MODC: Resilience for disaggregated memory architectures using task-based programming

TL;DR

MODC introduces a task-based programming framework for disaggregated memory architectures, enhancing resilience by leveraging failure independence and outperforming traditional checkpointing methods.

Contribution

This paper presents MODC, a novel framework that adapts task-based programming and fault tolerance techniques to disaggregated memory architectures for improved resilience.

Findings

MODC outperforms checkpoint-based resilience methods in experiments.

Disaggregated memory architectures benefit from task-based resilience strategies.

MODC demonstrates effective fault tolerance in disaggregated systems.

Abstract

Disaggregated memory architectures provide benefits to applications beyond traditional scale out environments, such as independent scaling of compute and memory resources. They also provide an independent failure model, where computations or the compute nodes they run on may fail independently of the disaggregated memory; thus, data that's resident in the disaggregated memory is unaffected by the compute failure. Blind application of traditional techniques for resilience (e.g., checkpoints or data replication) does not take advantage of these architectures. To demonstrate the potential benefit of these architectures for resilience, we develop Memory-Oriented Distributed Computing (MODC), a framework for programming disaggregated architectures that borrows and adapts ideas from task-based programming models, concurrent programming techniques, and lock-free data structures. This framework includes a task-based application programming model and a runtime system that provides scheduling, coordination, and fault tolerance mechanisms. We present highlights of our MODC prototype and experimental results demonstrating that MODC-style resilience outperforms a checkpoint-based approach in the face of failures.