RMP: fault-tolerant group communication

Jia, W.; Kaiser, Jörg; Nett, Edgar

doi:10.1109/40.491463

Cited by 34 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DWM is evaluated by analysis, and absolute delay time and real-time requirements are not considered. Group management and group communication enables scalable replication when group sizes are relatively small [8]. This is orthogonal to our work and will likely improve resource usage for replication in ViFuR-A.…”

Section: S2: Storage and Delay Scalabilitymentioning

confidence: 95%

Virtual Full Replication by Adaptive Segmentation

Mathiason

Andler

Son

2007

13th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA 2007)

View full text Add to dashboard Cite

Section: S2: Storage and Delay Scalabilitymentioning

confidence: 95%

Virtual Full Replication by Adaptive Segmentation

Mathiason

Andler

Son

2007

13th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA 2007)

View full text Add to dashboard Cite

“…Transis [2] was the first system that allowed partitions to continue with independent groups. It has been followed by several other such as Totem [18], Moshe [14], Relacs [5], Jgroups [6], Newtop [10], and RMP [13]. For a comprehensive comparison of different group communication services, we recommend the paper by Chockler et al [9].…”

Section: Related Workmentioning

confidence: 99%

Specification, Implementation and Verification of Dynamic Group Membership for Vehicle Coordination

Asplund

Lövhall

Villani

2017

2017 IEEE 22nd Pacific Rim International Symposium on Dependable Computing (PRDC)

View full text Add to dashboard Cite

Abstract-New advanced traffic management solutions with fully or semi-autonomous vehicles that communicate over a wireless interface to coordinate their driving decisions create new challenges in distributed computing. In this paper we address the problem of dynamic group membership in three stages. First, we propose three criteria to specify correctness and performance of the group views created by such algorithms in terms of soundness, completeness and freshness. Second, we develop a group membership protocol tailored for vehicular coordination. Finally, we show through simulation and model-based verification that the protocol does indeed meet the criteria and provide at least 95% perfect group membership views under as adverse conditions as 70% packet loss or very high churn rate.

show abstract

“…The RMP [1], DTP [2], Pin Wheel [3] and [4,22] are the various mechanisms to achieve moving sequencer based atomic broadcast. In moving sequencer mechanisms, there must be some process that is responsible for sequencing.…”

Section: Related Workmentioning

confidence: 99%

“…So to get rid of this problem moving sequencer is a best option where not a fixed process will be sequencer. RMP [1], DTP [2] ,pin wheel [3] and [4] are based on moving sequencer and tolerate crash failure but not capable to tolerate the omission Failure. So this work has proposed a new mechanism to build atomic broadcast that is based on moving sequencer and will tolerate the omission failure.…”

Section: Introductionmentioning

confidence: 99%

Rigorous Design of moving Sequencer Omission Tolerant Atomic Broadcast

Srivastava¹,

Chakrabarti²,

Panwar³

2014

IJCA

View full text Add to dashboard Cite

This article investigates a mechanism to tolerate omission failure in moving sequencer based atomic broadcast at distributed systems. Various mechanisms are already given for moving sequencer based atomic broadcast like RMP [1], DTP [2], Pin Wheel [3] and mechanism proposed by [4]. But none of these mechanisms are efficient to tolerate different failure. Scholarly observation is that, these algorithms can tolerate only crash failure but not capable to tolerate omission or byzantine failure. This work is an extension of [4]. This work proposes a mechanism to tolerate omission failure in moving sequencer based atomic broadcast. Hence this work is a refined version of [4]. This work relies on unicast broadcast hence it will introduce a very less number of messages in comparison to previous mechanisms [5]. B [6] has been used as formal technique for development of proposed model. B uses set theory as a modeling notation, refinements to represent system at different abstraction level. Pro B [7] has been used as model checker and animator for constraint based checking, to discover errors due to invariant violation and for deadlocks, thereby, validating the specifications.

show abstract

RMP: fault-tolerant group communication

Cited by 34 publications

References 15 publications

Virtual Full Replication by Adaptive Segmentation

Virtual Full Replication by Adaptive Segmentation

Specification, Implementation and Verification of Dynamic Group Membership for Vehicle Coordination

Rigorous Design of moving Sequencer Omission Tolerant Atomic Broadcast

Contact Info

Product

Resources

About