From 44788b313287c3307d226cf31e419693969ce666 Mon Sep 17 00:00:00 2001
From: Brad Stein <Brad.Stein@gmail.com>
Date: Wed, 28 Jan 2026 13:47:37 -0300
Subject: [PATCH] monitoring: alert on ariadne schedules

---
 .../monitoring/grafana-alerting-config.yaml   | 115 ++++++++++++++++--
 1 file changed, 108 insertions(+), 7 deletions(-)

diff --git a/services/monitoring/grafana-alerting-config.yaml b/services/monitoring/grafana-alerting-config.yaml
index d8402fa..37b66f4 100644
--- a/services/monitoring/grafana-alerting-config.yaml
+++ b/services/monitoring/grafana-alerting-config.yaml
@@ -286,8 +286,8 @@ data:
               summary: "node-image-sweeper not fully ready"
             labels:
               severity: warning
-          - uid: maint-cron-stale
-            title: "Maintenance CronJobs stale (>3h since success)"
+          - uid: maint-ariadne-image-sweeper-stale
+            title: "Ariadne image sweeper stale (>8d since success)"
             condition: C
             for: "5m"
             data:
@@ -297,10 +297,10 @@ data:
                   to: 0
                 datasourceUid: atlas-vm
                 model:
-                  expr: time() - max by (cronjob) (kube_cronjob_status_last_successful_time{namespace="maintenance",cronjob="image-sweeper"}) and on(cronjob) (kube_cronjob_spec_suspend{namespace="maintenance",cronjob="image-sweeper"} == 0)
+                  expr: time() - ariadne_schedule_last_success_timestamp_seconds{task="schedule.image_sweeper"}
                   intervalMs: 60000
                   maxDataPoints: 43200
-                  legendFormat: '{{cronjob}}'
+                  legendFormat: '{{task}}'
                   datasource:
                     type: prometheus
                     uid: atlas-vm
@@ -321,17 +321,118 @@ data:
                   type: threshold
                   conditions:
                     - evaluator:
-                        params: [10800]
+                        params: [691200]
                         type: gt
                       operator:
                         type: and
                       reducer:
                         type: last
                       type: query
-            noDataState: NoData
+            noDataState: OK
             execErrState: Error
             annotations:
-              summary: "Maintenance cronjob stale >3h since last success"
+              summary: "Ariadne image sweeper stale >8d since last success"
+            labels:
+              severity: warning
+      - orgId: 1
+        name: ariadne
+        folder: Alerts
+        interval: 1m
+        rules:
+          - uid: ariadne-schedule-error
+            title: "Ariadne schedule task failed"
+            condition: C
+            for: "10m"
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: atlas-vm
+                model:
+                  expr: ariadne_schedule_last_status{task=~"schedule\\..+"}
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  legendFormat: '{{task}}'
+                  datasource:
+                    type: prometheus
+                    uid: atlas-vm
+              - refId: B
+                datasourceUid: __expr__
+                model:
+                  expression: A
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  reducer: last
+                  type: reduce
+              - refId: C
+                datasourceUid: __expr__
+                model:
+                  expression: B
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  type: threshold
+                  conditions:
+                    - evaluator:
+                        params: [1]
+                        type: lt
+                      operator:
+                        type: and
+                      reducer:
+                        type: last
+                      type: query
+            noDataState: OK
+            execErrState: Error
+            annotations:
+              summary: "Ariadne schedule failed ({{ $labels.task }})"
+            labels:
+              severity: warning
+          - uid: ariadne-scheduler-stalled
+            title: "Ariadne scheduler behind (>15m)"
+            condition: C
+            for: "10m"
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: atlas-vm
+                model:
+                  expr: time() - ariadne_schedule_next_run_timestamp_seconds{task=~"schedule\\..+"}
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  legendFormat: '{{task}}'
+                  datasource:
+                    type: prometheus
+                    uid: atlas-vm
+              - refId: B
+                datasourceUid: __expr__
+                model:
+                  expression: A
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  reducer: last
+                  type: reduce
+              - refId: C
+                datasourceUid: __expr__
+                model:
+                  expression: B
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  type: threshold
+                  conditions:
+                    - evaluator:
+                        params: [900]
+                        type: gt
+                      operator:
+                        type: and
+                      reducer:
+                        type: last
+                      type: query
+            noDataState: OK
+            execErrState: Error
+            annotations:
+              summary: "Ariadne scheduler behind for {{ $labels.task }}"
             labels:
               severity: warning
       - orgId: 1