Add node-problem-detector-app, add machine health check schema

Author: AndiDog

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- Add node-problem-detector-app, disabled by default
+
 ### Changed
 
 - Change the default root disk size for Karpenter node pools. Karpenter will choose the cheapest instances, and certain instances, like `g6f.xlarge` come with some drivers that require a larger disk.

helm/cluster-aws/Chart.lock

@@ -1,9 +1,9 @@
 dependencies:
 - name: cluster
-  repository: https://giantswarm.github.io/cluster-catalog
-  version: 4.2.0
+  repository: https://giantswarm.github.io/cluster-test-catalog
+  version: 4.2.0-6589491ce629d9017244a6fe7c967eacc47c0be7
 - name: cluster-shared
   repository: https://giantswarm.github.io/cluster-catalog
   version: 0.7.1
-digest: sha256:1c4c18cdeba1c6586ff1ff61b0e332d8cb2c68ac88cd29d7179795d2d4370f8b
-generated: "2025-10-14T16:08:13.682067655Z"
+digest: sha256:7860315c96114b4223e73c6c7f2f36a8a20df484c082e7de0b1dc02ba1379742
+generated: "2025-10-23T12:28:24.727371+02:00"

helm/cluster-aws/Chart.yaml

@@ -16,8 +16,8 @@ restrictions:
     - capa
 dependencies:
   - name: cluster
-    version: "4.2.0"
-    repository: https://giantswarm.github.io/cluster-catalog
+    version: "4.2.0-91d64c817d0186dabd6b5148e2255093afb5823b"
+    repository: https://giantswarm.github.io/cluster-test-catalog
   - name: cluster-shared
     version: "0.7.1"
     repository: https://giantswarm.github.io/cluster-catalog

helm/cluster-aws/README.md

@@ -393,6 +393,9 @@ Properties within the `.global.controlPlane` object
 | `global.controlPlane.loadBalancerIngressAllowCidrBlocks[*]` | **Address range**|**Type:** `[string]`<br/>|
 | `global.controlPlane.logVolumeSizeGB` | **Log volume size (GB)** - Size of the volume mounted at /var/log on the control plane nodes.|**Type:** `[integer]`<br/>**Default:** `15`|
 | `global.controlPlane.machineHealthCheck` | **Machine health check**|**Type:** `[object]`<br/>|
+| `global.controlPlane.machineHealthCheck.diskFullContainerdTimeout` | **DiskFullContainerd timeout** - Determines how long a machine health check should wait for a node with condition DiskFullContainerd=True before considering a machine unhealthy. Use an empty value to not consider this condition.|**Type:** `[string]`<br/>**Examples:** `"10m", "100s"`<br/>**Default:** `""`|
+| `global.controlPlane.machineHealthCheck.diskFullKubeletTimeout` | **DiskFullKubelet timeout** - Determines how long a machine health check should wait for a node with condition DiskFullKubelet=True before considering a machine unhealthy. Use an empty value to not consider this condition.|**Type:** `[string]`<br/>**Examples:** `"10m", "100s"`<br/>**Default:** `""`|
+| `global.controlPlane.machineHealthCheck.diskFullVarLogTimeout` | **DiskFullVarLog timeout** - Determines how long a machine health check should wait for a node with condition DiskFullVarLog=True before considering a machine unhealthy. Use an empty value to not consider this condition.|**Type:** `[string]`<br/>**Examples:** `"10m", "100s"`<br/>**Default:** `""`|
 | `global.controlPlane.machineHealthCheck.enabled` | **Enable**|**Type:** `[boolean]`<br/>**Default:** `true`|
 | `global.controlPlane.machineHealthCheck.maxUnhealthy` | **Maximum unhealthy nodes**|**Type:** `[string]`<br/>**Example:** `"40%"`<br/>**Default:** `"40%"`|
 | `global.controlPlane.machineHealthCheck.nodeStartupTimeout` | **Node startup timeout** - Determines how long a machine health check should wait for a node to join the cluster, before considering a machine unhealthy.|**Type:** `[string]`<br/>**Examples:** `"10m", "100s"`<br/>**Default:** `"8m0s"`|
@@ -465,7 +468,7 @@ Information about the workload cluster release.
 | **Property** | **Description** | **More Details** |
 | :----------- | :-------------- | :--------------- |
 | `baseDomain` | **Base DNS domain**|**Type:** `[string]`<br/>|
-| `cluster` | **Cluster** - Helm values for the provider-independent cluster chart|**Type:** `[object]`<br/>**Default:** `{"providerIntegration":{"apps":{"certExporter":{"enable":true},"certManager":{"configTemplateName":"awsCertManagerHelmValues","enable":true},"chartOperatorExtensions":{"enable":true},"cilium":{"configTemplateName":"awsCiliumHelmValues","enable":true},"ciliumServiceMonitors":{"enable":true},"clusterAutoscaler":{"configTemplateName":"awsClusterAutoscalerHelmValues","enable":true},"coreDns":{"configTemplateName":"awsCorednsHelmValues","enable":true},"coreDnsExtensions":{"enable":true},"etcdDefrag":{"enable":true},"etcdKubernetesResourcesCountExporter":{"enable":true},"externalDns":{"configTemplateName":"awsExternalDnsHelmValues","enable":true},"k8sAuditMetrics":{"enable":true},"k8sDnsNodeCache":{"enable":true},"metricsServer":{"enable":true},"netExporter":{"enable":true},"networkPolicies":{"configTemplateName":"awsNetworkPoliciesHelmValues","enable":true},"nodeExporter":{"enable":true},"observabilityBundle":{"enable":true},"observabilityPolicies":{"enable":true},"prometheusBlackboxExporter":{"enable":true},"securityBundle":{"configTemplateName":"awsSecurityBundleHelmValues","enable":true},"teleportKubeAgent":{"enable":true},"verticalPodAutoscaler":{"enable":true},"verticalPodAutoscalerCrd":{"enable":true}},"clusterAnnotationsTemplateName":"awsConnectivityLabels","components":{"systemd":{"timesyncd":{"ntp":["169.254.169.123"]}}},"connectivity":{"proxy":{"noProxy":{"templateName":"awsNoProxyList","value":["elb.amazonaws.com","169.254.169.254"]}}},"controlPlane":{"kubeadmConfig":{"clusterConfiguration":{"apiServer":{"apiAudiences":{"templateName":"awsApiServerApiAudiences"},"serviceAccountIssuers":[{"templateName":"awsIrsaServiceAccountIssuer"}]}},"files":[],"ignition":{"containerLinuxConfig":{"additionalConfig":{"storage":{"filesystems":[{"mount":{"device":"/dev/xvdc","format":"xfs","label":"etcd","wipeFilesystem":true},"name":"etcd"},{"mount":{"device":"/dev/xvdd","format":"xfs","label":"lib","wipeFilesystem":true},"name":"lib"},{"mount":{"device":"/dev/xvde","format":"xfs","label":"log","wipeFilesystem":true},"name":"log"}]},"systemd":{"units":[{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/etcd","where":"/var/lib/etcd"},"unit":{"defaultDependencies":false,"description":"etcd volume"}},"enabled":true,"name":"var-lib-etcd.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/lib","where":"/var/lib"},"unit":{"defaultDependencies":false,"description":"var lib volume"}},"enabled":true,"name":"var-lib.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/log","where":"/var/log"},"unit":{"defaultDependencies":false,"description":"log volume"}},"enabled":true,"name":"var-log.mount"}]}}}}},"resources":{"infrastructureMachineTemplate":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSMachineTemplate","version":"v1beta2"},"infrastructureMachineTemplateSpecTemplateName":"controlplane-awsmachinetemplate-spec"}},"environmentVariables":{"hostName":"COREOS_EC2_HOSTNAME","ipv4":"COREOS_EC2_IPV4_LOCAL"},"kubeadmConfig":{"files":[{"contentFrom":{"secret":{"key":"kubelet-aws-config.sh","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/opt/bin/kubelet-aws-config.sh","permissions":"0755"},{"contentFrom":{"secret":{"key":"kubelet-aws-config.service","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/etc/systemd/system/kubelet-aws-config.service","permissions":"0644"},{"contentFrom":{"secret":{"key":"99-unmanaged-devices.network","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/etc/systemd/network/99-unmanaged-devices.network","permissions":"0644"}],"ignition":{"containerLinuxConfig":{"additionalConfig":{"systemd":{"units":[{"enabled":true,"name":"kubelet-aws-config.service"}]}}}}},"osImage":{"variant":"3"},"pauseProperties":{"global.connectivity.vpcMode":"private"},"provider":"aws","registry":{"templateName":"awsContainerImageRegistry"},"resourcesApi":{"bastionResourceEnabled":false,"cleanupHelmReleaseResourcesEnabled":true,"clusterResourceEnabled":true,"controlPlaneResourceEnabled":true,"helmRepositoryResourcesEnabled":true,"infrastructureCluster":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSCluster","version":"v1beta2"},"infrastructureMachinePool":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSMachinePool","version":"v1beta2"},"machineHealthCheckResourceEnabled":true,"machinePoolResourcesEnabled":true,"nodePoolKind":"MachinePool"},"useReleases":true,"workers":{"defaultNodePools":{"def00":{"customNodeLabels":["label=default"],"instanceType":"r6i.xlarge","instanceWarmup":600,"maxSize":3,"minHealthyPercentage":90,"minSize":3}},"kubeadmConfig":{"files":[],"ignition":{"containerLinuxConfig":{"additionalConfig":{"storage":{"filesystems":[{"mount":{"device":"/dev/xvdd","format":"xfs","label":"lib","wipeFilesystem":true},"name":"lib"},{"mount":{"device":"/dev/xvde","format":"xfs","label":"log","wipeFilesystem":true},"name":"log"}]},"systemd":{"units":[{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/lib","where":"/var/lib"},"unit":{"defaultDependencies":false,"description":"lib volume"}},"enabled":true,"name":"var-lib.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/log","where":"/var/log"},"unit":{"defaultDependencies":false,"description":"log volume"}},"enabled":true,"name":"var-log.mount"}]}}}},"taints":[{"effect":"NoExecute","key":"ebs.csi.aws.com/agent-not-ready"}]}}}}`|
+| `cluster` | **Cluster** - Helm values for the provider-independent cluster chart|**Type:** `[object]`<br/>**Default:** `{"providerIntegration":{"apps":{"certExporter":{"enable":true},"certManager":{"configTemplateName":"awsCertManagerHelmValues","enable":true},"chartOperatorExtensions":{"enable":true},"cilium":{"configTemplateName":"awsCiliumHelmValues","enable":true},"ciliumServiceMonitors":{"enable":true},"clusterAutoscaler":{"configTemplateName":"awsClusterAutoscalerHelmValues","enable":true},"coreDns":{"configTemplateName":"awsCorednsHelmValues","enable":true},"coreDnsExtensions":{"enable":true},"etcdDefrag":{"enable":true},"etcdKubernetesResourcesCountExporter":{"enable":true},"externalDns":{"configTemplateName":"awsExternalDnsHelmValues","enable":true},"k8sAuditMetrics":{"enable":true},"k8sDnsNodeCache":{"enable":true},"metricsServer":{"enable":true},"netExporter":{"enable":true},"networkPolicies":{"configTemplateName":"awsNetworkPoliciesHelmValues","enable":true},"nodeExporter":{"enable":true},"nodeProblemDetector":{"enable":true},"observabilityBundle":{"enable":true},"observabilityPolicies":{"enable":true},"prometheusBlackboxExporter":{"enable":true},"securityBundle":{"configTemplateName":"awsSecurityBundleHelmValues","enable":true},"teleportKubeAgent":{"enable":true},"verticalPodAutoscaler":{"enable":true},"verticalPodAutoscalerCrd":{"enable":true}},"clusterAnnotationsTemplateName":"awsConnectivityLabels","components":{"systemd":{"timesyncd":{"ntp":["169.254.169.123"]}}},"connectivity":{"proxy":{"noProxy":{"templateName":"awsNoProxyList","value":["elb.amazonaws.com","169.254.169.254"]}}},"controlPlane":{"kubeadmConfig":{"clusterConfiguration":{"apiServer":{"apiAudiences":{"templateName":"awsApiServerApiAudiences"},"serviceAccountIssuers":[{"templateName":"awsIrsaServiceAccountIssuer"}]}},"files":[],"ignition":{"containerLinuxConfig":{"additionalConfig":{"storage":{"filesystems":[{"mount":{"device":"/dev/xvdc","format":"xfs","label":"etcd","wipeFilesystem":true},"name":"etcd"},{"mount":{"device":"/dev/xvdd","format":"xfs","label":"lib","wipeFilesystem":true},"name":"lib"},{"mount":{"device":"/dev/xvde","format":"xfs","label":"log","wipeFilesystem":true},"name":"log"}]},"systemd":{"units":[{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/etcd","where":"/var/lib/etcd"},"unit":{"defaultDependencies":false,"description":"etcd volume"}},"enabled":true,"name":"var-lib-etcd.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/lib","where":"/var/lib"},"unit":{"defaultDependencies":false,"description":"var lib volume"}},"enabled":true,"name":"var-lib.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/log","where":"/var/log"},"unit":{"defaultDependencies":false,"description":"log volume"}},"enabled":true,"name":"var-log.mount"}]}}}}},"resources":{"infrastructureMachineTemplate":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSMachineTemplate","version":"v1beta2"},"infrastructureMachineTemplateSpecTemplateName":"controlplane-awsmachinetemplate-spec"}},"environmentVariables":{"hostName":"COREOS_EC2_HOSTNAME","ipv4":"COREOS_EC2_IPV4_LOCAL"},"kubeadmConfig":{"files":[{"contentFrom":{"secret":{"key":"kubelet-aws-config.sh","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/opt/bin/kubelet-aws-config.sh","permissions":"0755"},{"contentFrom":{"secret":{"key":"kubelet-aws-config.service","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/etc/systemd/system/kubelet-aws-config.service","permissions":"0644"},{"contentFrom":{"secret":{"key":"99-unmanaged-devices.network","name":"provider-specific-files-4","prependClusterNameAsPrefix":true}},"path":"/etc/systemd/network/99-unmanaged-devices.network","permissions":"0644"}],"ignition":{"containerLinuxConfig":{"additionalConfig":{"systemd":{"units":[{"enabled":true,"name":"kubelet-aws-config.service"}]}}}}},"osImage":{"variant":"3"},"pauseProperties":{"global.connectivity.vpcMode":"private"},"provider":"aws","registry":{"templateName":"awsContainerImageRegistry"},"resourcesApi":{"bastionResourceEnabled":false,"cleanupHelmReleaseResourcesEnabled":true,"clusterResourceEnabled":true,"controlPlaneResourceEnabled":true,"helmRepositoryResourcesEnabled":true,"infrastructureCluster":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSCluster","version":"v1beta2"},"infrastructureMachinePool":{"group":"infrastructure.cluster.x-k8s.io","kind":"AWSMachinePool","version":"v1beta2"},"machineHealthCheckResourceEnabled":true,"machinePoolResourcesEnabled":true,"nodePoolKind":"MachinePool"},"useReleases":true,"workers":{"defaultNodePools":{"def00":{"customNodeLabels":["label=default"],"instanceType":"r6i.xlarge","instanceWarmup":600,"maxSize":3,"minHealthyPercentage":90,"minSize":3}},"kubeadmConfig":{"files":[],"ignition":{"containerLinuxConfig":{"additionalConfig":{"storage":{"filesystems":[{"mount":{"device":"/dev/xvdd","format":"xfs","label":"lib","wipeFilesystem":true},"name":"lib"},{"mount":{"device":"/dev/xvde","format":"xfs","label":"log","wipeFilesystem":true},"name":"log"}]},"systemd":{"units":[{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/lib","where":"/var/lib"},"unit":{"defaultDependencies":false,"description":"lib volume"}},"enabled":true,"name":"var-lib.mount"},{"contents":{"install":{"wantedBy":["local-fs-pre.target"]},"mount":{"type":"xfs","what":"/dev/disk/by-label/log","where":"/var/log"},"unit":{"defaultDependencies":false,"description":"log volume"}},"enabled":true,"name":"var-log.mount"}]}}}},"taints":[{"effect":"NoExecute","key":"ebs.csi.aws.com/agent-not-ready"}]}}}}`|
 | `cluster-shared` | **Library chart**|**Type:** `[object]`<br/>|
 | `managementCluster` | **Management cluster** - Name of the Cluster API cluster managing this workload cluster.|**Type:** `[string]`<br/>|
 | `provider` | **Cluster API provider name**|**Type:** `[string]`<br/>|

helm/cluster-aws/ci/test-machinehealthcheck-node-problem-detector-used-control-plane-values.yaml

@@ -0,0 +1,22 @@
+global:
+  release:
+    version: 29.1.0
+  metadata:
+    name: node-problem-detector-used
+    organization: test
+    servicePriority: lowest
+  connectivity:
+    baseDomain: example.com
+  controlPlane:
+    machineHealthCheck:
+      enabled: true
+      diskFullVarLogTimeout: "1337m"
+  providerSpecific:
+    region: "eu-west-1"
+  managementCluster: test
+
+cluster:
+  internal:
+    ephemeralConfiguration:
+      offlineTesting:
+        renderWithoutReleaseResource: true

helm/cluster-aws/ci/test-machinehealthcheck-node-problem-detector-used-workers-values.yaml

@@ -0,0 +1,25 @@
+global:
+  release:
+    version: 29.1.0
+  metadata:
+    name: node-problem-detector-used
+    organization: test
+    servicePriority: lowest
+  connectivity:
+    baseDomain: example.com
+  nodePools:
+    pool0:
+      maxSize: 3
+      minSize: 3
+      machineHealthCheck:
+        enabled: true
+        diskFullContainerdTimeout: "1337m"
+  providerSpecific:
+    region: "eu-west-1"
+  managementCluster: test
+
+cluster:
+  internal:
+    ephemeralConfiguration:
+      offlineTesting:
+        renderWithoutReleaseResource: true