LISA '11 Banner

LISA '11 Home |  Registration |  Discounts |  Organizers |  At a Glance |  Training |  Tech Sessions
Workshops |  Data Storage Day |  WiPs |  Poster Sessions |  BoFs |  Exhibition |  Sponsors |  Activities |  Hotel/Travel
Students |  Questions? |  Help Promote! |  For Participants |  Call for Papers |  Past Proceedings


TECHNICAL SESSIONS

Proceedings Front Matter: Proceedings covers | Title Page and List of Organizers | Table of Contents | Message from the Program Co-Chairs

Complete Proceedings (PDF)

E-Book Proceedings: Read the proceedings on the go in iPad-friendly EPUB format or Kindle-friendly Mobipocket format.

The LISA '11 theme is "DevOps: New Challenges, Proven Values." DevOps sessions are denoted by this icon: DevOps

Tech Sessions: Wednesday, December 7 | Thursday, December 8 | Friday, December 9 | Invited Talk Speakers

Wednesday, December 7
8:45 a.m.–10:30 a.m. Wednesday

Constitution Ballroom

Opening Remarks, Awards, and Keynote Address

LISA '11 Program Co-Chairs: Thomas A. Limoncelli, Google, Inc., and Doug Hughes, D. E. Shaw Research, LLC

Video View the Video   |   MP3 Icon Listen to the MP3

Keynote Address
The DevOps Transformation DevOps

Ben Rockwood, Joyent

Slides View the Slides   |   Video View the Video   |   MP3 Icon Listen to the MP3

DevOps may be a new term, but it's not a new idea. in this session we'll deconstruct it into its three transformation phases, look back at the often referenced but rarely explained history that influences it, and see how it is a catalyst that is changing the craft of system administration.

10:30 a.m.–11:00 a.m.   Break with Beverages and Snacks, Grand Ballroom
11:00 a.m.–12:30 p.m. Wednesday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Carolyn Rowland, National Institute of Standards and Technology (NIST)

Perspicacious Packaging

Staging Package Deployment via Repository Management
Chris St. Pierre and Matt Hermanson, Oak Ridge National Laboratory

Read the Full paper

SlidesView the Slides

CDE: Run Any Linux Application On-Demand Without Installation
Philip J. Guo, Stanford University

SlidesView the Slides

Read the Full paper

Improving Virtual Appliance Management through Virtual Layered File Systems
Shaya Potter and Jason Nieh, Columbia University

Read the Full paper

INVITED TALKS I: Databases

Back Bay A

Session Chair: Tim Nelson, Worcester Polytechnic Institute

NewSQL vs. NoSQL for New OLTP
Michael Stonebraker, MIT

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Enterprises once used RDBMs for online transaction processing (OLTP) applications, which we affectionately call OldSQL. New OLTP applications have greater performance requirements; in many modern applications—multiplayer games, gambling, social networks, etc.—OldSQL is cracking under the volume of interactions. I contrast two alternatives to OldSQL: NoSQL, where SQL and ACID are jettisoned for better performance; and NewSQL, where SQL and ACID are retained, and innovative architectures improve performance.

INVITED TALKS II: Newish Technologies

Back Bay C

Session Chair: Avleen Vig, Etsy, Inc.

Issues and Trends in Reliably Sanitizing Solid State Disks
Michael Wei, University of California, San Diego

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Reliably erasing data from storage media (sanitizing the media) is a critical component of secure data management. While sanitizing entire disks and individual files is well understood for hard drives, flash-based solid state disks have a very different internal architecture. Our lab has evaluated the effectiveness of state-of-the-art sanitization on solid state disks (SSDs) and determined that it is unreliable and could lead to a false sense of security. This talk focuses on the issues and trends today in solid state disk sanitization.

Apache Traffic Server: More Than Just a Proxy
Leif Hedstrom, GoDaddy

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Apache Traffic Server is an Apache Software Foundation open project, implementing a fast, scalable, and feature-rich HTTP proxy caching server. This presentation will give a solid introduction to the software, its features and capabilities, and how to successfully deploy and use it in your applications. We will discuss several typical use cases, with example setup and configurations.

THE GURU IS IN

Gardner

Session Chair: Duncan Hutty, ZOLL

Security
Matt Disney, Oak Ridge National Laboratory

Matt Disney is the team lead for cybersecurity administration in the National Center for Computational Sciences at Oak Ridge National Laboratory. He approaches security with the background of a system administrator and specializes in deployment automation, configuration management, workflow processes, and intrusion detection. Matt holds an MS in Network and System Administration from the University of Oslo and serves on the LOPSA Board of Directors.

12:30 p.m.–2:00 p.m.   Lunch (on your own)
2:00 p.m.–3:30 p.m. Wednesday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Duncan Hutty, ZOLL

Clusters and Configuration Control DevOps

Sequencer: Smart Control of Hardware and Software Components in Clusters (and Beyond)
Pierre Vignéras, Bull, Architect of an Open World

Read the Full paper

Awarded Best Student Paper!
Automated Planning for Configuration Changes
Herry Herry, Paul Anderson, and Gerhard Wickler, University of Edinburgh

Read the Full paper

Slides View the Slides

Video View the Video

Fine-grained Access-control for the Puppet Configuration Language
Bart Vanbrabant, Joris Peeraer, and Wouter Joosen, DistriNet, K.U. Leuven

Read the Full paper

Slides View the Slides

INVITED TALKS I: DevOps: Chef

Back Bay A

Session Chair: Kent Skaar, VMware, Inc.

GameDay: Creating Resiliency Through Destruction DevOps
Jesse Robbins, Opscode, LLC

Video View the Video

MP3 Icon Listen to the MP3

Converting the Ad-Hoc Configuration of a Heterogeneous Environment to a CFM, or, How I Learned to Stop Worrying and Love the Chef DevOps
Dimitri Aivaliotis, EveryWare AG

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

There are as many ways of managing the configuration of heterogeneous systems as there are engineers trying to solve this problem. This talk explores one way of converting an ad-hoc configuration management system into one codified in Chef. We will describe extensions to the FreeBSD and Solaris providers and explore cookbooks to detail how the configuration is modeled. But why would you actually use a CFM? Will it make your job easier? Can you own it? We will reveal these answers and more.

INVITED TALKS II: Panel

Back Bay C

How University Programs Prepare the Next Generation of Sysadmins

Moderator: Carolyn Rowland, National Institute of Standards and Technology (NIST)
Panelists: Kyrre Begnum, Oslo and Akershus University College of Applied Sciences; Andrew Seely, University of Maryland University College; Steve VanDevender, University of Oregon; Guy Hembroff, Michigan Technological University

Video View the Video

MP3 Icon Listen to the MP3

A team of panelists with real-world experience as educators and sysadmins discuss the challenges and successes of university programs aimed at preparing students to be effective and sought-after system administrators. How do you teach strong analytical skills and what makes a student in demand right after graduation? Bring your questions and hear how different institutions address the challenge.

THE GURU IS IN

Gardner

Session Chair: Federico D. Sacerdoti, Aien Capital & Aien Technology

IPv6
Owen DeLong, Hurricane Electric

Owen DeLong is an IPv6 Evangelist at Hurricane Electric and a member of the ARIN Advisory Council, with more than twenty-five years of industry experience. He is an active member of the system administration, operations, and IP policy communities. Owen has worked at Tellme Networks (Senior Network Engineer); Exodus Communications (Senior Backbone Engineer), where he was part of the team that took Exodus from a pre-IPO startup with two data centers to a major global provider of hosting services; Netcom Online (Network Engineer), where he worked on a team that moved the Internet from an expensive R&E tool to a system accessible to anyone with a computer; Sun Microsystems (Senior Systems Administrator); and more.

3:30 p.m.–4:00 p.m.   Break with Beverages and Snacks, Grand Ballroom
4:00 p.m.–5:30 p.m. Wednesday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Tim Nelson, Worcester Polytechnic Institute

Security 1

Tiqr: A Novel Take on Two-Factor Authentication
Roland M. van Rijswijk and Joost van Dijk, SURFnet BV

Read the Full paper

Slides View the Slides

Building Useful Security Infrastructure for Free (Practice & Experience Report)

Brad Lhotsky, National Institutes on Health, National Institute on Aging, Intramural Research Program

Read the Full paper

Awarded Best Paper!
Local System Security via SSHD Instrumentation
Scott Campbell, National Energy Research Scientific Computing Center, Lawrence Berkeley National Lab

Slides View the Slides

Read the Full paper

INVITED TALKS I: DevOps Case

Back Bay A

Session Chair: Duncan Hutty, ZOLL

The Operational Impact of Continuous Deployment DevOps
Avleen Vig, Etsy, Inc.

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Continuous deployment has significant advantages for getting code changes into production with short turnaround times. We will go over the requirements of an operations group to support a continuous deployment environment. The impact of monitoring, escalations, capacity planning, and tools on the culture and workflow of operations teams will be discussed as we enter "The Continuous Deployment Zone."

DevOps: The past and future are here. It's just not evenly distributed (yet). DevOps
Kris Buytaert, Inuits

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

We've come a long way since introducing new ideas in server automation and deployment, and also in creating a culture of collaboration between the traditional silos in organizations. But how does this impact the traditional sysadmin world? Are we all a DevOps now? Does a DevOps person = sysadmin 2.0? Will DevOps put us out of a job? I will give a brief overview of how culture, workflow, and behavior have evolved. After evaluating the past and the present, I will tallk about the future, identifying technical gaps in monitoring, packaging, and data collection and identifying emerging human, organizational evolutions.

INVITED TALKS II: Infrastructure Best Practices

Back Bay C

Session Chair: Mark Roth, Google, Inc.

3 Myths and 3 Challenges to Bring System Administration out of the Dark Ages DevOps
Mark Burgess, CFEngine

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Mark Burgess, a provocative thinker about system administration since the 1990s, recently wrote a controversial blog about three ideas that he believes are holding the field of system administration in the past. In this talk he outlines those and chooses three themes everyone should have in mind to accelerate the future of the field: business integration, knowledge management, and emergent design to handle complexity. These are a part of the DevOps movement, but have people really thought through the issues?

Linux Systems Capacity Planning: Beyond RRD and top
Rodrigo Campos

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

As infrastructure costs rise, there's an urgent need to squeeze more performance from the same hardware. After several years of measuring and managing the capacity of thousands of Linux servers, we have learned that most typical tools and metrics are not sufficient to predict performance bottlenecks, particularly during traffic spikes. By using queue theory formulas and instrumenting our applications we were able to find the limits of our systems, improve reliability, and maximize throughput and performance.

THE GURU IS IN

Gardner

Panel: Women in Tech

Moderator: Lois Bennett
Panelists: Carolyn Rowland, National Institute of Standards and Technology (NIST); Deb Nicholson, MediaGoblin; Máirín Duffy, Red Hat, Inc.

Lois Bennett has been a system administrator for about 25 years. She earned a Master's degree in electrical engineering (UConn '85), with a concentration in electro-magnetics and solid state physics, and studied antennas and fiber optics. Currently, she is a senior system administrator for Channing Laboratory at Brigham & Women's Hospital in Boston. She has worked for Harvard and MIT. She enjoys scripting and Perl. She serves on the LOPSA board as Secretary/Treasurer and also on the Education and Mentorship committees. She served as USENIX Treasurer from 2002 to 2004 and was chair of the SAGE Certification Program Governing Board 2000 to 2003. Lois also attended the United Nations Commission on the status of Women Meeting in NYC in 2005 as a representative of the Episcopal Church and has been active in promoting the work of several non-profits working to support women in Mexico and in Africa.

Carolyn Rowland began her UNIX system administration career in 1991. She currently leads a team of sysadmins at the National Institute of Standards and Technology (NIST). She focuses on raising the visibility of IT by aligning technology with business needs. She finds strength in service delivery, standardization, automation, and cost control. Her tireless efforts succeeded in changing the perception of her team from yet another overhead cost to a highly respected part of the organization. Her team has distinguished itself as a leader in the development of new technology solutions that solve business and research problems across the NIST campus.

Deb Nicholson works at the intersection of technology and social justice. She has over fifteen years of non-profit management experience and got involved in the free software movement about five years ago. She currently splits her time between MediaGoblin, a federated media-hosting start-up, Open Hatch, a non-profit dedicated to identifying and mentoring new free software contributors, and Harvard, where she is slowly pursuing a graduate degree in Information Technology.

Máirín Duffy is an interaction designer for Red Hat and is the design team lead of the Fedora Project. She has been involved in various free software community women's groups such as GNOME Women and the FSF Women's Caucus. She is an active advocate for free software creative tools such as Inkscape and Gimp; she has served as instructor for various programs introducing children to these tools. Máirín graduated with an MS in Human-Computer Interaction from Rensselaer Polytechnic Institute.

5:30 p.m.–6:30 p.m. Wednesday

Vendor Exhibition, Grand Ballroom

Exhibit Hall Happy Hour

Sponsored by Oracle

Join us at the Vendor Exhibition for refreshments and take the opportunity to learn about the latest products and technologies.

6:30 p.m.–7:30 p.m. Wednesday

Ballroom Foyer

Poster Session

Check out the cool new ideas and the latest preliminary work on display at the Poster Sessions. Take advantage of an opportunity to mingle with colleagues who may be interested in the same area. The list of accepted posters is available here.

Tech Sessions: Wednesday, December 7 | Thursday, December 8 | Friday, December 9 | Invited Talk Speakers
Thursday, December 8
8:45 a.m.–10:15 a.m. Thursday

Constitution Ballroom

Plenary Session

Session Chairs: Thomas A. Limoncelli, Google, Inc., and Doug Hughes, D. E. Shaw Research, LLC

One Size Does Not Fit All in DB Systems DevOps

Andy Palmer, Global Head of Software and Data Engineering, Novartis Institute for Biomedical Research

Video View the Video

MP3 Icon Listen to the MP3

The past 25 years of commercial DBMS development can be summed up in a single phrase: "One size fits all." The traditional DBMS architecture (originally designed and optimized for business data processing) has been used to support many data-centric applications, with widely varying characteristics and requirements. The commercial database market is beginning to transform into a number of segments—most notably, OLTP vs. data warehousing—each of which is defined by a specific workload. Innovative "purpose-built" independent database engines are now being widely adopted to satisfy specific workloads. Picking the right engine for a given workload is a new challenge, and doing this well can offer discontinuous benefits in terms of performance, scale, maintainability, and concurrency.

10:15 a.m.–10:45 a.m.   Break with Beverages and Snacks, Grand Ballroom 
10:45 a.m.–12:45 p.m. Thursday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Carolyn Rowland, National Institute of Standards and Technology (NIST)

From Small Migration to Big Iron

Awarded Best Practice & Experience Report!
Deploying IPv6 in the Google Enterprise Network: Lessons Learned (Practice & Experience Report)
Haythum Babiker, Irena Nikolova, and Kiran Kumar Chittimaneni, Google

Read the Full paper

Slides View the Slides

Bringing Up Cielo: Experiences with a Cray XE6 System, or, Getting Started with Your New 140k Processor System (Practice & Experience Report)

Cory Lueninghoener, Daryl Grunau, Timothy Harrington, Kathleen Kelly, and Quellyn Snead, Los Alamos National Laboratory

Read the Full paper

Slides View the Slides

Backup Bonanza

Capacity Forecasting in a Backup Storage Environment (Practice & Experience Report)

Mark Chamness, EMC

Read the Full paper

Slides View the Slides

Content-aware Load Balancing for Distributed Backup
Fred Douglis and Deepti Bhardwaj, EMC; Hangwei Qian, Case Western Reserve University; Philip Shilane, EMC

Read the Full paper

Slides View the Slides

INVITED TALKS I: DevOps: Core

Back Bay A

Session Chair: Kent Skaar, VMware, Inc.

SRE@Google: Thousands of DevOps Since 2004

DevOps
Thomas A. Limoncelli, Google NYC

Tom will describe technologies and policies that Google uses to do what is (now) called DevOps. Google doesn't just empower developers and operations to work together; we have a system that empowers every group to be their own DevOps team.

Deployinator: Being Stupid to Be Smart DevOps
Erik Kastner and John Goulah, Etsy, Inc.

Developers deploy production code more than 30 times per day at Etsy. Small, rapid changes allow us to move fast, detect failure, and respond quickly. This works for a number of cultural and technical reasons. Learn about the tool we built, Deployinator, to automate this process and how we accomplish this effectively. We hope open-sourcing the tool will give people an opportunity to make their deployment process more agile and efficient.

INVITED TALKS II

Back Bay C

Session Chair: Narayan Desai, Argonne National Lab

Fork Yeah! The Rise and Development of illumos
Bryan M. Cantrill, Joyent

Slides View the Slides

In August 2010, illumos, a new OpenSolaris derivative, was born. While not at the time intended to be a fork, Oracle sealed the fate of illumos when it elected to close OpenSolaris: by choosing to cease its contributions, Oracle promoted illumos from a downstream repository to the open source repository of record for such revolutionary technologies as ZFS, DTrace, and Zones. This move accelerated the diaspora of kernel engineers from the former Sun Microsystems, many of whom have landed in the illumos community, where they continue to innovate. We will discuss the history of illumos but will focus on its promising future.

GPFS Native RAID for 100,000-Disk Petascale Systems DevOps
Veera Deenadhayalan, IBM Almaden Research Center

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

GPFS (General Parallel File System) is widely used in HPC systems and GPFS. Native RAID (GNR) is a newly added, robust RAID layer tightly integrated into GPFS. GNR effectively utilizes the multiple CPU cores of modern IO servers to eliminate the hardware cost, firmware hassles, and maintenance associated with standalone RAID controllers. To effectively deal with a 100,000-disk petascale system that is expected to experience disk failures on a daily basis, GNR uses declustered RAID to lower the impact of RAID rebuild operations, 3-fault-tolerant redundancy codes, comprehensive asynchronous disk diagnostics, and end-to-end checksum protection to meet the cost, reliability, and integrity goals of the system.

THE GURU IS IN

Gardner

Session Chair: Chris St. Pierre, Oak Ridge National Laboratory

Documentation
Janice Gelb, Oracle Corporation

Janice Gelb is a Senior Developmental Editor at Oracle Corporation, where she is responsible for editing print and online documentation for numerous software products. She is a certified trainer for their internal SGML/XML authoring tool. Janice also worked as a technical editor at Ashton-Tate and at Scitex Corporation. She has presented papers at several technical communication conferences and was the project lead for the popular editorial style guide Read Me First! A Style Guide for the Computer Industry.

Running PHP
Dimitri Aivaliotis, EveryWare Ltd

Dimitri Aivaliotis is the leader of the UNIX Team at EveryWare Ltd, a hosting provider based in Zurich, Switzerland. His career has taken him from building a Linux-based computer network for a school up through dual-datacenter high-availability infrastructures for banks and online portals. He has spent over a decade solving his customers' problems and enjoys finding new ways to engineer himself out of a job. Dimitri graduated summa cum laude with a BS in Physics from Rensselaer Polytechnic Institute and followed that with an MS in Management Information Systems at Florida State University.

12:45 p.m.–2:00 p.m.   Lunch (on your own)
2:00 p.m.–3:00 p.m. Thursday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Avleen Vig, Etsy, Inc.

To the Cloud!

Getting to Elastic: Adapting a Legacy Vertical Application Environment for Scalability
Eric Shamow, Puppet Labs

Read the Full paper

Slides View the Slides

Scaling on EC2 in a Fast-Paced Environment (Practice & Experience Report)
Nicolas Brousse, TubeMogul, Inc.

Read the Full paper

View the Slides

INVITED TALKS I: DevOps: Puppet

Back Bay A

Session Chair: Kent Skaar, VMware, Inc.

Building IronMan, Not Programming DevOps
Luke Kanies, Founder, Puppet and Puppet Labs

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

There is a lot of discussion about DevOps being about operations and development becoming one, or operations becoming developers. This talk will instead argue that while the world of development is a source of inspiration, DevOps is about improving operations and sysadmins. DevOps isn't about sysadmins becoming developers or going away entirely—it's about the best way for sysadmins to get better at their jobs and provide value in their roles. This talk will draw parallels to the world of agile development, which focuses on results and the people involved. We will cover reduction in process, the importance of new tool adoption, and collaboration between disparate groups, all of which are critical to DevOps making a difference.

INVITED TALKS II

Back Bay C

Session Chair: Chris St. Pierre, Oak Ridge National Laboratory

IPv6, DNSSEC, RPKI, etc.: What's the Holdup and How Can We Help?
Richard Jimmerson, IETF ISOC

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3 

You're busy. We get it. This industry moves fast and you've got your hands full keeping your networks updated and secure from the threat of the day. But why is it taking so long to deploy IPv6, DNSSEC, and other standards coming out of the IETF? These standards are the future of the Internet, but deployment to date has been slow.

The Internet Society has launched a new initiative that aims to bridge the gap between the IETF standards process and final adoption of those standards by the global operations community. Already deployed the latest and greatest technologies? Work with us on case studies and how-to documents to help other organizations. Ready to deploy IPv6, but don't know where to start? Let us know what you need. We're amassing a collection of detailed, hands-on information that you can easily use to get your organization moving in the right direction.

In this talk, I'll explain the new initiative and provide a forum for you to share your needs and your success stories. Join us to help define how the nonprofit Internet Society can best serve your deployment information needs. We are here to listen and will produce the resources you need.

THE GURU IS IN

Gardner

Session Chair: Thomas A. Limoncelli, Google, Inc.

Time Management
Thomas A. Limoncelli, Google, Inc.

Thomas A. Limoncelli is an internationally recognized author, speaker, and system administrator. His best-known books include Time Management for System Administrators (O'Reilly) and The Practice of System and Network Administration (Addison-Wesley). He received the SAGE 2005 Outstanding Achievement Award. He works at Google in NYC and blogs at http://EverythingSysadmin.com/. He also happens to be co-chair of LISA '11.

3:00 p.m.–3:30 p.m.   Break with Beverages and Snacks, Republic Foyer
3:30 p.m.–5:30 p.m. Thursday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Thomas A. Limoncelli, Google, Inc.

Honey and Eggs: Keeping Out the Bad Guys with Food

DarkNOC: Dashboard for Honeypot Management
Bertrand Sobesto and Michel Cukier, University of Maryland; Matti Hiltunen, Dave Kormann, and Gregg Vesonder, AT&T Labs Research; Robin Berthier, University of Illinois

Read the Full paper

View the Slides

A Cuckoo's Egg in the Malware Nest: On-the-fly Signature-less Malware Analysis, Detection, and Containment for Large Networks
Damiano Bolzoni and Christiaan Schade, University of Twente; Sandro Etalle, University of Twente and Eindhoven Technical University

Read the Full paper

SlidesView the Slides

Seriously Snooping Packets

Auto-learning of SMTP TCP Transport-Layer Features for Spam and Abusive Message Detection
Georgios Kakavelakis, Robert Beverly, and Joel Young, Naval Postgraduate School

Read the Full paper

Slides View the Slides

Using Active Intrusion Detection to Recover Network Trust
John F. Williamson and Sergey Bratus, Dartmouth College; Michael E. Locasto, University of Calgary; Sean W. Smith, Dartmouth College

Read the Full paper

INVITED TALKS I

Back Bay A

Session Chair: Nicole Forsgren Velasquez, Pepperdine University

DevOps Case: Scholastic

Fixing the Flying Plane: A Production DevOps Team DevOps
Calvin Domenico, Marie Hetrick, Elijah Aydnwylde, J. Brandon Arsenault, Patrick McAndrew, Alastair Firth, and Jesse Campbell, Scholastic, Inc.

Slides View the Slides

At Scholastic, Inc., the Web Hosting Department practices DevOps in action, leveraging both their development abilities and their sysadmin skills to improve and modify the behavior of software using ops and infrastructure tweaks. A diverse but very tight-knit group of ten, the group faces the challenges of delivering hosted SaaS (Software as a Service) to a growing customer base, using software that was originally designed for client-server local installations. Recently the group designed and implemented a new datacenter utilizing infrastructure, virtualization, and custom development to maximize the department's offerings.

Case Study: Big Launch

Releasing 9/11 Data to Satisfy FOIA: It's Just a Simple Web Site, Right?
David Pullman and Carolyn Rowland, NIST

The National Institute of Standards and Technology (NIST) collected photos, videos, and other data from many sources to aid in an investigation of the collapse of the World Trade Center. Just prior to the tenth anniversary of 9/11, NIST released this data on a public Web server to meet FOIA requirements. A team of sysadmins took a winding path to hosting the data, using a combination of open source tools and the cloud. Technical and non-technical challenges threatened this project along the way.

INVITED TALKS II

Back Bay C

Session Chair: Mario Obejas, Raytheon

Storage

My First Petabyte: Now What?
Jacob Farmer, Cambridge Computer

Video View the Video

MP3 Icon Listen to the MP3

When we talk about a person's age, the chic expression is that 30 is the new 20. When we talk about data storage, it's tempting to say that the petabyte is the new terabyte. Many organizations now have a petabyte, large corporations have several petabytes, and content repositories have hundreds of petabytes. The reality is that the technologies for moving and managing data have not kept pace with ballooning capacities. The major problem areas include: navigating a name space with hundreds of millions of files; backup and restore; replication, fail-over, and fail-back; life cycle management; and migrations and hardware refreshes. This session explores these problem areas and describes various solutions.

Security

Can Vulnerability Disclosure Processes Be Responsible, Rational, and Effective?
Larissa Shapiro, Internet Security Consortium

Slides View the Slides

VideoView the Video

MP3 Icon Listen to the MP3

ISC produces critical infrastructure software and services upon which the Internet and telecommunications industries depend. Through our Phased Vulnerability Disclosure process, we provide rational disclosure of vulnerabilities through a series of notifications, so industry can prepare without rushed actions, and critical infrastructure can be upgraded without "bad guys" knowing about the vulnerability. As an organization dedicated to open source software and open process, ISC is publishing the policies, processes, and tools involved. Please join us as we walk through a new model that vendors and operators can use to roll out security fixes without adding to operational risk.

THE GURU IS IN

Gardner

Session Chair: Chris St. Pierre, Oak Ridge National Laboratory

ITIL
Jeanne Schock, Afilias, Inc.

Jeanne has eleven years of experience in system administration, working with FreeBSD, Solaris, Linux, and Windows. She has worked at a number of companies in the Internet industry, including a regional ISP, a video hosting company, and, for the past four years, Afilias, a Registry and DNS service provider. For the past two years she's been managing the change management process at Afilias and is helping to coordinate full implementation of ITIL, beginning with incident and problem management. She also manages projects geared toward site reliability and disaster recovery. Jeanne got her BA from Vassar College and did graduate work at the University of Toronto in Medieval European studies, teaching Latin in her pre-IT years.

Chef
Aaron Peterson, Opscode, Inc.

Aaron Peterson is a seasoned systems and networking engineer. He has wielded real-time command-line kung fu on tens of thousands of servers at once and automated global production infrastructure at Amazon.com. He is excited about information design and visualization, scale, and analysis.

5:30 p.m.–6:30 p.m. Thursday

Republic Foyer

Poster Session

Check out the cool new ideas and the latest preliminary work on display at the Poster Sessions. Take advantage of an opportunity to mingle with colleagues who may be interested in the same area. The list of accepted posters is available here.

6:30 p.m.–8:00 p.m. Thursday

Grand Ballroom

Reception for the 25th LISA

Jump in the time machine and take stroll through LISAs past while enjoying dinner and drinks. From photos to awards to stories, we'll give you a fun look back. Since it all began in the '80s, we hope you'll join us by wearing your favorite '80s attire. There will be a prize for best costume (extra points if you're sporting '80s LISA gear).

Tech Sessions: Wednesday, December 7 | Thursday, December 8 | Friday, December 9 | Invited Talk Speakers
Friday, December 9
9:00 a.m.–10:30 a.m. Friday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Nicole Forsgren Velasquez, Pepperdine University

Network Security

Community-based Analysis of Netflow for Early Detection of Security Incidents
Stefan Weigert, TU Dresden; Matti A. Hiltunen, AT&T Labs Research; Christof Fetzer, TU Dresden

Read the Full paper

WCIS: A Prototype for Detecting Zero-Day Attacks in Web Server Requests
Melissa Danforth, California State University, Bakersfield

Read the Full paper

Slides View the Slides

INVITED TALKS I: Networking

Back Bay A

Session Chair: Doug Hughes, D. E. Shaw Research, LLC

Ethernet's Future Trajectory
John D'Ambrosia, Force10 Networks

Video View the Video

MP3 Icon Listen to the MP3

In 2010, with the introduction of 40 gigabit Ethernet and 100 gigabit Ethernet, the release of IEEE Std 802.3ba™-2010 heralded the next step in Ethernet. These technologies, combined with the ongoing mass deployment of 10 gigabit Ethernet, are driving the evolution of the Ethernet ecosystem. This session will provide an overview of the state of Ethernet, as well as insight into current efforts and the future.

INVITED TALKS II: IPv6

Back Bay C

Session Chair: David Williamson, Microsoft Tellme

IPv6: No Longer Optional
Owen DeLong, Hurricane Electric Internet Services

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

This is a talk about the need to move forward with IPv6 or become increasingly disconnected from the Internet. Topics covered will include: a brief history of IPv4 run-out; why IPv6?; how do I get started with IPv6?; an introduction to IPv6 on Linux as an example of a POSIX-like system.

Implementing IPv6 on a Global Scale: Experiences at Akamai
Erik Nygren, Akamai

Video View the Video

MP3 Icon Listen to the MP3

Akamai's global platform for application acceleration and content delivery consists of nearly 100,000 servers in over 1,000 networks and 74 countries. We now have IPv6 connectivity in over 45 countries, with hundreds of server locations. Our diverse global footprint across many network providers has given us perspective into the Internet's IPv6 connectivity and has posed interesting challenges. This talk will touch on observations of IPv6 network connectivity and client behavior, common misconceptions, approaches for migrating sites to dual-stacked IPv6, and experiences with how dual-stack deployments impact server operations.

THE GURU IS IN

Gardner

Session Chair: Chris St. Pierre, Oak Ridge National Laboratory

SELinux
Dan Walsh, Red Hat, Inc.

Slides View the Slides

Daniel Walsh has worked in the computer security field for over twenty-five years. Dan joined Red Hat in August 2001. He has led the SELinux project, concentrating on the application space and policy development. Dan helped developed sVirt (Secure Virtualization) and he created the SELinux Sandbox, the Xguest user, and the Secure Kiosk. Dan has worked on Netect/Bindview's HackerShield and BVControl for UNIX, two vulnerability assessment products. Dan worked for Digital Equipment Corporation on the Athena Project, along with designing and developing the AltaVista Firewall and AltaVista Tunnel (VPN). Dan has a BA in Mathematics from the College of the Holy Cross and a MS in Computer Science from Worcester Polytechnic Institute.

10:30 a.m.–11:00 a.m.   Break with Beverages and Snacks, Republic Foyer
11:00 a.m.–12:30 p.m. Friday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Federico D. Sacerdoti, Aien Capital & Aien Technology

Networking 1

Automating Network and Service Configuration Using NETCONF and YANG
Stefan Wallin, Luleå University of Technology; Claes Wikström, Tail-f Systems AB

Read the Full paper

Adventures in (Small) Datacenter Migration (Practice & Experience Report)


Jon Kuroda, Jeff Anderson-Lee, Albert Goto, and Scott McNally, University of California, Berkeley

Read the Full paper

Experiences with BOWL: Managing an Outdoor WiFi Network (or How to Keep Both Internet Users and Researchers Happy?) (Practice & Experience Report)

T. Fischer, T. Hühn, R. Kuck, R. Merz, J. Schulz-Zander, and C. Sengul, TU Berlin/Deutsche Telekom Laboratories

Read the Full paper

INVITED TALKS I: Panel

Back Bay A

What Will Be Hot Next Year?

Moderator: Narayan Desai, Argonne National Lab
Panelists: Kris Buytaert, Inuits; John D'Ambrosia, Force10 Networks; Jacob Farmer, Cambridge Computer

Video View the Video

MP3 Icon Listen to the MP3

What will be the hot technologies in 2012 and 2013? What should you be investigating now, so that you are ready for the future? When one technology leaps forward, it exposes bottlenecks in the others. Are you prepared? This prestigious panel of prognosticators includes one apps expert, one storage expert, and one networking expert.

INVITED TALKS II: Beyond Technology

Back Bay C

Session Chair: Marc Stavely, Consultant

Customer Service for Sysadmins
H. Wade Minter, TeamSnap Inc.

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

Everybody knows the stereotype of BOFHs, hiding behind the glow of their monitors, disregarding all human interaction that doesn't arrive via IRC. Some of us may even resemble that stereotype to a degree. But whether your customers are internal developers or external users, your personal and company success depends in large part on their perceptions, especially in this era of social media and worldwide feedback. A veteran sysadmin will talk about how his startup, TeamSnap, has built a passionate and devoted following by using simple, inexpensive tools and techniques for listening and responding to customers.

Playing the Certification Game (No Straitjacket Required), a.k.a How to Become Certified Without Becoming Certifiable
Dru Lavigne, iXsystems, PC-BSD Project, FreeNAS Project, FreeBSD Foundation, BSD Certification Group

Slides View the Slides

Video View the Video

MP3 Icon Listen to the MP3

This presentation provides a slightly tongue-in-cheek overview of the good, the bad, and the ugly of system administration certifications. Drawing upon her experience as a certificant, trainer, and chair of a certifying organization, the presenter will provide examples of how not to create a certification program, what to look for in a certification program in order to advance one's career, and how to spend one's training dollars wisely while possibly even learning some new skills along the way.

THE GURU IS IN

Gardner

Session Chair: Tim Nelson, Worcester Polytechnic Institute

Cloud Computing and *aaS
David Nalley, CloudStack

David Nalley is currently employed by Citrix (née Cloud.com) as the Community Manager for the CloudStack project. David's a recovering sysadmin of ten years' standing and a long-time contributor to the Fedora Project, where he is currently serving on the Fedora Project Board. He's also contributed in various forms to Cobbler, Zenoss, Opengroupware.org, OLPC Math4, and Sahana. He is a frequent speaker at free software conferences around the nation and writes for a number of technical and open source media publications, including Linux Pro Magazine and OpenSource.com.

12:30 p.m.–2:00 p.m.   Lunch (on your own)
2:00 p.m.–3:30 p.m. Friday

REFEREED PAPERS

Constitution Ballroom

Session Chair: Tim Nelson, Worcester Polytechnic Institute

Migrations, Mental Maps, and Make Modernization

Why Do Migrations Fail and What Can We Do about It?
Gong Zhang and Ling Liu, Georgia Institute of Technology

Read the Full paper

Provenance for System Troubleshooting
Marc Chiarini, Harvard SEAS

Read the Full paper

Debugging Makefiles with remake
Rocky Bernstein

Read the Full paper

N.B. There will be no presentation of this paper.

INVITED TALKS I: Security

Back Bay A

Session Chair: Marc Stavely, Consultant

Surveillance or Security? The Risks Posed by New Wiretapping Technologies
Susan Landau, Visiting Scholar, Department of Computer Science, Harvard University

Video View the Video

MP3 Icon Listen to the MP3

The United States has moved large portions of business and commerce, including the control of critical infrastructure, onto IP-based networks. This reliance on information systems leaves the US highly exposed and vulnerable to cyberattack, yet US law enforcement remains focused on building wiretapping systems within communications infrastructure. By embedding eavesdropping mechanisms into communications technology itself, we build tools that could easily be turned against us. Indeed, such attacks have already occurred. In a world that has Al-Qaeda, nation-state economic espionage, and Hurricane Katrina, how do we get communications security right?

INVITED TALKS II: Sysadmin in/and the World

Back Bay C

Session Chair: Mark Roth, Google, Inc.

Copacetic.
David N. Blank-Edelman, Northeastern University College of Computer and Information Science

Video View the Video

MP3 Icon Listen to the MP3

During a hiring search, I talked to far too many sysadmins who wanted to use best practices at their workplace (configuration management, DevOps techniques, etc.) but felt personally disempowered to do anything but fight fires or perpetuate the current environment, as well as to those who had lost the enjoyment of working in our field. Some of these unhappy souls were managers; some of them were managed. These interactions harshed my mellow so much that I became determined to find a way to extract them from both their internal and their external mire. There's fabulous research being done on the nature of happiness, motivation, and reality hacking that is directly applicable to our field. Come to this talk to learn some surprising but practical ways to improve your happiness or the happiness of sysadmins/DevOps who work for you.

Project Cauã
Jon "maddog" Hall, Linux International and Project Cauã

Video View the Video

MP3 Icon Listen to the MP3

Project Cauã is an open source software and hardware project to create millions of new high-tech jobs in Brazil and millions more in the rest of Latin America. Project Cauã will also cut electricity usage, make computers easier to use, allow for the creation of gratis wireless support over large urban areas, and provide a low-cost or gratis super-computing grid. All of the work will be freely available, and parts of Project Cauã may be useful in high-density areas such as Manhattan, Chicago, Detroit, or Beijing. World peace comes next year.

WORK-IN-PROGRESS REPORTS

Gardner

Work-in-Progress Reports (WiPs)
Chair: William Bilancio, Arora and Associates, P.C.

Short, pithy, and fun, Work-in-Progress reports introduce interesting new or ongoing work. If you have work you would like to share or a cool idea that's not quite ready for publication, post a one- or two-paragraph summary to the Sign Up Form by 6:00 p.m. EST on Thursday, December 8. We are particularly interested in presenting students' work. A schedule of presentations will be posted here, and the speakers will be notified in advance. Work-in-Progress reports are five-minute presentations; the time limit will be strictly enforced.

3:30 p.m.–4:00 p.m.   Break with Beverages and Snacks, Republic Foyer
4:00 p.m.–5:30 p.m. Friday

Constitution Ballroom

Closing Session

Session Chair: Doug Hughes, D. E. Shaw Research, LLC, and Thomas A. Limoncelli, Google, Inc.

What Is Watson?
Michael P. Perrone, Manager, Multicore Computing, IBM T.J. Watson Research Center

Slides View the Slides   |   Video View the Video   |   MP3 Icon Listen to the MP3

The TV quiz show Jeopardy! is famous for giving contestants answers to which they must supply the correct questions. Contestants must be fast, with an almost encyclopedic knowledge of the world and the ability to figure out clues that are vague, involve double meanings, and frequently rely on puns. Early this year, Jeopardy! aired a match involving the two all-time most successful Jeopardy! contestants and Watson, an artificial intelligence system designed by IBM. Watson won the Jeopardy! match by a wide margin. In doing so, it brought the leading edge of computer technology a little closer to human abilities. This presentation will describe the supercomputer implementation of Watson used for the Jeopardy! match and the challenges that had to be overcome to create a computer capable of accurately answering open-ended, natural-language questions in real time—typically in under 3 seconds.

?Need help? Use our Contacts page.

Last changed: 5 May 2012 mpn