593
edits
Changes
Jump to navigation
Jump to search
mLine 1:
Line 1: − + + − + + + + + + + + + + + + +
no edit summary
This page explains how CRIU handles GPU-accelerated workloads, what vendor components are needed (NVIDIA & AMD), and how to use them for processes and containers.
This page explains how CRIU handles GPU-accelerated workloads, what vendor components are needed (NVIDIA & AMD), and how to use them for processes and containers. For more information, see the
NVIDIA's [https://developer.nvidia.com/blog/checkpointing-cuda-applications-with-criu/ Checkpointing CUDA Applications with CRIU] blog post and the [https://arxiv.org/abs/2502.16631 CRIUgpu paper].
CRIU checkpoints Linux-kernel resources (e.g., memory, threads, files, sockets). GPU state such as device memory, contexts, and queues that lives outside normal process address space needs special handling, so CRIU relies on vendor-specific [[plugins]].
== How CRIU integrates with GPU checkpointing mechanisms? ==
CRIU checkpoints Linux-kernel resources (e.g., memory, threads, files, sockets). GPU state such as device memory, contexts, and queues that lives outside normal process address space needs special handling, so CRIU relies on vendor-specific [[plugins]].
=== CUDA Plugin ===
The checkpointing functionality for CUDA applications is enabled through the [http://github.com/NVIDIA/cuda-checkpoint cuda-checkpoint] utility. This utility allows to transparently checkpoint and restore the CUDA state of a running Linux process. The CUDA plugin integrates this external utility with CRIU to safely pause, checkpoint, and restore processes and containers that use NVIDIA GPUs. It detects whether <code>cuda-checkpoint</code> is available and whether the system has an NVIDIA GPU; if not, the plugin disables itself.
=== AMDGPU Plugin ===
== Usage Examples ==
== Limitations ==