Motivating Next-Generation OS Physical Memory Management for Terabyte-Scale NVMMs

TL;DR

This paper analyzes how traditional OS physical memory management is inadequate for modern hybrid memory systems with large, high-latency NVMMs, and argues for fundamental redesigns to optimize performance.

Contribution

It provides a comprehensive evaluation of Linux's memory management on hybrid DRAM-NVMM systems and highlights the need for new OS strategies tailored for terabyte-scale NVMMs.

Findings

Page allocation is negatively impacted by NVMM latency.

Conventional fragmentation management is inadequate for NVMMs.

Some traditional memory management functionalities remain unaffected.

Abstract

Software managed byte-addressable hybrid memory systems consisting of DRAMs and NVMMs offer a lot of flexibility to design efficient large scale data processing applications. Operating systems (OS) play an important role in enabling the applications to realize the integrated benefits of DRAMs' low access latency and NVMMs' large capacity along with its persistent characteristics. In this paper, we comprehensively analyze the performance of conventional OS physical memory management subsystems that were designed only based on the DRAM memory characteristics in the context of modern hybrid byte-addressable memory systems. To study the impact of high access latency and large capacity of NVMMs on physical memory management, we perform an extensive evaluation on Linux with Intel's Optane NVMM. We observe that the core memory management functionalities such as page allocation are negatively impacted by high NVMM media latency, while functionalities such as conventional fragmentation management are rendered inadequate. We also demonstrate that certain traditional memory management functionalities are affected by neither aspects of modern NVMMs. We conclusively motivate the need to overhaul fundamental aspects of traditional OS physical memory management in order to fully exploit terabyte-scale NVMMs.