iamabhishek-dubey

global:
  # The smarthost and SMTP sender used for mail notifications.
  smtp_smarthost: 'localhost:25'
  smtp_from: 'alertmanager@example.org'
  smtp_auth_username: 'alertmanager'
  smtp_auth_password: 'password'
  # The auth token for Hipchat.
  hipchat_auth_token: '1234556789'
  # Alternative host for Hipchat.
  hipchat_api_url: 'https://hipchat.foobar.org/'

iamabhishek-dubey

scrape_configs:
  - job_name: "node"
    scrape_interval: "15s"
    static_configs:
    - targets: ['localhost:9100']
    - targets: ['192.168.2.10:9117']
    - targets: ['192.168.2.10:9104']
    - targets: ['192.168.2.25:9115'] # Target to probe with http on port 8   

  - job_name: "haproxy_exporter"

iamabhishek-dubey

global:                                                                                                                                                             
  scrape_interval:     30s # Default is every 1 minute.                                                                                                             
  evaluation_interval: 60s # The default is every 1 minute.                                                                                                         
  scrape_timeout: 10s      # global default is 10s                                                                                                                  
                                                                                                                                                                    
  # Attach these labels to any time series or alerts when communicating with                                                                                        
  # external systems (federation, 

iamabhishek-dubey

groups:                                                                                                                                                             
- name: cluster-rules                                                                                                                                               
  interval: 30s # defaults to global interval testing threshold                                                                                                     
  rules:                                                                                                                                                            
  - alert: os_cluster_memory_low                                                                                                                                    
    expr: sum (container_memory_working_set_bytes{id="/"}) / sum (machine_memory_bytes{}) *100 > 70                                                                 
    for: 10m                      

iamabhishek-dubey

{
  "annotations": {
    "list": []
  },
  "description": "HAproxy backend servers",
  "editable": true,
  "gnetId": 2428,
  "graphTooltip": 1,
  "hideControls": false,
  "id": 61,

iamabhishek-dubey

{
    "annotations": {
      "list": []
    },
    "description": "HAproxy backend servers",
    "editable": true,
    "gnetId": 2428,
    "graphTooltip": 1,
    "hideControls": false,
    "id": 61,

iamabhishek-dubey

User Creation in Grafana with HTTP Api

curl -XPOST -H "Content-Type: application/json" -d '{
  "name":"User",
  "email":"user@graf.com",
  "login":"user",
 "password":"userpassword"

iamabhishek-dubey

Prometheus Rule File for Pod Failure

There are two rule files for Pod Failure of Openshift or Kubernetes in Prometheus

1. One is:-

- name: pod.rules
  rules:
  - alert: Pod is failed

iamabhishek-dubey

apiVersion: v1
data:
  prometheus.rules: |
    groups:
    - name: custom-rules
      rules:
      - alert: DBsDown
        expr: count((up{job="db-exporter"} == 0 )) > 0
        for: 2m
        labels:

iamabhishek-dubey

apiVersion: v1
data:
  config.yml: |-
    global:


    # The directory from which notification templates are read.
    templates:
    - '/etc/alertmanager/template/*.tmpl'