Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically

From	Steven Rostedt <rostedt@goodmis.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically
Date	2017-05-16 15:20 +0200
Message-ID	<tHKym-65Z-3@gated-at.bofh.it> (permalink)
References	<tGbCF-8iQ-3@gated-at.bofh.it> <tGbCF-8iQ-7@gated-at.bofh.it> <tGjJT-5NS-5@gated-at.bofh.it> <tHECB-2bV-1@gated-at.bofh.it> <tHI3v-4o0-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Tue, 16 May 2017 11:32:41 +0100
Juri Lelli <juri.lelli@arm.com> wrote:

> Not sure, but if we are going to retry a lot it might be better off to
> put proper locking instead? We could also simply bail out when we notice

Actually, locking can make it much worse. I've been playing with RT on
boxes with 240 cores (with HT turned off!), and *any* locks in the
scheduler can cause huge contention.

> that something is changed under our feet. I'd say (again :) we might
> first want to understand (with some numbers) how bad the problem is and
> then fix it. I guess numbers might also help us to better understand
> what the best fix is?

Exactly. I haven't seen any numbers. Yes, it is not perfect, but we
don't know how unperfect it is. Numbers will help to know if there is
even a problem or not with the current solution.

-- Steve

Thread

[PATCH v4 0/5] Make find_later_rq() choose a closer cpu in topology Byungchul Park <byungchul.park@lge.com> - 2017-05-12 07:50 +0200
  [PATCH v4 3/5] sched/deadline: Change return value of cpudl_find() Byungchul Park <byungchul.park@lge.com> - 2017-05-12 07:50 +0200
  [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Byungchul Park <byungchul.park@lge.com> - 2017-05-12 07:50 +0200
    Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements  atomically Steven Rostedt <rostedt@goodmis.org> - 2017-05-12 16:30 +0200
      Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Juri Lelli <juri.lelli@arm.com> - 2017-05-15 10:40 +0200
        Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Byungchul Park <byungchul.park@lge.com> - 2017-05-16 09:10 +0200
      Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Byungchul Park <byungchul.park@lge.com> - 2017-05-16 09:00 +0200
        Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Juri Lelli <juri.lelli@arm.com> - 2017-05-16 12:40 +0200
          Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements  atomically Steven Rostedt <rostedt@goodmis.org> - 2017-05-16 15:20 +0200
            Re: [PATCH v4 1/5] sched/deadline: Refer to cpudl.elements atomically Byungchul Park <byungchul.park@lge.com> - 2017-05-23 03:20 +0200
  [PATCH v4 4/5] sched/deadline: Add support for SD_PREFER_SIBLING on find_later_rq() Byungchul Park <byungchul.park@lge.com> - 2017-05-12 08:00 +0200
  [PATCH v4 5/5] sched/rt: Add support for SD_PREFER_SIBLING on find_lowest_rq() Byungchul Park <byungchul.park@lge.com> - 2017-05-12 08:00 +0200

csiph-web