Faster Transaction Commit even when Nodes Crash

TL;DR

This paper introduces a new protocol for in-memory transactions that ensures faster commit times even during node crashes by enabling uninterrupted progress without blocking.

Contribution

The paper presents a novel atomic broadcast protocol that maintains progress during node crashes, improving transaction commit speed and system availability.

Findings

Protocol achieves faster transaction commits during crashes.

System maintains progress without blocking during node failures.

Enhanced in-memory transaction reliability and performance.

Abstract

Atomic broadcasts play a central role in serialisable in-memory transactions. Best performing ones block, when a node crashes, until a new view is installed. We augment a new protocol for uninterrupted progress in the interim period.