public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* Re: Linux Preemptive patch success 2.4.10-pre4 + lots of other
@ 2001-09-08  6:29 Dieter Nützel
  0 siblings, 0 replies; 2+ messages in thread
From: Dieter Nützel @ 2001-09-08  6:29 UTC (permalink / raw)
  To: Robert Love; +Cc: Linux Kernel List

Robert Love wrote:
> I am glad you take a pro side to the preemption issue.  Hopefully I can
> get some continued support and see some work towards inclusion in 2.5. 
> Any help is appreciated.

I've tested your former patch against 2.4.7-acX and sent you some feedback 
but you didn't answered my post.

Is the module problem (missing preempt_xxx symbols) thing fixed?

Aside from that I saw some nice speed increase (UP Athlon) and very snappy 
system.

dbench-1.1 32 clients load drops to mostly below 16 (33 before)

Go on with your great work!

Greetings,
	Dieter

-- 
Dieter Nützel
Graduate Student, Computer Science
University of Hamburg

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: Linux Preemptive patch success 2.4.10-pre4 + lots of other
       [not found] <200109080629.f886TrG13025@zero.tech9.net>
@ 2001-09-08  6:39 ` Robert Love
  0 siblings, 0 replies; 2+ messages in thread
From: Robert Love @ 2001-09-08  6:39 UTC (permalink / raw)
  To: Dieter Nützel; +Cc: Linux Kernel List

On Sat, 2001-09-08 at 02:29, Dieter Nützel wrote:
> I've tested your former patch against 2.4.7-acX and sent you some feedback 
> but you didn't answered my post.
>
> Is the module problem (missing preempt_xxx symbols) thing fixed?

I am not sure what module problem you are talking about.  There was a
bug in my original patch that caused a link error in most situations
where CONFIG_MODULE was set, but this had to do with
atomic_dec_and_lock, not preempt_xxx -- what preempt_xxx symbols?

Anyhow, I suggest you grab 2.4.9-ac10 and
http://tech9.net/rml/linux/patch-rml-2.4.9-ac10-preempt-kernel-1 and
enable CONFIG_PREEMPT and give that a whirl.  You should have no
problems on a UP system.

> Aside from that I saw some nice speed increase (UP Athlon) and very snappy 
> system.

Very glad.  Especially to hear there are no problems on Athlon.

> dbench-1.1 32 clients load drops to mostly below 16 (33 before)

Great.  Data points such as this are welcome.  What about the actual
throughput?  Both I and Nigel (see http://kpreempt.sourceforge.net) 
benched the patch with `dbench -16' and we both got decent throughput
increase.

> Go on with your great work!

Thanks.

-- 
Robert M. Love
rml at ufl.edu
rml at tech9.net


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2001-09-08  6:39 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <200109080629.f886TrG13025@zero.tech9.net>
2001-09-08  6:39 ` Linux Preemptive patch success 2.4.10-pre4 + lots of other Robert Love
2001-09-08  6:29 Dieter Nützel

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox