Merge branch 'unvariance:main' into feature/unvariance#9-resctrl_supp…

…ort_checker

.devcontainer.json

@@ -9,7 +9,8 @@
                 "ms-vscode.cpptools",
                 "ms-vscode.makefile-tools",
                 "ms-azuretools.vscode-docker",
-                "ms-vscode.cmake-tools"
+                "ms-vscode.cmake-tools",
+                "golang.go"
             ]
         }
     },

.github/workflows/ci-cpi-count.yaml

@@ -44,7 +44,7 @@ jobs:
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.docker-metadata.outputs.tags }}
           labels: ${{ steps.docker-metadata.outputs.labels }}
-          context: cmd/cpi-count
+          context: .
           file: cmd/cpi-count/Dockerfile
           platforms: linux/amd64,linux/arm64
           cache-from: type=registry,ref=ghcr.io/${{ github.repository }}/cpi-count:cache # Need to add the repository name

.github/workflows/ci-collector.yaml → .github/workflows/ci-prometheus-metrics.yaml

@@ -1,13 +1,13 @@
-name: CI Collector Workflow
-run-name: Building Collector by @${{ github.actor }}
+name: CI Prometheus Metrics Workflow
+run-name: Building Prometheus Metrics by @${{ github.actor }}
 
 on:
   workflow_dispatch:
   push:
     branches:
       - main
     paths:
-      - 'cmd/collector/**'
+      - 'cmd/prometheus_metrics/**'
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -33,7 +33,7 @@ jobs:
         id: docker-metadata
         uses: docker/metadata-action@v5
         with:
-          images: ghcr.io/${{ github.repository }}/collector
+          images: ghcr.io/${{ github.repository }}/prometheus-metrics
           tags: |
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}.{{patch}}
@@ -44,9 +44,8 @@ jobs:
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.docker-metadata.outputs.tags }}
           labels: ${{ steps.docker-metadata.outputs.labels }}
-          context: cmd/collector
-          file: cmd/collector/Dockerfile
+          context: .
+          file: cmd/prometheus_metrics/Dockerfile
           platforms: linux/amd64,linux/arm64
-          cache-from: type=registry,ref=ghcr.io/${{ github.repository }}/collector:cache
-          cache-to: type=registry,image-manifest=true,oci-mediatypes=true,ref=ghcr.io/${{ github.repository }}/collector:cache,mode=max
-
+          cache-from: type=registry,ref=ghcr.io/${{ github.repository }}/prometheus-metrics:cache
+          cache-to: type=registry,image-manifest=true,oci-mediatypes=true,ref=ghcr.io/${{ github.repository }}/prometheus-metrics:cache,mode=max 

.github/workflows/prometheus-metrics-test.yml

@@ -0,0 +1,27 @@
+name: Prometheus Metrics Integration Test
+
+on:
+  push:
+    branches: [ "main" ]
+    paths:
+      - cmd/prometheus_metrics/**
+  pull_request:
+    branches: [ "main" ]
+    paths:
+      - cmd/prometheus_metrics/**
+
+jobs:
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Go
+      uses: actions/setup-go@v4
+      with:
+        go-version: '1.22.9'
+
+    - name: Test
+      working-directory: ./cmd/prometheus_metrics/
+      run: go test -v 

.github/workflows/test-ebpf-collector.yaml

@@ -0,0 +1,200 @@
+name: Test eBPF Collector
+on: 
+  workflow_dispatch:  # Manual trigger for testing
+    inputs:
+      instance-type:
+        description: 'EC2 instance type to use'
+        required: false
+        default: 'c5.9xlarge'
+        type: string
+  push:
+    branches:
+      - main
+    paths:
+      - cmd/collector/**
+      - .github/workflows/test-ebpf-collector.yaml
+
+permissions:
+  id-token: write # Required for requesting the JWT
+
+jobs:
+  start-runner:
+    name: Start EC2 runner
+    runs-on: ubuntu-latest
+    outputs:
+      label: ${{ steps.start-ec2-runner.outputs.label }}
+      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
+    steps:
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
+          aws-region: ${{ secrets.AWS_REGION }}
+          role-session-name: github-runner-session
+
+      - name: Start EC2 runner
+        id: start-ec2-runner
+        uses: machulav/[email protected]
+        with:
+          mode: start
+          github-token: ${{ secrets.REPO_ADMIN_TOKEN }}
+          ec2-image-id: ami-0cb91c7de36eed2cb  # Ubuntu 24.04 LTS in us-east-2
+          ec2-instance-type: ${{ inputs.instance-type || 'm5zn.6xlarge' }} # or c5.9xlarge
+          market-type: spot
+          subnet-id: ${{ secrets.AWS_SUBNET_ID }}
+          security-group-id: ${{ secrets.AWS_SECURITY_GROUP_ID }}
+          aws-resource-tags: >
+            [
+              {"Key": "Name", "Value": "github-runner"},
+              {"Key": "Repository", "Value": "${{ github.repository }}"},
+              {"Key": "Workflow", "Value": "${{ github.workflow }}"},
+              {"Key": "RunId", "Value": "${{ github.run_id }}"},
+              {"Key": "RunNumber", "Value": "${{ github.run_number }}"},
+              {"Key": "SHA", "Value": "${{ github.sha }}"},
+              {"Key": "Branch", "Value": "${{ github.ref_name }}"},
+              {"Key": "Actor", "Value": "${{ github.actor }}"}
+            ]
+
+  test-ebpf:
+    needs: start-runner
+    runs-on: ${{ needs.start-runner.outputs.label }}
+    timeout-minutes: 10
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Disable IPv6
+        run: |
+          # Disable IPv6 via sysctl
+          sudo sysctl -w net.ipv6.conf.all.disable_ipv6=1
+          sudo sysctl -w net.ipv6.conf.default.disable_ipv6=1
+          sudo sysctl -w net.ipv6.conf.lo.disable_ipv6=1
+
+          # Force apt to use IPv4
+          echo 'Acquire::ForceIPv4 "true";' | sudo tee /etc/apt/apt.conf.d/99force-ipv4
+
+      - name: Install dependencies
+        run: |
+          # Update all archive URLs to use HTTPS in both old and new locations
+          sudo find /etc/apt/sources.list /etc/apt/sources.list.d/ -type f -exec sed -i 's/http:/https:/g' {} +
+          sudo apt-get update
+          sudo apt-get install -y build-essential linux-headers-$(uname -r) \
+            golang-go llvm clang libbpf-dev git vim curl kmod unzip
+
+      - name: Install pqrs
+        run: |
+          # Download latest pqrs release
+          curl -L -o pqrs.zip https://github.com/manojkarthick/pqrs/releases/download/v0.3.2/pqrs-0.3.2-x86_64-unknown-linux-gnu.zip
+          unzip pqrs.zip
+          sudo mv pqrs-0.3.2-x86_64-unknown-linux-gnu/bin/pqrs /usr/local/bin/
+          rm pqrs.zip
+
+      - name: Build kernel module
+        working-directory: module
+        run: |
+          # Try to compile and capture the warning message
+          make 2>&1 | tee compile_output.txt || true
+          
+          # Extract gcc version from the warning message
+          KERNEL_GCC_VERSION=$(grep "The kernel was built by:" compile_output.txt | grep -oP 'gcc-\K\d+' || echo "")
+          echo "Detected kernel compiler version: ${KERNEL_GCC_VERSION}"
+          
+          # Install specific gcc version if detected
+          if [ ! -z "$KERNEL_GCC_VERSION" ]; then
+            echo "Installing gcc-${KERNEL_GCC_VERSION}"
+            sudo apt-get install -y gcc-${KERNEL_GCC_VERSION}
+            
+            # Configure as default gcc
+            sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-${KERNEL_GCC_VERSION} 100
+            sudo update-alternatives --set gcc /usr/bin/gcc-${KERNEL_GCC_VERSION}
+          else
+            echo "Warning: Could not detect kernel compiler version"
+          fi
+          
+          # Verify gcc version
+          gcc --version
+          
+          # Now try the actual build
+          make
+
+          ls -l build/collector.ko
+
+      - name: Build collector
+        working-directory: cmd/collector
+        run: |
+          export HOME=/tmp
+          echo "HOME: $HOME"
+          export GOCACHE=$HOME/golang/pkg/mod
+          echo "GOCACHE: $GOCACHE"
+
+          mkdir -p $GOCACHE
+          go env -w GOMODCACHE=$GOCACHE
+
+          # Set up asm link for go2bpf
+          arch=$(uname -m) && \
+              case ${arch} in \
+                  aarch64) ln -sf /usr/include/aarch64-linux-gnu/asm /usr/include/asm ;; \
+                  x86_64)  ln -sf /usr/include/x86_64-linux-gnu/asm /usr/include/asm ;; \
+                  *)       echo "Unsupported architecture: ${arch}" && exit 1 ;; \
+              esac
+          go generate
+          go build -v
+          ls -l collector
+
+      - name: Load kernel module
+        working-directory: module
+        run: |
+          sudo insmod build/collector.ko
+          lsmod | grep collector
+
+      - name: Run eBPF collector
+        working-directory: cmd/collector
+        run: |
+          sudo ./collector
+
+      - name: Upload parquet file
+        uses: actions/upload-artifact@v4
+        with:
+          name: metrics-parquet
+          path: cmd/collector/metrics.parquet
+          if-no-files-found: error
+
+      - name: Verify parquet output
+        working-directory: cmd/collector
+        run: |
+          # Print parquet file contents as CSV
+          echo "Parquet file contents:"
+          pqrs cat --csv metrics.parquet
+          
+          # Verify file exists and has content
+          if [ ! -s metrics.parquet ]; then
+            echo "Error: metrics.parquet is empty or does not exist"
+            exit 1
+          fi
+
+      - name: Unload kernel module
+        working-directory: module
+        run: |
+          sudo rmmod collector
+          ! lsmod | grep collector
+
+  stop-runner:
+    name: Stop EC2 runner
+    needs: [start-runner, test-ebpf]
+    runs-on: ubuntu-latest
+    if: always()
+    steps:
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
+          aws-region: ${{ secrets.AWS_REGION }}
+          role-session-name: github-runner-session
+
+      - name: Stop EC2 runner
+        uses: machulav/[email protected]
+        with:
+          mode: stop
+          github-token: ${{ secrets.REPO_ADMIN_TOKEN }}
+          label: ${{ needs.start-runner.outputs.label }}
+          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}