Heavy Networking 539: Preventing The 4poKalypse With Inter-Domain Multicast

The 4poKalypse is coming, and service providers need more tools in their toolbox to combat congestion in eyeball networks. Local content caches close to the eyeballs (pretty much how we do it today) isn’t going to be quite enough.
Multicast to the rescue. You mean, like on the public Internet? Multicast? For reals? Didn’t we, uh, try that once? I thought that didn’t work out so well…why will it work this time?
Jake Holland of Akamai is here to tell us just why inter-domain multicast is important, and why…this time…we can make it work.
We discuss:

* Why content caches aren’t good enough in a 4K world
* The nitty-gritty on “inter-domain”
* What’s different about inter-domain multicast this time around?
* Relevant IETF proposals
* Potential drawbacks in hardware, software, and networks
* How listeners can prepare and participate
* More

Sponsor: Apstra
Today’s episode is sponsored in part by Apstra. Apstra enables continuous automation and validation of your data center network architecture and operations. Find out more at apstra.com/packetpushers.
Sponsor: DriveNets
DriveNets offers a network cloud: a hugely scalable network on a disaggregated platform. Get higher capacity at a lower cost. FInd out more at drivenets.com/resources.
Show Links:
Why Inter-Domain Multicast Now Makes Sense – APNIC Blog
MulticastReceiver Explainer – GitHub
RFC 8777 – IETF
Discovery Of Restconf Metadata for Source-specific multicast – IETF
Asymmetric Manifest Based Integrity – IETF
Circuit Breaker Assisted Congestion Control – IETF
Multicast Source Discovery Protocol (MSDP) Deployment Scenarios – IETF
Jake Holland on LinkedIn
GrumpyOldTroll – Jake Holland’s GitHub repo