Benchmarking Apache Kafka Latency at the 99th Percentile ft. Anna Povzner

Apache Kafka® Committer Matthias J. Sax explains fault tolerance, high-availability stream processing, and Kafka Streams. He explains the differences between changelogging and checkpointing, as well as making changes in Kafka versus hot standbys, explaining what qualifies nodes as a hot standby, why Kafka Streams doesn’t do watermarking, and finally, why Kafka Streams is a library and not infrastructure.

Inventory management systems are crucial for reducing real-time inventory data drift, improving customer experience, and minimizing out-of-stock events. Kafka provides seamless inventory tracking at scale, saving billions of dollars in the supply chain, making modernized data architectures more important to retailers now more than ever. In this episode, we’ll discuss how Kafka enables stateful event streaming on a cloud-native platform for application and architecture modernization, leveraging Spring Boot, Kafka Streams, and Apache Cassandra.

Learn about the five different parts to a business value framework: (1) baseline, (2) target state, (3) quantified benefits, (4) unquantified benefits, and (5) proof points; cost effectiveness with Confluent Cloud; how to measure ROI vs. TCO; and a retail example from a customer that details their implementation of an event streaming platform.