feat: add HPA support for cluster checks runners

charts/datadog/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Datadog changelog
 
+## 3.134.0
+
+* Add HPA support for ClusterChecks runners via `clusterChecksRunner.autoscaling`.
+
 ## 3.133.0
 
 * Revert changes in 3.131.4 because the configuration is going to be deprecated.

charts/datadog/Chart.yaml

@@ -1,7 +1,7 @@
 ---
 apiVersion: v1
 name: datadog
-version: 3.133.0
+version: 3.134.0
 appVersion: "7"
 description: Datadog Agent
 keywords:

charts/datadog/README.md

@@ -1,6 +1,6 @@
 # Datadog
 
-![Version: 3.133.0](https://img.shields.io/badge/Version-3.133.0-informational?style=flat-square) ![AppVersion: 7](https://img.shields.io/badge/AppVersion-7-informational?style=flat-square)
+![Version: 3.134.0](https://img.shields.io/badge/Version-3.134.0-informational?style=flat-square) ![AppVersion: 7](https://img.shields.io/badge/AppVersion-7-informational?style=flat-square)
 
 [Datadog](https://www.datadoghq.com/) is a hosted infrastructure monitoring platform. This chart adds the Datadog Agent to all nodes in your cluster via a DaemonSet. It also optionally depends on the [kube-state-metrics chart](https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-state-metrics). For more information about monitoring Kubernetes with Datadog, please refer to the [Datadog documentation website](https://docs.datadoghq.com/agent/basic_agent_usage/kubernetes/).
 
@@ -665,6 +665,13 @@ helm install <RELEASE_NAME> \
 | clusterAgent.volumes | list | `[]` | Specify additional volumes to mount in the cluster-agent container |
 | clusterChecksRunner.additionalLabels | object | `{}` | Adds labels to the cluster checks runner deployment and pods |
 | clusterChecksRunner.affinity | object | `{}` | Allow the ClusterChecks Deployment to schedule using affinity rules. |
+| clusterChecksRunner.autoscaling | object | `{"behavior":{},"enabled":false,"maxReplicas":5,"minReplicas":2,"targetCPUUtilizationPercentage":80,"targetMemoryUtilizationPercentage":80}` | Horizontal Pod Autoscaler configuration for Cluster Checks Runner |
+| clusterChecksRunner.autoscaling.behavior | object | `{}` | HPA scaling behavior configuration |
+| clusterChecksRunner.autoscaling.enabled | bool | `false` | Enable autoscaling for Cluster Checks Runner deployment |
+| clusterChecksRunner.autoscaling.maxReplicas | int | `5` | Maximum number of replicas |
+| clusterChecksRunner.autoscaling.minReplicas | int | `2` | Minimum number of replicas |
+| clusterChecksRunner.autoscaling.targetCPUUtilizationPercentage | int | `80` | Target CPU utilization percentage |
+| clusterChecksRunner.autoscaling.targetMemoryUtilizationPercentage | int | `80` | Target memory utilization percentage (optional) |
 | clusterChecksRunner.containers.agent.securityContext | object | `{}` | Specify securityContext on the agent container |
 | clusterChecksRunner.containers.initContainers.securityContext | object | `{}` | Specify securityContext on the init containers |
 | clusterChecksRunner.createPodDisruptionBudget | bool | `false` | Create the pod disruption budget to apply to the cluster checks agents |

charts/datadog/templates/_helpers.tpl

@@ -1267,3 +1267,14 @@ false
     true
   {{- end -}}
 {{- end -}}
+
+{{/*
+Return the appropriate apiVersion for HorizontalPodAutoscaler APIs.
+*/}}
+{{- define "autoscaling.horizontalpodautoscaler.apiVersion" -}}
+{{- if or (.Capabilities.APIVersions.Has "autoscaling/v2/HorizontalPodAutoscaler") (semverCompare ">=1.23" .Capabilities.KubeVersion.Version) -}}
+"autoscaling/v2"
+{{- else -}}
+"autoscaling/v2beta2"
+{{- end -}}
+{{- end -}}

charts/datadog/templates/agent-clusterchecks-deployment.yaml

@@ -15,7 +15,9 @@ metadata:
   annotations: {{ toYaml .Values.clusterChecksRunner.deploymentAnnotations | nindent 4 }}
   {{- end }}
 spec:
+  {{- if not .Values.clusterChecksRunner.autoscaling.enabled }}
   replicas: {{ .Values.clusterChecksRunner.replicas }}
+  {{- end }}
   revisionHistoryLimit: {{ .Values.clusterChecksRunner.revisionHistoryLimit }}
   strategy:
 {{ toYaml .Values.clusterChecksRunner.strategy | indent 4 }}

charts/datadog/templates/agent-clusterchecks-hpa.yaml

@@ -0,0 +1,37 @@
+{{- if and (eq (include "should-deploy-cluster-agent" .) "true") (eq (include "should-enable-cluster-check-workers" .) "true") .Values.clusterChecksRunner.autoscaling.enabled -}}
+apiVersion: {{ template "autoscaling.horizontalpodautoscaler.apiVersion" . }}
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ template "datadog.fullname" . }}-clusterchecks
+  namespace: {{ .Release.Namespace }}
+  labels:
+{{ include "datadog.labels" . | indent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ template "datadog.fullname" . }}-clusterchecks
+  minReplicas: {{ .Values.clusterChecksRunner.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.clusterChecksRunner.autoscaling.maxReplicas }}
+  metrics:
+  {{- if .Values.clusterChecksRunner.autoscaling.targetMemoryUtilizationPercentage }}
+  - type: Resource
+    resource:
+      name: memory
+      target:
+        type: Utilization
+        averageUtilization: {{ .Values.clusterChecksRunner.autoscaling.targetMemoryUtilizationPercentage }}
+  {{- end }}
+  {{- if .Values.clusterChecksRunner.autoscaling.targetCPUUtilizationPercentage }}
+  - type: Resource
+    resource:
+      name: cpu
+      target:
+        type: Utilization
+        averageUtilization: {{ .Values.clusterChecksRunner.autoscaling.targetCPUUtilizationPercentage }}
+  {{- end }}
+  {{- if .Values.clusterChecksRunner.autoscaling.behavior }}
+  behavior:
+{{ toYaml .Values.clusterChecksRunner.autoscaling.behavior | indent 4 }}
+  {{- end }}
+{{- end }}

charts/datadog/values.yaml

@@ -2428,7 +2428,8 @@ clusterChecksRunner:
   # clusterChecksRunner.replicas -- Number of Cluster Checks Runner instances
 
   ## If you want to deploy the clusterChecks agent in HA, keep at least clusterChecksRunner.replicas set to 2.
-  ## And increase the clusterChecksRunner.replicas according to the number of Cluster Checks.
+  ## And increase the clusterChecksRunner.replicas according to the number of Cluster Checks or
+  ## use clusterChecksRunner.autoscaling to enable HPA.
   replicas: 2
 
   # clusterChecksRunner.revisionHistoryLimit -- The number of old ReplicaSets to keep in this Deployment.
@@ -2443,6 +2444,37 @@ clusterChecksRunner:
   #   cpu: 200m
   #   memory: 500Mi
 
+  # clusterChecksRunner.autoscaling -- Horizontal Pod Autoscaler configuration for Cluster Checks Runner
+  autoscaling:
+    # clusterChecksRunner.autoscaling.enabled -- Enable autoscaling for Cluster Checks Runner deployment
+    enabled: false
+    # clusterChecksRunner.autoscaling.minReplicas -- Minimum number of replicas
+    minReplicas: 2
+    # clusterChecksRunner.autoscaling.maxReplicas -- Maximum number of replicas
+    maxReplicas: 5
+    # clusterChecksRunner.autoscaling.targetCPUUtilizationPercentage -- Target CPU utilization percentage
+    targetCPUUtilizationPercentage: 80
+    # clusterChecksRunner.autoscaling.targetMemoryUtilizationPercentage -- Target memory utilization percentage (optional)
+    targetMemoryUtilizationPercentage: 80
+    # clusterChecksRunner.autoscaling.behavior -- HPA scaling behavior configuration
+    behavior: {}
+    # scaleDown:
+    #   stabilizationWindowSeconds: 300
+    #   policies:
+    #   - type: Percent
+    #     value: 100
+    #     periodSeconds: 15
+    # scaleUp:
+    #   stabilizationWindowSeconds: 0
+    #   policies:
+    #   - type: Percent
+    #     value: 100
+    #     periodSeconds: 15
+    #   - type: Pods
+    #     value: 4
+    #     periodSeconds: 15
+    #   selectPolicy: Max
+
   # clusterChecksRunner.affinity -- Allow the ClusterChecks Deployment to schedule using affinity rules.
 
   ## By default, ClusterChecks Deployment Pods are preferred to run on different Nodes.