Messages in this thread | | | Date | Fri, 3 Nov 2023 14:01:38 +0000 | Subject | Re: [RFC PATCH 5/6] sched/uclamp: Remove all uclamp bucket logic | From | Hongyan Xia <> |
| |
On 03/11/2023 13:50, Dietmar Eggemann wrote: > On 04/10/2023 11:04, Hongyan Xia wrote: >> From: Hongyan Xia <hongyan.xia2@arm.com> >> >> Also rewrite uclamp_update_active() so that the effective uclamp values >> are updated every time we change task group properties, change system >> defaults or a request is issued from userspace. > > Tested it with > > # cgcreate -g cpu:/A > # echo $$ > /sys/fs/cgroup/cpu/A/tasks > > (1) per-task > > # uclampset --pid $$ -m 256 -M 768 > > (2) per taskgroup > > # echo 25.0 > /sys/fs/cgroup/cpu/A/cpu.uclamp.min > # echo 75.0 > /sys/fs/cgroup/cpu/A/cpu.uclamp.max > > (3) system-wide > > # echo 256 > /proc/sys/kernel/sched_util_clamp_min > # echo 768 > /proc/sys/kernel/sched_util_clamp_max > > uclamp_update_active() -> uclamp_update_active_nolock() is called in all > cases. >
Thanks for testing!
> > uclamp_eff_get()'s function header still mentions `clamp bucket index`.
This is indeed confusing. I have changed it from 'clamp bucket index' to just 'uclamp value'.
>> [...] > > [...]
| |