abstract={Data replication is a key technology in distributed systems that enables higher availability and performance. This article surveys optimistic replication algorithms. They allow replica contents to diverge in the short term to support concurrent work practices and tolerate failures in low-quality communication links. The importance of such techniques is increasing as collaboration through wide-area and mobile networks becomes popular.Optimistic replication deploys algorithms not seen in traditional “pessimistic” systems. Instead of synchronous replica coordination, an optimistic algorithm propagates changes in the background, discovers conflicts after they happen, and reaches agreement on the final contents incrementally.We explore the solution space for optimistic replication algorithms. This article identifies key challenges facing optimistic replication systems---ordering operations, detecting and resolving conflicts, propagating changes efficiently, and bounding replica divergence---and provides a comprehensive survey of techniques developed for addressing these challenges.},
pages={42},
number={1},
journaltitle={{ACM} Computing Surveys},
author={Saito, Yasushi and Shapiro, Marc},
urldate={2023-06-09},
date={2005},
langid={english},
file={Saito et Shapiro - 2005 - Optimistic Replication.pdf:/home/amaury/Zotero/storage/4WJX5IAN/Saito et Shapiro - 2005 - Optimistic Replication.pdf:application/pdf},
}
@article{singh_zeno_nodate,
title={Zeno: Eventually Consistent Byzantine-Fault Tolerance},
abstract={Many distributed services are hosted at large, shared, geographically diverse data centers, and they use replication to achieve high availability despite the unreachability of an entire data center. Recent events show that non-crash faults occur in these services and may lead to long outages. While Byzantine-Fault Tolerance ({BFT}) could be used to withstand these faults, current {BFT} protocols can become unavailable if a small fraction of their replicas are unreachable. This is because existing {BFT} protocols favor strong safety guarantees (consistency) over liveness (availability).},
author={Singh, Atul and Fonseca, Pedro and Kuznetsov, Petr and Rodrigues, Rodrigo and Maniatis, Petros},
langid={english},
file={Singh et al. - Zeno Eventually Consistent Byzantine-Fault Tolera.pdf:/home/amaury/Zotero/storage/K6J2UEBK/Singh et al. - Zeno Eventually Consistent Byzantine-Fault Tolera.pdf:application/pdf},
}
@inproceedings{shakarami_refresh_2019,
title={Refresh Instead of Revoke Enhances Safety and Availability: A Formal Analysis},
volume={{LNCS}-11559},
url={https://inria.hal.science/hal-02384596},
doi={10.1007/978-3-030-22479-0_16},
shorttitle={Refresh Instead of Revoke Enhances Safety and Availability},
abstract={Due to inherent delays and performance costs, the decision point in a distributed multi-authority Attribute-Based Access Control ({ABAC}) system is exposed to the risk of relying on outdated attribute values and policy; which is the safety and consistency problem. This paper formally characterizes three increasingly strong levels of consistency to restrict this exposure. Notably, we recognize the concept of refreshing attribute values rather than simply checking the revocation status, as in traditional approaches. Refresh replaces an older value with a newer one, while revoke simply invalidates the old value. Our lowest consistency level starts from the highest level in prior revocation-based work by Lee and Winslett ({LW}). Our two higher levels utilize the concept of request time which is absent in {LW}. For each of our levels we formally show that using refresh instead of revocation provides added safety and availability.},
eventtitle={33th {IFIP} Annual Conference on Data and Applications Security and Privacy ({DBSec})},
pages={301},
publisher={Springer International Publishing},
author={Shakarami, Mehrnoosh and Sandhu, Ravi},
urldate={2023-06-09},
date={2019-07-15},
langid={english},
file={Shakarami et Sandhu - 2019 - Refresh Instead of Revoke Enhances Safety and Avai.pdf:/home/amaury/Zotero/storage/XQNWKF7H/Shakarami et Sandhu - 2019 - Refresh Instead of Revoke Enhances Safety and Avai.pdf:application/pdf},
}
@article{misra_axioms_1986,
title={Axioms for memory access in asynchronous hardware systems},
volume={8},
issn={0164-0925, 1558-4593},
url={https://dl.acm.org/doi/10.1145/5001.5007},
doi={10.1145/5001.5007},
abstract={The problem of concurrent accesses to registers by asynchronous components is considered. A set of axioms about the values in a register during concurrent accesses is proposed. It is shown that if these axioms are met by a register, then concurrent accesses to it may be viewed as nonconcurrent, thus making it possible to analyze asynchronous algorithms without elaborate timing analysis of operations. These axioms are shown, in a certain sense, to be the weakest. Motivation for this work came from analyzing low-level hardware components in a {VLSI} chip which concurrently accesses a flip-flop.},
pages={142--153},
number={1},
journaltitle={{ACM} Transactions on Programming Languages and Systems},
shortjournal={{ACM} Trans. Program. Lang. Syst.},
author={Misra, J.},
urldate={2023-06-08},
date={1986-01-02},
langid={english},
file={Misra - 1986 - Axioms for memory access in asynchronous hardware .pdf:/home/amaury/Zotero/storage/KZP2774N/Misra - 1986 - Axioms for memory access in asynchronous hardware .pdf:application/pdf},
}
@article{lamport_interprocess_1986,
title={On interprocess communication},
volume={1},
issn={1432-0452},
url={https://doi.org/10.1007/BF01786228},
doi={10.1007/BF01786228},
abstract={Interprocess communication is studied without assuming any lower-level communication primitives. Three classes of communication registers are considered, and several constructions are given for implementing one class of register with a weaker class. The formalism developed in Part I is used in proving the correctness of these constructions.},
pages={86--101},
number={2},
journaltitle={Distributed Computing},
shortjournal={Distrib Comput},
author={Lamport, Leslie},
urldate={2023-06-08},
date={1986-06-01},
langid={english},
keywords={Communication Network, Computer Hardware, Computer System, Operating System, System Organization},
file={Lamport - 1986 - On interprocess communication.pdf:/home/amaury/Zotero/storage/XV7AEARN/Lamport - 1986 - On interprocess communication.pdf:application/pdf},
}
@book{lipton_pram_1988,
title={{PRAM}: A Scalable Shared Memory},
shorttitle={{PRAM}},
pagetotal={13},
publisher={Princeton University, Department of Computer Science},
author={Lipton, Richard J. and Sandberg, Jonathan S.},
date={1988},
langid={english},
note={Google-Books-{ID}: 962epwAACAAJ},
file={Lipton et Sandberg - 1988 - PRAM A Scalable Shared Memory.pdf:/home/amaury/Zotero/storage/3ZYT3WT4/Lipton et Sandberg - 1988 - PRAM A Scalable Shared Memory.pdf:application/pdf},
}
@inproceedings{hutto_slow_1990,
title={Slow memory: weakening consistency to enhance concurrency in distributed shared memories},
abstract={The use of weakly consistent memories in distributed shared memory systems to combat unacceptable network delay and to allow such systems to scale is proposed. Proposed memory correctness conditions are surveyed, and how they are related by a weakness hierarchy is demonstrated. Multiversion and messaging interpretations of memory are introduced as means of systematically exploring the space of possible memories. Slow memory is presented as a memory that allows the effects of writes to propagate slowly through the system, eliminating the need for costly consistency maintenance protocols that limit concurrency. Slow memory processes a valuable locality property and supports a reduction from traditional atomic memory. Thus slow memory is as expressive as atomic memory. This expressiveness is demonstrated by two exclusion algorithms and a solution to M.J. Fischer and A. Michael's (1982) dictionary problem on slow memory.},
eventtitle={Proceedings.,10th International Conference on Distributed Computing Systems},
file={Hutto et Ahamad - 1990 - Slow memory weakening consistency to enhance conc.pdf:/home/amaury/Téléchargements/Hutto et Ahamad - 1990 - Slow memory weakening consistency to enhance conc.pdf:application/pdf},
}
@article{lamport_how_1979,
title={How to Make a Multiprocessor Computer That Correctly Executes Multiprocess Programs},
volume={C-28},
issn={1557-9956},
doi={10.1109/TC.1979.1675439},
abstract={Many large sequential computers execute operations in a different order than is specified by the program. A correct execution is achieved if the results produced are the same as would be produced by executing the program steps in order. For a multiprocessor computer, such a correct execution by each processor does not guarantee the correct execution of the entire program. Additional conditions are given which do guarantee that a computer correctly executes multiprocess programs.},
pages={690--691},
number={9},
journaltitle={{IEEE} Transactions on Computers},
author={{Lamport}},
date={1979-09},
note={Conference Name: {IEEE} Transactions on Computers},
file={IEEE Xplore Abstract Record:/home/amaury/Zotero/storage/IVGSSPNE/1675439.html:text/html;Lamport - 1979 - How to Make a Multiprocessor Computer That Correct.pdf:/home/amaury/Zotero/storage/GY8CWGUV/Lamport - 1979 - How to Make a Multiprocessor Computer That Correct.pdf:application/pdf},
abstract={This paper discusses memory consistency models and their influence on software in the context of parallel machines. In the first part we review previous work on memory consistency models. The second part discusses the issues that arise due to weakening memory consistency. We are especially interested in the influence that weakened consistency models have on language, compiler, and runtime system design. We conclude that tighter interaction between those parts and the memory system might improve performance considerably.},
pages={18--26},
number={1},
journaltitle={{ACM} {SIGOPS} Operating Systems Review},
abstract={The use of weakly consistent memories in distributed shared memory systems to combat unacceptable network delay and to allow such systems to scale is proposed. Proposed memory correctness conditions are surveyed, and how they are related by a weakness hierarchy is demonstrated. Multiversion and messaging interpretations of memory are introduced as means of systematically exploring the space of possible memories. Slow memory is presented as a memory that allows the effects of writes to propagate slowly through the system, eliminating the need for costly consistency maintenance protocols that limit concurrency. Slow memory processes a valuable locality property and supports a reduction from traditional atomic memory. Thus slow memory is as expressive as atomic memory. This expressiveness is demonstrated by two exclusion algorithms and a solution to M.J. Fischer and A. Michael's (1982) dictionary problem on slow memory.},
eventtitle={Proceedings.,10th International Conference on Distributed Computing Systems},
booktitle={Foundations of Software Technology and Theoretical Computer Science},
publisher={Springer Berlin Heidelberg},
author={Raynal, Michel and Schiper, André},
editor={Thiagarajan, P. S.},
editorb={Goos, Gerhard and Hartmanis, Juris and Leeuwen, Jan},
editorbtype={redactor},
urldate={2023-06-06},
date={1995},
langid={english},
doi={10.1007/3-540-60692-0_48},
note={Series Title: Lecture Notes in Computer Science},
file={Raynal et Schiper - 1995 - From causal consistency to sequential consistency .pdf:/home/amaury/Zotero/storage/B8UNWUSA/Raynal et Schiper - 1995 - From causal consistency to sequential consistency .pdf:application/pdf},
}
@thesis{kumar_fault-tolerant_2019,
title={Fault-Tolerant Distributed Services in Message-Passing Systems},
institution={Texas A\&M University},
type={phdthesis},
author={Kumar, Saptaparni},
date={2019},
file={Kumar - 2019 - Fault-Tolerant Distributed Services in Message-Pas.pdf:/home/amaury/Zotero/storage/Q9XK77W9/Kumar - 2019 - Fault-Tolerant Distributed Services in Message-Pas.pdf:application/pdf;Snapshot:/home/amaury/Zotero/storage/7JB26RAJ/1.html:text/html},
}
@article{somasekaram_high-availability_2022,
title={High-Availability Clusters: A Taxonomy, Survey, and Future Directions},
volume={187},
issn={01641212},
url={http://arxiv.org/abs/2109.15139},
doi={10.1016/j.jss.2021.111208},
shorttitle={High-Availability Clusters},
abstract={The delivery of key services in domains ranging from finance and manufacturing to healthcare and transportation is underpinned by a rapidly growing number of mission-critical enterprise applications. Ensuring the continuity of these complex applications requires the use of software-managed infrastructures called high-availability clusters ({HACs}). {HACs} employ sophisticated techniques to monitor the health of key enterprise application layers and of the resources they use, and to seamlessly restart or relocate application components after failures. In this paper, we first describe the manifold uses of {HACs} to protect essential layers of a critical application and present the architecture of high availability clusters. We then propose a taxonomy that covers all key aspects of {HACs} -- deployment patterns, application areas, types of cluster, topology, cluster management, failure detection and recovery, consistency and integrity, and data synchronisation; and we use this taxonomy to provide a comprehensive survey of the end-to-end software solutions available for the {HAC} deployment of enterprise applications. Finally, we discuss the limitations and challenges of existing {HAC} solutions, and we identify opportunities for future research in the area.},
pages={111208},
journaltitle={Journal of Systems and Software},
shortjournal={Journal of Systems and Software},
author={Somasekaram, Premathas and Calinescu, Radu and Buyya, Rajkumar},
urldate={2023-06-06},
date={2022-05},
eprinttype={arxiv},
eprint={2109.15139 [cs, eess]},
keywords={Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Networking and Internet Architecture, Electrical Engineering and Systems Science - Systems and Control},
file={arXiv.org Snapshot:/home/amaury/Zotero/storage/B4KCP9BG/2109.html:text/html;Somasekaram et al. - 2022 - High-Availability Clusters A Taxonomy, Survey, an.pdf:/home/amaury/Zotero/storage/K3LQZLC8/Somasekaram et al. - 2022 - High-Availability Clusters A Taxonomy, Survey, an.pdf:application/pdf},
}
@book{perrin_concurrence_2017,
title={Concurrence et cohérence dans les systèmes répartis},
isbn={978-1-78405-295-9},
abstract={La société moderne est de plus en plus dominée par la société virtuelle, le nombre d’internautes dans le monde ayant dépassé les trois milliards en 2015. A la différence de leurs homologues séquentiels, les systèmes répartis sont beaucoup plus difficiles à concevoir, et sont donc sujets à de nombreux problèmes.La cohérence séquentielle fournit la même vue globale à tous les utilisateurs, mais le confort d\&\#39;utilisation qu\&\#39;elle apporte est trop coûteux, voire impossible, à mettre en oeuvre à grande échelle. Concurrence et cohérence dans les systèmes répartis examine les meilleures façons de spécifier les objets que l’on peut tout de même implémenter dans ces systèmes.Cet ouvrage explore la zone grise des systèmes répartis et dresse une carte des critères de cohérence faible, identifiant plusieurs familles et démontrant comment elles peuvent s’intégrer dans un langage de programmation.},
pagetotal={194},
publisher={{ISTE} Group},
author={Perrin, Matthieu},
date={2017-09-01},
langid={french},
note={Google-Books-{ID}: 6DRlDwAAQBAJ},
file={Perrin - 2017 - Concurrence et cohérence dans les systèmes réparti.pdf:/home/amaury/Téléchargements/Perrin - 2017 - Concurrence et cohérence dans les systèmes réparti.pdf:application/pdf},
}
@article{van_der_linde_practical_2020,
title={Practical client-side replication: weak consistency semantics for insecure settings},
abstract={Client-side replication and direct client-to-client synchronization can be used to create highly available, low-latency interactive applications. Causal consistency, the strongest available consistency model under network partitions, is an attractive consistency model for these applications.},
pages={2590--2605},
number={12},
journaltitle={Proceedings of the {VLDB} Endowment},
shortjournal={Proc. {VLDB} Endow.},
author={Van Der Linde, Albert and Leitão, João and Preguiça, Nuno},
urldate={2023-06-06},
date={2020-08},
langid={english},
file={Van Der Linde et al. - 2020 - Practical client-side replication weak consistenc.pdf:/home/amaury/Zotero/storage/5TJ3SA56/Van Der Linde et al. - 2020 - Practical client-side replication weak consistenc.pdf:application/pdf},
}
@article{decandia_dynamo_nodate,
title={Dynamo: Amazon’s Highly Available Key-value Store},
abstract={Reliability at massive scale is one of the biggest challenges we face at Amazon.com, one of the largest e-commerce operations in the world; even the slightest outage has significant financial consequences and impacts customer trust. The Amazon.com platform, which provides services for many web sites worldwide, is implemented on top of an infrastructure of tens of thousands of servers and network components located in many datacenters around the world. At this scale, small and large components fail continuously and the way persistent state is managed in the face of these failures drives the reliability and scalability of the software systems.},
author={{DeCandia}, Giuseppe and Hastorun, Deniz and Jampani, Madan and Kakulapati, Gunavardhan and Lakshman, Avinash and Pilchin, Alex and Sivasubramanian, Swaminathan and Vosshall, Peter and Vogels, Werner},
langid={english},
file={DeCandia et al. - Dynamo Amazon’s Highly Available Key-value Store.pdf:/home/amaury/Zotero/storage/KDHRPBGR/DeCandia et al. - Dynamo Amazon’s Highly Available Key-value Store.pdf:application/pdf},
__perrin_concurrence_2017__, "Concurrence et cohérence dans les systèmes répartis":
Etat de l'art sur la cohérence dans les systèmes repartis. Présentation d'une approche de modélisation des histoires concurentes. Formaisations de différents critères de cohérences. Comparaison et "hierarchisation" des différents critères de cohérences.
Formalisation d'une cohérence séquentiel "single writer"
__misra_axioms_1986__, "Axioms for memory access in asynchronous hardware systems":
Exetnsion de lamport_interprocess_1986 dans une approche "multi-writer"
__lipton_pram_1988__, "{PRAM}: A Scalable Shared Memory":
Definition de la mémoire PRAM (cohérence pipeline).
## Cohérence en contextes byzantins
### Algorithmes
__van_der_linde_practical_2020__, "Practical client-side replication: weak consistency semantics for insecure settings":
Algorithme pour de la Cohérence causale BFT. (Reflexions sur des erreurs byzantines possible + algo et implé)
__kumar_fault-tolerant_2019__, "Fault-Tolerant Distributed Services in Message-Passing Systems":
Pas spécifiquement à propos des fautes byzantines dans la cohérence faible mais fait un panorama des differentes fautes non-byzantine possibles dans les systèmes distribués.
__singh_zeno_2009__, "Zeno: Eventually Consistent Byzantine-Fault Tolerance":
Algorithme pour de la convergence BFT. (Reflexions sur des erreurs byzanties possible + algo et implé)
