{
  "tags": [],
  "title": "Kubernetes Deployment metrics",
  "widgets": [
    {
      "layout": {
        "x": 0,
        "y": 0,
        "width": 12,
        "height": 3
      },
      "definition": {
        "type": "group",
        "title": "Total usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 4,
              "height": 2
            },
            "definition": {
              "type": "query_value",
              "title": "Deployment memory usage",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.memory.working_set{pod_name:$Deployment.value*}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:machine_memory_bytes{$Node}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / query2 * 100"
                    }
                  ],
                  "response_format": "scalar",
                  "conditional_formats": [
                    {
                      "value": 65,
                      "palette": "white_on_gray",
                      "comparator": ">="
                    },
                    {
                      "value": 90,
                      "palette": "white_on_gray",
                      "comparator": ">="
                    }
                  ]
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center",
              "custom_unit": "%"
            }
          },
          {
            "layout": {
              "x": 4,
              "y": 0,
              "width": 4,
              "height": 2
            },
            "definition": {
              "type": "query_value",
              "title": "Deployment CPU usage",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:machine_cpu_cores{$Node}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / 1000000000 / query2 * 100"
                    }
                  ],
                  "response_format": "scalar",
                  "conditional_formats": [
                    {
                      "value": 65,
                      "palette": "white_on_gray",
                      "comparator": ">="
                    },
                    {
                      "value": 90,
                      "palette": "white_on_gray",
                      "comparator": ">="
                    }
                  ]
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center",
              "custom_unit": "%"
            }
          },
          {
            "layout": {
              "x": 8,
              "y": 0,
              "width": 4,
              "height": 2
            },
            "definition": {
              "type": "query_value",
              "title": "Replicas",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes_state.deployment.replicas_available{$Deployment}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:kubernetes_state.deployment.replicas{$Deployment}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / query2 * 100"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center",
              "custom_unit": "%"
            }
          },
          {
            "layout": {
              "x": 0,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Used",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.memory.working_set{pod_name:$Deployment.value*}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center",
              "custom_unit": "B"
            }
          },
          {
            "layout": {
              "x": 2,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Total",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.memory.working_set{host:$Node.value*}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center",
              "custom_unit": "B"
            }
          },
          {
            "layout": {
              "x": 4,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Used",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / 1000000000"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center"
            }
          },
          {
            "layout": {
              "x": 6,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Total",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes_state.node.cpu_capacity{$Node}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center"
            }
          },
          {
            "layout": {
              "x": 8,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Available",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes_state.deployment.replicas_available{$Deployment}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center"
            }
          },
          {
            "layout": {
              "x": 10,
              "y": 2,
              "width": 2,
              "height": 1
            },
            "definition": {
              "type": "query_value",
              "title": "Total",
              "requests": [
                {
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes_state.deployment.replicas{$Deployment}",
                      "aggregator": "last",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "response_format": "scalar"
                }
              ],
              "autoscale": true,
              "precision": 2,
              "text_align": "center"
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 3,
        "width": 12,
        "height": 2
      },
      "definition": {
        "type": "group",
        "title": "Deployment CPU usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 2
            },
            "definition": {
              "type": "timeseries",
              "title": "Deployment CPU usage",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": false
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / 1000000000"
                    }
                  ],
                  "display_type": "line",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 5,
        "width": 12,
        "height": 2
      },
      "definition": {
        "type": "group",
        "title": "Containers CPU usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 2
            },
            "definition": {
              "type": "timeseries",
              "title": "Containers CPU usage",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": false
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*,!kube_container_name:pod} by {kube_container_name,pod_name}",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*} by {pod_name,image_name}",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query3",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / 1000000000"
                    },
                    {
                      "formula": "query2 / 1000000000"
                    },
                    {
                      "formula": "query3 / 1000000000"
                    }
                  ],
                  "display_type": "line",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 7,
        "width": 12,
        "height": 4
      },
      "definition": {
        "type": "group",
        "title": "All processes CPU usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 4
            },
            "definition": {
              "type": "timeseries",
              "title": "All processes CPU usage",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": false
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.cpu.usage.total{pod_name:$Deployment.value*} by {kube_container_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1 / 1000000000"
                    }
                  ],
                  "display_type": "line",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 11,
        "width": 12,
        "height": 2
      },
      "definition": {
        "type": "group",
        "title": "Deployment memory usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 2
            },
            "definition": {
              "type": "timeseries",
              "title": "Deployment memory usage",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": false
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.memory.working_set{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "display_type": "line",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 13,
        "width": 12,
        "height": 4
      },
      "definition": {
        "type": "group",
        "title": "All processes memory usage",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 4
            },
            "definition": {
              "type": "timeseries",
              "title": "All processes memory usage",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": false
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.memory.working_set{pod_name:$Deployment.value*} by {kube_container_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    }
                  ],
                  "display_type": "line",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 17,
        "width": 12,
        "height": 2
      },
      "definition": {
        "type": "group",
        "title": "Deployment network I/O",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 2
            },
            "definition": {
              "type": "timeseries",
              "title": "Deployment network I/O",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": true
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.network.rx_bytes{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:kubernetes.network.tx_bytes{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    },
                    {
                      "formula": "query2 * -1"
                    }
                  ],
                  "display_type": "area",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    },
    {
      "layout": {
        "x": 0,
        "y": 19,
        "width": 12,
        "height": 4
      },
      "definition": {
        "type": "group",
        "title": "All processes network I/O",
        "widgets": [
          {
            "layout": {
              "x": 0,
              "y": 0,
              "width": 12,
              "height": 4
            },
            "definition": {
              "type": "timeseries",
              "title": "All processes network I/O",
              "yaxis": {
                "max": "auto",
                "min": "auto",
                "label": "",
                "scale": "linear",
                "include_zero": true
              },
              "requests": [
                {
                  "style": {
                    "palette": "dog_classic",
                    "line_type": "solid",
                    "line_width": "normal"
                  },
                  "queries": [
                    {
                      "name": "query1",
                      "query": "sum:kubernetes.network.rx_bytes{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    },
                    {
                      "name": "query2",
                      "query": "sum:kubernetes.network.tx_bytes{pod_name:$Deployment.value*} by {pod_name}",
                      "data_source": "metrics"
                    }
                  ],
                  "formulas": [
                    {
                      "formula": "query1"
                    },
                    {
                      "formula": "query2 * -1"
                    }
                  ],
                  "display_type": "area",
                  "response_format": "timeseries"
                }
              ],
              "show_legend": true,
              "legend_layout": "auto",
              "legend_columns": [
                "avg",
                "min",
                "max",
                "value",
                "sum"
              ]
            }
          }
        ],
        "show_title": true,
        "layout_type": "ordered"
      }
    }
  ],
  "description": "Converted from Grafana dashboard https://grafana.com/grafana/dashboards/741 (by Ore Olarewaju). Monitors Kubernetes deployments in cluster using Prometheus. Shows overall cluster CPU / Memory of deployments, replicas in each deployment. Uses Kube state metrics and cAdvisor metrics ",
  "layout_type": "ordered",
  "reflow_type": "fixed",
  "template_variables": [
    {
      "name": "Deployment",
      "prefix": "kube_deployment",
      "default": "*",
      "available_values": []
    },
    {
      "name": "Node",
      "prefix": "host",
      "default": "*",
      "available_values": []
    }
  ]
}