How to Scale Data Centers. A Report from Yandex
We have designed a data center network that allows deploying compute clusters larger than 100,000 servers with a peak bisection bandwidth of over one petabyte per second. From Dmitry Afanasyev's report, you will learn about the fundamental principles of the new design, the scaling of topologies, the issues that arise, possible solutions, the peculiarities of routing, and the scaling of the forwarding plane features of modern […]
