Demystifying Stream Processing with Apache Kafka
summary
Argues that Kafka plus an embedded library changes stream processing tradeoffs: Kafka Streams is a lightweight, embeddable API (processor API + DSL) that uses Kafka topics and consumer groups for parallelism, local state backed by RocksDB plus a Kafka changelog for fault recovery, and supports event-time windowing and reprocessing via offsets and log compaction. Claims this reduces Lambda architecture complexity, fits existing deployment tooling, and notes at scale LinkedIn processes ~1.2 trillion messages per day using the same log-based platform.
AI-written summary · about
chapters (19)
- 0:00Intro
- 7:36Myths about Stream Processing
- 9:47Summary of Stream Processing
- 11:51Stream Processing Challenges
- 17:52Lambda Architecture
- 22:32What is Kafka
- 24:38Partitioning messages
- 32:13Batch vs Stream processing
- 33:46Stream processing as a consumer
- 34:38Tapas Trains
- 35:24Library vs Framework
- 37:45Kafka Processor API
- 40:11Kafka Application
- 41:06Execution Model
- 43:17Load Balancing
- 44:17State Storage
- 45:40Map to Physical Processes
- 46:40Time
- 50:53Kafka Connect
related talks
45mApplications in the Emerging World of Stream Processing
50mApplication development and data in the emerging world ...
37mIntroducing Kafka Streams, new stream processing library ...
35mBuilding a Real-time Streaming Platform Using Kafka Streams...
33mKafka Microservices with Kafka plus Akka and Kafka Streams
03h 00mStream Processing, Going Beyond Pub/Sub with Kafka Streams and...
30mEvent Streaming and the Future of Applications
01h 29mEvent stream processing using Kafka Streams
