litmus-hub/monitoring/dashboards/litmus-portal/node_metrics.json

{
  "dashboardID": "generic_node_metrics",
  "name": "Node metrics",
  "information": "This dashboard visualizes Node level CPU, memory, disk and IO utilization metrics interleaved with chaos events.",
  "chaosEventQueryTemplate": "litmuschaos_awaited_experiments{job=\"chaos-exporter\", chaos_injection_time!=\"\"}",
  "chaosVerdictQueryTemplate": "litmuschaos_experiment_verdict{job=\"chaos-exporter\", chaosresult_verdict!=\"Awaited\"}",
  "panelGroupMap": [
    {
      "groupName": "CPU Utilization Metrics",
      "panels": ["Chaos-Node-CPU Utilization"]
    },
    {
      "groupName": "Memory Utilization Metrics",
      "panels": ["Chaos-Node-Memory Utilization"]
    },
    {
      "groupName": "Disk Usage Metrics",
      "panels": [
        "Chaos-Node-Disk I/O Usage R/W",
        "Chaos-Node-Disk I/O Usage Times"
      ]
    },
    {
      "groupName": "Network Usage Metrics",
      "panels": [
        "Chaos-Node-Network Traffic Bits",
        "Chaos-Node-Network Traffic Packets"
      ]
    }
  ],
  "panelGroups": [
    {
      "panel_group_name": "CPU Utilization Metrics",
      "panels": [
        {
          "panel_name": "Chaos-Node-CPU Utilization",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "Cores",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "%",
          "prom_queries": [
            {
              "prom_query_name": "instance:node_cpu_utilisation:rate1m*100",
              "legend": "{{instance}}",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        }
      ]
    },
    {
      "panel_group_name": "Memory Utilization Metrics",
      "panels": [
        {
          "panel_name": "Chaos-Node-Memory Utilization",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "Memory",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "%",
          "prom_queries": [
            {
              "prom_query_name": "instance:node_memory_utilisation:ratio*100",
              "legend": "{{instance}}",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        }
      ]
    },
    {
      "panel_group_name": "Disk Usage Metrics",
      "panels": [
        {
          "panel_name": "Chaos-Node-Disk I/O Usage R/W",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "bytes read (-) / write (+)",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "KiB",
          "prom_queries": [
            {
              "prom_query_name": "node_disk_read_bytes_total",
              "legend": "{{instance}} - {{device}} - Successfully read bytes",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            },
            {
              "prom_query_name": "node_disk_written_bytes_total",
              "legend": "{{instance}} - {{device}} - Successfully written bytes",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        },
        {
          "panel_name": "Chaos-Node-Disk I/O Usage Times",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "time",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "ms",
          "prom_queries": [
            {
              "prom_query_name": "node_disk_io_time_seconds_total",
              "legend": "{{instance}} - {{device}} - Time spent doing I/Os",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        }
      ]
    },
    {
      "panel_group_name": "Network Usage Metrics",
      "panels": [
        {
          "panel_name": "Chaos-Node-Network Traffic Bits",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "bits out (-) / in (+)",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "b/s",
          "prom_queries": [
            {
              "prom_query_name": "node_network_receive_bytes_total*8",
              "legend": "{{instance}} - {{device}} - Receive",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            },
            {
              "prom_query_name": "node_network_transmit_bytes_total*8",
              "legend": "{{instance}} - {{device}} - Transmit",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        },
        {
          "panel_name": "Chaos-Node-Network Traffic Packets",
          "panel_options": {
            "points": false,
            "grids": true,
            "left_axis": true
          },
          "y_axis_left": "packets out (-) / in (+)",
          "y_axis_right": "CHAOS",
          "x_axis_down": "Time",
          "unit": "p/s",
          "prom_queries": [
            {
              "prom_query_name": "node_network_receive_packets_total",
              "legend": "{{instance}} - {{device}} - Receive",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            },
            {
              "prom_query_name": "node_network_transmit_packets_total",
              "legend": "{{instance}} - {{device}} - Transmit",
              "resolution": "1/2",
              "minstep": "5",
              "line": true,
              "close_area": false
            }
          ]
        }
      ]
    }
  ]
}