Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 25 Aug 2015 19:45:08 +0300
From:      Slawa Olhovchenkov <slw@zxy.spb.ru>
To:        Gerrit =?koi8-r?Q?K=22uhn?= <gerrit.kuehn@aei.mpg.de>
Cc:        Rick Macklem <rmacklem@uoguelph.ca>, stable@freebsd.org
Subject:   Re: dev.ix.0.queueX.interrupt_rate
Message-ID:  <20150825164508.GH21849@zxy.spb.ru>
In-Reply-To: <20150825160441.48ed35049f5947f0dbbaa801@aei.mpg.de>
References:  <20150824192926.GL3158@zxy.spb.ru> <20150825095448.53458554a4ee7f96129a2d70@aei.mpg.de> <202540715.30987815.1440503749374.JavaMail.zimbra@uoguelph.ca> <20150825160441.48ed35049f5947f0dbbaa801@aei.mpg.de>

next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Aug 25, 2015 at 04:04:41PM +0200, Gerrit K"uhn wrote:

> On Tue, 25 Aug 2015 07:55:49 -0400 (EDT) Rick Macklem
> <rmacklem@uoguelph.ca> wrote about Re: dev.ix.0.queueX.interrupt_rate:
> 
> 
> RM> If you have tso enabled, you could try this patch:
> RM>   https://reviews.freebsd.org/D3477
> RM> 
> RM> If TSO is disabled, then we don't have an explanation for poor NFS
> RM> performance yet. 
> 
> I tried both with or without TSO, and it does not appear to make any
> difference for me. I get about 50MB/s net write speed and about 200MB/s
> read. Even my 1GBE interface perform better in terms of writing.
> 
> RM> If you haven't seen it, you might want to keep an eye
> RM> on this thread: http://docs.FreeBSD.org/cgi/mid.cgi?55DC1B5A.8010109
> 
> Yes, I am watching this. Thanks for the pointer.

For discover poor network performance you need:

1. check cables
2. capture interface statisctics from all ports on paths on network
switchs
3. capture NIC statisctics on hosts (netstat -nbeI)
4. ifconfig -a
5. netstat -rn
6. /var/log/dmesg.boot



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20150825164508.GH21849>