FluidMem: Memory as a Service for the Datacenter

TL;DR

FluidMem introduces a comprehensive Memory as a Service system for datacenters, enabling transparent remote memory access for cloud applications, addressing hardware heterogeneity and deployment complexity.

Contribution

It presents FluidMem, a complete Linux-based system that implements memory disaggregation as a service, including performance evaluation with real-world applications.

Findings

Supports remote memory for standard applications like MongoDB and genome sequencing.

Demonstrates transparent and efficient memory disaggregation in datacenter environments.

Addresses heterogeneity and deployment challenges in cloud-based memory disaggregation.

Abstract

Disaggregating resources in data centers is an emerging trend. Recent work has begun to explore memory disaggregation, but suffers limitations including lack of consideration of the complexity of cloud-based deployment, including heterogeneous hardware and APIs for cloud users and operators. In this paper, we present FluidMem, a complete system to realize disaggregated memory in the datacenter. Going beyond simply demonstrating remote memory is possible, we create an entire Memory as a Service. We define the requirements of Memory as a Service and build its implementation in Linux as FluidMem. We present a performance analysis of FluidMem and demonstrate that it transparently supports remote memory for standard applications such as MongoDB and genome sequencing applications.