benchdriver - execute clusterpunch benchmarks on current node
> 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
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.
clusterpunchserver, clusterpunch.start, clusterpunch.shutdown
clusterpunch.pm
benchdriver, clusterbench, clusterlogin, clusternodecount, clustersnapshot
Martin Krzywinski (martink@bcgsc.ca)
$Id: benchdriver,v 1.7 2003/01/26 08:03:55 martink Exp $