cvs commit: src/sys/kern sched_ule.c

Kevin Oberman oberman at
Mon Oct 1 07:53:03 PDT 2007

> Date: Mon, 1 Oct 2007 21:26:39 +1000 (EST)
> From: Bruce Evans <brde at>
> On Mon, 1 Oct 2007, Jeff Roberson wrote:
> > On Mon, 1 Oct 2007, Bruce Evans wrote:
> >
> >> On Sun, 30 Sep 2007, Jeff Roberson wrote:
> >> 
> >>> On Sat, 29 Sep 2007, Kevin Oberman wrote:
> >> 
> >>>> YMMV, but ULE seems to generally work better then 4BSD for interactive
> >>>> uniprocessor systems. The preferred scheduler for uniprocessor servers
> >>>> is less clear, but many test have shown ULE does better for those
> >>>> systems in the majority of cases.
> >>> 
> >>> I feel it's safe to say desktop behavior on UP is definitely superior.
> >> 
> >> This is unsafe to say.
> >
> > Given that the overwhelming amount of feedback by qualified poeple, I think 
> > it's fair to say that ULE gives a more responsive system under load.
> This is not my experience.  Maybe I don't run enough interactive bloatware
> to have a large enough interactive load for the scheduler to make a
> difference.

That, or you don't run interactive on older systems with slow CPUs and
limited memory. (This does NOT imply that ULE is going to help when
experiencing heavy swapfile activity. I don't think anything helps
that except more RAM.)

The place it seem most evident to me is X responsiveness when the system
(1GHz X 256MB PIII) is busy with large builds. Performance is terrible
with 4BSD and only bad with ULE. Note that I am running Gnome (speaking
of bloatware).

The difference when running ULE is pretty dramatic.
R. Kevin Oberman, Network Engineer
Energy Sciences Network (ESnet)
Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab)
E-mail: oberman at			Phone: +1 510 486-8634
Key fingerprint:059B 2DDF 031C 9BA3 14A4  EADA 927D EBB3 987B 3751
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 224 bytes
Desc: not available
Url :

More information about the cvs-src mailing list