Treffer: Leaderless state-machine replication: specification, properties, limits

Title:
Leaderless state-machine replication: specification, properties, limits
Contributors:
Institut Polytechnique de Paris (IP Paris), Département Informatique (TSP - INF), Institut Mines-Télécom Paris (IMT)-Télécom SudParis (TSP), Institut Polytechnique de Paris (IP Paris)-Institut Polytechnique de Paris (IP Paris), Efficient and safe distributed systems (Benagil-Samovar), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Institut Polytechnique de Paris (IP Paris)-Institut Polytechnique de Paris (IP Paris)-Institut Mines-Télécom Paris (IMT)-Télécom SudParis (TSP)
Source:
https://hal.science/hal-04251870 ; Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2020, 34th International Symposium on Distributed Computing, ⟨10.4230/LIPIcs.DISC.2020.24⟩.
Publisher Information:
CCSD
Schloss Dagstuhl - Leibniz-Zentrum für Informatik
Publication Year:
2020
Document Type:
Konferenz conference object
Language:
English
DOI:
10.4230/LIPIcs.DISC.2020.24
Accession Number:
edsbas.B3780B9D
Database:
BASE

Weitere Informationen

International audience ; Modern Internet services commonly replicate critical data across several geographical locations using state-machine replication (SMR). Due to their reliance on a leader replica, classical SMR protocols offer limited scalability and availability in this setting. To solve this problem, recent protocols follow instead a leaderless approach, in which each replica is able to make progress using a quorum of its peers. In this paper, we study this new emerging class of SMR protocols and states some of their limits. We first propose a framework that captures the essence of leaderless state-machine replication (Leaderless SMR). Then, we introduce a set of desirable properties for these protocols: (R)eliability, (O)ptimal (L)atency and (L)oad Balancing. We show that protocols matching all of the ROLL properties are subject to a trade-off between performance and reliability. We also establish a lower bound on the message delay to execute a command in protocols optimal for the ROLL properties. This lower bound explains the persistent chaining effect observed in experimental results.