Atomic RMI 2: Highly Parallel Pessimistic Distributed Transactional Memory

TL;DR

This paper introduces Atomic RMI 2, a highly parallel distributed transactional memory system based on the control flow model, which outperforms existing systems by supporting fine-grained pessimistic concurrency and asynchronous execution.

Contribution

It presents OptSVA-CF, a novel control flow DTM synchronization algorithm that enables high parallelism and strong safety, filling a gap in existing control flow DTM systems.

Findings

Outperforms HyFlow2 in benchmarks

Supports fine-grained pessimistic concurrency

Achieves high parallelism with safety guarantees

Abstract

Distributed Transactional Memory (DTM) is an emerging approach to distributed synchronization based on the application of the transaction abstraction to distributed computation. DTM comes in several system models, but the control flow model (CF) is particularly powerful, since it allows transactions to delegate computation to remote nodes as well as access shared data. However, there are no existing CF DTM systems that perform on par with state-of-the-art systems operating in other models. Hence, we introduce a CF DTM synchronization algorithm, OptSVA-CF. It supports fine-grained pessimistic concurrency control, so it avoids aborts, and thus avoids problems with irrevocable operations. Furthermore, it uses early release and asynchrony to parallelize concurrent transactions to a high degree, while retaining strong safety properties. We implement it as Atomic RMI 2, in effect producing a CF DTM system that, as our evaluation shows, can outperform a state-of-the-art non-CF DTM such as HyFlow2.