scripts/dashboards_render_atlas.py

@@ -419,17 +419,16 @@ ARIADNE_SCHEDULE_LAST_ERROR_RANGE_HOURS = (
     "(time() - max_over_time(ariadne_schedule_last_error_timestamp_seconds[$__range])) / 3600"
 )
 ARIADNE_ACCESS_REQUESTS = "ariadne_access_requests_total"
-TEST_REPO_SELECTOR = 'repo=~"ariadne|metis"'
+ARIADNE_CI_COVERAGE = 'ariadne_ci_coverage_percent{repo="ariadne"}'
-TEST_CI_COVERAGE = f'ariadne_ci_coverage_percent{{{TEST_REPO_SELECTOR}}}'
+ARIADNE_CI_TESTS = 'ariadne_ci_tests_total{repo="ariadne"}'
-TEST_CI_TESTS = f'ariadne_ci_tests_total{{{TEST_REPO_SELECTOR}}}'
+ARIADNE_TEST_SUCCESS_RATE = (
-TEST_SUCCESS_RATE = (
     "100 * "
-    f'sum(max_over_time(ariadne_ci_tests_total{{{TEST_REPO_SELECTOR},result="passed"}}[30d])) '
+    'sum(max_over_time(ariadne_ci_tests_total{repo="ariadne",result="passed"}[30d])) '
     "/ clamp_min("
-    f'sum(max_over_time(ariadne_ci_tests_total{{{TEST_REPO_SELECTOR},result=~"passed|failed|error"}}[30d])), 1)'
+    'sum(max_over_time(ariadne_ci_tests_total{repo="ariadne",result=~"passed|failed|error"}[30d])), 1)'
 )
-TEST_FAILURES_24H = (
+ARIADNE_TEST_FAILURES_24H = (
-    f'sum by (result) (max_over_time(ariadne_ci_tests_total{{{TEST_REPO_SELECTOR},result=~"failed|error"}}[24h]))'
+    'sum by (result) (max_over_time(ariadne_ci_tests_total{repo="ariadne",result=~"failed|error"}[24h]))'
 )
 POSTGRES_CONN_USED = (
     'label_replace(sum(pg_stat_activity_count), "conn", "used", "__name__", ".*") '
@@ -1291,53 +1290,48 @@ def build_overview():
             },
         }
     )
-    test_success = timeseries_panel(
+    panels.append(
-        42,
+        timeseries_panel(
-        "Platform Test Success Rate",
+            42,
-        TEST_SUCCESS_RATE,
+            "Ariadne Test Success Rate",
-        {"h": 6, "w": 6, "x": 12, "y": 14},
+            ARIADNE_TEST_SUCCESS_RATE,
-        unit="percent",
+            {"h": 6, "w": 6, "x": 12, "y": 14},
-        max_value=100,
+            unit="percent",
-        legend=None,
+            max_value=100,
-        legend_display="list",
+            legend=None,
+            legend_display="list",
+        )
     )
-    test_success["description"] = (
+    panels.append(
-        "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. "
+        bargauge_panel(
-        "Add new test series there first so they roll up here."
+            43,
-    )
+            "Tests with Failures (24h)",
-    panels.append(test_success)
+            ARIADNE_TEST_FAILURES_24H,
-    test_failures = bargauge_panel(
+            {"h": 6, "w": 6, "x": 18, "y": 14},
-        43,
+            unit="none",
-        "Platform Tests with Failures (24h)",
+            instant=True,
-        TEST_FAILURES_24H,
+            legend="{{result}}",
-        {"h": 6, "w": 6, "x": 18, "y": 14},
+            overrides=[
-        unit="none",
+                {
-        instant=True,
+                    "matcher": {"id": "byName", "options": "error"},
-        legend="{{result}}",
+                    "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "yellow"}}],
-        overrides=[
+                },
-            {
+                {
-                "matcher": {"id": "byName", "options": "error"},
+                    "matcher": {"id": "byName", "options": "failed"},
-                "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "yellow"}}],
+                    "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "red"}}],
-            },
+                },
-            {
-                "matcher": {"id": "byName", "options": "failed"},
-                "properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "red"}}],
-            },
-        ],
-        thresholds={
-            "mode": "absolute",
-            "steps": [
-                {"color": "green", "value": None},
-                {"color": "yellow", "value": 1},
-                {"color": "orange", "value": 5},
-                {"color": "red", "value": 10},
             ],
-        },
+            thresholds={
+                "mode": "absolute",
+                "steps": [
+                    {"color": "green", "value": None},
+                    {"color": "yellow", "value": 1},
+                    {"color": "orange", "value": 5},
+                    {"color": "red", "value": 10},
+                ],
+            },
+        )
     )
-    test_failures["description"] = (
-        "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
-    )
-    panels.append(test_failures)
 
     cpu_scope = "$namespace_scope_cpu"
     gpu_scope = "$namespace_scope_gpu"
@@ -2655,31 +2649,29 @@ def build_jobs_dashboard():
             legend="{{status}}",
         )
     )
-    coverage_panel = stat_panel(
+    panels.append(
-        17,
+        stat_panel(
-        "Platform CI Coverage (%)",
+            17,
-        TEST_CI_COVERAGE,
+            "Ariadne CI Coverage (%)",
-        {"h": 6, "w": 4, "x": 8, "y": 11},
+            ARIADNE_CI_COVERAGE,
-        unit="percent",
+            {"h": 6, "w": 4, "x": 8, "y": 11},
-        decimals=1,
+            unit="percent",
-        instant=True,
+            decimals=1,
-        legend="{{branch}}",
+            instant=True,
+            legend="{{branch}}",
+        )
     )
-    coverage_panel["description"] = "Internal source panel for Atlas Overview automation test rollups."
+    panels.append(
-    panels.append(coverage_panel)
+        table_panel(
-    tests_panel = table_panel(
+            18,
-        18,
+            "Ariadne CI Tests (latest)",
-        "Platform CI Tests (latest)",
+            ARIADNE_CI_TESTS,
-        TEST_CI_TESTS,
+            {"h": 6, "w": 12, "x": 12, "y": 11},
-        {"h": 6, "w": 12, "x": 12, "y": 11},
+            unit="none",
-        unit="none",
+            transformations=[{"id": "labelsToFields", "options": {}}, {"id": "sortBy", "options": {"fields": ["Value"], "order": "desc"}}],
-        transformations=[{"id": "labelsToFields", "options": {}}, {"id": "sortBy", "options": {"fields": ["Value"], "order": "desc"}}],
+            instant=True,
-        instant=True,
+        )
     )
-    tests_panel["description"] = (
-        "Atlas Overview test panels depend on these internal repo-tagged CI series."
-    )
-    panels.append(tests_panel)
 
     return {
         "uid": "atlas-jobs",

services/harbor/helmrelease.yaml

@@ -422,7 +422,8 @@ spec:
                           - $patch: replace
                           - name: VAULT_ENV_FILE
                             value: /vault/secrets/harbor-jobservice-env.sh
-                        envFrom: []
+                        envFrom:
+                          - $patch: replace
                           - configMapRef:
                               name: harbor-jobservice-env
                         volumeMounts:

services/maintenance/ariadne-deployment.yaml

@@ -339,12 +339,6 @@ spec:
               value: "1099511627776"
             - name: OPENSEARCH_INDEX_PATTERNS
               value: kube-*,journald-*,trace-analytics-*
-            - name: METIS_BASE_URL
-              value: http://metis.maintenance.svc.cluster.local
-            - name: METIS_TIMEOUT_SEC
-              value: "15"
-            - name: ARIADNE_SCHEDULE_METIS_SENTINEL_WATCH
-              value: "*/30 * * * *"
             - name: METRICS_PATH
               value: "/metrics"
           resources:

services/maintenance/image.yaml

@@ -21,72 +21,3 @@ spec:
   policy:
     semver:
       range: ">=0.1.0-0"
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImageRepository
-metadata:
-  name: metis
-  namespace: maintenance
-spec:
-  image: registry.bstein.dev/bstein/metis
-  interval: 1m0s
-  secretRef:
-    name: harbor-regcred
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImagePolicy
-metadata:
-  name: metis
-  namespace: maintenance
-spec:
-  imageRepositoryRef:
-    name: metis
-  policy:
-    semver:
-      range: ">=0.1.0-0"
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImageRepository
-metadata:
-  name: metis-sentinel
-  namespace: maintenance
-spec:
-  image: registry.bstein.dev/bstein/metis-sentinel
-  interval: 1m0s
-  secretRef:
-    name: harbor-regcred
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImagePolicy
-metadata:
-  name: metis-sentinel
-  namespace: maintenance
-spec:
-  imageRepositoryRef:
-    name: metis-sentinel
-  policy:
-    semver:
-      range: ">=0.1.0-0"
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImageRepository
-metadata:
-  name: soteria
-  namespace: maintenance
-spec:
-  image: registry.bstein.dev/bstein/soteria
-  interval: 1m0s
-  secretRef:
-    name: harbor-regcred
----
-apiVersion: image.toolkit.fluxcd.io/v1beta2
-kind: ImagePolicy
-metadata:
-  name: soteria
-  namespace: maintenance
-spec:
-  imageRepositoryRef:
-    name: soteria
-  policy:
-    semver:
-      range: ">=0.1.0-0"

services/maintenance/kustomization.yaml

@@ -5,43 +5,28 @@ resources:
   - namespace.yaml
   - image.yaml
   - secretproviderclass.yaml
-  - metis-configmap.yaml
-  - metis-data-pvc.yaml
   - vault-serviceaccount.yaml
   - vault-sync-deployment.yaml
   - ariadne-serviceaccount.yaml
   - ariadne-rbac.yaml
   - disable-k3s-traefik-serviceaccount.yaml
   - k3s-traefik-cleanup-rbac.yaml
-  - metis-serviceaccount.yaml
-  - metis-rbac.yaml
-  - metis-token-sync-serviceaccount.yaml
-  - metis-token-sync-rbac.yaml
   - node-nofile-serviceaccount.yaml
   - pod-cleaner-rbac.yaml
   - ariadne-deployment.yaml
-  - metis-deployment.yaml
   - oneoffs/ariadne-migrate-job.yaml
   - ariadne-service.yaml
   - disable-k3s-traefik-daemonset.yaml
   - oneoffs/k3s-traefik-cleanup-job.yaml
   - node-nofile-daemonset.yaml
-  - metis-sentinel-daemonset.yaml
-  - metis-k3s-token-sync-cronjob.yaml
   - k3s-agent-restart-daemonset.yaml
   - pod-cleaner-cronjob.yaml
   - node-image-sweeper-serviceaccount.yaml
   - node-image-sweeper-daemonset.yaml
   - image-sweeper-cronjob.yaml
-  - metis-service.yaml
-  - metis-ingress.yaml
 images:
   - name: registry.bstein.dev/bstein/ariadne
     newTag: 0.1.0-22 # {"$imagepolicy": "maintenance:ariadne:tag"}
-  - name: registry.bstein.dev/bstein/metis
-    newTag: 0.1.0-0 # {"$imagepolicy": "maintenance:metis:tag"}
-  - name: registry.bstein.dev/bstein/metis-sentinel
-    newTag: 0.1.0-0 # {"$imagepolicy": "maintenance:metis-sentinel:tag"}
 configMapGenerator:
   - name: disable-k3s-traefik-script
     namespace: maintenance

services/maintenance/metis-configmap.yaml

@@ -1,20 +0,0 @@
-# services/maintenance/metis-configmap.yaml
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: metis
-  namespace: maintenance
-data:
-  METIS_BIND_ADDR: :8080
-  METIS_INVENTORY_PATH: /app/inventory.titan-rpi4.yaml
-  METIS_DATA_DIR: /var/lib/metis
-  METIS_DEFAULT_FLASH_HOST: titan-22
-  METIS_FLASH_HOSTS: titan-22
-  METIS_LOCAL_HOST: titan-22
-  METIS_ALLOWED_GROUPS: admin,maintainer
-  METIS_MAX_DEVICE_BYTES: "300000000000"
-  METIS_SENTINEL_PUSH_URL: http://metis.maintenance.svc.cluster.local/internal/sentinel/snapshot
-  METIS_SENTINEL_INTERVAL_SEC: "1800"
-  METIS_SENTINEL_NSENTER: "1"
-  METIS_IMAGE_RPI4_ARMBIAN_LONGHORN: https://armbian.chi.auroradev.org/dl/rpi4b/archive/Armbian_26.2.1_Rpi4b_noble_current_6.18.9_minimal.img.xz
-  METIS_IMAGE_RPI4_ARMBIAN_LONGHORN_SHA256: sha256:c450687adf4cc6a59725c43aefd58baf42ec71bdd379227d403cdde281768e46

services/maintenance/metis-data-pvc.yaml

@@ -1,13 +0,0 @@
-# services/maintenance/metis-data-pvc.yaml
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: metis-data
-  namespace: maintenance
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 40Gi
-  storageClassName: local-path

services/maintenance/metis-deployment.yaml

@@ -1,47 +0,0 @@
-# services/maintenance/metis-deployment.yaml
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: metis
-  namespace: maintenance
-spec:
-  replicas: 1
-  revisionHistoryLimit: 3
-  selector:
-    matchLabels:
-      app: metis
-  template:
-    metadata:
-      labels:
-        app: metis
-      annotations:
-        prometheus.io/scrape: "true"
-        prometheus.io/port: "8080"
-        prometheus.io/path: "/metrics"
-    spec:
-      serviceAccountName: metis
-      nodeSelector:
-        kubernetes.io/hostname: titan-22
-        kubernetes.io/arch: amd64
-        node-role.kubernetes.io/worker: "true"
-      containers:
-        - name: metis
-          image: registry.bstein.dev/bstein/metis:latest
-          imagePullPolicy: Always
-          envFrom:
-            - configMapRef:
-                name: metis
-          ports:
-            - name: http
-              containerPort: 8080
-          resources:
-            requests:
-              cpu: 100m
-              memory: 128Mi
-            limits:
-              cpu: 500m
-              memory: 512Mi
-          securityContext:
-            allowPrivilegeEscalation: false
-            capabilities:
-              drop: ["ALL"]

services/maintenance/metis-ingress.yaml

@@ -1,27 +0,0 @@
-# services/maintenance/metis-ingress.yaml
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: metis
-  namespace: maintenance
-  annotations:
-    kubernetes.io/ingress.class: traefik
-    cert-manager.io/cluster-issuer: letsencrypt
-    traefik.ingress.kubernetes.io/router.entrypoints: websecure
-    traefik.ingress.kubernetes.io/router.tls: "true"
-    traefik.ingress.kubernetes.io/router.middlewares: sso-oauth2-proxy-forward-auth@kubernetescrd
-spec:
-  tls:
-    - hosts: ["metis.bstein.dev"]
-      secretName: metis-tls
-  rules:
-    - host: metis.bstein.dev
-      http:
-        paths:
-          - path: /
-            pathType: Prefix
-            backend:
-              service:
-                name: metis
-                port:
-                  number: 80

services/maintenance/metis-k3s-token-sync-cronjob.yaml

@@ -1,51 +0,0 @@
-# services/maintenance/metis-k3s-token-sync-cronjob.yaml
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: metis-k3s-token-sync
-  namespace: maintenance
-spec:
-  schedule: "11 */6 * * *"
-  concurrencyPolicy: Forbid
-  successfulJobsHistoryLimit: 1
-  failedJobsHistoryLimit: 2
-  jobTemplate:
-    spec:
-      template:
-        spec:
-          serviceAccountName: metis-token-sync
-          restartPolicy: OnFailure
-          nodeSelector:
-            kubernetes.io/arch: arm64
-            node-role.kubernetes.io/control-plane: "true"
-          tolerations:
-            - key: node-role.kubernetes.io/control-plane
-              operator: Exists
-              effect: NoSchedule
-            - key: node-role.kubernetes.io/master
-              operator: Exists
-              effect: NoSchedule
-          containers:
-            - name: sync
-              image: registry.bstein.dev/bstein/kubectl:1.35.0
-              imagePullPolicy: IfNotPresent
-              command:
-                - /bin/sh
-                - -c
-              args:
-                - |
-                  set -euo pipefail
-                  token="$(tr -d '\n' < /host/var/lib/rancher/k3s/server/node-token)"
-                  kubectl -n maintenance create secret generic metis-runtime \
-                    --from-literal=k3s_token="${token}" \
-                    --dry-run=client -o yaml | kubectl apply -f -
-              securityContext:
-                runAsUser: 0
-              volumeMounts:
-                - name: k3s-server
-                  mountPath: /host/var/lib/rancher/k3s/server
-                  readOnly: true
-          volumes:
-            - name: k3s-server
-              hostPath:
-                path: /var/lib/rancher/k3s/server

services/maintenance/metis-rbac.yaml

@@ -1,27 +0,0 @@
-# services/maintenance/metis-rbac.yaml
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: metis-node-manager
-rules:
-  - apiGroups: [""]
-    resources:
-      - nodes
-    verbs:
-      - get
-      - list
-      - watch
-      - delete
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: metis-node-manager
-subjects:
-  - kind: ServiceAccount
-    name: metis
-    namespace: maintenance
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: metis-node-manager

services/maintenance/metis-sentinel-daemonset.yaml

@@ -1,133 +0,0 @@
-# services/maintenance/metis-sentinel-daemonset.yaml
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  name: metis-sentinel
-  namespace: maintenance
-spec:
-  selector:
-    matchLabels:
-      app: metis-sentinel
-  updateStrategy:
-    type: RollingUpdate
-  template:
-    metadata:
-      labels:
-        app: metis-sentinel
-      annotations:
-        prometheus.io/scrape: "true"
-        prometheus.io/port: "8080"
-        prometheus.io/path: "/metrics"
-    spec:
-      serviceAccountName: metis
-      nodeSelector:
-        kubernetes.io/os: linux
-        node-role.kubernetes.io/worker: "true"
-      containers:
-        - name: metis-sentinel
-          image: registry.bstein.dev/bstein/metis-sentinel:latest
-          imagePullPolicy: Always
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - |
-              set -eu
-              out_dir="${METIS_SENTINEL_OUT:-/var/run/metis-sentinel}"
-              interval="${METIS_SENTINEL_INTERVAL_SEC:-120}"
-              mkdir -p "${out_dir}"
-              while true; do
-                ts="$(date -u +%Y%m%dT%H%M%SZ)"
-                node="${METIS_SENTINEL_NODE:-unknown}"
-                tmp="${out_dir}/${node}-${ts}.json.tmp"
-                out="${out_dir}/${node}-${ts}.json"
-                if metis-sentinel > "${tmp}"; then
-                  mv "${tmp}" "${out}"
-                else
-                  rm -f "${tmp}" || true
-                fi
-                sleep "${interval}"
-              done
-          envFrom:
-            - configMapRef:
-                name: metis
-          env:
-            - name: METIS_SENTINEL_NODE
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-          ports:
-            - name: http
-              containerPort: 8080
-          volumeMounts:
-            - name: sentinel-output
-              mountPath: /var/run/metis-sentinel
-          resources:
-            requests:
-              cpu: 25m
-              memory: 64Mi
-            limits:
-              cpu: 250m
-              memory: 256Mi
-          securityContext:
-            allowPrivilegeEscalation: false
-            runAsUser: 0
-            capabilities:
-              drop: ["ALL"]
-        - name: sentinel-pusher
-          image: curlimages/curl:8.12.1
-          imagePullPolicy: IfNotPresent
-          command:
-            - /bin/sh
-            - -c
-          args:
-            - |
-              set -eu
-              out_dir="${METIS_SENTINEL_OUT:-/var/run/metis-sentinel}"
-              push_url="${METIS_SENTINEL_PUSH_URL:-}"
-              interval="${METIS_SENTINEL_PUSH_INTERVAL_SEC:-120}"
-              timeout="${METIS_SENTINEL_PUSH_TIMEOUT_SEC:-10}"
-              mkdir -p "${out_dir}"
-              while true; do
-                for snapshot in "${out_dir}"/*.json; do
-                  [ -f "${snapshot}" ] || continue
-                  if [ -z "${push_url}" ]; then
-                    break
-                  fi
-                  if curl -fsS --connect-timeout "${timeout}" --max-time "${timeout}" \
-                    -X POST \
-                    -H "Content-Type: application/json" \
-                    -H "X-Metis-Node: ${METIS_SENTINEL_NODE:-unknown}" \
-                    --data-binary "@${snapshot}" \
-                    "${push_url}"; then
-                    rm -f "${snapshot}"
-                  fi
-                done
-                sleep "${interval}"
-              done
-          envFrom:
-            - configMapRef:
-                name: metis
-          env:
-            - name: METIS_SENTINEL_NODE
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-          volumeMounts:
-            - name: sentinel-output
-              mountPath: /var/run/metis-sentinel
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              cpu: 100m
-              memory: 128Mi
-          securityContext:
-            allowPrivilegeEscalation: false
-            runAsUser: 0
-            capabilities:
-              drop: ["ALL"]
-      volumes:
-        - name: sentinel-output
-          emptyDir: {}

services/maintenance/metis-service.yaml

@@ -1,18 +0,0 @@
-# services/maintenance/metis-service.yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: metis
-  namespace: maintenance
-  annotations:
-    prometheus.io/scrape: "true"
-    prometheus.io/port: "80"
-    prometheus.io/path: "/metrics"
-spec:
-  type: ClusterIP
-  selector:
-    app: metis
-  ports:
-    - name: http
-      port: 80
-      targetPort: http

services/maintenance/metis-serviceaccount.yaml

@@ -1,6 +0,0 @@
-# services/maintenance/metis-serviceaccount.yaml
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: metis
-  namespace: maintenance

services/maintenance/metis-token-sync-rbac.yaml

@@ -1,30 +0,0 @@
-# services/maintenance/metis-token-sync-rbac.yaml
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: metis-token-sync
-  namespace: maintenance
-rules:
-  - apiGroups: [""]
-    resources:
-      - secrets
-    verbs:
-      - get
-      - list
-      - create
-      - update
-      - patch
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: metis-token-sync
-  namespace: maintenance
-subjects:
-  - kind: ServiceAccount
-    name: metis-token-sync
-    namespace: maintenance
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: metis-token-sync

services/maintenance/metis-token-sync-serviceaccount.yaml

@@ -1,6 +0,0 @@
-# services/maintenance/metis-token-sync-serviceaccount.yaml
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: metis-token-sync
-  namespace: maintenance

services/monitoring/dashboards/atlas-jobs.json

@@ -1125,7 +1125,7 @@
     {
       "id": 17,
       "type": "stat",
-      "title": "Platform CI Coverage (%)",
+      "title": "Ariadne CI Coverage (%)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1138,7 +1138,7 @@
       },
       "targets": [
         {
-          "expr": "ariadne_ci_coverage_percent{repo=~\"ariadne|metis\"}",
+          "expr": "ariadne_ci_coverage_percent{repo=\"ariadne\"}",
           "refId": "A",
           "legendFormat": "{{branch}}",
           "instant": true
@@ -1183,13 +1183,12 @@
           "values": false
         },
         "textMode": "value"
-      },
+      }
-      "description": "Internal source panel for Atlas Overview automation test rollups."
     },
     {
       "id": 18,
       "type": "table",
-      "title": "Platform CI Tests (latest)",
+      "title": "Ariadne CI Tests (latest)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1202,7 +1201,7 @@
       },
       "targets": [
         {
-          "expr": "ariadne_ci_tests_total{repo=~\"ariadne|metis\"}",
+          "expr": "ariadne_ci_tests_total{repo=\"ariadne\"}",
           "refId": "A",
           "instant": true
         }
@@ -1234,8 +1233,7 @@
             "order": "desc"
           }
         }
-      ],
+      ]
-      "description": "Atlas Overview test panels depend on these internal repo-tagged CI series."
     }
   ],
   "time": {

services/monitoring/dashboards/atlas-overview.json

@@ -1677,7 +1677,7 @@
     {
       "id": 42,
       "type": "timeseries",
-      "title": "Platform Test Success Rate",
+      "title": "Ariadne Test Success Rate",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1690,7 +1690,7 @@
       },
       "targets": [
         {
-          "expr": "100 * sum(max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=\"passed\"}[30d])) / clamp_min(sum(max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=~\"passed|failed|error\"}[30d])), 1)",
+          "expr": "100 * sum(max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=\"passed\"}[30d])) / clamp_min(sum(max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=~\"passed|failed|error\"}[30d])), 1)",
           "refId": "A"
         }
       ],
@@ -1709,13 +1709,12 @@
         "tooltip": {
           "mode": "multi"
         }
-      },
+      }
-      "description": "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. Add new test series there first so they roll up here."
     },
     {
       "id": 43,
       "type": "bargauge",
-      "title": "Platform Tests with Failures (24h)",
+      "title": "Tests with Failures (24h)",
       "datasource": {
         "type": "prometheus",
         "uid": "atlas-vm"
@@ -1728,7 +1727,7 @@
       },
       "targets": [
         {
-          "expr": "sort_desc(sum by (result) (max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=~\"failed|error\"}[24h])))",
+          "expr": "sort_desc(sum by (result) (max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=~\"failed|error\"}[24h])))",
           "refId": "A",
           "legendFormat": "{{result}}",
           "instant": true
@@ -1815,8 +1814,7 @@
             "order": "desc"
           }
         }
-      ],
+      ]
-      "description": "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
     },
     {
       "id": 11,

services/monitoring/grafana-dashboard-jobs.yaml

@@ -1134,7 +1134,7 @@ data:
         {
           "id": 17,
           "type": "stat",
-          "title": "Platform CI Coverage (%)",
+          "title": "Ariadne CI Coverage (%)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1147,7 +1147,7 @@ data:
           },
           "targets": [
             {
-              "expr": "ariadne_ci_coverage_percent{repo=~\"ariadne|metis\"}",
+              "expr": "ariadne_ci_coverage_percent{repo=\"ariadne\"}",
               "refId": "A",
               "legendFormat": "{{branch}}",
               "instant": true
@@ -1192,13 +1192,12 @@ data:
               "values": false
             },
             "textMode": "value"
-          },
+          }
-          "description": "Internal source panel for Atlas Overview automation test rollups."
         },
         {
           "id": 18,
           "type": "table",
-          "title": "Platform CI Tests (latest)",
+          "title": "Ariadne CI Tests (latest)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1211,7 +1210,7 @@ data:
           },
           "targets": [
             {
-              "expr": "ariadne_ci_tests_total{repo=~\"ariadne|metis\"}",
+              "expr": "ariadne_ci_tests_total{repo=\"ariadne\"}",
               "refId": "A",
               "instant": true
             }
@@ -1243,8 +1242,7 @@ data:
                 "order": "desc"
               }
             }
-          ],
+          ]
-          "description": "Atlas Overview test panels depend on these internal repo-tagged CI series."
         }
       ],
       "time": {

services/monitoring/grafana-dashboard-overview.yaml

@@ -1686,7 +1686,7 @@ data:
         {
           "id": 42,
           "type": "timeseries",
-          "title": "Platform Test Success Rate",
+          "title": "Ariadne Test Success Rate",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1699,7 +1699,7 @@ data:
           },
           "targets": [
             {
-              "expr": "100 * sum(max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=\"passed\"}[30d])) / clamp_min(sum(max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=~\"passed|failed|error\"}[30d])), 1)",
+              "expr": "100 * sum(max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=\"passed\"}[30d])) / clamp_min(sum(max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=~\"passed|failed|error\"}[30d])), 1)",
               "refId": "A"
             }
           ],
@@ -1718,13 +1718,12 @@ data:
             "tooltip": {
               "mode": "multi"
             }
-          },
+          }
-          "description": "Atlas Overview mirrors the Atlas Jobs internal dashboard for automation test health. Add new test series there first so they roll up here."
         },
         {
           "id": 43,
           "type": "bargauge",
-          "title": "Platform Tests with Failures (24h)",
+          "title": "Tests with Failures (24h)",
           "datasource": {
             "type": "prometheus",
             "uid": "atlas-vm"
@@ -1737,7 +1736,7 @@ data:
           },
           "targets": [
             {
-              "expr": "sort_desc(sum by (result) (max_over_time(ariadne_ci_tests_total{repo=~\"ariadne|metis\",result=~\"failed|error\"}[24h])))",
+              "expr": "sort_desc(sum by (result) (max_over_time(ariadne_ci_tests_total{repo=\"ariadne\",result=~\"failed|error\"}[24h])))",
               "refId": "A",
               "legendFormat": "{{result}}",
               "instant": true
@@ -1824,8 +1823,7 @@ data:
                 "order": "desc"
               }
             }
-          ],
+          ]
-          "description": "This summary is sourced from the Atlas Jobs internal dashboard rather than a separate overview-only query."
         },
         {
           "id": 11,