From: Eric Dumazet <eric.dumazet@gmail.com>
To: Changli Gao <xiaosuo@gmail.com>
Cc: David Miller <davem@davemloft.net>,
therbert@google.com, netdev@vger.kernel.org
Subject: Re: [PATCH v7] rps: Receive Packet Steering
Date: Wed, 17 Mar 2010 08:07:53 +0100 [thread overview]
Message-ID: <1268809673.2932.62.camel@edumazet-laptop> (raw)
In-Reply-To: <412e6f7f1003161854w32ed4516w2e52003097051fc7@mail.gmail.com>
Le mercredi 17 mars 2010 à 09:54 +0800, Changli Gao a écrit :
> On Wed, Mar 17, 2010 at 5:13 AM, David Miller <davem@davemloft.net> wrote:
> >
> > I'll integrate this as soon as I open up net-next-2.6
>
> It is really a good news. Now linux also can dispatch packets as
> FreeBSD does via netisr. Can we walk farer, and support weighted
> distribution?
>
May I ask why ? What would be the goal ?
If you perform too much work behalf the first cpu (the one actually
dealing with the device and dispatching packets to other cpus), you risk
bringing into its cache whole packet and consuming too many cpu cycles.
For instance, I would prefer a basic spreading, and try to reorganise
sk_buffs to that this cpu touches only one cache line in sk_buff, and
read one cache line in packet data to compute rxhash.
Then some NIC could compute rxhash themselves and provide it in their
rx_desc. Of course multiqueue support is much better and current
hardware prefer to implement the real thing.
next prev parent reply other threads:[~2010-03-17 7:07 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-12 20:13 [PATCH v7] rps: Receive Packet Steering Tom Herbert
2010-03-12 21:28 ` Eric Dumazet
2010-03-12 23:08 ` Tom Herbert
2010-03-16 18:03 ` Tom Herbert
2010-03-16 21:00 ` Eric Dumazet
2010-03-16 21:13 ` David Miller
2010-03-17 1:54 ` Changli Gao
2010-03-17 7:07 ` Eric Dumazet [this message]
2010-03-17 7:59 ` Changli Gao
2010-03-17 14:09 ` Eric Dumazet
2010-03-17 15:01 ` Tom Herbert
2010-03-17 15:34 ` Eric Dumazet
2010-03-17 23:50 ` Tom Herbert
2010-03-18 2:14 ` Changli Gao
2010-03-18 6:30 ` Eric Dumazet
2010-03-18 6:20 ` Eric Dumazet
2010-03-18 6:48 ` Changli Gao
2010-03-18 20:37 ` Eric Dumazet
2010-03-18 21:23 ` Stephen Hemminger
2010-03-17 4:26 ` David Miller
2010-03-12 22:20 ` Stephen Hemminger
2010-03-12 22:32 ` David Miller
2010-03-12 22:23 ` Stephen Hemminger
2010-03-12 22:33 ` David Miller
2010-03-12 23:05 ` Tom Herbert
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=1268809673.2932.62.camel@edumazet-laptop \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=therbert@google.com \
--cc=xiaosuo@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