INGI Seminar

Transparent Speculation in Geo-Replicated Transactional Data Stores

by Zhongmiao Li, a PhD student at INGI department of UCLouvain

This work presents Speculative Transaction Replication (STR), a protocol that exploits transparent speculation techniques to enhance performance of geo-distributed, partially replicated transactional data stores. In addition, we define a new consistency model, Speculative Snapshot Isolation (SPSI), that extends the semantics of Snapshot Isolation (SI) to shelter applications from the subtle anomalies that can arise from using speculative transaction processing. SPSI extends SI in an intuitive and rigorous fashion by specifying desirable atomicity and isolation guarantees that must hold when using speculative execution. STR provides a form of speculation that is fully transparent for programmers (it does not expose the e ects of misspeculations to clients). We assess STR’s performance on up to nine geo-distributed Amazon EC2 data centers, using both synthetic benchmarks as well as realistic benchmarks. Our evaluation shows that STR achieves throughput gains up to 11× and latency reduction up to 10×.

Zhongmiao Li is a PhD student at INGI department of UCLouvain, Belgium. Prior to that, he did a joint master in Distributed Computing in Instituto Superior Técnico, Portugal and Royal Institute of Technology, Sweden. His PhD research is about applying speculative techniques to partially-replicated distributed transactions data store to improve performance.