LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: Al Boldi <a1426z@gawab.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [patch] sched: accurate user accounting
Date: Mon, 26 Mar 2007 07:27:30 +0200	[thread overview]
Message-ID: <1174886850.7040.71.camel@Homer.simpson.net> (raw)
In-Reply-To: <200703260811.18236.a1426z@gawab.com>

On Mon, 2007-03-26 at 08:11 +0300, Al Boldi wrote:

> > +       /* Sanity check. It should never go backwards or ruin accounting
> > */ +       if (unlikely(now < p->last_ran))
> > +               goto out_set;
> 
> If sched_clock() goes backwards, why not fix it, instead of hacking around 
> it?

When tasks change cpu, timestamp correction is attempted, but isn't
perfect (perfection: submit patch to read remote clock - people likely
toast poor submitter's buns very thoroughly).  Timewarps happen, and
even on Intel processors there seems to be very small difference in TSCs
in the same package.  (that's what instrumentation here said must be
true, possible booboos aside)

	-Mike


  reply	other threads:[~2007-03-26  5:27 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-03-26  5:11 Al Boldi
2007-03-26  5:27 ` Mike Galbraith [this message]
2007-03-26  8:45 ` Con Kolivas
  -- strict thread matches above, loose matches on Subject: below --
2007-03-25  1:59 [PATCH] [RFC] " Con Kolivas
2007-03-25  7:51 ` [patch] " Ingo Molnar
2007-03-25  8:39   ` Con Kolivas
2007-03-25  9:04     ` Ingo Molnar
2007-03-25 11:34   ` malc
2007-03-25 11:46     ` Con Kolivas
2007-03-25 12:02       ` Con Kolivas
2007-03-25 12:32         ` Gene Heskett
2007-03-25 12:41           ` Con Kolivas
2007-03-25 13:33             ` Gene Heskett
2007-03-25 13:05         ` malc
2007-03-25 13:06         ` malc
2007-03-25 14:15           ` Con Kolivas
2007-03-25 14:57             ` malc
2007-03-25 15:08               ` Con Kolivas
2007-03-25 15:19                 ` malc
2007-03-25 15:28                   ` Con Kolivas
2007-03-25 17:14                     ` malc
2007-03-25 23:01                       ` Con Kolivas
2007-03-25 23:57                         ` Con Kolivas
2007-03-26 10:49                           ` malc
2007-03-28 11:37                             ` Ingo Molnar
2007-06-14 17:56                               ` Vassili Karpov
2007-06-14 20:42                                 ` Ingo Molnar
2007-06-14 20:56                                   ` malc
2007-06-14 21:18                                     ` Ingo Molnar
2007-06-14 21:37                                       ` malc
2007-06-15  3:44                                         ` Balbir Singh
2007-06-15  6:07                                           ` malc
2007-06-16 13:21                                             ` Balbir Singh
2007-06-16 14:07                                               ` malc
2007-06-16 18:40                                                 ` Ingo Molnar
2007-06-16 20:31                                                   ` malc

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=1174886850.7040.71.camel@Homer.simpson.net \
    --to=efault@gmx.de \
    --cc=a1426z@gawab.com \
    --cc=linux-kernel@vger.kernel.org \
    --subject='Re: [patch] sched: accurate user accounting' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).