wulflogger is a derived cousin of wulfstat that monitors very similar statistics but just writes them out to stdout in an easily parsed, timestamped format. The output can then be redirected into a file or piped into perl or other scripting languages for further processing and display in fancier media, e.g. a graph, report, or web page. It uses the same format as the wulfhosts file(s) of wulfstat and requires xmlsysd to be installed on the monitored nodes or LAN workstations.

wulflogger is very much under construction (we're talking alpha here, not beta, although it seems to work well enough in the published snapshots). It can currently monitor load average, memory utilization, network utilization, a variety of systems parameters of interest in constructing a load-balanced distribution of jobs (e.g. CPU type, clock, cache), date and time, "duty cycle" (fraction of CPU clocks actually used since the last reboot) and running jobs, masked by task name or user.

If you need any particular output from wulflogger let me know. Eventually I'll probably come up with an output format descriptor that can be read in as input so you can roll your own format and get precisely what you want, but we're not there yet.