INDIGO: Page Migration for Hardware Memory Disaggregation Across a Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Patke, Archit, Pinto, Christian, Jha, Saurabh, Qiu, Haoran, Kalbarczyk, Zbigniew, Iyer, Ravishankar
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917966611742720
author Patke, Archit
Pinto, Christian
Jha, Saurabh
Qiu, Haoran
Kalbarczyk, Zbigniew
Iyer, Ravishankar
author_facet Patke, Archit
Pinto, Christian
Jha, Saurabh
Qiu, Haoran
Kalbarczyk, Zbigniew
Iyer, Ravishankar
contents Hardware memory disaggregation (HMD) is an emerging technology that enables access to remote memory, thereby creating expansive memory pools and reducing memory underutilization in datacenters. However, a significant challenge arises when accessing remote memory over a network: increased contention that can lead to severe application performance degradation. To reduce the performance penalty of using remote memory, the operating system uses page migration to promote frequently accessed pages closer to the processor. However, previously proposed page migration mechanisms do not achieve the best performance in HMD systems because of obliviousness to variable page transfer costs that occur due to network contention. To address these limitations, we present INDIGO: a network-aware page migration framework that uses novel page telemetry and a learning-based approach for network adaptation. We implemented INDIGO in the Linux kernel and evaluated it with common cloud and HPC applications on a real disaggregated memory system prototype. Our evaluation shows that INDIGO offers up to 50-70% improvement in application performance compared to other state-of-the-art page migration policies and reduces network traffic up to 2x.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle INDIGO: Page Migration for Hardware Memory Disaggregation Across a Network
Patke, Archit
Pinto, Christian
Jha, Saurabh
Qiu, Haoran
Kalbarczyk, Zbigniew
Iyer, Ravishankar
Distributed, Parallel, and Cluster Computing
Hardware memory disaggregation (HMD) is an emerging technology that enables access to remote memory, thereby creating expansive memory pools and reducing memory underutilization in datacenters. However, a significant challenge arises when accessing remote memory over a network: increased contention that can lead to severe application performance degradation. To reduce the performance penalty of using remote memory, the operating system uses page migration to promote frequently accessed pages closer to the processor. However, previously proposed page migration mechanisms do not achieve the best performance in HMD systems because of obliviousness to variable page transfer costs that occur due to network contention. To address these limitations, we present INDIGO: a network-aware page migration framework that uses novel page telemetry and a learning-based approach for network adaptation. We implemented INDIGO in the Linux kernel and evaluated it with common cloud and HPC applications on a real disaggregated memory system prototype. Our evaluation shows that INDIGO offers up to 50-70% improvement in application performance compared to other state-of-the-art page migration policies and reduces network traffic up to 2x.
title INDIGO: Page Migration for Hardware Memory Disaggregation Across a Network
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2503.18140