Profile Driven Component Placement for Cluster-based Online Services Christopher Stewart (University of Rochester) Kai Shen (University of Rochester) Sandhya.

Slides:



Advertisements
Similar presentations
Scheduling in Web Server Clusters CS 260 LECTURE 3 From: IBM Technical Report.
Advertisements

University of Minnesota Optimizing MapReduce Provisioning in the Cloud Michael Cardosa, Aameek Singh†, Himabindu Pucha†, Abhishek Chandra
SLA-Oriented Resource Provisioning for Cloud Computing
Comprehensive Depiction of Configuration-dependent Performance Anomalies in Distributed Server Systems Christopher Stewart, Ming Zhong, Kai Shen, and Thomas.
Cloud Computing Resource provisioning Keke Chen. Outline  For Web applications statistical Learning and automatic control for datacenters  For data.
Helper Threads via Virtual Multithreading on an experimental Itanium 2 processor platform. Perry H Wang et. Al.
VSphere vs. Hyper-V Metron Performance Showdown. Objectives Architecture Available metrics Challenges in virtual environments Test environment and methods.
Green Cloud Computing Hadi Salimi Distributed Systems Lab, School of Computer Engineering, Iran University of Science and Technology,
CloudScale: Elastic Resource Scaling for Multi-Tenant Cloud Systems Zhiming Shen, Sethuraman Subbiah, Xiaohui Gu, John Wilkes.
Efficient Autoscaling in the Cloud using Predictive Models for Workload Forecasting Roy, N., A. Dubey, and A. Gokhale 4th IEEE International Conference.
Performance Engineering Methodology Chapter 4. Performance Engineering Performance engineering analyzes the expected performance characteristics of a.
NUMA Tuning for Java Server Applications Mustafa M. Tikir.
H.264/AVC Baseline Profile Decoder Complexity Analysis Michael Horowitz, Anthony Joch, Faouzi Kossentini, and Antti Hallapuro IEEE TRANSACTIONS ON CIRCUITS.
Karl Schnaitter and Neoklis Polyzotis (UC Santa Cruz) Serge Abiteboul (INRIA and University of Paris 11) Tova Milo (University of Tel Aviv) Automatic Index.
Fair Scheduling in Web Servers CS 213 Lecture 17 L.N. Bhuyan.
Handling Web Hotspots at Dynamic Content Web Sites Using DotSlash Weibin Zhao Henning Schulzrinne Columbia University Dagstuhl.
Yaksha: A Self-Tuning Controller for Managing the Performance of 3-Tiered Web Sites Abhinav Kamra, Vishal Misra CS Department Columbia University Erich.
© 2008 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice Automated Workload Management in.
1 Exploring Data Reliability Tradeoffs in Replicated Storage Systems NetSysLab The University of British Columbia Abdullah Gharaibeh Matei Ripeanu.
Power Containers: An OS Facility for Fine-Grained Power and Energy Management on Multicore Servers Kai Shen, Arrvindh Shriraman, Sandhya Dwarkadas, Xiao.
U NIVERSITY OF M ASSACHUSETTS, A MHERST Department of Computer Science Black-box and Gray-box Strategies for Virtual Machine Migration Timothy Wood, Prashant.
Computer Science 1 Resource Overbooking and Application Profiling in Shared Hosting Platforms Bhuvan Urgaonkar Prashant Shenoy Timothy Roscoe † UMASS Amherst.
Generating Adaptation Policies for Multi-Tier Applications in Consolidated Server Environments College of Computing Georgia Institute of Technology Gueyoung.
Self-Adaptive QoS Guarantees and Optimization in Clouds Jim (Zhanwen) Li (Carleton University) Murray Woodside (Carleton University) John Chinneck (Carleton.
AUTONOMOUS RESOURCE PROVISIONING FOR MULTI-SERVICE WEB APPLICATIONS Jiang Dejun,Guillaume Pierre,Chi-Hung Chi WWW '10 Proceedings of the 19th international.
Adaptive Control of Virtualized Resources in Utility Computing Environments HP Labs: Xiaoyun Zhu, Mustafa Uysal, Zhikui Wang, Sharad Singhal University.
An Analytical Performance Model for Co-Management of Last-Level Cache and Bandwidth Sharing Taecheol Oh, Kiyeon Lee, and Sangyeun Cho Computer Science.
Database Replication Policies for Dynamic Content Applications Gokul Soundararajan, Cristiana Amza, Ashvin Goel University of Toronto EuroSys 2006: Leuven,
AUTHORS: STIJN POLFLIET ET. AL. BY: ALI NIKRAVESH Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload.
Profiling and Modeling Resource Usage of Virtualized Applications Timothy Wood 1, Ludmila Cherkasova 2, Kivanc Ozonat 2, and Prashant Shenoy 1 1 University.
Workload-driven Analysis of File Systems in Shared Multi-Tier Data-Centers over InfiniBand K. Vaidyanathan P. Balaji H. –W. Jin D.K. Panda Network-Based.
An Efficient Approach for Content Delivery in Overlay Networks Mohammad Malli Chadi Barakat, Walid Dabbous Planete Project To appear in proceedings of.
1 CMG, 2006 Reno Yiping Ding and Ethan Bolker How Many Guests Can You Serve? - On the Number of Partitions.
© 2006 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice Profiling and Modeling Resource Usage.
1 Specification and Implementation of Dynamic Web Site Benchmarks Sameh Elnikety Department of Computer Science Rice University.
QoS Enabled Application Server The Controller Service Bologna, February 19 th 2004.
Performance Prediction for Random Write Reductions: A Case Study in Modelling Shared Memory Programs Ruoming Jin Gagan Agrawal Department of Computer and.
Federated Database Set Up Greg Magsamen ITK478 SIA.
Performance evaluation of component-based software systems Seminar of Component Engineering course Rofideh hadighi 7 Jan 2010.
Power Containers: An OS Facility for Fine-Grained Power and Energy Management on Multicore Servers Kai Shen, Arrvindh Shriraman, Sandhya Dwarkadas, Xiao.
Investigating the Effects of Using Different Nursery Sizing Policies on Performance Tony Guan, Witty Srisa-an, and Neo Jia Department of Computer Science.
Towards Dynamic Green-Sizing for Database Servers Mustafa Korkmaz, Alexey Karyakin, Martin Karsten, Kenneth Salem University of Waterloo.
VGreen: A System for Energy Efficient Manager in Virtualized Environments G. Dhiman, G Marchetti, T Rosing ISLPED 2009.
1 Admission Control and Request Scheduling in E-Commerce Web Sites Sameh Elnikety, EPFL Erich Nahum, IBM Watson John Tracey, IBM Watson Willy Zwaenepoel,
Ó 1998 Menascé & Almeida. All Rights Reserved.1 Part V Workload Characterization for the Web.
1 Exploiting Nonstationarity for Performance Prediction Christopher Stewart (University of Rochester) Terence Kelly and Alex Zhang (HP Labs)
Network Weather Service. Introduction “NWS provides accurate forecasts of dynamically changing performance characteristics from a distributed set of metacomputing.
EuroSys Doctoral Workshop 2011 Resource Provisioning of Web Applications in Heterogeneous Cloud Jiang Dejun Supervisor: Guillaume Pierre
CHARACTERIZING CLOUD COMPUTING HARDWARE RELIABILITY Authors: Kashi Venkatesh Vishwanath ; Nachiappan Nagappan Presented By: Vibhuti Dhiman.
1 Performance Modeling and System Management for Multi-Component Online Services Christopher Stewart and Kai Shen University of Rochester.
Scientific days, June 16 th & 17 th, 2014 This work has been partially supported by the LabEx PERSYVAL-Lab (ANR-11-LABX ) funded by the French program.
If you have a transaction processing system, John Meisenbacher
Cloud Computing: Pay-per-Use for On-Demand Scalability Developing Cloud Computing Applications with Open Source Technologies Shlomo Swidler.
1
Spark on Entropy : A Reliable & Efficient Scheduler for Low-latency Parallel Jobs in Heterogeneous Cloud Huankai Chen PhD Student at University of Kent.
Dynamic Resource Allocation for Shared Data Centers Using Online Measurements By- Abhishek Chandra, Weibo Gong and Prashant Shenoy.
Resource Specification Prediction Model Richard Huang joint work with Henri Casanova and Andrew Chien.
Abhinav Kamra, Vishal Misra CS Department Columbia University
Diskpool and cloud storage benchmarks used in IT-DSS
IBM Tivoli Web Site Analyzer Training Document
CARP: Context-Aware Reliability Prediction of Black-Box Web Services
Standards and Patterns for Dynamic Resource Management
Evaluating Transaction System Performance
Admission Control and Request Scheduling in E-Commerce Web Sites
Dept. of Computer Science, Univ. of Rochester
QuaSAQ: Enabling End-to-End QoS for Distributed Multimedia Databases
Hardware Counter Driven On-the-Fly Request Signatures
Software Acceleration in Hybrid Systems Xiaoqiao (XQ) Meng IBM T. J
Request Behavior Variations
Fabric metrics Qi Zhang(IBM Research – T.J. Watson) Hardware Software
Presentation transcript:

Profile Driven Component Placement for Cluster-based Online Services Christopher Stewart (University of Rochester) Kai Shen (University of Rochester) Sandhya Dwarkadas (University of Rochester) Michael Scott (University of Rochester) Jian Yin (IBM TJ Watson)

Large Distributed Online Services Amazon, EBay, Google, Citrix, etc. Implemented via many distinct single- purpose components  Developers use common interface Service demands affect the bottom line  Sustained Throughput  Response time, Reliability, etc. Hardware costs affect bottom line. How can we optimize transparently?

Component Placement Is system performance affected by component placement? Can we determine the maximal throughput placement? Given a complex service divided into N components distributed among M machines:

Our Solution 1. Build component profiles 2. Ascertain workload and available resources 3. Estimate throughput for all settings (or use heuristic) 4. Setting with largest throughput estimate is optimal Web Server WS Business Logic A A Business Logic B B Database DB Component Resource Consumption Profiles Available resources and workload Placement Decisions Placement Executive Runtime environment for a cluster-based online services Offline

Component Profiles Characterize resource consumption per component Acquired via offline examination Contain information on the following resources  CPU Consumption (average, peak)  Memory Usage (peak)  Network Consumption (average, peak) Derived from proc file system We hypothesize resource consumption grows linearly with workload (requests per second).

Profile Validation Resulting component profile: Workload (requests/second) average average linear fitting peak peak linear fitting CPU usage (in percentage) Network usage (in Mb) Resource consumption is proportional to workload.

Predicting Throughput For any given placement: A server reaches maximum throughput when a resource saturates Using component profiles, we predict resource consumption over all components on the server  CPU consumption = CPU per-request * Workload + CPU overhead A workload is non-saturating iff  CPU saturation > CPU per-request * Workload + CPU overhead CPU max : Largest non-saturating workload TP = MIN[ CPU max, MEM max, NET max ] of all servers

Experimental Setup RUBiS [Amza et al., 2002]  Auction benchmark modeled after EBay  11 Components : Web server, Database, and 9 Enterprise Java Beans. 2 Machine setup  1.26 GHz, 2 GB Memory, JBOSS, and MySql  Business logic: No replication, Static database and web server Compare 4 Placement Strategies  All on web, All on DB, Writer’s with Web, and Profiler’s choice

Impact of Placement Input workload (requests/second) All with Web All with database Writers with Web Profiler‘s choice Throughput (requests/second) We Observe: Placement affects maximal throughput by 38% Profiler’s choice exceeds other strategies by % We Conclude: Component placement can significantly affect performance. Component Profiles can choose a good placement strategy.

Prediction Accuracy AllWebAllDBWritersWebProfiler Pessimistic estimation Measurement result Optimistic estimation Throughput (requests/decond) We Observe: Throughput tends to fall between peak and average predictions Large ranges We Conclude: Component profile predictions are generally accurate More accurate measurement tools are needed.

Future Work Improve Prediction Accuracy Use profiles for other QoS metrics and service needs  response time, service differentiation, and capacity planning Dynamic placement decisions  Adjust to changing workloads online  Support plug and play hardware modifications Placement over wide area networks  Extend edge servers for optimal performance

Take Away Points 1. Component placement has a significant impact upon performance in online services. 2. Component profiles capture resource consumption characteristics 3. Resource consumption and throughput can be predicted via component profiles

More Information