Main Page

Download Tarball: criu-3.19.tar.gz Version: 3.19 "Bronze Peacock" Released: 27 Nov 2023 GIT tag: v3.19 Installation • Usage Releases

Welcome to CRIU, a project to implement checkpoint/restore functionality for Linux in userspace.

Checkpoint/Restore In Userspace, or CRIU (pronounced kree-oo, w:IPA: /krɪʊ/, Russian: криу), is a software tool for Linux operating system. Using this tool, you can freeze a running application (or part of it) and checkpoint it to a hard drive as a collection of files. You can then use the files to restore and run the application from the point it was frozen at. The distinctive feature of the CRIU project is that it is mainly implemented in user space.

http://static.openvz.org/criu_88x31.gif is a project of http://static.openvz.org/openvz_88x31.gif and is sponsored and supported by http://static.openvz.org/parallels_88x31.gif

Using

Installation

What to do to have CRIU on your system

Usage

How to run the tool

Usage scenarios

Ideas how crtools can be used (some are crazy indeed)

What software is supported

Describes TODO list in higher level terms

HOWTOs

Real examples of how to use CRIU. Some are complex, some are not.

What can change after C/R

CRIU cannot (yet) save and restore every single bit of tasks' state. This page describes what bits visible through standard kernel API are such.

Developing

If you're interested in CRIU development, please subscribe to the criu mailing list: http://lists.openvz.org/mailman/listinfo/criu

Images

Description of image files format

Commits

Mainline kernel commits tracker

Manpages

Kernel's manpages commits tracker

ZDTM Test Suite

Zero downtime test suite

TODO

Current TODO list

Postulates

What to keep in mind when writing new code

Code coverage results

Shows how zdtm run covers the crtools code paths

How to submit patches

Events Open Source Summit North America 2024 April 17, 2024, Seattle, Washington Investigating Checkpoint and Restore for GPU-Accelerated Containers NVIDIA GTC 2024 March 21, 2024, San Jose, CA Achieving K8S and Public Cloud Operational Efficiency using a New Checkpoint/Restart Feature for GPUs KubeCon EU 2024 March 22, 2024, Paris, France The Party Must Go on - Resume Pods After Spot Instance Shut Down Enabling Coordinated Checkpointing for Distributed HPC Applications FOSDEM 2024 February 3, 2024, Brussels, Belgium Zeroing and the semantic gap between host and guest Forensic container checkpointing and analysis

Under the hood

• Sockets
• Memory dumping and restoring
• Checkpoint/Restore
• TCP connection
• Porting crtools to new kernel releases
• Files
• Pending signals
• Stages of restoring
• COW
• Code blobs
• Comparison to other CR projects

External links

• 2024-04-22, Pronghorn: Effective Checkpoint Orchestration for Serverless Hot-Starts
• 2023-11-12, Checkpoint/Restart for CUDA Kernels
• 2023-10-23, Evicting for the greater good: The Case for Reactive Checkpointing in Serverless Computing
• 2023-04-20, A Dynamic Checkpoint Interval Decision Algorithm for Live Migration-Based Drone-Recovery System
• 2023-03-10, Forensic Container Analysis
• 2023-01-14, Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level
• 2022-12-05, Forensic container checkpointing in Kubernetes
• 2022-11-13, Out of hypervisor (OoH): efficient dirty page tracking in userspace using hardware virtualization feature
• 2022-08-07, iContainer: Consecutive Checkpointing with Rapid Resilience for Immortal Container-based Services

More external articles...

Other

• Project history
• Logo description
• Events
• Join the CRIU acronym fun