From: "Denys Fedoryshchenko" <denys@visp.net.lb>
To: David Miller <davem@davemloft.net>, benny+usenet@amorsen.dk
Cc: netdev@vger.kernel.org
Subject: Re: e1000 performance issue in 4 simultaneous links
Date: Sat, 12 Jan 2008 07:13:06 +0200 [thread overview]
Message-ID: <20080112050841.M73900@visp.net.lb> (raw)
In-Reply-To: <20080111.174109.57502326.davem@davemloft.net>
Sorry. that i interfere in this subject.
Do you recommend CONFIG_IRQBALANCE to be enabled?
If it is enabled - irq's not jumping nonstop over processors. softirqd
changing this behavior.
If it is disabled, irq's distributed over each processor, and in loaded
systems it seems harmful.
I work a little yesterday with server with CONFIG_IRQBALANCE=no, 160kpps load.
It was packetloss-ing, till i set smp_affinity.
Maybe it is useful to put more info in Kconfig, since it is very important
for performance option.
On Fri, 11 Jan 2008 17:41:09 -0800 (PST), David Miller wrote
> From: Benny Amorsen <benny usenet@amorsen.dk>
> Date: Fri, 11 Jan 2008 12:09:32 0100
>
> > David Miller <davem@davemloft.net> writes:
> >
> > > No IRQ balancing should be done at all for networking device
> > > interrupts, with zero exceptions. It destroys performance.
> >
> > Does irqbalanced need to be taught about this?
>
> The userland one already does.
>
> It's only the in-kernel IRQ load balancing for these (presumably
> powerpc) platforms that is broken.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Denys Fedoryshchenko
Technical Manager
Virtual ISP S.A.L.
next prev parent reply other threads:[~2008-01-12 5:13 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-10 16:17 e1000 performance issue in 4 simultaneous links Breno Leitao
2008-01-10 16:36 ` Ben Hutchings
2008-01-10 16:51 ` Jeba Anandhan
2008-01-10 17:31 ` Breno Leitao
2008-01-10 18:18 ` Kok, Auke
2008-01-10 18:37 ` Rick Jones
2008-01-10 18:26 ` Rick Jones
2008-01-10 20:52 ` Brandeburg, Jesse
2008-01-11 1:28 ` David Miller
2008-01-11 11:09 ` Benny Amorsen
2008-01-12 1:41 ` David Miller
2008-01-12 5:13 ` Denys Fedoryshchenko [this message]
2008-01-30 16:57 ` Kok, Auke
2008-01-11 16:20 ` Breno Leitao
2008-01-11 16:48 ` Eric Dumazet
2008-01-11 17:36 ` Denys Fedoryshchenko
2008-01-11 18:45 ` Breno Leitao
2008-01-11 18:19 ` Breno Leitao
2008-01-11 18:48 ` Rick Jones
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=20080112050841.M73900@visp.net.lb \
--to=denys@visp.net.lb \
--cc=benny+usenet@amorsen.dk \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.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 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).