On Sun, Feb 6, 2011 at 2:04 PM, Daniel Tiron <[email protected]> wrote:
> Hi.
>
> During my research I did some performance tests. In some of your paper
> on ovs I read that "Open vSwitch is almost as fast as the native
> bridge". Well in my environment ovs beats the Linux Bridge [1].
>
> Do you have any explanation why Open vSwitch, with all it features, is
> faster than the "simple" Bridge?
>
> My setup is:
> - Host:
>        o kernel 2.6.36.1
>        o ovs 1.1.0pre2
>        o one bridge
> - 2 guests:
>        o kernel 2.6.36.2
>        o QEMU 0.12.4
>        o TAP interface (attached to bridge)
> - measurement
>        o iperf
>        o 15 runs
>        o 5 minutes each

I have some scripts that automate some testing here:
https://github.com/deshantm/Open-vSwitch-Testing

They may need to be dusted off a bit, but they do all the basics
needed for the netPIPE graphs that are similar to the ones in the
paper and also my dissertation [1].

Hope they help.

Thanks,
Todd

[1] https://github.com/deshantm/Rapid-Recovery-Desktop-Testing,
http://todddeshane.net/phd

_______________________________________________
discuss mailing list
[email protected]
http://openvswitch.org/mailman/listinfo/discuss_openvswitch.org

Reply via email to