Changes between Version 39 and Version 40 of WikiStart


Ignore:
Timestamp:
01/13/12 15:40:13 (12 years ago)
Author:
Florian Janetzko
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • WikiStart

    v39 v40  
    2828      * `UsedKe`
    2929
    30 When monitoring per task each task writes the value for each key to the file `.memlog/task<MPI-rank>.log` and waits for the next time step. When monitoring by node the process running on core 0 of each node writes the value for each key to the file `node<node-name>_task<MPI-task>.log`.
     30When monitoring per task each task writes the value for each key to the file `.memlog/task<MPI-rank>.log` and waits for the next time step. When monitoring by node the process running on core 0 of each node writes the value for each key to the file `node<node-name>_task<MPI-task>.log`. Both (monitoring by task and monitoring by node) can be active at the same time.
    3131
    32 After the run is finished the analyzer `juman` is run in the `PBS_O_WORKDIR`, either from within the same job script or afterwards on the login node to analyze the consumed resources. It will create graphs with the value of key (default: `VmSize`, => `key`, option `-k`) for each task at each time step (use `juman -k help` for a list of available keys), the process with the maximum value of the key at each time step and the total sum of all values of a key across all tasks at each time step (=> `statistics`, option `-s`). If `-i` is specified the graphs are displayed immediately.
     32The data produced by `jumel` can be analyzed by the `juman` script which performs statistical analysis of the data (minimum, maximum and total sum of values) and generates corresponding graphs.
    3333
    3434== Usage ==
     
    3939juman -u
    4040}}}
    41 
    42 Defaults:
    43   * work directory: `.memlog`
    44   * delay: 10 seconds
    45   * all ranks log the memory consumption
    46   * resources logged: `/proc/<id>/status: VmSize, VmRSS, VmData, VmStk`
    4741
    4842Suppose the application to monitor is started usually as follows:
     
    5650
    5751{{{
    58 mpiexec -np 32 -e PBS_ID,APP_ROOT jumel -a "app.x -i app.inp" > my.out
     52mpiexec -np 32 -e PBS_ID,APP_ROOT jumel -n -a "app.x -i app.inp" > my.out
    5953}}}
    6054
     
    6256
    6357{{{
    64 juman -s all -i
     58juman -s all -n -i
    6559}}}
    6660
    67 The -s option switches on the statistics (currently: total consumption and maximum consumption per time step) and the `-i` option will start the graphical display of the results. Currently only a `gnuplot` interface is implemented and postscript of `xfig` files can be generated. An interface for visualization with Python is planned.
     61The -s option switches on the statistics and the `-i` option will start the graphical display of the results. Currently only a `gnuplot` interface is implemented and postscript or `xfig` files can be generated. An interface for visualization with Python is planned.
    6862
    6963== Example: Namd ==
     
    7872module load namd/2.7
    7973
    80 mpiexec -np 32 -e PBS_JOBID jumel -a "$NAMD_ROOT/bin/namd2 apoa1.namd"
     74mpiexec -np 32 -e PBS_JOBID jumel -n -p -t -a "$NAMD_ROOT/bin/namd2 apoa1.namd"
    8175
    8276}}}
     
    8579
    8680{{{
    87 juman -s all -i
     81juman -s all -n -t -i
    8882}}}
    8983
     
    10498
    10599
    106 mpiexec -np 16 jumel -d 2 -a "mapt.x" > mapt.out
     100mpiexec -np 16 jumel -d 2 -n -p -t -a "mapt.x" > mapt.out
    107101
    108102}}}
     
    111105
    112106{{{
    113 juman -s all -i
     107juman -s all -i -n -t
    114108}}}
    115109