The Next Evolution of Java: ☕️ Achieving Hyper Performance and Efficiency in Cloud Native Workloads
summary
Compares concrete techniques: Quarkus + Jib for minimal images, GraalVM Native Image for tiny cold starts (example build ~25–30s with ~2–3GB peak build RAM producing a ~51MB native binary), CRaC for 200–300ms JVM resume, and CDS class-data-sharing to avoid repeated class parsing. Measured numbers: JVM startup ~300–340ms and ~130MB RSS, native startup ~33ms and ~10MB RSS, Kubernetes scale‑out hits ~100 replicas in under 10s. build time and peak RAM tradeoffs native reduces footprint and cold start
AI-written summary · about
chapters (15)
- 0:00Java's cloud evolution
- 1:06Java in Kubernetes challenges
- 3:56Enterprises rely on Java
- 9:36Performance goals in containers
- 12:05Java performance tools
- 18:22Quarkus vs Spring Boot
- 22:15Faster startup with CDS and CRaC
- 27:31Live demo setup
- 32:06JVM vs native benchmarks
- 39:23JVM vs GraalVM trade-offs
- 41:31Quarkus container deployment
- 44:25Scaling Java apps
- 46:11Java tuning tips
- 48:18Key takeaways
- 49:00Q&A on GraalVM
related talks
01h 00mKeynote: The Java Renaissance
40mHigh-Performance Java-Cloud-Native Apps & Microservices
44mJava In The Cloud with GraalVM
01h 00mAdapting Java for the Serverless world
42mJava in the Cloud with GraalVM
42mKeynote: Subatomic Java Microservices with Quarkus
48mSupersonic, Subatomic Java with Quarkus
17mAdopting Java for the Serverless world
