DecLock: A Case of Decoupled Locking for Disaggregated Memory

TL;DR

DecLock introduces a decentralized locking mechanism for disaggregated memory systems that significantly reduces contention and improves throughput and latency for high-demand applications.

Contribution

It proposes DecLock, a novel decentralized locking scheme with cooperative queue-notify locking, enhancing performance and fairness in disaggregated memory environments.

Findings

Achieves up to 43.37× throughput improvement over RDMA spinlocks.

Reduces 99th-percentile latency by up to 98.8%.

Improves application throughput by up to 35.60×.

Abstract

This paper reveals that locking can significantly degrade the performance of applications on disaggregated memory (DM), sometimes by several orders of magnitude, due to contention on the NICs of memory nodes (MN-NICs). To address this issue, we present DecLock, a locking mechanism for DM that employs decentralized coordination for ownership transfer across compute nodes (CNs) while retaining centralized state maintenance on memory nodes (MNs). DecLock features cooperative queue-notify locking that queues lock waiters on MNs atomically, enabling clients to transfer lock ownership via message-based notifications between CNs. This approach conserves MN-NIC resources for DM applications and ensures fairness. Evaluations show DecLock achieves throughput improvements of up to 43.37$\times$ and 1.81$\times$ over state-of-the-art RDMA-based spinlocks and MCS locks, respectively. Furthermore, DecLock helps two DM applications, including an object store and a real-world database index (Sherman), avoid performance degradation under high contention, improving throughput by up to 35.60$\times$ and 2.31$\times$ and reducing 99th-percentile latency by up to 98.8% and 82.1%.