monitoring: refresh grafana dashboards

services/monitoring/grafana-dashboard-public.yaml

@@ -25,17 +25,30 @@ data:
         ]
       },
       "editable": false,
-      "fiscalYearStartMonth": 0,
+      "folderUid": "atlas-public",
       "graphTooltip": 0,
-      "id": null,
       "links": [],
-      "liveNow": false,
       "panels": [
         {
+          "id": 1,
+          "type": "stat",
+          "title": "Running pods",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
+          "gridPos": {
+            "h": 6,
+            "w": 6,
+            "x": 0,
+            "y": 0
+          },
+          "targets": [
+            {
+              "expr": "sum(kube_pod_status_phase{phase=\"Running\"})",
+              "refId": "A"
+            }
+          ],
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -46,8 +59,12 @@ data:
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green",
+                    "color": "rgba(115, 115, 115, 1)",
                     "value": null
+                  },
+                  {
+                    "color": "green",
+                    "value": 1
                   }
                 ]
               },
@@ -55,59 +72,105 @@ data:
             },
             "overrides": []
           },
-          "gridPos": {
-            "h": 7,
-            "w": 6,
-            "x": 0,
-            "y": 0
-          },
-          "id": 1,
           "options": {
             "colorMode": "value",
             "graphMode": "area",
-            "justifyMode": "auto",
+            "justifyMode": "center",
-            "orientation": "auto",
             "reduceOptions": {
               "calcs": [
                 "lastNotNull"
               ],
               "fields": "",
               "values": false
-            },
-            "text": {},
-            "textMode": "auto"
-          },
-          "pluginVersion": "10.4.0",
-          "targets": [
-            {
-              "datasource": {
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "editorMode": "code",
-              "expr": "sum(kube_pod_status_phase{phase=\"Running\"})",
-              "legendFormat": "",
-              "range": true,
-              "refId": "A"
             }
-          ],
+          }
-          "title": "Running pods",
-          "type": "stat"
         },
         {
+          "id": 2,
+          "type": "stat",
+          "title": "Ready node percentage",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
-          "description": "Aggregated CPU usage across all schedulable nodes.",
+          "gridPos": {
+            "h": 6,
+            "w": 6,
+            "x": 6,
+            "y": 0
+          },
+          "targets": [
+            {
+              "expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"}) / sum(kube_node_info) * 100",
+              "refId": "A"
+            }
+          ],
           "fieldConfig": {
             "defaults": {
               "color": {
-                "mode": "continuous-BlYlRd"
+                "mode": "palette-classic"
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "percentage",
+                "steps": [
+                  {
+                    "color": "red",
+                    "value": null
+                  },
+                  {
+                    "color": "orange",
+                    "value": 90
+                  },
+                  {
+                    "color": "green",
+                    "value": 98
+                  }
+                ]
+              },
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "center",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
+        },
+        {
+          "id": 3,
+          "type": "stat",
+          "title": "Cluster CPU saturation",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 6,
+            "w": 6,
+            "x": 12,
+            "y": 0
+          },
+          "targets": [
+            {
+              "expr": "avg((1 - rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
               },
               "mappings": [],
-              "max": 100,
-              "min": 0,
               "thresholds": {
                 "mode": "percentage",
                 "steps": [
@@ -117,7 +180,7 @@ data:
                   },
                   {
                     "color": "yellow",
-                    "value": 60
+                    "value": 65
                   },
                   {
                     "color": "red",
@@ -129,79 +192,165 @@ data:
             },
             "overrides": []
           },
-          "gridPos": {
-            "h": 7,
-            "w": 6,
-            "x": 6,
-            "y": 0
-          },
-          "id": 2,
           "options": {
             "colorMode": "value",
             "graphMode": "area",
-            "justifyMode": "auto",
+            "justifyMode": "center",
-            "orientation": "auto",
             "reduceOptions": {
               "calcs": [
                 "lastNotNull"
               ],
               "fields": "",
               "values": false
-            },
-            "text": {},
-            "textMode": "auto"
-          },
-          "targets": [
-            {
-              "datasource": {
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "avg(100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100))",
-              "legendFormat": "",
-              "refId": "A"
             }
-          ],
+          }
-          "title": "Average node CPU",
-          "type": "stat"
         },
         {
+          "id": 4,
+          "type": "stat",
+          "title": "Cluster memory usage",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
           "gridPos": {
-            "h": 8,
+            "h": 6,
-            "w": 12,
+            "w": 6,
-            "x": 0,
+            "x": 18,
-            "y": 7
+            "y": 0
           },
-          "id": 3,
           "targets": [
             {
-              "datasource": {
+              "expr": "100 - (sum(node_memory_MemAvailable_bytes) / sum(node_memory_MemTotal_bytes) * 100)",
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "sum(kube_pod_status_phase{phase=\"Running\"}) by (namespace)",
-              "legendFormat": "{{namespace}}",
               "refId": "A"
             }
           ],
-          "title": "Running pods per namespace",
+          "fieldConfig": {
-          "type": "bargauge",
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "percentage",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "yellow",
+                    "value": 70
+                  },
+                  {
+                    "color": "red",
+                    "value": 85
+                  }
+                ]
+              },
+              "unit": "percent"
+            },
+            "overrides": []
+          },
           "options": {
-            "displayMode": "gradient",
+            "colorMode": "value",
-            "orientation": "horizontal",
+            "graphMode": "area",
+            "justifyMode": "center",
             "reduceOptions": {
-              "calcs": ["lastNotNull"],
+              "calcs": [
+                "lastNotNull"
+              ],
               "fields": "",
               "values": false
-            },
+            }
-            "showUnfilled": false
           }
         },
         {
+          "id": 5,
+          "type": "piechart",
+          "title": "Namespace CPU share",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 0,
+            "y": 6
+          },
+          "targets": [
+            {
+              "expr": "topk(8, sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace))",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "cores"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "list",
+              "placement": "right"
+            },
+            "pieType": "pie",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
+        },
+        {
+          "id": 6,
+          "type": "piechart",
+          "title": "Namespace memory share",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 12,
+            "y": 6
+          },
+          "targets": [
+            {
+              "expr": "topk(8, sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\",container!=\"\"}) by (namespace))",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "bytes"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "list",
+              "placement": "right"
+            },
+            "pieType": "donut",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
+        },
+        {
+          "id": 7,
+          "type": "timeseries",
+          "title": "Node CPU usage (per node)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -212,38 +361,70 @@ data:
             "x": 0,
             "y": 15
           },
-          "id": 4,
           "targets": [
             {
-              "datasource": {
+              "expr": "avg(rate(node_cpu_seconds_total{mode!=\"idle\"}[5m])) by (instance) * 100",
-                "type": "prometheus",
+              "refId": "A",
-                "uid": "atlas-vm"
+              "legendFormat": "{{instance}}"
-              },
-              "expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"})",
-              "legendFormat": "Ready",
-              "refId": "A"
-            },
-            {
-              "datasource": {
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"false\"})",
-              "legendFormat": "Not Ready",
-              "refId": "B"
             }
           ],
-          "title": "Node readiness",
+          "fieldConfig": {
-          "type": "piechart",
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
           "options": {
             "legend": {
               "displayMode": "table",
-              "placement": "right"
+              "placement": "bottom"
             },
-            "pieType": "donut"
+            "tooltip": {
+              "mode": "multi"
+            }
           }
         },
         {
+          "id": 8,
+          "type": "timeseries",
+          "title": "Node memory usage (per node)",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 15
+          },
+          "targets": [
+            {
+              "expr": "avg((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100) by (instance)",
+              "refId": "A",
+              "legendFormat": "{{instance}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 9,
+          "type": "table",
+          "title": "Key service availability",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -254,29 +435,39 @@ data:
             "x": 0,
             "y": 23
           },
-          "id": 5,
           "targets": [
             {
-              "datasource": {
+              "expr": "max by (service) (up{service=~\"traefik|gitea|vault|victoria-metrics-single|grafana|alertmanager\"})",
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "sum by (namespace) (increase(kube_pod_status_phase{phase=\"Failed\"}[1d]))",
-              "legendFormat": "{{namespace}}",
               "refId": "A"
             }
           ],
-          "title": "Failed pods (24h)",
-          "type": "table",
           "fieldConfig": {
             "defaults": {
-              "unit": "none",
+              "mappings": [
-              "mappings": [],
+                {
+                  "id": 0,
+                  "type": 1,
+                  "value": "0",
+                  "text": "Down"
+                },
+                {
+                  "id": 1,
+                  "type": 1,
+                  "value": "1",
+                  "text": "Up"
+                }
+              ],
               "thresholds": {
                 "mode": "absolute",
                 "steps": [
-                  {"color": "green", "value": null},
+                  {
-                  {"color": "red", "value": 1}
+                    "color": "red",
+                    "value": null
+                  },
+                  {
+                    "color": "green",
+                    "value": 1
+                  }
                 ]
               }
             },
@@ -285,6 +476,126 @@ data:
           "options": {
             "showHeader": true
           }
+        },
+        {
+          "id": 10,
+          "type": "table",
+          "title": "Failed pods (24h trend)",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 23
+          },
+          "targets": [
+            {
+              "expr": "topk(10, sum(increase(kube_pod_status_phase{phase=\"Failed\"}[24h])) by (namespace))",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "showHeader": true
+          }
+        },
+        {
+          "id": 11,
+          "type": "timeseries",
+          "title": "Cluster network throughput",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 31
+          },
+          "targets": [
+            {
+              "expr": "sum(rate(container_network_receive_bytes_total{namespace!=\"\"}[5m]))",
+              "refId": "A",
+              "legendFormat": "Receive"
+            },
+            {
+              "expr": "sum(rate(container_network_transmit_bytes_total{namespace!=\"\"}[5m]))",
+              "refId": "B",
+              "legendFormat": "Transmit"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "Bps"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 12,
+          "type": "timeseries",
+          "title": "Storage usage across nodes",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 31
+          },
+          "targets": [
+            {
+              "expr": "100 - (sum(node_filesystem_avail_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"}) / sum(node_filesystem_size_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"}) * 100)",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "list",
+              "placement": "bottom"
+            }
+          }
+        },
+        {
+          "id": 13,
+          "type": "text",
+          "title": "About this dashboard",
+          "gridPos": {
+            "h": 6,
+            "w": 24,
+            "x": 0,
+            "y": 39
+          },
+          "options": {
+            "content": "### Atlas at a glance\n- Raspberry Pi + Jetson hybrid cluster with Flux-managed GitOps\n- Metrics powered by VictoriaMetrics, visualized by Grafana\n- Login for SRE mode with pod-level drilldowns, alert routes, and storage health",
+            "mode": "markdown"
+          }
         }
       ],
       "refresh": "30s",
@@ -301,10 +612,8 @@ data:
         "from": "now-12h",
         "to": "now"
       },
-      "timepicker": {},
-      "timezone": "",
       "title": "Atlas Public Overview",
       "uid": "atlas-public",
-      "version": 1,
+      "version": 3
-      "weekStart": ""
     }
+

services/monitoring/grafana-dashboard-sre.yaml

@@ -20,29 +20,41 @@ data:
             "hide": true,
             "iconColor": "rgba(0, 211, 255, 1)",
             "name": "Annotations & Alerts",
-              "type": "dashboard"
+            "type": "dashboard"
           }
         ]
       },
       "editable": true,
-      "fiscalYearStartMonth": 0,
+      "folderUid": "atlas-sre",
       "graphTooltip": 0,
       "links": [],
       "panels": [
         {
+          "id": 1,
+          "type": "stat",
+          "title": "Ready nodes",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
-          "description": "Percentage of Ready nodes.",
+          "gridPos": {
+            "h": 5,
+            "w": 6,
+            "x": 0,
+            "y": 0
+          },
+          "targets": [
+            {
+              "expr": "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\"}) / sum(kube_node_info) * 100",
+              "refId": "A"
+            }
+          ],
           "fieldConfig": {
             "defaults": {
               "color": {
-                "mode": "continuous-RdYlGr"
+                "mode": "palette-classic"
               },
               "mappings": [],
-              "max": 100,
-              "min": 0,
               "thresholds": {
                 "mode": "percentage",
                 "steps": [
@@ -50,9 +62,13 @@ data:
                     "color": "red",
                     "value": null
                   },
+                  {
+                    "color": "yellow",
+                    "value": 95
+                  },
                   {
                     "color": "green",
-                    "value": 90
+                    "value": 99
                   }
                 ]
               },
@@ -60,18 +76,10 @@ data:
             },
             "overrides": []
           },
-          "gridPos": {
-            "h": 7,
-            "w": 6,
-            "x": 0,
-            "y": 0
-          },
-          "id": 10,
           "options": {
             "colorMode": "value",
-            "graphMode": "none",
+            "graphMode": "area",
             "justifyMode": "center",
-            "orientation": "auto",
             "reduceOptions": {
               "calcs": [
                 "lastNotNull"
@@ -79,92 +87,192 @@ data:
               "fields": "",
               "values": false
             }
-          },
+          }
-          "targets": [
-            {
-              "datasource": {
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "avg(kube_node_status_condition{condition=\"Ready\",status=\"true\"}) * 100",
-              "refId": "A"
-            }
-          ],
-          "title": "Ready nodes",
-          "type": "stat"
         },
         {
+          "id": 2,
+          "type": "stat",
+          "title": "Pending pods",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
           "gridPos": {
-            "h": 7,
+            "h": 5,
             "w": 6,
             "x": 6,
             "y": 0
           },
-          "id": 11,
-          "options": {
-            "legend": {
-              "displayMode": "table",
-              "placement": "bottom"
-            },
-            "tooltip": {
-              "mode": "multi"
-            }
-          },
           "targets": [
             {
-              "datasource": {
+              "expr": "sum(kube_pod_status_phase{phase=\"Pending\"})",
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "sum by (node)(node_filesystem_avail_bytes{mountpoint=\"/\"})",
-              "legendFormat": "{{node}}",
               "refId": "A"
             }
           ],
-          "title": "Free root filesystem bytes",
+          "fieldConfig": {
-          "type": "timeseries"
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "yellow",
+                    "value": 3
+                  },
+                  {
+                    "color": "red",
+                    "value": 10
+                  }
+                ]
+              },
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "center",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
         },
         {
+          "id": 3,
+          "type": "stat",
+          "title": "Unavailable deployment replicas",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
           },
           "gridPos": {
-            "h": 10,
+            "h": 5,
-            "w": 12,
+            "w": 6,
-            "x": 0,
+            "x": 12,
-            "y": 7
+            "y": 0
-          },
-          "id": 12,
-          "options": {
-            "legend": {
-              "calcs": [],
-              "displayMode": "list",
-              "placement": "bottom"
-            },
-            "tooltip": {
-              "mode": "single"
-            }
           },
           "targets": [
             {
-              "datasource": {
+              "expr": "sum(kube_deployment_status_replicas_unavailable)",
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"crypto\",container!=\"\"}[5m])) by (pod)",
-              "legendFormat": "{{pod}}",
               "refId": "A"
             }
           ],
-          "title": "Crypto namespace CPU usage",
+          "fieldConfig": {
-          "type": "timeseries"
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "yellow",
+                    "value": 1
+                  },
+                  {
+                    "color": "red",
+                    "value": 3
+                  }
+                ]
+              },
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "center",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
         },
         {
+          "id": 4,
+          "type": "stat",
+          "title": "Active alerts",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 5,
+            "w": 6,
+            "x": 18,
+            "y": 0
+          },
+          "targets": [
+            {
+              "expr": "sum(ALERTS{alertstate=\"firing\"})",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  },
+                  {
+                    "color": "yellow",
+                    "value": 1
+                  },
+                  {
+                    "color": "red",
+                    "value": 3
+                  }
+                ]
+              },
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "center",
+            "reduceOptions": {
+              "calcs": [
+                "lastNotNull"
+              ],
+              "fields": "",
+              "values": false
+            }
+          }
+        },
+        {
+          "id": 5,
+          "type": "timeseries",
+          "title": "Node CPU usage",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -173,9 +281,168 @@ data:
             "h": 9,
             "w": 12,
             "x": 0,
-            "y": 17
+            "y": 5
+          },
+          "targets": [
+            {
+              "expr": "avg(rate(node_cpu_seconds_total{mode!=\"idle\"}[5m])) by (instance) * 100",
+              "refId": "A",
+              "legendFormat": "{{instance}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 6,
+          "type": "timeseries",
+          "title": "Node memory usage",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 12,
+            "y": 5
+          },
+          "targets": [
+            {
+              "expr": "avg((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100) by (instance)",
+              "refId": "A",
+              "legendFormat": "{{instance}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 7,
+          "type": "timeseries",
+          "title": "Top pod CPU (5m avg)",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 0,
+            "y": 14
+          },
+          "targets": [
+            {
+              "expr": "topk(5, sum(rate(container_cpu_usage_seconds_total{pod!=\"\",container!=\"\"}[5m])) by (namespace,pod))",
+              "refId": "A",
+              "legendFormat": "{{namespace}}/{{pod}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "cores"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 8,
+          "type": "timeseries",
+          "title": "Top pod memory working set",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 12,
+            "y": 14
+          },
+          "targets": [
+            {
+              "expr": "topk(5, sum(container_memory_working_set_bytes{pod!=\"\",container!=\"\"}) by (namespace,pod))",
+              "refId": "A",
+              "legendFormat": "{{namespace}}/{{pod}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "bytes"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 9,
+          "type": "bargauge",
+          "title": "Namespace restart rate (6h)",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 23
+          },
+          "targets": [
+            {
+              "expr": "topk(8, sum(increase(kube_pod_container_status_restarts_total{namespace!=\"\"}[6h])) by (namespace))",
+              "refId": "A"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "none"
+            },
+            "overrides": []
           },
-          "id": 13,
           "options": {
             "displayMode": "gradient",
             "orientation": "horizontal",
@@ -185,22 +452,112 @@ data:
               ],
               "fields": "",
               "values": false
-            },
+            }
-            "showUnfilled": false
+          }
+        },
+        {
+          "id": 10,
+          "type": "table",
+          "title": "Deployments missing replicas",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 23
           },
           "targets": [
             {
-              "datasource": {
+              "expr": "topk(10, sum by (namespace,deployment) (kube_deployment_status_replicas_unavailable))",
-                "type": "prometheus",
-                "uid": "atlas-vm"
-              },
-              "expr": "count(sum(kube_pod_status_phase{phase=\"Failed\"}) by (namespace))",
-              "legendFormat": "",
               "refId": "A"
             }
           ],
-          "title": "Namespaces with failed pods",
+          "fieldConfig": {
-          "type": "bargauge"
+            "defaults": {
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "showHeader": true
+          }
+        },
+        {
+          "id": 11,
+          "type": "timeseries",
+          "title": "Pod phase breakdown",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 0,
+            "y": 31
+          },
+          "targets": [
+            {
+              "expr": "sum(kube_pod_status_phase) by (phase)",
+              "refId": "A",
+              "legendFormat": "{{phase}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "none"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
+        },
+        {
+          "id": 12,
+          "type": "timeseries",
+          "title": "PVC usage (top 8)",
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 9,
+            "w": 12,
+            "x": 12,
+            "y": 31
+          },
+          "targets": [
+            {
+              "expr": "topk(8, sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes / kubelet_volume_stats_capacity_bytes * 100))",
+              "refId": "A",
+              "legendFormat": "{{namespace}}/{{persistentvolumeclaim}}"
+            }
+          ],
+          "fieldConfig": {
+            "defaults": {
+              "unit": "percent"
+            },
+            "overrides": []
+          },
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "bottom"
+            },
+            "tooltip": {
+              "mode": "multi"
+            }
+          }
         }
       ],
       "schemaVersion": 39,
@@ -216,8 +573,8 @@ data:
         "from": "now-12h",
         "to": "now"
       },
-      "timepicker": {},
       "title": "Atlas SRE Overview",
       "uid": "atlas-sre",
-      "version": 1
+      "version": 2
     }
+

services/monitoring/grafana-folders.yaml

@@ -0,0 +1,28 @@
+# services/monitoring/grafana-folders.yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-folders
+  labels:
+    app.kubernetes.io/name: grafana
+    app.kubernetes.io/component: folders
+data:
+  folders.yaml: |
+    apiVersion: 1
+    folders:
+      - uid: atlas-public
+        title: Atlas Public
+        permissions:
+          - role: Viewer
+            permission: View
+          - role: Editor
+            permission: Edit
+          - role: Admin
+            permission: Admin
+      - uid: atlas-sre
+        title: Atlas SRE
+        permissions:
+          - role: Editor
+            permission: View
+          - role: Admin
+            permission: Admin

services/monitoring/helmrelease.yaml

@@ -297,6 +297,11 @@ spec:
     dashboardsConfigMaps:
       public: grafana-dashboard-public
       sre: grafana-dashboard-sre
+    extraConfigmapMounts:
+      - name: grafana-folders
+        mountPath: /etc/grafana/provisioning/folders
+        configMap: grafana-folders
+        readOnly: true
 
 ---
 

services/monitoring/kustomization.yaml

@@ -7,4 +7,5 @@ resources:
   - rbac.yaml
   - grafana-dashboard-public.yaml
   - grafana-dashboard-sre.yaml
+  - grafana-folders.yaml
   - helmrelease.yaml