[c-nsp] Cisco 8000

[Mark Tinka]

On 21/Dec/19 20:06, adamv0025 at netconsultings.com wrote:

>
> For all the engineers, 
> When in doubt whether you're dealing with pipeline or run to completion NPU,
> Stuff the NPU with pps all the way till it starts dropping packets then dial
> back a little so you can get packets through without any loss,
> Now start adding features like QOS, Filters, IPFIX, etc... 
> If the NPU won't drop any packets that means it's pipeline, if it starts to
> drop more and more the more features you enable it's run to completion.
>
> And obviously the list of features or combinations of features that you can
> enable will be lot less on pipeline NPU -but each packet is guaranteed to
> leave the pipeline precisely at its clocking speed, compared to run to
> completion NPU where you can enable just about any combination of features
> you can think of, but the NPU will take its time to process each packet
> -meaning it might not have time for some newly arriving packets.

I suppose for us, the issue is less about getting packets through at a
certain pps rate vs. getting features to work as understood or advertised.

We have no problem moving to the next line card in order to increase
pps, but not at the expense of features we have been accustomed to, or
have been advertised to work without much detriment to the base system.

Mark.