Compaction-Free Memory Defragmentation for Virtualization via Infinite Guest Physical Address Space
Peixin Zeng, Hao Huang, Yanqi Pan, Wen Xia, Darong Yang, Jiahao Chen, Nan Zhang
Abstract
In virtualized environments, guest memory defragmentation is essential for exploiting huge-page benefits and improving application performance. However, existing approaches directly reuse host-side defragmentation and assume a limited guest physical address (GPA) space. As a result, they rely on memory compaction to defragment this constrained space, causing throughput to drop by up to 51% and latency to rise by up to 102% in YCSB-Redis workloads.
This paper proposes INFINIDEFRAG, a compaction-free memory defragmentation technique for virtualization. Our key insight is that the GPA space can be regarded as (nearly) infinite by controlling the mapping between GPA and host physical address (HPA), thereby eliminating the need for guest-side memory compaction. To realize this insight, we introduce (1) Infinite Address Manager that expands the GPA space while reclaiming free fragment pages; (2) Host Memory Guard that maintains the GPA-HPA mapping and constrains HPA usage within each VM's quota; and (3) Scalability Optimizer that scales GPA/HPA space management to multi-thread and multi-VM environments. Experiments on micro-benchmarks and real-world applications show that IN-FINIDEFRAG outperforms state-of-the-art approaches and can achieve ideal, fragmentation-free performance.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 0099d211-a5eb-4d95-96f0-4b05a7a2e07cBuilds on16
- Learning-based Memory Allocation for C++ Server WorkloadsMartin Maas, David G. Andersen, Michael Isard, Mohammad Mahdi Javanmard et al.ASPLOS 2020 · 59 citations
- Beyond malloc efficiency to fleet efficiency: a hugepage-aware memory allocatorA. H. Hunter, Chris Kennelly, Paul Turner, Darryl Gove et al.OSDI 2021 · 51 citations
- Enhancing and Exploiting Contiguity for Fast Memory VirtualizationChloe Alverti, Stratos Psomadakis, Vasileios Karakostas, Jayneel Gandhi et al.ISCA 2020 · 41 citations
- A Comprehensive Analysis of Superpage Management Mechanisms and PoliciesWeixi Zhu, Alan L. Cox, Scott RixnerUSENIX ATC 2020 · 40 citations
- Perforated Page: Supporting Fragmented Memory Allocation for Large PagesChang Hyun Park, Sanghoon Cha, Bokyeong Kim, Youngjin Kwon et al.ISCA 2020 · 35 citations
Related papers
- PTEMagnet: fine-grained physical memory reservation for faster page walks in public cloudsArtemiy Margaritov, Dmitrii Ustiugov, Amna Shahab, Boris GrotASPLOS 2021 · 19 citations
- Efficient Memory Overcommitment for I/O Passthrough Enabled VMs via Fine-grained Page Meta-data ManagementYaohui Wang, Ben Luo, Yibin ShenUSENIX ATC 2023 · 18 citations
- Blowfish: Elastic Virtual Machine Memory for Disaggregated MemoryYulong Zhang, Yilong Luo, Diyu Zhou, Quan Chen et al.OSDI 2026
- Taming Hot Bloat Under Virtualization with HUGESCOPEChuandong Li, Sai Sha, Yangqing Zeng, Xiran Yang et al.USENIX ATC 2024 · 8 citations
- LLFree: Scalable and Optionally-Persistent Page-Frame AllocationLars Wrenger, Florian Rommel, Alexander Halbuer, Christian Dietrich et al.USENIX ATC 2023 · 17 citations
