logstash 字符串转换

匿名 | 发布于2018年06月07日 | 阅读数：11078

logstash 这块还需要继续优化下：
request_time， upstream_response_time 等的数据类型需要改为float或者double，
以及 status 为int等等，目前默认是string的，
从而无法在kibana上按照histogram或者 average等维度查看请求的状态分布、延迟分布等信息。

日志格式是文本格式，目前logstash是这样写的。
"message" =>"%{IPV4:remote_addr} - (%{USERNAME:user}|-) \[%{HTTPDATE:nginx_timestamp}\] %{NUMBER:http_status_code} %{BASE10NUM:bytes_sent:int} %{BASE16FLOAT:request_time} (%{BASE16FLOAT:upstream_response_time}|-) %{WORD:scheme} %{HOSTNAME:domain} \"%{WORD:verb} (?<request>\S+) HTTP/%{NUMBER:httpversion}\" \"(?<http_referer>\S+)\" \"(?<http_user_agent>(\S+\s+)*\S+)\" \"(?<http_x_forwarded_for>(\S+\s+)*\S+)\" \"(?<http_pinpoint_traceid>\S+)\""

4 个回复

auroracxy

赞同来自: fantaigan 、duffy 、caogx

我给你一个我现成的配置，按需修改吧：
nginx部分配置直接用json，省去很多麻烦，注意里面有request_body, 所有后面logstash有一些转义的配置，如果不需要直接把它删了吧

    log_format json '{"@timestamp":"$time_iso8601",'

                     '"server_addr":"$server_addr",'

                     '"remote_addr":"$remote_addr",'

                     '"cookie_JSESSIONID":"$cookie_JSESSIONID",'

                     '"body_bytes_sent":$body_bytes_sent,'

                     '"request_uri":"$request_uri",'

                     '"request_method":"$request_method",'

                     '"server_protocol":"$server_protocol",'

                     '"scheme":"$scheme",'

                     '"request_time":$request_time,'

                     '"upstream_response_time":"$upstream_response_time",'

                     '"upstream_addr":"$upstream_addr",'

                     '"host":"$host",'

                     '"hostname":"$hostname",'

                     '"http_host":"$http_host",'

                     '"uri":"$uri",'

                     '"http_x_forwarded_for":"$http_x_forwarded_for",'

                     '"http_referer":"$http_referer",'

                     '"http_user_agent":"$http_user_agent",'

                     '"X-Forwarded-Proto":"$http_x_forwarded_proto",'

                     '"request_body":"$request_body",'

                     '"status":"$status"}';



    access_log  /var/log/nginx/access.json.log  json;

filebeat配置部分：

filebeat.prospectors:

- input_type: log

  paths:

    - /var/log/nginx/access.json.log

  document_type: nginx_access_log

  ignore_older: 0

  tail_files: true

  symlinks: true

  close_removed: true

  clean_removed: true



output.logstash:

  # Boolean flag to enable or disable the output module.

  enabled: true



  # The Logstash hosts

  hosts: ["log-collection.internal.xxx.com:5517"]

logstah配置部分：

input {

  beats {

    port => 5517

  }

}

filter {

  if [type] == "nginx_access_log" {

    mutate {

      gsub => ["message", "\\x", "\\\x"]

    }

    json {

      source => "message"

    }

    mutate {

      remove_field => [ "message" ]

    }

    if "HEAD" in [request_method] or "x.x.x.x" in [remote_addr] or "x.x.x.x" in [http_x_forwarded_for] {

      drop {}

    }



    useragent {

      source => "http_user_agent"

      target => "ua"

    }



    if "-" in [upstream_response_time] {

      mutate {

        replace => {

          "upstream_response_time" => "0"

        }

      }

    }



    mutate {

      convert => [ "upstream_response_time", "float" ]

    }



    if "," in [http_x_forwarded_for] {

      mutate {

        add_field => { "[@metadata][user_ip_list]" => "%{http_x_forwarded_for}" }

      }

      mutate {

        split => { "[@metadata][user_ip_list]" => ", " }

        add_field => { "[@metadata][user_ip]" => "%{[@metadata][user_ip_list][0]}" }

      }

      geoip {

        source => "[@metadata][user_ip]"

        database => "/logstash/config/GeoLite2-City.mmdb"

        target => "geoip"

      }

    } else {

      geoip {

        source => "http_x_forwarded_for"

        database => "/logstash/config/GeoLite2-City.mmdb"

        target => "geoip"

      }

    }

    mutate {

      gsub => [

        "request_body", "\\x22", '"'

      ]

      gsub => [

        "request_body", "\\x0A", "\n"

      ]

    }

  }

 }

 

 output{

   if [type] == "nginx_access_log" {

    elasticsearch {

      hosts => ["",""]

      index => "nginxlog-%{+YYYY}"

      template => "/home/test/template_nginxlog.json"

      template_name => "nginxlog"

      template_overwrite => true

    }

  }

 }