... for as long as SD and CFS have been around. If I have ... running at nice 0, with v19 java gets so little cpu that ... -v19 of the CFS scheduler patchset. > > The rolled-up CFS patch ... biggest user-visible change in -v19 is reworked sleeper fairness: > it' ...

linux-kernel - Ed Tomlinson - Jul 14 2007 - 13:19

... -v19 of the CFS scheduler patchset. > > The rolled-up CFS patch against today's -git kernel, v2.6.22-rc7, > v2. ... biggest user-visible change in -v19 is reworked sleeper fairness: > it' ... perform the most relevant tests. V19 works very well here on ...

linux-kernel - Willy Tarreau - Jul 8 2007 - 13:46

... release -v19 of the CFS scheduler patchset. > > The rolled-up CFS patch against today's -git kernel, v2 ... cfs-v19 patch for the 2.6.21 kernels. Its a amd64 system and the "normal" (=only gentoo patches) kernel is working fine! > As usual ...

linux-kernel - Markus - Jul 14 2007 - 07:34

... for as long > as SD and CFS have been around. If I have ... compile running at nice 0, with v19 java > gets so little cpu that ... is gentoo 2.6.22-r1 + cfs v19 > > How can I help to ... eliminate the sleeper fairness changes in v19, since that was the biggest ...

linux-kernel - Mike Galbraith - Jul 15 2007 - 01:25

... biggest user-visible change in -v19 is reworked sleeper > > > fairness: it's ... it's a small tweak. CFS is O(31) in sleep/ ... the scheduler) with that many tasks being runnable. [ > With CFS you ... people will tell me "you're completely dumb, you could have ...

linux-kernel - Willy Tarreau - Jul 17 2007 - 17:44

... > The biggest user-visible change in -v19 is reworked sleeper > > fairness: it's similar ... - it's a small tweak. CFS is O(31) in sleep/wakeup so ... bottleneck somewhere (likely not in the scheduler) with that many tasks being runnable. [ With CFS you can ...

linux-kernel - Ingo Molnar - Jul 9 2007 - 18:39

... the v2.6.21.6-cfsv19 patch, and that > does not include the ... if yes, please revert it via patch -p1 -R ) As already said, ... .6.22.1-cfs-v19 includes the patch and 2.6.21.6-cfs-v19 does not include it. ... problem. I now reversed the patch on 2.6.22.1- ...

linux-kernel - Markus - Jul 20 2007 - 18:26

... 'm pleased to announce release -v19 of the CFS scheduler patchset. > > I've taken mainline git tree (freshly integrated CFS!) out for a > multimedia spin. I ... in test or with real use is cfs-v13. -- Bill Davidsen ...

linux-kernel - Bill Davidsen - Jul 11 2007 - 13:26

... > application here for as long as SD and CFS have been around. If I > have a compile running at nice 0, with v19 java gets so little cpu > that the the ... > it to start. This is new in v19 - something in v19 is not meshing > well with my ...

linux-kernel - Ingo Molnar - Jul 16 2007 - 05:17

... > > application here for as long as SD and CFS have been around. If I > > have a compile running at nice 0, with v19 java gets so little cpu > > that the the ... > it to start. This is new in v19 - something in v19 is not meshing > > well with ...

linux-kernel - Ed Tomlinson - Jul 16 2007 - 07:10

... he tried the v2.6.21.6-cfsv19 patch, and that > does not include the time.c ... below? (if yes, please revert it via patch -p1 -R ) Well, the 2.6.22.1 ... the 2.6.21.6-cfs-v19 does not have that patch applied. But both show this problem. Markus - ...

linux-kernel - Markus - Jul 17 2007 - 18:03

... the patch below is merged against 2.6.22.1-cfs-v19 - ... any other bad side-effects)? Ingo -------------------> Subject: time: introduce xtime_seconds From: Ingo Molnar ... (sec); } EXPORT_SYMBOL(do_gettimeofday); Index: linux-cfs-2.6.22.q/kernel/ ...

linux-kernel - Ingo Molnar - Jul 19 2007 - 13:17

... -06 at 19:33 +0200, Ingo Molnar wrote: > i'm pleased to announce release -v19 of the CFS scheduler patchset. I've taken mainline git tree (freshly integrated CFS!) out for a multimedia spin. I tested watching movies and ...

linux-kernel - Mike Galbraith - Jul 10 2007 - 04:08

... (in or outside of the scheduler). An app vanishing > unexpectedly might mean ... any problem. Then I applied the cfs-v19 for that kernel, rebuild ... /pub/linux/kernel/people/akpm/patches/2.6/2.6.22- ... -out/vdso-print-fatal-signals.patch > > you can turn it on ...

linux-kernel - Markus - Jul 16 2007 - 13:59

... moment) >>> >> Can you confirm whether CFS is involved, i.e. does ... like that >> even without the CFS patch applied? >> > > I will try ... latest 2.6.21 with cfs-v19 doesn't have any ... 6.22 w/o the patch. > hmmm .... could you take out ...

linux-kernel - Bill Davidsen - Jul 17 2007 - 00:22

... disappearing isn't you're typical process scheduler problem > > by any ... the same problem with the cfs-patch applied like the > git- ... original report, there are other patches involved, which are an unknown ... a plain 2.6.22 without cfs and one with it and ...

linux-kernel - Mike Galbraith - Jul 16 2007 - 02:42

... Tasks disappearing isn't you're typical process scheduler problem > by any means ... shows the same problem with the cfs-patch applied like the git-snapshot, I would say its a cfs issue. There is nothing in the ... a plain 2.6.22 without cfs and one with it and ...

linux-kernel - Markus - Jul 15 2007 - 17:11

... I've taken mainline git tree (freshly integrated CFS!) out for a > > multimedia spin. I tested ... in test or with > real use is cfs-v13. just as a test, does this ... this connected to the way X is scheduled? Another thing to check would be whether ...

linux-kernel - Ingo Molnar - Jul 11 2007 - 16:55

... 've taken mainline git tree (freshly integrated CFS!) out for a >>> multimedia spin. I ... this connected to the way X is scheduled? > > Partial answer: -10 didn't help with ... with none and the rest of us subject to "load shedding" with zero warning, ...

linux-kernel - Bill Davidsen - Jul 12 2007 - 08:41

... I've taken mainline git tree (freshly integrated CFS!) out for a >>> multimedia spin. I tested ... in test or with >> real use is cfs-v13. > > just as a test, does ... this connected to the way X is scheduled? > Doing this slows down the display rates, ...

linux-kernel - Bill Davidsen - Jul 13 2007 - 17:19