Am Montag 09 April 2007 schrieb Mike Galbraith:
> On Mon, 2007-04-09 at 07:26 -0400, Ed Tomlinson wrote:
> > On Monday 09 April 2007 01:38, Mike Galbraith wrote:
> > > On Sun, 2007-04-08 at 09:08 -0400, Ed Tomlinson wrote:
> > > > Hi,
> > > >
> > > > I am one of those who have been happily testing
On Sunday 22 April 2007 20:48, Martin Steigerwald wrote:
> Am Montag 09 April 2007 schrieb Mike Galbraith:
> > On Mon, 2007-04-09 at 07:26 -0400, Ed Tomlinson wrote:
> > > On Monday 09 April 2007 01:38, Mike Galbraith wrote:
> > > > On Sun, 2007-04-08 at 09:08 -0400, Ed Tomlinson wrote:
> > > > > H
On Tue, 2007-04-10 at 07:23 -0400, Ed Tomlinson wrote:
> On Monday 09 April 2007 22:39, Mike Galbraith wrote:
> > On Mon, 2007-04-09 at 07:38 +0200, Mike Galbraith wrote:
> >
> > > I don't think you can have very much effect on latency using nice with
> > > SD once the CPU is fully utilized. See
On Monday 09 April 2007 22:39, Mike Galbraith wrote:
> On Mon, 2007-04-09 at 07:38 +0200, Mike Galbraith wrote:
>
> > I don't think you can have very much effect on latency using nice with
> > SD once the CPU is fully utilized. See below.
> >
> > /*
> > * This contains a bitmap for each dynamic
On Mon, 2007-04-09 at 07:38 +0200, Mike Galbraith wrote:
> I don't think you can have very much effect on latency using nice with
> SD once the CPU is fully utilized. See below.
>
> /*
> * This contains a bitmap for each dynamic priority level with empty slots
> * for the valid priorities each
On 04/09/2007 03:27 PM, Andreas Mohr wrote:
And I really don't see much difference whatsoever to the I/O scheduler
area: some people want predictable latency, while others want maximum
throughput or fastest operation for seek-less flash devices (noop).
Hardware varies similarly greatly has well:
On Monday 09 April 2007, Ingo Molnar wrote:[...]
>
>i didnt say that, in fact my first lkml comment about RSDL on lkml was
>the exact opposite, but you SD advocates are _still_ bickering about
>(and not accepting) fundamental things like Mike's make -j5 workload and
>flagging it as unrealistic, so
On 04/09/2007 07:48 PM, Ingo Molnar wrote:
i didnt say that, in fact my first lkml comment about RSDL on lkml
was the exact opposite, but you SD advocates are _still_ bickering
about (and not accepting) fundamental things like Mike's make -j5
workload and flagging it as unrealistic, so until the
* William Lee Irwin III <[EMAIL PROTECTED]> wrote:
>> I strongly suggest assembling a battery of cleanly and properly
>> written, configurable testcases, and scripting a series of regression
>> tests as opposed to just randomly running kernel compiles and relying
>> on Braille.
On Mon, Apr 09,
* William Lee Irwin III <[EMAIL PROTECTED]> wrote:
> I strongly suggest assembling a battery of cleanly and properly
> written, configurable testcases, and scripting a series of regression
> tests as opposed to just randomly running kernel compiles and relying
> on Braille.
there's interbench
On Sat, 2007-04-07 at 20:08 +0200, Ingo Molnar wrote:
>> not many - and i dont think Mike tested any of these - Mike tested
>> pretty low make -j values (Mike, can you confirm?).
On Sat, Apr 07, 2007 at 09:14:21PM +0200, Mike Galbraith wrote:
> Yes. I don't test anything more than make -j5 when
* Rene Herman <[EMAIL PROTECTED]> wrote:
> > - the code actually has to match that stated goal. Right now it
> > diverges from it (it is not a "fair" scheduler), and it's not
> > clear why.
>
> I read most of the discussion centering around that specific point as
> well, and frankly, I mos
On Mon, 2007-04-09 at 14:14 +0200, Rene Herman wrote:
> This turned into an interactivity thing, and while interactivity is in
> fact better for a large majority of testers, that isn't what Kolivas'
> scheduler is about. It's about predictability and leaving the dead-end
> road of these endless
On 04/09/2007 04:15 PM, Ingo Molnar wrote:
* Rene Herman <[EMAIL PROTECTED]> wrote:
To me, the example rather serves as confirmation of what Kolivas
has been saying; endlessly tweaking the tweaks isn't going
anywhere.
but ... SD clearly regresses in some areas, so by that logic SD isnt
going
On Mon, 2007-04-09 at 07:26 -0400, Ed Tomlinson wrote:
> On Monday 09 April 2007 01:38, Mike Galbraith wrote:
> > On Sun, 2007-04-08 at 09:08 -0400, Ed Tomlinson wrote:
> > > Hi,
> > >
> > > I am one of those who have been happily testing Con's patches.
> > >
> > > They work better than mainlin
On 04/09/2007 03:53 PM, Ingo Molnar wrote:
In any case, it would be very nice if you could try Mike's latest
patch, how does it work on your setup? (i've attached it)
Can do. Note that "my setup" in that case consisted of browsing around
eBay in firefox with ogg123 playing audio directly to A
* Rene Herman <[EMAIL PROTECTED]> wrote:
> To me, the example rather serves as confirmation of what Kolivas has
> been saying; endlessly tweaking the tweaks isn't going anywhere.
but ... SD clearly regresses in some areas, so by that logic SD isnt
going anywhere either?
note that i still like
* Rene Herman <[EMAIL PROTECTED]> wrote:
> > and that change from Mike responded to a testcase. Mike's latest
> > changes (the ones you just tested) were mostly driven by actual
> > testcases too, which measured long-term timeslice distribution
> > fairness.
>
> Ah yes, that one. Here's the n
Hi,
On Mon, Apr 09, 2007 at 02:14:49PM +0200, Rene Herman wrote:
> This turned into an interactivity thing, and while interactivity is in
> fact better for a large majority of testers, that isn't what Kolivas'
> scheduler is about. It's about predictability and leaving the dead-end
> road of th
On Monday 09 April 2007, Mike Galbraith wrote:
>On Mon, 2007-04-09 at 00:08 -0400, Gene Heskett wrote:
>> On Monday 09 April 2007, Mike Galbraith wrote:
>> >Actually, there was practically nil interest in testing. We made a
>> >couple of minor adjustments to the interactivity logic, and all went
>
On 04/09/2007 06:23 AM, Mike Galbraith wrote:
On Sun, 2007-04-08 at 20:51 +0200, Rene Herman wrote:
On 04/08/2007 12:41 PM, Ingo Molnar wrote:
commit 5ce74abe788a26698876e66b9c9ce7e7acc25413
Author: Mike Galbraith <[EMAIL PROTECTED]>
Date: Mon Apr 10 22:52:44 2006 -0700
[PATCH]
On Monday 09 April 2007 01:38, Mike Galbraith wrote:
> On Sun, 2007-04-08 at 09:08 -0400, Ed Tomlinson wrote:
> > Hi,
> >
> > I am one of those who have been happily testing Con's patches.
> >
> > They work better than mainline here.
>
> (I tried a UP kernel yesterday, and even a single kernel
On Mon, 2007-04-09 at 01:16 -0400, Gene Heskett wrote:
> On Monday 09 April 2007, Mike Galbraith wrote:
> >
> >So tar -cvf - / | gzip --best | tar -tvzf - should reproduce the
> >problem?
> >
> That looks as if it should demo it pretty well if I understand correctly
> everything you're doing there
On Mon, 2007-04-09 at 01:23 -0400, Gene Heskett wrote:
> This may not be so informative, its almost behaving ATM.
>
> 29252 amanda22 0 1856 572 220 R 76.4 0.1 1:07.24 gzip
> 29235 amanda15 0 2992 1224 888 S 5.6 0.1 0:02.80 chunker
> 29500 root 18 0 2996 1164 788 S
On Mon, 2007-04-09 at 01:16 -0400, Gene Heskett wrote:
> On Monday 09 April 2007, Mike Galbraith wrote:
> >So tar -cvf - / | gzip --best | tar -tvzf - should reproduce the
> >problem?
> >
> > -Mike
>
> That looks as if it should demo it pretty well if I understand correctly
> everything you'r
On Mon, 2007-04-09 at 00:08 -0400, Gene Heskett wrote:
> On Monday 09 April 2007, Mike Galbraith wrote:
> >
> >
> >Actually, there was practically nil interest in testing. We made a
> >couple of minor adjustments to the interactivity logic, and all went
> >quiet, so I didn't think it was enough of
On Sun, 2007-04-08 at 09:08 -0400, Ed Tomlinson wrote:
> Hi,
>
> I am one of those who have been happily testing Con's patches.
>
> They work better than mainline here.
(I tried a UP kernel yesterday, and even a single kernel build would
make noticeable hitches if I move a window around. YMMV
On Monday 09 April 2007, Mike Galbraith wrote:
>On Sun, 2007-04-08 at 13:57 -0400, Gene Heskett wrote:
>> On Sunday 08 April 2007, Mike Galbraith wrote:
>> >On Sun, 2007-04-08 at 13:40 +0200, Mike Galbraith wrote:
>> >> On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
>> >> > That seems to be
On Monday 09 April 2007, Mike Galbraith wrote:
>On Sun, 2007-04-08 at 13:56 -0400, Gene Heskett wrote:
>> On Sunday 08 April 2007, Mike Galbraith wrote:
>> >On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
>> >> That seems to be the killer loading here, building a kernel (make
>> >> -j3) does
On Sun, 2007-04-08 at 20:51 +0200, Rene Herman wrote:
> On 04/08/2007 12:41 PM, Ingo Molnar wrote:
>
> > this is pretty hard to get right, and the most objective way to change
> > it is to do it testcase-driven. FYI, interactivity tweaking has been
> > gradual, the last bigger round of interacti
On Sun, 2007-04-08 at 13:57 -0400, Gene Heskett wrote:
> On Sunday 08 April 2007, Mike Galbraith wrote:
> >On Sun, 2007-04-08 at 13:40 +0200, Mike Galbraith wrote:
> >> On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
> >> > That seems to be the killer loading here, building a kernel (make
>
On Sun, 2007-04-08 at 13:56 -0400, Gene Heskett wrote:
> On Sunday 08 April 2007, Mike Galbraith wrote:
> >On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
> >> That seems to be the killer loading here, building a kernel (make -j3)
> >> doesn't seem to lag it all that bad. One session of gzi
On Monday 09 April 2007, Mike Galbraith wrote:
>On Sun, 2007-04-08 at 13:04 -0400, Gene Heskett wrote:
>> On Sunday 08 April 2007, Ingo Molnar wrote:
>> >and note that a year ago Mike did a larger patch too, not unlike his
>> >current patch - but we hoped that his smaller change would be
>> > suffi
On Sun, 2007-04-08 at 13:04 -0400, Gene Heskett wrote:
> On Sunday 08 April 2007, Ingo Molnar wrote:
> >and note that a year ago Mike did a larger patch too, not unlike his
> >current patch - but we hoped that his smaller change would be sufficient
> >- and nobody came along and said "i tested Mik
On 04/08/2007 12:41 PM, Ingo Molnar wrote:
this is pretty hard to get right, and the most objective way to change
it is to do it testcase-driven. FYI, interactivity tweaking has been
gradual, the last bigger round of interactivity changes were done a year
ago:
commit 5ce74abe788a26698876e66
On Sunday 08 April 2007, Mike Galbraith wrote:
>On Sun, 2007-04-08 at 13:40 +0200, Mike Galbraith wrote:
>> On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
>> > That seems to be the killer loading here, building a kernel (make
>> > -j3) doesn't seem to lag it all that bad. One session of gz
On Sunday 08 April 2007, Mike Galbraith wrote:
>On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
>> That seems to be the killer loading here, building a kernel (make -j3)
>> doesn't seem to lag it all that bad. One session of gzip -best makes
>> it fall plumb over though, which was a disappo
On Sunday 08 April 2007, Ingo Molnar wrote:
>* Ingo Molnar <[EMAIL PROTECTED]> wrote:
>> > My question then, is why did it take a very public cat-fight to get
>> > this looked at and the code adjusted? Its been what, nearly 2 years
>> > since Linus himself made a comment that this thing needed fix
Hi,
I am one of those who have been happily testing Con's patches.
They work better than mainline here.
There seems to be a disconnect on what Con is trying to achieve with SD.
They do not improve interactivity per say. Instead they make the scheduler
predictable by removing the alchemy used
On Sun, 2007-04-08 at 13:40 +0200, Mike Galbraith wrote:
> On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
>
> > That seems to be the killer loading here, building a kernel (make -j3)
> > doesn't seem to lag it all that bad. One session of gzip -best makes it
> > fall plumb over though,
On Sun, 2007-04-08 at 07:33 -0400, Gene Heskett wrote:
> That seems to be the killer loading here, building a kernel (make -j3)
> doesn't seem to lag it all that bad. One session of gzip -best makes it
> fall plumb over though, which was a disappointment.
Can you make a testcase that doesn't r
On Sunday 08 April 2007, Ingo Molnar wrote:
>* Gene Heskett <[EMAIL PROTECTED]> wrote:
>> That said, I am booted to the patch you sent me now, and this also is
>> a very obvious improvement, one I could easily live with on a long
>> term basis. I haven't tried a kernel build in the background yet,
* Ingo Molnar <[EMAIL PROTECTED]> wrote:
> > My question then, is why did it take a very public cat-fight to get
> > this looked at and the code adjusted? Its been what, nearly 2 years
> > since Linus himself made a comment that this thing needed fixed.
> > The fixes then done were of very l
* Gene Heskett <[EMAIL PROTECTED]> wrote:
> That said, I am booted to the patch you sent me now, and this also is
> a very obvious improvement, one I could easily live with on a long
> term basis. I haven't tried a kernel build in the background yet, but
> I have sat here and played patience
On Saturday 07 April 2007, Mike Galbraith wrote:
>On Sat, 2007-04-07 at 20:08 +0200, Ingo Molnar wrote:
>> * Gene Heskett <[EMAIL PROTECTED]> wrote:
>> > (who the hell runs a 'make -j 200' or 50 while(1)'s in the real
>> > world?
>>
>> not many - and i dont think Mike tested any of these - Mike tes
On Saturday 07 April 2007, Ingo Molnar wrote:
>* Gene Heskett <[EMAIL PROTECTED]> wrote:
>> Yes it would be Ingo, but so far, none of the recent -rt patches has
>> booted on this machine, the last one I tried a few days ago failing to
>> find /dev/root, whatever the heck that is.
>
>did you have a
On Sat, 2007-04-07 at 20:08 +0200, Ingo Molnar wrote:
> * Gene Heskett <[EMAIL PROTECTED]> wrote:
> > (who the hell runs a 'make -j 200' or 50 while(1)'s in the real world?
>
> not many - and i dont think Mike tested any of these - Mike tested
> pretty low make -j values (Mike, can you confirm?)
* Gene Heskett <[EMAIL PROTECTED]> wrote:
> Yes it would be Ingo, but so far, none of the recent -rt patches has
> booted on this machine, the last one I tried a few days ago failing to
> find /dev/root, whatever the heck that is.
did you have a chance to try the yum kernel by any chance? The
On Saturday 07 April 2007, Ingo Molnar wrote:
>* Gene Heskett <[EMAIL PROTECTED]> wrote:
>> To be expected, there are after all, only so many cpu cycles to go
>> around. Here I sit, running 2.6.21-rc6 ATM, and since there is not an
>> SD patch that applies cleanly to rc6, I am back to typing half
* Gene Heskett <[EMAIL PROTECTED]> wrote:
> To be expected, there are after all, only so many cpu cycles to go
> around. Here I sit, running 2.6.21-rc6 ATM, and since there is not an
> SD patch that applies cleanly to rc6, I am back to typing half or more
> of a sentence blind while I answer
On Sat, 2007-04-07 at 16:50 +1000, Con Kolivas wrote:
> On Friday 06 April 2007 20:03, Ingo Molnar wrote:
> > (There was one person who
> > reported wide-scale interactivity regressions against mainline but he
> > didnt answer my followup posts to trace/debug the scenario.)
>
> That was one user
On Saturday 07 April 2007, Con Kolivas wrote:
>On Friday 06 April 2007 20:03, Ingo Molnar wrote:
>> * Con Kolivas <[EMAIL PROTECTED]> wrote:
>[...]
>>
>> firstly, testing on various workloads Mike's tweaks work pretty well,
>> while SD still doesnt handle the high-load case all that well. Note
>>
On Friday 06 April 2007 20:03, Ingo Molnar wrote:
> * Con Kolivas <[EMAIL PROTECTED]> wrote:
> > > I was more focused on the general case, but all I should have to do
> > > to de-claw all of these sleep exploits is account rr time (only a
> > > couple of lines, done and building now). It's only a
On Fri, 2007-04-06 at 19:28 +1000, Con Kolivas wrote:
> On Friday 06 April 2007 19:07, Mike Galbraith wrote:
> > On Fri, 2007-04-06 at 11:03 +1000, Con Kolivas wrote:
> > > On Thursday 05 April 2007 21:54, Ingo Molnar wrote:
> > > > - fiftyp.c: noticeable, but alot better than previously!
> > >
>
On Fri, 2007-04-06 at 12:03 +0200, Ingo Molnar wrote:
> already-fixed corners, but it didnt happen in practice. But ... i'm
> awaiting further SD and Mike tweaks, the race certainly looks
> interesting ;)
I think I lapped him, but since we're running in opposite
directions, it's hard to tell.
* Con Kolivas <[EMAIL PROTECTED]> wrote:
> > I was more focused on the general case, but all I should have to do
> > to de-claw all of these sleep exploits is account rr time (only a
> > couple of lines, done and building now). It's only a couple of
> > lines.
>
> The more you try to "de-cla
On Friday 06 April 2007 19:07, Mike Galbraith wrote:
> On Fri, 2007-04-06 at 11:03 +1000, Con Kolivas wrote:
> > On Thursday 05 April 2007 21:54, Ingo Molnar wrote:
> > > - fiftyp.c: noticeable, but alot better than previously!
> >
> > fiftyp.c seems to have been stumbled across by accident as ha
On Fri, 2007-04-06 at 11:03 +1000, Con Kolivas wrote:
> On Thursday 05 April 2007 21:54, Ingo Molnar wrote:
> > - fiftyp.c: noticeable, but alot better than previously!
>
> fiftyp.c seems to have been stumbled across by accident as having an effect
> when Xenofon was trying to recreate Mike's 5
58 matches
Mail list logo
