WIP: Resilience

bibliography.bib

@@ -957,3 +957,341 @@ @misc{olcf:ace
   year          = "2024",
   url           = "https://docs.olcf.ornl.gov/ace_testbed/"
 }
+
+@article{daly06higher,
+  author        = "John T. Daly",
+  title         = "A higher order estimate of the optimum checkpoint interval for restart dumps",
+  journal       = "Future Generation Computer Systems",
+  volume        = "22",
+  number        = "3",
+  pages         = "303--312",
+  year          = 2006,
+  issn          = "0167-739X",
+  doi           = "10.1016/j.future.2004.11.016"
+}
+
+@inproceedings{Bautista-Gomez:2011,
+author = {Bautista-Gomez, Leonardo and Tsuboi, Seiji and Komatitsch, Dimitri and Cappello, Franck and Maruyama, Naoya and Matsuoka, Satoshi},
+title = {{FTI}: High Performance Fault Tolerance Interface for Hybrid Systems},
+booktitle = {Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis},
+series = {SC '11},
+year = {2011},
+isbn = {978-1-4503-0771-0},
+location = {Seattle, Washington},
+pages = {32:1--32:32},
+articleno = {32},
+numpages = {32}
+}
+
+@inproceedings{ansel2009dmtcp,
+  title={{DMTCP}: Transparent Checkpointing for Cluster Computations
+         and the Desktop},
+  author={Ansel, Jason and Arya, Kapil and Cooperman, Gene},
+  booktitle={2009 IEEE International Symposium on Parallel
+	 \& Distributed Processing (IPDPS'09)},
+  pages={1--12},
+  year={2009},
+  organization={IEEE},
+  address   = "Rome, Italy",
+}
+
+@inproceedings{Fiala:2012,
+  author        = "David Fiala
+                   and Frank Mueller
+                   and Christian Engelmann
+                   and Kurt Ferreira
+                   and Ron Brightwell
+                   and Rolf Riesen",
+  title         = "Detection and Correction of Silent Data Corruption for
+                   Large-Scale High-Performance Computing",
+  booktitle     = "Proceedings of the $25^{th}$ IEEE/ACM International
+                   Conference on High Performance Computing, Networking, Storage
+                   and Analysis (SC) 2012",
+  pages         = "78:1--78:12",
+  month         = nov # "~10-16, ",
+  year          = "2012",
+  address       = "Salt Lake City, UT, USA",
+  publisher     = "ACM Press, New York, NY, USA",
+  isbn          = "978-1-4673-0804-5",
+  doi           = "10.1109/SC.2012.49"
+}
+
+@article{he09symmetric,
+  author        = "Xubin (Ben) He
+                   and Li Ou
+                   and Christian Engelmann
+                   and Xin Chen
+                   and Stephen L. Scott",
+  title         = "Symmetric Active/Active Metadata Service for High
+                   Availability Parallel File Systems",
+  journal       = "Journal of Parallel and Distributed Computing (JPDC)",
+  volume        = "69",
+  number        = "12",
+  pages         = "961-973",
+  month         = dec,
+  year          = "2009",
+  publisher     = "Elsevier B.V, Amsterdam, The Netherlands",
+  issn          = "0743-7315",
+  doi           = "10.1016/j.jpdc.2009.08.004"
+}
+
+@inproceedings{yu06benefits,
+  author        = "Weikuan Yu and Ranjit Noronha and Shuang Liang and Dhabaleswar K. Panda",
+  title         = "Benefits of High Speed Interconnects to Cluster File Systems: {A} Case Study with {Lustre}",
+  booktitle     = "Proceedings of the $20^{st}$ {IEEE} International Parallel and Distributed Processing Symposium ({IPDPS}) 2006",
+  pages         = "8-15",
+  month         = apr # "~25-29, ",
+  year          = "2006",
+  address       = "Rhodes Island, Greece",
+  publisher     = "IEEE Computer Society",
+  isbn          = "1-4244-0054-6"
+}
+
+@inproceedings{yoo03slurm,
+  author        = "Andy B. Yoo and Morris A. Jette and Mark Grondona",
+  title         = "{SLURM}: {S}imple {Linux} Utility for Resource Management",
+  booktitle     = "Lecture Notes in Computer Science: Proceedings of the $9^{th}$ International Workshop on Job Scheduling Strategies for Parallel Processing ({JSSPP}) 2003",
+  volume        = "2862",
+  pages         = "44--60",
+  month         = jun # "~24, ",
+  year          = "2003",
+  address       = "Seattle, WA, USA",
+  publisher     = "Springer",
+  isbn          = "978-3-540-20405-3, ISSN 0302-9743"
+}
+
+@misc{IPMI,
+  title         = "Intelligent Platform Management Interface ({IPMI}), v2.0 specification",
+  howpublished  = "\url{http://www.intel.com/content/www/us/en/servers/ipmi/ipmi-home.html}",
+  year          = "2015",
+}
+
+@article{Ganglia,
+author = {Massie, Matthew L and Chun, Brent N and Culler, David E},
+title = {The ganglia distributed monitoring system: design, implementation, and experience},
+journal = {Parallel Computing},
+volume = {30},
+number = {7},
+pages = {817 - 840},
+year = {2004},
+issn = {0167-8191},
+doi = {http://dx.doi.org/10.1016/j.parco.2004.04.001},
+url = {http://ganglia.info/},
+}
+
+@article{pla06drbd,
+  author        = "Pedro Pla",
+  title         = "DRBD in a Heartbeat",
+  journal       = "Linux Journal (LJ)",
+  month         = sep,
+  year          = "2006",
+  url           = "http://www.linuxjournal.com/article/9074",
+  abstract      = "How to build a redundant, high-availability system with DRBD and Heartbeat."
+}
+
+@Misc{vampir,
+  title         = "Vampir - Performance Optimization",
+  howpublished  = "\url{https://vampir.eu}",
+}
+
+@inproceedings{engelmann09proactive,
+  author        = "Christian Engelmann
+                   and Geoffroy R. Vall\'ee
+                   and Thomas Naughton
+                   and Stephen L. Scott",
+  title         = "Proactive Fault Tolerance Using Preemptive Migration",
+  booktitle     = "Proceedings of the $17^{th}$ Euromicro International
+                   Conference on Parallel, Distributed, and network-based
+                   Processing (PDP) 2009",
+  pages         = "252--257",
+  month         = feb # "~18-20, ",
+  year          = "2009",
+  address       = "Weimar, Germany",
+  publisher     = "IEEE Computer Society, Los Alamitos, CA, USA",
+  isbn          = "978-0-7695-3544-9",
+  issn          = "1066-6192",
+  doi           = "10.1109/PDP.2009.31"
+}
+
+@article{wang12proactive,
+  author        = "Chao Wang
+                   and Frank Mueller
+                   and Christian Engelmann
+                   and Stephen L. Scott",
+  title         = "Proactive Process-Level Live Migration and Back Migration in
+                   {HPC} Environments",
+  journal       = "Journal of Parallel and Distributed Computing (JPDC)",
+  volume        = "72",
+  number        = "2",
+  pages         = "254--267",
+  month         = feb,
+  year          = "2012",
+  publisher     = "Elsevier B.V, Amsterdam, The Netherlands",
+  issn          = "0743-7315",
+  doi           = "10.1016/j.jpdc.2011.10.009"
+}
+
+@inproceedings{nagarajan07proactive,
+  author        = "Arun B. Nagarajan
+                   and Frank Mueller
+                   and Christian Engelmann
+                   and Stephen L. Scott",
+  title         = "Proactive Fault Tolerance for {HPC} with {Xen}
+                   Virtualization",
+  booktitle     = "Proceedings of the $21^{st}$ ACM International
+                   Conference on Supercomputing (ICS) 2007",
+  pages         = "23--32",
+  month         = jun # "~16-20, ",
+  year          = "2007",
+  address       = "Seattle, WA, USA",
+  publisher     = "ACM Press, New York, NY, USA",
+  isbn          = "978-1-59593-768-1",
+  doi           = "10.1145/1274971.1274978"
+}
+
+@inproceedings{liang06blue, 
+  author        = "Yinglung Liang
+                   and Yanyong Zhang
+                   and A. Sivasubramaniam
+                   and M. Jette and R. Sahoo", 
+  title         = "{Blue Gene/L} Failure Analysis and Prediction Models",
+  booktitle     = "Proceedings of the $36^{th}$ IEEE/IFIP International Conference
+                   on Dependable Systems and Networks (DSN) 2006",
+  pages         = "425-434",
+  month         = jun,
+  year          = "2006",
+  publisher     = "IEEE Computer Society, Los Alamitos, CA, USA",
+  issn          = "1530-0889",
+  doi           = "10.1109/DSN.2006.18"
+}
+
+@inproceedings{sahoo03critical,
+  author        = "Sahoo, R. K.
+                   and Oliner, A. J.
+                   and Rish, I.
+                   and Gupta, M.
+                   and Moreira, J. E.
+                   and Ma, S.
+                   and Vilalta, R.
+                   and Sivasubramaniam, A.",
+  title         = "Critical Event Prediction for Proactive Management in Large-scale
+                   Computer Clusters",
+  booktitle     = "Proceedings of the $9^{th}$ ACM SIGKDD International Conference
+                   on Knowledge Discovery and Data Mining (KDD) 2003",
+  pages         = "426--435",
+  year          = "2003",
+  address       = "Washington, DC, USA",
+  publisher     = "ACM Press, New York, NY, USA",
+  isbn          = "1-58113-737-0",
+  doi           = "10.1145/956750.956799"
+}
+
+@misc{Nvidia:DPR,
+author={Nvidia},
+title={Dynamic Page Retirement, Reference Guide vR352},
+howpublished={\url{https://docs.nvidia.com/deploy/pdf/Dynamic_Page_Retirement.pdf}},
+year={2015},
+}
+
+@article{Bland:2013:IJHPCA,
+ author = {Bland, Wesley and Bouteiller, Aurelien and Herault, Thomas and Bosilca, George and Dongarra, Jack},
+ title = {Post-failure recovery of {MPI} communication capability: Design and rationale},
+ volume = {27},
+ number = {3},
+ pages = {244-254},
+ year = {2013},
+ journal = {International Journal of High Performance Computing Applications}
+}
+
+@article{Chien:2016,
+author = {A Chien and P Balaji and N Dun and A Fang and H Fujita and K Iskra and Z Rubenstein and Z Zheng and J Hammond and I Laguna and D Richards and A Dubey and B van Straalen and M Hoemmen and M Heroux and K Teranishi and A Siegel},
+title = {Exploring versioned distributed arrays for resilience in scientific applications: global view resilience},
+journal = {The International Journal of High Performance Computing Applications},
+volume = {0},
+number = {0},
+pages = {1094342016664796},
+year = {0},
+doi = {10.1177/1094342016664796},
+}
+
+@article{ltaief08fault,
+  author        = "Hatem Ltaief and Edgar Gabriel and Marc Garbey",
+  title         = "{F}ault Tolerant Algorithms for Heat Transfer Problems",
+  journal       = "Journal of Parallel and Distributed Computing (JPDC)",
+  volume        = "68",
+  number        = "5",
+  pages         = "663--677",
+  year          = "2008",
+  publisher     = "Elsevier",
+  issn          = "0743-7315",
+  doi           = "10.1016/j.jpdc.2007.09.004"
+}
+
+@inproceedings{Chung:2011:SC,
+ author = {Chung, Jinsuk and Lee, Ikhwan and Sullivan, Michael and Ryoo, Jee Ho and Kim, Dong Wan and Yoon, Doe Hyun and Kaplan, Larry and Erez, Mattan},
+ title = {Containment domains: a scalable, efficient, and flexible resilience scheme for exascale systems},
+ booktitle = {Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis},
+ year = {2012},
+ location = {Salt Lake City, Utah},
+ pages = {58:1--58:11},
+ numpages = {11},
+}
+
+@Misc{Mellanox:2011,
+authors={Mellanox Technologies},
+title={Mellanox {I}nfiniBand {FDR} 56{G}b/s For Server and Storage Interconnect Solutions},
+howpublished={\url{http://www.mellanox.com/related-docs/whitepapers/WP_InfiniBand_FDR.pdf}},
+year={2011},
+}
+
+@book{Moon:2005,
+title={Error Correction Coding: Mathematical Methods and Algorithms},
+author={Moon, Todd K},
+year={2005},
+publisher={Wiley-Interscience},
+isbn={9780471648000},
+doi={10.1002/0471739219}
+}
+
+@article{Huang:1984,
+author={Kuang-Hua Huang and J. A. Abraham},
+journal={IEEE Transactions on Computers},
+title={Algorithm-Based Fault Tolerance for Matrix Operations},
+year={1984},
+volume={C-33},
+number={6},
+pages={518-528},
+month={June},
+}
+
+@inproceedings{jeong203d,
+  author        = "Haewon Jeong
+                   and Yaoqing Yang
+                   and Christian Engelmann
+                   and Vipul Gupta
+                   and Tze Meng Low
+                   and Pulkit Grover
+                   and Viveck Cadambe
+                   and Kannan Ramchandran",
+  title         = "{3D} Coded {SUMMA}: {C}ommunication-Efficient and Robust
+                   Parallel Matrix Multiplication",
+  booktitle     = "Lecture Notes in Computer Science: Proceedings of the
+                   26th European Conference on Parallel and Distributed Computing
+                   (Euro-Par) 2020",
+  volume        = "12247",
+  pages         = "392--407",
+  month         = aug # "~24-28, ",
+  year          = "2020",
+  address       = "Warsaw, Poland",
+  publisher     = "Springer Verlag, Berlin, Germany",
+  isbn          = "978-3-030-57674-5",
+  doi           = "10.1007/978-3-030-57675-2\_25"
+}
+
+@misc{ibm:chipkill,
+  author        = "Timothy J. Dell",
+  title         = "A White Paper on the Benefits of Chipkill-Correct {ECC} for {PC} Server Main Memory",
+  year          = "1997",
+  howpublished  = "{IBM Microelectronics Division}",
+  url           = "http://www.ece.umd.edu/courses/enee759h.S2003/references/chipkill_white_paper.pdf"
+}

sos/logical/errors.rst

@@ -309,7 +309,9 @@ User-defined response
    user-defined response would request additional resources ahead of time and
    perform user-defined actions when required. Additionally, delegation may
    also be an appropriate user-defined response, such as when another task is
-   better equipped to handkle an error or failure.
+   better equipped to handkle an error or failure. See
+   :ref:`intersect:arch:sos:logical:resilience` for  different options for a
+   user-defined response.
 
 There is also the aspect of error and failure handling in the
 :ref:`intersect:arch:sos:operational`, specifically with

sos/logical/index.rst

@@ -20,3 +20,4 @@ between the different components. The logical view defines
    systems/index
    adapters
    errors
+   resilience/index