Files
stack/infra/grafana/dashboards/gpu-notebooks.json
2026-05-01 11:39:12 -04:00

18 lines
1.5 KiB
JSON

{
"title": "GPU & Notebooks",
"uid": "gpu-notebooks",
"tags": ["homelab", "stack"],
"timezone": "browser",
"schemaVersion": 39,
"time": {"from": "now-6h", "to": "now"},
"refresh": "30s",
"panels": [
{"id": 1, "title": "GPU utilization %", "type": "timeseries", "gridPos": {"x": 0, "y": 0, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "DCGM_FI_DEV_GPU_UTIL"}]},
{"id": 2, "title": "GPU memory used (MiB)", "type": "timeseries", "gridPos": {"x": 12, "y": 0, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "DCGM_FI_DEV_FB_USED"}]},
{"id": 3, "title": "GPU temp (°C)", "type": "timeseries", "gridPos": {"x": 0, "y": 8, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "DCGM_FI_DEV_GPU_TEMP"}]},
{"id": 4, "title": "GPU power (W)", "type": "timeseries", "gridPos": {"x": 12, "y": 8, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "DCGM_FI_DEV_POWER_USAGE"}]},
{"id": 5, "title": "Notebooks/Zotero CPU %", "type": "timeseries", "gridPos": {"x": 0, "y": 16, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "rate(container_cpu_usage_seconds_total{name=~\"notebooks|zotero\"}[1m]) * 100", "legendFormat": "{{name}}"}]},
{"id": 6, "title": "Notebooks/Zotero memory", "type": "timeseries", "gridPos": {"x": 12, "y": 16, "w": 12, "h": 8}, "datasource": {"uid": "prometheus"}, "targets": [{"expr": "container_memory_working_set_bytes{name=~\"notebooks|zotero\"} / 1024 / 1024", "legendFormat": "{{name}}"}]}
]
}