low(er) disk performance with sched_4bsd then with sched_ule
lehmann at ans-netz.de
Sun Sep 18 01:15:09 PDT 2005
Joseph Koshy wrote:
> > I don't know the disk codepath very well, but the samples look
> > little suspect.
> They do look odd. For one, there are entries for the p4_*_pmc
> functions which would never get called on a P-III box.
> Oliver, after you sync'ed up with RELENG_6, did you keep the
> sources for pmcstat(8) sync'ed with current?
No, I didn't. I now recompiled CURRENT pmcstat, and rerun the tests. I
uploaded the new output: http://pofo.de/tmp/gprof.4bsd.3
More information about the freebsd-current