[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKfTPtBV6tkf237ZAtWrHAYAiK+o3m_cd7ctX3EeLzt+onzUZQ@mail.gmail.com>
Date: Fri, 28 Dec 2018 19:04:23 +0100
From: Vincent Guittot <vincent.guittot@...aro.org>
To: Tejun Heo <tj@...nel.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Sargun Dhillon <sargun@...gun.me>,
Xie XiuQi <xiexiuqi@...wei.com>,
Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>, xiezhipeng1@...wei.com,
huawei.libin@...wei.com,
linux-kernel <linux-kernel@...r.kernel.org>,
Dmitry Adamushko <dmitry.adamushko@...il.com>,
Rik van Riel <riel@...riel.com>
Subject: Re: [PATCH] sched: fix infinity loop in update_blocked_averages
On Fri, 28 Dec 2018 at 18:46, Tejun Heo <tj@...nel.org> wrote:
>
> On Fri, Dec 28, 2018 at 06:25:37PM +0100, Vincent Guittot wrote:
> > > done without extra space as long as each node has the parent pointer,
> > > which they do. Is the dedicated list an optimization?
> >
> > It prevents to parse and walk all task group struct every time.
> > Instead, you just have to follow a linked list
>
> Hmmm... I'm having a bit of a hard time imagining doing an actual
> traversal being a meaningful optimization. It may require more
> branches but that shouldn't be expensive at all, especially compared
> to walking all idle groups in the system each time which the code used
> to do. Anyways, this is tangential.
>
> Thanks for the explanation and happy new year!
Happy new year for you too
Thanks
Vincent
>
> --
> tejun
Powered by blists - more mailing lists