[Lxc-users] LXC vs ESX

Toens Bueker toens.bueker at lists0903.nurfuerspam.neuroserve.de
Mon May 23 12:37:58 UTC 2011


Ulli Horlacher <framstag at rus.uni-stuttgart.de> wrote:

> A small network application benchmark between LXC and VMware ESX:
> 
> ESX:
> 
> framstag at diaspora:~: fexsend  -i unifex /tmp/2GB.tmp .
> Server/User: http://fex.uni-stuttgart.de/framstag@rus.uni-stuttgart.de
> /tmp/2GB.tmp : 2048 MB in 87 s (24105 kB/s)
> 
> LXC:
> 
> framstag at diaspora:~: fexsend  -i flupp /tmp/2GB.tmp .
> Server/User: http://flupp/framstag@rus.uni-stuttgart.de
> /tmp/2GB.tmp : 2048 MB in 24 s (87381 kB/s)
> 
> The ESX host has about twice of native CPU and disk power than the LXC
> host. ESX has 10 Gb/s, LXC has 1 GB/s. Both VMs run the same software.

But that is to be expected, is it?

There is no virtual i/O layer on lxc; ESX (or is it ESXi?) probably is
not using SRIOV with that 10G NIC, etc.

But lxc won't be able to run Windows (which is the main purpose of
ESX(i)).

Kind regards,
Töns
-- 
There is no safe distance.




More information about the lxc-users mailing list