Performance evaluation of Amazon EC2 Zhonghong Ou Post-doc researcher Data Communications Software (DCS) Lab, Department of Computer Science and Engineering,

Slides:

Advertisements

Similar presentations

Tuning of Loop Cache Architectures to Programs in Embedded System Design Susan Cotterell and Frank Vahid Department of Computer Science and Engineering.

Advertisements

Performance Evaluation of Cache Replacement Policies for the SPEC CPU2000 Benchmark Suite Hussein Al-Zoubi.

Hadi Goudarzi and Massoud Pedram

Dynamic Thread Assignment on Heterogeneous Multiprocessor Architectures Pree Thiengburanathum Advanced computer architecture Oct 24,

SLA-Oriented Resource Provisioning for Cloud Computing

Towards Efficient Wavefront Parallel Encoding of HEVC: Parallelism Analysis and Improvement Keji Chen, Yizhou Duan, Jun Sun, Zongming Guo 2014 IEEE 16th.

Difference Engine: Harnessing Memory Redundancy in Virtual Machines by Diwaker Gupta et al. presented by Jonathan Berkhahn.

Virtual Machine Usage in Cloud Computing for Amazon EE126: Computer Engineering Connor Cunningham Tufts University 12/1/14 “Virtual Machine Usage in Cloud.

Performance Anomalies Within The Cloud 1 This slide includes content from slides by Venkatanathan Varadarajan and Benjamin Farley.

1 Distributed Systems Meet Economics: Pricing in Cloud Computing Hadi Salimi Distributed Systems Lab, School of Computer Engineering, Iran University of.

CSC457 Seminar YongKang Zhu December 6 th, 2001 About Network Processor.

st International Conference on Parallel Processing (ICPP)

Automatic Resource Scaling for Web Applications in the Cloud Ching-Chi Lin Institute of Information Science, Academia Sinica Department of Computer Science.

COMMA: Coordinating the Migration of Multi-tier applications 1 Jie Zheng* T.S Eugene Ng* Kunwadee Sripanidkulchai† Zhaolei Liu* *Rice University, USA †NECTEC,

1 Routing and Scheduling in Web Server Clusters. 2 Reference The State of the Art in Locally Distributed Web-server Systems Valeria Cardellini, Emiliano.

Lincoln University Canterbury New Zealand Evaluating the Parallel Performance of a Heterogeneous System Elizabeth Post Hendrik Goosen formerly of Department.

Considerations for Mondriaan-like Systems 2009 Workshop on Duplicating, Deconstructing, and Debunking Emmett Witchel University of Texas at Austin.

Experimental Evaluation in Computer Science: A Quantitative Study Paul Lukowicz, Ernst A. Heinz, Lutz Prechelt and Walter F. Tichy Journal of Systems and.

Chia-Yen Hsieh Laboratory for Reliable Computing Microarchitecture-Level Power Management Iyer, A. Marculescu, D., Member, IEEE IEEE Transaction on VLSI.

Maximizing Classifier Utility when Training Data is Costly Gary M. Weiss Ye Tian Fordham University.

Disco Running Commodity Operating Systems on Scalable Multiprocessors.

Distributed Systems Meet Economics: Pricing In The Cloud Authors: Hongyi Wang, Qingfeng Jing, Rishan Chen, Bingsheng He, Zhengping He, Lidong Zhou Presenter:

Engineering the Cloud Andrew McCombs March 10th, 2011.

Memory Allocation via Graph Coloring using Scratchpad Memory

CSE598C Virtual Machines and Their Applications Operating System Support for Virtual Machines Coauthored by Samuel T. King, George W. Dunlap and Peter.

1 Integrating a Network IDS into an Open Source Cloud Computing Environment 1st International Workshop on Security and Performance in Emerging Distributed.

“Early Estimation of Cache Properties for Multicore Embedded Processors” ISERD ICETM 2015 Bangkok, Thailand May 16, 2015.

Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical.

GENI-related research activities of CSE, Aalto Zhonghong Ou Post-doc researcher Department of Computer Science and Engineering.

WEB ENGINEERING LECTURE 4 BY Kiramat Rahman. outline  In this Lecture you will learn about:  Term “Software” and its relationship with “Hardware” 

A Cloud is a type of parallel and distributed system consisting of a collection of inter- connected and virtualized computers that are dynamically provisioned.

Data Center Virtualization: Xen and Xen-blanket

Virtualization. Virtualization  In computing, virtualization is a broad term that refers to the abstraction of computer resources  It is "a technique.

2011/08/09 Sunwook Bae. Contents Paper Info Introduction Overall Architecture Resource Management Evaluation Conclusion References.

So, Jung-ki Distributed Computing System LAB School of Computer Science and Engineering Seoul National University Implementation of Package Management.

November , 2009SERVICE COMPUTATION 2009 Analysis of Energy Efficiency in Clouds H. AbdelSalamK. Maly R. MukkamalaM. Zubair Department.

An Autonomic Framework in Cloud Environment Jiedan Zhu Advisor: Prof. Gagan Agrawal.

1 Time & Cost Sensitive Data-Intensive Computing on Hybrid Clouds Tekin Bicer David ChiuGagan Agrawal Department of Compute Science and Engineering The.

A Framework for Elastic Execution of Existing MPI Programs Aarthi Raveendran Tekin Bicer Gagan Agrawal 1.

Introduction to Experimental Design

Hadi Salimi Distributed Systems Lab, School of Computer Engineering, Iran University of Science and Technology, Fall 2010 Performance.

A Framework for Elastic Execution of Existing MPI Programs Aarthi Raveendran Graduate Student Department Of CSE 1.

1 Instruction Sets and Beyond Computers, Complexity, and Controversy Brian Blum, Darren Drewry Ben Hocking, Gus Scheidt.

Our work on virtualization Chen Haogang, Wang Xiaolin {hchen, Institute of Network and Information Systems School of Electrical Engineering.

SMARTPHONE HARDWARE Mainak Chaudhuri

OPERATING SYSTEMS Lecture 3: we will explore the role of the operating system in a computer Networks and Communication Department 1.

Job scheduling algorithm based on Berger model in cloud environment Advances in Engineering Software (2011) Baomin Xu,Chunyan Zhao,Enzhao Hua,Bin Hu 2013/1/251.

King Fahd University of Petroleum and Minerals King Fahd University of Petroleum and Minerals Computer Engineering Department Computer Engineering Department.

Deconstructing Storage Arrays Timothy E. Denehy, John Bent, Florentina I. Popovici, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau University of Wisconsin,

Introducing Virtualization via an OpenStack “Cloud” System to SUNY Orange Applied Technology Students SUNY Innovative Instruction Technology Grant Christopher.

Min Lee, Vishal Gupta, Karsten Schwan

Shanjiang Tang, Bu-Sung Lee, Bingsheng He, Haikun Liu School of Computer Engineering Nanyang Technological University Long-Term Resource Fairness Towards.

June 30 - July 2, 2009AIMS 2009 Towards Energy Efficient Change Management in A Cloud Computing Environment: A Pro-Active Approach H. AbdelSalamK. Maly.

Design Issues of Prefetching Strategies for Heterogeneous Software DSM Author :Ssu-Hsuan Lu, Chien-Lung Chou, Kuang-Jui Wang, Hsiao-Hsi Wang, and Kuan-Ching.

An Automated Development Framework for a RISC Processor with Reconfigurable Instruction Set Extensions Nikolaos Vassiliadis, George Theodoridis and Spiridon.

1 Efficient Mixed-Platform Clouds Phillip B. Gibbons, Intel Labs Michael Kaminsky, Michael Kozuch, Padmanabhan Pillai (Intel Labs) Gregory Ganger, David.

3/12/2013Computer Engg, IIT(BHU)1 CLOUD COMPUTING-2.

1 An Execution-Driven Simulation Tool for Teaching Cache Memories in Introductory Computer Organization Courses Salvador Petit, Noel Tomás Computer Engineering.

EuroSys Doctoral Workshop 2011 Resource Provisioning of Web Applications in Heterogeneous Cloud Jiang Dejun Supervisor: Guillaume Pierre

Practical IT Research that Drives Measurable Results 1Info-Tech Research Group Get Moving with Server Virtualization.

Platform & Engineering Services CERN IT Department CH-1211 Geneva 23 Switzerland t PES Agile Infrastructure Project Overview : Status and.

Usage Of Cloud Computing Simulators And Future Systems In Computational Research Dr. Ramkumar Lakshminarayanan Mr. Rajasekar Ramalingam.

OPERATING SYSTEMS CS 3502 Fall 2017

Collecting, cataloguing and searching performance information of Cloud resources. Olaf Elzinga.

| A Comparative Study on I/O Performance between Compute and Storage Optimized Instances of Amazon.

Amazon Web Services Submitted By- Section - B Group - 4

The Problem Finding a needle in haystack An expert (CPU)

Hui Chen, Shinan Wang and Weisong Shi Wayne State University

Sorin Manolache, Petru Eles, Zebo Peng {sorma, petel,

Presentation transcript:

Performance evaluation of Amazon EC2 Zhonghong Ou Post-doc researcher Data Communications Software (DCS) Lab, Department of Computer Science and Engineering, Aalto University Zhonghong Ou 26/09/2014

Outline Motivation Experimental configuration Experimental results –Micro-benchmark –Application benchmark Cost analysis Conclusion & future work Zhonghong Ou 2

Motivation Cloud computing attracts attention because of –Pay-as-you-go –Theoretically unlimited resource –Reduced Capital Expenditure (CAPEX) and Operating Expense (OPEX) –And more… Amazon EC2 –Introduced in 2006 –Provisioning various categories of instances, diversified types of instances within the same category Hardware heterogeneity likely from –Hardware upgrade and replacement Research problems –Homogeneous vs. heterogeneous? –Performance variation? 3 Zhonghong Ou

Experimental configurations 4 Zhonghong Ou CPUID –Non-trapping instruction Confirmed with –cat /proc/cpuinfo Collected info from Amazon EC2 for two periods of time –Apr. – Jul –Jan. – Mar –200 instances collected for each instance type Micro-benchmark –CPU performance: UnixBench –Memory performance: Redis –Disk performance: Dbench Application benchmark –Httperf

Hardware information 5 Zhonghong Ou Released: E5507: Q1'10 E5430: Q4'07 E5645: Q1' HE:Q3’06 Newer processor models replace older ones progressively Hardware info varies significantly among different availability zones

Outline Motivation Experimental configuration Experimental results –Micro-benchmark CPU performance: UnixBench Memory performance: Redis Disk performance: Dbench –Application benchmark Httperf Cost analysis Conclusion & future work Zhonghong Ou 6

CPU performance: UnixBench 7 Zhonghong Ou

Memory performance: Redis 8 Zhonghong Ou

Disk performance: Dbench 9 Zhonghong Ou Shows similar results as UnixBench and Redis E5645 is approximately 1.25 times better than E5507 E5430 is comparable to E5507

Application performance: Httperf 10 Zhonghong Ou E5645 is 1.6 times as efficient as E5507 E5430 is 1.2 times as E5507

Cost analysis 11 Zhonghong Ou Saving money by seeking for better performing instances, simply using “trial-and-failure” method –Applying for instances randomly; –Checking if performing well; –If not, drop and apply for new ones.

Cost analysis (cont.d) 12 Zhonghong Ou P: probability of the better- performing instance in the overall instances

Conclusion Amazon EC2 uses diversified hardware to host the same type of instance. The hardware diversity results in performance variation. In general, the variation between the fast instances and slow instances can reach 40%. In some applications, the variation can even approach up to 60%. By selecting fast instances within the same instance type, Amazon EC2 users can acquire up to 30% of cost saving, if the fast instances have a relatively low probability. 13 Zhonghong Ou

Reference Z. Ou, H. Zhuang, J.K. Nurminen, A. Ylä-Jääski and P. Hui. Exploiting Hardware Heterogeneity within the Same Instance Type of Amazon EC2. The 4th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud '12) (acceptance rate: 24/75) (covered by BBC News, The Register, ACM TechNews etc). Z. Ou, H. Zhuang, A. Lukyanenko, J.K. Nurminen, P. Hui, V. Mazalov, A. Ylä-Jääski. Is the Same Instance Type Created Equal? Exploiting Heterogeneity of Public Clouds. IEEE Transactions on Cloud Computing, Volume 1, Issue 2, 2013, pages: 201 – 214. H. Zhuang, X. Liu, Z. Ou, K. Aberer. Impact of Instance Seeking Strategies on Resource Allocation in Cloud Data Centers. IEEE 6th International Conference on Cloud Computing (IEEE Cloud 2013) (acceptance ratio 18%). 2/19/2010 Word template user guide 14