Line 154:
 export MYLOCALSCRATCH=/localscratch/$SLURM_JOB_ID export MYLOCALSCRATCH=/localscratch/$SLURM_JOB_ID
 cd $MYLOCALSCRATCH cd $MYLOCALSCRATCH
 +pwd
  
 echo "$SLURMD_NODENAME JOB_PID=$SLURM_JOB_ID" >> foo echo "$SLURMD_NODENAME JOB_PID=$SLURM_JOB_ID" >> foo
Line 162: Line 165:
  
 ^NrJobs^N^hh:mm:ss^ ^NrJobs^N^hh:mm:ss^
-| 1,000|8|00:??:??|  +| 1,000|8|00:05:00|  
-|10,000|8|00:??:??|  +5,000|8|00:23:43|  
-|25,000|8|00:??:??|  +|10,000|8|00:47:12|  
-|50,000|8|00:??:??+|25,000|8|00:58:01
-|75,000|8|00:??:??| + 
-|100,000|8|00:??:??|+ 
 +==== MPI ==== 
 + 
 +With ''sbatch'' there is no need for a wrapper scriptslurm figures it all out. 
 + 
 +<code> 
 + 
 +#!/bin/bash 
 +#/share/apps/lsf/slurm_prolog.pl 
 + 
 +#SBATCH --job-name="MPI" 
 +#SBATCH --ntasks=8 
 +#SBATCH --begin=now 
 + 
 +# unique job scratch dir 
 +#export MYLOCALSCRATCH=/localscratch/$SLURM_JOB_ID 
 +#cd $MYLOCALSCRATCH 
 + 
 +echo "$SLURMD_NODENAME JOB_PID=$SLURM_JOB_ID" 
 + 
 +rm -rf err out logfile mdout restrt mdinfo 
 + 
 +export PATH=/share/apps/openmpi/1.2+intel-9/bin:$PATH 
 +export LD_LIBRARY_PATH=/share/apps/openmpi/1.2+intel-9/lib:$LD_LIBRARY_PATH 
 +which mpirun 
 + 
 +mpirun /share/apps/amber/9+openmpi-1.2+intel-9/exe/pmemd -O \ 
 +-i inp/mini.in -p 1g6r.cd.parm -c 1g6r.cd.randions.crd.1 \ 
 +-ref 1g6r.cd.randions.crd.1 
 + 
 +#/share/apps/lsf/slurm_epilog.pl 
 + 
 +</code> 
 + 
 +When submitted we see 
 + 
 +<code> 
 + 
 +             JOBID PARTITION     NAME     USER ST       TIME  NODES NODELIST(REASON) 
 +            902246      test      MPI    hmeij  R       0:05      v[1-8] 
 + 
 +</code> 
 + 
 +Dumping the environment we observe some key parameters 
 + 
 +<code> 
 + 
 +SLURM_NODELIST=v[1-8] 
 +SLURM_JOB_NAME=MPI 
 +SLURMD_NODENAME=v1 
 +SLURM_NNODES=8 
 +SLURM_NTASKS=8 
 +SLURM_TASKS_PER_NODE=1(x8) 
 +SLURM_NPROCS=8 
 +SLURM_CPUS_ON_NODE=1 
 +SLURM_JOB_NODELIST=v[1-8] 
 +SLURM_JOB_CPUS_PER_NODE=1(x8) 
 +SLURM_JOB_NUM_NODES=8 
 + 
 +</code> 
 + 
 +And in the slurmjob.log file 
 + 
 +<code> 
 + 
 +JobId=902245 UserId=hmeij(8216) GroupId=its(623) \ 
 +Name=MPI JobState=COMPLETED Partition=test TimeLimit=UNLIMITED \ 
 +StartTime=2014-08-21T15:55:06 EndTime=2014-08-21T15:57:04 \ 
 +NodeList=v[1-8] NodeCnt=8 ProcCnt=8 WorkDir=/home/hmeij/1g6r/cd 
 + 
 +</code>
  
  
 \\ \\
 **[[cluster:0|Back]]** **[[cluster:0|Back]]**
cluster/134.1408544784.txt.gz · Last modified: 2014/08/20 10:26 by hmeij