Storm: a fast transactional dataplane for remote data structures

TL;DR

Storm is a high-performance transactional dataplane leveraging RDMA one-sided primitives, designed to improve scalability and outperform existing systems in distributed in-memory storage environments.

Contribution

The paper introduces Storm, a novel RDMA-based transactional dataplane that exploits one-sided primitives for enhanced scalability and performance in distributed systems.

Findings

Storm outperforms eRPC, FaRM, and LITE by up to 17.1x.

Using one-sided RDMA primitives yields higher performance in rack-scale environments.

New guidelines for scaling RDMA hardware are proposed based on hardware advancements.

Abstract

RDMA is an exciting technology that enables a host to access the memory of a remote host without involving the remote CPU. Prior work shows how to use RDMA to improve the performance of distributed in-memory storage systems. However, RDMA is widely believed to have scalability issues, due to the amount of active protocol state that needs to be cached in the limited NIC cache. These concerns led to several software-based proposals to enhance scalability by trading off performance. In this work, we revisit these trade-offs in light of newer RDMA hardware and propose new guidelines for scaling RDMA. We show that using one-sided remote memory primitives leads to higher performance compared to send/receive and kernel-based systems in rack-scale environments. Based on these insights, we design and implement Storm, a transactional dataplane using one-sided read and write-based RPC primitives. We show that Storm outperforms eRPC, FaRM, and LITE by 3.3x, 3.6x, and 17.1x, respectively, on an Infinband EDR cluster with Mellanox ConnectX-4 NICs.