Wisethrottling: A new asynchronous task scheduler for mitigating i/o bottleneck in large-scale datacenter servers

Fang Lv; Lei Liu; Hui Min Cui; Lei Wang; Ying Liu; Xiao Bing Feng; Pen Chung Yew

doi:10.1007/s11227-015-1427-7

Wisethrottling: A new asynchronous task scheduler for mitigating i/o bottleneck in large-scale datacenter servers

Fang Lv, Lei Liu, Hui Min Cui, Lei Wang, Ying Liu, Xiao Bing Feng, Pen Chung Yew

Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Datacenter servers are stepping into an era marked by powerful multi- /many-core processors. Severe problems such as I/O contentions in those large-scale platforms pose an unprecedented challenge. Prior studies primarily considered I/O bandwidth as a major performance bottleneck. However, ourwork reveals that in many cases the fundamental cause of I/O contentions is the inefficiency of OS schedulers. Particularly, the modern system is not aware of this fact and thus suffers from poor I/O performance, especially for datacenter servers. Based on our findings, we propose a new software-based scheduling approach, WiseThrottling, to reduce I/O contention. WiseThrottling performs asynchronous and self-adjustment scheduling for concurrent tasks.We evaluate our approach across a wide range of C/OpenMP/MapReduce workloads on a 64-core server in Dawning Cluster datacenter. The experimental results exhibit that WiseThrottling is effective for reducing the I/O bottleneck and it can improve the overall system performance by up to 207 %.

Original language	English (US)
Article number	A013
Pages (from-to)	3054-3093
Number of pages	40
Journal	Journal of Supercomputing
Volume	71
Issue number	8
DOIs	https://doi.org/10.1007/s11227-015-1427-7
State	Published - Aug 1 2015

Bibliographical note

Funding Information:
This research is supported by the National High Technology Research and Development Program of China under Grants No. 2012AA010902 and 2015AA011505; the NSFC under Grants No. 61202055, 61221062, 61303053, 61432016 and 61402445; and the National Basic Research Program of China under Grant No. 2011CB302504.

Publisher Copyright:
© Springer Science+Business Media New York 2015.

Keywords

I/O contention
Multi-/many-core server
Resource description
Scheduling

Access

10.1007/s11227-015-1427-7

OpenUrl availability

Full text

Cite this

@article{7a7b7557a3ef4868aa342cf0df22fd16,

title = "Wisethrottling: A new asynchronous task scheduler for mitigating i/o bottleneck in large-scale datacenter servers",

abstract = "Datacenter servers are stepping into an era marked by powerful multi- /many-core processors. Severe problems such as I/O contentions in those large-scale platforms pose an unprecedented challenge. Prior studies primarily considered I/O bandwidth as a major performance bottleneck. However, ourwork reveals that in many cases the fundamental cause of I/O contentions is the inefficiency of OS schedulers. Particularly, the modern system is not aware of this fact and thus suffers from poor I/O performance, especially for datacenter servers. Based on our findings, we propose a new software-based scheduling approach, WiseThrottling, to reduce I/O contention. WiseThrottling performs asynchronous and self-adjustment scheduling for concurrent tasks.We evaluate our approach across a wide range of C/OpenMP/MapReduce workloads on a 64-core server in Dawning Cluster datacenter. The experimental results exhibit that WiseThrottling is effective for reducing the I/O bottleneck and it can improve the overall system performance by up to 207 %.",

keywords = "I/O contention, Multi-/many-core server, Resource description, Scheduling",

author = "Fang Lv and Lei Liu and Cui, {Hui Min} and Lei Wang and Ying Liu and Feng, {Xiao Bing} and Yew, {Pen Chung}",

note = "Funding Information: This research is supported by the National High Technology Research and Development Program of China under Grants No. 2012AA010902 and 2015AA011505; the NSFC under Grants No. 61202055, 61221062, 61303053, 61432016 and 61402445; and the National Basic Research Program of China under Grant No. 2011CB302504. Publisher Copyright: {\textcopyright} Springer Science+Business Media New York 2015.",

year = "2015",

month = aug,

day = "1",

doi = "10.1007/s11227-015-1427-7",

language = "English (US)",

volume = "71",

pages = "3054--3093",

journal = "Journal of Supercomputing",

issn = "0920-8542",

publisher = "Springer Netherlands",

number = "8",

}

TY - JOUR

T1 - Wisethrottling

T2 - A new asynchronous task scheduler for mitigating i/o bottleneck in large-scale datacenter servers

AU - Lv, Fang

AU - Liu, Lei

AU - Cui, Hui Min

AU - Wang, Lei

AU - Liu, Ying

AU - Feng, Xiao Bing

AU - Yew, Pen Chung

N1 - Funding Information: This research is supported by the National High Technology Research and Development Program of China under Grants No. 2012AA010902 and 2015AA011505; the NSFC under Grants No. 61202055, 61221062, 61303053, 61432016 and 61402445; and the National Basic Research Program of China under Grant No. 2011CB302504. Publisher Copyright: © Springer Science+Business Media New York 2015.

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Datacenter servers are stepping into an era marked by powerful multi- /many-core processors. Severe problems such as I/O contentions in those large-scale platforms pose an unprecedented challenge. Prior studies primarily considered I/O bandwidth as a major performance bottleneck. However, ourwork reveals that in many cases the fundamental cause of I/O contentions is the inefficiency of OS schedulers. Particularly, the modern system is not aware of this fact and thus suffers from poor I/O performance, especially for datacenter servers. Based on our findings, we propose a new software-based scheduling approach, WiseThrottling, to reduce I/O contention. WiseThrottling performs asynchronous and self-adjustment scheduling for concurrent tasks.We evaluate our approach across a wide range of C/OpenMP/MapReduce workloads on a 64-core server in Dawning Cluster datacenter. The experimental results exhibit that WiseThrottling is effective for reducing the I/O bottleneck and it can improve the overall system performance by up to 207 %.

AB - Datacenter servers are stepping into an era marked by powerful multi- /many-core processors. Severe problems such as I/O contentions in those large-scale platforms pose an unprecedented challenge. Prior studies primarily considered I/O bandwidth as a major performance bottleneck. However, ourwork reveals that in many cases the fundamental cause of I/O contentions is the inefficiency of OS schedulers. Particularly, the modern system is not aware of this fact and thus suffers from poor I/O performance, especially for datacenter servers. Based on our findings, we propose a new software-based scheduling approach, WiseThrottling, to reduce I/O contention. WiseThrottling performs asynchronous and self-adjustment scheduling for concurrent tasks.We evaluate our approach across a wide range of C/OpenMP/MapReduce workloads on a 64-core server in Dawning Cluster datacenter. The experimental results exhibit that WiseThrottling is effective for reducing the I/O bottleneck and it can improve the overall system performance by up to 207 %.

KW - I/O contention

KW - Multi-/many-core server

KW - Resource description

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=84943354641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943354641&partnerID=8YFLogxK

U2 - 10.1007/s11227-015-1427-7

DO - 10.1007/s11227-015-1427-7

M3 - Article

AN - SCOPUS:84943354641

SN - 0920-8542

VL - 71

SP - 3054

EP - 3093

JO - Journal of Supercomputing

JF - Journal of Supercomputing

IS - 8

M1 - A013

ER -

Wisethrottling: A new asynchronous task scheduler for mitigating i/o bottleneck in large-scale datacenter servers

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this