From: Thomas Gleixner <tglx@linutronix.de>
To: David Lang <david@lang.hm>
Cc: Christoph Lameter <cl@linux.com>,
Richard Cochran <richardcochran@gmail.com>,
linux-kernel@vger.kernel.org
Subject: Re: Why do we still have 32 bit counters? Interrupt counters overflow within 50 days
Date: Mon, 6 Oct 2014 14:28:26 +0200 (CEST) [thread overview]
Message-ID: <alpine.DEB.2.11.1410061426471.4383@nanos> (raw)
In-Reply-To: <alpine.DEB.2.02.1410060347300.26324@nftneq.ynat.uz>
On Mon, 6 Oct 2014, David Lang wrote:
> On Sun, 5 Oct 2014, Thomas Gleixner wrote:
>
> > >
> > > 64 bit counters on 32 bit machines are not an easy thing and could be
> >
> > Whats so hard about 64bit counters on 32bit machines?
> >
> > > expensive to handle in particular because these counters are used in
> > > performance critical hotpaths.
> >
> > The expensive overhead is a single "adcl" instruction.
>
> As I understand it, since the 64 bit math cannot be made atomic, it requires
> protecting the counter with a lock so that it can't be read while half
> updated. Aquiring a lock on every update is an expensive thing to do. It's not
> something people like to see in a fast path, especially for something of as
> low an importance as the counters.
As I said before. Both reader and writer side are already protected by
the irq descriptor lock. We take that lock anyway.
Thanks,
tglx
next prev parent reply other threads:[~2014-10-06 12:28 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-03 9:45 Why do we still have 32 bit counters? Interrupt counters overflow within 50 days Christoph Lameter
2014-10-03 10:33 ` Thomas Gleixner
2014-10-03 11:54 ` Christoph Lameter
2014-10-03 12:03 ` Richard Cochran
2014-10-03 12:07 ` Christoph Lameter
2014-10-03 12:17 ` Richard Cochran
2014-10-03 14:04 ` Christoph Lameter
2014-10-05 21:49 ` Thomas Gleixner
2014-10-05 23:24 ` Christoph Lameter
2014-10-05 23:57 ` Eric Dumazet
2014-10-06 8:06 ` Thomas Gleixner
2014-10-06 10:22 ` Christoph Lameter
2014-10-06 13:01 ` Thomas Gleixner
2014-10-06 15:16 ` Christoph Lameter
2014-10-06 15:28 ` Thomas Gleixner
2014-10-06 19:34 ` Henrique de Moraes Holschuh
2014-10-06 15:31 ` David Lang
2014-10-06 19:45 ` Christoph Lameter
2014-10-05 23:59 ` Eric Dumazet
2014-10-06 7:54 ` Thomas Gleixner
2014-10-06 10:49 ` David Lang
2014-10-06 12:28 ` Thomas Gleixner [this message]
2014-10-03 12:15 ` Paul Bolle
2014-10-03 12:23 ` Christoph Lameter
2014-10-04 10:26 ` Bernd Petrovitsch
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=alpine.DEB.2.11.1410061426471.4383@nanos \
--to=tglx@linutronix.de \
--cc=cl@linux.com \
--cc=david@lang.hm \
--cc=linux-kernel@vger.kernel.org \
--cc=richardcochran@gmail.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