Developing the Stratoscale System At Scale

Stratoscale is building a distributed operating system for clouds that manages the compute, storage, and network resources of thousands of machines connected over myriad networks and spanning multiple data centers. The company has grown in two years from two founders to an army of scores of developers, all constantly developing new code and pushing the system to its limits.

This talk will focus not on the Stratoscale system but rather on how the development team develops, tests, deploys and operates it. How do we get tens of developers to work productively at a high velocity while maintaining system cohesion and quality? How can we tame the inherent complexity of such a distributed system? How do we continuously integrate, test, deploy and operate it? How do we take devops to the limit? And just how tasty is our own dog food?

We will share the lessons we've learned, what worked for us and what didn't, and our thoughts on tackling the next challenge: an order of magnitude increase in the number of developers/operators.

About the speaker - Muli Ben-Yehuda

Muli Ben-Yehuda is a systems researcher and an expert in the area of machine and I/O virtualization. He holds a B.A. (cum laude) from the Open University of Israel and an M.Sc. in Computer Science from the Technion -- Israel Institute of Technology. From 2002 until 2012 he held senior research and managerial positions at IBM Research, where he was also an IBM Master Inventor. In 2013 he founded a boutique virtualization and cloud computing consulting company, Hypervisor Technologies and Consulting Ltd, that provided expert consulting services to select clients. Currently he is solving hard cloud computing problems as Stratoscale's Chief Scientist.

Muli has co-authored over forty academic publications and holds over thirty-five US patents in such areas as machine and I/O virtualization, cloud computing, and operating system and hypervisor design and implementation. His code and ideas are included in many operating systems and hypervisors, including the Linux kernel and the Xen and KVM hypervisors. His work on The Turtles Project: Design and Implementation of Nested Virtualization has won the prestigious OSDI Jay Lepreau Best Paper Award and the IBM Research Pat Goldberg Memorial Best Paper Award.