[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080708064324.GA11776@2ka.mipt.ru>
Date: Tue, 8 Jul 2008 10:43:24 +0400
From: Evgeniy Polyakov <johnpol@....mipt.ru>
To: Roland Dreier <rdreier@...co.com>
Cc: Bill Fink <billfink@...dspring.com>,
David Miller <davem@...emloft.net>, aglo@...i.umich.edu,
shemminger@...tta.com, netdev@...r.kernel.org, rees@...ch.edu,
bfields@...ldses.org
Subject: Re: setsockopt()
On Mon, Jul 07, 2008 at 11:29:31PM -0700, Roland Dreier (rdreier@...co.com) wrote:
> nuttcp -T30 -i1 ends up with:
>
> 14465.0625 MB / 30.01 sec = 4043.6073 Mbps 82 %TX 2 %RX
>
> while setting the window even to 128 KB with
> nuttcp -w128k -T30 -i1 ends up with:
>
> 36416.8125 MB / 30.00 sec = 10182.8137 Mbps 90 %TX 96 %RX
>
> so it's a factor of 2.5 with nuttcp. I've never seen other apps behave
> like that -- for example NPtcp (netpipe) only gets slower when
> explicitly setting the window size.
>
> Strange...
Maybe nuttcp by default sets very small socket buffer size?
--
Evgeniy Polyakov
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists