University of Michigan Electrical Engineering and Computer Science Anatomizing Application Performance Differences on Smartphones Junxian Huang, Qiang.

Slides:



Advertisements
Similar presentations
Cost-Based Cache Replacement and Server Selection for Multimedia Proxy Across Wireless Internet Qian Zhang Zhe Xiang Wenwu Zhu Lixin Gao IEEE Transactions.
Advertisements

1 The ns-2 Network Simulator H Plan: –Discuss discrete-event network simulation –Discuss ns-2 simulator in particular –Demonstration and examples: u Download,
MicroCast: Cooperative Video Streaming on Smartphones Lorenzo Keller, Anh Le, Blerim Cic, Hulya Seferoglu LIDS, Christina Fragouli, Athina Markopoulou.
CSE 6590 Department of Computer Science & Engineering York University 1 Introduction to Wireless Ad-hoc Networking 5/4/2015 2:17 PM.
Obtaining In-Context Measurements of Cellular Network Performance Aaron Gember, Aditya Akella University of Wisconsin-Madison Jeffrey Pang, Alexander Varshavsky,
Broadband Internet Performance: A View from the Gateway Srikanth Sundaresan, Walter de Donato, Nick Feamster, Renata Teixeira, Sam Crawford, Antonio Pescapè.
Demystifying Page Load Performance with WProf Aruna Balasubramanian With Xiao (Sophia) Wang, Arvind Krishnamurthy, and David Wetherall University of Washington.
Junxian Huang Feng Qian Alexandre Gerber Z. Morley Mao Subhabrata Sen Oliver Spatscheck University of Michigan AT&T Labs - Research Presented by Tianxiong.
Broadband Internet Performance: A View from the Gateway Srikanth Sundaresan, Walter de Donato, Nick Feamster, Renata Teixeira, Sam Crawford, Antonio Pescapè.
Application, Network and Link Layer Measurements of Streaming Video over a Wireless Campus Network Passive & Active Measurement Workshop 05 Boston, MA,
How’s My Network (HMN)? A Java approach to Home Network Measurement Alan Ritacco, Craig Wills, and Mark Claypool Computer Science Department Worcester.
Performance Analysis of Orb Rabin Karki and Thangam V. Seenivasan 1.
Performance Analysis of the Intertwined Effects between Network Layers for g Transmissions Wireless Multimedia Networking and Performance Modeling.
1 A Framework for Lazy Replication in P2P VoD Bin Cheng 1, Lex Stein 2, Hai Jin 1, Zheng Zhang 2 1 Huazhong University of Science & Technology (HUST) 2.
Windows Streaming Media Performance Analysis on a IEEE g Residential Network The Seventh International Conferences on Wireless and Optical Communications.
Characterization by Measurement of a CDMA 1x EVDO Network Presenter: Mingzhe Li Wireless Internet Conference (WICON’06) Boston, Massachusetts,
1 Drafting Behind Akamai (Travelocity-Based Detouring) AoJan Su, David R. Choffnes, Aleksandar Kuzmanovic, and Fabian E. Bustamante Department of Electrical.
CDMA X RTT Overview. Global 3G Evolution.
V1.00 © 2009 Research In Motion Limited Introduction to Mobile Device Web Development Trainer name Date.
Performance Comparison of Congested HTTP/2 Links Brian Card, CS /7/
Effects of a Bad Channel on the overall WLAN Performance. CS577 Advanced Networking Spring 05 Ashish Samant, Jon Gretarsson, Feng Li {Asamant, jontg,
Comparison of Routing Metrics for a Static Multi-Hop Wireless Network Richard Draves, Jitendra Padhye, Brian Zill Microsoft Research Presented by: Jón.
The Future of the Internet Jennifer Rexford ’91 Computer Science Department Princeton University
Performance Analysis of the Intertwined Effects between Network Layers for g Transmissions Wireless Multimedia Networking and Performance Modeling.
Putting the Network to Work
SG12 Regional Group for Africa Meeting 18 th to 19 th of July, 2013 Ouagadougou, Burkinafaso By Yvonne UMUTONI Quality of Service Development Group (QSDG)
Junxian Huang 1 Feng Qian 2 Yihua Guo 1 Yuanyuan Zhou 1 Qiang Xu 1 Z. Morley Mao 1 Subhabrata Sen 2 Oliver Spatscheck 2 1 University of Michigan 2 AT&T.
WEB SCIENCE: SEARCHING THE WEB. Basic Terms Search engine Software that finds information on the Internet or World Wide Web Web crawler An automated program.
Timecard: Controlling User-Perceived Delays in Server-Based Mobile Applications Lenin Ravindranath, Jitu Padhye, Ratul Mahajan, Hari Balakrishnan.
All rights reserved © 2006, Alcatel Accelerating TCP Traffic on Broadband Access Networks  Ing-Jyh Tsang 
TCP Behavior across Multihop Wireless Networks and the Wired Internet Kaixin Xu, Sang Bae, Mario Gerla, Sungwook Lee Computer Science Department University.
Niranjan Balasubramanian Aruna Balasubramanian Arun Venkataramani University of Massachusetts Amherst Energy Consumption in Mobile Phones: A Measurement.
A Credit-based Home Access Point (CHAP) to Improve Application Performance on IEEE Networks Choong-Soo Lee, Mark Claypool and Robert Kinicki In.
A measurement study of vehicular internet access using in situ Wi-Fi networks Vladimir Bychkovsky, Bret Hull, Allen Miu, Hari Balakrishnan, and Samuel.
 Zhichun Li  The Robust and Secure Systems group at NEC Research Labs  Northwestern University  Tsinghua University 2.
DNN Performance & Scalability Planning, Evaluating & Improving : Part 2.
Characterizing and Modeling the Impact of Wireless Signal Strength on Smartphone Battery Drain Ning Ding Xiaomeng Chen Abhinav Pathak Y. Charlie Hu 1 Daniel.
Krerk Piromsopa. Advance Net-Centric Computing Technology Krerk Piromsopa. Department of Computer Engineering. Chulalongkorn University.
Global NetWatch Copyright © 2003 Global NetWatch, Inc. Factors Affecting Web Performance Getting Maximum Performance Out Of Your Web Server.
Best-Case WiBro Performance for a Single Flow 1 MICNET 2009 Shinae Woo †, Keon Jang †, Sangman Kim † Soohyun Cho *, Jaehwa Lee *, Youngseok Lee ‡, Sue.
A First Look at Traffic on Smartphones Hossein Falaki Dimitrios Lymberopoulos Ratul Mahajan Srikanth Kandula Deborah Estrin.
Snooze: Energy Management in n WLANs Ki-Young Jang, Shuai Hao, Anmol Sheth, Ramesh Govindan.
1 Dr. Jim Martin Associate Professor School of Computing Clemson University Networking Lab’s.
1 Requirements for the Transmission of Streaming Video in Mobile Wireless Networks Vasos Vassiliou, Pavlos Antoniou, Iraklis Giannakou, and Andreas Pitsillides.
Module 4: Fundamentals of Communication Technologies.
Understanding the Performance of TCP Pacing Amit Aggarwal, Stefan Savage, Thomas Anderson Department of Computer Science and Engineering University of.
CING-YU CHU INFOCOM Outline  Introduction  Measurement  Measurement Results  Modeling Skype Behaviors  Analysis on TCP-friendly.
A Measurement Based Memory Performance Evaluation of High Throughput Servers Garba Isa Yau Department of Computer Engineering King Fahd University of Petroleum.
Timecard: Controlling User-Perceived Delays in Server-Based Mobile Applications Lenin Ravindranath, Jitu Padhye, Ratul Mahajan, Hari Balakrishnan.
Opportunistic Use of Client Repeaters to Improve Performance of WLANs Victor Bahl 1, Ranveer Chandra 1, Patrick P. C. Lee 2, Vishal Misra 2, Jitendra Padhye.
1 Measuring Congestion Responsiveness of Windows Streaming Media James Nichols Advisors: Prof. Mark Claypool Prof. Bob Kinicki Reader: Prof. David Finkel.
Multicast instant channel change in IPTV systems 1.
1 1 July 28, Goal of this session is too have a discussion where we learn about the relevant data to help us understand the problem and design.
Measuring and Mitigating Web Performance Bottlenecks in Broadband Access Networks Srikanth Sundaresan, Nick Feamster (Georgia Tech) Renata Teixeira (Inria)
PROTEUS: Network Performance Forecast for Real- Time, Interactive Mobile Applications Qiang Xu* Sanjeev Mehrotra# Z. Morley Mao* Jin Li# *University of.
Profiling Resource Usage for Mobile Applications: a Cross-layer Approach Feng Qian 1, Zhaoguang Wang 1, Alexandre Gerber 2, Z. Morley Mao 1, Subhabrata.
A Credit-based Home Access Point (CHAP) to Improve Application Quality on IEEE Networks Choong-Soo Lee Ph.D. Dissertation Defense Worcester Polytechnic.
Characterizing Radio Resource Allocation for 3G Networks Feng Qian* Zhaoguang Wang* Alexandre Gerber † Z. Morley Mao* Subhabrata Sen † Oliver Spatscheck.
A Measurement Based Memory Performance Evaluation of Streaming Media Servers Garba Isa Yau and Abdul Waheed Department of Computer Engineering King Fahd.
Emir Halepovic, Jeffrey Pang, Oliver Spatscheck AT&T Labs - Research
Periodic Transfers in Mobile Applications: Network-wide Origin, Impact, and Optimization Feng Qian 1, Zhaoguang Wang 1, Yudong Gao 1, Junxian Huang 1 Alexandre.
Development of a QoE Model Himadeepa Karlapudi 03/07/03.
1 Evaluation of Cooperative Web Caching with Web Polygraph Ping Du and Jaspal Subhlok Department of Computer Science University of Houston presented at.
WHAT'S THE DIFFERENCE BETWEEN A WEB APPLICATION STREAMING NETWORK AND A CDN? INSTART LOGIC.
Performance Evaluation of Redirection Schemes in Content Distribution Networks Jussi Kangasharju, Keith W. Ross Institut Eurecom Jim W. Roberts France.
Efficient Opportunistic Sensing using Mobile Collaborative Platform MOSDEN.
Obtaining In-Context Measurements of Cellular Network Performance Aaron Gember, Aditya Akella University of Wisconsin-Madison Jeffrey Pang, Alexander Varshavsky,
SAFARI TEST AUTOMATION: NAVIGATING THROUGH THE JUNGLE BY KARAN KUMAR AND JAMES CHUONG.
For more course tutorials visit NTC 406 Entire Course NTC 406 Week 1 Individual Assignment Network Requirements Analysis Paper NTC 406.
PredictRemainingTime
Presentation transcript:

University of Michigan Electrical Engineering and Computer Science Anatomizing Application Performance Differences on Smartphones Junxian Huang, Qiang Xu, Birjodh Tiwana, Z. Morley Mao University of Michigan Ming Zhang, Victor Bahl Microsoft Research

University of Michigan Electrical Engineering and Computer Science Smartphones are popular  Various smartphone platforms  Many applications  High speed network access  3G (UMTS & EVDO)  4G (LTE) 1

University of Michigan Electrical Engineering and Computer Science Understanding application performance is important 2 AT&T T-Mobile Verizon

University of Michigan Electrical Engineering and Computer Science  User coverage vs. collected information Design tradeoff in smartphone measurement 3 User coverage More info Fewer users More info Fewer users Less info More users Less info More users Collected information Speedtest.net FCC’s broadband test Speedtest.net FCC’s broadband test Liu, MobiCom 2008 Zhong, HotMetrics 2010 Willkomm, DySPAN 2008 Our study

University of Michigan Electrical Engineering and Computer Science Our contributions  3GTest  Widely deployed  Provide new insights into cellular network performance  A systematic methodology to understand application performance  Isolate individual factors  Enable fair comparisons  Identify performance bottlenecks  Offer concrete recommendations for improvements 4

University of Michigan Electrical Engineering and Computer Science Outline  Cellular network performance study  3GTest design  3GTest results  Web performance analysis  Experimental methodology & setup  Web performance results  Streaming video & VoIP performance study  Conclusion 5

University of Michigan Electrical Engineering and Computer Science Key challenges of 3GTest  Adoptability  User privacy  Running time  Ease of use  Energy consumption  Data usefulness  Metrics relevant to network applications 6

University of Michigan Electrical Engineering and Computer Science How to make 3GTest easily adoptable?  Avoid personal identifiable information 7

University of Michigan Electrical Engineering and Computer Science What information is most relevant for 3GTest? 8 Smartphone Local DNS server Web server example.com? Get index.html Ping to 1 st hop End-end ping

University of Michigan Electrical Engineering and Computer Science Representativeness of 3GTest data 66K+ users 148K+ runs 84 carriers 147 countries over 10 months 9

University of Michigan Electrical Engineering and Computer Science Throughput comparison 10 CDF T- Mobile:600 kbps AT&T 1Mbps AT&T 1Mbps

University of Michigan Electrical Engineering and Computer Science RTT comparison 11 CDF T-Mobile 450ms T-Mobile 450ms AT&T 350ms AT&T 350ms

University of Michigan Electrical Engineering and Computer Science Retransmission rate comparison 12 CDF T-Mobile AT&T

University of Michigan Electrical Engineering and Computer Science Insights from 3GTest results  Local DNS server performance is good  200 ms comparable to ping to 1 st hop  Carrier network delay dominates end-to-end RTT  End-end ping close to ping to 1 st hop  Time of day effect  AT&T’s downlink throughput  Signal strength correlates with TCP performance 13

University of Michigan Electrical Engineering and Computer Science Smartphone web browsing is complicated 14 Smartphone Local DNS server Web server DNS lookup Content customization TCP handshake TCP data transfer Server configuration Client configuration HTML rendering & JavaScript execution 5 5 Network condition Server processing delay 3 3

University of Michigan Electrical Engineering and Computer Science Key challenges of web performance analysis  Multiple factors have impact  Network condition  Client settings  Server configurations  Content differences  Lack of low-level information and access  No visibility into link layer  Difficult to instrument client OS and application  No access to public web servers 15

University of Michigan Electrical Engineering and Computer Science How to isolate impact of individual factor?  Vary one factor at a time  Network condition  Simulate cellular network with WiFi  Client settings  Control TCP concurrency  Server configurations  Change compression mode and server parallelism  Content difference  Host static website snapshots locally 16

University of Michigan Electrical Engineering and Computer Science How to identify performance bottlenecks?  TCP flow analysis technique to break down page load time  DNS lookup time  TCP handshake time  TCP idle time  TCP transfer time 17 index.html logo.png Time

University of Michigan Electrical Engineering and Computer Science Controlled experiment setup  Platform  Web browsing  Other applications 18

University of Michigan Electrical Engineering and Computer Science Simple website page load time break down 19 TCP idle time TCP transfer time

University of Michigan Electrical Engineering and Computer Science Content-rich website page load time break down 20 TCP idle time TCP transfer time

University of Michigan Electrical Engineering and Computer Science JavaScript execution comparison 21 PC 80X (CPU <10X)

University of Michigan Electrical Engineering and Computer Science Lessons from application performance study  Performance bottlenecks of web browsing  Client execution  Data download  Higher concurrency significantly improves performance  Compression is usually helpful  Content customization is beneficial  Data URL scheme  Minification  Minimal redirections  Video & VoIP  Platform specific application behaviors 22

University of Michigan Electrical Engineering and Computer Science Conclusion  3GTest for measuring cellular network performance  Deployed widely  Gain insights into cellular network performance  A systematic methodology to understand application performance  Isolate impact of individual factor  Identify performance bottlenecks  Offer recommendations on performance improvement 23

University of Michigan Electrical Engineering and Computer Science Visit 3GTest website 24 AndroidiPhoneWindows Mobile