Category: Software Gone Wild
Remember how Nick Buraglio tried to use OpenDaylight to build a small part of SuperComputing conference network… and ended up with a programmable patch panel?
We started with the usual “what problem were you trying to solve” and quickly started teasing apart the architecture and got geekily focused on interesting things like:
I mentioned Multipath TCP (MP-TCP) numerous times in the past but I never managed to get beyond “this is the thing that might solve some TCP multihoming challenges” We fixed this omission in Episode 100 of Software Gone Wild with Christoph Paasch (software engineer @ Apple) and Mat Martineau from Open Source Technology Center @ Intel.
A while ago we did a podcast with Luke Gorrie in which he explained why he’d love to have simple, dumb, and easy-to-work-with Ethernet NICs. What about the other side of the coin – smart NICs with their own CPU, RAM and operating system? Do they make sense, when and why would you use them, and how would you integrate them with Linux kernel?
In Episode 98 we focused on another interesting application developed by Max Rottenkolber: high-speed VPN gateway using IPsec on top of Snabb Switch (details). Enjoy!
In summer 2018 Juniper started talking about another forward-looking concept: Network Reliability Engineering. We wanted to find out whether that’s another unicorn driving DeLorean with flux capacitors or something more tangible, so we invited Matt Oswalt, the author of Network Reliability Engineer’s Manifesto to talk about it in Episode 97 of Software Gone Wild.
We love to claim that we’re engineers and yet sometimes we have no clue how technology we use really works and what its limitations are… quite often because understanding those limitations would involve diving pretty deep into math (graphs, queuing and system reliability quickly come to mind).
After a series of forward-looking podcast episodes we returned to real life and talked with Carl Buchmann about his network automation journey, from managing upgrades with Excel and using Excel as the configuration consistency tool to network-infrastructure-as-code concepts he described in a guest blog post in February 2018
In recent years Linux networking started evolving at an amazing pace. You can hear about all the cool new stuff at netdev conference… or listen to Episode 94 of Software Gone Wild to get a CliffsNotes version.
Roopa Prabhu, Jamal Hadi Salim, and Tom Herbert joined Nick Buraglio and myself and we couldn’t help diverging into the beauties of tc, and the intricacies of low-latency forwarding before coming back on track and started discussing cool stuff like:
Hardware vendors are always making their silicon more complex and feature-rich. Is that a great idea or a disaster waiting to happen? We asked Luke Gorrie, the lead developer of Snabb Switch (an open-source user-land virtual switch written in Lua) about his opinions on the topic.
TL&DL version: Give me a dumb NIC, software can do everything else.
In recent Software Gone Wild episodes we explored emerging routing protocols trying to address the specific needs of highly-meshed data center fabrics – RIFT and OpenFabric. In Episode 92 with Dinesh Dutt we decided to revisit the basics trying to answer a seemingly simple question: do we really need new routing protocols?
In 2014, we did a series of podcasts on Snabb Switch (Snabb Switch and OpenStack, Deep Dive), a software-only switch delivering 10-20 Gbps of forwarded bandwidth per x86 core. In the meantime, Snabb community slowly expanded, optimized the switching code, built a number of solutions on top of the packet forwarding core, and even forked a just-in-time Lua compiler to get better performance.
David Barroso was sick-and-tired of using ZX Spectrum of Network Automation and decided to create an alternative with similar functionality but a proper programming language instead of YAML dictionaries masquerading as one. The result: Nornir, an interesting network automation tool formerly known as Brigade we discussed in Episode 90 of Software Gone Wild.
As always, we started with the “what’s wrong with what we have right now, like using BGP as a better IGP” question, resulting in “BGP is becoming the trash can of the Internet”.
Years ago Petr Lapukhov decided that it’s a waste of time to try to make OSPF or IS-IS work in large-scale data center leaf-and-spine fabrics and figured out how to use BGP as a better IGP.
In the meantime, old-time routing gurus started designing routing protocols targeting a specific environment: highly meshed leaf-and-spine fabrics. First in the list: Routing in Fat Trees (RIFT).
We started with simple questions like “what is an interface” and “how do they get such weird names in some Linux distributions” which quickly turned into a complex discussion about kernel objects and udev, and details of implementing logical interfaces that are associated with ASIC front-panel physical ports.