[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-users] Benchmarking virtual and native servers - procedures, standards?

  • To: Xen-users@xxxxxxxxxxxxxxxxxxx
  • From: "Dirk Westfal" <dwestfal@xxxxxxxxxxxxxx>
  • Date: Fri, 16 Feb 2007 21:01:41 +0100
  • Delivery-date: Mon, 19 Feb 2007 02:37:14 -0800
  • Domainkey-signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=beta; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=rbNZdC9oIjb/HSltZUzceKxzbRjwOHFwAELgnrLDKxTk9d4PUo/Ay3XA7W0UV8RmozucTtre4YN1W7XB4AY7kkQzGBZJ5KezTk+eEsx4uI3xJOHQ30JVAyUefXYhlJ5JEaaXCLfuUel/5bLQIzBv3RpWUWIyA0nwUnqrRdcIADE=
  • List-id: Xen user discussion <xen-users.lists.xensource.com>

hi all,

i currently have two equal servers here, one with a native w2k3
installation, the other with fedora core 6 and xen 3.0.3 as well as
vmware server with a non-xen-kernel.

So far we have benchmarked all three using sisoft sandra, superpi and
an inhouse application (scripted rescan process with image correction
and ocr with the source data on a network share).

While that covers most flanks for us, the results cannot be compared
to other systems, so my questions is:

is there a recommended benchmark
- a set of tests for disk and network io
- cpu performance

I`ve seen the netperf and iometer tests beeing used around here - are
there any recommended testconfigurations?


Xen-users mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.