mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Yuyang Du <yuyang.du@intel.com>
To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: umgwanakikbuti@gmail.com, bsegall@google.com, pjt@google.com,
	morten.rasmussen@arm.com, vincent.guittot@linaro.org,
	dietmar.eggemann@arm.com, matt@codeblueprint.co.uk,
	Yuyang Du <yuyang.du@intel.com>
Subject: [RFC PATCH 00/11] Refactor select_task_rq_fair()
Date: Thu, 16 Jun 2016 09:49:24 +0800	[thread overview]
Message-ID: <1466041775-4528-1-git-send-email-yuyang.du@intel.com> (raw)

Hi all,

As a follow-up of my recent proposal to remove SD_WAKE_AFFINE, I have this
initial-draft and unfinished refactoring to select_task_rq_fair().

Basic idea is to form a comprehensive view of the topology to guide the
select.

My many wanted jobs haven't been achieved, so I decided to post this initial
draft earlier to have your comments and experiences (I have no experience on
production multi-socket machines and no real experince on heterogeneous CPUs).
But generally, better topology view, I believe, should greatly help with the
full spectrum of machines from big to small.

Just lightly tested, it only works, :)

So my patches are built on Peter's select_idle_sibling() patches (so all of
them should be a little outdated), and borrowed his scan cost regulation part.

Thanks a lot.

Yuyang

--

Peter Zijlstra (6):
  sched: Remove unused @cpu argument from destroy_sched_domain*()
  sched: Restructure destroy_sched_domain()
  sched: Introduce struct sched_domain_shared
  sched: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched: Rewrite select_idle_siblings()
  sched: Optimize SCHED_SMT

Yuyang Du (5):
  sched: Clean up SD_BALANCE_WAKE flags in sched domain build-up
  sched: Remove SD_WAKE_AFFINE flag and replace it with SD_BALANCE_WAKE
  sched: Add per CPU variable sd_socket_id to specify the CPU's socket
  sched: Add sched_llc_complete static key to specify whether the LLC
    covers all CPUs
  sched/fair: Refactor select_task_rq_fair()

 include/linux/sched.h    |   17 +-
 kernel/sched/core.c      |  134 ++++++++---
 kernel/sched/deadline.c  |    2 +-
 kernel/sched/fair.c      |  589 +++++++++++++++++++++++++++++++++++++++++-----
 kernel/sched/features.h  |    1 +
 kernel/sched/idle_task.c |    2 +-
 kernel/sched/rt.c        |    2 +-
 kernel/sched/sched.h     |   28 ++-
 kernel/time/tick-sched.c |   10 +-
 9 files changed, 680 insertions(+), 105 deletions(-)

-- 
1.7.9.5

             reply	other threads:[~2016-06-16  9:46 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-16  1:49 Yuyang Du [this message]
2016-06-16  1:49 ` [RFC PATCH 01/11] sched: Remove unused @cpu argument from destroy_sched_domain*() Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 02/11] sched: Restructure destroy_sched_domain() Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 03/11] sched: Introduce struct sched_domain_shared Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 04/11] sched: Replace sd_busy/nr_busy_cpus with sched_domain_shared Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 05/11] sched: Rewrite select_idle_siblings() Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 06/11] sched: Optimize SCHED_SMT Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 07/11] sched: Clean up SD_BALANCE_WAKE flags in sched domain build-up Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 08/11] sched: Remove SD_WAKE_AFFINE flag and replace it with SD_BALANCE_WAKE Yuyang Du
2016-06-23 13:04   ` Matt Fleming
2016-06-23 13:54     ` Peter Zijlstra
2016-06-23 14:06     ` Mike Galbraith
2016-06-16  1:49 ` [RFC PATCH 09/11] sched: Add per CPU variable sd_socket_id to specify the CPU's socket Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 10/11] sched: Add sched_llc_complete static key to specify whether the LLC covers all CPUs Yuyang Du
2016-06-16  1:49 ` [RFC PATCH 11/11] sched/fair: Refactor select_task_rq_fair() Yuyang Du
2016-06-16  1:57   ` Yuyang Du

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1466041775-4528-1-git-send-email-yuyang.du@intel.com \
    --to=yuyang.du@intel.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matt@codeblueprint.co.uk \
    --cc=mingo@kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=umgwanakikbuti@gmail.com \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®