diff --git a/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh b/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh index 5dd53420dfdf..610243145621 100755 --- a/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh +++ b/.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh @@ -2,14 +2,45 @@ set -xu + +remove_docker_container() { + docker rm -f tpu-test || true; + docker rm -f vllm-tpu || true; +} + +trap remove_docker_container EXIT + +# Remove the container that might not be cleaned up in the previous run. +remove_docker_container + # Build the docker image. docker build -f docker/Dockerfile.tpu -t vllm-tpu . # Set up cleanup. -remove_docker_container() { docker rm -f tpu-test || true; } -trap remove_docker_container EXIT -# Remove the container that might not be cleaned up in the previous run. -remove_docker_container +cleanup_docker() { + # Get Docker's root directory + docker_root=$(docker info -f '{{.DockerRootDir}}') + if [ -z "$docker_root" ]; then + echo "Failed to determine Docker root directory." + exit 1 + fi + echo "Docker root directory: $docker_root" + # Check disk usage of the filesystem where Docker's root directory is located + disk_usage=$(df "$docker_root" | tail -1 | awk '{print $5}' | sed 's/%//') + # Define the threshold + threshold=70 + if [ "$disk_usage" -gt "$threshold" ]; then + echo "Disk usage is above $threshold%. Cleaning up Docker images and volumes..." + # Remove dangling images (those that are not tagged and not used by any container) + docker image prune -f + # Remove unused volumes / force the system prune for old images as well. + docker volume prune -f && docker system prune --force --filter "until=72h" --all + echo "Docker images and volumes cleanup completed." + else + echo "Disk usage is below $threshold%. No cleanup needed." + fi +} +cleanup_docker # For HF_TOKEN. source /etc/environment