public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Matheos Worku <Matheos.Worku@Sun.COM>
To: Jesper Krogh <jesper@krogh.cc>
Cc: David Miller <davem@davemloft.net>,
	yhlu.kernel@gmail.com, linux-kernel@vger.kernel.org,
	netdev@vger.kernel.org
Subject: Re: NIU - Sun Neptune 10g - Transmit timed out reset (2.6.24)
Date: Fri, 09 May 2008 15:36:17 -0700	[thread overview]
Message-ID: <4824D1E1.10007@sun.com> (raw)
In-Reply-To: <4824CCF0.5050302@krogh.cc>

Jesper Krogh wrote:

> Matheos Worku wrote:
>
>> Jesper Krogh wrote:
>>
>>> David Miller wrote:
>>>
>>>> From: Jesper Krogh <jesper@krogh.cc>
>>>> Date: Fri, 09 May 2008 20:32:53 +0200
>>>>
>>>>> When it works I doesnt seem to be able to get it pass 500MB/s.
>>>>
>>>>
>>>> With this card you really need multiple cpus and multiple threads
>>>> sending data through the card in order to fill the 10Gb pipe.
>>>>
>>>> Single connections will not fill the pipe.
>>>
>>>
>>> The server is a Sun X4600 with 8 x dual-core CPU's, setup with 64
>>> NFS-threads. The other end of the fiber goes into a switch with gigabit
>>> ports connected to 48 dual-core cpus. The test was done doing a dd on a
>>> 4.5GB file from the server to /dev/null on the clients.
>>
>>
>> Are you doing a TX or RX (with respect to the 10G if)?
>
>
> Thats a transmit.. from the NFS server to the clients.

I have observed TX throughput degradation (and increased CPU 
utilization)  occurs with increased # of connections, when CPU count > 4 
CPUs.  I don't think it is related to the driver (or HW). A while ago I 
prototyped a driver which drops all UDP TX packets and the throughput 
degradation (and CPU utilization increase) behavior occurred though the 
driver was not doing much work.   LSO/TSO seems to help with the 
situation though. With LSO disabled, I have observed the issue on 
several 10G nics.

Regards
Matheos


>
> Jesper



  reply	other threads:[~2008-05-09 22:36 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-07 18:23 NIU - Sun Neptune 10g - Transmit timed out reset (2.6.24) Jesper Krogh
2008-05-07 18:30 ` Yinghai Lu
2008-05-07 21:15   ` David Miller
2008-05-09 18:32     ` Jesper Krogh
2008-05-09 21:32       ` David Miller
2008-05-09 21:59         ` Jesper Krogh
2008-05-09 22:07           ` David Miller
2008-05-09 22:13             ` Jesper Krogh
2008-05-09 22:09           ` Matheos Worku
2008-05-09 22:15             ` Jesper Krogh
2008-05-09 22:36               ` Matheos Worku [this message]
2008-05-09 22:43                 ` Matheos Worku
2008-05-09 22:46                   ` David Miller
2008-05-09 23:10                   ` Jesper Krogh
2008-05-09 23:21                     ` Matheos Worku
2008-05-09 22:45                 ` David Miller
2008-05-22 16:32                   ` Jesper Krogh
2008-05-22 17:15                     ` Ben Hutchings
2008-05-22 17:41                     ` David Miller
2008-05-22 18:14                       ` Ben Hutchings
2008-05-22 18:28                         ` David Miller
2008-06-01  7:25                       ` Andrey Panin
2008-06-01 16:01                         ` David Miller
2008-05-09 22:20           ` Rick Jones
2008-05-09 22:48             ` Jesper Krogh
2008-05-09 23:03               ` Rick Jones
2008-05-09 23:13                 ` Jesper Krogh
2008-05-09 23:33                   ` Rick Jones
2008-05-09 23:08               ` David Dillow
2008-05-10  6:22                 ` Jesper Krogh
2008-05-10 15:53                   ` Roland Dreier
2008-05-12  6:49                     ` Jesper Krogh
2008-05-10  2:20               ` Bill Fink
2008-05-10 11:01       ` Jesper Krogh
2008-05-11  4:34         ` David Miller
2008-05-11  5:44           ` Jesper Krogh
2008-05-11  6:08             ` David Miller
2008-05-11  9:47               ` Jesper Krogh
2008-05-12  6:52           ` Jesper Krogh
2008-05-26 19:03             ` Jesper Krogh
2008-05-26 19:33               ` David Miller
2008-05-26 19:39                 ` David Miller
2008-05-26 20:54                   ` Jesper Krogh
2008-05-26 22:15                     ` David Miller
2008-05-26 22:21                       ` Jesper Krogh
2008-05-26 22:30                         ` David Miller
2008-05-27  6:19                       ` Jesper Krogh
2008-05-28  1:18                         ` Matheos Worku
2008-05-29  5:34                           ` David Miller
2008-05-30  0:14                             ` Matheos Worku
2008-05-30  7:00                               ` David Miller
2008-06-16 18:09                                 ` Matheos Worku
2008-06-16 18:21                                   ` Jesper Krogh
2008-06-18  0:02                           ` David Miller

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=4824D1E1.10007@sun.com \
    --to=matheos.worku@sun.com \
    --cc=davem@davemloft.net \
    --cc=jesper@krogh.cc \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=yhlu.kernel@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