research-article

An Empirical Analysis of Amazon EC2 Spot Instance Features Affecting Cost-effective Resource Procurement

Authors:

Bhuvan UrgaonkarAuthors Info & Claims

ICPE '17: Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering

Pages 63 - 74

https://doi.org/10.1145/3030207.3030210

Published: 17 April 2017 Publication History

Abstract

Many cost-conscious public cloud workloads ("tenants") are turning to Amazon EC2's spot instances because, on average, these instances offer significantly lower prices (up to 10 times lower) than on-demand and reserved instances of comparable advertized resource capacities. To use spot instances effectively, a tenant must carefully weigh the lower costs of these instances against their poorer availability. Towards this, we empirically study four features of EC2 spot instance operation that a cost-conscious tenant may find useful to model. Using extensive evaluation based on both historical and current spot instance data, we show shortcomings in the state-of-the-art modeling of these features that we overcome. Our analysis reveals many novel properties of spot instance operation some of which offer predictive value while others do not. Using these insights, we design predictors for our features that offer a balance between computational efficiency (allowing for online resource procurement) and cost-efficacy. We explore "case studies" wherein we implement prototypes of dynamic spot instance procurement advised by our predictors for two types of workloads. Compared to the state-of-the-art, our approach achieves (i) comparable cost but much better performance (fewer bid failures) for a latency-sensitive in-memory Memcached cache, and (ii) an additional 18% cost-savings with comparable (if not better than) performance for a delay-tolerant batch workload.

References

[1]

O. A. Ben-Yehuda, M. Ben-Yehuda, A. Schuster, and D. Tsafrir. Deconstructing amazon ec2 spot instance pricing. In Proc. of CloudCom'11, 2011.

Digital Library

[2]

Avrora, 2016. http://dacapobench.org/benchmarks.html.

[3]

Building price-aware applications using ec2 spot instances, 2015. https://aws.amazon.com/blogs/aws/category/ec2-spot-instances/.

[4]

Ec2 boot time, 2016. http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ComponentsAMIs.html.

[5]

EC2 spot, 2016. http://aws.amazon.com/ec2/spot-instances/.

[6]

Y. Gong, B. He, and A. C. Zhou. Monetary cost optimizations for mpi-based hpc applications on amazon clouds: Checkpoints and replicated execution. In Proc. of the SC'15, 2015.

Digital Library

[7]

J. A. Hartigan and M. A. Wong. Algorithm as 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), 28(1):100--108, 1979.

[8]

J. He, Y. Wen, J. Huang, and D. Wu. On the cost--qoe tradeoff for cloud-based video streaming under amazon ec2's pricing models. Circuits and Systems for Video Technology, IEEE Transactions on, 2014.

[9]

iPerf, 2016. https://iperf.fr/iperf-download.php.

[10]

B. Javadi, R. Thulasiramy, and R. Buyya. Statistical modeling of spot instance prices in public cloud environments. In Proc. of UCC'11, 2011.

Digital Library

[11]

G. Kesidis, B. Urgaonkar, N. Nasiriani, and C. Wang. Neutrality in future public clouds: Implications and challenges. In HotCloud'16, 2016.

[12]

S. Khatua and N. Mukherjee. Application-centric resource provisioning for amazon ec2 spot instances. In Euro-Par 2013 Parallel Processing. 2013.

Digital Library

[13]

M. Mao and M. Humphrey. A performance study on the vm startup time in the cloud. In Proc. of IEEE CLOUD'12, 2012.

Digital Library

[14]

A. Marathe, R. Harris, D. Lowenthal, B. R. de Supinski, B. Rountree, and M. Schulz. Exploiting redundancy for cost-effective, time-constrained execution of hpc applications on amazon ec2. In HPDC'14, 2014.

Digital Library

[15]

M. Mattess, C. Vecchiola, and R. Buyya. Managing peak loads by leasing cloud infrastructure services from a spot market. In Proc. of HPCC'10, 2010.

Digital Library

[16]

Memcached, 2016. https://memcached.org/.

[17]

I. Menache, O. Shamir, and N. Jain. On-demand, spot, or both: Dynamic resource allocation for executing batch jobs in the cloud. In Proc. of ICAC'14, 2014.

[18]

Spot characterization code and data, 2016. https://github.com/patiner/spot_characterization.git.

[19]

P. Sharma, D. Irwin, and P. Shenoy. How not to bid the cloud. In Proc. of HotCloud'16, 2016.

[20]

P. Sharma, S. Lee, T. Guo, D. Irwin, and P. Shenoy. Spotcheck: Designing a derivative iaas cloud on the spot market. In Proc. of EuroSys'15, 2015.

Digital Library

[21]

Y. Song, M. Zafer, and K. Lee. Optimal bidding in spot instance market. In INFOCOM'12, 2012.

[22]

Spot instance: featured customer testimonials, 2015. https://aws.amazon.com/ec2/spot/testimonials/.

[23]

Spot fleet, 2016. http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/spot-fleet.html.

[24]

Spot bid status, 2016. http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/spot-bid-status.html.

[25]

STREAM, 2016. http://www.cs.virginia.edu/stream/.

[26]

S. Subramanya, T. Guo, P. Sharma, D. Irwin, and P. Shenoy. Spoton: A batch computing service for the spot market. In Proc. of SoCC'15, 2015.

Digital Library

[27]

S. Subramanya, A. Rizk, and D. Irwin. Cloud spot markets are not sustainable: The case for transient guarantees. In Proc. of HotCloud'16, 2016.

[28]

S. Tang, J. Yuan, and X.-Y. Li. Towards optimal bidding strategy for amazon ec2 cloud spot instance. In Proc. of IEEE CLOUD'12, 2012.

Digital Library

[29]

G. Urdaneta, G. Pierre, and M. Van Steen. Wikipedia workload analysis for decentralized hosting. Elsevier Computer Networks, 53(11), 2009.

[30]

R. M. Wallace, V. Turchenko, M. Sheikhalishahi, I. Turchenko, V. Shults, J. L. Vazquez-Poletti, and L. Grandinetti. Applications of neural-based spot market prediction for cloud computing. In IDAACS'13, 2013.

[31]

C. Wang, Q. Liang, and B. Urgaonkar. An empirical analysis of amazon ec2 spot instance features affecting cost-effective resource procurement. Technical report, CSE TR-16-006, Penn State University. http://www.cse.psu.edu/research/publications/tech-reports/2016/CSE-16-006.pdf, 2016.

[32]

C. Wang, B. Urganokar, A. Gupta, L. Chen, R. Birke, and G. Kesidis. Effective capacity modulation as an explicit control knob for public cloud profitability. In ICAC'16, 2016.

[33]

Z. Wu, M. Butkiewicz, D. Perkins, E. Katz-Bassett, and H. V. Madhyastha. Spanstore: Cost-effective geo-replicated storage spanning multiple cloud services. In Proc. of SOSP'13, 2013.

Digital Library

[34]

Z. Xu, C. Stewart, N. Deng, and X. Wang. Blending on-demand and spot instances to lower costs for in-memory storage. In Proc. of IEEE Infocom'16, 2016.

[35]

M. Zafer, Y. Song, and K.-W. Lee. Optimal bids for spot vms in a cloud for deadline constrained jobs. In Cloud'12, 2012.

Digital Library

[36]

H. Zhao, M. Pan, X. Liu, X. Li, and Y. Fang. Optimal resource rental planning for elastic applications in cloud market. In Proc. of IPDPS'12, 2012.

Digital Library

Cited By

Kim KLee KChua TNgo CKa-Wei Lee RKumar RLauw H(2024)Making Cloud Spot Instance Interruption Events VisibleProceedings of the ACM Web Conference 202410.1145/3589334.3645548(2998-3009)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645548
Xu ZPan LLiu S(2024)An Online Algorithm Based on Replication for Using Spot Instances in IaaS CloudsJournal of Computer Science and Technology10.1007/s11390-023-1535-439:1(103-115)Online publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1007/s11390-023-1535-4
Lee SHwang JLee K(2022)SpotLake: Diverse Spot Instance Dataset Archive Service2022 IEEE International Symposium on Workload Characterization (IISWC)10.1109/IISWC55918.2022.00029(242-255)Online publication date: Nov-2022
https://doi.org/10.1109/IISWC55918.2022.00029
Show More Cited By

Index Terms

An Empirical Analysis of Amazon EC2 Spot Instance Features Affecting Cost-effective Resource Procurement
1. Computer systems organization
  1. Architectures
    1. Distributed architectures
      1. Cloud computing
2. Computing methodologies
  1. Modeling and simulation
    1. Model development and analysis

Recommendations

Deconstructing Amazon EC2 Spot Instance Pricing

Cloud providers possessing large quantities of spare capacity must either incentivize clients to purchase it or suffer losses. Amazon is the first cloud provider to address this challenge, by allowing clients to bid on spare capacity and by granting ...
An Empirical Analysis of Amazon EC2 Spot Instance Features Affecting Cost-Effective Resource Procurement
Special Issue on ICPE 2017 and Regular Papers

Many cost-conscious public cloud workloads (“tenants”) are turning to Amazon EC2’s spot instances because, on average, these instances offer significantly lower prices (up to 10 times lower) than on-demand and reserved instances of comparable advertised ...
Application-Centric resource provisioning for amazon EC2 spot instances
Euro-Par'13: Proceedings of the 19th international conference on Parallel Processing

In late 2009, Amazon introduced spot instances to offer their unused resources at lower cost with reduced reliability. Amazon's spot instances allow customers to bid on unused Amazon EC2 capacity and run those instances for as long as their bid exceeds ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICPE '17: Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering

April 2017

450 pages

ISBN:9781450344043

DOI:10.1145/3030207

General Chairs:
Walter Binder
Università della Svizzera Italiana, Switzerland
,
Vittorio Cortellessa
Università dell'Aquila, Italy
,
Program Chairs:
Anne Koziolek
Karlsruhe Institute of Technology, Germany
,
Evgenia Smirni
College of William & Mary, USA
,
Meikel Poess
Oracle Corporation, USA

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part 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 components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMETRICS: ACM Special Interest Group on Measurement and Evaluation
SIGSOFT: ACM Special Interest Group on Software Engineering
SPEC: SPEC Research Group

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 April 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

IBM faculty partnership award
NSF career award

Conference

ICPE '17

Sponsor:

ICPE '17: ACM/SPEC International Conference on Performance Engineering

April 22 - 26, 2017

L'Aquila, Italy

Acceptance Rates

ICPE '17 Paper Acceptance Rate 27 of 83 submissions, 33%;

Overall Acceptance Rate 252 of 851 submissions, 30%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
212
Total Downloads

Downloads (Last 12 months)2
Downloads (Last 6 weeks)2

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kim KLee KChua TNgo CKa-Wei Lee RKumar RLauw H(2024)Making Cloud Spot Instance Interruption Events VisibleProceedings of the ACM Web Conference 202410.1145/3589334.3645548(2998-3009)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645548
Xu ZPan LLiu S(2024)An Online Algorithm Based on Replication for Using Spot Instances in IaaS CloudsJournal of Computer Science and Technology10.1007/s11390-023-1535-439:1(103-115)Online publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1007/s11390-023-1535-4
Lee SHwang JLee K(2022)SpotLake: Diverse Spot Instance Dataset Archive Service2022 IEEE International Symposium on Workload Characterization (IISWC)10.1109/IISWC55918.2022.00029(242-255)Online publication date: Nov-2022
https://doi.org/10.1109/IISWC55918.2022.00029
Yuhala PFelber PSchiavoni VTchana A(2021)Plinius: Secure and Persistent Machine Learning Model Training2021 51st Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)10.1109/DSN48987.2021.00022(52-62)Online publication date: Jun-2021
https://doi.org/10.1109/DSN48987.2021.00022
Khandelwal VChaturvedi AGupta C(2020)Amazon EC2 Spot Price Prediction Using Regression Random ForestsIEEE Transactions on Cloud Computing10.1109/TCC.2017.27801598:1(59-72)Online publication date: 1-Jan-2020
https://doi.org/10.1109/TCC.2017.2780159
Ristov SFahringer TPeer DPham TGusev MMas-Machuca C(2020)Resilient Techniques Against Disruptions of Volatile Cloud ResourcesGuide to Disaster-Resilient Communication Networks10.1007/978-3-030-44685-7_15(379-400)Online publication date: 23-Jul-2020
https://doi.org/10.1007/978-3-030-44685-7_15
Khandelwal VGupta CChaturvedi A(2018)Perceptive bidding strategy for Amazon EC2 spot instance marketMultiagent and Grid Systems10.3233/MGS-18028214:1(83-102)Online publication date: 16-Apr-2018
https://doi.org/10.3233/MGS-180282
Shastri SIrwin D(2018)Cloud Index TrackingProceedings of the ACM Symposium on Cloud Computing10.1145/3267809.3267821(451-463)Online publication date: 11-Oct-2018
https://dl.acm.org/doi/10.1145/3267809.3267821
Wang CLiang QUrgaonkar B(2018)An Empirical Analysis of Amazon EC2 Spot Instance Features Affecting Cost-Effective Resource ProcurementACM Transactions on Modeling and Performance Evaluation of Computing Systems10.1145/31645383:2(1-24)Online publication date: 22-Mar-2018
https://dl.acm.org/doi/10.1145/3164538
Pham TRistov SFahringer T(2018)Performance and Behavior Characterization of Amazon EC2 Spot Instances2018 IEEE 11th International Conference on Cloud Computing (CLOUD)10.1109/CLOUD.2018.00017(73-81)Online publication date: Jul-2018
https://doi.org/10.1109/CLOUD.2018.00017
Show More Cited By

View Options

Login options

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

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten