System Cpu Between 50-70% and need to find out why

Kris Kennaway kris at obsecurity.org
Sat May 5 16:02:22 UTC 2007


On Sat, May 05, 2007 at 12:23:12PM +0100, Chris wrote:
> On 24/04/07, Kris Kennaway <kris at obsecurity.org> wrote:
> >On Mon, Apr 23, 2007 at 10:50:47PM -0400, Paul wrote:
> >>
> >> >It was almost certainly what I said above.  Too bad you weren't able
> >> >to follow through with it.
> >> >
> >> >Kris
> >>
> >> Hi Kris,
> >>
> >> I was running the make depend for over 1 hour and it showed no end in
> >> sight. I figured to run that to the finish and the full make it might
> >> have taken all day so I really had no choice :)
> >
> >Odd, I suspect you were doing more than just building a kernel, which
> >only takes a few minutes to build completely (even on a quota-enabled
> >machine ;)
> >
> >> I will test this and see if it fixes the problem and confirm if this
> >> is the culprit (or not).
> >>
> >> I am surprised to hear this is all a function of the Quota problem
> >> you mention. I suppose nobody is using this anymore or is there a
> >> better system being used?
> >
> >It's just a left-over from the post-4.x SMP rewrite that didn't get
> >addressed until recently.  In the grand scheme of things quotas are
> >relatively infrequently used, so it was a higher priority for the
> >developers to work on other things first.  As I mentioned, fixing this
> >performance problem with quotas has now been completed in 7.0 and it
> >will probably make it back into 6.x before 6.3.
> >
> >Kris
> >
> >
> 
> Hi Kris please address this ASAP in 6.x, QUOTA is used quite often in
> server environments probably more so then you believe.  Considering
> 6.x is pushed as a stable version of FreeBSD and 4.x was killed off
> its dissapointing QUOTA was knowingly broken and left unpatched.

Have you tested the 6.x patch?  It's easy to criticize the developers
but harder to actually step up and help with the process yourself.

Kris



More information about the freebsd-smp mailing list