From mboxrd@z Thu Jan  1 00:00:00 1970
From: Jacob Gorm Hansen <jacobg@diku.dk>
Subject: First result from small address spaces
Date: Tue, 26 Apr 2005 16:58:53 -0700
Message-ID: <426ED5BD.6010709@diku.dk>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xensource.com>
List-Unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: xen-devel <xen-devel@lists.xensource.com>
List-Id: xen-devel@lists.xenproject.org

hi,

I finally have a setup where I can measure I/O performance of stock vs. 
my own 'small address spaces' enabled version of Xen.

Doing a simple iperf -w256K with the client in domU and the server on a 
remote machine, everything without hyper-threading and using bridged 
networking.

Stock xen : 574MBits/s
SAS xen: 620MBits/s

Not massive, but an 8% improvement in this one case. I suspect that in 
general, this only makes a real difference if the domU doing something 
useful with the CPU other than feeding data into a socket.

Where can I adjust the thresholds for buffering of packets and interrupts?

Jacob