[patch] CFS scheduler, -v8




i'm pleased to announce release -v8 of the CFS scheduler patchset. (The
main goal of CFS is to implement "desktop scheduling" with as high
quality as technically possible.)

The CFS patch against v2.6.21.1 (or against v2.6.20.10) can be
downloaded from the usual place:

http://people.redhat.com/mingo/cfs-scheduler/

-v7 resolved a couple of important regresisons while not introducing new
regressions, so i felt it was time to step forward: -v8 tries to address
one of the last (known) frontiers: 3D/OpenGL games^H^H^H applications
'smoothness'.

To achieve more scheduling smoothness, -v8 introduces a new 'precise
load calculation and smoothing' feature. (A variant of this was
suggested by Peter Williams in earlier CFS discussions - thanks Peter!)

i was able to reuse the rq->cpu_load[] load average calculation from
Peter Williams's smpnice code, and it's thus now utilized on UP too. As
a nice side-effect of CFS using a smoothed load metric, apps should also
start up faster under load. CFS now utilizes the full range of smpnice
metrics.

No other fundamental portion of CFS was touched, so the rate of change
is moderate:

7 files changed, 140 insertions(+), 79 deletions(-)

Changes since -v7:

- powerpc debug output and build warning fixes (Balbir Singh)

- documentation fixes (Zach Carter)

- interactivity: precise load calculation and load smoothing

As usual, any sort of feedback, bugreport, fix and suggestion is more
than welcome,

Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



Relevant Pages

  • Re: [patch] CFS scheduler, -v12
    ... weighted load. ... Mainline's convergence to proper CPU bandwidth ... This doesn't directly translate to cfs. ... probably try to figure out if its aggregate lag is ...
    (Linux-Kernel)
  • Re: [ck] Re: SD still better than CFS for 3d ?(was Re: 2.6.23-rc1)
    ... that when i tried to find a 3D regression in CFS i found a 3D regression ... on 2.6.22 and SD it drops instantly to 4 fps. ... While CFS runs ~70 with 1.9 load. ... With this patch someone sent me over IRC i get similar values to CFS, ...
    (Linux-Kernel)
  • Re: [ck] Re: SD still better than CFS for 3d ?(was Re: 2.6.23-rc1)
    ... compare numbers to wine? ... I regularly test native Linux games on CFS, ... you have to start up your favorite game in a way ... then create load the following way, by entering this into a shell: ...
    (Linux-Kernel)
  • Re: "REPORT: sd-0.46 vs cfs-v6 vs mainline 2.6.21-rc7 Beryl + Video + Audio"
    ... When not under load everything ... run's better or similarly to cfs or mainline. ... Occasionally I had complete mouse freezes with cfs when the system was ... Please read the FAQ at http://www.tux.org/lkml/ ...
    (Linux-Kernel)
  • Re: [patch] CFS scheduler, -v8
    ... I was begining to work on a prototype to do group scheduling based ... have the mindshare cfs seems to have acquired. ... The big question I have is, how well does DWRR fits into the "currently hot" ... the intent of DWRR was to provide proportional fairness and rely ...
    (Linux-Kernel)