记-Windows环境下Prometheus+alertmanager+windows_exporter+mtail监控部署提起网关日志

mtail -version

mtail version3.0.0-rc48 git revision e19766e45ca2dedf34794fea51444c7963a7c3d6 go version go1.17.5 go arch386 go os linux

nohup mtail -port8080 -logtostderr -progs /etc/mtail/access.mtail -logs /xxx/xxx.log &

#8080端口可以自定义，也可同时启动多个mtail监控多个日志文件。

counter apache_http_requests_total by request_method, http_version, status_code
counter apache_http_bytes_total by request_method, http_version, status_code
gauge apache_http_response_time by remote_host, request_method, request_uri, status_code
gauge apache_http_response_size by remote_host, request_method, request_uri, status_code
 
histogram apache_http_request_time_millseconds_bucket buckets0,1,2,4,8 by status_code/^/ +
/(?P<remote_host>[0-9A-Za-z\.:-]+) / + # %h/(?P<remote_logname>[0-9A-Za-z-]+) / + # %l/(?P<remote_username>[0-9A-Za-z-]+) / + # %u/\[(?P<timestamp>\d{2}\/\w{3}\/\d{4}:\d{2}:\d{2}:\d{2} (\+|-)\d{4})\] / + # %u/"(?P<request_method>[A-Z]+) (?P<request_uri>\S+) (?P<http_version>HTTP\/[0-9\.]+)" / + # \"%r\"
/(?P<status_code>\d{3}) / + # %>s/((?P<response_size>\d+)|-) / + # %b/(?P<response_time>\d+) / + # %D/"(?P<referer>\S+)" / + # \"%{Referer}i\"
/"(?P<user_agent>[[:print:]]+)"/ + # \"%{User-agent}i\"
/$/ {
  strptime($timestamp,"02/Jan/2006:15:04:05 -0700")
 
  apache_http_requests_total[$request_method][$http_version][$status_code]++
  $response_size>0 {
      apache_http_bytes_total[$request_method][$http_version][$status_code]+= $response_size
      apache_http_response_size[$remote_host][$request_method][$request_uri][$status_code]+= $response_size
  }
  apache_http_response_time[$remote_host][$request_method][$request_uri][$status_code]= $response_time
  apache_http_request_time_millseconds_bucket[$status_code]= $response_time
}
 
getfilename()!~ /access_log.?log/ {
  stop
}

counter media_request_total/receive http request path is/ {
  media_request_total++
}
#第一段代码是监控apache日志，第一阶段测试可用此段配置。

counter app_http_requests_total by uri, request_method,http_status#该段代码为获取网关（geteway）日志代码
gauge app_http_requests_time by uri, request_method, http_status

histogram app_http_request_time_millseconds_bucket buckets0,1,2,4,8 by uri, request_method, http_status/`"(?P<request_method>[A-Z]+) (?P<uri>[\/a-zA-Z0-9-_]+)(?:\??)(?:\S*) (?P<http_version>HTTP\/[0-9\.]+)"/ +
/`"(?P<http_user_agent>.+)"/ +
/`(?P<http_status>\d{3})/ +
/`(?P<remote_addr>/ +
/\[((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})(\.((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})){3}\])/ +
/`(?P<http_x_log_uid>\W+)/ +
/`"(?P<http_referer>\W+)"/ +
/`(?P<request_time>\d{1,}\.\d{3})/ +
/`(?P<body_bytes_sent>\d+)`/ +
/(?P<http_x_forwarded_for>\S+)/ +
/`(?P<http_host>((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})(\.((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})){3})/ +
/`(?P<domain>.+)/ +
/`(?P<http_cookie>.+)/ +
/`(?P<upstream_addr>\[((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})(\.((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})){3}:\d{4}\])/ +
/`(?P<upstream_response_time>(\d{1,}\.\d{3}))/ +
/`xd$/{/\/coco-server\/v1\/users\//{    
  }else {
    app_http_requests_total[$uri][$request_method][$http_status]++
    app_http_requests_time[$uri][$request_method][$http_status]= $request_time
    app_http_request_time_millseconds_bucket[$uri][$request_method][$http_status]= $request_time
  }
}

# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every15 seconds. Default is every1 minute.
  evaluation_interval: 15s # Evaluate rules every15 seconds. The default is every1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:- static_configs:- targets:- alertmanager:9093

# Load rules once and periodically evaluate them according to the global'evaluation_interval'.
rule_files:-"rules/*_rules.yml" 
    #告警规则yml文件
  #-"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: ["localhost:9090"]- job_name:"node_exporter"
    scrape_interval: 5s  
    #每五秒检查一次应用进程
    metrics_path:"/metrics"  
    #指标路径
    static_configs:- targets: ["localhost:9182"]- job_name:"alertmanager"
    scrape_interval: 5s

    static_configs:- targets: ["localhost:9093"]- job_name:"mtail"
    scrape_interval: 5s
 
    static_configs:- targets: ["xx.xx.xx.xx:8080"]

groups:- name: node-up    
# 分组名称
  rules:           # 规则设置- alert: node-up  
  #告警名称expr: up{job="windows_exporter"} ==0   
    # 表达式，查询式语句查询up的值是否等于0，如果等于则告警for: 15s   
    # 告警持续时间
    labels:
      severity:1
      team: node
    annotations:    # 注解
      summary:"{{ $labels.instance }} 已停止运行超过 15s！"

global:
  resolve_timeout: 5m
  smtp_smarthost:'smtp.qq.com:465'
  smtp_from:'xxxxxxxxx@qq.com'
  smtp_auth_username:'xxxxxxxxx@qq.com'
  smtp_auth_password:'xxxxxxxxx'    # 16位qq邮箱授权码作为密码
  smtp_require_tls:false

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver:'email'    # 选用邮箱告警发送

receivers:- name:'email'
  email_configs:- to:'xxxxxxxxx@qq.com'

inhibit_rules:- source_match:
      severity:'critical'
    target_match:
      severity:'warning'
    equal: ['alertname','dev','instance']