Report
KCensus: Synthesizing Latency-Optimal Consensus Fast Paths (Extended Version)
| Τίτλος: | KCensus: Synthesizing Latency-Optimal Consensus Fast Paths (Extended Version) |
|---|---|
| Συγγραφείς: | Burgelin, Clément, Murat, Antoine, Sela, Gal, Aguilera, Marcos K., Guerraoui, Rachid |
| Έτος έκδοσης: | 2026 |
| Θεματικοί όροι: | Distributed, Parallel, and Cluster Computing, C.2.4; C.4 |
| Περιγραφή: | Strongly consistent geo-replication often relies on fast paths to reduce latency in the common case of no failures or contention. Existing fast-path schemes, however, are ad hoc and restrictive: each corresponds to a point in a broad design space shaped by network topology, workload, and latency objective, so no single scheme works best across settings. This paper looks at fast-path schemes from a new perspective, as mechanisms that spread knowledge about proposals. With this view, we identify a fundamental condition on the spread of knowledge for a fast-path scheme to work. We then introduce KCensus, a framework that turns this condition into an optimization problem, synthesizing new fast-path schemes that are optimal for a given setting. We use KCensus to build a geo-replicated key-value store and evaluate it across AWS regions. Our system outperforms competing protocols, with up to 16% lower average latency. 38 pages, 15 figures. Extended version of the paper to appear in the 22nd European Conference on Computer Systems (EuroSys '27), Rabat, Morocco. Includes appendices with full correctness and optimality proofs |
| Τύπος εγγράφου: | Working Paper |
| DOI: | 10.48550/arXiv.2609.31302 |
| Σύνδεσμος πρόσβασης: | https://arxiv.org/abs/2609.31302 |
| Αριθμός Καταχώρησης: | edsarx.2609.31302 |
| Βάση Δεδομένων: | arXiv |
| DOI: | 10.48550/arXiv.2609.31302 |
|---|