Systems for Memory Disaggregation: Challenges & Opportunities

TL;DR

Memory disaggregation systems aim to improve cluster memory utilization and flexibility by decoupling CPU and memory, but face challenges related to performance, design trade-offs, and implementation, requiring further research for widespread adoption.

Contribution

This paper reviews recent memory disaggregation systems, analyzing their design choices, performance optimizations, and trade-offs, and discusses open challenges and future research directions.

Findings

Memory disaggregation can increase effective memory capacity.

Design trade-offs impact application performance and system efficiency.

Open questions remain in optimizing disaggregation for practical deployment.

Abstract

Memory disaggregation addresses memory imbalance in a cluster by decoupling CPU and memory allocations of applications while also increasing the effective memory capacity for (memory-intensive) applications beyond the local memory limit imposed by traditional fixed-capacity servers. As the network speeds in the tightly-knit environments like modern datacenters inch closer to the DRAM speeds, there has been a recent proliferation of work in this space ranging from software solutions that pool memory of traditional servers for the shared use of the cluster to systems targeting the memory disaggregation in the hardware. In this report, we look at some of these recent memory disaggregation systems and study the important factors that guide their design, such as the interface through which the memory is exposed to the application, their runtime design and relevant optimizations to retain the near-native application performance, various approaches they employ in managing cluster memory to maximize utilization, etc. and we analyze the associated trade-offs. We conclude with a discussion on some open questions and potential future directions that can render disaggregation more amenable for adoption.