[c-nsp] 3550 high cpu & process switched traffic

[Mikael Abrahamsson]

On Sat, 19 Aug 2006, Tassos Chatzithomaoglou wrote:

> I still wonder what might be the relationship between routing table size 
> and amount of traffic, so the same routing table size with different 
> amounts of traffic is causing different cpu loads on a

Well, if it'll TCAM switch some traffic and CPU switch some traffic, then 
the CPU load will be dependant on what prefixes are where, and which of 
these are seeing traffic thru the unit. If you happen to have a lot of the 
traffic on the prefixes being CPU switched, then of course you get high 
CPU load.

This of course if the switch actaully will populate all of TCAM space and 
then "fall back" to the rest of the prefixes being CPU switched, I am not 
sure this is the case but your experiences seem to indicate that this is 
the case.

-- 
Mikael Abrahamsson    email: swmike at swm.pp.se