Skip to content
Docker Slurm

Add tcsh to containers #21

Sign in to view logs

Add tcsh to containers

Add tcsh to containers #21

Workflow file for this run

.github/workflows/docker.yml at 42b94b1
name: Docker Slurm
on:
push:
branches: [ main ]
pull_request:
branches: [ main ]
workflow_dispatch:
env:
REGISTRY_FRONTEND_IMAGE: ghcr.io/noaa-gsl/dockerspackstackslurmcluster/frontend
REGISTRY_MASTER_IMAGE: ghcr.io/noaa-gsl/dockerspackstackslurmcluster/master
REGISTRY_NODE_IMAGE: ghcr.io/noaa-gsl/dockerspackstackslurmcluster/node
AWS_REGION: us-east-2
jobs:
build-frontend-arm64:
runs-on: LinuxARM64-8core-32G-300Gb
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
# Beta ARM runners do not have Docker installed
name: Install Docker
run: |
# Uninstall incompatible packages
for pkg in docker.io containerd runc; do sudo apt-get remove $pkg; done
# Add Docker's official GPG key:
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc
# Add the repository to Apt sources:
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update -y
# Install docker packages
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
# Allow runner use to run docker without sudo
sudo usermod -aG docker $USER
sudo apt-get install acl
sudo setfacl --modify user:$USER:rw /var/run/docker.sock
-
name: Test Docker Installation
run: docker run hello-world
-
name: Install AWS CLI
run: sudo apt-get install -y --no-install-recommends awscli
-
name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: ${{ env.AWS_REGION }}
role-to-assume: arn:aws:iam::${{ secrets.AWS_ACCOUNT_ID }}:role/${{ secrets.AWS_GITHUB_ROLE }}
role-duration-seconds: 21600 # 6 hours
role-session-name: spackstackslurmcluster-github-actions
-
name: Test authentication
run: |
aws sts get-caller-identity
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_FRONTEND_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./frontend
file: ./frontend/Dockerfile
platforms: linux/arm64
labels: ${{ steps.meta.outputs.labels }}
secrets: |
"access_key_id=${{ env.AWS_ACCESS_KEY_ID }}"
"secret_access_key=${{ env.AWS_SECRET_ACCESS_KEY }}"
"session_token=${{ env.AWS_SESSION_TOKEN }}"
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/frontend-cache-arm64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/frontend-cache-arm64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_FRONTEND_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: frontend-digests-linux-arm64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
-
name: Debug session
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3
timeout-minutes: 60
with:
limit-access-to-actor: true
build-frontend-amd64:
runs-on: ubuntu2204-8c-32g-300ssd
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Install AWS CLI
run: sudo apt install -y awscli
-
name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: ${{ env.AWS_REGION }}
role-to-assume: arn:aws:iam::${{ secrets.AWS_ACCOUNT_ID }}:role/${{ secrets.AWS_GITHUB_ROLE }}
role-duration-seconds: 21600 # 6 hours
role-session-name: spackstackslurmcluster-github-actions
-
name: Test authentication
run: |
aws sts get-caller-identity
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_FRONTEND_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build spack-stack and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./frontend
file: ./frontend/Dockerfile
platforms: linux/amd64
secrets: |
"access_key_id=${{ env.AWS_ACCESS_KEY_ID }}"
"secret_access_key=${{ env.AWS_SECRET_ACCESS_KEY }}"
"session_token=${{ env.AWS_SESSION_TOKEN }}"
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/frontend-cache-amd64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/frontend-cache-amd64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_FRONTEND_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: frontend-digests-linux-amd64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
-
name: Debug session
if: ${{ failure() }}
uses: mxschmitt/action-tmate@v3
timeout-minutes: 60
with:
limit-access-to-actor: true
merge-frontend:
runs-on: ubuntu-latest
needs:
- build-frontend-amd64
- build-frontend-arm64
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Download digests
uses: actions/download-artifact@v4
with:
path: /tmp/digests
pattern: frontend-digests-*
merge-multiple: true
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_FRONTEND_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.REGISTRY_FRONTEND_IMAGE }}@sha256:%s ' *)
-
name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.REGISTRY_FRONTEND_IMAGE }}:${{ steps.meta.outputs.version }}
build-master-arm64:
runs-on: LinuxARM64-8core-32G-300Gb
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
# Beta ARM runners do not have Docker installed
name: Install Docker
run: |
# Uninstall incompatible packages
for pkg in docker.io containerd runc; do sudo apt-get remove $pkg; done
# Add Docker's official GPG key:
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc
# Add the repository to Apt sources:
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update -y
# Install docker packages
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
# Allow runner use to run docker without sudo
sudo usermod -aG docker $USER
sudo apt-get install acl
sudo setfacl --modify user:$USER:rw /var/run/docker.sock
-
name: Test Docker Installation
run: docker run hello-world
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_MASTER_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./master
file: ./master/Dockerfile
platforms: linux/arm64
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/master-cache-arm64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/master-cache-arm64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_MASTER_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: master-digests-linux-arm64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
build-master-amd64:
runs-on: ubuntu2204-8c-32g-300ssd
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_MASTER_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build spack-stack and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./master
file: ./master/Dockerfile
platforms: linux/amd64
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/master-cache-amd64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/master-cache-amd64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_MASTER_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: master-digests-linux-amd64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
merge-master:
runs-on: ubuntu-latest
needs:
- build-master-amd64
- build-master-arm64
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Download digests
uses: actions/download-artifact@v4
with:
path: /tmp/digests
pattern: master-digests-*
merge-multiple: true
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_MASTER_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.REGISTRY_MASTER_IMAGE }}@sha256:%s ' *)
-
name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.REGISTRY_MASTER_IMAGE }}:${{ steps.meta.outputs.version }}
build-node-arm64:
runs-on: LinuxARM64-8core-32G-300Gb
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
# Beta ARM runners do not have Docker installed
name: Install Docker
run: |
# Uninstall incompatible packages
for pkg in docker.io containerd runc; do sudo apt-get remove $pkg; done
# Add Docker's official GPG key:
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc
# Add the repository to Apt sources:
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update -y
# Install docker packages
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
# Allow runner use to run docker without sudo
sudo usermod -aG docker $USER
sudo apt-get install acl
sudo setfacl --modify user:$USER:rw /var/run/docker.sock
-
name: Test Docker Installation
run: docker run hello-world
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_NODE_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./node
file: ./node/Dockerfile
platforms: linux/arm64
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/node-cache-arm64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/node-cache-arm64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_NODE_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: node-digests-linux-arm64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
build-node-amd64:
runs-on: ubuntu2204-8c-32g-300ssd
#needs: docker_compose_test
timeout-minutes: 360
permissions:
packages: write
contents: read
id-token: write
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_NODE_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Prune pre-loaded GHA docker images
run: |
docker images
docker image prune -a -f
docker images
-
name: Build spack-stack and push by digest
id: build
uses: docker/build-push-action@v5
with:
context: ./node
file: ./node/Dockerfile
platforms: linux/amd64
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/node-cache-amd64:cache
cache-to: type=registry,ref=ghcr.io/noaa-gsl/dockerspackstackslurmcluster/node-cache-amd64:cache,mode=max
outputs: type=image,name=${{ env.REGISTRY_NODE_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
-
name: Upload digest
uses: actions/upload-artifact@v4
with:
name: node-digests-linux-amd64
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
merge-node:
runs-on: ubuntu-latest
needs:
- build-node-amd64
- build-node-arm64
steps:
-
name: Checkout repository
uses: actions/checkout@v4
-
name: Download digests
uses: actions/download-artifact@v4
with:
path: /tmp/digests
pattern: node-digests-*
merge-multiple: true
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY_NODE_IMAGE }}
tags: |
type=raw,value=latest
flavor: |
latest=true
prefix=
suffix=
-
name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
logout: false
-
name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.REGISTRY_NODE_IMAGE }}@sha256:%s ' *)
-
name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.REGISTRY_NODE_IMAGE }}:${{ steps.meta.outputs.version }}
docker-compose-test:
runs-on: ubuntu2204-8c-32g-300ssd
needs:
- merge-frontend
- merge-master
- merge-node
steps:
-
name: Checkout Repository
uses: actions/checkout@v4
-
name: Build and start containers
run: docker compose -f docker-compose-test.yml up --build -d
-
name: Check cluster logs
run: docker compose -f docker-compose-test.yml logs
-
name: Check status of the cluster containers
run: docker compose -f docker-compose-test.yml ps
-
name: Check status of Slurm
run: docker exec spack-stack-frontend sinfo
-
name: Run a Slurm job
run: docker exec spack-stack-frontend srun hostname
-
name: Test ssh access to Slurm compute nodes
run: |
docker exec spack-stack-frontend timeout 1s ssh slurmnode1 hostname
docker exec spack-stack-frontend timeout 1s ssh slurmnode2 hostname
docker exec spack-stack-frontend timeout 1s ssh slurmnode3 hostname
-
name: Load spack-stack envs
run: |
docker exec spack-stack-frontend bash -l -c "module use /opt/spack-stack/envs/unified-env/install/modulefiles/Core ; module load stack-gcc stack-openmpi stack-python jedi-mpas-env; module list"
docker exec spack-stack-frontend bash -l -c "module use /opt/spack-stack/envs/unified-env/install/modulefiles/Core ; module load stack-gcc stack-openmpi stack-python jedi-fv3-env; module list"
-
name: Compile and run MPI program
run: |
docker exec spack-stack-frontend bash -l -c "cd test; ./test_hello.sh"
-
name: Shut down Slurm cluster containers
run: docker compose -f docker-compose-test.yml down