AKC: Advanced KSM for cloud computing

Sioh Lee, Bongkyu Kim, Youngpil Kim, Hyuck Yoo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Kernel samepage merging (KSM) in Linux kernel archive is a memory deduplication scheme that finds duplicate pages and shares the page in order to alleviate memory bottleneck in cloud. However, because the KSM has to scan all pages in memory to find duplicate pages, KSM consumes high CPU cycles and so causes virtual machines (VMs) performance degradation [1]. This degradation of VMs performance is an obstacle in cloud to service real-time applications (i.e. Netflix) [3]. A previous work, CMD [1] proposed page grouping scheme to reduce page comparisons, but it requires special monitoring hardware, XLH [2] enhanced page sharing with the information of guest VM I/O operation. However, the CPU overhead of XLH is still very high - similar to the default KSM. to make KSM more useful, we need an optimization scheme that consume less CPU cycles. Therefore, we first profile the CPU cycle consumption of KSM and the results show that page comparison (28.77%) and page checksum (26.14%) take most of cycles. Based on the results, we propose advanced KSM for cloud computing (AKC) that consumes less CPU cycles than the default KSM. to reduce the number of page comparisons, we apply checksum based RB-tree structure. In addition, AKC decreases page checksum overhead with hardware-accelerated crc32 hash function.

Original languageEnglish
Title of host publicationSoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing
PublisherAssociation for Computing Machinery, Inc
Number of pages1
ISBN (Electronic)9781450350280
DOIs
Publication statusPublished - 2017 Sep 24
Event2017 Symposium on Cloud Computing, SoCC 2017 - Santa Clara, United States
Duration: 2017 Sep 242017 Sep 27

Other

Other2017 Symposium on Cloud Computing, SoCC 2017
CountryUnited States
CitySanta Clara
Period17/9/2417/9/27

Fingerprint

Cloud computing
Cloud Computing
Merging
kernel
Program processors
Cycle
Virtual Machine
Data storage equipment
Degradation
Hardware
Hash functions
Hash Function
Linux
Tree Structure
Grouping
Sharing
Monitoring
Real-time
Decrease
Optimization

Keywords

  • Kernel samepage merging
  • KSM
  • Memory deduplication

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Lee, S., Kim, B., Kim, Y., & Yoo, H. (2017). AKC: Advanced KSM for cloud computing. In SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing Association for Computing Machinery, Inc. https://doi.org/10.1145/3127479.3131616

AKC : Advanced KSM for cloud computing. / Lee, Sioh; Kim, Bongkyu; Kim, Youngpil; Yoo, Hyuck.

SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing. Association for Computing Machinery, Inc, 2017.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, S, Kim, B, Kim, Y & Yoo, H 2017, AKC: Advanced KSM for cloud computing. in SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing. Association for Computing Machinery, Inc, 2017 Symposium on Cloud Computing, SoCC 2017, Santa Clara, United States, 17/9/24. https://doi.org/10.1145/3127479.3131616
Lee S, Kim B, Kim Y, Yoo H. AKC: Advanced KSM for cloud computing. In SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing. Association for Computing Machinery, Inc. 2017 https://doi.org/10.1145/3127479.3131616
Lee, Sioh ; Kim, Bongkyu ; Kim, Youngpil ; Yoo, Hyuck. / AKC : Advanced KSM for cloud computing. SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing. Association for Computing Machinery, Inc, 2017.
@inproceedings{667875842f834288b1ca45d7a266d69d,
title = "AKC: Advanced KSM for cloud computing",
abstract = "Kernel samepage merging (KSM) in Linux kernel archive is a memory deduplication scheme that finds duplicate pages and shares the page in order to alleviate memory bottleneck in cloud. However, because the KSM has to scan all pages in memory to find duplicate pages, KSM consumes high CPU cycles and so causes virtual machines (VMs) performance degradation [1]. This degradation of VMs performance is an obstacle in cloud to service real-time applications (i.e. Netflix) [3]. A previous work, CMD [1] proposed page grouping scheme to reduce page comparisons, but it requires special monitoring hardware, XLH [2] enhanced page sharing with the information of guest VM I/O operation. However, the CPU overhead of XLH is still very high - similar to the default KSM. to make KSM more useful, we need an optimization scheme that consume less CPU cycles. Therefore, we first profile the CPU cycle consumption of KSM and the results show that page comparison (28.77{\%}) and page checksum (26.14{\%}) take most of cycles. Based on the results, we propose advanced KSM for cloud computing (AKC) that consumes less CPU cycles than the default KSM. to reduce the number of page comparisons, we apply checksum based RB-tree structure. In addition, AKC decreases page checksum overhead with hardware-accelerated crc32 hash function.",
keywords = "Kernel samepage merging, KSM, Memory deduplication",
author = "Sioh Lee and Bongkyu Kim and Youngpil Kim and Hyuck Yoo",
year = "2017",
month = "9",
day = "24",
doi = "10.1145/3127479.3131616",
language = "English",
booktitle = "SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - AKC

T2 - Advanced KSM for cloud computing

AU - Lee, Sioh

AU - Kim, Bongkyu

AU - Kim, Youngpil

AU - Yoo, Hyuck

PY - 2017/9/24

Y1 - 2017/9/24

N2 - Kernel samepage merging (KSM) in Linux kernel archive is a memory deduplication scheme that finds duplicate pages and shares the page in order to alleviate memory bottleneck in cloud. However, because the KSM has to scan all pages in memory to find duplicate pages, KSM consumes high CPU cycles and so causes virtual machines (VMs) performance degradation [1]. This degradation of VMs performance is an obstacle in cloud to service real-time applications (i.e. Netflix) [3]. A previous work, CMD [1] proposed page grouping scheme to reduce page comparisons, but it requires special monitoring hardware, XLH [2] enhanced page sharing with the information of guest VM I/O operation. However, the CPU overhead of XLH is still very high - similar to the default KSM. to make KSM more useful, we need an optimization scheme that consume less CPU cycles. Therefore, we first profile the CPU cycle consumption of KSM and the results show that page comparison (28.77%) and page checksum (26.14%) take most of cycles. Based on the results, we propose advanced KSM for cloud computing (AKC) that consumes less CPU cycles than the default KSM. to reduce the number of page comparisons, we apply checksum based RB-tree structure. In addition, AKC decreases page checksum overhead with hardware-accelerated crc32 hash function.

AB - Kernel samepage merging (KSM) in Linux kernel archive is a memory deduplication scheme that finds duplicate pages and shares the page in order to alleviate memory bottleneck in cloud. However, because the KSM has to scan all pages in memory to find duplicate pages, KSM consumes high CPU cycles and so causes virtual machines (VMs) performance degradation [1]. This degradation of VMs performance is an obstacle in cloud to service real-time applications (i.e. Netflix) [3]. A previous work, CMD [1] proposed page grouping scheme to reduce page comparisons, but it requires special monitoring hardware, XLH [2] enhanced page sharing with the information of guest VM I/O operation. However, the CPU overhead of XLH is still very high - similar to the default KSM. to make KSM more useful, we need an optimization scheme that consume less CPU cycles. Therefore, we first profile the CPU cycle consumption of KSM and the results show that page comparison (28.77%) and page checksum (26.14%) take most of cycles. Based on the results, we propose advanced KSM for cloud computing (AKC) that consumes less CPU cycles than the default KSM. to reduce the number of page comparisons, we apply checksum based RB-tree structure. In addition, AKC decreases page checksum overhead with hardware-accelerated crc32 hash function.

KW - Kernel samepage merging

KW - KSM

KW - Memory deduplication

UR - http://www.scopus.com/inward/record.url?scp=85032441964&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032441964&partnerID=8YFLogxK

U2 - 10.1145/3127479.3131616

DO - 10.1145/3127479.3131616

M3 - Conference contribution

AN - SCOPUS:85032441964

BT - SoCC 2017 - Proceedings of the 2017 Symposium on Cloud Computing

PB - Association for Computing Machinery, Inc

ER -