netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Phil Sutter <phil@nwl.cc>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	netdev@vger.kernel.org, brouer@redhat.com
Subject: Re: [net-next PATCH 1/3] net: make default tx_queue_len configurable
Date: Thu, 13 Aug 2015 15:10:33 +0200	[thread overview]
Message-ID: <20150813151033.048d73b8@redhat.com> (raw)
In-Reply-To: <20150813011339.GF32353@orbit.nwl.cc>


On Thu, 13 Aug 2015 03:13:40 +0200 Phil Sutter <phil@nwl.cc> wrote:

> On Tue, Aug 11, 2015 at 06:13:49PM -0700, Alexei Starovoitov wrote:

> > In general 'changing the default' may be an acceptable thing, but then
> > it needs to strongly justified. How much performance does it bring?
> 
> A quick test on my local VM with veth and netperf (netserver and veth
> peer in different netns) I see an increase of about 5% of throughput
> when using noqueue instead of the default pfifo_fast.

Good that you can show 5% improvement with a single netperf flow.  We
are saving approx 6 atomic operations avoiding the qdisc code path.

This fixes a scalability issue with veth. Thus, the real performance
boost will happen with multiple flows and multiple CPU cores in
action.  You can try with a multi core VM and use super_netperf.

https://github.com/borkmann/stuff/blob/master/super_netperf

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Sr. Network Kernel Developer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer

  reply	other threads:[~2015-08-13 13:10 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-29 20:51 [net-next PATCH 0/3] Backwards-compatible noqueue in virtual interfaces Phil Sutter
2015-07-29 20:51 ` [net-next PATCH 1/3] net: make default tx_queue_len configurable Phil Sutter
2015-07-29 20:51   ` [net-next PATCH 2/3] net: sched: set tx_queue_len to default when changing noqueue device's qdisc Phil Sutter
2015-07-29 20:51     ` [net-next PATCH 3/3] veth: don't assign a qdisc to veth Phil Sutter
2015-07-29 21:10     ` [net-next PATCH 2/3] net: sched: set tx_queue_len to default when changing noqueue device's qdisc Florian Westphal
2015-07-29 21:10     ` Eric Dumazet
2015-07-29 22:08       ` Phil Sutter
2015-07-29 21:06   ` [net-next PATCH 1/3] net: make default tx_queue_len configurable Florian Westphal
2015-07-29 21:34     ` Phil Sutter
2015-07-29 21:37       ` David Miller
2015-08-11 15:48         ` Jesper Dangaard Brouer
2015-08-11 16:23           ` Phil Sutter
2015-08-12  1:13             ` Alexei Starovoitov
2015-08-12 14:55               ` Eric Dumazet
2015-08-13  1:13               ` Phil Sutter
2015-08-13 13:10                 ` Jesper Dangaard Brouer [this message]
2015-08-13 15:06                   ` Phil Sutter
2015-07-29 23:10 ` [net-next PATCH 0/3] Backwards-compatible noqueue in virtual interfaces Cong Wang

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=20150813151033.048d73b8@redhat.com \
    --to=brouer@redhat.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=phil@nwl.cc \
    /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).