Ashley Pittman <[EMAIL PROTECTED]> writes: > Note that it's not just the "OS" fluff which causes problems and turning > things off doesn't get you anything like 100% of the way there, some > deamons have to run (your job scheduler) so all you can do it tune them > or re-code them to use less CPU and some kernel versions are pretty bad, > one version of Red-Hat was effectively un-usable on clusters because of > kscand.
To agree with you and to expand a bit: In theory, daemons should not be an issue. With a properly written real time scheduler and proper interrupt management, one can reasonably guarantee maximum latencies. However, in practice: 1) PC hardware is incapable of guaranteeing very tight latencies, full stop. I've mentioned SM mode, and that's only one of the issues you face. 2) Most operating systems are not designed for true real time performance. They are built to maximize throughput, not to minimize latency. Linux is no exception. Perry -- Perry E. Metzger [EMAIL PROTECTED] _______________________________________________ Beowulf mailing list, [email protected] To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
