Merge branch 'unvariance:main' into main

.devcontainer.json

@@ -0,0 +1,18 @@
+{
+    "name": "Kernel Module Development",
+    "dockerFile": "Dockerfile.devcontainer",
+    "workspaceFolder": "/workspace",
+    "workspaceMount": "source=${localWorkspaceFolder},target=/workspace,type=bind,consistency=cached",
+    "customizations": {
+        "vscode": {
+            "extensions": [
+                "ms-vscode.cpptools",
+                "ms-vscode.makefile-tools",
+                "ms-azuretools.vscode-docker",
+                "ms-vscode.cmake-tools"
+            ]
+        }
+    },
+    "remoteUser": "root"
+}
+

.github/workflows/get-resctrl-and-perf-info.yaml

@@ -0,0 +1,123 @@
+name: Get Resctrl and Perf info
+on: workflow_dispatch  # Manual trigger for testing
+
+# Add permissions needed for OIDC authentication
+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 Server 24.04 LTS (HVM), SSD Volume Type
+          ec2-instance-type: m7i.metal-24xl
+          market-type: spot
+          subnet-id: ${{ secrets.AWS_SUBNET_ID }}
+          security-group-id: ${{ secrets.AWS_SECURITY_GROUP_ID }}
+          pre-runner-script: |
+            sudo yum update -y && \
+            sudo yum install docker git libicu -y
+            sudo systemctl enable docker
+          aws-resource-tags: >
+            [
+              {"Key": "Name", "Value": "github-runner"},
+              {"Key": "Repository", "Value": "${{ 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 }}"}
+            ]
+
+  do-job:
+    needs: start-runner
+    runs-on: ${{ needs.start-runner.outputs.label }}
+    steps:
+      - name: List perf counters
+        run: |
+          perf list
+      - name: List perf - detailed
+        run: |
+          perf list --long-desc --details || true
+      - name: Check perf paranoid
+        run: |
+          ls /proc/sys/kernel/perf_event_paranoid
+          cat /proc/sys/kernel/perf_event_paranoid
+      - name: Check RDT Capabilities
+        run: |
+          sudo mkdir -p /sys/fs/resctrl
+          sudo mount -t resctrl resctrl /sys/fs/resctrl || true
+          
+          echo "Mounting resctrl filesystem"
+          mount | grep resctrl || true
+          
+          echo "Checking RDT capabilities"
+          ls /sys/fs/resctrl/info || true
+          
+          echo "Monitoring features:"
+          cat /sys/fs/resctrl/info/L3_MON/mon_features || true
+          
+          echo "Number of available RMIDs:"
+          cat /sys/fs/resctrl/info/L3_MON/num_rmids || true
+
+          echo "Number of CAT classes:"
+          cat /sys/fs/resctrl/info/L3/num_closids || true
+          
+          echo "CPU RDT features:"
+          grep -E "cat_l3|cdp_l3|cqm_occup_llc|cqm_mbm_total|cqm_mbm_local" /proc/cpuinfo || true
+          
+          # we do not unmount, maybe mounting affects the intel_cqm checks below
+          #sudo umount /sys/fs/resctrl || true           
+      - name: Check intel_cqm
+        run: |
+          echo "*** Listing /sys/devices/intel_cqm"
+          ls -la /sys/devices/intel_cqm || true
+          echo "*** Traversing  /sys/devices/intel_cqm/events"
+          find /sys/devices/intel_cqm/events || true
+          echo "checking type"
+          cat /sys/devices/intel_cqm/type || true
+          echo "reading llc_occupancy"
+          cat /sys/devices/intel_cqm/events/llc_occupancy || true
+          cat /sys/devices/intel_cqm/events/llc_occupancy.scale || true
+      - name: Power off
+        run: |
+          shutdown --poweroff now
+
+  stop-runner:
+    name: Stop EC2 runner
+    needs: [start-runner, do-job]
+    runs-on: ubuntu-latest
+    if: always()  # Run even if previous jobs fail
+    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 }}

.github/workflows/test-kernel-module.yaml

@@ -0,0 +1,153 @@
+name: Test Kernel Module
+on: workflow_dispatch  # Manual trigger for testing
+
+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-0884d2865dbe9de4b  # Ubuntu 22.04 LTS in us-east-2
+          ec2-instance-type: t3.large
+          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-module:
+    needs: start-runner
+    runs-on: ${{ needs.start-runner.outputs.label }}
+    timeout-minutes: 10  # Add timeout in case system hangs
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Disable IPv6
+        run: |
+          # Disable IPv6 via sysctl
+          sudo sysctl -w net.ipv6.conf.all.disable_ipv6=1
+          sudo sysctl -w net.ipv6.conf.default.disable_ipv6=1
+          sudo sysctl -w net.ipv6.conf.lo.disable_ipv6=1
+
+          # Force apt to use IPv4
+          echo 'Acquire::ForceIPv4 "true";' | sudo tee /etc/apt/apt.conf.d/99force-ipv4
+
+      - name: Configure apt to use HTTPS
+        run: |
+          # Update all archive URLs to use HTTPS
+          sudo sed -i 's/http:/https:/g' /etc/apt/sources.list
+
+          # Install apt-transport-https (might fail initially, hence the || true)
+          sudo apt-get update || true
+          sudo apt-get install -y apt-transport-https ca-certificates
+
+          # Update again with HTTPS now configured
+          sudo apt-get update
+
+      - name: Install build dependencies
+        run: |
+          # Install base dependencies
+          sudo apt-get install -y build-essential linux-headers-$(uname -r)
+          
+      - 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/memory_collector.ko
+
+      - name: Load and test module
+        working-directory: module
+        run: |
+          # Load module
+          sudo insmod build/memory_collector.ko
+          
+          # Verify module is loaded
+          lsmod | grep memory_collector
+          
+          # Check kernel logs for module initialization
+          dmesg | grep "Memory Collector" || true
+          
+          # Unload module
+          sudo rmmod memory_collector
+          
+          # Verify module unloaded successfully
+          if lsmod | grep -q memory_collector; then
+            echo "Error: Module still loaded"
+            exit 1
+          fi
+          
+          # Check kernel logs for cleanup message
+          dmesg | grep "Memory Collector" || true
+
+  stop-runner:
+    name: Stop EC2 runner
+    needs: [start-runner, test-module]
+    runs-on: ubuntu-latest
+    if: always()  # Run even if previous jobs fail
+    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 }} 

Dockerfile.devcontainer

@@ -0,0 +1,21 @@
+FROM ubuntu:latest
+
+# Avoid prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Update and install essential build tools and kernel headers
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    linux-headers-6.8.0-52-generic \
+    linux-image-6.8.0-52-generic \
+    git \
+    vim \
+    curl \
+    kmod \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set the working directory
+WORKDIR /workspace
+
+# Keep container running
+CMD ["sleep", "infinity"]