poster

Public Access

Optimizing Speculative Execution of Deadline-Sensitive Jobs in Cloud

Authors:

Maotong Xu,

Sultan Alamro,

Tian Lan,

Suresh SubramaniamAuthors Info & Claims

SIGMETRICS '17 Abstracts: Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems

Pages 17 - 18

https://doi.org/10.1145/3078505.3078541

Published: 05 June 2017 Publication History

PDF eReader

Abstract

In this paper, we bring various speculative scheduling strategies together under a unifying optimization framework, which defines a new metric, Probability of Completion before Deadlines (PoCD), to measure the probability that MapReduce jobs meet their desired deadlines. We propose an optimization problem to jointly optimize PoCD and execution cost in different strategies. Three strategies are prototyped on Hadoop MapReduce and evaluated against two baseline strategies using experiments. A 78% net utility increase with up to 94% PoCD and 12% cost improvement is achieved.

References

[1]

G. Ananthanarayanan, A. Ghodsi, S. Shenker, and I. Stoica, "Effective straggler mitigation: Attack of the clones," in Presented as part of the 10th USENIX Symposium on Networked Systems Design and Implementation (NSDI 13), 2013, pp. 185--198.

Digital Library

Google Scholar

[2]

M. Zaharia, A. Konwinski, A. D. Joseph, R. H. Katz, and I. Stoica, "Improving mapreduce performance in heterogeneous environments." in OSDI, vol. 8, no. 4, 2008, p. 7.

Digital Library

Google Scholar

[3]

G. Ananthanarayanan, M. C.-C. Hung, X. Ren, I. Stoica, A. Wierman, and M. Yu, "Grass: trimming stragglers in approximation analytics," in 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14), 2014, pp. 289--302.

Digital Library

Google Scholar

[4]

D.Wang, G. Joshi, and G.Wornell, "Using straggler replication to reduce latency in large-scale parallel computing," ACM SIGMETRICS Performance Evaluation Review, vol. 43, no. 3, pp. 7--11, 2015.

Digital Library

Google Scholar

[5]

X. Ren, G. Ananthanarayanan, A. Wierman, and M. Yu, "Hopper: Decentralized speculation-aware cluster scheduling at scale," ACM SIGCOMM Computer Communication Review, vol. 45, no. 4, pp. 379--392, 2015.

Digital Library

Google Scholar

Cited By

View all

Alamro SXu MLan TSubramaniam S(2020)Shed+: Optimal Dynamic Speculation to Meet Application Deadlines in CloudIEEE Transactions on Network and Service Management10.1109/TNSM.2020.298647717:3(1515-1526)Online publication date: Sep-2020
https://doi.org/10.1109/TNSM.2020.2986477
Xu HWang QSong SJohn LLiu XEigenmann RDing CMcKee S(2019)Can we trust profiling results?Proceedings of the ACM International Conference on Supercomputing10.1145/3330345.3330371(284-295)Online publication date: 26-Jun-2019
https://dl.acm.org/doi/10.1145/3330345.3330371
Alamro SXu MLan TSubramaniam S(2018)Shed: Optimal Dynamic Cloning to Meet Application Deadlines in Cloud2018 IEEE International Conference on Communications (ICC)10.1109/ICC.2018.8422557(1-7)Online publication date: May-2018
https://doi.org/10.1109/ICC.2018.8422557
Show More Cited By

Index Terms

Optimizing Speculative Execution of Deadline-Sensitive Jobs in Cloud
1. Computer systems organization
  1. Architectures
    1. Distributed architectures
      1. Cloud computing

Recommendations

Optimizing Speculative Execution of Deadline-Sensitive Jobs in Cloud
Performance evaluation review

In this paper, we bring various speculative scheduling strategies together under a unifying optimization framework, which defines a new metric, Probability of Completion before Deadlines (PoCD), to measure the probability that MapReduce jobs meet their ...
Preemptive Hadoop Jobs Scheduling under a Deadline
SKG '12: Proceedings of the 2012 Eighth International Conference on Semantics, Knowledge and Grids

MapReduce has become the dominant programming model in a cloud-based data processing environment, such as Hadoop. First In First Out (FIFO) is the default job scheduling policy of Hadoop, but it cannot guarantee that the job will be completed by a ...
Bipartite Matching Based Speculative Execution to Improve Cloud MapReduce Performance
ACIT-CSI '15: Proceedings of the 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence

MapReduce is a software framework which canparallelize the job execution by dividing a job into a number ofmap and reduce tasks in cloud computing systems. Due to somereasons (hardware malfunction, input data skew, heterogeneouscloud environment, etc.), ...

Comments

Information & Contributors

Information

Published In

SIGMETRICS '17 Abstracts: Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems

June 2017

84 pages

ISBN:9781450350327

DOI:10.1145/3078505

General Chairs:
Bruce Hajek
University of Illinois
,
Sewoong Oh
University of Illinois
,
Program Chairs:
Augustin Chaintreau
Columbia University
,
Leana Golubchik
University of Southern California
,
Zhi-Li Zhang
University of Minnesota

ACM SIGMETRICS Performance Evaluation Review Volume 45, Issue 1
Performance evaluation review
June 2017
70 pages
ISSN:0163-5999
DOI:10.1145/3143314
Editor:
Nidhi Hegde
Bell Labs, Nokia
Issue’s Table of Contents

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 June 2017

Check for updates

Author Tags

Qualifiers

Poster

Funding Sources

National Science Foundation

Conference

SIGMETRICS '17

Sponsor:

SIGMETRICS

SIGMETRICS '17: ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems

June 5 - 9, 2017

Illinois, Urbana-Champaign, USA

Acceptance Rates

SIGMETRICS '17 Abstracts Paper Acceptance Rate 27 of 76 submissions, 36%;

Overall Acceptance Rate 459 of 2,691 submissions, 17%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
380
Total Downloads

Downloads (Last 12 months)88
Downloads (Last 6 weeks)17

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Alamro SXu MLan TSubramaniam S(2020)Shed+: Optimal Dynamic Speculation to Meet Application Deadlines in CloudIEEE Transactions on Network and Service Management10.1109/TNSM.2020.298647717:3(1515-1526)Online publication date: Sep-2020
https://doi.org/10.1109/TNSM.2020.2986477
Xu HWang QSong SJohn LLiu XEigenmann RDing CMcKee S(2019)Can we trust profiling results?Proceedings of the ACM International Conference on Supercomputing10.1145/3330345.3330371(284-295)Online publication date: 26-Jun-2019
https://dl.acm.org/doi/10.1145/3330345.3330371
Alamro SXu MLan TSubramaniam S(2018)Shed: Optimal Dynamic Cloning to Meet Application Deadlines in Cloud2018 IEEE International Conference on Communications (ICC)10.1109/ICC.2018.8422557(1-7)Online publication date: May-2018
https://doi.org/10.1109/ICC.2018.8422557
Wang KZhou QGuo SLuo J(2018)Cluster Frameworks for Efficient Scheduling and Resource Allocation in Data Center Networks: A SurveyIEEE Communications Surveys & Tutorials10.1109/COMST.2018.285792220:4(3560-3580)Online publication date: Dec-2019
https://doi.org/10.1109/COMST.2018.2857922
Xu MAlamro SLan TSubramaniam S(2017)CRED: Cloud Right-Sizing with Execution Deadlines and Data LocalityIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2017.272607128:12(3389-3400)Online publication date: 1-Dec-2017
https://doi.org/10.1109/TPDS.2017.2726071
Gill SOuyang XGarraghan P(2020)Tails in the cloud: a survey and taxonomy of straggler management within large-scale cloud data centresThe Journal of Supercomputing10.1007/s11227-020-03241-x76:12(10050-10089)Online publication date: 1-Dec-2020
https://dl.acm.org/doi/10.1007/s11227-020-03241-x
Xu MAlamro SLan TSubramaniam S(2017)LASER: A Deep Learning Approach for Speculative Execution and Replication of Deadline-Critical Jobs in Cloud2017 26th International Conference on Computer Communication and Networks (ICCCN)10.1109/ICCCN.2017.8038373(1-8)Online publication date: Jul-2017
https://doi.org/10.1109/ICCCN.2017.8038373

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Optimizing Speculative Execution of Deadline-Sensitive Jobs in Cloud

Preemptive Hadoop Jobs Scheduling under a Deadline

Bipartite Matching Based Speculative Execution to Improve Cloud MapReduce Performance