Bug #21167
Updated by Peter Amstutz 7 months ago
It would be interesting to be able to checkpoint a Crunch container, then restore it later. A couple cases where this would be useful: * avoid losing progress when a spot instance is reclaimed by checkpoint periodically and/or when the "about to be reclaimed" notification happens (depends on how fast you can save the process) * Start a process on an medium sized instance type, and automatically checkpoint and restore to a larger/smaller instance with more/less RAM if the RAM usage goes above/below a threshold. https://memverge.com/ (commercial) https://criu.org/Main_Page (open source) "docker checkpoint" is an experimental feature that uses CRIU, https://docs.docker.com/engine/reference/commandline/checkpoint/ Looks like it's still classified as experimental (requires enabling "experimental" features in the docker config file) but is present in current docker releases. Some more information here: https://criu.org/Docker