In modern data architectures, stream processing engines such as Apache Flink are used to ingest continuous streams of data into data lakes such as Apache Iceberg. Streaming ingestion to Iceberg tables can suffer from two problems: the small files problem that can hurt read performance, and poor data clustering that can make file pruning less effective.
In this session, we will discuss how data teams can address those problems by adding a shuffling stage to the Flink Iceberg streaming writer to intelligently group data via bin packaging or range partition, reduce the number of concurrent files that every task writes, and improve data clustering. We will explain the motivations in detail and dive into the design of the shuffling stage. We will also share the evaluation results that demonstrate the effectiveness of smart shuffling.