[lvs-users] LVS-DR performance not good as expected

Dongsheng Song dongsheng.song at gmail.com
Thu Mar 21 13:22:28 GMT 2013

On Thu, Mar 21, 2013 at 8:27 PM, Anders Henke <anders.henke at 1und1.de> wrote:
> In some areas, the performance impact by virtualization is dramatically
> high (especially in networking), in others the performance impact
> (cpu-intensive tasks like calculation) it can be as low as 3-5%.
> As a rule of thumb, most kind of virtualization result in 10-20% of
> overall performance loss, which fits your "12.5%" fairly well.

But after I increased the users, I can got 12000/min with direct access,
LVS-DR could not, is is normal ?

> The virtualization layer does add some latency to your network. While
> the overall amount may look low, compare it to the usual latency on your
> network and you may experience an overall roundtrip increase of 200%.
> If you're putting a virtualized load balancer in front of this,
> you'll add not only the "natural" latency but also the extra
> latency by the virtualization layer - so in the end, the latency
> from a hardware client via VM-loadbalancer to VM-realserver may be
> 3-4 times as high as a hardware client accessing a hardware realserver.

So for transactions on short lived tcp connection, large roundtrip can
not achieve high performance, right ?

> Another point is CPU overcommitment: adding more virtual cores to a
> server doesn't necessarily increase the performance, it may also worsen
> performance. You've assigned 8*4 cores for the real servers and 2 more
> cores for the loadbalancer. The x7550 does offer 8 real cores, so set
> aside one core just for the virtualization layer and management, your
> hypervisor has around 7 cores to spend.

My test machine have 2 X7550 CPU, total 16 cores, 32 threads, when I
use 32  virtual cores, and 2 virtual cores which assign to loadbalancer
is near idle, it should not be overcommitment, right ?

> My advice:
> -test the performance of accessing all VMs in parallel without using the
>  loadbalancer. If your application is not sensitive to network latency,
>  the result shouldn't be very far from your current results and
>  probably a little better (as you're reducing network latency).
> -do assign less CPU cores to each VM to reduce the overall hypervisor
>  switching overhead, test again. The performance should improve a lot.
> -if network latency is an issue, do put your balancer on "real" hardware.

Very good advice, thank you very much!


> Anders
> --
> 1&1 Internet AG              Expert Systems Architect (IT Operations)
> Brauerstrasse 50             v://49.721.91374.0
> D-76135 Karlsruhe            f://49.721.91374.225
> Amtsgericht Montabaur HRB 6484
> Vorstände: Henning Ahlert, Ralph Dommermuth, Matthias Ehrlich,
> Robert Hoffmann, Andreas Hofmann, Markus Huhn, Hans-Henning Kettler,
> Dr. Oliver Mauss, Jan Oetjen, Martin Witt, Christian Würst
> Aufsichtsratsvorsitzender: Michael Scheeren

More information about the lvs-users mailing list