On Sat, Jul 23, 2022 at 04:28:28AM -1000, Tejun Heo wrote:
> 3942a9bd7b58 ("locking, rcu, cgroup: Avoid synchronize_sched() in
> __cgroup_procs_write()") disabled percpu operations on threadgroup_rwsem
> because the impiled synchronize_rcu() on write locking was pushing up the
> latencies too much for android which constantly moves processes between
> cgroups.
>
> This makes the hotter paths - fork and exit - slower as they're always
> forced into the slow path. There is no reason to force this on everyone
> especially given that more common static usage pattern can now completely
> avoid write-locking the rwsem. Write-locking is elided when turning on and
> off controllers on empty sub-trees and CLONE_INTO_CGROUP enables seeding a
> cgroup without grabbing the rwsem.
>
> Restore the default percpu operations and introduce the mount option
> "favordynmods" and config option CGROUP_FAVOR_DYNMODS for users who need
> lower latencies for the dynamic operations.
>
> Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
> Cc: Christian Brauner <brauner@xxxxxxxxxx>
> Cc: Michal Koutný <mkoutny@xxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: John Stultz <john.stultz@xxxxxxxxxx>
> Cc: Dmitry Shmidt <dimitrysh@xxxxxxxxxx>
> Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
> ---
Seems sane,
Acked-by: Christian Brauner (Microsoft) <brauner@xxxxxxxxxx>
