Steward: Scaling Byzantine Fault-Tolerant Replication to Wide Area Networks

Amir, Yair; Danilov, Claudiu; Dolev, Danny; Kirsch, John A. W.; Lane, John W.; Nita-Rotaru, Cristina; Olsen, Josh; Zage, David John

doi:10.1109/tdsc.2008.53

Cited by 90 publications

(90 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While "correct" in the traditional sense (both safety and liveness are met), systems vulnerable to such performance degradation are of limited practical use in adversarial environments. We experienced this problem firsthand in 2005, when DARPA conducted a red team experiment on our Steward system [7]. Steward survived all of the tests according to the metrics of safety and liveness, and most attacks did not impact performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prime: Byzantine Replication under Attack

Amir

Coan²,

Kirsch

et al. 2011

IEEE Trans. Dependable and Secure Comput.

145

104

View full text Add to dashboard Cite

Abstract-Existing Byzantine-resilient replication protocols satisfy two standard correctness criteria, safety and liveness, even in the presence of Byzantine faults. The runtime performance of these protocols is most commonly assessed in the absence of processor faults and is usually good in that case. However, in some protocols faulty processors can significantly degrade performance, limiting the practical utility of these protocols in adversarial environments. This paper demonstrates the extent of performance degradation possible in some existing protocols that do satisfy liveness and that do perform well absent Byzantine faults. We propose a new performanceoriented correctness criterion that requires a consistent level of performance, even when the system exhibits Byzantine faults. We present a new Byzantine fault-tolerant replication protocol that meets the new correctness criterion and evaluate its performance in fault-free executions and when under attack.

show abstract

Section: Introductionmentioning

confidence: 99%

“…We observed that most of the protocols (e.g., [5], [6], [7], [8], [9], [10], [11]) share a common feature: they rely on an elected leader to coordinate the agreement protocol. We call such protocols leader based.…”

Section: Introductionmentioning

confidence: 99%

Prime: Byzantine Replication under Attack

Amir

Coan²,

Kirsch

et al. 2011

IEEE Trans. Dependable and Secure Comput.

145

104

View full text Add to dashboard Cite

show abstract

“…Numerous BFT algorithms have been proposed [19][20][21][22][23][24][25][26][27][28][29]. Many of these algorithms are designed to protect generic stateful servers against Byzantine faulty server replicas and faulty clients.…”

Section: Related Workmentioning

confidence: 99%

Towards Trustworthy Collaborative Editing

Babi¹,

Zhao²

2017

Computers

View full text Add to dashboard Cite

Real-time collaborative editing applications are drastically different from typical client-server applications in that every participant has a copy of the shared document. In this type of environment, each participant acts as both a client and a server replica. In this article, we elaborate on how to adapt Byzantine fault tolerance (BFT) mechanisms to enhance the trustworthiness of such applications. It is apparent that traditional BFT algorithms cannot be used directly because it would dictate that all updates submitted by participants be applied sequentially, which would defeat the purpose of collaborative editing. The goal of this study is to design and implement an efficient BFT solution by exploiting the application semantics and by doing a threat analysis of these types of applications. Our solution can be considered as a form of optimistic BFT in that local states maintained by each participant may diverge temporarily. The states of the participants are made consistent with each other by a periodic synchronization mechanism.

show abstract

“…Steward [22] is a hierarchical replicated state machine architecture for WAN. A group of servers in a site is converted into a logical entity that works as a single participant in a wide-area protocol.…”

Section: Related Workmentioning

confidence: 99%

D-Paxos: Building Hierarchical Replicated State Machine for Cloud Environments

Liu

Yang

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe present a hierarchical replicated state machine (H-RSM) and its corresponding consensus protocol D-Paxos for replication across multiple data centers in the cloud. Our H-RSM is based on the idea of parallel processing and aims to improve resource utilization. We detail D-Paxos and theoretically prove that D-Paxos implements an H-RSM. With batching and logical pipelining, D-Paxos efficiently utilizes the idle time caused by high-latency message transmission in a wide-area network and available bandwidth in a local-area network. Experiments show that D-Paxos provides higher throughput and better scalability than other Paxos variants for replication across multiple data centers. To predict the optimal batch sizes when D-Paxos reaches its maximum throughput, an analytical model is developed theoretically and validated experimentally.

show abstract

Steward: Scaling Byzantine Fault-Tolerant Replication to Wide Area Networks

Cited by 90 publications

References 38 publications

Prime: Byzantine Replication under Attack

Prime: Byzantine Replication under Attack

Towards Trustworthy Collaborative Editing

D-Paxos: Building Hierarchical Replicated State Machine for Cloud Environments

Contact Info

Product

Resources

About