Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization

Renhai Chen; Yi Wang; Jingtong Hu; Duo Liu; Zili Shao; Yong Guan

doi:10.1109/NVMSA.2014.6927204

Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization

Renhai Chen, Yi Wang, Jingtong Hu, Duo Liu, Zili Shao, Yong Guan

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

3 Citations (Scopus)

Abstract

Mobile virtualization introduces extra layers in software stacks, which leads to performance degradation. Especially, each I/O operation has to pass through several software layers to reach the NAND-flash-based storage systems. Among all the I/O operations, a large percentage is updating metadata. Frequent updating metadata not only degrades overall I/O performance but also severely reduces flash memory lifetime. In this paper, we propose a novel I/O optimization technique to identify the metadata of a guest file system which are stored in a VM image file and frequently updated. Then these metadata are stored in a small additional non-volatile memory which is faster and more endurable to greatly improve flash memory's performance and lifetime. The proposed scheme is evaluated on a real hardware embedded platform. The experimental results show that the proposed techniques can effectively improve the I/O performance in mobile devices with virtualization.

Original language	English
Title of host publication	2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014
Publisher	IEEE
ISBN (Electronic)	9781479955763
DOIs	https://doi.org/10.1109/NVMSA.2014.6927204
Publication status	Published - 1 Jan 2014
Event	2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014 - Chongqing, China Duration: 20 Aug 2014 → 21 Aug 2014

Conference

Conference	2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014
Country/Territory	China
City	Chongqing
Period	20/08/14 → 21/08/14

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Signal Processing
Software

More information

10.1109/NVMSA.2014.6927204

Cite this

@inproceedings{b26c7d18d54241699515d5e75911bc82,

title = "Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization",

abstract = "Mobile virtualization introduces extra layers in software stacks, which leads to performance degradation. Especially, each I/O operation has to pass through several software layers to reach the NAND-flash-based storage systems. Among all the I/O operations, a large percentage is updating metadata. Frequent updating metadata not only degrades overall I/O performance but also severely reduces flash memory lifetime. In this paper, we propose a novel I/O optimization technique to identify the metadata of a guest file system which are stored in a VM image file and frequently updated. Then these metadata are stored in a small additional non-volatile memory which is faster and more endurable to greatly improve flash memory's performance and lifetime. The proposed scheme is evaluated on a real hardware embedded platform. The experimental results show that the proposed techniques can effectively improve the I/O performance in mobile devices with virtualization.",

author = "Renhai Chen and Yi Wang and Jingtong Hu and Duo Liu and Zili Shao and Yong Guan",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/NVMSA.2014.6927204",

language = "English",

booktitle = "2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014",

publisher = "IEEE",

address = "United States",

note = "2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014 ; Conference date: 20-08-2014 Through 21-08-2014",

}

Chen, R, Wang, Y, Hu, J, Liu, D, Shao, Z & Guan, Y 2014, Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization. in 2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014., 6927204, IEEE, 2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014, Chongqing, China, 20/08/14. https://doi.org/10.1109/NVMSA.2014.6927204

Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization. / Chen, Renhai; Wang, Yi; Hu, Jingtong et al.
2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014. IEEE, 2014. 6927204.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization

AU - Chen, Renhai

AU - Wang, Yi

AU - Hu, Jingtong

AU - Liu, Duo

AU - Shao, Zili

AU - Guan, Yong

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Mobile virtualization introduces extra layers in software stacks, which leads to performance degradation. Especially, each I/O operation has to pass through several software layers to reach the NAND-flash-based storage systems. Among all the I/O operations, a large percentage is updating metadata. Frequent updating metadata not only degrades overall I/O performance but also severely reduces flash memory lifetime. In this paper, we propose a novel I/O optimization technique to identify the metadata of a guest file system which are stored in a VM image file and frequently updated. Then these metadata are stored in a small additional non-volatile memory which is faster and more endurable to greatly improve flash memory's performance and lifetime. The proposed scheme is evaluated on a real hardware embedded platform. The experimental results show that the proposed techniques can effectively improve the I/O performance in mobile devices with virtualization.

AB - Mobile virtualization introduces extra layers in software stacks, which leads to performance degradation. Especially, each I/O operation has to pass through several software layers to reach the NAND-flash-based storage systems. Among all the I/O operations, a large percentage is updating metadata. Frequent updating metadata not only degrades overall I/O performance but also severely reduces flash memory lifetime. In this paper, we propose a novel I/O optimization technique to identify the metadata of a guest file system which are stored in a VM image file and frequently updated. Then these metadata are stored in a small additional non-volatile memory which is faster and more endurable to greatly improve flash memory's performance and lifetime. The proposed scheme is evaluated on a real hardware embedded platform. The experimental results show that the proposed techniques can effectively improve the I/O performance in mobile devices with virtualization.

UR - http://www.scopus.com/inward/record.url?scp=84912076455&partnerID=8YFLogxK

U2 - 10.1109/NVMSA.2014.6927204

DO - 10.1109/NVMSA.2014.6927204

M3 - Conference article published in proceeding or book

BT - 2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014

PB - IEEE

T2 - 2014 IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2014

Y2 - 20 August 2014 through 21 August 2014

ER -

Virtual-machine metadata optimization for I/O traffic reduction in mobile virtualization

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this