Saved in:
Bibliographic Details
Main Authors: Pandurov, Milan, Humbel, Lukas, Sepp, Dmitry, Ttofari, Adamos, Thomm, Leon, Quoc, Do Le, Chandrasekaran, Siddharth, Santhanam, Sharan, Ye, Chuan, Bergman, Shai, Wang, Wei, Lundgren, Sven, Sagonas, Konstantinos, Ros, Alberto
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.13327
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912036944871424
author Pandurov, Milan
Humbel, Lukas
Sepp, Dmitry
Ttofari, Adamos
Thomm, Leon
Quoc, Do Le
Chandrasekaran, Siddharth
Santhanam, Sharan
Ye, Chuan
Bergman, Shai
Wang, Wei
Lundgren, Sven
Sagonas, Konstantinos
Ros, Alberto
author_facet Pandurov, Milan
Humbel, Lukas
Sepp, Dmitry
Ttofari, Adamos
Thomm, Leon
Quoc, Do Le
Chandrasekaran, Siddharth
Santhanam, Sharan
Ye, Chuan
Bergman, Shai
Wang, Wei
Lundgren, Sven
Sagonas, Konstantinos
Ros, Alberto
contents Memory has become the primary cost driver in cloud data centers. Yet, a significant portion of memory allocated to VMs in public clouds remains unused. To optimize this resource, "cold" memory can be reclaimed from VMs and stored on slower storage or compressed, enabling memory overcommit. Current overcommit systems rely on general-purpose OS swap mechanisms, which are not optimized for virtualized workloads, leading to missed memory-saving opportunities and ineffective use of optimizations like prefetchers. This paper introduces a userspace memory management framework designed for VMs. It enables custom policies that have full control over the virtual machines' memory using a simple userspace API, supports huge page-based swapping to satisfy VM performance requirements, is easy to deploy by leveraging Linux/KVM, and supports zero-copy I/O virtualization with shared VM memory. Our evaluation demonstrates that an overcommit system based on our framework outperforms the state-of-the-art solutions on both micro-benchmarks and commonly used cloud workloads. Specifically our implementation outperforms the Linux Kernel baseline implementation by up to 25% while saving a similar amount of memory. We also demonstrate the benefits of custom policies by implementing workload-specific reclaimers and prefetchers that save $10\%$ additional memory, improve performance in a limited memory scenario by 30% over the Linux baseline, and recover faster from hard limit releases.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13327
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Flexible Swapping for the Cloud
Pandurov, Milan
Humbel, Lukas
Sepp, Dmitry
Ttofari, Adamos
Thomm, Leon
Quoc, Do Le
Chandrasekaran, Siddharth
Santhanam, Sharan
Ye, Chuan
Bergman, Shai
Wang, Wei
Lundgren, Sven
Sagonas, Konstantinos
Ros, Alberto
Distributed, Parallel, and Cluster Computing
Operating Systems
D.4.2
Memory has become the primary cost driver in cloud data centers. Yet, a significant portion of memory allocated to VMs in public clouds remains unused. To optimize this resource, "cold" memory can be reclaimed from VMs and stored on slower storage or compressed, enabling memory overcommit. Current overcommit systems rely on general-purpose OS swap mechanisms, which are not optimized for virtualized workloads, leading to missed memory-saving opportunities and ineffective use of optimizations like prefetchers. This paper introduces a userspace memory management framework designed for VMs. It enables custom policies that have full control over the virtual machines' memory using a simple userspace API, supports huge page-based swapping to satisfy VM performance requirements, is easy to deploy by leveraging Linux/KVM, and supports zero-copy I/O virtualization with shared VM memory. Our evaluation demonstrates that an overcommit system based on our framework outperforms the state-of-the-art solutions on both micro-benchmarks and commonly used cloud workloads. Specifically our implementation outperforms the Linux Kernel baseline implementation by up to 25% while saving a similar amount of memory. We also demonstrate the benefits of custom policies by implementing workload-specific reclaimers and prefetchers that save $10\%$ additional memory, improve performance in a limited memory scenario by 30% over the Linux baseline, and recover faster from hard limit releases.
title Flexible Swapping for the Cloud
topic Distributed, Parallel, and Cluster Computing
Operating Systems
D.4.2
url https://arxiv.org/abs/2409.13327