[c-nsp] Cisco 7301 running at 99% CPU doing iBGP update

Marian Durkovic md at bts.sk
Fri Jun 30 03:25:18 EDT 2006


On Thu, Jun 29, 2006 at 11:03:54PM -0400, Rodney Dunn wrote:
> I've never yet seen anone put that in the lab and prove there is
> transit packet loss when this happens.
> 
> Traceroutes going to process level is one thing. Packet switched
> under interrupt is another.

Well, not sure about 7301, but on Cat6500 running the -SXF train
during BGP scanner runs the box certainly drops some of the process-switched
packets due to SPD queue overflows. This can be reproduced by e.g.
configuring TTL threshold for IP multicast (which forces multicast packets
to process-switching path) and sending e.g. 8 Mbps video stream.


	With kind regards, 

--------------------------------------------------------------------------
----                                                                  ----
----   Marian Durkovic                       network  manager         ----
----                                                                  ----
----   Slovak Technical University           Tel: +421 2 524 51 301   ----
----   Computer Centre, Nam. Slobody 17      Fax: +421 2 524 94 351   ----
----   812 43 Bratislava, Slovak Republic    E-mail/sip: md at bts.sk    ----
----                                                                  ----
--------------------------------------------------------------------------


More information about the cisco-nsp mailing list