Enhance documentation

.github/workflows/e2e.yaml

@@ -28,6 +28,11 @@ jobs:
   e2e-test:
     runs-on: linux-amd64-cpu4
     if: ${{ github.event.workflow_run.conclusion == 'success' }} && ${{ github.event.workflow_run.event == 'push' }}
+    strategy:
+      matrix:
+        label: [default, legacy, dra, kernel]
+    name: E2E Test (${{ matrix.label }})
+
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
@@ -42,9 +47,8 @@ jobs:
       run: |
         sudo apt-get update
         sudo apt-get install -y make
-        make ginkgo
 
-    - name: Run e2e tests
+    - name: Run e2e test for ${{ matrix.label }}
       env:
         AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
         AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
@@ -55,13 +59,12 @@ jobs:
         echo "${{ secrets.AWS_SSH_KEY }}" > "$e2e_ssh_key"
         chmod 600 "$e2e_ssh_key"
         export E2E_SSH_KEY="$e2e_ssh_key"
-
-        make -f tests/Makefile test
+        make -f tests/Makefile test GINKGO_ARGS="--label-filter='${{ matrix.label }}'"
 
     - name: Archive Ginkgo logs
       uses: actions/upload-artifact@v4
       with:
-        name: ginkgo-logs
+        name: ginkgo-logs-${{ matrix.label }}
         path: ginkgo.json
         retention-days: 15
 

.github/workflows/golang.yaml

@@ -75,7 +75,14 @@ jobs:
       with:
         go-version: ${{ needs.variables.outputs.GOLANG_VERSION }}
 
-    - run: make coverage
+    - name: Run unit tests and generate coverage report
+      run: make coverage
+
+    - name: Upload to Coveralls
+      uses: coverallsapp/github-action@v2
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        file: coverage.out
 
   build:
     name: Build

Makefile

@@ -86,8 +86,7 @@ test:
 	go test -coverprofile=$(COVERAGE_FILE) ./pkg/...
 
 coverage: test
-	cat $(COVERAGE_FILE) | grep -v "_mock.go" > $(COVERAGE_FILE).no-mocks
-	go tool cover -func=$(COVERAGE_FILE).no-mocks
+	go tool cover -func=$(COVERAGE_FILE)
 
 mdlint:
 	${CONTAINER_RUN_CMD} \

README.md

@@ -1,6 +1,6 @@
 # Holodeck
 
-> * Tech preview, under heavy development *
+[![Latest Release](https://img.shields.io/github/v/release/NVIDIA/holodeck?label=latest%20release)](https://github.com/NVIDIA/holodeck/releases/latest)
 
 A tool for creating and managing GPU-ready Cloud test environments.
 
@@ -13,6 +13,7 @@ A tool for creating and managing GPU-ready Cloud test environments.
 - [Commands Reference](docs/commands/)
 - [Contributing Guide](docs/contributing/)
 - [Examples](docs/examples/)
+- [Latest Release](https://github.com/NVIDIA/holodeck/releases/latest)
 
 ---
 
@@ -89,19 +90,11 @@ holodeck status <instance-id>
 holodeck dryrun -f ./examples/v1alpha1_environment.yaml
 ```
 
----
-
-## 📦 Supported Cuda-Drivers
-
-See [docs/prerequisites.md](docs/prerequisites.md#supported-cuda-drivers) for the full list and usage.
-
----
-
 ## 📂 More
 
 - [Examples](docs/examples/)
 - [Guides](docs/guides/)
 
 ---
 
-For more information, see the [docs/](docs/) directory.
+For more information, see the [documentation](docs/README.md) directory.

docs/README.md

@@ -0,0 +1,24 @@
+# Holodeck Documentation
+
+[![Latest Release](https://img.shields.io/github/v/release/NVIDIA/holodeck?label=latest%20release)](https://github.com/NVIDIA/holodeck/releases/latest)
+
+Welcome to the Holodeck documentation! Here you'll find everything you need to
+get started, use, and contribute to Holodeck.
+
+## 📚 Sections
+
+- [Quick Start](quick-start.md): Get up and running with Holodeck in minutes.
+- [Prerequisites](prerequisites.md): What you need before you begin.
+- [Commands Reference](commands/README.md): Detailed documentation for every
+    Holodeck CLI command.
+- [Contributing Guide](contributing/README.md): How to contribute to Holodeck,
+    including coding standards and PR process.
+- [Examples](examples/README.md): Example configuration files and usage scenarios.
+- [Guides](guides/README.md): In-depth guides and tutorials for advanced usage.
+- [Latest Release](https://github.com/NVIDIA/holodeck/releases/latest)
+
+---
+
+For general information, see the [main README](../README.md).
+
+If you have questions or want to contribute, check out the [Contributing Guide](contributing/README.md)!

docs/examples/README.md

@@ -67,4 +67,4 @@ A sample kind cluster configuration for use with the kind installer.
 ---
 
 For more details on configuration options, see the
-[Command Reference](../commands/) and [Quick Start Guide](../quick-start.md).
+[Command Reference](../commands/README.md) and [Quick Start Guide](../quick-start.md).

docs/guides/README.md

@@ -0,0 +1,10 @@
+# Guides
+
+This section is for in-depth guides and tutorials related to Holodeck.
+
+- If you are looking for step-by-step instructions or advanced usage, guides
+    will be listed here as they are added.
+- To contribute a guide, simply add a new Markdown file to this folder and
+    update this README with a link.
+
+*No guides are available yet. Stay tuned!*

docs/quick-start.md

@@ -71,5 +71,5 @@ holodeck delete <instance-id>
 
 - Check out the [Prerequisites](prerequisites.md) for detailed setup
    requirements
-- Explore the [Command Reference](commands/) for all available commands
+- Explore the [Command Reference](commands/README.md) for all available commands
 - See [Examples](../examples/) for more complex configurations

pkg/provisioner/templates/kubernetes.go

@@ -116,13 +116,13 @@ with_retry 10 20s kubectl --kubeconfig $KUBECONFIG wait --for=condition=establis
 # Apply custom resources with increased retry attempts
 with_retry 10 20s kubectl --kubeconfig $KUBECONFIG apply -f https://raw.githubusercontent.com/projectcalico/calico/${CALICO_VERSION}/manifests/custom-resources.yaml
 
-# Wait for cluster to be ready
-with_retry 10 20s kubectl --kubeconfig $KUBECONFIG wait --for=condition=ready --timeout=300s nodes --all
-
 # Make single-node cluster schedulable
 kubectl taint nodes --all node-role.kubernetes.io/control-plane:NoSchedule-
 kubectl label node --all node-role.kubernetes.io/worker=
 kubectl label node --all nvidia.com/holodeck.managed=true
+
+# Wait for cluster to be ready
+with_retry 10 30s kubectl --kubeconfig $KUBECONFIG wait --for=condition=ready --timeout=300s nodes --all
 `
 
 const KindTemplate = `