Impact of the Consistency Model on Checkpointing of Distributed Shared Memory

TL;DR

This paper examines how different consistency models in distributed shared memory affect the design and efficiency of checkpointing and rollback algorithms, highlighting that stronger consistency simplifies these processes.

Contribution

It develops checkpointing and rollback algorithms tailored for four specific consistency models and empirically shows that stronger models facilitate simpler, more efficient checkpointing.

Findings

Stronger consistency models lead to simpler checkpointing algorithms.

Checkpointing mechanisms vary significantly across different consistency models.

Empirical results demonstrate efficiency gains with stronger consistency implementations.

Abstract

In this report, we consider the impact of the consistency model on checkpointing and rollback algorithms for distributed shared memory. In particular, we consider specific implementations of four consistency models for distributed shared memory, namely, linearizability, sequential consistency, causal consistency and eventual consistency, and develop checkpointing and rollback algorithms that can be integrated into the implementations of the consistency models. Our results empirically demonstrate that the mechanisms used to implement stronger consistency models lead to simpler or more efficient checkpointing algorithms.