The Berkeley/Stanford Recovery-Oriented Computing (ROC) Project

The Recovery-Oriented Computing (ROC) project is a joint Berkeley/Stanford research project that is investigating novel techniques for building highly-dependable Internet services.

Read an overview of our research into Recovery-Oriented Computing.

Quick navigate to: [ Research | People | Publications | Talks | Retreats | Projects | Stanford Page | Internal ]

ROC News

• New RAD Lab project and website!
  • Summer 2005 RADS Retreat
• Winter 2005 ROC Retreat
• Please participate in our BOINC projects collecting Windows crash data and resource availability.
• Laying the foundation for the next-generation of distributed computing. EE Times, November 2004
• CS 444A/294-4 Reliable Adaptive Distributed Systems (RADS) Class, Fall 2004
• Summer 2004 ROC Retreat
• Release of initial implementation of Undo for System Administrators and Operators (v0.1) (12 June 2003)
• Self-Repairing Computers. Scientific American, June 2003.
• CHI 2003 workshop "System Administrators are Users, Too: Designing Workspaces for Managing Internet-scale Systems", April 7th, 2003.
• Autonomic Computing. Scientific American, May 2002.

People

Courses

• Berkeley CS294-4/Stanford CS444A "Reliable Adaptive Distributed Systems". Thursdays, 3:15-6:00 PM (Gates 100, Stanford) or 2:10-6:00 (320 Soda Hall, Berkeley).  From 9 September to 9 December 2004.

Fall 2001

• Berkeley CS294-4/Stanford CS444A "Recovery-Oriented Computing Seminar".

Publications

General ROC

• Patterson, D. A., A. Brown, P. Broadwell, G. Candea, M. Chen, J. Cutler, P. Enriquez, A. Fox, E. Kiciman, M. Merzbacher, D. Oppenheimer, N. Sastry, W. Tetzlaff, J. Traupman, N. Treuhaft. Recovery-Oriented Computing (ROC): Motivation, Definition, Techniques, and Case Studies. UC Berkeley Computer Science Technical Report UCB//CSD-02-1175, March 15, 2002. [pdf] [doc]
   
• Brown, A. and D. A. Patterson. Embracing Failure: A Case for Recovery-Oriented Computing (ROC). 2001 High Performance Transaction Processing Symposium, Asilomar, CA, October 2001. [pdf]
   
• Brown, A. and D. A. Patterson. To Err is Human. Proceedings of the First Workshop on Evaluating and Architecting System dependabilitY (EASY '01), Göteborg, Sweden, July 2001. [pdf]
   
• Brown, A. Accepting Failure: Availability through Repair-Centric System Design. UC Berkeley Qualifying Examination Proposal, Berkeley, CA, April 2001. [pdf]

ROC Techniques

• Brown, A.  A Recovery-Oriented Approach to Dependable Services: Repairing Past Errors With System-Wide Undo, UC Berkeley Computer Science Division Technical Report UCB//CSD-04-1304, December 2003. [abstract] [pdf]
   
• Brown, A. and D. A. Patterson. Undo for Operators: Building an Undoable E-mail Store. In Proceedings of the 2003 USENIX Annual Technical Conference, San Antonio, TX, June 2003 (Best Paper Award). [pdf] [html]
   
• Brown, A. and D. A. Patterson. Rewind, Repair, Replay: Three R's to Dependability. 10th ACM SIGOPS European Workshop, Saint-Emilion, France, September 2002. [pdf]
   
• George Candea and Armando Fox. A Utility-Centered Approach to Building Dependable Infrastructure Services, Appears in Proc. 10th ACM SIGOPS European Workshop (EW-2002), Saint-Émilion, France, September 2002. [pdf]
   
• Broadwell, P., N. Sastry and J. Traupman. FIG: A Prototype Tool for Online Verification of Recovery Mechanisms. To appear in Workshop on Self-Healing, Adaptive and self-MANaged Systems (SHAMAN), New York, NY, June 2002. [pdf]
   
• George Candea, James Cutler, Armando Fox, Rushabh Doshi, Priyank Garg, Rakesh Gowda.  Reducing Recovery Time in a Small Recursively Restartable System. Proc. International Conference on Dependable Systems and Networks (DSN-2002), Washington, D.C., June 2002. [pdf]
   
• George Candea and Armando Fox. Recursive Restartability: Turning the Reboot Sledgehammer into a Scalpel. Proc. 8th Workshop on Hot Topics in Operating Systems (HotOS-VIII), Schloss Elmau, Germany, May 2001. [pdf]

Diagnosis

• Oppenheimer, D. The importance of understanding distributed system configuration. System Administrators are Users, Too: Designing Workspaces for Managing Internet-Scale Systems (CHI 2003 (Conference on Human Factors in Computing Systems) workshop), April 2003. [pdf] 

• Chen, M., E. Kiciman, E. Fratkin, E. Brewer and A. Fox. Pinpoint: Problem Determination in Large, Dynamic, Internet Services. Proceedings of the International Conference on Dependable Systems and Networks (IPDS Track), Washington D.C., 2002. [Abstract] [pdf]
   
• George Candea and Armando Fox. Designing for High Availability and Measurability. Proc. 1st Workshop on Evaluating and Architecting System Dependability (EASY), Göteborg, Sweden, July 2001. [pdf]
   
• Brown, A., G. Kar, and A. Keller. An Active Approach to Characterizing Dynamic Dependencies for Problem Determination in a Distributed Environment. Proceedings of the Seventh IFIP/IEEE International Symposium on Integrated Network Management (IM 2001), Seattle, WA, May 2001. [pdf]

Benchmarking and System Measurement

• Brown, A., L. Chung, W. Kakes, C. Ling, and D.A. Patterson. Experience with Evaluating Human-Assisted Recovery Processes. Proceedings of the 2004 International Conference on Dependable Systems and Networks. Florence, Italy, June 2004. [pdf] [materials]

• Broadwell, P.  Response Time as a Performability Metric for Online Services. UC Berkeley Computer Science Technical Report UCB CSD-04-1324, May 2004. [pdf]
  

• Oppenheimer, D., Archana Ganapathi, and David A. Patterson. Why do Internet services fail, and what can be done about it? 4th USENIX Symposium on Internet Technologies and Systems (USITS '03), March 2003. [pdf] [talk slides]

• Oppenheimer, D., Aaron B. Brown, Jonathan Traupman, Pete Broadwell, and David A. Patterson. Practical issues in dependability benchmarking. Second Workshop on Evaluating and Architecting System Dependability (EASY), October 2002. [pdf]

• Oppenheimer, D. and D. A. Patterson. Studying and using failure data from large-scale Internet services. 10th ACM SIGOPS European Workshop, Saint-Emilion, France, September 2002. [pdf]

• Merzbacher, M and Dan Patterson. Measuring End-User Availability on the Web: Practical Experience. International Performance and Dependability Symposium, Washington DC, June 2002. [pdf] [ps] [doc]

• Oppenheimer, D. Why do Internet services fail, and what can be done about it? UC Berkeley Computer Science Division Technical Report UCB//CSD-02-1185, May 2002. [pdf]

• Patterson, D. A. A simple way to estimate the cost of downtime. Submission to 16th Systems Administration Conference (LISA '02), 2002. [pdf]

• Brown, A., L. C. Chung, D. A. Patterson. Including the Human Factor in Dependability Benchmarks. To appear in the 2002 DSN Workshop on Dependability Benchmarking, Washington, D.C., June 2002. [pdf]

• Oppenheimer, D. and D. A. Patterson. Architecture, operation, and dependability of large-scale Internet services: three case studies. IEEE Internet Computing special issue on Global Deployment of Data Centers, September/October 2002. [pdf]

• Brown, A. Towards Availability and Maintainability Benchmarks: A Case Study of Software RAID Systems. UC Berkeley Masters Report, also available as UC Berkeley Computer Science Division Technical Report UCB//CSD-01-1132, Berkeley, CA, January 2001. [pdf] [ps] 

• Brown, A. Availability Benchmarking of a Database System. Unpublished report, soon to be a Technical Report, Berkeley, CA, December 2000.  

• Brown, A. and D.A. Patterson. Towards Availability Benchmarks: A Case Study of Software RAID Systems. Proceedings of the 2000 USENIX Annual Technical Conference, San Diego, CA, June 2000. [pdf] [ps] [html]

ROC Hardware

• Oppenheimer, D., A. Brown, J. Beck, D. Hettena, J. Kuroda, N. Treuhaft, D.A. Patterson, and K. Yelick. ROC-1: Hardware Support for Recovery-Oriented Computing. IEEE Transactions on Computers, vol. 51, no. 2, February 2002. [pdf]

Talks

General ROC

• A Simple Way to Estimate the Cost of Downtime. David Patterson. USENIX 16th System Administrators Conference (LISA '02). Presented November 7, 2002, Philadelphia, CA. [ppt] [pdf]
   
• Recovery Oriented Computing. David Patterson. Presented at Princeton University, University of Illinois, and University of Michigan, October 2002. [ppt] [pdf]
   
• Recovery Oriented Computing: A New Research Agenda for a New Century. David Patterson. 8th International Symposium on High-Performance Computer Architecture (HPCA 8) Keynote address, Presented  February 6, 2002, Boston, MA. [Abstract] [ppt] [pdf] [MADtv clip] [MadTV clip script]
   
• Availability and Maintainability >> Performance: New Focus for a New Century. David Patterson. USENIX Conference on File and Storage Technologies (FAST '02) Keynote address, Presented January  29, 2002, Monterey, CA. [Abstract] [ppt] [pdf]
   
• Recovery-Oriented Computing. Keynote Address by David Patterson at High Performance Transaction Systems Workshop (HPTS), October 2001. [ppt] [pdf]
   
• CS 294-4 First lecture. David Patterson. September 6, 2001 [ppt] [pdf]
   
• Recovery-Oriented Computing. David Patterson. HP Labs, June 6, 2001. [Abstract] [ppt] [pdf]
   
• Embracing Failure: Availability through Recovery-Oriented Computing (ROC). Aaron Brown. Stanford CS548 Guest Lecture, May 2, 2001. [Abstract] [ppt] [pdf]
   
• Embracing Failure: Availability through Repair-Centric Design. Aaron Brown. UC Berkeley Qualifying Examination Presentation, April 13, 2001. [ppt] [pdf]
   

• Reboot-Based High Availability. George Candea. Work-in-progress talk and poster, Symposium for Operating System Design and Implementation (OSDI),San Diego, CA, October 2000. [pdf](Abstract) [pdf](Poster)

• Measuring End-User Availability and the Web: Practical Experience.  Matthew Merzbacher.  International Performance and Dependability Symposium, Washington DC, June 24, 2002. [ppt - 61.5KB]

Undo and Human Error

• Rewind, Repair, Replay: Three R's to Dependability. Aaron Brown. SIGOPS European Workshop, St. Emilion, France, September 2002. [ppt]
   
• Rewind, Repair, Replay: Three R's to cope with human error. Talk given at IBM Almaden, March 2002. [ppt] [pdf]
   
• Bringing Undo to System Administration: A New Paradigm for Recovery. Work-in-progress talk, 15th Annual Systems Administration Conference (LISA 2001), December 2001. [ppt] [pdf]
   
• To Err is Human. First EASY Workshop, Göteborg, Sweden, July 1, 2001. [ppt] [pdf]
   
• Addressing Human Error with Undo. Summer 2001 ISTORE Retreat, Granlibakken, CA, June 2001. [ppt] [pdf]

ROC Techniques

Diagnosis

• An Active Approach to Characterizing Dynamic Dependencies for Problem Determination. IM 2001 Conference, May 16, 2001. [ppt] [pdf]

Benchmarking

• Availability and Maintainability Benchmarks: A Case Study of Software RAID Systems. UC Berkeley CS294-8 Guest Lecture, November 7, 2000. [ppt] [pdf]

Retreat Talks and Posters

• Summer 2004
• Winter 2004
• Summer 2003
• Winter 2003
• Summer 2002
• Winter 2002

Hardware

• IBM X-Cluster
• ROC-1 (see ISTORE-1) Cluster

Projects

• SWORD: Scalable Wide-Area Resource Discovery
• The Stanford Software Infrastructures Group ROC Page
• FIG: Library-Level Error Injection for Shared Libraries in UNIX/Linux. [download tar.gz]
• Undo for System Administrators and Operators (source code available)

The ROC project is funded by NSF grant no. CCR-0085899, the NASA CICT (Computing, Information & Communication Technologies) Program, an NSF CAREER award, Allocity, Hewlett Packard, IBM, Microsoft, NEC, and Sun Microsystems.