initial commit

skills/self-hosting/docker-gpu-acceleration/scripts/verify-cockpit-gpu.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+# Verify Cockpit NVIDIA GPU dashboard health
+# Returns non-zero exit code if anything is wrong.
+
+FAIL=0
+
+echo "=== Checking systemd service ==="
+if systemctl is-active --quiet nvidia-gpu-monitor; then
+    echo "  [PASS] nvidia-gpu-monitor service is running"
+else
+    echo "  [FAIL] nvidia-gpu-monitor service is NOT running"
+    FAIL=1
+fi
+
+echo ""
+echo "=== Checking data files ==="
+for f in /run/nvidia-gpu.txt /run/nvidia-processes.txt /run/nvidia-cuda.txt; do
+    if [ -f "$f" ]; then
+        CONTENT=$(head -1 "$f")
+        echo "  [PASS] $f: $CONTENT"
+    else
+        echo "  [FAIL] $f does not exist"
+        FAIL=1
+    fi
+done
+
+echo ""
+echo "=== Checking Cockpit package ==="
+MANIFEST="/usr/share/cockpit/nvidia-gpu/manifest.json"
+INDEX="/usr/share/cockpit/nvidia-gpu/index.html"
+if [ -f "$MANIFEST" ] && [ -f "$INDEX" ]; then
+    echo "  [PASS] Cockpit nvidia-gpu package installed"
+    echo "  Manifest: $(wc -c < "$MANIFEST") bytes"
+    echo "  Index:    $(wc -c < "$INDEX") bytes"
+else
+    echo "  [FAIL] Cockpit package files missing"
+    FAIL=1
+fi
+
+echo ""
+echo "=== Checking GPU accessibility ==="
+GPU_LINE=$(nvidia-smi --query-gpu=name --format=csv,noheader 2>/dev/null | head -1)
+if [ -n "$GPU_LINE" ]; then
+    echo "  [PASS] GPU detected: $GPU_LINE"
+else
+    echo "  [FAIL] nvidia-smi not working"
+    FAIL=1
+fi
+
+echo ""
+echo "=== Cockpit service ==="
+if systemctl is-active --quiet cockpit; then
+    echo "  [PASS] Cockpit running on port 9090"
+else
+    echo "  [FAIL] Cockpit is not running"
+    FAIL=1
+fi
+
+echo ""
+if [ "$FAIL" -eq 0 ]; then
+    echo "All checks passed. GPU dashboard should be functional."
+else
+    echo "Some checks FAILED. See above."
+fi
+exit $FAIL