Reconfigurable distributed storage for dynamic networks

Chockler, Gregory; Gilbert, Seth; Gramoli, Vincent; Musial, Peter M.; Shvartsman, Alexander A.

doi:10.1016/j.jpdc.2008.07.007

Cited by 34 publications

(23 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Indeed, not only the traversal is lock-free compared to [3], but it does not require the confirmation phase of [9,8], while proposing fast adaptive read operations: such operations are called fast since they require a single phase instead of two. Minimizing atomic read operation latency suffers some limitations.…”

Section: Algorithm Descriptionmentioning

confidence: 99%

“…Quorums for dynamic systems appeared in [10,13,2,17,16,9,8,7]. Herlihy [10] proposes quorum modification to cope with failures.…”

Section: Introductionmentioning

confidence: 99%

“…Herlihy [10] proposes quorum modification to cope with failures. In [13,9,8] quorum systems are subsequently replaced by independent ones to cope with permanent failures. In [2,17,16,19], a quorum relies on a specific dynamic structure, and quorum probes are said adaptive (they contact the quorum members successively in a reactive manner).…”

Section: Introductionmentioning

confidence: 99%

“…Since then, [3,13,9,8] have implemented atomicity in dynamic systems. First, the architecture of [3] provides an atomic service that locks operations when a value is being written to prevent from reading stale values.…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, high concurrency might delay such operations for an arbitrarily long period of time. The work presented in [13,9,8] provide quorum reconfiguration mechanisms to cope with permanent changes. These papers have a common design seed: they propose quorum system replacement, thus replacing the whole quorums participants by others.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Square

Gramoli

Anceaume

Virgillito

2007

Proceedings of the 2007 ACM Symposium on Applied Computing

Self Cite

View full text Add to dashboard Cite

Internet-scale applications require more and more resources to satisfy the unpredictable clients needs. Specifically, such applications must ensure quality of service despite bursts of load. Distributed dynamic self-organized systems present an inherent adaptiveness that can face unpredictable bursts of load. Nevertheless quality of service, and more particularly data consistency, remains hardly achievable in such systems since participants (i.e., nodes) can crash, leave, and join the system at arbitrary time. Atomic consistency guarantees that any read operation returns the last written value of a data and is generalizable to data composition. To guarantee atomic consistency in message-passing model, mutually intersecting sets (a.k.a. quorums) of nodes are used. The solution presented here, namely Square, uses self-adaptiveness and load-balancing to provide atomic consistency in large-scale dynamic distributed systems. This paper presents the Square algorithm and uses extensive simulation to show it achieves its desirable properties.

show abstract

Section: Algorithm Descriptionmentioning

confidence: 99%

“…Quorums for dynamic systems appeared in [10,13,2,17,16,9,8,7]. Herlihy [10] proposes quorum modification to cope with failures.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Square

Gramoli

Anceaume

Virgillito

2007

Proceedings of the 2007 ACM Symposium on Applied Computing

Self Cite

View full text Add to dashboard Cite

show abstract

ComChain: A blockchain with Byzantine fault‐tolerant reconfiguration

Vizier

Gramoli

2019

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Selecting which blockchain participants can decide upon a new block is a difficult problem.Consortium blockchains need the participants to be predetermined while public blockchains incentivize all participants to waste their resources to decide every block. In this paper, we introduce the community blockchain that allows potentially all participants to decide upon ''some'' block while restricting the set of participants deciding upon ''one'' block. To this end, we propose a blockchain reconfiguration, a Byzantine consensus protocol that allows to dynamically change the set of blockchain participants deciding upon the upcoming blocks. The resulting blockchain, called ComChain, is resilience optimal and transitions through different configurations of participants recorded in dedicated blocks so that each configuration decides upon its subsequent transaction blocks. We evaluate an implementation that adds reconfiguration to the Red Belly Blockchain and demonstrates its practical performance in a distributed system.

show abstract