mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Rick Lindsley <ricklind@us.ibm.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
	Andrew Morton <akpm@osdl.org>,
	linux-kernel@vger.kernel.org, Andi Kleen <ak@suse.de>
Subject: Re: [PATCH 12/13] schedstats additions for sched-balance-fork
Date: Fri, 25 Feb 2005 03:07:25 -0800	[thread overview]
Message-ID: <200502251107.j1PB7Ptk008435@owlet.beaverton.ibm.com> (raw)
In-Reply-To: Your message of "Thu, 24 Feb 2005 09:46:22 +0100." <20050224084622.GC10023@elte.hu>

    There is little help we get from userspace, and i'm not sure we want to
    add scheduler overhead for this single benchmark - when something like a
    _tiny_ bit of NUMAlib use within the OpenMP library would probably solve
    things equally well!

There's has been a general problem with sched domains and it trying to
meet two goals: "1) spread things around evenly within a domain and
balance across domains infrequently", and "2) load up cores before
loading up siblings, even at the expense of violating 1)".

We've had trouble getting both 1) and 2) implemented correctly in
the past.  If this patch gets us closer to that nirvana, it will be
valuable regardless of the benchmark it also happens to be improving.

Regardless, I agree it will need good testing, and we may need to
pick the wheat from the chaff.

Rick

  parent reply	other threads:[~2005-02-25 11:08 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-02-24  7:14 [PATCH 0/13] Multiprocessor CPU scheduler patches Nick Piggin
2005-02-24  7:16 ` [PATCH 1/13] timestamp fixes Nick Piggin
2005-02-24  7:16   ` [PATCH 2/13] improve pinned task handling Nick Piggin
2005-02-24  7:18     ` [PATCH 3/13] rework schedstats Nick Piggin
2005-02-24  7:19       ` [PATCH 4/13] find_busiest_group fixlets Nick Piggin
2005-02-24  7:20         ` [PATCH 5/13] find_busiest_group cleanup Nick Piggin
2005-02-24  7:21           ` [PATCH 6/13] no aggressive idle balancing Nick Piggin
2005-02-24  7:22             ` [PATCH 7/13] better active balancing heuristic Nick Piggin
2005-02-24  7:24               ` [PATCH 8/13] generalised CPU load averaging Nick Piggin
2005-02-24  7:25                 ` [PATCH 9/13] less affine wakups Nick Piggin
2005-02-24  7:27                   ` [PATCH 10/13] remove aggressive idle balancing Nick Piggin
2005-02-24  7:28                     ` [PATCH 11/13] sched-domains aware balance-on-fork Nick Piggin
2005-02-24  7:28                       ` [PATCH 12/13] schedstats additions for sched-balance-fork Nick Piggin
2005-02-24  7:30                         ` [PATCH 13/13] basic tuning Nick Piggin
2005-02-24  8:46                         ` [PATCH 12/13] schedstats additions for sched-balance-fork Ingo Molnar
2005-02-24 22:13                           ` Nick Piggin
2005-02-25 11:07                           ` Rick Lindsley [this message]
2005-02-25 11:21                             ` Nick Piggin
2005-02-24  8:41                     ` [PATCH 10/13] remove aggressive idle balancing Ingo Molnar
2005-02-24 12:13                       ` Nick Piggin
2005-02-24 12:16                         ` Ingo Molnar
2005-03-06  5:43                         ` Siddha, Suresh B
2005-03-07  5:34                           ` Nick Piggin
2005-03-07  8:04                             ` Siddha, Suresh B
2005-03-07  8:28                               ` Nick Piggin
2005-03-08  7:22                                 ` Siddha, Suresh B
2005-03-08  8:17                                   ` Nick Piggin
2005-03-08 19:36                                     ` Siddha, Suresh B
2005-02-24  8:39               ` [PATCH 7/13] better active balancing heuristic Ingo Molnar
2005-02-24  8:36         ` [PATCH 4/13] find_busiest_group fixlets Ingo Molnar
2005-02-24  8:07       ` [PATCH 3/13] rework schedstats Ingo Molnar
2005-02-25 10:50       ` Rick Lindsley
2005-02-25 11:10         ` Nick Piggin
2005-02-25 11:25           ` DHCP on multi homed host! Ravindra Nadgauda
2005-02-24  8:04     ` [PATCH 2/13] improve pinned task handling Ingo Molnar
2005-02-24  7:46   ` [PATCH 1/13] timestamp fixes Ingo Molnar
2005-02-24  7:56     ` Nick Piggin
2005-02-24  8:34       ` Ingo Molnar

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=200502251107.j1PB7Ptk008435@owlet.beaverton.ibm.com \
    --to=ricklind@us.ibm.com \
    --cc=ak@suse.de \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=nickpiggin@yahoo.com.au \
    /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®