Mercury: QoS-Aware Tiered Memory System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jiaheng, Zhang, Yiwen, Maruf, Hasan Al, Park, Minseo, Tang, Yunxuan, Lai, Fan, Chowdhury, Mosharaf
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929627126038528
author Lu, Jiaheng
Zhang, Yiwen
Maruf, Hasan Al
Park, Minseo
Tang, Yunxuan
Lai, Fan
Chowdhury, Mosharaf
author_facet Lu, Jiaheng
Zhang, Yiwen
Maruf, Hasan Al
Park, Minseo
Tang, Yunxuan
Lai, Fan
Chowdhury, Mosharaf
contents Memory tiering has received wide adoption in recent years as an effective solution to address the increasing memory demands of memory-intensive workloads. However, existing tiered memory systems often fail to meet service-level objectives (SLOs) when multiple applications share the system because they lack Quality-of-Service (QoS) support. Consequently, applications suffer severe performance drops due to local memory contention and memory bandwidth interference. In this paper, we present Mercury, a QoS-aware tiered memory system that ensures predictable performance for coexisting memory-intensive applications with different SLOs. Mercury enables per-tier page reclamation for application-level resource management and uses a proactive admission control algorithm to satisfy SLOs via per-tier memory capacity allocation and intra- and inter-tier bandwidth interference mitigation. It reacts to dynamic requirement changes via real-time adaptation. Extensive evaluations show that Mercury improves application performance by up to 53.4% and 20.3% compared to TPP and Colloid, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08938
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mercury: QoS-Aware Tiered Memory System
Lu, Jiaheng
Zhang, Yiwen
Maruf, Hasan Al
Park, Minseo
Tang, Yunxuan
Lai, Fan
Chowdhury, Mosharaf
Operating Systems
Distributed, Parallel, and Cluster Computing
Memory tiering has received wide adoption in recent years as an effective solution to address the increasing memory demands of memory-intensive workloads. However, existing tiered memory systems often fail to meet service-level objectives (SLOs) when multiple applications share the system because they lack Quality-of-Service (QoS) support. Consequently, applications suffer severe performance drops due to local memory contention and memory bandwidth interference. In this paper, we present Mercury, a QoS-aware tiered memory system that ensures predictable performance for coexisting memory-intensive applications with different SLOs. Mercury enables per-tier page reclamation for application-level resource management and uses a proactive admission control algorithm to satisfy SLOs via per-tier memory capacity allocation and intra- and inter-tier bandwidth interference mitigation. It reacts to dynamic requirement changes via real-time adaptation. Extensive evaluations show that Mercury improves application performance by up to 53.4% and 20.3% compared to TPP and Colloid, respectively.
title Mercury: QoS-Aware Tiered Memory System
topic Operating Systems
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2412.08938