public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Rick Jones <rick.jones2@hp•com>
To: Herbert Xu <herbert@gondor•apana.org.au>
Cc: Evgeniy Polyakov <johnpol@2ka•mipt.ru>,
	netdev@vger•kernel.org,
	Christoph Lameter <cl@linux-foundation•org>,
	Mel Gorman <mel@csn•ul.ie>, David Miller <davem@davemloft•net>,
	Lennert Buytenhek <buytenh@marvell•com>
Subject: Re: Patch for tbench regression.
Date: Mon, 29 Sep 2008 10:07:12 -0700	[thread overview]
Message-ID: <48E10B40.4000205@hp.com> (raw)
In-Reply-To: <20080929095126.GA25371@gondor.apana.org.au>

Sigh - email reading timing....  anyway

> It seems that netperf is issuing 16384-byte writes and as such
> we're sending the packets out immediately so TSO doesn't get a
> chance to merge the data.  Running netperf with -m 65536 makes
> TSO beat non-TSO by 6293Mb/s to 4761Mb/s.

By default, netperf's TCP_STREAM test will use whatever 
getsockopt(SO_SNDBUF) reports just after the data socket is created. 
The choice was completely arbitrary and burried deep in the history of 
netperf.

For evaluating changes, it would probably be a good idea to test a 
number of settings for the test-specific -m option.  Of course I have no 
good idea what those values should be.  There is the tcp_range_script 
(might be a bit dusty today) but those values are again pretty arbitrary.

It would probably be a good idea to include the TCP_RR test.

happy benchmarking,

rick jones

As an asside - I would be interested in hearing peoples' opinions 
(offline) on a future version of netperf possibly violating the 
principle of least surprise and automatically including CPU utilization 
if the code is running on a system which does not require calibration...

  reply	other threads:[~2008-09-29 17:07 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-09-28 21:15 Patch for tbench regression Evgeniy Polyakov
2008-09-29  3:12 ` Herbert Xu
2008-09-29  5:36   ` Evgeniy Polyakov
2008-09-29  5:40     ` Herbert Xu
2008-09-29  5:52       ` Evgeniy Polyakov
2008-09-29  6:40         ` Herbert Xu
2008-09-29  6:45           ` Evgeniy Polyakov
2008-09-29  7:02             ` Herbert Xu
2008-09-29  7:11               ` Evgeniy Polyakov
2008-09-29  7:20                 ` Herbert Xu
2008-09-29  9:43               ` Herbert Xu
2008-09-29  9:51                 ` Herbert Xu
2008-09-29 17:07                   ` Rick Jones [this message]
2008-09-29 10:34                 ` Evgeniy Polyakov
2008-09-29 13:34                   ` Christoph Lameter
2008-09-29 17:01                 ` 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=48E10B40.4000205@hp.com \
    --to=rick.jones2@hp$(echo .)com \
    --cc=buytenh@marvell$(echo .)com \
    --cc=cl@linux-foundation$(echo .)org \
    --cc=davem@davemloft$(echo .)net \
    --cc=herbert@gondor$(echo .)apana.org.au \
    --cc=johnpol@2ka$(echo .)mipt.ru \
    --cc=mel@csn$(echo .)ul.ie \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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