LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Arjan van de Ven <arjan@infradead.org>
To: Gergely Imre <imre.gergely@astral.ro>
Cc: linux-kernel@vger.kernel.org, hancockr@shaw.ca
Subject: Re: irq balancing question
Date: Fri, 23 Feb 2007 16:54:45 +0100	[thread overview]
Message-ID: <1172246085.3241.24.camel@laptopd505.fenrus.org> (raw)
In-Reply-To: <45DF012D.3080802@astral.ro>


> in fact i have two cards, and 4 CPUs, but i was interested in then answer
> Robert gave, that only _some_ machines distribute interrupts in hardware.
> software distribution is obviously not good. consider this scenario:
> 
> you have one machine with 4 cpus, and two ethernet cards with a lot of
> traffic on them. if you bind every card to one cpu, two of them are not used,
> so you really use only half the power. not let's say you have so much traffic
> (with limiting enabled, htb or something), that the two CPUs are on 100% all
> the time, but the other two are doing nothing.
> 
> now if you could balance that to all 4 cpus, you could use all the power AND
> no cpu would be used 100%.

actually this will give you worse performance than only using 2 cores.
The reason for this is twofold
1) If you rotate the irqs, TCP and IP packet fragments will arrive at
different CPUs. This in turn means that a VERY expensive reassembly path
gets taken, compared to local-cpu-only reassembly
2) If you rotate the irqs, you bounce cachelines between the caches ALL
THE TIME, which is also very expensive.

Both make it more likely that you'll be slower than just using only 2
cores...



-- 
if you want to mail me at work (you don't), use arjan (at) linux.intel.com
Test the interaction between Linux and your BIOS via http://www.linuxfirmwarekit.org


  reply	other threads:[~2007-02-23 15:54 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-23 11:32 Imre Gergely
2007-02-23 14:45 ` Arjan van de Ven
2007-02-23 14:58   ` Gergely Imre
2007-02-23 15:54     ` Arjan van de Ven [this message]
2007-02-23 18:51       ` Gergely Imre
2007-02-23 19:01         ` Arjan van de Ven
2007-02-23 20:57           ` Gergely Imre
     [not found] <fa.o8VX4Uax4/73QDX3vvhLW5NBvRE@ifi.uio.no>
2007-02-23 14:39 ` Robert Hancock
  -- strict thread matches above, loose matches on Subject: below --
2005-12-15 14:00 Pallipadi, Venkatesh
2005-11-17  8:28 ` JaniD++
2005-12-15  0:48 Pallipadi, Venkatesh
2005-12-15  9:10 ` JaniD++
2005-12-14 21:05 JaniD++
2005-12-14 21:16 ` Arjan van de Ven
2005-12-14 21:31   ` JaniD++

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=1172246085.3241.24.camel@laptopd505.fenrus.org \
    --to=arjan@infradead.org \
    --cc=hancockr@shaw.ca \
    --cc=imre.gergely@astral.ro \
    --cc=linux-kernel@vger.kernel.org \
    --subject='Re: irq balancing question' \
    /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).