|
Hello,
On Mon, 6 Nov 2000, David D.W. Downey wrote:
>
> OK having some routing issues as follows. Working in an LVS cluster (load
> balancing). The front end works fine.
> We have a 2nd netework in the 10.10.10.0 range which we need to be able
> to route to. I have a linux router box in place with
> the appropriate routes added. The problem is that we get MAJOR delays or
> MAJOR ping rates when we try to ping any of the boxes on the 10.10.10.0
> network. If we ping a box (say 10.10.10.204) we get a major delay or no
> response.
How LVS participates in this ping? This looks like a network
problem.
> If we stop the ping and ping again, we get an answer this time but the rates
> are like 8000.3 ms or higher. If we stop it again and retry a 3rd time the
> response rate drops down into the normal 0.3 to 1.0 ms range. In order for
> routing from the front end to work or the middle range webfarm to be able to
> hit the 10.10.10.0 network I must manually do this every time or routing
> doesn't work. Any ideas?
Hunt for hardware problems.
> I _think_ it may be an issue involving the way packets have to travel in the
> cluster but I am unsure of this.
And how they travel? Share this info!
> ---
> DAVID D.W. DOWNEY SENIOR LINUX SYSTEMS ADMINISTRATOR
> QIXO, Inc. Home Page =
> http://QIXO.com
> 2192 Fortune Drive Company Email =
> ddowney@xxxxxxxx
> San Jose, CA 95131 Company Phone = +1
> (408) 514-6441
> USA Company FAX =
> +1 (408) 516-9090
> ---
Regards
--
Julian Anastasov <ja@xxxxxx>
|
