refactor(infra): restructure metrics collection infrastructure

Added new playbook `setup_metrics_server.yml` and standalone role `roles/metrics_server/` to centralize Kubernetes metrics server deployment and configuration, separating concerns from the main uyuni role for modularity and reuse.
This commit is contained in:
mrwho 2026-07-19 15:02:19 +03:00
parent b0a8b35dd9
commit 6e0200f64c
9 changed files with 480 additions and 0 deletions

View file

@ -0,0 +1,6 @@
---
- name: Deploy Kubernetes Metrics Server
hosts: manager_nodes
become: false
roles:
- metrics_server

View file

@ -0,0 +1,15 @@
---
metrics_server_namespace: kube-system
metrics_server_kubeconfig: "/home/{{ ansible_user }}/.kube/config"
metrics_server_chart_version: "3.12.0"
metrics_server_use_helm: true
metrics_server_args:
- --kubelet-insecure-tls
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --metric-resolution=15s
metrics_server_resources_requests_memory: "200Mi"
metrics_server_resources_requests_cpu: "100m"
metrics_server_resources_limits_memory: "500Mi"
metrics_server_resources_limits_cpu: "500m"

View file

@ -0,0 +1,199 @@
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:aggregated-metrics-reader
rules:
- apiGroups:
- metrics.k8s.io
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
rules:
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- pods
- nodes
- nodes/stats
- namespaces
- configmaps
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server-auth-reader
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server:system:auth-delegator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:auth-delegator
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
labels:
k8s-app: metrics-server
name: extension-apiserver-authentication-reader
namespace: kube-system
rules:
- apiGroups:
- ""
resources:
- configmaps
name: extension-apiserver-authentication
verbs:
- get
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: metrics-server
strategy:
rollingUpdate:
maxUnavailable: 0
template:
metadata:
labels:
k8s-app: metrics-server
spec:
containers:
- args:
- --kubelet-insecure-tls
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --metric-resolution=15s
image: registry.k8s.io/metrics-server/metrics-server:v0.7.2
imagePullPolicy: IfNotPresent
livenessProbe:
failureThreshold: 3
httpGet:
path: /livez
port: https
scheme: HTTPS
periodSeconds: 10
name: metrics-server
ports:
- containerPort: 4443
name: https
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /readyz
port: https
scheme: HTTPS
periodSeconds: 10
resources:
requests:
cpu: 100m
memory: 200Mi
limits:
cpu: 500m
memory: 500Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
volumeMounts:
- mountPath: /tmp
name: tmp-dir
nodeSelector:
kubernetes.io/os: linux
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
volumes:
- emptyDir: {}
name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
labels:
k8s-app: metrics-server
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io
groupPriorityMinimum: 100
insecureSkipTLSVerify: true
service:
name: metrics-server
namespace: kube-system
version: v1beta1
versionPriority: 100

View file

@ -0,0 +1,2 @@
---
dependencies: []

View file

@ -0,0 +1,30 @@
---
- name: Helm | Add metrics-server repository
ansible.builtin.command: helm repo add metrics-server https://kubernetes-sigs.github.io/metrics-server/
register: _helm_repo_add
changed_when: "'already exists' not in _helm_repo_add.stdout"
failed_when: _helm_repo_add.rc != 0 and 'already exists' not in _helm_repo_add.stdout
- name: Helm | Update repositories
ansible.builtin.command: helm repo update
changed_when: false
- name: Helm | Install or upgrade metrics-server
ansible.builtin.command: >
helm upgrade --install metrics-server metrics-server/metrics-server
--namespace {{ metrics_server_namespace }}
--create-namespace
--version {{ metrics_server_chart_version }}
--set args[0]=--kubelet-insecure-tls
--set args[1]=--metric-resolution=15s
--set resources.requests.cpu={{ metrics_server_resources_requests_cpu }}
--set resources.requests.memory={{ metrics_server_resources_requests_memory }}
--set resources.limits.cpu={{ metrics_server_resources_limits_cpu }}
--set resources.limits.memory={{ metrics_server_resources_limits_memory }}
--timeout 10m0s
--wait
environment:
KUBECONFIG: "{{ metrics_server_kubeconfig }}"
PATH: "/usr/local/bin:/usr/bin:/bin"
register: _helm_install
changed_when: "'STATUS: deployed' in _helm_install.stdout or 'has been upgraded' in _helm_install.stdout"

View file

@ -0,0 +1,8 @@
---
- name: Helm | Deploy metrics-server
ansible.builtin.include_tasks: helm.yml
when: metrics_server_use_helm | bool
- name: Manifest | Deploy metrics-server
ansible.builtin.include_tasks: manifest.yml
when: not metrics_server_use_helm | bool

View file

@ -0,0 +1,9 @@
---
- name: Manifest | Apply metrics-server
ansible.builtin.command: kubectl apply -f {{ role_path }}/files/metrics-server-manifest.yml
environment:
KUBECONFIG: "{{ metrics_server_kubeconfig }}"
PATH: "/usr/local/bin:/usr/bin:/bin"
register: _manifest_apply
changed_when: "'created' in _manifest_apply.stdout or 'configured' in _manifest_apply.stdout"
failed_when: _manifest_apply.rc != 0 and 'already exists' not in _manifest_apply.stderr

View file

@ -0,0 +1,199 @@
apiVersion: v1
kind: ServiceAccount
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:aggregated-metrics-reader
rules:
- apiGroups:
- metrics.k8s.io
resources:
- pods
- nodes
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
rules:
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- list
- watch
- apiGroups:
- ""
resources:
- pods
- nodes
- nodes/stats
- namespaces
- configmaps
verbs:
- get
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server-auth-reader
namespace: kube-system
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: metrics-server:system:auth-delegator
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:auth-delegator
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
labels:
k8s-app: metrics-server
name: system:metrics-server
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:metrics-server
subjects:
- kind: ServiceAccount
name: metrics-server
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
labels:
k8s-app: metrics-server
name: extension-apiserver-authentication-reader
namespace: kube-system
rules:
- apiGroups:
- ""
resources:
- configmaps
name: extension-apiserver-authentication
verbs:
- get
---
apiVersion: apps/v1
kind: Deployment
metadata:
labels:
k8s-app: metrics-server
name: metrics-server
namespace: kube-system
spec:
selector:
matchLabels:
k8s-app: metrics-server
strategy:
rollingUpdate:
maxUnavailable: 0
template:
metadata:
labels:
k8s-app: metrics-server
spec:
containers:
- args:
- --kubelet-insecure-tls
- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname
- --metric-resolution=15s
image: registry.k8s.io/metrics-server/metrics-server:v0.7.2
imagePullPolicy: IfNotPresent
livenessProbe:
failureThreshold: 3
httpGet:
path: /livez
port: https
scheme: HTTPS
periodSeconds: 10
name: metrics-server
ports:
- containerPort: 4443
name: https
protocol: TCP
readinessProbe:
failureThreshold: 3
httpGet:
path: /readyz
port: https
scheme: HTTPS
periodSeconds: 10
resources:
requests:
cpu: 100m
memory: 200Mi
limits:
cpu: 500m
memory: 500Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
volumeMounts:
- mountPath: /tmp
name: tmp-dir
nodeSelector:
kubernetes.io/os: linux
priorityClassName: system-cluster-critical
serviceAccountName: metrics-server
volumes:
- emptyDir: {}
name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:
labels:
k8s-app: metrics-server
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io
groupPriorityMinimum: 100
insecureSkipTLSVerify: true
service:
name: metrics-server
namespace: kube-system
version: v1beta1
versionPriority: 100

View file

@ -0,0 +1,12 @@
args:
{% for arg in metrics_server_args %}
- {{ arg }}
{% endfor %}
resources:
requests:
memory: {{ metrics_server_resources_requests_memory }}
cpu: {{ metrics_server_resources_requests_cpu }}
limits:
memory: {{ metrics_server_resources_limits_memory }}
cpu: {{ metrics_server_resources_limits_cpu }}