Skip to content

MON-4029: Add KubeStateMetricsConfig to ClusterMonitoring API #2778

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
danielmellado wants to merge 1 commit into
base: master
Choose a base branch
from
Open

MON-4029: Add KubeStateMetricsConfig to ClusterMonitoring API #2778

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
238 changes: 238 additions & 0 deletions config/v1alpha1/tests/clustermonitorings.config.openshift.io/ClusterMonitoringConfig.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -815,3 +815,241 @@ tests:
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
expectedError: "Duplicate value"
- name: Should be able to create KubeStateMetricsConfig with valid resources
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources:
- name: "cpu"
request: "50m"
limit: "200m"
- name: "memory"
request: "50Mi"
limit: "200Mi"
expected: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources:
- name: "cpu"
request: "50m"
limit: "200m"
- name: "memory"
request: "50Mi"
limit: "200Mi"
- name: Should be able to create KubeStateMetricsConfig with valid topologySpreadConstraints
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
app: kube-state-metrics
- maxSkew: 2
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
app: kube-state-metrics
expected: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
app: kube-state-metrics
- maxSkew: 2
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
app: kube-state-metrics
- name: Should be able to create KubeStateMetricsConfig with all fields
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
nodeSelector:
kubernetes.io/os: linux
resources:
- name: "cpu"
request: "50m"
limit: "200m"
tolerations:
- key: "node-role.kubernetes.io/infra"
operator: "Exists"
effect: "NoSchedule"
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
app: kube-state-metrics
expected: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
nodeSelector:
kubernetes.io/os: linux
resources:
- name: "cpu"
request: "50m"
limit: "200m"
tolerations:
- key: "node-role.kubernetes.io/infra"
operator: "Exists"
effect: "NoSchedule"
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
app: kube-state-metrics
- name: Should reject KubeStateMetricsConfig with empty object
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig: {}
expectedError: 'spec.kubeStateMetricsConfig: Invalid value: 0: spec.kubeStateMetricsConfig in body should have at least 1 properties'
- name: Should reject KubeStateMetricsConfig with too many resources
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources:
- name: "cpu"
request: "100m"
- name: "memory"
request: "64Mi"
- name: "hugepages-2Mi"
request: "32Mi"
- name: "hugepages-1Gi"
request: "1Gi"
- name: "ephemeral-storage"
request: "1Gi"
- name: "nvidia.com/gpu"
request: "1"
- name: "example.com/foo"
request: "1"
- name: "example.com/bar"
request: "1"
- name: "example.com/baz"
request: "1"
- name: "example.com/qux"
request: "1"
- name: "example.com/quux"
request: "1"
expectedError: 'spec.kubeStateMetricsConfig.resources: Too many: 11: must have at most 10 items'
- name: Should reject KubeStateMetricsConfig with limit less than request
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources:
- name: "cpu"
request: "500m"
limit: "200m"
expectedError: 'spec.kubeStateMetricsConfig.resources[0]: Invalid value: "object": limit must be greater than or equal to request'
- name: Should reject KubeStateMetricsConfig with too many topologySpreadConstraints
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
topologySpreadConstraints:
- maxSkew: 1
topologyKey: "zone1"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone2"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone3"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone4"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone5"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone6"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone7"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone8"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone9"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone10"
whenUnsatisfiable: DoNotSchedule
- maxSkew: 1
topologyKey: "zone11"
whenUnsatisfiable: DoNotSchedule
expectedError: 'spec.kubeStateMetricsConfig.topologySpreadConstraints: Too many: 11: must have at most 10 items'
- name: Should reject KubeStateMetricsConfig with empty resources array
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources: []
expectedError: 'spec.kubeStateMetricsConfig.resources: Invalid value: 0: spec.kubeStateMetricsConfig.resources in body should have at least 1 items'
- name: Should reject KubeStateMetricsConfig with empty topologySpreadConstraints array
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
topologySpreadConstraints: []
expectedError: 'spec.kubeStateMetricsConfig.topologySpreadConstraints: Invalid value: 0: spec.kubeStateMetricsConfig.topologySpreadConstraints in body should have at least 1 items'
- name: Should reject KubeStateMetricsConfig with duplicate resource names
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
resources:
- name: "cpu"
request: "100m"
- name: "cpu"
request: "200m"
expectedError: 'spec.kubeStateMetricsConfig.resources[1]: Duplicate value: map[string]interface {}{"name":"cpu"}'
- name: Should reject KubeStateMetricsConfig with duplicate topologySpreadConstraints
initial: |
apiVersion: config.openshift.io/v1alpha1
kind: ClusterMonitoring
spec:
kubeStateMetricsConfig:
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
- maxSkew: 2
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: DoNotSchedule
expectedError: "Duplicate value"
76 changes: 76 additions & 0 deletions config/v1alpha1/types_cluster_monitoring.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,6 +126,12 @@ type ClusterMonitoringSpec struct {
// When omitted, this means no opinion and the platform is left to choose a reasonable default, which is subject to change over time.
// +optional
OpenShiftStateMetricsConfig OpenShiftStateMetricsConfig `json:"openShiftStateMetricsConfig,omitempty,omitzero"`
// kubeStateMetricsConfig is an optional field that can be used to configure the kube-state-metrics
// agent that runs in the openshift-monitoring namespace. kube-state-metrics generates metrics about
// the state of Kubernetes objects such as Deployments, Nodes, and Pods.
// When omitted, this means no opinion and the platform is left to choose a reasonable default, which is subject to change over time.
// +optional
KubeStateMetricsConfig KubeStateMetricsConfig `json:"kubeStateMetricsConfig,omitempty,omitzero"`
}

// OpenShiftStateMetricsConfig provides configuration options for the openshift-state-metrics agent
Expand Down Expand Up @@ -1799,3 +1805,73 @@ type Audit struct {
// +required
Profile AuditProfile `json:"profile,omitempty"`
}

// KubeStateMetricsConfig provides configuration options for the kube-state-metrics agent
// that runs in the `openshift-monitoring` namespace. kube-state-metrics generates metrics
// about the state of Kubernetes objects such as Deployments, Nodes, and Pods.
// +kubebuilder:validation:MinProperties=1
type KubeStateMetricsConfig struct {
// nodeSelector defines the nodes on which the Pods are scheduled.
// nodeSelector is optional.
//
// When omitted, this means the user has no opinion and the platform is left
// to choose reasonable defaults. These defaults are subject to change over time.
// The current default value is `kubernetes.io/os: linux`.
// When specified, nodeSelector must contain at least 1 entry and must not contain more than 10 entries.
// +optional
// +kubebuilder:validation:MinProperties=1
// +kubebuilder:validation:MaxProperties=10
NodeSelector map[string]string `json:"nodeSelector,omitempty"`
// resources defines the compute resource requests and limits for the kube-state-metrics container.
// This includes CPU, memory and HugePages constraints to help control scheduling and resource usage.
// When not specified, defaults are used by the platform. Requests cannot exceed limits.
// This field is optional.
// More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/
// This is a simplified API that maps to Kubernetes ResourceRequirements.
// The current default values are:
// resources:
// - name: cpu
// request: 4m
// limit: null
// - name: memory
// request: 40Mi
// limit: null
// When specified, resources must contain at least 1 entry and must not contain more than 10 entries.
// Each resource name must be unique within this list.
// +optional
// +listType=map
// +listMapKey=name
// +kubebuilder:validation:MaxItems=10
// +kubebuilder:validation:MinItems=1
Resources []ContainerResource `json:"resources,omitempty"`
// tolerations defines tolerations for the pods.
// tolerations is optional.
//
// When omitted, this means the user has no opinion and the platform is left
// to choose reasonable defaults. These defaults are subject to change over time.
// Defaults are empty/unset.
// When specified, tolerations must contain at least 1 entry and must not contain more than 10 entries.
// +kubebuilder:validation:MaxItems=10
// +kubebuilder:validation:MinItems=1
// +listType=atomic
// +optional
Tolerations []v1.Toleration `json:"tolerations,omitempty"`
// topologySpreadConstraints defines rules for how kube-state-metrics Pods should be distributed
// across topology domains such as zones, nodes, or other user-defined labels.
// topologySpreadConstraints is optional.
// This helps improve high availability and resource efficiency by avoiding placing
// too many replicas in the same failure domain.
//
// When omitted, this means no opinion and the platform is left to choose a default, which is subject to change over time.
// This field maps directly to the `topologySpreadConstraints` field in the Pod spec.
// Defaults are empty/unset.
// When specified, topologySpreadConstraints must contain at least 1 entry and must not contain more than 10 entries.
// Entries must have unique topologyKey and whenUnsatisfiable pairs.
// +kubebuilder:validation:MaxItems=10
// +kubebuilder:validation:MinItems=1
// +listType=map
// +listMapKey=topologyKey
// +listMapKey=whenUnsatisfiable
// +optional
TopologySpreadConstraints []v1.TopologySpreadConstraint `json:"topologySpreadConstraints,omitempty"`
}
Loading