Filebeat介绍及部署

Filebeat介绍

Filebeat附带预构建的模块，这些模块包含收集、解析、充实和可视化各种日志文件格式数据所需的配置，每个Filebeat模块由一个或多个文件集组成，这些文件集包含摄取节点管道、Elasticsearch模板、Filebeat勘探者配置和Kibana仪表盘。

Filebeat模块很好的入门，它是轻量级单用途的日志收集工具，用于在没有安装java的服务器上专门收集日志，可以将日志转发到logstash、elasticsearch或redis等场景中进行下一步处理。

Filebeat和Logstash使用内存对比

Logstash内存占用

[root@linux-node1 ~]# ps -ef |  grep -v grep |    grep logstash  | awk '{print $2}'
12628
[root@linux-node1 ~]# cat /proc/12628/status | grep -i vm
VmPeak:  6252788 kB
VmSize:  6189252 kB
VmLck:         0 kB
VmHWM:    661168 kB
VmRSS:    661168 kB
VmData:  6027136 kB
VmStk:        88 kB
VmExe:         4 kB
VmLib:     16648 kB
VmPTE:      1888 kB
VmSwap:        0 kB

Filebeat内存占用

[root@linux-node1 ~]# cat  /proc/12750/status  /proc/12751/status |  grep -i vm 
VmPeak:    11388 kB
VmSize:    11388 kB
VmLck:         0 kB
VmHWM:       232 kB
VmRSS:       232 kB
VmData:    10424 kB
VmStk:        88 kB
VmExe:       864 kB
VmLib:         0 kB
VmPTE:        16 kB
VmSwap:        0 kB


VmPeak:    25124 kB
VmSize:    25124 kB
VmLck:         0 kB
VmHWM:     15144 kB
VmRSS:     15144 kB
VmData:    15496 kB
VmStk:        88 kB
VmExe:      4796 kB
VmLib:         0 kB
VmPTE:        68 kB
VmSwap:        0 kB

Filebeat部署

官方文档:https://www.elastic.co/guide/en/beats/filebeat/current/filebeat-configuration-details.html

官网下载地址:https://www.elastic.co/downloads/beats/filebeat

#下载Filebeat安装包
[root@linux-node5 ~]# wget https://artifacts.elastic.co/downloads/beats/filebeat/filebeat-5.3.2-x86_64.rpm
#安装Filebeat
[root@linux-node5 ~]# yum localinstall -y filebeat-5.3.2-x86_64.rpm

Filebeat收集单类型日志到本地文件

配置Filebeat

#编辑Filebeat配置文件
[root@linux-node5 ~]# vim /etc/filebeat/filebeat.yml
filebeat.prospectors:
- input_type: log
  paths:
    - /usr/local/nginx/logs/access_json.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: ngx_log

output.file:
  path: "/tmp"
  filename: "zls_filebeat.txt"

#启动Filebeat(CentOS6)
[root@linux-node5 ~]# /etc/init.d/filebeat start
#启动Filebeat(CentOS7)
[root@linux-node5 ~]# systemctl start filebeat
#检测进程
[root@linux-node5 ~]# ps -ef|grep filebeat
root      10881      1  0 01:06 pts/1    00:00:00 /usr/share/filebeat/bin/filebeat-god -r / -n -p /var/run/filebeat.pid -- /usr/share/filebeat/bin/filebeat -c /etc/filebeat/filebeat.yml -path.home /usr/share/filebeat -path.config /etc/filebeat -path.data /var/lib/filebeat -path.logs /var/log/filebeat
root      10882  10881  0 01:06 pts/1    00:00:00 /usr/share/filebeat/bin/filebeat -c /etc/filebeat/filebeat.yml -path.home /usr/share/filebeat -path.config /etc/filebeat -path.data /var/lib/filebeat -path.logs /var/log/filebeat

检测本地数据文件

#查看本地/tmp目录下内容
[root@linux-node5 ~]#  ll /tmp/
-rw------- 1 root root 4513 Aug  2 17:20 zls_filebeat.txt
#查看日志内容
[root@linux-node5 ~]# cat /tmp/zls_filebeat.txt 
{"@timestamp":"2019-08-02T09:20:22.599Z","beat":{"hostname":"linux-node5.98yz.cn","name":"linux-node5.98yz.cn","version":"5.3.3"},"input_type":"log","message":"{\"@timestamp\":\"2019-08-02T17:17:30+08:00\",\"host\":\"192.168.6.244\",\"clientip\":\"192.168.3.46\",\"size\":3700,\"responsetime\":0.000,\"upstreamtime\":\"-\",\"upstreamhost\":\"-\",\"http_host\":\"192.168.6.244\",\"url\":\"/index.html\",\"domain\":\"192.168.6.244\",\"xff\":\"-\",\"referer\":\"-\",\"status\":\"200\"}","offset":275,"source":"/var/log/nginx/access_json.log","type":"ngx_log"}
{"@timestamp":"2019-08-02T09:20:22.599Z","beat":{"hostname":"linux-node5.98yz.cn","name":"linux-node5.98yz.cn","version":"5.3.3"},"input_type":"log","message":"{\"@timestamp\":\"2019-08-02T17:17:30+08:00\",\"host\":\"192.168.6.244\",\"clientip\":\"192.168.3.46\",\"size\":368,\"responsetime\":0.000,\"upstreamtime\":\"-\",\"upstreamhost\":\"-\",\"http_host\":\"192.168.6.244\",\"url\":\"/nginx-logo.png\",\"domain\":\"192.168.6.244\",\"xff\":\"-\",\"referer\":\"http://192.168.6.244/\",\"status\":\"200\"}","offset":573,"source":"/var/log/nginx/access_json.log","type":"ngx_log"}

Filebeat收集单类型多个日志到Logstash

配置Filebeat

#编辑Filebeat配置文件
[root@linux-node5 ~]# vim /etc/filebeat/filebeat.yml
filebeat.prospectors:
- input_type: log
  paths:
    - /usr/local/nginx/logs/access_json.log
    - /usr/local/nginx/logs/access.log
  exclude_lines: ["^DBG","^$"]
  document_type: ngx_zls

output.logstash:
#logstash 服务器地址，可以是多个
  hosts: ["192.168.6.241:6666"]
#是否开启输出至logstash，默认即为true
  enabled: true
#工作线程数
  worker: 1
#压缩级别
  compression_level: 3
#多个输出的时候开启负载
#  loadbalance: true

#重启Filebeat
[root@linux-node5 ~]# /etc/init.d/filebeat stop
Stopping filebeat:                                         [确定]
[root@linux-node5 ~]# rm -f /var/lib/filebeat/registry
[root@linux-node5 ~]# /etc/init.d/filebeat start

配置Logstash输出到ES

#进入Logstash配置文件目录
[root@linux-node1 ~]# cd /etc/logstash/conf.d/
#编辑Logstash配置文件
[root@elkstack03 conf.d]# vim beats.conf
input {
        beats {
        port => 6666
        codec => "json"
        }
}

output {
    elasticsearch {
      hosts => ["192.168.6.241:9200"]
      index => "%{type}-%{+YYYY.MM.dd}"
    }
}

#启动Logstash
[root@linux-node1 conf.d]# /usr/share/logstash/bin/logstash -f /etc/logstash/conf.d/beats.conf &

验证数据

打开浏览器，访问：http://192.168.6.241:9100/

Filebeat收集单类型多个日志到Redis

配置Filebeat

#编辑Filebeat配置文件
[root@linux-node5 ~]# vim /etc/filebeat/filebeat.yml
filebeat.prospectors:
- input_type: log
  paths:
    - /usr/local/nginx/logs/access_json.log
    - /usr/local/nginx/logs/access.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: www.driverzeng.com

output.redis:
  hosts: ["192.168.6.243:6379"]
#Redis中的key名称
  key: "nginx"
#使用1库
  db: 2
#设置超时时间
  timeout: 5
#redis密码
  password: zls

#重启Filebeat
[root@linux-node5 ~]# systemctl stop filebeat.service 
[root@linux-node5 ~]# rm -f /var/lib/filebeat/registry
[root@linux-node5 ~]# systemctl start filebeat.service

登录Redis验证数据

#登录Redis
[root@linux-node5 ~]# redis-cli -a zls
#查看所有key
127.0.0.1:6379> KEYS *
1) "nginx"
#查看nginx key长度
127.0.0.1:6379> LLEN nginx
(integer) 218
#取出一条日志
127.0.0.1:6379> LPOP nginx
"{\"@timestamp\":\"2019-08-02T09:50:18.113Z\",\"beat\":{\"hostname\":\"linux-node5.98yz.cn\",\"name\":\"linux-node5.98yz.cn\",\"version\":\"5.3.3\"},\"input_type\":\"log\",\"message\":\"{\\\"@timestamp\\\":\\\"2019-08-02T17:41:52+08:00\\\",\\\"host\\\":\\\"192.168.6.244\\\",\\\"clientip\\\":\\\"192.168.3.46\\\",\\\"size\\\":0,\\\"responsetime\\\":0.000,\\\"upstreamtime\\\":\\\"-\\\",\\\"upstreamhost\\\":\\\"-\\\",\\\"http_host\\\":\\\"192.168.6.244\\\",\\\"url\\\":\\\"/index.html\\\",\\\"domain\\\":\\\"192.168.6.244\\\",\\\"xff\\\":\\\"-\\\",\\\"referer\\\":\\\"-\\\",\\\"status\\\":\\\"304\\\"}\",\"offset\":272,\"source\":\"/usr/local/nginx/logs/access_json.log\",\"type\":\"www.driverzeng.com\"}"

Filebeat收集多类型日志到Redis

#修改Filebeat配置文件
[root@linux-node5 conf.d]# vim /etc/filebeat/filebeat.yml
filebeat.prospectors:
- input_type: log
  paths:
    - /usr/local/nginx/logs/access_json.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: ngx_log

- input_type: log
  paths:
    - /usr/local/tomcat/logs/tomcat_access_log*.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: tc_log

output.redis:
  hosts: ["192.168.6.243:6379"]
#Redis中的key名称
  key: "tomcat_nginx"
#使用3库
  db: 3
#设置超时时间
  timeout: 5
#redis密码
  password: zls

#重启Filebeat
[root@linux-node5 ~]# systemctl stop filebeat.service 
[root@linux-node5 ~]# rm -f /var/lib/filebeat/registry
[root@linux-node5 ~]# systemctl start filebeat.service

登录Redis验证数据

[root@linux-node4 ~]# redis-cli -a zls
127.0.0.1:6379> select 3
OK
127.0.0.1:6379[3]> KEYS *
1) "tomcat_nginx"
127.0.0.1:6379[3]>  LPOP tomcat_nginx
"{\"@timestamp\":\"2019-08-02T10:10:36.278Z\",\"beat\":{\"hostname\":\"linux-node5.98yz.cn\",\"name\":\"linux-node5.98yz.cn\",\"version\":\"5.3.3\"},\"input_type\":\"log\",\"message\":\"{\\\"@timestamp\\\":\\\"2019-08-02T18:10:33+08:00\\\",\\\"host\\\":\\\"192.168.6.244\\\",\\\"clientip\\\":\\\"192.168.3.46\\\",\\\"size\\\":0,\\\"responsetime\\\":0.000,\\\"upstreamtime\\\":\\\"-\\\",\\\"upstreamhost\\\":\\\"-\\\",\\\"http_host\\\":\\\"192.168.6.244\\\",\\\"url\\\":\\\"/index.html\\\",\\\"domain\\\":\\\"192.168.6.244\\\",\\\"xff\\\":\\\"-\\\",\\\"referer\\\":\\\"-\\\",\\\"status\\\":\\\"304\\\"}\",\"offset\":6800,\"source\":\"/usr/local/nginx/logs/access_json.log\",\"type\":\"ngx_log\"}"
127.0.0.1:6379[3]>  LPOP tomcat_nginx
"{\"@timestamp\":\"2019-08-02T10:10:41.278Z\",\"beat\":{\"hostname\":\"linux-node5.98yz.cn\",\"name\":\"linux-node5.98yz.cn\",\"version\":\"5.3.3\"},\"input_type\":\"log\",\"message\":\"{\\\"clientip\\\":\\\"192.168.3.46\\\",\\\"ClientUser\\\":\\\"-\\\",\\\"authenticated\\\":\\\"-\\\",\\\"AccessTime\\\":\\\"[02/Aug/2019:18:10:30 +0800]\\\",\\\"method\\\":\\\"GET / HTTP/1.1\\\",\\\"status\\\":\\\"200\\\",\\\"SendBytes\\\":\\\"11418\\\",\\\"Query?string\\\":\\\"\\\",\\\"partner\\\":\\\"-\\\",\\\"AgentVersion\\\":\\\"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36\\\"}\",\"offset\":3484,\"source\":\"/usr/local/tomcat/logs/tomcat_access_log2019-08-02.log\",\"type\":\"tc_log\"}"

看的出来，tomcat日志和nginx日志都在一个key中

那么有人会问了，都在一个key中，日志不就混乱了么？我们该如何查看日志呢？接下来我们就来解决这个问题。

使用Logstash将beat放入redis的数据输出到ES

#进入Logstash配置文件目录
[root@linux-node1 ~]# cd /etc/logstash/conf.d/
#编辑Logstash配置文件
[root@elkstack03 conf.d]# vim beats_redis_es.conf
input {
  redis {
    host => "192.168.6.243"
    port => "6379"
    db => "3"
    key => "tomcat_nginx"
    data_type => "list"
    password => "zls"
    codec  => "json"
 }
}

output {
    elasticsearch {
      hosts => ["192.168.6.241:9200"]
      index => "%{type}-%{+YYYY.MM.dd}"
  }
}
#启动Logstash
[root@linux-node1 conf.d]# /usr/share/logstash/bin/logstash -f /etc/logstash/conf.d/beats_redis_es.conf &

验证数据

打开浏览器，访问：http://92.168.6.241:9100/

可以看到，我们通过Logstash利用type将日志区分开，分别输出到ES中，虽然在Redis中没有区分开，但是最终在ES中区分开了，那么添加到Kibana中，同样是两个日志。

Filebeat收集多类型日志输出到多个目标

配置Filebeat

我们将nginx日志 tomcat日志同时输出到Redis和本地文件中

[root@linux-node5 conf.d]# vim /etc/filebeat/filebeat.yml
filebeat.prospectors:
- input_type: log
  paths:
    - /usr/local/nginx/logs/access_json.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: ngx_log

- input_type: log
  paths:
    - /usr/local/tomcat/logs/tomcat_access_log.*.log
#不收集的行
  exclude_lines: ["^DBG","^$"]
#日志类型
  document_type: tc_log

output.redis:
#redis 服务器地址，可以是多个
  hosts: ["192.168.6.243:6379"]
  key: "tn"
  db: 2
  timeout: 5
  password: zls

output.file:
  path: "/tmp"
  filename: "zls.txt"
#工作线程数
  worker: 1
#压缩级别
  compression_level: 3
#多个输出的时候开启负载
  loadbalance: true

#重启Filebeat
[root@linux-node5 ~]# systemctl stop filebeat.service 
[root@linux-node5 ~]# rm -f /var/lib/filebeat/registry
[root@linux-node5 ~]# systemctl start filebeat.service

验证Redis数据和本地文件数据

#登录redis
[root@elkstack04 ~]# redis-cli -a zls
#切换2库
127.0.0.1:6379> SELECT 2
OK
#查看所有key
127.0.0.1:6379[2]> KEYS *
1) "tn"
#查看key长度
127.0.0.1:6379[2]> LLEN tn
(integer) 27
#取出日志
127.0.0.1:6379[2]> LPOP tn
"{\"@timestamp\":\"2019-08-02T10:33:09.320Z\",\"beat\":{\"hostname\":\"linux-node5.98yz.cn\",\"name\":\"linux-node5.98yz.cn\",\"version\":\"5.3.3\"},\"input_type\":\"log\",\"message\":\"{\\\"@timestamp\\\":\\\"2019-08-02T17:41:52+08:00\\\",\\\"host\\\":\\\"192.168.6.244\\\",\\\"clientip\\\":\\\"192.168.3.46\\\",\\\"size\\\":0,\\\"responsetime\\\":0.000,\\\"upstreamtime\\\":\\\"-\\\",\\\"upstreamhost\\\":\\\"-\\\",\\\"http_host\\\":\\\"192.168.6.244\\\",\\\"url\\\":\\\"/index.html\\\",\\\"domain\\\":\\\"192.168.6.244\\\",\\\"xff\\\":\\\"-\\\",\\\"referer\\\":\\\"-\\\",\\\"status\\\":\\\"304\\\"}\",\"offset\":272,\"source\":\"/usr/local/nginx/logs/access_json.log\",\"type\":\"ngx_log\"}"

#进入tmp目录
[root@linux-node5 ~]# cd /tmp/
#查看文件是否生成
[root@linux-node5 tmp]# ll
total 24
drwxr-xr-x 2 root root    18 Aug  2 18:09 hsperfdata_root
drwx------ 3 root root    17 Aug  1 09:41 systemd-private-fc5735963c2a42acbb5751c85a9a7eee-chronyd.service-rKn7xV
drwx------ 3 root root    17 Aug  2 17:27 systemd-private-fc5735963c2a42acbb5751c85a9a7eee-nginx.service-7eKP5i
drwx------ 3 root root    17 Aug  1 09:41 systemd-private-fc5735963c2a42acbb5751c85a9a7eee-vgauthd.service-zjVHU8
drwx------ 3 root root    17 Aug  1 09:41 systemd-private-fc5735963c2a42acbb5751c85a9a7eee-vmtoolsd.service-DIJYNm
-rw------- 1 root root  4513 Aug  2 17:20 zls_filebeat.txt
-rw------- 1 root root 15171 Aug  2 18:33 zls.txt
#查看文件内容
[root@linux-node5 tmp]# cat zls.txt 
{"@timestamp":"2019-08-02T10:33:09.320Z","beat":{"hostname":"linux-node5.98yz.cn","name":"linux-node5.98yz.cn","version":"5.3.3"},"input_type":"log","message":"{\"@timestamp\":\"2019-08-02T17:41:52+08:00\",\"host\":\"192.168.6.244\",\"clientip\":\"192.168.3.46\",\"size\":0,\"responsetime\":0.000,\"upstreamtime\":\"-\",\"upstreamhost\":\"-\",\"http_host\":\"192.168.6.244\",\"url\":\"/index.html\",\"domain\":\"192.168.6.244\",\"xff\":\"-\",\"referer\":\"-\",\"status\":\"304\"}","offset":272,"source":"/usr/local/nginx/logs/access_json.log","type":"ngx_log"}
{"@timestamp":"2019-08-02T10:33:09.320Z","beat":{"hostname":"linux-node5.98yz.cn","name":"linux-node5.98yz.cn","version":"5.3.3"},"input_type":"log","message":"{\"@timestamp\":\"2019-08-02T17:41:52+08:00\",\"host\":\"192.168.6.244\",\"clientip\":\"192.168.3.46\",\"size\":0,\"responsetime\":0.000,\"upstreamtime\":\"-\",\"upstreamhost\":\"-\",\"http_host\":\"192.168.6.244\",\"url\":\"/index.html\",\"domain\":\"192.168.6.244\",\"xff\":\"-\",\"referer\":\"-\",\"status\":\"304\"}","offset":544,"source":"/usr/local/nginx/logs/access_json.log","type":"ngx_log"}
{"@timestamp":"2019-08-02T10:33:09.320Z","beat":{"hostname":"linux-node5.98yz.cn","name":"linux-node5.98yz.cn","version":"5.3.3"},"input_type":"log","message":"{\"@timestamp\":\"2019-08-02T17:41:53+08:00\",\"host\":\"192.168.6.244\",\"clientip\":\"192.168.3.46\",\"size\":0,\"responsetime\":0.000,\"upstreamtime\":\"-\",\"upstreamhost\":\"-\",\"http_host\":\"192.168.6.244\",\"url\":\"/index.html\",\"domain\":\"192.168.6.244\",\"xff\":\"-\",\"referer\":\"-\",\"status\":\"304\"}","offset":816,"source":"/usr/local/nginx/logs/access_json.log","type":"ngx_log"}

文档更新时间: 2019-08-02 18:39   作者：李延召