Linux----------ELK进阶使用logstash（二）

一、logstash简介
二、logstash.conf

ELK官网：https://www.elastic.co

一、logstash简介

Logstash是一个开源数据收集引擎，具有实时管道功能。Logstash可以动态地将来自不同数据源的数据统一起来，并将数据标准化到你所选择的目的地。
Logstash 能够动态地采集、转换和传输数据，不受格式或复杂度的影响。利用 Grok 从非结构化数据中派生出结构，从 IP 地址解码出地理坐标，匿名化或排除敏感字段，并简化整体处理过程。
Logstash有三个主要模块input输入、filter过滤器、output输出。

1.1 input输入

输入：采集各种样式、大小和来源的数据

数据往往以各种各样的形式，或分散或集中地存在于很多系统中。Logstash 支持各种输入选择，可以在同一时间从众多常用来源捕捉事件。能够以连续的流式传输方式，轻松地从您的日志、指标、Web 应用、数据存储以及各种 AWS 服务采集数据。

1.2 filter过滤器

过滤器：实时解析和转换数据

数据从源传输到存储库的过程中，Logstash 过滤器能够解析各个事件，识别已命名的字段以构建结构，并将它们转换成通用格式，以便更轻松、更快速地分析和实现商业价值。

利用 Grok 从非结构化数据中派生出结构
从 IP 地址破译出地理坐标
将 PII 数据匿名化，完全排除敏感字段
简化整体处理，不受数据源、格式或架构的影响

1.3 output输出

输出：选择您的存储库，导出您的数据，Elasticsearch是首选

尽管 Elasticsearch 是我们的首选输出方向，能够为我们的搜索和分析带来无限可能，但它并非唯一选择。
Logstash 提供众多输出选择，您可以将数据发送到您要指定的地方，并且能够灵活地解锁众多下游用例。

二、logstash.conf

logstasg将模块input输入、filter过滤器、output输出写入到自建的logstash.conf来生成json字段保存到Elasticsearch中。以下有几个ELK官网模板借鉴

官网模板：https://www.elastic.co/guide/en/logstash/current/logstash-config-for-filebeat-modules.html

2.1 logstash之Apache日志模板

logstash之Apache日志模板

input {
  beats {
    port => 5044
    host => "0.0.0.0"
  }
}
filter {
  if [fileset][module] == "apache2" {
    if [fileset][name] == "access" {
      grok {
        match => { "message" => ["%{IPORHOST:[apache2][access][remote_ip]} - %{DATA:[apache2][access][user_name]} \[%{HTTPDATE:[apache2][access][time]}\] \"%{WORD:[apache2][access][method]} %{DATA:[apache2][access][url]} HTTP/%{NUMBER:[apache2][access][http_version]}\" %{NUMBER:[apache2][access][response_code]} %{NUMBER:[apache2][access][body_sent][bytes]}( \"%{DATA:[apache2][access][referrer]}\")?( \"%{DATA:[apache2][access][agent]}\")?",
          "%{IPORHOST:[apache2][access][remote_ip]} - %{DATA:[apache2][access][user_name]} \\[%{HTTPDATE:[apache2][access][time]}\\] \"-\" %{NUMBER:[apache2][access][response_code]} -" ] }
        remove_field => "message"
      }
      mutate {
        add_field => { "read_timestamp" => "%{@timestamp}" }
      }
      date {
        match => [ "[apache2][access][time]", "dd/MMM/YYYY:H:m:s Z" ]
        remove_field => "[apache2][access][time]"
      }
      useragent {
        source => "[apache2][access][agent]"
        target => "[apache2][access][user_agent]"
        remove_field => "[apache2][access][agent]"
      }
      geoip {
        source => "[apache2][access][remote_ip]"
        target => "[apache2][access][geoip]"
      }
    }
    else if [fileset][name] == "error" {
      grok {
        match => { "message" => ["\[%{APACHE_TIME:[apache2][error][timestamp]}\] \[%{LOGLEVEL:[apache2][error][level]}\]( \[client %{IPORHOST:[apache2][error][client]}\])? %{GREEDYDATA:[apache2][error][message]}",
          "\[%{APACHE_TIME:[apache2][error][timestamp]}\] \[%{DATA:[apache2][error][module]}:%{LOGLEVEL:[apache2][error][level]}\] \[pid %{NUMBER:[apache2][error][pid]}(:tid %{NUMBER:[apache2][error][tid]})?\]( \[client %{IPORHOST:[apache2][error][client]}\])? %{GREEDYDATA:[apache2][error][message1]}" ] }
        pattern_definitions => {
          "APACHE_TIME" => "%{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{YEAR}"
        }
        remove_field => "message"
      }
      mutate {
        rename => { "[apache2][error][message1]" => "[apache2][error][message]" }
      }
      date {
        match => [ "[apache2][error][timestamp]", "EEE MMM dd H:m:s YYYY", "EEE MMM dd H:m:s.SSSSSS YYYY" ]
        remove_field => "[apache2][error][timestamp]"
      }
    }
  }
}
output {
  elasticsearch {
    hosts => localhost
    manage_template => false
    index => "%{[@metadata][beat]}-%{[@metadata][version]}-%{+YYYY.MM.dd}"
  }
}

2.2 logstash之nginx日志模板

logstash之nginx日志模板

input {
  beats {
    port => 5044
    host => "0.0.0.0"
  }
}
filter {
  if [fileset][module] == "nginx" {
    if [fileset][name] == "access" {
      grok {
        match => { "message" => ["%{IPORHOST:[nginx][access][remote_ip]} - %{DATA:[nginx][access][user_name]} \[%{HTTPDATE:[nginx][access][time]}\] \"%{WORD:[nginx][access][method]} %{DATA:[nginx][access][url]} HTTP/%{NUMBER:[nginx][access][http_version]}\" %{NUMBER:[nginx][access][response_code]} %{NUMBER:[nginx][access][body_sent][bytes]} \"%{DATA:[nginx][access][referrer]}\" \"%{DATA:[nginx][access][agent]}\""] }
        remove_field => "message"
      }
      mutate {
        add_field => { "read_timestamp" => "%{@timestamp}" }
      }
      date {
        match => [ "[nginx][access][time]", "dd/MMM/YYYY:H:m:s Z" ]
        remove_field => "[nginx][access][time]"
      }
      useragent {
        source => "[nginx][access][agent]"
        target => "[nginx][access][user_agent]"
        remove_field => "[nginx][access][agent]"
      }
      geoip {
        source => "[nginx][access][remote_ip]"
        target => "[nginx][access][geoip]"
      }
    }
    else if [fileset][name] == "error" {
      grok {
        match => { "message" => ["%{DATA:[nginx][error][time]} \[%{DATA:[nginx][error][level]}\] %{NUMBER:[nginx][error][pid]}#%{NUMBER:[nginx][error][tid]}: (\*%{NUMBER:[nginx][error][connection_id]} )?%{GREEDYDATA:[nginx][error][message]}"] }
        remove_field => "message"
      }
      mutate {
        rename => { "@timestamp" => "read_timestamp" }
      }
      date {
        match => [ "[nginx][error][time]", "YYYY/MM/dd H:m:s" ]
        remove_field => "[nginx][error][time]"
      }
    }
  }
}
output {
  elasticsearch {
    hosts => localhost
    manage_template => false
    index => "%{[@metadata][beat]}-%{[@metadata][version]}-%{+YYYY.MM.dd}"
  }
}

2.3 logstash之mysql日志模板

logstash之mysql日志模板

input {
  beats {
    port => 5044
    host => "0.0.0.0"
  }
}
filter {
  if [fileset][module] == "mysql" {
    if [fileset][name] == "error" {
      grok {
        match => { "message" => ["%{LOCALDATETIME:[mysql][error][timestamp]} (\[%{DATA:[mysql][error][level]}\] )?%{GREEDYDATA:[mysql][error][message]}",
          "%{TIMESTAMP_ISO8601:[mysql][error][timestamp]} %{NUMBER:[mysql][error][thread_id]} \[%{DATA:[mysql][error][level]}\] %{GREEDYDATA:[mysql][error][message1]}",
          "%{GREEDYDATA:[mysql][error][message2]}"] }
        pattern_definitions => {
          "LOCALDATETIME" => "[0-9]+ %{TIME}"
        }
        remove_field => "message"
      }
      mutate {
        rename => { "[mysql][error][message1]" => "[mysql][error][message]" }
      }
      mutate {
        rename => { "[mysql][error][message2]" => "[mysql][error][message]" }
      }
      date {
        match => [ "[mysql][error][timestamp]", "ISO8601", "YYMMdd H:m:s" ]
        remove_field => "[mysql][error][time]"
      }
    }
    else if [fileset][name] == "slowlog" {
      grok {
        match => { "message" => ["^# User@Host: %{USER:[mysql][slowlog][user]}(\[[^\]]+\])? @ %{HOSTNAME:[mysql][slowlog][host]} \[(IP:[mysql][slowlog][ip])?\](\s*Id:\s* %{NUMBER:[mysql][slowlog][id]})?\n# Query_time: %{NUMBER:[mysql][slowlog][query_time][sec]}\s* Lock_time: %{NUMBER:[mysql][slowlog][lock_time][sec]}\s* Rows_sent: %{NUMBER:[mysql][slowlog][rows_sent]}\s* Rows_examined: %{NUMBER:[mysql][slowlog][rows_examined]}\n(SET timestamp=%{NUMBER:[mysql][slowlog][timestamp]};\n)?%{GREEDYMULTILINE:[mysql][slowlog][query]}"] }
        pattern_definitions => {
          "GREEDYMULTILINE" => "(.|\n)*"
        }
        remove_field => "message"
      }
      date {
        match => [ "[mysql][slowlog][timestamp]", "UNIX" ]
      }
      mutate {
        gsub => ["[mysql][slowlog][query]", "\n# Time: [0-9]+ [0-9][0-9]:[0-9][0-9]:[0-9][0-9](\\.[0-9]+)?$", ""]
      }
    }
  }
}
output {
  elasticsearch {
    hosts => localhost
    manage_template => false
    index => "%{[@metadata][beat]}-%{[@metadata][version]}-%{+YYYY.MM.dd}"
  }
}

2.4 logstash之系统日志模板

logstash之system日志模板

input {
  beats {
    port => 5044
    host => "0.0.0.0"
  }
}
filter {
  if [fileset][module] == "system" {
    if [fileset][name] == "auth" {
      grok {
        match => { "message" => ["%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} sshd(?:\[%{POSINT:[system][auth][pid]}\])?: %{DATA:[system][auth][ssh][event]} %{DATA:[system][auth][ssh][method]} for (invalid user )?%{DATA:[system][auth][user]} from %{IPORHOST:[system][auth][ssh][ip]} port %{NUMBER:[system][auth][ssh][port]} ssh2(: %{GREEDYDATA:[system][auth][ssh][signature]})?",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} sshd(?:\[%{POSINT:[system][auth][pid]}\])?: %{DATA:[system][auth][ssh][event]} user %{DATA:[system][auth][user]} from %{IPORHOST:[system][auth][ssh][ip]}",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} sshd(?:\[%{POSINT:[system][auth][pid]}\])?: Did not receive identification string from %{IPORHOST:[system][auth][ssh][dropped_ip]}",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} sudo(?:\[%{POSINT:[system][auth][pid]}\])?: \s*%{DATA:[system][auth][user]} :( %{DATA:[system][auth][sudo][error]} ;)? TTY=%{DATA:[system][auth][sudo][tty]} ; PWD=%{DATA:[system][auth][sudo][pwd]} ; USER=%{DATA:[system][auth][sudo][user]} ; COMMAND=%{GREEDYDATA:[system][auth][sudo][command]}",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} groupadd(?:\[%{POSINT:[system][auth][pid]}\])?: new group: name=%{DATA:system.auth.groupadd.name}, GID=%{NUMBER:system.auth.groupadd.gid}",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} useradd(?:\[%{POSINT:[system][auth][pid]}\])?: new user: name=%{DATA:[system][auth][useradd][name]}, UID=%{NUMBER:[system][auth][useradd][uid]}, GID=%{NUMBER:[system][auth][useradd][gid]}, home=%{DATA:[system][auth][useradd][home]}, shell=%{DATA:[system][auth][useradd][shell]}$",
                  "%{SYSLOGTIMESTAMP:[system][auth][timestamp]} %{SYSLOGHOST:[system][auth][hostname]} %{DATA:[system][auth][program]}(?:\[%{POSINT:[system][auth][pid]}\])?: %{GREEDYMULTILINE:[system][auth][message]}"] }
        pattern_definitions => {
          "GREEDYMULTILINE"=> "(.|\n)*"
        }
        remove_field => "message"
      }
      date {
        match => [ "[system][auth][timestamp]", "MMM  d HH:mm:ss", "MMM dd HH:mm:ss" ]
      }
      geoip {
        source => "[system][auth][ssh][ip]"
        target => "[system][auth][ssh][geoip]"
      }
    }
    else if [fileset][name] == "syslog" {
      grok {
        match => { "message" => ["%{SYSLOGTIMESTAMP:[system][syslog][timestamp]} %{SYSLOGHOST:[system][syslog][hostname]} %{DATA:[system][syslog][program]}(?:\[%{POSINT:[system][syslog][pid]}\])?: %{GREEDYMULTILINE:[system][syslog][message]}"] }
        pattern_definitions => { "GREEDYMULTILINE" => "(.|\n)*" }
        remove_field => "message"
      }
      date {
        match => [ "[system][syslog][timestamp]", "MMM  d HH:mm:ss", "MMM dd HH:mm:ss" ]
      }
    }
  }
}
output {
  elasticsearch {
    hosts => localhost
    manage_template => false
    index => "%{[@metadata][beat]}-%{[@metadata][version]}-%{+YYYY.MM.dd}"
  }
}

posted @ 2020-01-02 11:50 A学无止境A 阅读(377) 评论(0) 编辑收藏举报

会员力量，点亮园子希望

刷新页面返回顶部

A学无止境A

部分文档借鉴马哥教育