CSE 592 - Internet Measurement (Fall 2013)

Instructor: Phillipa Gill
Time: MW 4-5:20
Location: Frey Hall Rm. 222 New location: Computer Science Rm. 2313A
Web forum: This term we will be using Piazza as a Web forum. Rather than emailing questions, I encourage you to post your questions on Piazza. Piazza also is a useful tool for finding partners for presentations and the course project. If you have any problems or feedback for the developers, email team@piazza.com. Find our class page at: https://piazza.com/stonybrook/fall2013/cse592/home

Announcements

• Presentation requirements have been updated. See below.
• Lecture 2 slides posted to Piazza. Class location moved to Computer Science 2313A.
• Lecture 1 slides posted to Piazza
• A list of potential topics has been posted on the Piazza site. Check it out!
• Information for Piazza (an online forum for the course) posted above.
• Initial course outline and information is posted.
• Course Web site is launched!

Description

This course will cover tools and techniques for measuring different facets of the Internet, ranging from application to network layer measurements. The course will center around readings of foundational and cutting edge research papers in the area of network measurement. By the end of the course, students will be well equipped to read and evaluate network measurement research and engage in research in this topic area.

Textbooks

There is no required textbook for the course, but the following may be a useful reference:

• Internet Measurement: Infrastructure, Traffic and Applications. by M. Crovella and B. Krishnamurthy.

Prerequisites

The course will assume basic familiarity with networking protocols (e.g., TCP, HTTP). The material is appropriate for students that have previously taken the graduate networking course, or equivalent.

Grading

• 20% Presentation
• 10% Participation
• 20% Paper summaries
• 50% Project

Schedule

Date	Presenter	Topics	Notes	Readings
8/26/2013	Phillipa	Administravia + Introduction		Note: It is not required to summarize these papers. They are meant as a useful resource as you read other papers in the course. How to Read A Paper. S. Keshav. Computer Communication Review (CCR) 2007 Strategies for Sound Internet Measurement. V. Paxson. IMC 2004. Issues and Etiquette Concerning Use of Shared Mesaurement Data. M. Allman and V. Paxson. IMC 2007. Reverse Engineering the Internet. N. Spring, D. Wetherall, and T. Anderson. Hotnets 2003. A Socratic Method for Validation of Measurement-based Networking Research. B. Krishnamurthy, W. Willinger, P. Gill, and M. Arlitt. Computer Communications. 2011.
8/28/2013	Phillipa	Internet Topology (review of Internet routing + paper discussion)	*Action item:* Send me a URL of your blog by end of the day. Data sets and tools: Routeviews UCLA Topology CAIDA IRL BGP Parser	On Power-Law Relationships of the Internet Topology. M. Faloutsos, P. Faloutsos, and C. Faloutsos. SIGCOMM 1999. 10 Lessons from 10 Years of Measuring and Modeling the Internet's Autonomous Systems. M. Roughan, W. Willinger, O. Maennel, D. Perouli, and R. Bush. Journal on Select Areas in Communications, 2011.
9/2/2013	Labor day
9/4/2013	Tzu-Wen	Internet Topology		Quantifying the Completeness of the Observed Internet AS-level Structure. R. Oliveira, D. Pei, W. Willinger, B. Zhang, and L. Zhang. UCLA Tech Report. 2008. Where the Sidewalk Ends: Extending the Internet AS Graph Using Traceroutes from P2P Users. K. Chen, D. Choffnes, R. Potharaju, Y. Chen, F. Bustamante, D. Pei, and Y. Zhao. CoNEXT '09. Optional: Bigfoot, Sasquatch, the Yeti, and Other Missing Links: What We Don't Know About the AS Graph. M. Roughan, J. Tuke, and O. Maennel. IMC 2008. The Flattening Internet Topology: Natural Evolution, Unsightly Barnacles or Contrived Collapse?. P. Gill, M. Arlitt, Z. Li, and A. Mahanti. PAM 2008
9/9/2013		Internet Topology (Internet eXchange Points)	Data sets/URLs: IXPs mapped data Packet Clearing House PeeringDB	IXPs: Mapped?. B. Augustin, B. Krishnamurthy, and W. Willinger. IMC 2009. Anatomy of a Large European IXP. B. Ager, N. Chatzis, A. Feldmann, N. Sarrar, S. Uhlig, and W. Willinger. SIGCOMM 2012.
9/11/2013		Improvements to Traceroute	Data sets: CAIDA Ark iPlane	Avoiding traceroute anomalies with Paris traceroute. B. Augustin, X. Cuvellier, B. Orgogozo, F. Viger, T. Friedman, M. Latapy, C. Magnien, and R. Teixeira. IMC 2006. Reverse Traceroute.. E. Katz-Bassett, H. Madhyastha, V. Adhikari, C. Scott, J. Sherry, P. van Wesep, A. Krishnamurthy, and T. Anderson. NSDI 2010. Optional: Understanding the Efficacy of Deployed Internet Source Address Validation Filtering. R. Beverly, A. Berger, Y. Hyun, and k claffy. IMC 2009.
9/16/2013	Haseeb	Transport Layer		An Analysis of TCP Reset Behavior on the Internet. M. Arlitt, and C. Williamson. Full version of paper that appeared in ACM CCR 2005. Trickle: Rate Limiting YouTube Video Streaming. M. Ghobadi, Y. Cheng, A. Jain, and M. Mathis. USENIX ATC 2012.
9/18/2013		Reliability (Edge networks)	Interesting URL: Outages mailing list	California Fault Lines: Understanding the Causes and Impact of Network Failures. D. Turner, K. Levchenko, A. Snoeren, and S. Savage. SIGCOMM 2010. Understanding Network Failures in Data Centers: Measurement, Analysis, and Implications. P. Gill, N. Jain, and N. Nagappan. SIGCOMM 2011. Optional A First Look at Problems in the Cloud. T. Benson, S. Sahu, A. Akella, and A. Shaikh. HotCloud 2010.
9/23/2013		Reliability (Backbone/ISP networks)	*Action item*: Project proposal due	Characterization of Failures in an Operational IP Backbone Network. A. Markopoulou, G. Iannacone, S. Bhattacharyya, C. Chuah, Y. Ganjali, and C. Diot. Transactions on Networking 2008. Experiences With Monitoring OSPF on a Regional Service Provider Network. D. Watson, and F. Jahanian, and C. Labovitz. ICDCS 2003. Optional: A Case Study of OSPF Behavior in a Large Enterprise Network. A. Shaikh, C. Isett, A. Greenberg, M. Roughan, and J. Gottlieb. IMW 2002.
9/25/2013		Reliability (End-to-end)		End-to-End Routing Behavior in the Internet. V. Paxson. Transactions on Networking 1997. A Study of End-to-End Web Access Failures. V. Padmanabhan, S. Ramabhadran, S. Agarwal, and J. Padhye. CoNEXT 2006.
9/30/2013	Class	Project elevator pitches
10/2/2013		Web workload characterization I	Data sets: The Internet Traffic Archive.	Web Server Workload Characterization: The Search for Invariants. M. Arlitt, and C. Williamson. SIGMETRICS 1996. Self-Similarity in World Wide Web Traffic: Evidence and Possible Causes. M. Crovella, and A. Bestavros. SIGMETRICS 1996. Optional: Web Workload Characterization: Ten Years Later. A. Williams, M. Arlitt, C. Williamson, and K. Barker. Book Chapter 2005.
10/7/2013		User Generated Content		YouTube Traffic Characterization: A View From the Edge. P. Gill, M. Arlitt, Z. Li, and A. Mahanti. IMC 2007 I Tube, You Tube, Everybody Tubes: Analyzing the World's Largest User Generated Content Video System. M. Cha, H. Kwak, P. Rodriguez, Y. Ahn, and S. Moon. IMC 2007 Optional: Broadcast Yourself: Understanding YouTube Uploaders. Y. Ding, Y. Du, Y. Hu, Z. Liu, L. Wang, K. Ross, and A. Ghose. IMC 2011.
10/9/2013	James	Online Social Networks		Understanding Online Social Network Usage from a Network Perspective. F. Schneider, A. Feldmann, B. Krishnamurthy, and W. Willinger. IMC 2009. Network Level Footprints of Facebook Applications. A. Nazir, S. Raza, D. Gupta, C. Chuah and B. Krishnamurthy. IMC 2009. Optional: Characterizing User Behavior in Online Social Networks. F. Benevenuto, T. Rodrigues, M. Cha, and V. Almeida. IMC 2009.
10/14/2013	Dung Fang	Web workload characterization II		Understanting Website Complexity: Measurements, Metrics, and Implications.. M. Butkiewicz, H. Madhyastha, and V. Sekar. IMC 2011. Towards Understanding Modern Web Traffic. S. Ihm, and V. Pai. IMC 2011.
10/16/2013		Peer-to-peer		Taming the Torrent: A Practical Approach to Reducing Cross-ISP Traffic in P2P Systems. D. Choffnes, and F. Bustamante. SIGCOMM 2008. On Blind Mice and the Elephant -- Understanding the Network Impact of a Large Distributed System. J. Otto, M. Sanchez, D. Choffnes, F. Bustamante, and G. Siganos. SIGCOMM 2011
10/21/2013	Abbas	Mobile (Provider's view)	Data sets: CRAWDAD	Identifying Diverse Usage Behaviors of Smartphone Apps. Q. Xu, J. Erman, A. Gerber, Z. Mao, J. Pang, and S. Venkataraman. Large-scale App-based Reporting of Customer Problems in Cellular Networks: Potential and Limitations. Y. Jin, N. Duffield, A. Gerber, P. Haffner, W. Hsu, G. Jacobson, S. Sen, S. Venkataraman, and Z. Zhang. W-MUST 2011.
10/23/2013	Phillipa traveling
10/28/2013	Class	Midterm project updates	Midterm report due
10/30/2013	Javad and Abbas	Mobile (From the edge)		A First Look at Traffic on Smartphones. H. Falaki, D. Lymberopoulos, R. Mahajan, S. Kandula, and D. Estrin. IMC 2010. Cell vs. WiFi: On the Performance of Metro Area Mobile Connections. J. Sommers, and P. Barford. IMC 2012. Meddle: Middleboxes for Increased Transparency and Control of Mobile Traffic. A. Rao, D. Choffnes, J. SHerry, A. Legout, A. Krishnamurthy, and W. Dabbous. CoNEXT Student Workshop 2012 (2 pages).
11/4/2013		Broadband		Characterizing Residential Broadband Networks. M. Dischinger, A. Haeberlen, K. Gummadi, and S. Saroiu. IMC 2007. Netalyzr: Illuminating The Edge Network. C. Kreibich, B. Nechaev, V. Paxson, and N. Weaver. IMC 2010. Optional: Revisiting Broadband Performance. I. Canadi, P. Barford, and J. Sommers. IMC 2012.
11/6/2013		Broadband		Dasu: Pushing Experiments to the Internet's Edge. M. Sanchez, J. Otto, Z. Bischof, D. Choffnes. F. Bustamante, B. Krishnamurthy, and W. Willinger. NSDI 2013. Broadband Internet Performance: A View from the Gateway. S. Sundaresan, W. de Donato, N. Feamster, R. Teixeira, S. Crawford, and A. Pescape. SIGCOMM 2011.
11/11/2013		Internet Censorship/Transparency		ConceptDoppler: A Weather Tracker for Internet Censorship. J. Crandall, D. Zinn, M. Byrd, E. Barr, and R. East. ACM CCS 2007 Internet Censorship in China: Where Does the Filtering Occur. X. Xu, Z. Mao, and J. Halderman. PAM 2011.
11/13/2013	Tzu-Wen	Internet Censorship/Transparency		Analysis of Country-wide Internet Outages Caused by Censorship. A. Dainotti, C. Squarcella, E. Aben, K. Claffy, M. Chiesa, M. Russo, and A. Pescape. Characterizing Censorship of Web Content Worldwide: Another Look at the OpenNet Initiative Data. P. Gill, M. Crete-Nishihata, J. Dalek, S. Goldberg, A. Senft, and G. Wiseman. Optional: Inferring Mechanics of Web Censorship around the World. J. Verkamp, and M. Gupta. USENIX FOCI 2012.
11/18/2013		Security (Prefix hijacks)		iSPY: Detecting IP Prefix Hijacking on My Own. Z. Zhang, Y. Zhang, Y. Hu, Z. Mao, and R. Bush. SIGCOMM 2008. Detecting Prefix Hijackings in the Internet with Argus. X. Shi, Y. Xiang, Z. Wang, X. Yin, and J. Wu. IMC 2012
11/20/2013		Security		Click Trajectories: End-to-End Analysis of the Spam Value Chain. K. Levchenko, A. Pitsillidis, N. Chachra, B. Enright, M. Felegyhazi, C. Grier, T. Halvorson, C. Kanich, C. Kreibich, H. Liu, D. McCoy, N. Weaver, V. Paxson, G. Voelker, and S. Savage. OAKLAND 2011. Impact of Spam Exposure on User Engagement. A. Dasgupta, K. Punera, J. Rao, and X. Wang. USENIX Security 2012.
11/25/2013		Data centers		The Nature of Datacenter Traffic: Measurements & Analysis. S. Kandula, S. Sengupta, A. Greenberg, P. Patel, and R. Chaiken. IMC 2009. Network Traffic Characteristics of Data Centers in the Wild. T. Benson, A. Akella, and D> Maltz. IMC 2010.
11/27/2013	Thanksgiving
12/2/2013	Class	Project presentations
12/4/2013	Class	Project presentations
12/4/2013	N/A	No class	Project report due at end of day.

Presentations

Students will be expected to sign up to present at least twice during the course of the term. Students should partner up and select a lecture where the pair will present the two assigned readings. You do not need the same partner for both presentations. Since the class size is small, the presentations will be individual. The presentation should be 40 minutes and cover the following points:

• Any relevant background for the discussion (e.g., does the paper rely on a little known protocol feature?)
• What is challenging about measuring the proposed system? (e.g., access to vantage points to perform measurements, access to high traffic servers or specific user populations)
• How does the paper go about addressing these challenges? Novel measurement infrastructure? Novel data analysis techniques?
• What specific tools or techniques does the paper propose? What are their limitations?
• What are 2-4 key insights from the data analysis in the paper?
• Partners should also discuss their papers with each other and when possible compare techniques and results between the papers. Are there discrepancies? Can these be explained by different methodologies? Why?
• The partners should also compare relative strengths and weaknesses between the papers, taking into account the age of the papers.

You are encouraged to consider the questions raised in this paper to aid in your critical analysis of the assigned readings. Students are encouraged to optionally send a draft of their slides or set up a brief meeting for feedback before their first presentation.

Participation

Each class we will discuss the assigned reading. Students are expected to actively participate in discussion of the papers. Bonus participation marks may be awarded for students who maintain blog entries summarizing the in class discussions.

Paper summaries/Course blog

During the course you will be expected to maintain a blog (does not need to be public, but I will need the URL and access to it). For each paper that is required reading you will be expected to post a blog entry summarizing the paper. Summaries are due prior to the start of the lesson where the paper is discussed. Repeatedly posting after the lecture and discussion have taken place will result in a reduction of marks.

You are encouraged to discuss the papers as you read them with your colleagues but your review must be written independently. Do not look at reviews from other classes that may be available on the Web. Your review should clearly address the following points:

• Summarize the high level goals of the paper and how it goes about achieving them. Highlight any perceived strengths and weaknesses of the paper and your general impression (did you like the paper or not?). (1 paragraph)
• What problem does the paper try to solve? Why is this an important problem? If you do not think the problem is important, state why not. (2-3 sentences)
• What are the strengths of the paper? (3-4 sentences)
• What are the weaknesses of the paper? (3-4 sentences)
• What would you do differently? Are there assumptions you disagree with? Do you see ideas for future work or improving the solution proposed? (5-6 sentences)

Project

Students are expected to undertake a semester long project related to material presented in the course. You are encouraged to work with a partner on the project. A list of potential topics is available on the Piazza site or students may come up with their own project. Milestones for the project are:

• Project proposal - after discussing your planned topic with the professor submit a 1 page summary outlining what you plan to accomplish (see deadline in syllabus).
• Elevator pitch - an in class opportunity to share your proposed topic with the class, emphasizing motivations and how your project will address the motivating issues.
• Midterm project report - this report should be an in progress version of your final report showing what steps you have accomplished and making clear what remains to be executed prior to the final report and presentation.
• Midterm project update - this is an in class opportunity to present your progress to your classmates. Students are encouraged to provide each other feedback or suggestions at this point that can be incorporated into the final write up and presentation.
• Final project report - This 6-8 page paper (please use the formatting guidelines set out here) will wrap up your project.
• Final project presentation - this is your opportunity to show your classmates what you have accomplished throughout the term and see what they have been working on. Students are again encouraged to give each other feedback and share thoughts and ideas.