Clusterpunch: a distributed mini-benchmark system for clusters

Documentation—benchdriver

benchdriver - execute clusterpunch benchmarks on current node

NAME

benchdriver - execute clusterpunch benchmarks on current node


SYNOPSIS

 > benchdriver
      punch1     6of8 0.406183
      punch2     6of8 0.231732
    benchmem     6of8 0.796433
     benchio     6of8 1.253465
         mhz     6of8 2792
        load     6of8 2.33
      uptime     6of8 90.3665393518518
      nusers     6of8 6
    jobusers     6of8 mapper:0.00 martink:0.15 robertk:0.10 srusaw:12.87
        lsof     6of8 622
        date     6of8 18:37:11
    nrunning     6of8 3


DESCRIPTION

This is part of the clusterpunch system. Each node that you wish to monitor must be running the clusterpunchserver daemon, documented in the clusterpunchserver. Once the server is running, you can poll it and send commands using the API documented in clusterpunchclient.pm, or through the various utilities, such as this one.

The benchdriver executes all the resource/capacity discovery functions and benchmark functions. This is useful to appraise how the arguments to these functions affect execution time.


SEE ALSO


Daemons

clusterpunchserver, clusterpunch.start, clusterpunch.shutdown


API

clusterpunch.pm


Utilities

benchdriver, clusterbench, clusterlogin, clusternodecount, clustersnapshot


CHANGES


AUTHOR

Martin Krzywinski (martink@bcgsc.ca)

$Id: benchdriver,v 1.7 2003/01/26 08:03:55 martink Exp $