Conquering a Billion Rows with Modern Java Concurrency | René Schwietzke (EN)

You might have seen my previous talk: "The First 80% of Reading One Billion Rows Fast Enough". It intentionally avoided concurrency to keep things simple. While we focused on single-thread performance before, this time we're going multi-core. This requires an entirely different approach to tuning, dissecting the problem, and implementing a sustainable solution. To keep things fair and cheap, we'll target 8 cores and see if the design can scale even further. Hardcore Java coding talks are rare nowadays. This is one of them. Expect plenty of code, flamecharts, perf-stats, and of course, a few necessary words about CPU internals, because you can't scale across cores without knowing what they're actually doing. Note: We're sticking to the JDK. No external libraries, and we won't go Unsafe, for reasons. This talk will take you on a journey. We'll start with an old-school, JDK 8-style first attempt, investigate what’s happening behind the scenes, and then evolve the code through parallel streams to modern virtual threads and preview features. ➜ Subscribe to JAVAPRO and never miss an update: https://bit.ly/YouTube-JAVAPRO-subscribe ▬ About us: ▬ JAVAPRO is the magazine for professional, real-world Java development. Beyond the publication, JAVAPRO organises the annual developer conference JCON, which focuses on Core Java, Enterprise Java, Microservices, AI, APIs, and frameworks. On this channel, you'll find interviews, sessions, tips & tricks, and everything a Java developer could ask for. ➜ Read JAVAPRO online or download the PDF: https://javapro.io ➜ Join the next live training session: https://javapro.io/training/ ▬ Follow us on social media: ▬ Twitter: https://x.com/JAVAPROmagazin LinkedIn: / 75505519 ➜ Thanks for watching – subscribe for more Java!