[root@vm-local1 prometheus-2.2.0.linux-amd64]# cat 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.评估间隔# scrape_timeout is set to the global default (10s). 默认抓取超时10秒# Alertmanager configuration #管理报警配置
alerting:alertmanagers:- static_configs:- targets: ["localhost:9093"]  #管理报警包需要单独下载，默认启动端口是9093# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:# - "first_rules.yml"# - "second_rules.yml"- rules/mengyuan.rules     #要发送报警，就得写规则，定义规则文件# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:    #抓取配置，就是你要抓取那些主机# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.- job_name: 'prometheus'  #任务名称# metrics_path defaults to '/metrics'  #默认抓取监控机的url后缀地址是/metrics# scheme defaults to 'http'.   #模式是httpstatic_configs:- targets: ['localhost:9090','localhost:9100']labels:group: 'zus'    #targets就是要抓取的主机，对应的客户端，我这有两个，把它们俩规定为一个组，组名是zus- job_name: dj   #又建立个任务名称static_configs:- targets: ['localhost:8000']  #我用django自定义的客户端

def metrics(req):ss = "feiji 32" + "\n" + "caidian 31"return HttpResponse(ss)

[root@vm-local1 rules]# cat mengyuan.rules
groups:
- name: zusrules:# Alert for any instance that is unreachable for >5 minutes.- alert: InstanceDown   #报警名字随便写expr: up == 0   #这是一个表达式，如果主机up状态为0,表示关机了，条件为真就会触发报警 可以通过$value得到值for: 5s         #5s内，还是0，就发送报警信息，当然是发送给报警管理器labels:severity: page  #这个类型的报警定了个标签annotations:summary: "Instance {{ $labels.instance }} down dangqian  {{ $value }}"description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."

[root@vm-local1 alertmanager-0.15.0-rc.1.linux-amd64]# cat alertmanager.yml
route:receiver: mengyuan2  #接收的名字，默认必须有一个，对应receivers的- namegroup_wait: 1s  #等待1sgroup_interval: 1s #发送间隔1srepeat_interval: 1m  #重复发送等待1m分钟再发group_by: ["zus"]   routes:      #路由了，匹配规则标签的severity:page 走 receiver: mengyuan , 如果routes不写，就会走默认的mengyuan2- receiver: mengyuan  match:severity: pagereceivers:
- name: 'mengyuan'webhook_configs:  #这我用的webhook_configs 钩子方法,  默认会把规则的报警信息发送到127.0.0.1:8000- url: http://127.0.0.1:8000send_resolved: true
- name: 'mengyuan2'webhook_configs:- url: http://127.0.0.1:8000/2send_resolved: true