PROMETHEUS.YAML

cat /etc/prometheus/prometheus.yml
root@master1:~# cat /etc/prometheus/prometheus.yml
# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:   ['localhost:9093'] 

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
   - "alerts.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["127.0.0.1:9090"]
       # The label name is added as a label `label_name=<label_value>` to any timeseries scraped from this config.
        labels:
          app: "prometheus"

  # Node Exporter
#  - job_name: 'node_exporter'
 #   static_configs:
  #    - targets: ["localhost:9100"]
   #     labels:
    #      app: "node_exporter"


  - job_name: 'node_exporter'
    static_configs:
      - targets:
          - "192.168.31.67:9100"     # master1
          - "192.168.122.151:9100"   # master2
          - "192.168.122.198:9100"   # master3
          - "192.168.122.155:9100"   # worker2
          - "192.168.122.232:9100"   # worker1
        labels:
          app: "node_exporter"


  - job_name: "alertmanager"
    static_configs:
      - targets: ["localhost:9093"]

  - job_name: "jenkins"
    metrics_path: /prometheus
    static_configs:
      - targets: ["localhost:8080"]

  - job_name: 'mlflow-metrics'
    static_configs:
      - targets: ['localhost:9105']


###########################################################



  - job_name: 'kube-state-metrics'
    metrics_path: /metrics
    static_configs:
      - targets:
          - 192.168.31.67:30080

###########################################


  - job_name: 'kubelet-worker2'
    scheme: https
    metrics_path: /metrics
    static_configs:
      - targets:
          - 192.168.31.67:10250
    tls_config:
      insecure_skip_verify: true


#  - job_name: 'mlflow-server'
#    metrics_path: /metrics
#    static_configs:
#      - targets: ['localhost:5000']
root@master1:~# 

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

root@master1:~# cat /etc/alertmanager/alertmanager.yml
global:
  smtp_smarthost: 'smtp.gmail.com:587'
  smtp_from: 'aanjireddy2024@gmail.com'
  smtp_auth_username: 'aanjireddy2024@gmail.com'
  smtp_auth_password: 'eaorjy'
  smtp_require_tls: true

route:
  receiver: 'email-alert'
  group_wait: 10s
  group_interval: 30s
  repeat_interval: 1h

receivers:
- name: 'email-alert'
  email_configs:
  - to: 'aanjireddy2024@gmail.com'
    send_resolved: true
root@master1:~# 
root@master1:~# 

root@master1:~# 
root@master1:~# cat /etc/kubernetes/manifests/etcd.yaml 
apiVersion: v1
kind: Pod
metadata:
  annotations:
    kubeadm.kubernetes.io/etcd.advertise-client-urls: https://192.168.31.67:2379
  creationTimestamp: null
  labels:
    component: etcd
    tier: control-plane
  name: etcd
  namespace: kube-system
spec:
  containers:
  - command:
    - etcd
    - --advertise-client-urls=https://192.168.31.67:2379
    - --cert-file=/etc/kubernetes/pki/etcd/server.crt
    - --client-cert-auth=true
    - --data-dir=/var/lib/etcd
    - --experimental-initial-corrupt-check=true
    - --experimental-watch-progress-notify-interval=5s
    - --initial-advertise-peer-urls=https://192.168.31.67:2380
    - --initial-cluster=master1=https://192.168.31.67:2380
    - --key-file=/etc/kubernetes/pki/etcd/server.key
    - --listen-client-urls=https://127.0.0.1:2379,https://192.168.31.67:2379
    - --listen-metrics-urls=http://127.0.0.1:2381
    - --listen-peer-urls=https://192.168.31.67:2380
    - --name=master1
    - --peer-cert-file=/etc/kubernetes/pki/etcd/peer.crt
    - --peer-client-cert-auth=true
    - --peer-key-file=/etc/kubernetes/pki/etcd/peer.key
    - --peer-trusted-ca-file=/etc/kubernetes/pki/etcd/ca.crt
    - --snapshot-count=10000
    - --trusted-ca-file=/etc/kubernetes/pki/etcd/ca.crt
    image: registry.k8s.io/etcd:3.5.24-0
    imagePullPolicy: IfNotPresent
    livenessProbe:
      failureThreshold: 8
      httpGet:
        host: 127.0.0.1
        path: /livez
        port: 2381
        scheme: HTTP
      initialDelaySeconds: 10
      periodSeconds: 10
      timeoutSeconds: 15
    name: etcd
    readinessProbe:
      failureThreshold: 3
      httpGet:
        host: 127.0.0.1
        path: /readyz
        port: 2381
        scheme: HTTP
      periodSeconds: 1
      timeoutSeconds: 15
    resources:
      requests:
        cpu: 100m
        memory: 100Mi
    startupProbe:
      failureThreshold: 24
      httpGet:
        host: 127.0.0.1
        path: /readyz
        port: 2381
        scheme: HTTP
      initialDelaySeconds: 10
      periodSeconds: 10
      timeoutSeconds: 15
    volumeMounts:
    - mountPath: /var/lib/etcd
      name: etcd-data
    - mountPath: /etc/kubernetes/pki/etcd
      name: etcd-certs
  hostNetwork: true
  priority: 2000001000
  priorityClassName: system-node-critical
  securityContext:
    seccompProfile:
      type: RuntimeDefault
  volumes:
  - hostPath:
      path: /etc/kubernetes/pki/etcd
      type: DirectoryOrCreate
    name: etcd-certs
  - hostPath:
      path: /var/lib/etcd
      type: DirectoryOrCreate
    name: etcd-data
Backup Prometheus config