ELK7.4-快速入门实现数据收集

小生博客：http://xsboke.blog.51cto.com

                    -------谢谢您的参考，如有疑问，欢迎交流

目录:

• 本次使用的组件
• 环境
• WEB配置
• Elasticsearch配置
• 通过nginx访问elasticsearch和kibana
• 扩展:filebeat input 配置
• 排错方法

组件简介和作用

filebeat收集日志   ->  logstash过滤/格式化  -> elasticsearch存储  ->  kibana展示

# 个人理解
其实logstash和filebeat都可以收集日志并且直接输出到elasticsearch.
只不过logstash功能比filebeat更多,比如:过滤,格式化
filebeat比logstash更轻,所以filebeat收集日志速度更快.

环境

#基于ELK7.4,通过收集Nginx日志示例.
centos7.2-web               172.16.100.251      nginx/filebeat/logstash
centos7.2-elasticsearch     172.16.100.252      elasticsearch/kibana

WEB配置

1. 安装Nginx

   yum -y install yum-utils
   vim /etc/yum.repos.d/nginx.repo
    [nginx-stable]
    name=nginx stable repo
    baseurl=http://nginx.org/packages/centos/$releasever/$basearch/
    gpgcheck=1
    enabled=1
    gpgkey=https://nginx.org/keys/nginx_signing.key
    module_hotfixes=true

    [nginx-mainline]
    name=nginx mainline repo
    baseurl=http://nginx.org/packages/mainline/centos/$releasever/$basearch/
    gpgcheck=1
    enabled=1
    gpgkey=https://nginx.org/keys/nginx_signing.key
    module_hotfixes=true

   yum-config-manager --enable nginx-mainline
   yum -y install nginx
   nginx

2. 配置JDK

   tar zxf jdk-8u202-linux-x64.tar.gz
   mv jdk1.8.0_202 /usr/local/jdk1.8
   vim /etc/profile
    export JAVA_HOME=/usr/local/jdk1.8
    export JRE_HOME=/usr/local/jdk1.8/jre
    export CLASSPATH=.:$JAVA_HOME/lib:$JRE_HOME/lib:$CLASSPATH
    export PATH=$JAVE_HOME/bin:$JRE_HOME/bin:$PATH

   source /etc/profile
   # 如果不做这个软连接logstash依然会报错找不到openSDK
   ln -s /usr/local/jdk1.8/bin/java /usr/bin/java   

3. 安装并且配置filebeat

   curl -L -O https://artifacts.elastic.co/downloads/beats/filebeat/filebeat-7.4.0-x86_64.rpm
   rpm -vi filebeat-7.4.0-x86_64.rpm    
   vim /etc/filebeat/filebeat.yml
    filebeat.inputs:
     - type: log
       enabled: true
         paths:
           - /var/log/nginx/access.log  # 监控的日志
         tags: ["access"]               # 用于实现多日志收集

     - type: log
       enabled: true
         paths:
           - /var/log/nginx/error.log
         tags: ["error"]

    output.logstash:
      hosts: ["localhost:5044"] # logstash的配置文件会指定监听这个端口

   # 注释: "output.elasticsearch",否则在启用logstash模块时会报错:Error initializing beat: error unpacking config data: more than one namespace configured accessing 'output' (source:'/etc/filebeat/filebeat.yml')

   # 启动logstatsh模块,其实修改的是这个文件"/etc/filebeat/modules.d/logstash.yml"
   filebeat modules enable logstash

4. 安装logstash

   rpm --import https://artifacts.elastic.co/GPG-KEY-elasticsearch
   vim /etc/yum.repos.d/logstash.repo
    [logstash-7.x]
    name=Elastic repository for 7.x packages
    baseurl=https://artifacts.elastic.co/packages/7.x/yum
    gpgcheck=1
    gpgkey=https://artifacts.elastic.co/GPG-KEY-elasticsearch
    enabled=1
    autorefresh=1
    type=rpm-md

   yum -y install logstash
   ln -s /usr/share/logstash/bin/logstash /usr/local/bin/

   # logstash.yml部分配置简介
   path.data: 数据存放目录
   config.reload.automatic: 是否动态加载配置文件
   config.reload.interval: 动态加载配置文件间隔
   http.host: 监听主机
   http.port: 端口

   # 在logstash/conf.d/ 下编写你的配置文件
   vim /etc/logstash/conf.d/nginx.conf
    input {
           beats {
               port => 5044
           }
    }
    output {  
           if "access" in [tags] {    # 通过判断标签名,为不同的日志配置不同的index
               elasticsearch {
                   hosts => ["172.16.100.252:9200"]
                   index => "nginx-access-%{+YYYY.MM.dd}" # 索引名不能大写
                   sniffing => true
                   template_overwrite => true
               }
           }

           if "error" in [tags] {
               elasticsearch {
                   hosts => ["172.16.100.252:9200"]
                   index => "nginx-error-%{+YYYY.MM.dd}"
                   sniffing => true
                   template_overwrite => true
               }
           }
    }

   systemctl daemon-reload
   systemctl enable logstashe
   systemctl start logstashe

5. 防火墙配置

   firewall-cmd --permanent --add-port=80/tcp
   firewall-cmd --reload

Elasticsearch配置

1. 配置JDK

   tar zxf jdk-8u202-linux-x64.tar.gz
   mv jdk1.8.0_202 /usr/local/jdk1.8
   vim /etc/profile
    export JAVA_HOME=/usr/local/jdk1.8
    export JRE_HOME=/usr/local/jdk1.8/jre
    export CLASSPATH=.:$JAVA_HOME/lib:$JRE_HOME/lib:$CLASSPATH
    export PATH=$JAVE_HOME/bin:$JRE_HOME/bin:$PATH

   source /etc/profile

2. 安装elasticsearch

```
vim /etc/yum.repos.d/elasticsearch.repo
    [elasticsearch-7.x]
    name=Elasticsearch repository for 7.x packages
    baseurl=https://artifacts.elastic.co/packages/7.x/yum
    gpgcheck=1
    gpgkey=https://artifacts.elastic.co/GPG-KEY-elasticsearch
    enabled=1
    autorefresh=1
    type=rpm-md

yum -y install elasticsearch
# 修改elasticsearch
    关键字:
        cluster.name:                       群集名字 
        node.name:                          节点名字
        path.data:                          数据存放路径
        path.logs:                          日志存放路径
        bootstrap.memory_lock:              在启动时侯是否锁定内存
        network.host:                       提供服务绑定的ip地址，0.0.0.0代表所有地址
        http.port:                          侦听端口
        discovery.seed_hosts:               集群主机
        cluster.initial_master_nodes:       指定master节点

sed -i "/#cluster.name: my-application/a\cluster.name: my-elk-cluster" /etc/elasticsearch/elasticsearch.yml
sed -i "/#node.name: node-1/a\node.name: node-1" /etc/elasticsearch/elasticsearch.yml
sed -i "s/path.data: \/var\/lib\/elasticsearch/path.data: \/data\/elasticsearch/g" /etc/elasticsearch/elasticsearch.yml
sed -i "/#bootstrap.memory_lock: true/a\bootstrap.memory_lock: false" /etc/elasticsearch/elasticsearch.yml
sed -i "/#network.host: 192.168.0.1/a\network.host: 0.0.0.0" /etc/elasticsearch/elasticsearch.yml
sed -i "/#http.port: 9200/a\http.port: 9200" /etc/elasticsearch/elasticsearch.yml
sed -i '/#discovery.seed_hosts: \["host1", "host2"\]/a\discovery.seed_hosts: \["172.16.100.252"\]' /etc/elasticsearch/elasticsearch.yml
sed -i '/#cluster.initial_master_nodes: \["node-1", "node-2"\]/a\cluster.initial_master_nodes: \["node-1"\]' /etc/elasticsearch/elasticsearch.yml

mkdir -p /data/elasticsearch
chown  elasticsearch:elasticsearch /data/elasticsearch
systemctl daemon-reload
systemctl enable elasticsearch
systemctl start elasticsearch
```

3. 安装配置Kibana

   rpm --import https://artifacts.elastic.co/GPG-KEY-elasticsearch
   vim /etc/yum.repos.d/kibana.repo
    [kibana-7.x]
    name=Kibana repository for 7.x packages
    baseurl=https://artifacts.elastic.co/packages/7.x/yum
    gpgcheck=1
    gpgkey=https://artifacts.elastic.co/GPG-KEY-elasticsearch
    enabled=1
    autorefresh=1
    type=rpm-md

   yum -y install kibana

   sed -i "/#server.port: 5601/a\server.port: 5601" /etc/kibana/kibana.yml
   sed -i '/#server.host: "localhost"/a\server.host: "0.0.0.0"' /etc/kibana/kibana.yml
   sed -i '/#elasticsearch.hosts: \["http:\/\/localhost:9200"\]/a\elasticsearch.hosts: \["http:\/\/localhost:9200"\]' /etc/kibana/kibana.yml
   sed -i '/#kibana.index: ".kibana"/a\kibana.index: ".kibana"' /etc/kibana/kibana.yml

   systemctl daemon-reload
   systemctl enable kibana
   systemctl start kibana

4. 防火墙配置

   firewall-cmd --permanent --add-port=9200/tcp
   # firewall-cmd --permanent --add-port=9300/tcp # 集群端口
   firewall-cmd --permanent --add-port=5601/tcp
   firewall-cmd --reload

通过nginx访问elasticsearch和kibana(使用nginx实现elasticsearch和kibana的访问限制)

1. 172.16.100.252

   # 修改hosts
   vim /etc/hosts
   172.16.100.252   elk.elasticsearch

   # 安装nginx并且配置
   server {
       listen       80;
       server_name  elk.elasticsearch;

       location / {
           allow 127.0.0.1/32;
           allow 172.16.100.251/32;
           deny all;
           proxy_pass http://127.0.0.1:9200;
       }
   }

   server {
       listen       80;
       server_name  elk.kibana;

       location / {
           allow "可以访问kibana的IP";
           deny all;
           proxy_pass http://127.0.0.1:5601;
       }
   }

   # 修改elasticsearch配置
   network.host: 127.0.0.1
   discovery.seed_hosts: ["elk.elasticsearch"]

   # 修改kibana配置
   server.host: "127.0.0.1"

   systemctl restart elasticsearch
   systemctl restart kibana

2. 172.16.100.251

   #  修改hosts
   vim /etc/hosts
   172.16.100.252   elk.elasticsearch

   # logstash input output conf
   vim /etc/logstash/conf.d/nginx.conf
    input {
           beats {
               port => 5044
           }
    }
    output {  
           if "access" in [tags] {    # 通过判断标签名,为不同的日志配置不同的index
               elasticsearch {
                   hosts => ["elk.elasticsearch:80"]    # 必须指定端口,否则默认访问9200
                   index => "nginx-access-%{+YYYY.MM.dd}" # 索引名不能大写
                   sniffing => false
                   template_overwrite => true
               }
           }

           if "error" in [tags] {
               elasticsearch {
                   hosts => ["elk.elasticsearch:80"]
                   index => "nginx-error-%{+YYYY.MM.dd}"
                   sniffing => false
                   template_overwrite => true
               }
           }
    }

   systemctl restart logstash

扩展:filebeat input 配置

# filebeat将多行合并为一行收集
filebeat.inputs:
     - type: log
       enabled: true
         paths:
           - /var/log/nginx/access.log
         tags: ["access"]
         multiline.pattern: '^\[[0-9]{4}'   # 指定要匹配的正则表达式模式,匹配以[YYYY 开头的行.
         multiline.negate: true             # 不匹配模式的连续行
         multiline.match: after             # 追加到不匹配的前一行

# filebeat收集指定目录下的日志并且包括子目录
filebeat.inputs:
- type: log
  enabled: true
  paths:
    - "/var/log/**"
  recursive_glob.enabled: true  # 开启递归模式
  tags: ["LogAll"]

排错方法

# 启动filebeat并且将信息输出到终端
filebeat -e

# 启动logstash并且将信息输出到终端
logstash /etc/logstash/conf.d/nginx.conf

# 随意写入内容到收集的日志中
echo "1" >> /var/log/nginx/access.log

# 然后通过查看filebeat和logstash的输出来判断错误