This is the setup:

There are 3 PCs.

1. Client
2. A custom TCP proxy based on 2.6.24 + tproxy
3. Server

All pretty high end machines.

Test sequence:

Step A. I send a data packet on already established TCP packet. Size is an MTU from machine 1.
Step B. Machine 2 receives it and proxies it.
Step C. Machine 3 receives it and echoes it back.

We measure the on-the-wire time in and out of machine (2).

In pure ipforwarding mode on machine 2, we see 2-3 ms latency.

In tproxy mode on machine 2, we see 5-6 ms latency (additional 3ms).

I hope that clarifies the scenario.

Any pointers/help is appreciated.

Thanks
Ravi

On Tue, Oct 14, 2008 at 4:49 AM, KOVACS Krisztian <hidden@sch.bme.hu> wrote:

Hi,

On h, okt 13, 2008 at 10:28:59 -0400, Ravi Valmikam wrote:
> Any of you aware of any tproxy performance data? Specifically, any extra
> latency it adds to packet processing (% is fine).
>
> Our testing seems to add significant latency (3ms on base 2-3 ms in non
> transparent proxy mode). Does it make sense?

Could you give us a bit more detailed description of what you measured and
how?

--
KOVACS Krisztian