logstash使用grok正则解析日志和kibana遇到的问题

#Nginx日志格式定义

log_format  combine '$remote_addr - $remote_user [$time_local] "$request" $http_host ' 
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for" '
'$upstream_addr $upstream_status $upstream_cache_status "$upstream_http_content_type" $upstream_response_time > $request_time';


#日志内容

11.11.1.1 - - [01/Mar/2013:12:23:53 +0800] "GET /v1/api HTTP/1.1" api.xx.com 200 4003 "https://api.xx.com/v1/api" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0)" "-" 10.1.1.1:80 200 - "text/html;charset=UTF-8" 0.023 > 0.023

# GROK pattern

%{IPORHOST:client_ip} %{USER:ident} %{USER:auth} \[%{HTTPDATE:timestamp}\] "(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:http_version})?|-)" %{HOST:domain} %{NUMBER:response} (?:%{NUMBER:bytes}|-) %{QS:referrer} %{QS:agent} "(%{WORD:x_forword}|-)" (%{URIHOST:upstream_host}|-) %{NUMBER:upstream_response} (%{WORD:upstream_cache_status}|-) %{QS:upstream_content_type} (%{BASE16FLOAT:upstream_response_time}) > (%{BASE16FLOAT:request_time})

#GROK 在logstash里面的定义,双引号转义一下

filter {
  grep {
    match => [ "@message", "DNSPod-monitor|DNSPod-reporting|(Webluker NetWork Probe Agent)|JianKongBao" ]
    type => "nginx-access"
    negate=> true
  }
 
grok {
    type => "nginx-access"
    pattern => "%{IPORHOST:client_ip} %{USER:ident} %{USER:auth} \[%{HTTPDATE:timestamp}\] \"(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:http_version})?|-)\" %{HOST:domain} %{NUMBER:response} (?:%{NUMBER:bytes}|-) %{QS:referrer} %{QS:agent} \"(%{QS:x_forword}|-)\" (%{URIHOST:upstream_host}|-) %{NUMBER:upstream_response} (%{WORD:upstream_cache_status}|-) %{QS:upstream_content_type} (%{BASE16FLOAT:upstream_response_time}) > (%{BASE16FLOAT:request_time})"
  }
 
}

#GROK 内置pattern

https://github.com/ logstash /logstash/blob/v1.1.9/patterns/grok-patterns

#在线调试地址:

http://grokdebug.herokuapp.com/

{
  "client_ip": [
    [
      "11.11.1.1"
    ]
  ],
  "ident": [
    [
      "-"
    ]
  ],
  "auth": [
    [
      "-"
    ]
  ],
  "timestamp": [
    [
      "01/Mar/2013:12:23:53 +0800"
    ]
  ],
  "verb": [
    [
      "GET"
    ]
  ],
  "request": [
    [
      "/v1/api"
    ]
  ],
  "http_version": [
    [
      "1.1"
    ]
  ],
  "domain": [
    [
      "api.xx.com"
    ]
  ],
  "response": [
    [
      "200"
    ]
  ],
  "bytes": [
    [
      "4003"
    ]
  ],
  "referrer": [
    [
      "\"https://api.xx.com/v1/api\""
    ]
  ],
  "agent": [
    [
      "\"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0)\""
    ]
  ],
  "x_forword": [
    [
      null
    ]
  ],
  "upstream_host": [
    [
      "10.1.1.1:80"
    ]
  ],
  "port": [
    [
      "80"
    ]
  ],
  "upstream_response": [
    [
      "200"
    ]
  ],
  "upstream_cache_status": [
    [
      null
    ]
  ],
  "upstream_content_type": [
    [
      "\"text/html;charset=UTF-8\""
    ]
  ],
  "upstream_response_time": [
    [
      "0.023"
    ]
  ],
  "request_time": [
    [
      "0.023"
    ]
  ]
}

StatsD监控

statsd {
    host => "10.1.1.1"
    port => 8125
    increment => "nginx.response.%{response}"
    increment => "nginx.request.total"
    timing => ["nginx.request.time", "%{request_time}"]
    timing => ["nginx.upstream.response.time", "%{upstream_response_time}"]
  }

-------------------------------------

妈蛋呀,改用logstash的原因是因为,scribe 真心搞不定,其次就是产品经理需要我开发一个可自定义的panel图表系统。

因为长时间没搞elk方案, 都忘了logstash的语法了,因为爬虫的都是我们自己定义的,这个时候需要自己手写正则了。 

logstash 本身就内置了很多程序的变量正则, 比如nginx  haproxy apahce tomcat的正则, 需要你自己指明 type格式就可以了。 

这里标记下文章的源地址, http://xiaorui.cc    http://xiaorui.cc/?p=1055

那么问题来了… …  type貌似不能随便的引入,我一开始没注意 就随意用了nginx-access  结果filter里的grok正则怎么都匹配不了,很是恼火 … … 

最后干掉了type后,就可以正常的匹配了,应该没这么二b,有时间再折腾下这个问题 。 

关于grep或者是grok,大家可以在http://grokdebug.herokuapp.com/   这里查询下正则的匹配。 

logstash使用grok正则解析日志和kibana遇到的问题_第1张图片

我经过测试后的logstash agent.conf的配置  。 


input {
    file {
                type => “producer”
                path => “/home/ruifengyun/buzzspider/spider/spider.log”
        }
}
filter  {
    grok    {
        pattern => “\[(?\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2},\d{3})\]\s(?\w*)\s\”Crawl\surl:(?(.*)) (?[0-9]{2,3})\stakes (?\d.\d\d).*”
        }
    }
output  {
    redis   {
               host => “123.116.x.x”
               data_type =>”list”
               key => “logstash:demo”
    }
    stdout { codec => rubydebug}
}


在终端的结果是:

       "message" => "[2015-01-27 14:56:55,613] INFO \"Crawl url:http://weixin.sogou.com/weixin?query=%E4%B9%90%E6%92%AD%E8%AF%97&tsn=1&interation=&type=2&interV=kKIOkrELjbkRmLkElbkTkKIMkrELjboImLkEk74TkKIRmLkEk78TkKILkbELjboN_105333196&ie=utf8&page=7&p=40040100&dp=1&num=100 200 takes 0.085 seconds, refer:, depth:2\"",
    "@timestamp" => "2015-01-27T06:56:56.359Z",
      "@version" => "1",
          "type" => "producer",
          "host" => "bj-buzz-dev01",
          "path" => "/home/ruifengyun/buzzspider/spider/spider.log",
      "datetime" => "2015-01-27 14:56:55,613",
         "level" => "INFO",
           "url" => "http://weixin.sogou.com/weixin?query=%E4%B9%90%E6%92%AD%E8%AF%97&tsn=1&interation=&type=2&interV=kKIOkrELjbkRmLkElbkTkKIMkrELjboImLkEk74TkKIRmLkEk78TkKILkbELjboN_105333196&ie=utf8&page=7&p=40040100&dp=1&num=100",
      "httpcode" => "200",
          "cost" => "0.08"
}
{
       "message" => "[2015-01-27 14:56:55,637] INFO \"Crawl url:http://dealer.autohome.com.cn/8178/newslist.html 200 takes 0.146 seconds, refer:, depth:2\"",
    "@timestamp" => "2015-01-27T06:56:56.359Z",
      "@version" => "1",
          "type" => "producer",
          "host" => "bj-buzz-dev01",
          "path" => "/home/ruifengyun/buzzspider/spider/spider.log",
      "datetime" => "2015-01-27 14:56:55,637",
         "level" => "INFO",
           "url" => "http://dealer.autohome.com.cn/8178/newslist.html",
      "httpcode" => "200",
          "cost" => "0.14"
}


我们在kibana 3的界面上看到的结果,我这里是搜索下 时间周期里爬了sogou.com有多少次。


kibana的一个问题是, 不知道怎么写搜索的语句 。 


url:*.sogou.com*   ,我一开始以为是可以写纯正则。 kibana后端调用的是es的语法,所以你的语法要和elasticsearch想对应。 
 

logstash使用grok正则解析日志和kibana遇到的问题_第2张图片

################ 官方文档也有详细的描述,在简单把logstash官方关于grok文章翻译下。 

Example

下面是日志的样子
55.3.244.1 GET /index.html 15824 0.043

正则的例子
%{IP:client} %{WORD:method} %{URIPATHPARAM:request} %{NUMBER:bytes} %{NUMBER:duration}

配置文件里是怎么写得? 

input {
  file {
    path => “/var/log/http.log”
  }
}
filter {
  grok {
    match => [ "message", "%{IP:client} %{WORD:method} %{URIPATHPARAM:request} %{NUMBER:bytes} %{NUMBER:duration}" ]
  }
}

解析后,是个什么样子? 

client: 55.3.244.1
method: GET
request: /index.html
bytes: 15824
duration: 0.043


自定义正则


(?the pattern here)

(?[0-9A-F]{10,11})

当然你也可以把众多的正则,放在一个集中文件里面。 
# in ./patterns/postfix 
POSTFIX_QUEUEID [0-9A-F]{10,11}

filter {
  grok {
    patterns_dir => “./patterns”
    match => [ "message", "%{SYSLOGBASE} %{POSTFIX_QUEUEID:queue_id}: %{GREEDYDATA:syslog_message}" ]
  }
}

############


logstash已经自带了不少的正则,如果想偷懒的话,可以在内置正则里借用下。 

USERNAME [a-zA-Z0-9._-]+
USER %{USERNAME}
INT (?:[+-]?(?:[0-9]+))
BASE10NUM (?[+-]?(?:(?:[0-9]+(?:\.[0-9]+)?)|(?:\.[0-9]+)))
NUMBER (?:%{BASE10NUM})
BASE16NUM (? BASE16FLOAT \b(?

POSINT \b(?:[1-9][0-9]*)\b
NONNEGINT \b(?:[0-9]+)\b
WORD \b\w+\b
NOTSPACE \S+
SPACE \s*
DATA .*?
GREEDYDATA .*
QUOTEDSTRING (?>(?”(?>\\.|[^\\"]+)+”|”"|(?>’(?>\\.|[^\\']+)+’)|”|(?>(?>\\.|[^\]+)+)|`))
UUID [A-Fa-f0-9]{8}-(?:[A-Fa-f0-9]{4}-){3}[A-Fa-f0-9]{12}

# Networking
MAC (?:%{CISCOMAC}|%{WINDOWSMAC}|%{COMMONMAC})
CISCOMAC (?:(?:[A-Fa-f0-9]{4}\.){2}[A-Fa-f0-9]{4})
WINDOWSMAC (?:(?:[A-Fa-f0-9]{2}-){5}[A-Fa-f0-9]{2})
COMMONMAC (?:(?:[A-Fa-f0-9]{2}:){5}[A-Fa-f0-9]{2})
IPV6 ((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?
IPV4 (? IP (?:%{IPV6}|%{IPV4})
HOSTNAME \b(?:[0-9A-Za-z][0-9A-Za-z-]{0,62})(?:\.(?:[0-9A-Za-z][0-9A-Za-z-]{0,62}))*(\.?|\b)
HOST %{HOSTNAME}
IPORHOST (?:%{HOSTNAME}|%{IP})
HOSTPORT (?:%{IPORHOST=~/\./}:%{POSINT})

# paths
PATH (?:%{UNIXPATH}|%{WINPATH})
UNIXPATH (?>/(?>[\w_%!$@:.,-]+|\\.)*)+
TTY (?:/dev/(pts|tty([pq])?)(\w+)?/?(?:[0-9]+))
WINPATH (?>[A-Za-z]+:|\\)(?:\\[^\\?*]*)+
URIPROTO [A-Za-z]+(\+[A-Za-z+]+)?
URIHOST %{IPORHOST}(?::%{POSINT:port})?
# uripath comes loosely from RFC1738, but mostly from what Firefox
# doesn’t turn into %XX
URIPATH (?:/[A-Za-z0-9$.+!*'(){},~:;=@#%_\-]*)+
#URIPARAM \?(?:[A-Za-z0-9]+(?:=(?:[^&]*))?(?:&(?:[A-Za-z0-9]+(?:=(?:[^&]*))?)?)*)?
URIPARAM \?[A-Za-z0-9$.+!*’|(){},~@#%&/=:;_?\-\[\]]*
URIPATHPARAM %{URIPATH}(?:%{URIPARAM})?
URI %{URIPROTO}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST})?(?:%{URIPATHPARAM})?

# Months: January, Feb, 3, 03, 12, December
MONTH \b(?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?)\b
MONTHNUM (?:0?[1-9]|1[0-2])
MONTHDAY (?:(?:0[1-9])|(?:[12][0-9])|(?:3[01])|[1-9])

# Days: Monday, Tue, Thu, etc…
DAY (?:Mon(?:day)?|Tue(?:sday)?|Wed(?:nesday)?|Thu(?:rsday)?|Fri(?:day)?|Sat(?:urday)?|Sun(?:day)?)

# Years?
YEAR (?>\d\d){1,2}
HOUR (?:2[0123]|[01]?[0-9])
MINUTE (?:[0-5][0-9])
# ’60′ is a leap second in most time standards and thus is valid.
SECOND (?:(?:[0-5][0-9]|60)(?:[:.,][0-9]+)?)
TIME (?!<[0-9])%{HOUR}:%{MINUTE}(?::%{SECOND})(?![0-9])
# datestamp is YYYY/MM/DD-HH:MM:SS.UUUU (or something like it)
DATE_US %{MONTHNUM}[/-]%{MONTHDAY}[/-]%{YEAR}
DATE_EU %{MONTHDAY}[./-]%{MONTHNUM}[./-]%{YEAR}
ISO8601_TIMEZONE (?:Z|[+-]%{HOUR}(?::?%{MINUTE}))
ISO8601_SECOND (?:%{SECOND}|60)
TIMESTAMP_ISO8601 %{YEAR}-%{MONTHNUM}-%{MONTHDAY}[T ]%{HOUR}:?%{MINUTE}(?::?%{SECOND})?%{ISO8601_TIMEZONE}?
DATE %{DATE_US}|%{DATE_EU}
DATESTAMP %{DATE}[- ]%{TIME}
TZ (?:[PMCE][SD]T|UTC)
DATESTAMP_RFC822 %{DAY} %{MONTH} %{MONTHDAY} %{YEAR} %{TIME} %{TZ}
DATESTAMP_OTHER %{DAY} %{MONTH} %{MONTHDAY} %{TIME} %{TZ} %{YEAR}

# Syslog Dates: Month Day HH:MM:SS
SYSLOGTIMESTAMP %{MONTH} +%{MONTHDAY} %{TIME}
PROG (?:[\w._/%-]+)
SYSLOGPROG %{PROG:program}(?:\[%{POSINT:pid}\])?
SYSLOGHOST %{IPORHOST}
SYSLOGFACILITY <%{NONNEGINT:facility}.%{NONNEGINT:priority}>
HTTPDATE %{MONTHDAY}/%{MONTH}/%{YEAR}:%{TIME} %{INT}

# Shortcuts
QS %{QUOTEDSTRING}

# Log formats
SYSLOGBASE %{SYSLOGTIMESTAMP:timestamp} (?:%{SYSLOGFACILITY} )?%{SYSLOGHOST:logsource} %{SYSLOGPROG}:
COMMONAPACHELOG %{IPORHOST:clientip} %{USER:ident} %{USER:auth} \[%{HTTPDATE:timestamp}\] “(?:%{WORD:verb} %{NOTSPACE:request}(?: HTTP/%{NUMBER:httpversion})?|%{DATA:rawrequest})” %{NUMBER:response} (?:%{NUMBER:bytes}|-)
COMBINEDAPACHELOG %{COMMONAPACHELOG} %{QS:referrer} %{QS:agent}

# Log Levels
LOGLEVEL ([A-a]lert|ALERT|[T|t]race|TRACE|[D|d]ebug|DEBUG|[N|n]otice|NOTICE|[I|i]nfo|INFO|[W|w]arn?(?:ing)?|WARN?(?:ING)?|[E|e]rr?(?:or)?|ERR?(?:OR)?|[C|c]rit?(?:ical)?|CRIT?(?:ICAL)?|[F|f]atal|FATAL|[S|s]evere|SEVERE|EMERG(?:ENCY)?|[Ee]merg(?:ency)?)



如果大家觉得文章对你有些作用!   帮忙点击广告. 一来能刺激我写博客的欲望,二来好维护云主机的费用. 
如果想赏钱,可以用微信扫描下面的二维码. 另外再次标注博客原地址  xiaorui.cc  ……   感谢!

你可能感兴趣的:(大数据)