[c-nsp] 1841 suitable for BGP?

[Tony Varriale]

Not to butt in but I could show you real world utilization (ave and peak) 
for a good handful of software based Cisco platforms.

I'm sure the gear I'm familiar with isn't crashing, but I can show you 50% 
peak CPU on NPE 400s because of BGP scanner running every 60 seconds (since 
that's it's run interval).  Also, I can show you how 1 eBGP peer reset will 
send that NPE400 to 100% CPU.

Since NPEs are software based and the CPU is at 100%, what would you say are 
happening to the packets that should be going thru the box?  I know for sure 
based on my monitoring that not all the packets are being forwarded at that 
time.  Are all being dropped?  No.  But it's very difficult to correlate 
exact microsecond CPU utilization and actual packet drop.

tv
----- Original Message ----- 
From: "Mikael Abrahamsson" <swmike at swm.pp.se>
To: <cisco-nsp at puck.nether.net>
Sent: Tuesday, August 29, 2006 12:39 AM
Subject: Re: [c-nsp] 1841 suitable for BGP?


> On Mon, 28 Aug 2006, Matthew Crocker wrote:
>
>> BGP updates once per minute will crush the router and cause all
>> packets to stop.
>
> Err, do you actually have proof of this? My experience is that if CEF is
> enabled, you won't see much affect on packet performance when the BGP
> process is working. If the router is doing a lot of packet forwarding, BGP
> processing will be slower and that might in a reconvergence scenario slow
> things down, but the actual passing of packets isn't much affected.
>
> The BGP processing and BGP scanner is run at low priority and as long as
> you're not process switching the packets it shouldn't affect performance.
>
> -- 
> Mikael Abrahamsson    email: swmike at swm.pp.se
> _______________________________________________
> cisco-nsp mailing list  cisco-nsp at puck.nether.net
> https://puck.nether.net/mailman/listinfo/cisco-nsp
> archive at http://puck.nether.net/pipermail/cisco-nsp/
>