Optimal Record and Replay under Causal Consistency

TL;DR

This paper determines the minimal amount of information needed to replay causally consistent executions in shared memory systems, providing optimal recording strategies for both offline and online scenarios.

Contribution

It introduces optimal record-keeping methods for replaying causally consistent executions, addressing both offline and online recording settings.

Findings

Optimal records identified for offline setting

Optimal online recording strategies developed

Enhanced understanding of causally consistent replay requirements

Abstract

We investigate the minimum record needed to replay executions of processes that share causally consistent memory. For a version of causal consistency, we identify optimal records under both offline and online recording setting. Under the offline setting, a central authority has information about every process' view of the execution and can decide what information to record for each process. Under the online setting, each process has to decide on the record at runtime as the operations are observed.