Adaptive request batching for byzantine replication

Abstract

Castro and Liskov proposed in 1999 a successful solution for byzantine fault-tolerant replication, named PBFT, which overcame performance drawbacks of earlier byzantine faulttolerant replication protocols. Other proposals extended PBFT with further optimizations, improving PBFT performance in certain conditions. One of the key optimizations of PBFT-based protocols is the use a request batching mechanism. If the target distributed system is dynamic, that is, if its underlying characteristics change dynamically, such as workload, channel QoS, network topology, etc., the configuration of the request batching mechanism must follow the dynamics of the system or it may not yield the desired performance improvement. This paper addresses this challenge by proposing an innovative solution to the dynamic configuration of request batching parameters inspired on feedback control theory. In order to evaluate its efficiency, the proposed solution is simulated in various scenarios and compared with the original version used in the PBFT-family protocols.

Bernoulli Meets PBFT: Modeling BFT Protocols in the Presence of Dynamic Failures

“…If the happy path of a protocol fails to make progress, a sub-protocol, e.g., a view change protocol, is triggered to recover [15]. To optimize performance, the timeout values should depend on the bounded message delay in the synchronous periods of the network, which plays an important role for deployments [16]. In addition to message delay characteristics, some networks, e.g., wireless networks, might be susceptible to link failures, leading to message omissions or corruptions.…”