WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-users

[Xen-users] overhead of Xen when using iSCSI

To: xen-users@xxxxxxxxxxxxxxxxxxx
Subject: [Xen-users] overhead of Xen when using iSCSI
From: Siim Vahtre <siim_@xxxxxxxx>
Date: Sun, 3 Jun 2007 11:56:21 +0300 (EEST)
Delivery-date: Sun, 03 Jun 2007 01:50:52 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx

I have setup iSCSI targets (with open-iscsi) to dom0 (Xen 3.1), which are exported to paravirtualized guests:

disk = [ 'phy:/dev/iscsi/test0,hda1,w' ]

Everything works fine, but there is huge overhead. If I write to iSCSI device in dom0 I get write speeds of about 29Mbytes/s, but if I write to /dev/hda1 in domU I only get about 14Mbytes/s.

This kind of performance drop does not happen with regular disks or even NBD - they have some overhead but not 50% like I have with iSCSI.

I have searched the list and I know that some people have successfully run setup similar to mine, so I'd like to ask if anyone could please share their experience and tell me if 50% performance drop is really normal.

Thanks!

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users

<Prev in Thread] Current Thread [Next in Thread>