All of lore.kernel.org
 help / color / mirror / Atom feed
From: linus.walleij@stericsson.com (Linus Walleij)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] RFC: nomadik: expand timesource to 63 bits
Date: Thu, 11 Nov 2010 11:31:43 +0100	[thread overview]
Message-ID: <4CDBC60F.8070905@stericsson.com> (raw)
In-Reply-To: <alpine.LFD.2.00.1011111054010.2900@localhost6.localdomain6>

Thomas Gleixner wrote:

> There is only one caveat. When nohz is on and you sleep longer than 16
> seconds then the limitation we have in place does not work anymore, as
> it would say that the long sleep time is less than the 63bit
> wraparound time. With 32bit clocksource it limits the sleep correclty
> to avoid the clocksource wrap issue.

Hm! So the .mask has that side effect (as I suspected), and with
this the sleep will be limited to what time you can get into 63 bits
(2200 years). And we sure want NOHZ...

But if I complement the solution with the keepwarm() timer from
Orion doing just a dummy read() on the clocksource every say 15 secs
it will work even if the system sleeps for so long.

> Aside of that you are trading a bit less source code with extra code
> in the clock read() function, which is called pretty frequently.

Hm, yeah. I would have to go to metrics but it's O(n)
is it not? Shouldn't hurt a high-frequency SMP system
I believe.

Yours,
Linus Walleij

WARNING: multiple messages have this Message-ID (diff)
From: Linus Walleij <linus.walleij@stericsson.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Nicolas Pitre <nico@fluxnic.net>,
	"linux-arm-kernel@lists.infradead.org" 
	<linux-arm-kernel@lists.infradead.org>,
	Colin Cross <ccross@google.com>,
	Rabin VINCENT <rabin.vincent@stericsson.com>
Subject: Re: [PATCH] RFC: nomadik: expand timesource to 63 bits
Date: Thu, 11 Nov 2010 11:31:43 +0100	[thread overview]
Message-ID: <4CDBC60F.8070905@stericsson.com> (raw)
In-Reply-To: <alpine.LFD.2.00.1011111054010.2900@localhost6.localdomain6>

Thomas Gleixner wrote:

> There is only one caveat. When nohz is on and you sleep longer than 16
> seconds then the limitation we have in place does not work anymore, as
> it would say that the long sleep time is less than the 63bit
> wraparound time. With 32bit clocksource it limits the sleep correclty
> to avoid the clocksource wrap issue.

Hm! So the .mask has that side effect (as I suspected), and with
this the sleep will be limited to what time you can get into 63 bits
(2200 years). And we sure want NOHZ...

But if I complement the solution with the keepwarm() timer from
Orion doing just a dummy read() on the clocksource every say 15 secs
it will work even if the system sleeps for so long.

> Aside of that you are trading a bit less source code with extra code
> in the clock read() function, which is called pretty frequently.

Hm, yeah. I would have to go to metrics but it's O(n)
is it not? Shouldn't hurt a high-frequency SMP system
I believe.

Yours,
Linus Walleij

  reply	other threads:[~2010-11-11 10:31 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-11  9:05 [PATCH] RFC: nomadik: expand timesource to 63 bits Linus Walleij
2010-11-11  9:05 ` Linus Walleij
2010-11-11 10:16 ` Thomas Gleixner
2010-11-11 10:16   ` Thomas Gleixner
2010-11-11 10:31   ` Linus Walleij [this message]
2010-11-11 10:31     ` Linus Walleij
2010-11-11 11:05     ` Thomas Gleixner
2010-11-11 11:05       ` Thomas Gleixner
2010-11-11 18:31       ` Nicolas Pitre
2010-11-11 18:31         ` Nicolas Pitre
2010-11-11 19:00         ` Thomas Gleixner
2010-11-11 19:00           ` Thomas Gleixner
2010-11-11 19:19           ` Nicolas Pitre
2010-11-11 19:19             ` Nicolas Pitre
2010-11-11 21:33 ` john stultz
2010-11-11 21:33   ` john stultz
2010-11-12  9:43   ` Linus Walleij
2010-11-12  9:43     ` Linus Walleij
2010-11-12  9:57   ` Uwe Kleine-König
2010-11-12  9:57     ` Uwe Kleine-König
2010-11-12 10:08     ` Linus Walleij
2010-11-12 10:08       ` Linus Walleij
2010-11-12 10:31       ` Thomas Gleixner
2010-11-12 10:31         ` Thomas Gleixner
2010-11-12 10:37         ` Linus Walleij
2010-11-12 10:37           ` Linus Walleij
2010-11-12 11:08           ` Thomas Gleixner
2010-11-12 11:08             ` Thomas Gleixner
2010-11-12 19:18           ` Nicolas Pitre
2010-11-12 19:18             ` Nicolas Pitre
2010-11-12 20:22           ` john stultz
2010-11-12 20:22             ` john stultz
2010-11-12 19:15     ` Nicolas Pitre
2010-11-12 19:15       ` Nicolas Pitre

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=4CDBC60F.8070905@stericsson.com \
    --to=linus.walleij@stericsson.com \
    --cc=linux-arm-kernel@lists.infradead.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.