Apache Spark Streaming and HarmonicIO: A Performance and Architecture Comparison

Studies have demonstrated that Apache Spark, Flink and related frameworks can perform stream processing at very high frequencies, whilst tending to focus on small messages with a computationally light `map' stage for each message; a common enterprise use case. We add to these benchmarks by broadening the domain to include loads with larger messages (leading to network-bound throughput), and that are computationally intensive (leading to CPU-bound throughput) in the map phase; in order to evaluate applicability of these frameworks to scientific computing applications. We present a performance benchmark comparison between Apache Spark Streaming (ASS) under both file and TCP streaming modes; and HarmonicIO, comparing maximum throughput over a broad domain of message sizes and CPU loads. We find that relative performance varies considerably across this domain, with the chosen means of stream source integration having a big impact. We offer recommendations for choosing and configuring the frameworks, and present a benchmarking toolset developed for this study.