[PATCH v2 01/11] sched: fix imbalance flag reset

Vincent Guittot vincent.guittot at linaro.org
Mon May 26 03:14:22 PDT 2014


On 26 May 2014 11:16, Preeti U Murthy <preeti at linux.vnet.ibm.com> wrote:
> On 05/26/2014 01:19 PM, Vincent Guittot wrote:
>> On 25 May 2014 12:33, Preeti U Murthy <preeti at linux.vnet.ibm.com> wrote:
>>> Hi Vincent,
>>>
>>> On 05/23/2014 09:22 PM, Vincent Guittot wrote:
>>>> The imbalance flag can stay set whereas there is no imbalance.
>>>>
>>>> Let assume that we have 3 tasks that run on a dual cores /dual cluster system.
>>>> We will have some idle load balance which are triggered during tick.
>>>> Unfortunately, the tick is also used to queue background work so we can reach
>>>> the situation where short work has been queued on a CPU which already runs a
>>>> task. The load balance will detect this imbalance (2 tasks on 1 CPU and an idle
>>>> CPU) and will try to pull the waiting task on the idle CPU. The waiting task is
>>>> a worker thread that is pinned on a CPU so an imbalance due to pinned task is
>>>> detected and the imbalance flag is set.
>>>> Then, we will not be able to clear the flag because we have at most 1 task on
>>>> each CPU but the imbalance flag will trig to useless active load balance
>>>> between the idle CPU and the busy CPU.
>>>
>>> Why do we do active balancing today when there is at-most 1 task on the
>>> busiest cpu? Shouldn't we be skipping load balancing altogether? If we
>>> do active balancing when the number of tasks = 1, it will lead to a ping
>>> pong right?
>>
>> That's the purpose of the patch to prevent this useless active load
>> balance. When the imbalance flag is set, an active load balance is
>> triggered whatever the load balance is because of pinned tasks that
>> prevents a balance state.
>
> No I mean this:
>
> sched:Do not continue load balancing when the busiest cpu has one
> running task

But you can have situation where you have to migrate the task even if
the busiest CPU has only 1 task. The use of imbalance flag is one
example. You can also be in a situation where the busiest group has
too much load compared to the local group and the busiest CPU even
with 1 task (at this instant) has been selected to move task away from
the busiest group

Vincent

>
> From: Preeti U Murthy <preeti at linux.vnet.ibm.com>
>
>
> ---
>  kernel/sched/fair.c |    2 ++
>  1 file changed, 2 insertions(+)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index c9617b7..b175333 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6626,6 +6626,8 @@ more_balance:
>                         }
>                         goto out_balanced;
>                 }
> +       } else {
> +               goto out;
>         }
>
>         if (!ld_moved) {
>
>
> }
>
> Regards
> Preeti U Murthy
>>
>> Vincent
>>
>>>
>>> Regards
>>> Preeti U Murthy
>>>
>>
>



More information about the linux-arm-kernel mailing list