1 @InProceedings
{labos2009
:viera09
,
2 address = {Estoril
, Lisbon
, Portugal
},
4 author = {Vieira
, Gustavo M. D. and Zwaenepoel
, Willy and Buzato
, Luis E.
},
5 booktitle = {Proceedings of the
39th
{I
}nternational
{C
}onference on
6 {D
}ependable
{S
}ystems and
{N
}etworks
({DSN
})},
7 details
= {http
://infoscience.epfl.ch
/record
/135193},
8 documenturl
= {http
://infoscience.epfl.ch
/getfile.py?recid
=135193&mode
=best
},
11 location
= {Estoril
, Lisbon
, Portugal
},
12 oai
-id
= {oai
:infoscience.epfl.ch
:135193},
13 oai
-set
= {conf
; fulltext
-public
; fulltext
},
18 title = {Dynamic
{C
}ontent
{W
}eb
{A
}pplications
: {C
}rash
,
19 {F
}ailover
, and
{R
}ecovery
{A
}nalysis
},
21 url
= {http
://www.dsn.org
/},
24 @article
{Chandra
:1996:WFD
:234533.234549,
25 author = {Chandra
, Tushar D. and Hadzilacos
, Vassos and Toueg
, Sam
},
26 title = {The weakest failure detector for solving consensus
},
35 url
= {http
://doi.acm.org
/10.1145/234533.234549},
36 doi
= {http
://doi.acm.org
/10.1145/234533.234549},
39 address = {New York
, NY
, USA
},
40 keywords = {Byzantine Generals' problem
, agreement problem
, asynchronous systems
, atomic broadcast
, commit problem
, consensus problem
, crash failures
, failure detection
, fault
-tolerance
, message passing
, partial synchrony
, processor failures
},
42 @inproceedings
{Aguilera
:2001:SLE
:645958.676119,
43 author = {Aguilera
, Marcos K. and Delporte
-Gallet
, Carole and Fauconnier
, Hugues and Toueg
, Sam
},
44 title = {Stable Leader Election
},
45 booktitle = {Proceedings of the
15th International Conference on Distributed Computing
},
48 isbn
= {3-540-42605-1},
51 url
= {http
://portal.acm.org
/citation.cfm?id
=645958.676119},
53 publisher = {Springer
-Verlag
},
54 address = {London
, UK
},
56 @InProceedings
{vieira08
:_trepl
,
57 author = {Vieira
, Gustavo M. D. and Buzato
, Luis E.
},
58 title = {Treplica
: {U
}biquitous
{R
}eplication
},
59 booktitle = {Proceedings of the
26th Brazilian Symposium on Computer Networks and Distributed Systems
},
61 @inproceedings
{Aguilera
:2007:SNP
:1294261.1294278,
62 author = {Aguilera
, Marcos K. and Merchant
, Arif and Shah
, Mehul and Veitch
, Alistair and Karamanolis
, Christos
},
63 title = {Sinfonia
: a new paradigm for building scalable distributed systems
},
64 booktitle = {Proceedings of twenty
-first ACM SIGOPS symposium on Operating systems principles
},
67 isbn
= {978-1-59593-591-5},
68 location
= {Stevenson
, Washington
, USA
},
71 url
= {http
://doi.acm.org
/10.1145/1294261.1294278},
72 doi
= {http
://doi.acm.org
/10.1145/1294261.1294278},
75 address = {New York
, NY
, USA
},
76 keywords = {distributed systems
, fault tolerance
, scalability
, shared memory
, transactions
, two
-phase commit
},
78 @article
{Lamport
:1978_clocks
,
79 author = {Lamport
, Leslie
},
80 title = {Time
, clocks
, and the ordering of events in a distributed system
},
81 journal = {Commun. ACM
},
89 url
= {http
://doi.acm.org
/10.1145/359545.359563},
90 doi
= {http
://doi.acm.org
/10.1145/359545.359563},
93 address = {New York
, NY
, USA
},
94 keywords = {clock synchronization
, computer networks
, distributed systems
, multiprocess systems
},
96 @inproceedings
{Isard
:2007:DDD
:1272996.1273005,
97 author = {Isard
, Michael and Budiu
, Mihai and Yu
, Yuan and Birrell
, Andrew and Fetterly
, Dennis
},
98 title = {Dryad
: distributed data
-parallel programs from sequential building blocks
},
99 booktitle = {Proceedings of the
2nd ACM SIGOPS
/EuroSys European Conference on Computer Systems
2007},
100 series = {EuroSys '
07},
102 isbn
= {978-1-59593-636-3},
103 location
= {Lisbon
, Portugal
},
106 url
= {http
://doi.acm.org
/10.1145/1272996.1273005},
107 doi
= {http
://doi.acm.org
/10.1145/1272996.1273005},
110 address = {New York
, NY
, USA
},
111 keywords = {cluster computing
, concurrency
, dataflow
, distributed programming
},
113 @article
{Defago
:2004,
114 author = {D\'
{e
}fago
, Xavier and Schiper
, Andr\'
{e
} and Urb\'
{a
}n
, P\'
{e
}ter
},
115 title = {Total order broadcast and multicast algorithms
: Taxonomy and survey
},
116 journal = {ACM Comput. Surv.
},
124 url
= {http
://doi.acm.org
/10.1145/1041680.1041682},
125 doi
= {http
://doi.acm.org
/10.1145/1041680.1041682},
128 address = {New York
, NY
, USA
},
129 keywords = {Distributed systems
, agreement problems
, atomic broadcast
, atomic multicast
, classification
, distributed algorithms
, fault
-tolerance
, global ordering
, group communication
, message passing
, survey
, taxonomy
, total ordering
},
131 @TechReport
{hadzilacos94
,
132 author = {Hadzilacos
, Vassos and Toueg
, Sam
},
133 title = {A modular approach to the specification and implementation of fault
-tolerant broadcasts
},
134 institution = {Department of Computer Science
, Cornell University
},
137 address = {Ithaca
, NY
},
139 @inproceedings
{Rodrigues
:2000,
140 author = {Rodrigues
, L. and Raynal
, M.
},
141 title = {Atomic Broadcast in Asynchronous Crash
-Recovery Distributed Systems
},
142 booktitle = {Proceedings of the The
20th International Conference on Distributed Computing Systems
( ICDCS
2000)},
143 series = {ICDCS '
00},
145 isbn
= {0-7695-0601-1},
147 url
= {http
://portal.acm.org
/citation.cfm?id
=850927.851790},
149 publisher = {IEEE Computer Society
},
150 address = {Washington
, DC
, USA
},
151 keywords = {Distributed Algorithms
, Distributed Fault Tolerant Systems
, Communication Protocols
}
153 @article
{Chandra
:1996:UFD
:226643.226647,
154 author = {Chandra
, Tushar D. and Toueg
, Sam
},
155 title = {Unreliable failure detectors for reliable distributed systems
},
164 url
= {http
://doi.acm.org
/10.1145/226643.226647},
165 doi
= {http
://doi.acm.org
/10.1145/226643.226647},
168 address = {New York
, NY
, USA
},
169 keywords = {Byzantine Generals' problem
, agreement problem
, asynchronous systems
, atomic broadcast
, commit problem
, consensus problem
, crash failures
, failure detection
, fault
-tolerance
, message passing
, partial synchrony
, processor failures
},
171 @inproceedings
{Schroeder
:2007:DFR
:1267903.1267904,
172 author = {Schroeder
, Bianca and Gibson
, Garth A.
},
173 title = {Disk failures in the real world
: what does an MTTF of
1,000,000 hours mean to you?
},
174 booktitle = {Proceedings of the
5th USENIX conference on File and Storage Technologies
},
176 location
= {San Jose
, CA
},
179 url
= {http
://portal.acm.org
/citation.cfm?id
=1267903.1267904},
181 publisher = {USENIX Association
},
182 address = {Berkeley
, CA
, USA
},
184 @article
{Dwork
:1988:CPP
:42282.42283,
185 author = {Dwork
, Cynthia and Lynch
, Nancy and Stockmeyer
, Larry
},
186 title = {Consensus in the presence of partial synchrony
},
195 url
= {http
://doi.acm.org
/10.1145/42282.42283},
196 doi
= {http
://doi.acm.org
/10.1145/42282.42283},
199 address = {New York
, NY
, USA
},
201 @ARTICLE
{Boichat_deconstructingpaxos
,
202 author = {Boichat
, Romain and Dutta
, Partha and Fr
{\o
}lund
, Svend and Guerraoui
, Rachid
},
203 title = {Deconstructing paxos
},
204 journal = {SIGACT News
},
212 url
= {http
://doi.acm.org
/10.1145/637437.637447},
213 doi
= {http
://doi.acm.org
/10.1145/637437.637447},
216 address = {New York
, NY
, USA
},
218 @article
{Lamport
:1998:PP
:279227.279229,
219 author = {Lamport
, Leslie
},
220 title = {The part
-time parliament
},
221 journal = {ACM Trans. Comput. Syst.
},
229 url
= {http
://doi.acm.org
/10.1145/279227.279229},
230 doi
= {http
://doi.acm.org
/10.1145/279227.279229},
233 address = {New York
, NY
, USA
},
234 keywords = {state machines
, three
-phase commit
, voting
},
236 @article
{Elnozahy
:2002:SRP
:568522.568525,
237 author = {Elnozahy
, E. N.
(Mootaz
) and Alvisi
, Lorenzo and Wang
, Yi
-Min and Johnson
, David B.
},
238 title = {A survey of rollback
-recovery protocols in message
-passing systems
},
239 journal = {ACM Comput. Surv.
},
240 issue_date
= {September
2002},
248 url
= {http
://doi.acm.org
/10.1145/568522.568525},
249 doi
= {http
://doi.acm.org
/10.1145/568522.568525},
252 address = {New York
, NY
, USA
},
253 keywords = {message logging
, rollback
-recovery
},
255 @inproceedings
{Koo
:1986:CRD
:324493.325074,
256 author = {Koo
, Richard and Toueg
, Sam
},
257 title = {Checkpointing and rollback
-recovery for distributed systems
},
258 booktitle = {Proceedings of
1986 ACM Fall joint computer conference
},
261 isbn
= {0-8186-4743-4},
262 location
= {Dallas
, Texas
, United States
},
263 pages = {1150--1158},
265 url
= {http
://portal.acm.org
/citation.cfm?id
=324493.325074},
267 publisher = {IEEE Computer Society Press
},
268 address = {Los Alamitos
, CA
, USA
},
270 @article
{10.1109/CCGRID
.2010.40,
271 author = {Leonardo Arturo Bautista Gomez and Naoya Maruyama and Franck Cappello and Satoshi Matsuoka
},
272 title = {Distributed Diskless Checkpoint for Large Scale Systems
},
273 journal ={Cluster Computing and the Grid
, IEEE International Symposium on
},
275 isbn
= {978-0-7695-4039-9},
278 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/CCGRID
.2010.40},
279 publisher = {IEEE Computer Society
},
280 address = {Los Alamitos
, CA
, USA
},
282 @article
{Charron
-Bost
:2007:HDF
:1233481.1233496,
283 author = {Charron
-Bost
, Bernadette and Schiper
, Andr\'
{e
}},
284 title = {Harmful dogmas in fault tolerant distributed computing
},
285 journal = {SIGACT News
},
293 url
= {http
://doi.acm.org
/10.1145/1233481.1233496},
294 doi
= {http
://doi.acm.org
/10.1145/1233481.1233496},
297 address = {New York
, NY
, USA
},
299 @inproceedings
{Camargos
:2007:MP
:1281100.1281150,
300 author = {Camargos
, L\'
{a
}saro Jonas and Schmidt
, Rodrigo Malta and Pedone
, Fernando
},
301 title = {Multicoordinated Paxos
},
302 booktitle = {Proceedings of the twenty
-sixth annual ACM symposium on Principles of distributed computing
},
305 isbn
= {978-1-59593-616-5},
306 location
= {Portland
, Oregon
, USA
},
309 url
= {http
://doi.acm.org
/10.1145/1281100.1281150},
310 doi
= {http
://doi.acm.org
/10.1145/1281100.1281150},
313 address = {New York
, NY
, USA
},
314 keywords = {Paxos
, atomic broadcast
, consensus
, generalized
, multicoordinated
},
316 @inproceedings
{Fischer
:1983:CPU
:647891.739594,
317 author = {Fischer
, Michael J.
},
318 title = {The Consensus Problem in Unreliable Distributed Systems
(A Brief Survey
)},
319 booktitle = {Proceedings of the
1983 International FCT
-Conference on Fundamentals of Computation Theory
},
321 isbn
= {3-540-12689-9},
324 url
= {http
://portal.acm.org
/citation.cfm?id
=647891.739594},
326 publisher = {Springer
-Verlag
},
327 address = {London
, UK
},
329 @article
{10.1109/SRDS
.2009.25,
330 author = {Omid Shahmirzadi and Sergio Mena and Andr\'
{e
} Schiper
},
331 title = {Relaxed Atomic Broadcast
: State
-Machine Replication Using Bounded Memory
},
332 journal ={Reliable Distributed Systems
, IEEE Symposium on
},
337 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/SRDS
.2009.25},
338 publisher = {IEEE Computer Society
},
339 address = {Los Alamitos
, CA
, USA
},
341 @inproceedings
{Okun
:2002:NSR
:829526.831119,
342 author = {Okun
, Michael and Barak
, Amnon
},
343 title = {On Node State Reconstruction for Fault Tolerant Distributed Algorithms
},
344 booktitle = {Proceedings of the
21st IEEE Symposium on Reliable Distributed Systems
},
347 isbn
= {0-7695-1659-9},
349 url
= {http
://portal.acm.org
/citation.cfm?id
=829526.831119},
351 publisher = {IEEE Computer Society
},
352 address = {Washington
, DC
, USA
},
353 keywords = {Distributed algorithms
, fault tolerance
, state reconstruction
, recovery
},
355 @inproceedings
{Chandra
:2007:PML
:1281100.1281103,
356 author = {Chandra
, Tushar D. and Griesemer
, Robert and Redstone
, Joshua
},
357 title = {Paxos made live
: an engineering perspective
},
358 booktitle = {Proceedings of the twenty
-sixth annual ACM symposium on Principles of distributed computing
},
361 isbn
= {978-1-59593-616-5},
362 location
= {Portland
, Oregon
, USA
},
365 url
= {http
://doi.acm.org
/10.1145/1281100.1281103},
366 doi
= {http
://doi.acm.org
/10.1145/1281100.1281103},
369 address = {New York
, NY
, USA
},
370 keywords = {Paxos
, experiences
, fault
-tolerance
, implementation
},
372 @conference
{juang2002crash
,
373 title={{Crash recovery with little overhead
}},
374 author={Juang
, T.T.Y. and Venkatesan
, S.
},
375 booktitle={Distributed Computing Systems
, 1991.
, 11th International Conference on
},
381 @inproceedings
{Freiling
:2009:MCA
:1729641.1730101,
382 author = {Freiling
, Felix C. and Lambertz
, Christian and Majster
-Cederbaum
, Mila
},
383 title = {Modular Consensus Algorithms for the Crash
-Recovery Model
},
384 booktitle = {Proceedings of the
2009 International Conference on Parallel and Distributed Computing
, Applications and Technologies
},
385 series = {PDCAT '
09},
387 isbn
= {978-0-7695-3914-0},
390 url
= {http
://dx.doi.org
/10.1109/PDCAT
.2009.50},
391 doi
= {http
://dx.doi.org
/10.1109/PDCAT
.2009.50},
393 publisher = {IEEE Computer Society
},
394 address = {Washington
, DC
, USA
},
395 keywords = {asynchronous systems
, consensus
, fault tolerance
, process crash and recovery
, stable storage
},
397 @TechReport
{oliveira97
:consensus
,
398 author = {Oliveira
, Rui and Guerraoui
, Rachid and Schiper
, Andr\'
{e
}},
399 title = {Consensus in the crash
-recover model
},
400 institution = {Département d'Informatique
, Ecole Polytechnique Fédérale
},
403 address = {Laussane
, Switzerland
},
405 @inproceedings
{Freiling
:2008:ECA
:1432291.1432332,
406 author = {Freiling
, Felix C. and Lambertz
, Christian and Majster
-Cederbaum
, Mila
},
407 title = {Easy Consensus Algorithms for the Crash
-Recovery Model
},
408 booktitle = {Proceedings of the
22nd international symposium on Distributed Computing
},
411 isbn
= {978-3-540-87778-3},
412 location
= {Arcachon
, France
},
415 url
= {http
://dx.doi.org
/10.1007/978-3-540-87779-0_39
},
416 doi
= {http
://dx.doi.org
/10.1007/978-3-540-87779-0_39
},
418 publisher = {Springer
-Verlag
},
419 address = {Berlin
, Heidelberg
},
421 @article
{Vieira
:2008:CRF
:1390853.1390875,
422 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
423 title = {On the coordinator's rule for Fast Paxos
},
424 journal = {Inf. Process. Lett.
},
432 url
= {http
://portal.acm.org
/citation.cfm?id
=1390853.1390875},
433 doi
= {10.1016/j.ipl
.2008.03.001},
435 publisher = {Elsevier North
-Holland
, Inc.
},
436 address = {Amsterdam
, The Netherlands
, The Netherlands
},
437 keywords = {Consensus
, Crash
-recovery
, Distributed systems
, Paxos
},
439 @article
{Schneider
:1990:IFS
:98163.98167,
440 author = {Schneider
, Fred B.
},
441 title = {Implementing fault
-tolerant services using the state machine approach
: a tutorial
},
442 journal = {ACM Comput. Surv.
},
450 url
= {http
://doi.acm.org
/10.1145/98163.98167},
451 doi
= {http
://doi.acm.org
/10.1145/98163.98167},
454 address = {New York
, NY
, USA
},
456 @article
{lamport1978implementation
,
457 title={{The implementation of reliable distributed multiprocess systems
}},
458 author={Lamport
, Leslie
},
459 journal={Computer Networks
(1976)},
467 @inproceedings
{Oki
:1988:VRN
:62546.62549,
468 author = {Oki
, Brian M. and Liskov
, Barbara H.
},
469 title = {Viewstamped Replication
: A New Primary Copy Method to Support Highly
-Available Distributed Systems
},
470 booktitle = {Proceedings of the seventh annual ACM Symposium on Principles of distributed computing
},
473 isbn
= {0-89791-277-2},
474 location
= {Toronto
, Ontario
, Canada
},
477 url
= {http
://doi.acm.org
/10.1145/62546.62549},
478 doi
= {http
://doi.acm.org
/10.1145/62546.62549},
481 address = {New York
, NY
, USA
},
483 @article
{Lamport
:1982:BGP
:357172.357176,
484 author = {Lamport
, Leslie and Shostak
, Robert and Pease
, Marshall
},
485 title = {The Byzantine Generals Problem
},
486 journal = {ACM Trans. Program. Lang. Syst.
},
487 issue_date
= {July
1982},
495 url
= {http
://doi.acm.org
/10.1145/357172.357176},
496 doi
= {http
://doi.acm.org
/10.1145/357172.357176},
499 address = {New York
, NY
, USA
},
501 @article
{Neiger
:1990:AIF
:83334.83337,
502 author = {Neiger
, Gil and Toueg
, Sam
},
503 title = {Automatically increasing the fault
-tolerance of distributed algorithms
},
504 journal = {J. Algorithms
},
512 url
= {http
://portal.acm.org
/citation.cfm?id
=83334.83337},
513 doi
= {10.1016/0196-6774(90)90019-B
},
515 publisher = {Academic Press
, Inc.
},
516 address = {Duluth
, MN
, USA
},
518 @TechReport
{vieira10
:implementing
-tr
,
519 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
520 title = {Implementation of an Object
-Oriented Specification
521 for Active Replication Using Consensus
},
522 institution = {Instituto de Computação
, Universidade Estadual de Campinas
},
526 @article
{Reynal
:2005:SIF
:1052796.1052806,
527 author = {Reynal
, Michel
},
528 title = {A short introduction to failure detectors for asynchronous distributed systems
},
529 journal = {SIGACT News
},
537 url
= {http
://doi.acm.org
/10.1145/1052796.1052806},
538 doi
= {http
://doi.acm.org
/10.1145/1052796.1052806},
541 address = {New York
, NY
, USA
},
543 @inproceedings
{Bonnet
:2010:CAD
:1825731.1826088,
544 author = {Bonnet
, Fran\c
{c
}ois and Raynal
, Michel
},
545 title = {Consensus in Anonymous Distributed Systems
: Is There a Weakest Failure Detector?
},
546 booktitle = {Proceedings of the
2010 24th IEEE International Conference on Advanced Information Networking and Applications
},
549 isbn
= {978-0-7695-4018-4},
552 url
= {http
://dx.doi.org
/10.1109/AINA
.2010.19},
553 doi
= {http
://dx.doi.org
/10.1109/AINA
.2010.19},
555 publisher = {IEEE Computer Society
},
556 address = {Washington
, DC
, USA
},
558 @inproceedings
{Gupta
:2001:SED
:383962.384010,
559 author = {Gupta
, Indranil and Chandra
, Tushar D. and Goldszmidt
, Germ\'
{a
}n S.
},
560 title = {On scalable and efficient distributed failure detectors
},
561 booktitle = {Proceedings of the twentieth annual ACM symposium on Principles of distributed computing
},
564 isbn
= {1-58113-383-9},
565 location
= {Newport
, Rhode Island
, United States
},
568 url
= {http
://doi.acm.org
/10.1145/383962.384010},
569 doi
= {http
://doi.acm.org
/10.1145/383962.384010},
572 address = {New York
, NY
, USA
},
573 keywords = {accuracy
, distributed systems
, efficiency
, failure detectors
, scalability
},
575 @inproceedings
{Xiong
:2009:SFD
:1632708.1633468,
576 author = {Xiong
, Naixue and Yang
, Yan and Cao
, Ming and He
, Jing and Shu
, Lei
},
577 title = {A Survey on Fault
-Tolerance in Distributed Network Systems
},
578 booktitle = {Proceedings of the
2009 International Conference on Computational Science and Engineering
- Volume
02},
581 isbn
= {978-0-7695-3823-5},
582 pages = {1065--1070},
584 url
= {http
://dx.doi.org
/10.1109/CSE
.2009.497},
585 doi
= {http
://dx.doi.org
/10.1109/CSE
.2009.497},
587 publisher = {IEEE Computer Society
},
588 address = {Washington
, DC
, USA
},
589 keywords = {Failure detector
, Fault
-tolerance
, Network Systems
, Quality
-of
-service
},
591 @article
{Chockler
:2001:GCS
:503112.503113,
592 author = {Chockler
, Gregory V. and Keidar
, Idit and Vitenberg
, Roman
},
593 title = {Group communication specifications
: a comprehensive study
},
594 journal = {ACM Comput. Surv.
},
595 issue_date
= {December
2001},
603 url
= {http
://doi.acm.org
/10.1145/503112.503113},
604 doi
= {http
://doi.acm.org
/10.1145/503112.503113},
607 address = {New York
, NY
, USA
},
608 keywords = {Group communication systems
, partitionable group membership
, process group membership
, specifications of group communication systems
, view synchrony
, virtual synchrony
},
610 @inproceedings
{Hurfin
:1998:CAS
:829523.830974,
611 author = {Hurfin
, Michel and Most\'
{e
}faoui
, Achour and Raynal
, Michel
},
612 title = {Consensus in Asynchronous Systems Where Processes Can Crash and Recover
},
613 booktitle = {Proceedings of the The
17th IEEE Symposium on Reliable Distributed Systems
},
616 isbn
= {0-8186-9218-9},
618 url
= {http
://portal.acm.org
/citation.cfm?id
=829523.830974},
620 publisher = {IEEE Computer Society
},
621 address = {Washington
, DC
, USA
},
623 @inproceedings
{Pinheiro
:2007:FTL
:1267903.1267905,
624 author = {Pinheiro
, Eduardo and Weber
, Wolf
-Dietrich and Barroso
, Luiz Andr\'
{e
}},
625 title = {Failure trends in a large disk drive population
},
626 booktitle = {Proceedings of the
5th USENIX conference on File and Storage Technologies
},
628 location
= {San Jose
, CA
},
631 url
= {http
://portal.acm.org
/citation.cfm?id
=1267903.1267905},
633 publisher = {USENIX Association
},
634 address = {Berkeley
, CA
, USA
},
636 @ARTICLE
{gray07
:empirical
,
637 author = {{Gray
}, Jim and
{van Ingen
}, Catherine
},
638 title = "
{Empirical Measurements of Disk Failure Rates and Error Rates
}"
,
639 journal = {ArXiv Computer Science e
-prints
},
640 eprint
= {arXiv
:cs
/0701166},
641 keywords = {Computer Science
- Databases
, Computer Science
- Architecture
},
644 adsurl
= {http
://adsabs.harvard.edu
/abs
/2007cs.......
.1166G
},
646 @article
{10.1109/SRDS
.2008.9,
647 author = {Timo Warns and Christian Storm and Wilhelm Hasselbring
},
648 title = {Availability of Globally Distributed Nodes
: An Empirical Evaluation
},
649 journal ={Reliable Distributed Systems
, IEEE Symposium on
},
654 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/SRDS
.2008.9},
655 publisher = {IEEE Computer Society
},
656 address = {Los Alamitos
, CA
, USA
},
658 @article
{10.1109/SRDS
.2010.17,
659 author = {Raphael Marcos Menderico and Islene Calciolari Garcia
},
660 title = {Diskless Checkpointing with Rollback
-Dependency Trackability
},
661 journal ={Reliable Distributed Systems
, IEEE Symposium on
},
666 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/SRDS
.2010.17},
667 publisher = {IEEE Computer Society
},
668 address = {Los Alamitos
, CA
, USA
},
670 @article
{Chandy
:1985:DSD
:214451.214456,
671 author = {Chandy
, K. Mani and Lamport
, Leslie
},
672 title = {Distributed snapshots
: determining global states of distributed systems
},
673 journal = {ACM Trans. Comput. Syst.
},
681 url
= {http
://doi.acm.org
/10.1145/214451.214456},
682 doi
= {http
://doi.acm.org
/10.1145/214451.214456},
685 address = {New York
, NY
, USA
},
687 @article
{Randell
:1978:RIC
:356725.356729,
688 author = {Randell
, Brian and Lee
, Pete and Treleaven
, Phillip C.
},
689 title = {Reliability Issues in Computing System Design
},
690 journal = {ACM Comput. Surv.
},
698 url
= {http
://doi.acm.org
/10.1145/356725.356729},
699 doi
= {http
://doi.acm.org
/10.1145/356725.356729},
702 address = {New York
, NY
, USA
},
704 @article
{Pease
:1980:RAP
:322186.322188,
705 author = {Pease
, Marshall and Shostak
, Robert and Lamport
, Leslie
},
706 title = {Reaching Agreement in the Presence of Faults
},
715 url
= {http
://doi.acm.org
/10.1145/322186.322188},
716 doi
= {http
://doi.acm.org
/10.1145/322186.322188},
719 address = {New York
, NY
, USA
},
721 @inproceedings
{Song
:2008:BBC
:1785854.1785862,
722 author = {Song
, Yee Jiun and van Renesse
, Robbert and Schneider
, Fred B. and Dolev
, Danny
},
723 title = {The building blocks of consensus
},
724 booktitle = {Proceedings of the
9th international conference on Distributed computing and networking
},
727 isbn
= {3-540-77443-2, 978-3-540-77443-3},
728 location
= {Kolkata
, India
},
731 url
= {http
://portal.acm.org
/citation.cfm?id
=1785854.1785862},
733 publisher = {Springer
-Verlag
},
734 address = {Berlin
, Heidelberg
},
736 @TechReport
{HUS
+02/LSR
,
737 author = {Hayashibara
, Naohiro and Urbán
, Péter and Schiper
, André
738 and Katayama
, Takuya
},
739 details
= {http
://infoscience.epfl.ch
/record
/49945},
740 documenturl
= {http
://infoscience.epfl.ch
/getfile.py?recid
=49945},
741 oai
-id
= {oai
:infoscience.epfl.ch
:49945},
742 oai
-set
= {fulltext
; report
; fulltext
-public
},
743 title = {Performance
{C
}omparison
{B
}etween the
{P
}axos and
744 {C
}handra
-{T
}oueg
{C
}onsensus
{A
}lgorithms
},
747 institution = {EPFL
},
749 @inproceedings
{Burrows
:2006:CLS
:1298455.1298487,
750 author = {Burrows
, Mike
},
751 title = {The Chubby lock service for loosely
-coupled distributed systems
},
752 booktitle = {Proceedings of the
7th symposium on Operating systems design and implementation
},
755 isbn
= {1-931971-47-1},
756 location
= {Seattle
, Washington
},
759 url
= {http
://portal.acm.org
/citation.cfm?id
=1298455.1298487},
761 publisher = {USENIX Association
},
762 address = {Berkeley
, CA
, USA
},
764 @article
{Camargos
:2007:SMH
:1272998.1273036,
765 author = {Camargos
, L\'
{a
}saro and Pedone
, Fernando and Wieloch
, Marcin
},
766 title = {Sprint
: a middleware for high
-performance transaction processing
},
767 journal = {SIGOPS Oper. Syst. Rev.
},
775 url
= {http
://doi.acm.org
/10.1145/1272998.1273036},
776 doi
= {http
://doi.acm.org
/10.1145/1272998.1273036},
779 address = {New York
, NY
, USA
},
780 keywords = {middleware
, parallel databases
, partitioning
, replication
},
782 @inproceedings
{MacCormick
:2004:BAF
:1251254.1251262,
783 author = {MacCormick
, John and Murphy
, Nick and Najork
, Marc and Thekkath
, Chandramohan A. and Zhou
, Lidong
},
784 title = {Boxwood
: abstractions as the foundation for storage infrastructure
},
785 booktitle = {Proceedings of the
6th conference on Symposium on Opearting Systems Design \
& Implementation
- Volume
6},
787 location
= {San Francisco
, CA
},
790 url
= {http
://portal.acm.org
/citation.cfm?id
=1251254.1251262},
792 publisher = {USENIX Association
},
793 address = {Berkeley
, CA
, USA
},
795 @inproceedings
{Saito
:2004:FBD
:1024393.1024400,
796 author = {Saito
, Yasushi and Fr
{\o
}lund
, Svend and Veitch
, Alistair and Merchant
, Arif and Spence
, Susan
},
797 title = {FAB
: building distributed enterprise disk arrays from commodity components
},
798 booktitle = {Proceedings of the
11th international conference on Architectural support for programming languages and operating systems
},
799 series = {ASPLOS
-XI
},
801 isbn
= {1-58113-804-0},
802 location
= {Boston
, MA
, USA
},
805 url
= {http
://doi.acm.org
/10.1145/1024393.1024400},
806 doi
= {http
://doi.acm.org
/10.1145/1024393.1024400},
809 address = {New York
, NY
, USA
},
810 keywords = {consensus
, disk array
, erasure coding
, replication
, storage
, voting
},
812 @PhdThesis
{vieira10
:thesis
,
813 author = {Vieira
, Gustavo M. D.
},
814 title = {Uma arquitetura de software para replicação baseda em consenso
},
815 school = {{U
}niversidade
{E
}studual de
{C
}ampinas
, {I
}nstituto de
{C
}omputaçao
},
819 @conference
{garcia2002message
,
820 title={{Message ordering in a multicast environment
}},
821 author={Garcia
-Molina
, Hector and Spauster
, Annemarie
},
822 booktitle={Distributed Computing Systems
, 1989.
, 9th International Conference on
},
828 @article
{cristian97
:high_performance
,
829 author={Flaviu Cristian and Shivakant Mishra and Guillermo Alvarez
},
830 title={High
-performance asynchronous atomic broadcast
},
831 journal={Distributed Systems Engineering
},
835 url
={http
://stacks.iop.org
/0967-1846/4/i
=2/a
=005},
838 @inproceedings
{Gopal
:1989:RBS
:645946.675018,
839 author = {Gopal
, Ajei S. and Toueg
, Sam
},
840 title = {Reliable Broadcast in Synchronous and Asynchronous Environments
(Preliminary Version
)},
841 booktitle = {Proceedings of the
3rd International Workshop on Distributed Algorithms
},
843 isbn
= {3-540-51687-5},
846 url
= {http
://portal.acm.org
/citation.cfm?id
=645946.675018},
848 publisher = {Springer
-Verlag
},
849 address = {London
, UK
},
851 @inproceedings
{Bar
-Joseph
:2002:EDA
:645959.676132,
852 author = {Bar
-Joseph
, Ziv and Keidar
, Idit and Lynch
, Nancy
},
853 title = {Early
-Delivery Dynamic Atomic Broadcast
},
854 booktitle = {Proceedings of the
16th International Conference on Distributed Computing
},
857 isbn
= {3-540-00073-9},
860 url
= {http
://portal.acm.org
/citation.cfm?id
=645959.676132},
862 publisher = {Springer
-Verlag
},
863 address = {London
, UK
, UK
},
865 @inproceedings
{Birman
:1987:EVS
:41457.37515,
866 author = {Birman
, Kenneth and Joseph
, Thomas
},
867 title = {Exploiting virtual synchrony in distributed systems
},
868 booktitle = {Proceedings of the eleventh ACM Symposium on Operating systems principles
},
871 isbn
= {0-89791-242-X
},
872 location
= {Austin
, Texas
, United States
},
875 url
= {http
://doi.acm.org
/10.1145/41457.37515},
876 doi
= {http
://doi.acm.org
/10.1145/41457.37515},
879 address = {New York
, NY
, USA
},
881 @article
{10.1109/DOA
.1999.794001,
882 author = {Pascal Felber and Xavier Défago and Rachid Guerraoui and Philipp Oser
},
883 title = {Failure Detectors as First Class Objects
},
884 journal ={Distributed Objects and Applications
, International Symposium on
},
886 isbn
= {0-7695-0182-6},
889 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/DOA
.1999.794001},
890 publisher = {IEEE Computer Society
},
891 address = {Los Alamitos
, CA
, USA
},
893 @article
{Aguilera
:2000:FDC
:1035750.1035753,
894 author = {Aguilera
, Marcos Kawazoe and Chen
, Wei and Toueg
, Sam
},
895 title = {Failure detection and consensus in the crash
-recovery model
},
896 journal = {Distributed Computing
},
904 url
= {http
://portal.acm.org
/citation.cfm?id
=1035750.1035753},
905 doi
= {10.1007/s004460050070
},
907 publisher = {Springer
-Verlag
},
908 address = {London
, UK
},
909 keywords = {asynchronous systems
, consensus
, failure detection
, fault tolerance
, process crash
, process recovery
, stable storage
},
911 @article
{Boichat
:2005:RTO
:1066486.1066487,
912 author = {Boichat
, Romain and Guerraoui
, Rachid
},
913 title = {Reliable and total order broadcast in the crash
-recovery model
},
914 journal = {J. Parallel Distrib. Comput.
},
922 url
= {http
://dx.doi.org
/10.1016/j.jpdc
.2004.10.008},
923 doi
= {http
://dx.doi.org
/10.1016/j.jpdc
.2004.10.008},
925 publisher = {Academic Press
, Inc.
},
926 address = {Orlando
, FL
, USA
},
927 keywords = {Complexity
, Crash
-recovery model
, Modularity
, Reliable broadcast
, Total order broadcast
},
928 }@INPROCEEDINGS
{aguilera09b
,
929 author = {Marcos K. Aguilera and Michael Walfish
},
930 title = {No Time for Asynchrony
},
931 booktitle = {Proc. of the
12th Workshop on Hot Topics in Operating Systems
},
933 publisher = {USENIX Association
},
934 file
= {:/Users
/buzato
/bibliobase
/papers
/aguilera09b.pdf
:PDF
},
935 keywords = {pfdtreplica
},
937 timestamp
= {2010.03.29}
940 author = {Flaviu Cristian and Christof Fetzer
},
941 title = {The Timed Asynchronous Distributed System Model
},
942 journal = {IEEE Transactions on Parallel and Distributed Systems
},
946 address = {Los Alamitos
, CA
, USA
},
947 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/71.774912},
948 file
= {:/Users
/buzato
/bibliobase
/papers
/cristian99.pdf
:PDF
},
951 publisher = {IEEE Computer Society
},
952 timestamp
= {2010.07.29}
954 @INPROCEEDINGS
{ezhilchelvan09
,
955 author = {Paul Ezhilchelvan and Santosh Shrivastava
},
956 title = {Learning from the Past for Resolving Dilemmas of Asynchrony
},
957 booktitle = {Proc. of the
3rd ACM SIGOPS International Workshop on Large Scale
958 Distributed Systems and Middleware
},
960 file
= {:/Users
/buzato
/bibliobase
/papers
/ezhilchelvan09.pdf
:PDF
},
961 keywords = {pfdtreplica
},
963 timestamp
= {2010.03.29}
965 @INPROCEEDINGS
{fetzer96
,
966 author = {Fetzer
, Christof and Cristian
, Flaviu
},
967 title = {Fail
-awareness in timed asynchronous systems
},
968 booktitle = {PODC '
96: Proceedings of the fifteenth annual ACM symposium on Principles
969 of distributed computing
},
972 address = {New York
, NY
, USA
},
974 doi
= {http
://doi.acm.org
/10.1145/248052.248119},
975 file
= {:/Users
/buzato
/bibliobase
/papers
/fetzer96.pdf
:PDF
},
976 isbn
= {0-89791-800-2},
977 keywords = {failure detector
, clock synchronization
, NTP
},
978 location
= {Philadelphia
, Pennsylvania
, United States
},
980 timestamp
= {2009.10.30}
982 @INPROCEEDINGS
{fetzer05
,
983 author = {Christof Fetzer and Ulrich Schmid and Martin S?sskraut
},
984 title = {On the Possibility of Consensus in Asynchronous Systems with Finite
985 Average Response Times
},
986 booktitle = {Distributed Computing Systems
, International Conference on
},
989 address = {Los Alamitos
, CA
, USA
},
990 publisher = {IEEE Computer Society
},
991 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/ICDCS
.2005.57},
992 file
= {:/Users
/buzato
/bibliobase
/papers
/fetzer05.pdf
:PDF
},
995 timestamp
= {2010.08.13}
998 author = {Michael J. Fischer and Nancy Lynch and Michael S. Paterson
},
999 title = {Impossibility of distributed consensus with one faulty process
},
1005 address = {New York
, NY
, USA
},
1006 doi
= {http
://doi.acm.org
/10.1145/3149.214121},
1007 file
= {fischer85.pdf
:papers
/fischer85.pdf
:PDF
},
1009 keywords = {consensus
},
1011 publisher = {ACM Press
},
1012 review
= {Classic impossibility result for asynchronous systems.
},
1013 timestamp
= {2008.10.10}
1016 author = {Idit Keidar and Sergio Rajsbaum
},
1017 title = {A simple proof of the uniform consensus synchronous lower bound
},
1018 journal = {Information Processing Letters
},
1023 doi
= {DOI
: 10.1016/S0020
-0190(02)00333-2},
1024 file
= {:/Users
/buzato
/bibliobase
/papers
/keidar02.pdf
:PDF
},
1026 keywords = {Distributed computing
},
1028 timestamp
= {2010.04.06},
1029 url
= {http
://www.sciencedirect.com
/science
/article
/B6V0F
-4619MD5
-2/2/1e18868b812187cd4f20949273362c61
}
1032 author = {Keidar
, Idit and Rajsbaum
, Sergio
},
1033 title = {On the cost of fault
-tolerant consensus when there are no faults
:
1034 preliminary version
},
1035 journal = {SIGACT News
},
1040 address = {New York
, NY
, USA
},
1041 doi
= {http
://doi.acm.org
/10.1145/504192.504195},
1042 file
= {:/Users
/buzato
/bibliobase
/papers
/keidar01.pdf
:PDF
},
1044 keywords = {pdftreplica
},
1047 timestamp
= {2010.04.02}
1050 author = {Leslie Lamport
},
1051 title = {Lower bounds for asynchronous consensus
},
1052 journal = {Distributed Computing
},
1055 pages = {104---125},
1058 file
= {lamport06b.pdf
:papers
/lamport06b.pdf
:PDF
},
1060 timestamp
= {2008.10.10}
1062 @ARTICLE
{lamport06a
,
1063 author = {Leslie Lamport
},
1064 title = {Fast
{P
}axos
},
1065 journal = {Distrib. Comput.
},
1071 address = {London
, UK
},
1072 doi
= {http
://dx.doi.org
/10.1007/s00446
-006-0005-x
},
1073 file
= {lamport06a.pdf
:papers
/lamport06a.pdf
:PDF
},
1075 keywords = {paxos
, consensus
},
1077 publisher = {Springer
-Verlag
},
1078 timestamp
= {2008.10.10}
1081 author = {Shivakant Mishra and Christof Fetzer and Flaviu Cristian
},
1082 title = {The Timewheel Group Communication System
},
1083 journal = {IEEE Transactions on Computers
},
1087 address = {Los Alamitos
, CA
, USA
},
1088 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/TC
.2002.1024737},
1091 publisher = {IEEE Computer Society
},
1092 timestamp
= {2010.07.29}
1096 author = {Dolev
, Danny and Dwork
, Cynthia and Stockmeyer
, Larry
},
1097 title = {On the minimal synchronism needed for distributed consensus
},
1098 journal = {Journal of the ACM
(JACM
)},
1104 @article
{charron
-bost04
,
1105 Publisher
= {Elsevier
},
1106 author = {Charron
-Bost
, B. and Schiper
, A.
},
1107 title = {Uniform consensus is harder than consensus
},
1108 journal = {Journal of Algorithms
},
1113 doi
= {10.1016/j.jalgor
.2003.11.001},
1115 @techreport
{raynal02
,
1116 address = {Université de Rennes
1},
1117 institution = {Institut de Reserche en Systèmes Alèatoires
},
1119 Publisher
= {IEEE Computer Society
},
1120 author = {Raynal
, M.
},
1121 title = {Consensus in synchronous systems
: a concise guided tour
},
1124 @techreport
{rodrigues02
,
1125 institution = {Department of Informatics
, University of Lisbon
},
1126 month = {September
},
1127 type = {Tech Report
},
1128 author = {Vicente
, P. and Rodrigues
, L.
},
1129 title = {An Indulgent Uniform Total Order Algorithm with Optimistic Delivery
},
1132 @incollection
{pedone98
,
1133 Affiliation
= {Ecole Polytechnique Fédérale de Lausanne Département d’Informatique
1015 Lausanne Switzerland
1015 Lausanne Switzerland
},
1134 booktitle = {Distributed Computing
},
1135 Chapter
= {Lecture Notes in Computer Science
},
1136 editor = {Kutten
, Shay
},
1137 publisher = {Springer
},
1138 Url
= {http
://dx.doi.org
/10.1007/BFb0056492
},
1139 author = {Pedone
, Fernando and Schiper
, André
},
1140 title = {Optimistic Atomic Broadcast
},
1141 journal = {Distributed Computing
},
1145 doi
= {10.1007/BFb0056492
},
1148 address = {Mesa
, AZ
, United States
},
1149 booktitle = {21st IEEE International Conference on Distributed Computing Systems
},
1150 Isbn
= {0-7695-1077-9},
1152 Organization
= {Published by the IEEE Computer Society
},
1153 Publisher
= {IEEE Computer Society
},
1154 author = {Felber
, Pascal and Schiper
, André
},
1155 title = {Optimistic Active Replication
},
1156 journal = {Distributed Computing Systems
, International Conference on
},
1160 doi
= {http
://doi.ieeecomputersociety.org
/10.1109/ICDSC
.2001.918963},
1162 @INPROCEEDINGS
{vieira09
,
1163 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
1164 title = {The Performance of
{P
}axos and
{F
}ast
{P
}axos
},
1165 booktitle = {SBRC '
09: Proc. of the
27th Brazilian Symposium on Computer Networks
1166 and Distributed Systems
},
1169 address = {Recife
, Brasil
},
1171 file
= {vieira09.pdf
:papers
/vieira09.pdf
:PDF
},
1172 keywords = {paxos
, performance
},
1174 timestamp
= {2010.02.09},
1175 url
= {http
://www.ic.unicamp.br
/~gdvieira
/publications
/}
1178 author = {Gustavo M. D. Vieira and Luiz E. Buzato
},
1179 title = {On the coordinator's rule for
{F
}ast
{P
}axos
},
1180 journal = {Information Processing Letters
},
1185 doi
= {http
://dx.doi.org
/10.1016/j.ipl
.2008.03.001},
1186 file
= {vieira08b.pdf
:papers
/vieira08b.pdf
:PDF
;Preprint
:papers
/vieira08b
-preprint.pdf
:PDF
},
1189 timestamp
= {2008.08.12}
1191 @TECHREPORT
{vieira09
-tr
,
1192 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
1193 title = {The Performance of
{P
}axos and
{F
}ast
{P
}axos
},
1194 institution = {Institute of Computing
, University of Campinas
},
1196 number = {IC
-08-35},
1198 file
= {vieira09
-tr.pdf
:papers
/vieira09
-tr.pdf
:PDF
},
1199 keywords = {paxos
, performance
},
1201 timestamp
= {2010.02.10},
1202 url
= {http
://www.ic.unicamp.br
/~reltech
/2008/abstracts.html
}
1204 @TECHREPORT
{vieira08a
-tr
,
1205 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
1206 title = {{T
}replica
: Ubiquitous replication
},
1207 institution = {Institute of Computing
, University of Campinas
},
1209 number = {IC
-07-37},
1211 file
= {vieira08a
-tr.pdf
:papers
/vieira08a
-tr.pdf
:PDF
},
1212 keywords = {active replication
, middleware
, paxos
, persistent queues
},
1214 timestamp
= {2010.02.10},
1215 url
= {http
://www.ic.unicamp.br
/~reltech
/2007/abstracts.html
}
1217 @TECHREPORT
{vieira08b
-tr
,
1218 author = {Vieira
, Gustavo M. D. and Buzato
, Luiz E.
},
1219 title = {On the coordinator's rule for
{F
}ast
{P
}axos
},
1220 institution = {Institute of Computing
, University of Campinas
},
1222 number = {IC
-07-35},
1224 file
= {vieira08b
-tr.pdf
:papers
/vieira08b
-tr.pdf
:PDF
},
1227 timestamp
= {2010.02.10},
1228 url
= {http
://www.ic.unicamp.br
/~reltech
/2007/abstracts.html
}
1230 @TECHREPORT
{vieira
-tr10a
,
1231 author = {Vieira
, Gustavo M. D. and Garcia
, Islene Calciolari and Buzato
,
1233 title = {Seamless
{P
}axos Coordinators
},
1234 institution = {Institute of Computing
, University of Campinas
},
1236 number = {IC
-10-13},
1238 file
= {vieira
-tr10a.pdf
:papers
/vieira
-tr10a.pdf
:PDF
},
1239 keywords = {paxos
, leader election
, dependability
, performance
},
1241 timestamp
= {2010.04.27},
1242 url
= {http
://www.ic.unicamp.br
/~reltech
/2010/abstracts.html
}
1244 @INPROCEEDINGS
{buzato09
,
1245 author = {Luiz E. Buzato and Gustavo M. D. Vieira and Willy Zwaenepoel
},
1246 title = {Dynamic Content Web Applications
: Crash
, Failover
, and Recovery Analysis
},
1247 booktitle = {DSN
2009: 39th International Conference on Dependable Systems and
1251 address = {Estoril
, Lisbon
, Portugal
},
1253 doi
= {http
://dx.doi.org
/10.1109/DSN
.2009.5270331},
1254 file
= {buzato09.pdf
:papers
/buzato09.pdf
:PDF
},
1255 keywords = {active replication
, dependability
, performance
},
1257 timestamp
= {2009.11.16}
1259 @InCollection
{Chor89
,
1260 author = {Chor
, Benny and Dwork
, Cynthia
},
1261 booktitle = {Advances in Computing research
},
1262 title = {Randomization in byzantine agreement
},
1266 @book
{dolev2000self
,
1267 title={{Self
-stabilization
}},
1268 author={Dolev
, Shlomi
},
1271 publisher={The MIT press
}
1273 @book
{Lynch
:1996:DA
:525656,
1274 author = {Lynch
, Nancy
},
1275 title = {Distributed Algorithms
},
1277 isbn
= {1558603484},
1278 publisher = {Morgan Kaufmann Publishers Inc.
},
1279 address = {San Francisco
, CA
, USA
},