Hacker News new | ask | show | jobs
by sean0- 2572 days ago
The FreeBSD/VPC hypervisor efforts ran into a few “corporate speed bumps.” A few folks, myself included, are working to merge this code and make it generally available. The FreeBSD hypervisor effort certainly was the best systems work I’ve seen in my life, especially in such a short amount of time and given the resources at our disposal. My favorite anecdote was that the internal first-pass review of the benchmark data was that we had cheated because we had “exceeded the laws of computer science physics” when we saturated 100GE with VXLAN encap’ed guest traffic with no hardware acceleration, and we were only using a half a CPU core. If someone asked me to do this type of work again I’d use FreeBSD as the base again in a heartbeat. Good systems engineers are invaluable. Working from a solid technical foundation is equally critical, so is the community.

The control plane work likely won’t be made available (it was Linux specific, anyway). :-/

As for both the FreeBSD work and control plane work, it was good times, good memories, and a great team while it lasted.

4 comments

"Corporate speed bump" is not how I would characterize any of what you did. Quite the spin!

I mean, if you want to publicly comment on your time at Joyent, please! I'm still pretty angry about it, and I left the better part of a year ago.

Wow pushing 100gbps on half a core without hardware acceleration is an incredible feat. Can you provide more information on how this was done?
Well you see, Sean is a known liar and conman. So it wasn't actually done. It is one of the reasons him and his team were fired by Samsung when their house of lies came tumbling down.

Or uh, so I heard.

Are there any blog posts/email threads you'd point people to if they want to read more about the work that was done?

I'd love to see and read about some of the things you ran into, and how you accomplished some of those high speed transfers.

The best talk I gave on this wasn’t recorded (and had another section on the details of the new MBUF struct that mmacy came up with), but here are a few pointers for the time being:

https://youtu.be/La4ekkKbM5o

https://github.com/joyent/freebsd/tree/projects/VPC

https://www.slideshare.net/mobile/SeanChittenden/freebsd-vpc...

It looks like that FreeBSD GitHub repo is private.
Thanks for the info! Yeah, I'd been lurking and reviewing what if any of it I could grok since I heard about it over a live session of BSDCan. Looking forward to it becoming GA you've got my blessings for sure.