Jay J. Wylie

Contact information

Background

I am interested in distributed systems, storage systems, scalable systems, erasure codes, consistency protocols, fault tolerance, and dependability.

Publications

Early experiences on the journey towards self-* storage.
Michael Abd-El-Malek, William V. Courtright II, Chuck Cranor, Gregory R. Ganger, James Hendricks, Andrew J. Klosterman, Michael Mesnier, Manish Prasad, Brandon Salmon, Raja R. Sambasivan, Shafeeq Sinnamohideen,John D. Strunk, Eno Thereska, Matthew Wachs, Jay J. Wylie. Early experiences on the journey towards self-* storage. IEEE Data Engineering Bulletin 29(3). Special issue on Self-managing database systems. September 2006.

Efficient eventual consistency in Pahoehoe, an erasure-coded key-blob archive.
Eric Anderson, Xiaozhou Li, Arif Merchant, Mehul A. Shah, Kevin Smathers, Joseph Tucek, Mustafa Uysal, Jay J. Wylie. Efficient eventual consistency in Pahoehoe, an erasure-coded key-blob archive. International Conference on Dependable Systems & Networks, June 28-July 1, 2010.

Flat XOR-based erasure codes in storage systems: Constructions, efficient recovery, and tradeoffs.
Kevin M. Greenan, Xiaozhou Li, Jay J. Wylie. Flat XOR-based erasure codes in storage systems: Constructions, efficient recovery, and tradeoffs. IEEE Symposium on Massive Storage Systems and Technologies (MSST2010), May, 2010.
Talk slides: greenan-msst10-talk.pdf.
Errata: errata.txt.

Reliability of flat XOR-based erasure codes on heterogeneous devices
Kevin M. Greenan, Ethan L. Miller, and Jay J. Wylie. Reliability of flat XOR-based erasure codes on heterogeneous devices. International Conference on Dependable Systems & Networks, June, 2008.

Determining fault tolerance of XOR-based erasure codes efficiently
Jay J. Wylie, Ram Swaminathan. Determining fault tolerance of XOR-based erasure codes efficiently. International Conference on Dependable Systems & Networks, June, 2007.
Errata: errata.txt. Correction to Table 3.

Informed data distribution selection in a self-predicting storage system.
Eno Thereska, Michael Abd-El-Malek, Jay J. Wylie, Dushyanth Narayanan, Gregory R. Ganger. Informed data distribution selection in a self-predicting storage system. Proceedings of the International Conference on Autonomic Computing (ICAC-06), Dublin, Ireland. June 12th-16th 2006.

Ursa Minor: versatile cluster-based storage. Award paper!
Michael Abd-El-Malek, William V. Courtright II, Chuck Cranor, Gregory R. Ganger, James Hendricks, Andrew J. Klosterman, Michael Mesnier, Manish Prasad, Brandon Salmon, Raja R. Sambasivan, Shafeeq Sinnamohideen, John D. Strunk, Eno Thereska, Matthew Wachs, Jay J. Wylie. Ursa Minor: versatile cluster-based storage. USENIX Conference on File and Storage Technologies (FAST, San Francisco, CA, December 14--16, 2005), USENIX Association, 2005.

Lazy verification in fault-tolerant distributed storage systems.
Michael Abd-El-Malek, Gregory R. Ganger, Garth R. Goodson, Michael K. Reiter, Jay J. Wylie. Lazy verification in fault-tolerant distributed storage systems. SRDS 2005, October 26-28, 2005, Orlando, Florida, USA.

Fault-scalable Byzantine fault-tolerant services.
Michael Abd-El-Malek, Gregory R. Ganger, Garth R. Goodson, Michael K. Reiter, Jay J. Wylie. Fault-scalable Byzantine fault-tolerant services. SOSP, October 23-26, 2005, Brighton, United Kingdom.

Efficient Byzantine-tolerant erasure-coded storage.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. Efficient Byzantine-tolerant erasure-coded storage. International Conference on Dependable Systems & Networks, June, 2004.

Survivable storage systems.
Gregory R. Ganger, Pradeep K. Khosla, Mehmet Bakkaloglu, Michael W. Bigrigg, Garth R. Goodson, Semih Oguz, Vijay Pandurangan, Craig A. N. Soules, John D. Strunk, Jay J. Wylie. Survivable storage systems. DARPA Information Survivability Conference and Exposition (Anaheim, CA, 12-14 June 2001), pages 184-195 volume 2. IEEE, 2001.

Finding the most fault-tolerant flat XOR-based erasure codes for storage systems (Invited paper)
Jay J. Wylie. Finding the most fault-tolerant flat XOR-based erasure codes for storage systems (Invited paper). The 45th Asilomar Conference on Signals, Systems, and Computers (SSC 2011), November 6-9, 2011, Pacific Grove, CA, USA.

What Consistency Does Your Key-Value Store Actually Provide?
Eric Anderson, Xiaozhou Li, Mehul A. Shah, Joseph Tucek, and Jay J. Wylie. What Consistency Does Your Key-Value Store Actually Provide? The sixth Workshop on Hot Topics in System Dependability (HotDep 2010), October 3, 2010, Vancouver, BC, CANADA.

Mean Time to Meaningless: MTTDL, Markov Models, and Storage System Reliability.
Kevin M. Greenan, James S. Plank, Jay J. Wylie. Mean Time to Meaningless: MTTDL, Markov Models, and Storage System Reliability. The 2nd Workshop on Hot Topics in Storage Systems (HotStorage2010), June 22, 2010, Boston MA, USA.

Consistability: Describing usually consistent systems.
Amitanand S. Aiyer, Eric Anderson, Xiaozhou Li, Mehul A. Shah, Jay J. Wylie. Consistability: Describing usually consistent systems. Fourth workshop on Hot Topics in Dependability, December 7, 2008, San Diego, California, USA.

A Spin-Up Saved is Energy Earned: Achieving Power-Efficient, Erasure-Coded Storage.
Kevin M. Greenan, Darrell D.E. Long, Ethan L. Miller, Thomas J. E. Schwarz, Jay J. Wylie. A Spin-Up Saved is Energy Earned: Achieving Power-Efficient, Erasure-Coded Storage. Fourth workshop on Hot Topics in Dependability, December 7, 2008, San Diego, California, USA.

A protocol family approach to survivable storage infrastructures.
Jay J. Wylie, Garth R. Goodson, Gregory R. Ganger, Michael K. Reiter. A protocol family approach to survivable storage infrastructures. Position paper. FuDiCo II: S.O.S. (Survivability: Obstacles and Solutions), 2nd Bertinoro Workshop on Future Directions in Distributed Computing, 23-25 June 2004, University of Bologna Residential Center, Bertinoro (Forlì), Italy.

Modeling correlated failures in survivable storage systems.
Mehmet Bakkaloglu, Jay J. Wylie, Chenxi Wang, Gregory R. Ganger. Modeling correlated failures in survivable storage systems. Fast Abstract at International Conference on Dependable Systems & Networks, June, 2002.
See Technical Report CMU-CS-02-129 below for full length article.

Survivable information storage systems.
Jay J. Wylie, Michael W. Bigrigg, John D. Strunk, Gregory R. Ganger, Han Kiliccote, and Pradeep K. Khosla. Survivable information storage systems. IEEE Computer, 33(8):61-68, August 2000.

A read/write protocol family for versatile storage infrastructures.
Jay J. Wylie. Published as Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-05-107, October, 2005.

Implementing Prato, a database on demand service (extended abstract)
Soila Pertet, John Wilkes, Jay J. Wylie. Implementing Prato, a database on demand service (extended abstract). Invited paper at the First International Workshop on Policy-Based Autonomic Computing (PBAC), June 11-15, 2007, Jacksonville, FL, USA. (Held in conjunction with HotAC II.)

Towards bounded wait-free PASIS (extended abstract).
Michael Abd-El-Malek, Gregory R. Ganger, Garth R. Goodson, Michael K. Reiter, Jay J. Wylie. Towards bounded wait-free PASIS (extended abstract). Dagstuhl Seminar From Security to Dependability, September 10-15, 2006, Schloss Dagstuhl, Germany.

Elie Krevat, Tomer Shiran, Eric Anderson, Joseph Tucek, Jay J. Wylie, and Gregory R. Ganger. Applying Idealized Lower-Bound Runtime Models to Understand Inefficiencies in Data-Intensive Computing. ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2011), June 7–11, 2011, San Jose, CA, USA.

On the Consistability of Storage Systems
Amitanand Aiyer, Eric Anderson, Xiaozhou Li, Mehul Shah, and Jay J. Wylie. On the Consistability of Storage Systems. Work-in-progress talk and poster at the Seventh USENIX Conference on File and Storage Technologies (FAST), February 24-27, 2009, San Francisco, CA, USA.

Reliability Markov models are becoming unreliable.
Kevin M. Greenan, Jay J. Wylie. Reliability Markov models are becoming unreliable. Work-in-progress talk and poster at the Sixth USENIX Conference on File and Storage Technologies (FAST), February 26-29, 2008, San Jose, CA, USA.

High-fidelity reliability simulation of XOR-based erasure codes.
Kevin M. Greenan, Jay J. Wylie. High-fidelity reliability simulation of XOR-based erasure codes. Poster at the Sixth USENIX Conference on File and Storage Technologies (FAST), February 26-29, 2008, San Jose, CA, USA.

Prato: databases on demand
Soila Pertet, Priya Narasimhan, John Wilkes, Jay J. Wylie. Prato: databases on demand. Poster at the IEEE International Conference on Autonomic Computing (ICAC) 07, June 11-14, 2007, Jacksonville, FL, USA.

List of Most Fault-Tolerant Flat XOR-based Erasure Codes for Storage Systems.
Jay J. Wylie. List of Most Fault-Tolerant Flat XOR-based Erasure Codes for Storage Systems. Hewlett-Packard Laboratories Technical Report HPL-2011-217, November, 2011.
Note this TR is a gzipped text file.

Correctness of the Read/Conditional-Write and Query/Update Protocols.
Michael Abd-El-Malek, Gregory R. Ganger, Garth R. Goodson, Michael K. Reiter, Jay J. Wylie. Correctness of the Read/Conditional-Write and Query/Update Protocols. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-05-107, September, 2005.

The safety and liveness properties of a protocol family for versatile survivable storage infrastructures.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. The safety and liveness properties of a protocol family for versatile survivable storage infrastructures. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-03-105, March 2004.

Efficient Byzantine-tolerant Erasure-coded Storage.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. Efficient Byzantine-tolerant Erasure-coded Storage. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-03-104, December 2003.
Please cite DSN 2004 conference publication listed above.

A protocol family for versatile survivable storage infrastructures.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. A protocol family for versatile survivable storage infrastructures. Carnegie Mellon University Parallel Data Lab Technical Report CMU-PDL-03-103, December 2003.

Byzantine-tolerant erasure-coded storage.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. Byzantine-tolerant erasure-coded storage. Technical Report CMU-CS-03-187. Carnegie Mellon University , September 2003.
This technical report is superseded by CMU-PDL-03-103, -104 and -105 listed above.

Efficient consistency for erasure-coded data via versioning servers.
Garth R. Goodson, Jay J. Wylie, Gregory R. Ganger, Michael K. Reiter. Efficient consistency for erasure-coded data via versioning servers. Technical Report CMU-CS-03-127. Carnegie Mellon University , April 2003.
This technical report is superseded by CMU-PDL-03-103, -104 and -105 listed above.

Decentralized storage consistency via versioning servers.
Garth Goodson, Jay J. Wylie, Greg Ganger, Mike Reiter. Decentralized storage consistency via versioning servers. Technical Report CMU-CS-02-180. Carnegie Mellon University, September 2002.
This technical report is superseded by CMU-PDL-03-103, -104 and -105 listed above.

On correlated failures in survivable storage systems.
Mehmet Bakkaloglu, Jay J. Wylie, Chenxi Wang, Gregory R. Ganger. On correlated failures in survivable storage systems. Technical Report CMU-CS-02-129. Carnegie Mellon University, May 2002.

Selecting the right data distribution scheme for a survivable storage system.
Jay J. Wylie, Mehmet Bakkaloglu, Vijay Pandurangan, Michael W. Bigrigg, Semih Oguz, Ken Tew, Cory Williams, Gregory R. Ganger, and Pradeep K. Khosla. Selecting the right data distribution scheme for a survivable storage system. Technical report CMU-CS-01-120. Carnegie Mellon University, May 2001.