Reconsidering OS memory optimizations in the presence of disaggregated memory
File(s)ismm22_hotbox_public.pdf (908.25 KB)
Accepted version
Author(s)
Bergman, Shai
Faldu, Priyank
Grot, Boris
Vilanova, Lluís
Silberstein, Mark
Type
Conference Paper
Abstract
Tiered memory systems introduce an additional memory level with higher-than-local-DRAM access latency and require sophisticated memory management mechanisms to achieve cost-efficiency and high performance. Recent works focus on byte-addressable tiered memory architectures which offer better performance than pure swap-based systems. We observe that adding disaggregation to a byte-addressable tiered memory architecture requires important design changes that deviate from the common techniques that target lower-latency non-volatile memory systems. Our comprehensive analysis of real workloads shows that the high access latency to disaggregated memory undermines the utility of well-established memory management optimizations Based on these insights, we develop HotBox – a disaggregated memory management subsystem for Linux that strives to maximize the local memory hit rate with low memory management overhead. HotBox introduces only minor changes to the Linux kernel while outperforming state-of-the-art systems on memory-intensive benchmarks by up to 2.25×.
Date Issued
2022-06-14
Date Acceptance
2022-06-01
Citation
ISMM 2022: Proceedings of the 2022 ACM SIGPLAN International Symposium on Memory Management, 2022, pp.1-14
ISBN
978-1-4503-9267-9
Publisher
ACM
Start Page
1
End Page
14
Journal / Book Title
ISMM 2022: Proceedings of the 2022 ACM SIGPLAN International Symposium on Memory Management
Copyright Statement
© 2022 Association for Computing Machinery.
Identifier
https://dl.acm.org/doi/10.1145/3520263.3534650
Source
ACM SIGPLAN International Symposium on Memory Management
Notes
group: conference
Publication Status
Published
Start Date
2022-06-14
Finish Date
2022-06-14
Coverage Spatial
San Diego, USA
Date Publish Online
2022-06-14