[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160714161413.GD30154@twins.programming.kicks-ass.net>
Date: Thu, 14 Jul 2016 18:14:13 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Oleg Nesterov <oleg@...hat.com>
Cc: Tejun Heo <tj@...nel.org>, John Stultz <john.stultz@...aro.org>,
Ingo Molnar <mingo@...hat.com>,
lkml <linux-kernel@...r.kernel.org>,
Dmitry Shmidt <dimitrysh@...gle.com>,
Rom Lemarchand <romlem@...gle.com>,
Colin Cross <ccross@...gle.com>, Todd Kjos <tkjos@...gle.com>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: Re: Severe performance regression w/ 4.4+ on Android due to cgroup
locking changes
On Thu, Jul 14, 2016 at 04:58:44PM +0200, Oleg Nesterov wrote:
>
> Of course, this leads to another question: do we really need rcu-sync at
> all, or should we change percpu-rwsem to always work in the "slow" mode
> which is not that slow with your change... I'd like to keep it ;)
>
> What do you think?
Yes, I think we wants to keep it. There are users where the read size
cost really are performance critical. I still have to repost that lglock
removal series for example, which replaces the fs/locks lglock with a
percpu-rwsem.
Powered by blists - more mailing lists