|
Stefan Peter wrote:
>
> 1. I have two distributor a master and a backup one. When I was spoofing
^^^^^^^^^^^
we call it a "director"
> the cluster with large number of sources and large number of packets the
> two distributors were alternating their functions at aprox. 5-10 seconds.
> First the master distributor produced large kernel load (even my shell on
> that machine has gone away), then the backup took its role, it got staffed
> as did the master in a couple of seconds, but by this time the master
> had come back again. Can I accept this as normal behavior?
In principle no. What probably has happened is that the heartbeat is not
being sent (or not being received) due to the load. The backup
assumes that the master has died. You could increase the timeout value.
Under DoS, I guess you could accept the machines behaving badly,
as long as they came back after. Looking from another machine,
it is is hard to tell the difference between a dead director
and one that is under heavy load.
> 2. The measurement values were also interesting: on the distributor
someone else will have to help you here.
> 3. An off-topic question:
>
> How many VIPs can be configured. On what property it depends?
I think it is as many IPs as the NIC can handle. I don't know that
LVS has any limits here. Julian?
Joe
--
Joseph Mack PhD, Senior Systems Engineer, Lockheed Martin
contractor to the National Environmental Supercomputer Center,
mailto:mack.joseph@xxxxxxx ph# 919-541-0007, RTP, NC, USA
|
