* HZ in 2.6 on PPC32
@ 2003-08-23 16:03 Michel Dänzer
2003-08-23 16:59 ` Benjamin Herrenschmidt
0 siblings, 1 reply; 2+ messages in thread
From: Michel Dänzer @ 2003-08-23 16:03 UTC (permalink / raw)
To: linuxppc-dev
Why is this still defined to 100? I'm running at 1000 now, and it makes
a huge difference for interactivity. Moreover, CONFIG_PREEMPT now makes
things even better instead of worse. :)
If the reason is the slow PPC32 CPUs still around, maybe make it a
config option?
--
Earthling Michel Dänzer \ Debian (powerpc), XFree86 and DRI developer
Software libre enthusiast \ http://svcs.affero.net/rm.php?r=daenzer
** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: HZ in 2.6 on PPC32
2003-08-23 16:03 HZ in 2.6 on PPC32 Michel Dänzer
@ 2003-08-23 16:59 ` Benjamin Herrenschmidt
0 siblings, 0 replies; 2+ messages in thread
From: Benjamin Herrenschmidt @ 2003-08-23 16:59 UTC (permalink / raw)
To: Michel Dänzer; +Cc: linuxppc-dev
On Sat, 2003-08-23 at 18:03, Michel Dänzer wrote:
> Why is this still defined to 100? I'm running at 1000 now, and it makes
> a huge difference for interactivity. Moreover, CONFIG_PREEMPT now makes
> things even better instead of worse. :)
>
> If the reason is the slow PPC32 CPUs still around, maybe make it a
> config option?
A config option would probably be a better idea, I doubt lots of embedded
or low end configs wants HZ at 1000... Regarding CONFIG_PREEMPT, it's
really weird that it "makes things worse" for you with HZ at 100. But
that may also be the 2.6-test scheduler suckyness...
Ben.
** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2003-08-23 16:59 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2003-08-23 16:03 HZ in 2.6 on PPC32 Michel Dänzer
2003-08-23 16:59 ` Benjamin Herrenschmidt
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).