FatPaths: Routing in Supercomputers, Data Centers, and Clouds with Low-Diameter Networks when Shortest Paths Fall Short
share
We introduce FatPaths: a simple, generic, and robust routing architecture for Ethernet stacks. FatPaths enables state-of-the-art low-diameter topologies such as Slim Fly to achieve unprecedented performance, targeting both HPC supercomputers as well as data centers and clusters used by cloud computing. FatPaths exposes and exploits the rich ("fat") diversity of both minimal and non-minimal paths for high-performance multi-pathing. Moreover, FatPaths features a redesigned "purified" transport layer, based on recent advances in data center networking, that removes virtually all TCP performance issues (e.g., the slow start). FatPaths also uses flowlet switching, a technique used to prevent packet reordering in TCP networks, to enable very simple and effective load balancing. Our design enables recent low-diameter topologies to outperform powerful Clos designs, achieving 15 lower latency for comparable cost. FatPaths will significantly accelerate Ethernet clusters that form more than 50 a standard routing scheme for modern topologies.
READ FULL TEXT
