feat: Add check-alert cron task (#2)

Author: teeohhem

README.md

@@ -114,6 +114,16 @@ hyperdx:
         key: API_KEY
 ```
 
+## Task Configuration
+
+By default, there is one task in the chart setup as a cronjob, responsible for checking whether alerts should fire. Here are its configuration options:
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `tasks.enabled` | Enable/Disable cron tasks in the cluster. By default, the HyperDX image will run cron tasks intra process. Change to true if you'd rather use a separate cron task in the cluster. | `false` |
+| `tasks.checkAlerts.schedule` | Cron schedule for the check-alerts task | `*/1 * * * *` |
+| `tasks.checkAlerts.resources` | Resource requests and limits for the check-alerts task | See `values.yaml` |
+
 ## Upgrading the Chart
 
 To upgrade to a newer version:

charts/hdx-oss-v2/data/users.xml

@@ -25,6 +25,7 @@
         <app>
             <password>{{ .Values.clickhouse.config.users.appUserPassword }}</password>
             <networks>
+                <ip>10.0.0.0/8</ip>     <!-- Kubernetes cluster IP range -->
                 <host_regexp>.*\.svc\.cluster\.local$</host_regexp>
             </networks>
             <profile>readonly</profile>

charts/hdx-oss-v2/templates/configmaps/app-configmap.yaml

@@ -17,4 +17,5 @@ data:
   NEXT_PUBLIC_SERVER_URL: "http://localhost:{{ .Values.hyperdx.apiPort }}"
   OTEL_SERVICE_NAME: "hdx-oss-api"
   REDIS_URL: "redis://{{ include "hdx-oss.fullname" . }}-redis:{{ .Values.redis.port }}"
-  USAGE_STATS_ENABLED: "{{ .Values.hyperdx.usageStatsEnabled | default true }}" 
+  USAGE_STATS_ENABLED: "{{ .Values.hyperdx.usageStatsEnabled | default true }}"
+  CRON_IN_APP_DISABLED: "{{ .Values.tasks.enabled | default false }}"

charts/hdx-oss-v2/templates/cronjobs/task-checkAlerts.yaml

@@ -0,0 +1,35 @@
+{{- if .Values.tasks.enabled }}
+---
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: {{ include "hdx-oss.fullname" . }}-check-alerts
+  labels:
+    {{- include "hdx-oss.labels" . | nindent 4 }}
+spec:
+  schedule: {{ .Values.tasks.checkAlerts.schedule | quote }}
+  concurrencyPolicy: Forbid
+  jobTemplate:
+    spec:
+      template:
+        metadata:
+          labels:
+            {{- include "hdx-oss.selectorLabels" . | nindent 12 }}
+            app.kubernetes.io/component: task
+        spec:
+          restartPolicy: OnFailure
+          containers:
+            - name: task
+              image: "{{ .Values.images.hdx.repository }}:{{ .Values.images.hdx.tag | default .Chart.AppVersion }}"
+              command: ["node", "/app/api/build/tasks/index.js", "check-alerts"]
+              envFrom:
+                - configMapRef:
+                    name: {{ include "hdx-oss.fullname" . }}-app-config
+              env:
+                - name: NODE_ENV
+                  value: "production"
+                - name: OTEL_SERVICE_NAME
+                  value: "hdx-oss-task-check-alerts"
+              resources:
+                {{- toYaml .Values.tasks.checkAlerts.resources | nindent 16 }}
+{{- end }}

charts/hdx-oss-v2/values.yaml

@@ -70,3 +70,15 @@ persistence:
   mongodb:
     enabled: true
     size: 10Gi
+
+tasks:
+  enabled: false
+  checkAlerts:
+    schedule: "*/1 * * * *"  # Runs every 1 minute
+    resources:
+      limits:
+        cpu: 200m
+        memory: 256Mi
+      requests:
+        cpu: 100m
+        memory: 128Mi