On Sunday 14 April 2002 03:00 pm, Luciano Miguel Ferreira Rocha wrote:
> On Sun, Apr 14, 2002 at 02:35:13PM -0400, Lamar Owen wrote:
> > Raw performance seems to be increased as well, due to an improved kernel
> > (2.4.18 plus low-latency and preemptible patches, according to the kernel
> > source RPM).
> The low-latency and preemptible patches are not meant for performance
> gains, but for responsiveness, and are not designed to be used in servers,
> only in workstations/desktops.
ISTM that improving interactive performance would also improve multiuser
performance in a server, as low latency and kernel preemption can increase
multiuser server responsiveness.
> > Although I am a little overwhelmed by the increased performance
> > of this new Athlon 1.2+512MB RAM versus my old Celeron 650+192MB RAM,
> > 7.2.93 seems to be faster on the same hardware.
> 2.4.18 does come with a improved VM, what could justify the performance
> increase. As could an update on the compiler (I've being using gcc 3.1 in
> my redhat 7.2).
The stock gcc on 7.2.93 is still the RedHat-branded 2.96, but with lots of
fixes backported from higher versions.
However, the improved VM may indeed be a large part of it. It sure feels
faster.
> But I can't recomend the beta to anyone, we had problems with one
> dual pentium iii server, causing random corruption on
> /usr/include/*.h and a lock up.
Did you happen to report it to Red Hat's Skipjack list, or to
bugzilla.redhat.com/bugzilla? Helps make a better dist!
I have had less problems thus far with 7.2.93 than I ever did with 7.2.
--
Lamar Owen
WGCR Internet Radio
1 Peter 4:11