lkml.org 
[lkml]   [2022]   [Apr]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [External] Re: [PATCH 1/2] sched/fair: Fix cfs_rq_clock_pelt() for throttled cfs_rq
From
On 2022/4/8 04:57, Benjamin Segall wrote:
> Chengming Zhou <zhouchengming@bytedance.com> writes:
>
>> Since commit 23127296889f ("sched/fair: Update scale invariance of PELT")
>> change to use rq_clock_pelt() instead of rq_clock_task(), we should also
>> use rq_clock_pelt() for throttled_clock_task_time and throttled_clock_task
>> accounting.
>
> I think this patch is indeed what we want, despite the confusing
> interactions between pelt slowdown+skipping and throttle_clock_task
> trying to freeze time.
>
> I think it would be slightly better to rename
> throttled_clock_task(_time) to be clock_pelt rather than clock_task, but
> that's minor.

It's a good suggestion, will do and send v2.

Thanks.

>
> Reviewed-by: Ben Segall <bsegall@google.com>
>
>>
>> Fixes: 23127296889f ("sched/fair: Update scale invariance of PELT")
>> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
>> ---
>> kernel/sched/fair.c | 6 +++---
>> 1 file changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index d4bd299d67ab..e6fa5d1141b4 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -4846,7 +4846,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
>>
>> cfs_rq->throttle_count--;
>> if (!cfs_rq->throttle_count) {
>> - cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
>> + cfs_rq->throttled_clock_task_time += rq_clock_pelt(rq) -
>> cfs_rq->throttled_clock_task;
>>
>> /* Add cfs_rq with load or one or more already running entities to the list */
>> @@ -4864,7 +4864,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
>>
>> /* group is entering throttled state, stop time */
>> if (!cfs_rq->throttle_count) {
>> - cfs_rq->throttled_clock_task = rq_clock_task(rq);
>> + cfs_rq->throttled_clock_task = rq_clock_pelt(rq);
>> list_del_leaf_cfs_rq(cfs_rq);
>> }
>> cfs_rq->throttle_count++;
>> @@ -5308,7 +5308,7 @@ static void sync_throttle(struct task_group *tg, int cpu)
>> pcfs_rq = tg->parent->cfs_rq[cpu];
>>
>> cfs_rq->throttle_count = pcfs_rq->throttle_count;
>> - cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
>> + cfs_rq->throttled_clock_task = rq_clock_pelt(cpu_rq(cpu));
>> }
>>
>> /* conditionally throttle active cfs_rq's from put_prev_entity() */

\
 
 \ /
  Last update: 2022-04-08 08:26    [W:0.046 / U:2.888 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site