Decoding Java snapshots with CRaC
summary
Introduces CRaC (Coordinated Restore at Checkpoint) for creating and restoring Java application snapshots to speed startup and reduce warm-up. Describes how to integrate CRaC with the JVM and applications, the benefits for latency-sensitive services, and practical considerations for checkpointing and restoring state.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 3:55Fast startup importance
- 9:52CRIU process snapshotting
- 15:14CRaC for JVM
- 18:45Demo: simple Java app
- 23:39Docker setup and checkpointing
- 27:36Demo: Spring Boot CRaC
- 30:23Breaking and fixing CRaC
- 37:04Unmanaged resources handling
- 41:20Security and memory concerns
- 43:06Scheduling and CRaC quirks
- 44:55Summary and trade-offs
- 46:22Q&A
related talks
53mWhat the CRaC Superfast JVM startup
51mJava on CRaC Superfast JVM Application Startup
53mJava on CRaC: Superfast JVM Application Startup
59mOpenJDK Project CRaC (Coordinated Restore at Checkpoint): Challenges and Issues
45mOptimizing Java Startup and Warmup: Exploring the Power of CRaC on Embedded
46mCRAC vs GraalVM
51mExploring the Power of CRaC on Embedded
01h 13mCoordinated Restore at Checkpoint: Quick Start for OpenJDK
