Nowadays, several software systems rely on stream processing architectures to deliver scalable performance and handle large volumes of data in near real time. Stream processing frameworks facilitate scalable computing by distributing the application's execution across multiple machines. Despite performance being extensively studied, the measurement of fault tolerance-a key and most appealing feature offered by stream processing frameworks-has still not been measured properly with updated and comprehensive testbeds. Moreover, the impact that fault recovery can have on performance is mostly ignored. This paper provides a comprehensive analysis of fault recovery performance, stability, and recovery time in a cloud-native environment with modern open-source frameworks, namely Flink, Kafka Streams, and Spark Structured Streaming. Our benchmarking analysis is inspired by chaos engineering to inject failures. Generally, our results indicate that much has changed compared to previous studies on fault recovery in distributed stream processing. In particular, the results indicate that Flink can be the fastest and stablest under failures. Moreover, Kafka Streams shows performance instabilities after failures, which is due to its current repartitioning strategy that can be suboptimal in terms of load balancing. Spark Structured Streaming shows suitable fault recovery performance and stability, but with higher event latency. Our study intends to (i) help industry practitioners in choosing the most suitable stream processing framework for efficient and reliable executions of data-intensive applications; (ii) support researchers in applying and extending our research method as well as our benchmark; (iii) identify, prevent, and assist in solving potential issues in production deployments.

翻译：如今，多个软件系统依赖流处理架构来实现可扩展性能，并近实时处理海量数据。流处理框架通过将应用执行分布到多台机器上促进可扩展计算。尽管性能已被广泛研究，但容错性——流处理框架提供的关键且最具吸引力的特性——仍未通过更新且全面的测试平台得到恰当测量。此外，故障恢复对性能的影响大多被忽视。本文基于现代开源框架（即Flink、Kafka Streams和Spark Structured Streaming），在云原生环境中对故障恢复性能、稳定性及恢复时间进行了全面分析。我们的基准分析受混沌工程启发以注入故障。总体而言，结果表明与以往分布式流处理故障恢复研究相比，情况已发生显著变化。具体而言，结果显示Flink在故障下速度最快且最稳定。此外，Kafka Streams在故障后表现出性能不稳定性，这归因于其当前的分区策略在负载均衡方面可能并非最优。Spark Structured Streaming展现出合适的故障恢复性能与稳定性，但事件延迟较高。本研究旨在：(i) 帮助工业实践者选择最适合高效可靠执行数据密集型应用的流处理框架；(ii) 支持研究人员应用并拓展我们的研究方法及基准；(iii) 识别、预防并协助解决生产部署中的潜在问题。