Separating agreement from execution for byzantine fault tolerant services

Abstract

We describe a new architecture for Byzantine fault tolerant state machine replication that separates agreement that orders requests from execution that processes requests. This separation yields two fundamental and practically significant advantages over previous architectures. First, it reduces replication costs because the new architecture can tolerate faults in up to half of the state machine replicas that execute requests. Previous systems can tolerate faults in at most a third of the combined agreement/state machine replicas. Second, separating agreement from execution allows a general privacy firewall architecture to protect confidentiality through replication. In contrast, replication in previous systems hurts confidentiality because exploiting the weakest replica can be sufficient to compromise the system. We have constructed a prototype and evaluated it running both microbenchmarks and an NFS server. Overall, we find that the architecture adds modest latencies to unreplicated systems and that its performance is competitive with existing Byzantine fault tolerant systems.

Byzantine Chain Replication

“…In HMAC Shuttle, it is not necessary for all 2t + 1 replicas to maintain running state [13]. The chain is split into two parts.…”

“…Aardvark [30] and Zyzzyvark [31] focus on sustainable performance rather than peak performance. Other proposals focus on reducing the number of full replicas [13,32,33]. Table 1 compares various aspects of Shuttle with related work.…”

“…Also, the protocols may require expensive cryptographic operations and significant network bandwidth, further increasing cost; -Significant progress has been made at reducing the cost of BSMR [12][13][14].…”

Proactive service migration for long-running Byzantine fault-tolerant systems

“…These malicious faults are often modeled as Byzantine faults [9], and they are detrimental to any online service providers. Such threats can be coped with using Byzantine fault tolerance (BFT) techniques, as demonstrated by many research results [2,3,4,5,7,11,13,16]. The Byzantine fault tolerance algorithms assume that only a small portion of the replicas can be faulty.…”

Practical Byzantine Group Communication

“…When the execution of client requests is computation-intensive, it is worth splitting the decision on the execution order from the execution itself [56]. For example, in [43], they use an agreement cluster of 3f + 1 nodes to decide only on the ordering of executions, and then pass the execution itself to a set, called primary committee, of only f + 1 nodes.…”