RDMC: A Reliable RDMA Multicast for Large Objects

摘要

Multicast patterns are common in cloud computing and datacenter settings. Applications and infrastructure tools such as Spark frequently move large objects around, update files replicated to multiple nodes, or push new versions of programs to compute nodes. Some applications use replication directly, for example to increase fault-tolerance or achieve parallelism. Implementations of Paxos, block chains and other libraries often employ a hand-built reliable multicast as a primitive. Yet operating systems continue to be focused on point-to-point communication solutions such as TCP or RDMA, a hardware layer with TCP-like semantics that offers zero copy transfers, but lacks a reliable multi-destination transfer capability. Our system, RDMC (RDMA Multicast), offers reliable multicast functionality constructed from RDMA unicast. We discuss design choices, present a theoretical analysis of RDMC's robustness to delays and slow network links, and report on experiments that evaluate RDMC over Mellanox RDMA.