CML-EC2-Runner #74
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CML-EC2-Runner | ||
| on: | ||
| workflow_dispatch: | ||
| jobs: | ||
| build-and-push-ecr-image: | ||
| name: Continuous Delivery | ||
| needs: integration | ||
|
Check failure on line 8 in .github/workflows/ec2-pipeline.yml
|
||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - name: Checkout Code | ||
| uses: actions/checkout@v3 | ||
| - name: Install Utilities | ||
| run: | | ||
| sudo apt-get update | ||
| sudo apt-get install -y jq unzip | ||
| - name: Configure AWS credentials | ||
| uses: aws-actions/configure-aws-credentials@v1 | ||
| with: | ||
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | ||
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
| aws-region: ${{ secrets.AWS_REGION }} | ||
| - name: Login to Amazon ECR | ||
| id: login-ecr | ||
| uses: aws-actions/amazon-ecr-login@v1 | ||
| - name: Build, tag, and push image to Amazon ECR | ||
| id: build-image | ||
| env: | ||
| ECR_REGISTRY: ${{ steps.login-ecr.outputs.registry }} | ||
| ECR_REPOSITORY: ${{ secrets.ECR_REPOSITORY_NAME }} | ||
| IMAGE_TAG: latest | ||
| run: | | ||
| # Build a docker container and | ||
| # push it to ECR so that it can | ||
| # be deployed to ECS. | ||
| docker build -t $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG . | ||
| docker push $ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG | ||
| echo "::set-output name=image::$ECR_REGISTRY/$ECR_REPOSITORY:$IMAGE_TAG" | ||
| launch-runner: | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - uses: actions/checkout@v3 | ||
| - uses: iterative/setup-cml@v2 | ||
| - name: Deploy runner on AWS EC2 | ||
| env: | ||
| REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }} | ||
| AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | ||
| AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
| run: | | ||
| cml runner launch \ | ||
| --cloud=aws \ | ||
| --name=session-08 \ | ||
| --cloud-region=ap-south-1 \ | ||
| --cloud-type=g4dn.xlarge \ | ||
| --cloud-hdd-size=64 \ | ||
| --cloud-spot \ | ||
| --single \ | ||
| --labels=cml-gpu \ | ||
| --idle-timeout=100 | ||
| train-and-report: | ||
| runs-on: [self-hosted, cml-gpu] | ||
| needs: launch-runner | ||
| timeout-minutes: 20 | ||
| # container: | ||
| # image: docker://pytorch/pytorch:2.4.0-cuda12.4-cudnn9-runtime | ||
| # options: --gpus all | ||
| # runs-on: ubuntu-latest | ||
| steps: | ||
| # - name: Set node environment | ||
| # run: | | ||
| # apt-get remove nodejs | ||
| # apt-get remove npm | ||
| # curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash | ||
| # chmod +x ~/.nvm/nvm.sh | ||
| # ls -a ~ | ||
| # nvm -v | ||
| # nvm install 20 | ||
| # node -v | ||
| # npm -v | ||
| # - uses: actions/setup-node@v4 | ||
| # with: | ||
| # node-version: 20 | ||
| # - run: npm ci | ||
| # - run: npm test | ||
| # - uses: actions/checkout@v2 | ||
| - name: Display CUDA Version | ||
| run: | | ||
| echo "CUDA Version:" | ||
| nvcc --version || true | ||
| - name: Display cuDNN Version | ||
| run: | | ||
| echo "cuDNN Version:" | ||
| cat /usr/local/cuda/include/cudnn_version.h | grep CUDNN_MAJOR -A 2 || true | ||
| - name: Verify EC2 Instance | ||
| run: | | ||
| echo "Checking instance information..." | ||
| # Check if we're on EC2 | ||
| TOKEN=$(curl -X PUT "http://169.254.169.254/latest/api/token" -H "X-aws-ec2-metadata-token-ttl-seconds: 21600") | ||
| curl -H "X-aws-ec2-metadata-token: $TOKEN" http://169.254.169.254/latest/meta-data/instance-type | ||
| echo "Checking system resources..." | ||
| lscpu | ||
| free -h | ||
| df -h | ||
| nvidia-smi # This will show GPU if available | ||
| echo "Checking environment..." | ||
| env | grep AWS || true | ||
| hostname | ||
| whoami | ||
| pwd | ||
| # Install the AWS CLI if not already available | ||
| if ! command -v aws &> /dev/null; then | ||
| apt-get update | ||
| apt-get install -y awscli | ||
| fi | ||
| # Get ECR login command and execute it | ||
| $(aws ecr get-login --no-include-email --region ap-south-1) | ||
| aws ecr get-login-password --region ap-south-1 | docker login --username AWS --password-stdin 306093656765.dkr.ecr.ap-south-1.amazonaws.com | ||
| - name: Set up AWS CLI credentials | ||
| env: | ||
| AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | ||
| AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
| AWS_DEFAULT_REGION: ap-south-1 # Change to your desired region | ||
| run: | | ||
| # Create the AWS config and credentials files | ||
| mkdir -p ~/.aws | ||
| echo "[default]" > ~/.aws/config | ||
| echo "region=${AWS_DEFAULT_REGION}" >> ~/.aws/config | ||
| echo "[default]" > ~/.aws/credentials | ||
| echo "aws_access_key_id=${AWS_ACCESS_KEY_ID}" >> ~/.aws/credentials | ||
| echo "aws_secret_access_key=${AWS_SECRET_ACCESS_KEY}" >> ~/.aws/credentials | ||
| - name: Test AWS CLI | ||
| run: | | ||
| # Now you can run any AWS CLI command | ||
| aws s3 ls # Example command to list S3 buckets | ||
| # - name: Authenticate with AWS ECR | ||
| # uses: aws-actions/configure-aws-credentials@v4 | ||
| # with: | ||
| # aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | ||
| # aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
| # aws-region: ${{ secrets.AWS_REGION }} | ||
| # - name: AWS ECR | ||
| # run: | | ||
| # aws configure aws_access_key_id=${{ secrets.AWS_ACCESS_KEY_ID }} aws_secret_access_key=${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
| # - name: Install Docker | ||
| # run: | | ||
| # curl -fsSL https://get.docker.com -o get-docker.sh | ||
| # sh get-docker.sh | ||
| # - name: Login to Amazon ECR | ||
| # id: login-ecr | ||
| # uses: aws-actions/amazon-ecr-login@v2 | ||
| # - name: CUDA Check | ||
| # run: | | ||
| # docker run --gpus all -it pytorch/pytorch:2.3.1-cuda11.8-cudnn8-runtime python3 -c " | ||
| # import torch; | ||
| # print(f'CUDA Available: {torch.cuda.is_available()}'); | ||
| # if torch.cuda.is_available(): | ||
| # print(f'Device: {torch.cuda.get_device_name(0)}')" | ||
| - name: Pull Docker image from ECR | ||
| run: | | ||
| docker pull ${{secrets.AWS_ECR_LOGIN_URI}}/${{ secrets.ECR_REPOSITORY_NAME }}:latest | ||
| ls -a | ||
| - name: Run DVC commands in container | ||
| run: | | ||
| mkdir -p model_storage | ||
| docker run --gpus=all \ | ||
| -v "$(pwd)/model_storage:/workspace/model_storage" \ | ||
| -e AWS_ACCESS_KEY_ID=${{ secrets.AWS_ACCESS_KEY_ID }} \ | ||
| -e AWS_SECRET_ACCESS_KEY=${{ secrets.AWS_SECRET_ACCESS_KEY }} \ | ||
| -e AWS_DEFAULT_REGION=${{ secrets.AWS_REGION }} \ | ||
| ${{ secrets.AWS_ECR_LOGIN_URI }}/${{ secrets.ECR_REPOSITORY_NAME }}:latest \ | ||
| /bin/bash -c " | ||
| dvc pull -r myremote && \ | ||
| mkdir -p model_storage && \ | ||
| dvc repro -f | ||
| " | ||
| # # Wait a moment to ensure the container has started | ||
| # sleep 5 | ||
| ls model_storage/ | ||
| # # Print logs from the container | ||
| # docker logs $CONTAINER_ID | ||
| # # Stop the container after retrieving logs | ||
| # docker stop $CONTAINER_ID | ||
| - name: List files in folder | ||
| run: | | ||
| ls -l ./ | ||
| - name: Install jq | ||
| run: | | ||
| sudo apt-get update | ||
| sudo apt-get install -y jq | ||
| - name: Get latest commit ID from the repository | ||
| id: get_commit_id | ||
| env: | ||
| REPO_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }} | ||
| run: | | ||
| repo="ajithvcoder/emlo4-session-08-ajithvcoder" | ||
| latest_commit=$(curl -s -H "Authorization: token $REPO_TOKEN" \ | ||
| "https://api.github.com/repos/$repo/commits?per_page=1" | \ | ||
| jq -r '.[0].sha') | ||
| echo "COMMIT_ID=$latest_commit" >> $GITHUB_ENV | ||
| - name: List files in folder | ||
| run: | | ||
| ls -l ./model_storage | ||
| - name: Read best checkpoint file name | ||
| id: read_checkpoint | ||
| run: | | ||
| checkpoint_file=$(head -n 1 ./model_storage/best_model_checkpoint.txt) | ||
| echo "CHECKPOINT_FILE=$checkpoint_file" >> $GITHUB_ENV | ||
| - name: Upload checkpoint to S3 | ||
| run: | | ||
| checkpoint_path="${{ env.CHECKPOINT_FILE }}" # Use the checkpoint path from the file | ||
| bucket_name="mybucket-emlo-mumbai/session-08-checkpoint/" # Change to your S3 bucket name | ||
| s3_key="session-08-checkpoint/${{ env.COMMIT_ID }}/$(basename "$checkpoint_path")" # Define S3 key | ||
| echo "Uploading $checkpoint_path to s3://$bucket_name/$s3_key" | ||
| aws s3 cp "$checkpoint_path" "s3://$bucket_name/$s3_key" | ||
| - name: Clean previous images and containers | ||
| run: | | ||
| docker system prune -f | ||
