From eb3991b6283bfb606f094778fec437f0daef6203 Mon Sep 17 00:00:00 2001
From: Brad Stein <Brad.Stein@gmail.com>
Date: Sat, 15 Nov 2025 11:59:48 -0300
Subject: [PATCH] dashboards: improve public view and fix color

---
 .../monitoring/grafana-dashboard-public.yaml  | 115 +++++++++++++++---
 .../monitoring/grafana-dashboard-sre.yaml     |   2 +-
 2 files changed, 100 insertions(+), 17 deletions(-)

diff --git a/services/monitoring/grafana-dashboard-public.yaml b/services/monitoring/grafana-dashboard-public.yaml
index db5d6c1..aee871f 100644
--- a/services/monitoring/grafana-dashboard-public.yaml
+++ b/services/monitoring/grafana-dashboard-public.yaml
@@ -177,31 +177,114 @@ data:
             "y": 7
           },
           "id": 3,
-          "options": {
-            "legend": {
-              "calcs": [],
-              "displayMode": "list",
-              "placement": "bottom",
-              "showLegend": true
-            },
-            "tooltip": {
-              "mode": "single",
-              "sort": "none"
-            }
-          },
           "targets": [
             {
               "datasource": {
                 "type": "prometheus",
                 "uid": "atlas-vm"
               },
-              "expr": "sum(rate(container_cpu_usage_seconds_total{namespace!=\"\", container!=\"\"}[5m])) by (namespace)",
+              "expr": "sum(kube_pod_status_phase{phase=\"Running\"}) by (namespace)",
               "legendFormat": "{{namespace}}",
               "refId": "A"
             }
           ],
-          "title": "Namespace CPU (5m avg)",
-          "type": "timeseries"
+          "title": "Running pods per namespace",
+          "type": "bargauge",
+          "options": {
+            "displayMode": "gradient",
+            "orientation": "horizontal",
+            "reduceOptions": {
+              "calcs": ["lastNotNull"],
+              "fields": "",
+              "values": false
+            },
+            "showUnfilled": false
+          }
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 15
+          },
+          "id": 4,
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "atlas-vm"
+              },
+              "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",
+          "type": "piechart",
+          "options": {
+            "legend": {
+              "displayMode": "table",
+              "placement": "right"
+            },
+            "pieType": "donut"
+          }
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "atlas-vm"
+          },
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 23
+          },
+          "id": 5,
+          "targets": [
+            {
+              "datasource": {
+                "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": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {"color": "green", "value": null},
+                  {"color": "red", "value": 1}
+                ]
+              }
+            },
+            "overrides": []
+          },
+          "options": {
+            "showHeader": true
+          }
         }
       ],
       "refresh": "30s",
@@ -215,7 +298,7 @@ data:
         "list": []
       },
       "time": {
-        "from": "now-6h",
+        "from": "now-12h",
         "to": "now"
       },
       "timepicker": {},
diff --git a/services/monitoring/grafana-dashboard-sre.yaml b/services/monitoring/grafana-dashboard-sre.yaml
index 12995af..d146275 100644
--- a/services/monitoring/grafana-dashboard-sre.yaml
+++ b/services/monitoring/grafana-dashboard-sre.yaml
@@ -38,7 +38,7 @@ data:
           "fieldConfig": {
             "defaults": {
               "color": {
-                "mode": "continuous"
+                "mode": "continuous-RdYlGr"
               },
               "mappings": [],
               "max": 100,