[PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Con Kolivas]

What follows this email is a series of patches for the RSDL cpu scheduler as 
found in 2.6.21-rc3-mm1. This series is for 2.6.21-rc3-mm2 and has some 
bugfixes for the issues found so far. While it is not clear that I've 
attended to all the bugs, it is worth noting that a complete rewrite is a 
teensy bit more than a trivial change shall we say ;)

akpm it still has trouble on that monster config of yours but there's so much 
else going on in this -mm I don't know what to make of it. getting ppc to work 
on qemu was more work than I thought and I haven't succeeded there yet 
either :|

A rolled up patch can be found here:
http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc3-mm2-rsdl.patch

Patch series here:
http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc3-mm2/

and the patch series will follow. If time permits I will make available a 
newer version for the older kernels soon.

Changelog:
- Made it possible for the idle task to schedule on cpu_hotplug.
- Fixed the accounting across fork()
- Recalculation of priority for tasks that have already run this major 
rotation and are now on the expired array was wrong. It has been corrected.
- The bitmap error that has been hit on some architectures was made more 
verbose to make it clear that something has gone wrong, and will keep going 
off if the problem persists.

-- 
-ck

Re: [PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Nicolas Mailhot]

[-- Attachment #1: Type: text/plain, Size: 85 bytes --]

Oops

⇒ http://bugzilla.kernel.org/show_bug.cgi?id=8166

-- 
Nicolas Mailhot

[-- Attachment #2: Ceci est une partie de message numériquement signée --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Con Kolivas]

On Saturday 10 March 2007 18:25, Con Kolivas wrote:
> What follows this email is a series of patches for the RSDL cpu scheduler
> as found in 2.6.21-rc3-mm1. This series is for 2.6.21-rc3-mm2 and has some
> bugfixes for the issues found so far. While it is not clear that I've
> attended to all the bugs, it is worth noting that a complete rewrite is a
> teensy bit more than a trivial change shall we say ;)
>
> akpm it still has trouble on that monster config of yours but there's so
> much else going on in this -mm I don't know what to make of it. getting ppc
> to work on qemu was more work than I thought and I haven't succeeded there
> yet either :|
>
> A rolled up patch can be found here:
> http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc3-mm2-rsdl.patch
>
> Patch series here:
> http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc3-mm2/
>
> and the patch series will follow. If time permits I will make available a
> newer version for the older kernels soon.
>
> Changelog:
> - Made it possible for the idle task to schedule on cpu_hotplug.
> - Fixed the accounting across fork()
> - Recalculation of priority for tasks that have already run this major
> rotation and are now on the expired array was wrong. It has been corrected.
> - The bitmap error that has been hit on some architectures was made more
> verbose to make it clear that something has gone wrong, and will keep going
> off if the problem persists.

Oh and if it wasn't clear from this message. It still needs work to be bug 
free and probably shouldn't be part of -mm till I've ironed out all the 
oopsen. Thanks.

-- 
-ck

Re: [PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Con Kolivas]

On Saturday 10 March 2007 22:49, Nicolas Mailhot wrote:
> Oops
>
> ⇒ http://bugzilla.kernel.org/show_bug.cgi?id=8166

Thanks very much. I can't get your config to boot on qemu, but could you 
please try this debugging patch? It's not a patch you can really run the 
machine with but might find where the problem occurs. Specifically I'm 
looking for the warning MISSING STATIC BIT in your case. 

http://ck.kolivas.org/patches/crap/sched-rsdl-0.28-stuff.patch

Thanks!

-- 
-ck

Re: [PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Nicolas Mailhot]

[-- Attachment #1: Type: text/plain, Size: 638 bytes --]

Le dimanche 11 mars 2007 à 01:03 +1100, Con Kolivas a écrit :
> On Saturday 10 March 2007 22:49, Nicolas Mailhot wrote:
> > Oops
> >
> > ⇒ http://bugzilla.kernel.org/show_bug.cgi?id=8166
> 
> Thanks very much. I can't get your config to boot on qemu, but could you 
> please try this debugging patch? It's not a patch you can really run the 
> machine with but might find where the problem occurs. Specifically I'm 
> looking for the warning MISSING STATIC BIT in your case. 
> 
> http://ck.kolivas.org/patches/crap/sched-rsdl-0.28-stuff.patch

I attached a screenshot of the patched kernel boot

-- 
Nicolas Mailhot

[-- Attachment #2: Ceci est une partie de message numériquement signée --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [PATCH][RSDL-mm 0/6] Rotating Staircase DeadLine scheduler for -mm

[Con Kolivas]

On Sunday 11 March 2007 03:53, Nicolas Mailhot wrote:
> Le dimanche 11 mars 2007 à 01:03 +1100, Con Kolivas a écrit :
> > On Saturday 10 March 2007 22:49, Nicolas Mailhot wrote:
> > > Oops
> > >
> > > ⇒ http://bugzilla.kernel.org/show_bug.cgi?id=8166
> >
> > Thanks very much. I can't get your config to boot on qemu, but could you
> > please try this debugging patch? It's not a patch you can really run the
> > machine with but might find where the problem occurs. Specifically I'm
> > looking for the warning MISSING STATIC BIT in your case.
> >
> > http://ck.kolivas.org/patches/crap/sched-rsdl-0.28-stuff.patch
>
> I attached a screenshot of the patched kernel boot

Thanks. Darn the debugging didn't catch anything. Did you see any BUG during 
the boot earlier than that screenshot? Probably not. 

If you have the time I would appreciate you testing 2.6.20 with the rsdl 0.28 
patch for it with a config as close to this -mm2 one as possible.

http://ck.kolivas.org/patches/staircase-deadline/2.6.20-sched-rsdl-0.28.patch

and see if the bug recurs please?

Thanks!

-- 
-ck