Abstract

I will talk about the design and implementation of FaRM, a new main memory distributed computing platform that exploits RDMA communication to improve both latency and throughput by an order of magnitude relative to state of the art main memory systems that use TCP /IP. FaRM exposes the memory of machines in the cluster as a shared address space. Applications can allocate, read, write, and free objects in the address space. They can use distributed transactions to simplify dealing with complex corner cases that do not significantly impact performance. FaRM provides good common-case performance with lock-free reads over RDMA and with support for collocating objects and function shipping to enable the use of efficient single machine transactions. FaRM uses RDMA both to directly access data in the shared address space and for fast messaging and is carefully tuned for the best RDMA performance. We used FaRM to build a key-value store and a graph store similar to Facebook’s. They both perform well, for example, a 20-machine cluster can perform 160 million key-value lookups per second with a latency of 31micro-seconds.