[c-nsp] Sup720 CoPP, limits on CPU performance

[Rodney Dunn]

Explain the glean to me again?

Sorry..I'm overloaded but trying to catch up on the thread.

We, I need to go back and check, implemented periodic punts at one point 
that would match the glean and all subsequent packets were dropped in 
hw/under interrupt..it wasn't a 1:1 punt.

Rodney



On 3/24/10 10:17 AM, Gert Doering wrote:
> Hi,
>
> On Wed, Mar 24, 2010 at 09:35:51AM +0000, Dobbins, Roland wrote:
>> On Mar 24, 2010, at 4:28 PM, Gert Doering wrote:
>>
>>> (So in general, I agree with you, I just want a more fool-proof way to
>>> configure CoPP-drop-default in a way that has no surprising side-effects)
>>
>> I proposed a self-learning mode for CoPP, based upon identifying
>> 'to-me' traffic via the NetFlow cache, many years ago.  Unfortunately,
>> it wasn't ever taken up, AFAIK.
>
> That would be nice to figure out what needs to be permitted (and how much
> of it), but it's actually much more than I want.
>
> We know our network quite well, so we know what sort of traffic to expect.
>
> The "but" is in the fine print - ISIS, IPv6, ARP - either not (properly)
> supported in 6500 CoPP, or having side-effects (glean traffic).  Even
> though the problem with the glean traffic something we haven't seen here
> yet - maybe our 3Bs are not old enough :-)
>
> gert
>
>
>
> _______________________________________________
> 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/