Re: tests about latency

[Christopher Hicks <chicks () chicks net>]

On Fri, 12 Sep 2003, Mikael Olsson wrote:
> Neale Banks wrote:
> > Ob FW:  Whilst obviously anything that's not simply routed (e.g. proxied
> > protocols) would be a completely different kettle of fish, to what extent
> > could one then reasonably generalise the results obtained from ping tests
> > (i.e. ICMP packets) to other protocols?
>
> Your question is already answered, but: one should also note that doing any 
> kind of RTT tests (e.g. pinging) against routers is generally a Bad Idea.
>
> Example:
> - My default gateway: RTT ~1 ms
> - Hop outside my default gateway: RTT often 20-30 ms  <-- NOTE!
> - Next hop after that: RTT ~5 ms
> - ... 10 hops away: RTT 15 ms
>
> How can this happen, you ask?  Easy: forwarding and local processing
> is done in different processors in many routers.  The forwarding 
> processors can be just fine even though the "host" CPU can be totally 
> overloaded by things like aggressive SNMP polling, large dynamic
> routing calculations (OSPF et al) and whatnot.

pastmon is supposed to give you answers to these questions without adding 
any traffic.  Does anyone have experience or opinions with pastmon good or 
bad?

-- 
</chris>

No, no, you're not thinking, you're just being logical.
-Niels Bohr, physicist (1885-1962)

_______________________________________________
firewall-wizards mailing list
firewall-wizards () honor icsalabs com
http://honor.icsalabs.com/mailman/listinfo/firewall-wizards