Checkpoint/restore runc

Prerequisites

1. Create an account with Cedana, to get access to the GPU plugin. See authentication.

2. Set the Cedana URL & authentication token in the configuration.

3. Install the runc plugin with sudo cedana plugin install runc.

4. Ensure the daemon is running, see installation.

5. Do a health check to ensure the plugin is ready, see health checks.

Basic

1. Run a new runc container, for example:

sudo runc run --detach <container_id> --bundle ./my-bundle

1. Checkpoint:

cedana dump runc <container_id> --dir <dump-dir>

1. Restore:

cedana restore runc --bundle ./my-bundle --path <path-to-dump>

Managed

1. Run a new managed runc container:

cedana run runc --attach --jid <job_id> --bundle ./my-bundle

1. Checkpoint:

cedana dump job <job_id>

1. Restore:

cedana restore job --attach <job_id>

GPU support

Just like for processes, as explained in checkpoint/restore with GPUs, GPU support is also available for managed runc containers.

1. Run a new managed runc container with GPU support:

cedana run runc --attach --gpu-enabled --jid <job_id> --bundle ./my-bundle

1. Checkpoint:

cedana dump job <job_id>

1. Restore:

cedana restore job --attach <job_id>

For all available CLI options, see CLI reference. Directly interacting with daemon is also possible through gRPC, see API reference.