Index-Based Scheduling for Parallel State Machine Replication
Gang Wu1, Guodong Zhao, Yidong Song

TL;DR
This paper introduces an index-based scheduler for parallel state machine replication that reduces overhead and improves scalability by efficiently detecting transaction dependencies using a Bloom Filter and transaction queues.
Contribution
It proposes a novel index structure combining a Bloom Filter and transaction queues to enhance dependency detection and concurrent scheduling in parallel SMR.
Findings
The proposed scheduler outperforms existing methods in efficiency.
It demonstrates improved scalability and robustness.
Experimental results confirm better performance in various scenarios.
Abstract
State Machine Replication (SMR) is a fundamental approach to designing service with fault tolerance. However, its requirement for the deterministic execution of transactions often results in single-threaded replicas, which cannot fully exploit the multicore capabilities of today's processors. Therefore, parallel SMR has become a hot topic of recent research. The basic idea behind it is that independent transactions can be executed in parallel, while dependent transactions must be executed in their relative order to ensure consistency among replicas. The dependency detection of existing parallel SMR methods is mainly based on pairwise transaction comparison or batch comparison. These methods cannot simultaneously guarantee both effective detection and concurrent execution. Moreover, the scheduling process cannot execute concurrently, which introduces extra scheduling overhead as well. In…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDistributed systems and fault tolerance · Cognitive Functions and Memory · Optimization and Search Problems
