Changes between Version 26 and Version 27 of Public/User_Guide/Batch_system


Ignore:
Timestamp:
Mar 11, 2020, 3:20:56 PM (4 years ago)
Author:
Jochen Kreutz
Comment:

dp-esb partition added to the list of partitions ; added —account / -A in all examples

Legend:

Unmodified
Added
Removed
Modified

  • Public/User_Guide/Batch_system

    v26 v27  
    2323 || dp-dam ||  dp-dam[01-16], DEEP-EST Dam nodes (Xeon Cascadelake + 1 V100 + 1 Stratix 10) ||
    2424 || dp-dam-ext ||  dp-dam[09-16], DEEP-EST Dam nodes connected with Extoll Tourmalet ||
     25 || dp-esb || dp-esb[01-25], DEEP-EST Esb nodes (Xeon Cascadelake + 1 V100) ||
    2526 || dp-sdv-esb ||  dp-sdv-esb[01-02], DEEP-EST ESB Test nodes (Xeon Cascadelake + 1 V100) ||
    2627 || ml-gpu ||  ml-gpu[01-03], GPU test nodes for ML applications (up to 4 V100 cards) ||
    … …  
    5758First, start a shell on a node. You would like to run your mpi task on 4 machines with 2 tasks per machine:
    5859{{{
    59 [kreutz1@deepv /p/project/cdeep/kreutz1/Temp]$ srun -p dp-cn -N 4 -n 8 -t 00:30:00 --pty /bin/bash -i
     60[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
    6061[kreutz1@dp-cn01 /p/project/cdeep/kreutz1/Temp]$
    6162}}}
    6263
    63 The environment is transported to the remote shell, no {{{.profile}}}, {{{.bashrc}}}, ... are sourced (especially not the modules default from {{{/etc/profile.d/modules.sh}}}).
     64The environment is transported to the remote shell, no {{{.profile}}}, {{{.bashrc}}}, ... are sourced (especially not the modules default from {{{/etc/profile.d/modules.sh}}}). As of March 2020, an account has to be specified using the `--account` (short `-A`) option, which is "deep" for the project members. For people not included in the DEEP-EST project, please use the "Budget" name you received along with your account creation.
    6465
    6566Once 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):
    6667{{{
    67 [kreutz1@deepv Temp]$ srun -p dp-cn -N 4 -n 8 -t 00:30:00 --pty /bin/bash -i
     68[kreutz1@deepv Temp]$ srun -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 --pty /bin/bash -i
    6869[kreutz1@dp-cn01 Temp]$ srun ./MPI_HelloWorld
    6970Hello World from rank 3 of 8 on dp-cn02
    … …  
    8485
    8586{{{
    86 [kreutz1@deepv Temp]$ srun -p dp-cn -N 4 -n 8 -t 00:30:00 ./MPI_HelloWorld
     87[kreutz1@deepv Temp]$ srun -A deep -p dp-cn -N 4 -n 8 -t 00:30:00 ./MPI_HelloWorld
    8788Hello World from rank 7 of 8 on dp-cn04
    8889Hello World from rank 3 of 8 on dp-cn02
    … …  
    9899
    99100{{{
    100 [kreutz1@deepv Temp]$ salloc -p dp-cn -N 4 -n 8 -t 00:30:00
     101[kreutz1@deepv Temp]$ salloc -A deep -p dp-cn -N 4 -n 8 -t 00:30:00
    101102salloc: Granted job allocation 69263
    102103[kreutz1@deepv Temp]$ srun ./MPI_HelloWorld
    … …  
    125126
    126127#SBATCH --partition=dp-cn
     128#SBATCH -A deep
    127129#SBATCH -N 4
    128130#SBATCH -n 8
    … …  
    168170
    169171{{{
    170 srun --partition=dp-cn -N 1 -n 1 hostname : --partition=dp-dam -N 1 -n 1 hostname
     172srun --account=deep --partition=dp-cn -N 1 -n 1 hostname : --partition=dp-dam -N 1 -n 1 hostname
    171173dp-cn01
    172174dp-dam01