Messages in this thread | | | Date | Thu, 14 Jul 2016 19:34:27 +0200 | From | Oleg Nesterov <> | Subject | Re: Severe performance regression w/ 4.4+ on Android due to cgroup locking changes |
| |
On 07/14, Peter Zijlstra wrote: > > But I really think that this Android usecase invalidates the premise of > cgroups using a global lock.
Perhaps... but it would be nice to have a global lock for cgroups (and in fact probably unify it with dup_mmap_sem). And we can't simply revert that change now.
I am wondering if this use-case is really Android-specific or not. Because, once again, we can add a boot option or even run-time knob for cgroup_threadgroup_rwsem. If it is really Android-specific, we do not want to penalize fork/exit by default.
Oleg.
| |