Re: CFS group scheduler fairness broken starting from 2.6.29-rc1

[Ken Chen]

On Thu, Jul 23, 2009 at 12:57 AM, Bharata B
Rao<bharata@xxxxxxxxxxxxxxxxxx> wrote:
> Hi,
>
> Group scheduler fainess is broken since 2.6.29-rc1. git bisect led me
> to this commit:
>
> commit ec4e0e2fe018992d980910db901637c814575914
> Author: Ken Chen <kenchen@xxxxxxxxxx>
> Date:   Tue Nov 18 22:41:57 2008 -0800
>
>    sched: fix inconsistency when redistribute per-cpu tg->cfs_rq shares
>
>    Impact: make load-balancing more consistent
> ....
>
> ======================================================================
>                        % CPU time division b/n groups
> Group           2.6.29-rc1              2.6.29-rc1 w/o the above patch
> ======================================================================
> a with 8 tasks  44                      31
> b with 5 tasks  32                      34
> c with 3 tasks  22                      34
> ======================================================================
> All groups had equal shares.

What value did you use for each task_group's share?  For very large
value of tg->shares, it could be that all of the boost went to one CPU
and subsequently causes load-balancer to shuffle tasks around.  Do you
see any unexpected task migration?

- Ken
¢éì¹»®&Þ~º&¶¬?+-±éݶ¥?w®?Ë?±Êâméb?ìdz¹Þ?)í?æèw*jg¬±¨¶????Ý¢j/?êäz¹Þ??à2?Þ?¨è­Ú&¢)ß¡«a¶Úþø®G«?éh®æj:+v?¨?wè?Ù¥>W?±êÞiÛaxPjØm¶?ÿÃ-»+?ùd?_