[PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED"

[PATCH v3 00/12] sched: consolidation of cpu_power · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
[PATCH v3 01/12] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Preeti U Murthy <hidden> · 2014-07-08
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-08
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Preeti U Murthy <hidden> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Peter Zijlstra <peterz@infradead.org> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Preeti U Murthy <hidden> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Peter Zijlstra <peterz@infradead.org> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
[PATCH v4 ] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
Re: [PATCH v4 ] sched: fix imbalance flag reset · Preeti U Murthy <hidden> · 2014-07-10
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Preeti U Murthy <hidden> · 2014-07-10
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Peter Zijlstra <peterz@infradead.org> · 2014-07-09
Re: [PATCH v3 01/12] sched: fix imbalance flag reset · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-09
[PATCH v3 03/12] sched: fix avg_load computation · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 03/12] sched: fix avg_load computation · Rik van Riel <hidden> · 2014-07-09
[PATCH v3 06/12] sched: add per rq cpu_power_orig · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 06/12] sched: add per rq cpu_power_orig · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 06/12] sched: add per rq cpu_power_orig · Amit Kucheria <hidden> · 2014-07-09
[PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Peter Zijlstra <peterz@infradead.org> · 2014-07-10
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-11
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Peter Zijlstra <peterz@infradead.org> · 2014-07-11
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-11
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Peter Zijlstra <peterz@infradead.org> · 2014-07-11
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Morten Rasmussen <hidden> · 2014-07-14
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Peter Zijlstra <peterz@infradead.org> · 2014-07-14
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Morten Rasmussen <hidden> · 2014-07-14
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Peter Zijlstra <peterz@infradead.org> · 2014-07-14
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-15
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Dietmar Eggemann <dietmar.eggemann@arm.com> · 2014-07-14
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Yuyang Du <hidden> · 2014-07-18
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Morten Rasmussen <hidden> · 2014-07-11
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-15
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Morten Rasmussen <hidden> · 2014-07-15
Re: [PATCH v3 09/12] Revert "sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED" · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-15
[PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Peter Zijlstra <peterz@infradead.org> · 2014-07-10
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Peter Zijlstra <peterz@infradead.org> · 2014-07-11
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-11
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Peter Zijlstra <peterz@infradead.org> · 2014-07-14
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-15
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Peter Zijlstra <peterz@infradead.org> · 2014-07-10
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
Re: [PATCH v3 08/12] sched: move cfs task on a CPU with higher capacity · Peter Zijlstra <peterz@infradead.org> · 2014-07-10
[PATCH v3 12/12] sched: add SD_PREFER_SIBLING for SMT level · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
[PATCH v3 11/12] sched: replace capacity_factor by utilization · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
[PATCH v3 10/12] sched: get CPU's utilization statistic · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
[PATCH v3 07/12] sched: test the cpu's capacity in wake affine · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 07/12] sched: test the cpu's capacity in wake affine · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 07/12] sched: test the cpu's capacity in wake affine · Peter Zijlstra <peterz@infradead.org> · 2014-07-10
Re: [PATCH v3 07/12] sched: test the cpu's capacity in wake affine · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
[PATCH v3 05/12] ARM: topology: use new cpu_power interface · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 05/12] ARM: topology: use new cpu_power interface · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 05/12] ARM: topology: use new cpu_power interface · Amit Kucheria <hidden> · 2014-07-09
Re: [PATCH v3 05/12] ARM: topology: use new cpu_power interface · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-09
[PATCH v3 04/12] sched: Allow all archs to set the power_orig · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 04/12] sched: Allow all archs to set the power_orig · Rik van Riel <hidden> · 2014-07-09
Re: [PATCH v3 04/12] sched: Allow all archs to set the power_orig · Peter Zijlstra <peterz@infradead.org> · 2014-07-09
Re: [PATCH v3 04/12] sched: Allow all archs to set the power_orig · Vincent Guittot <vincent.guittot@linaro.org> · 2014-07-10
[PATCH v3 02/12] sched: remove a wake_affine condition · Vincent Guittot <vincent.guittot@linaro.org> · 2014-06-30
Re: [PATCH v3 02/12] sched: remove a wake_affine condition · Rik van Riel <hidden> · 2014-07-09

From: vincent.guittot@linaro.org (Vincent Guittot)
Date: 2014-07-15 09:54:05
Also in: lkml

On 15 July 2014 11:32, Morten Rasmussen [off-list ref] wrote:

On Tue, Jul 15, 2014 at 10:27:19AM +0100, Vincent Guittot wrote:

quoted

On 11 July 2014 18:13, Morten Rasmussen [off-list ref] wrote:

[snip]

quoted

In this example using rq->avg leads to imbalance whereas unweighted load
would not. Correct me if I missed anything.

You just miss to take into account how the imbalance is computed

I don't think so. I'm aware that the imbalance is calculated based on
the runnable_load_avg of the cpus. But if you pick the wrong cpus to
compare to begin with, it doesn't matter.

The average load of your sched_domain is 1 task per CPU so CPU1 will
pull only 1 task and not 2

Morten

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help