mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Venkatesh Pallipadi <venki@google.com>
Cc: Ingo Molnar <mingo@elte.hu>, "H. Peter Anvin" <hpa@zytor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	Martin Schwidefsky <schwidefsky@de.ibm.com>,
	linux-kernel@vger.kernel.org, Paul Turner <pjt@google.com>
Subject: Re: [PATCH 2/6] Add IRQ_TIME_ACCOUNTING, finer accounting of CPU irq time
Date: Mon, 20 Sep 2010 19:23:12 +0200	[thread overview]
Message-ID: <1285003392.2275.755.camel@laptop> (raw)
In-Reply-To: <AANLkTinu+2N7xnkuzMvhL+3V=vbRMDNT6ep-OHPrbT4y@mail.gmail.com>

On Mon, 2010-09-20 at 10:13 -0700, Venkatesh Pallipadi wrote:

> >> +       local_irq_save(flags);
> >> +
> >> +       cpu = task_cpu(tsk);
> >
> > Can this ever be anything other can smp_processor_id() and current?
> >
> >> +       now = sched_clock();
> >
> > this should be using one of the kernel/sched_clock.c thingies, probably
> > local_clock(), or sched_clock_cpu(cpu).
> 
> I don't really need task there. I can use smp_processor_id() or
> task_cpu(tsk) and I think latter one would be cheaper.

Not sure, task_cpu() gets the cpu number from the task_info struct,
smp_processor_id() gets it from per-cpu storage, both are a single
memory read.

But I think its a tad confusing that this function has a task argument
at all, but if its always current, it would be slightly better to call
it 'curr' or something.

Also, local_irq_safe() followed by smp_processor_id() is clearly local,
task_cpu(tsk) can be anything.

> You mean sched_clock() is not the right interface to use here.
> sched_clock_cpu() uses either sched_clock or remote_cpu stuff which I
> don't really need here and local_clock() also has irq
> disable/smp_processor_id() and calls sched_clock_cpu in turn.
> sched_clock() seemed to be more appropriate.

yeah, use sched_clock_cpu(smp_processor_id()), sched_clock() can be
utter crap on x86, the code in kernel/sched_clock.c tries its best to
sanitize the crap we get from the hardware.




  reply	other threads:[~2010-09-20 17:23 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-17  1:56 [PATCH 0/6] Proper kernel irq time accounting Venkatesh Pallipadi
2010-09-17  1:56 ` [PATCH 1/6] Consolidate account_system_vtime extern declaration Venkatesh Pallipadi
2010-09-17  1:56 ` [PATCH 2/6] Add IRQ_TIME_ACCOUNTING, finer accounting of CPU irq time Venkatesh Pallipadi
2010-09-19 11:11   ` Peter Zijlstra
2010-09-20 17:13     ` Venkatesh Pallipadi
2010-09-20 17:23       ` Peter Zijlstra [this message]
2010-09-19 11:21   ` Peter Zijlstra
2010-09-19 11:42     ` Peter Zijlstra
2010-09-19 12:01     ` Peter Zijlstra
2010-09-20  7:27       ` Martin Schwidefsky
2010-09-20  9:27         ` Peter Zijlstra
2010-09-20 17:16           ` Venkatesh Pallipadi
2010-09-20 17:26             ` Peter Zijlstra
2010-09-27 20:35               ` [PATCH] si time accounting accounts bh_disable'd time to si Venkatesh Pallipadi
2010-09-27 20:53                 ` Eric Dumazet
2010-09-27 21:11                   ` Venkatesh Pallipadi
2010-09-27 21:16                     ` Eric Dumazet
2010-09-30 11:17                 ` Peter Zijlstra
2010-09-17  1:56 ` [PATCH 3/6] x86: Add IRQ_TIME_ACCOUNTING in x86 Venkatesh Pallipadi
2010-09-17  1:56 ` [PATCH 4/6] sched: Do not account irq time to current task Venkatesh Pallipadi
2010-09-19 11:28   ` Peter Zijlstra
2010-09-20 17:33     ` Venkatesh Pallipadi
2010-09-20 17:38       ` Peter Zijlstra
2010-09-20 17:40         ` Venkatesh Pallipadi
2010-09-17  1:56 ` [PATCH 5/6] sched: Remove irq time from available CPU power Venkatesh Pallipadi
2010-09-19 11:31   ` Peter Zijlstra
2010-09-20 17:38     ` Venkatesh Pallipadi
2010-09-17  1:56 ` [PATCH 6/6] Export per cpu hardirq and softirq time in proc Venkatesh Pallipadi

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=1285003392.2275.755.camel@laptop \
    --to=peterz@infradead.org \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=pjt@google.com \
    --cc=schwidefsky@de.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=venki@google.com \
    /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

Powered by JetHome