Merge pull request #334 from 3dwardch3ng/infra/prometheus

add infra app prometheus
This commit is contained in:
2024-06-26 14:41:38 +10:00
committed by GitHub
8 changed files with 287 additions and 0 deletions

View File

@@ -8,4 +8,5 @@ resources:
- ./ingress-nginx/ingress-nginx-config.yaml
- ./namespaces/namespaces.yaml
- ./postgresql/postgresql.yaml
- ./prometheus/prometheus.yaml
- ./repositories/repositories.yaml

View File

@@ -0,0 +1,4 @@
apiVersion: v1
kind: Namespace
metadata:
name: prometheus

View File

@@ -0,0 +1,47 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: prometheus
namespace: prometheus
labels:
app: prometheus
spec:
replicas: 1
selector:
matchLabels:
app: prometheus
template:
metadata:
labels:
app: prometheus
spec:
containers:
- name: prometheus
image: prom/prometheus
args:
- "--storage.tsdb.retention.time=12h"
- "--config.file=/etc/prometheus/prometheus.yml"
- "--storage.tsdb.path=/prometheus/"
ports:
- containerPort: 9999
resources:
requests:
cpu: 500m
memory: 500M
limits:
cpu: 1
memory: 1Gi
volumeMounts:
- name: prometheus-config-volume
mountPath: /etc/prometheus/
- name: prometheus-storage-volume
mountPath: /prometheus/
volumes:
- name: prometheus-config-volume
configMap:
defaultMode: 420
name: prometheus-server-conf
- name: prometheus-storage-volume
hostPath:
path: /mnt/nfs/AppData/prometheus
type: Directory

View File

@@ -0,0 +1,31 @@
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: capacitor-ingress
namespace: capacitor
annotations:
nginx.ingress.kubernetes.io/ssl-redirect: "false"
nginx.ingress.kubernetes.io/use-regex: "true"
spec:
ingressClassName: nginx
rules:
- host: "prometheus.cluster.edward.sydney"
http:
paths:
- pathType: Prefix
path: "/"
backend:
service:
name: prometheus
port:
number: 30999
- host: "prometheus.cluster.local"
http:
paths:
- pathType: Prefix
path: "/"
backend:
service:
name: prometheus
port:
number: 30999

View File

@@ -0,0 +1,137 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-server-conf
labels:
name: prometheus-server-conf
namespace: prometheus
data:
prometheus.rules: |-
groups:
- name: rpi5 cluster alert
rules:
- alert: High Pod Memory
expr: sum(container_memory_usage_bytes) > 1
for: 1m
labels:
severity: slack
annotations:
summary: High Memory Usage
prometheus.yml: |-
global:
scrape_interval: 5s
evaluation_interval: 5s
rule_files:
- /etc/prometheus/prometheus.rules
alerting:
alertmanagers:
- scheme: http
static_configs:
- targets:
- "alertmanager.monitoring.svc:9093"
scrape_configs:
- job_name: 'node-exporter'
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_endpoints_name]
regex: 'node-exporter'
action: keep
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
- job_name: 'kubernetes-nodes'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics
- job_name: 'kubernetes-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
- job_name: 'kube-state-metrics'
static_configs:
- targets: ['kube-state-metrics.kube-system.svc.cluster.local:8080']
- job_name: 'kubernetes-cadvisor'
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
kubernetes_sd_configs:
- role: node
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_label_(.+)
- target_label: __address__
replacement: kubernetes.default.svc:443
- source_labels: [__meta_kubernetes_node_name]
regex: (.+)
target_label: __metrics_path__
replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
- job_name: 'kubernetes-service-endpoints'
kubernetes_sd_configs:
- role: endpoints
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
action: keep
regex: true
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
action: replace
target_label: __scheme__
regex: (https?)
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
action: replace
target_label: __address__
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: kubernetes_name

View File

@@ -0,0 +1,33 @@
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: prometheus
rules:
- apiGroups: [""]
resources:
- nodes
- nodes/proxy
- services
- endpoints
- pods
verbs: ["get", "list", "watch"]
- apiGroups:
- extensions
resources:
- ingresses
verbs: ["get", "list", "watch"]
- nonResourceURLs: ["/metrics"]
verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: prometheus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: prometheus
subjects:
- kind: ServiceAccount
name: prometheus
namespace: prometheus

View File

@@ -0,0 +1,16 @@
apiVersion: v1
kind: Service
metadata:
name: prometheus
namespace: prometheus
annotations:
prometheus.io/scrape: 'true'
prometheus.io/port: '9999'
spec:
selector:
app: prometheus
type: NodePort
ports:
- port: 9999
targetPort: 9999
nodePort: 30999

View File

@@ -0,0 +1,18 @@
apiVersion: kustomize.toolkit.fluxcd.io/v1
kind: Kustomization
metadata:
name: prometheus
namespace: prometheus
spec:
interval: 10m
timeout: 1m30s
retryInterval: 30s
path: ./kubernetes/infrastructure/prometheus/app
prune: true
sourceRef:
kind: GitRepository
namespace: flux-system
name: flux-system
dependsOn:
- name: namespaces
namespace: flux-system