Changes between Version 51 and Version 52 of Public/User_Guide/Batch_system


Ignore:
Timestamp:
Oct 15, 2021, 10:59:53 AM (4 years ago)
Author:
Jochen Kreutz
Comment:

introductory example updated

Legend:

Unmodified
Added
Removed
Modified

  • Public/User_Guide/Batch_system

    v51 v52  
    5555First, start a shell on a node. Assume you would like to run your mpi task on 4 cluster nodes with 2 tasks per node:
    5656{{{
    57 [kreutz1@deepv /p/project/cdeep/kreutz1/Temp]$ srun -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 --pty /bin/bash -i
     57[kreutz1@deepv /p/project/cdeep/kreutz1/Temp]$ srun -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 --pty --interactive /bin/bash -i
    5858[kreutz1@dp-cn01 /p/project/cdeep/kreutz1/Temp]$
    5959}}}
    … …  
    6363Once you get to the compute node, start your application using {{{srun}}}. Note that the number of tasks used is the same as specified in the initial {{{srun}}} command above (4 nodes with two tasks each):
    6464{{{
    65 [kreutz1@deepv Temp]$ srun -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 --pty /bin/bash -i
    66 [kreutz1@dp-cn01 Temp]$ srun ./MPI_HelloWorld
     65[kreutz1@deepv Temp]$ salloc -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 srun --pty --interactive /bin/bash -i
     66[kreutz1@dp-cn01 Temp]$ srun -N 2 -n 8 ./MPI_HelloWorld
    6767Hello World from rank 3 of 8 on dp-cn02
    6868Hello World from rank 7 of 8 on dp-cn04
    … …  
    7676
    7777You can ignore potential warnings about the cpu binding. !ParaStation will pin your processes.
     78
     79If you just need to one node to run your interactive session on you can simply use the `srun` command (without `salloc`), e.g.:
     80
     81{{{
     82[kreutz1@deepv ~]$ srun -A deep -N 1 -n 8 -p dp-cn -t 00:30:00 --pty --interactive bash -i
     83[kreutz1@dp-cn22 ~]$ srun -n 8 hostname
     84dp-cn22
     85dp-cn22
     86dp-cn22
     87dp-cn22
     88dp-cn22
     89dp-cn22
     90dp-cn22
     91dp-cn22
     92}}}
    7893
    7994=== Running directly from the front ends ===
    … …  
    94109}}}
    95110
    96 It can be useful to create an allocation which you can be used for several runs of your job:
     111It can be useful to create an allocation which can be used for several runs of your job:
    97112
    98113{{{
    … …  
    115130salloc: Relinquishing job allocation 69263
    116131}}}
     132
     133Note that in this case the `-N` and `-n` options for the `srun` command can be skipped (they default to the corresponding options given to `salloc`).
    117134
    118135=== Batch script ===