ELK日志监控测试部署

Logstash是一个开源的用于收集，分析和存储日志的工具。 Kibana4用来搜索和查看Logstash已索引的日志的web接口。这两个工具都基于Elasticsearch。
  ● Logstash: Logstash服务的组件，用于处理传入的日志。
  ● Elasticsearch: 存储所有日志
  ● Kibana 4: 用于搜索和可视化的日志的Web界面，通过nginx反代
  ● Logstash Forwarder: 安装在将要把日志发送到logstash的服务器上，作为日志转发的道理，通过  lumberjack 网络协议与 Logstash 服务通讯
注意：logstash-forwarder要被beats替代了，关注后续内容。后续会转到logstash+elasticsearch+beats上。
ELK架构如下：

elasticsearch-1.7.2.tar.gz
kibana-4.1.2-linux-x64.tar.gz
logstash-1.5.6-1.noarch.rpm
logstash-forwarder-0.4.0-1.x86_64.rpm
	
 
单机模式
#OS
CentOS release 6.5 (Final)
 
#Base and JDK
groupadd elk
useradd -g elk elk 
passwd elk
yum install vim lsof man wget ntpdate vixie-cron -y
crontab -e
*/1 * * * * /usr/sbin/ntpdate time.windows.com > /dev/null 2>&1
service crond restart
 
 
禁用selinux，关闭iptables
sed -i "s#SELINUX=enforcing#SELINUX=disabled#" /etc/selinux/config
service iptables stop
reboot
 
tar -zxvf jdk-8u92-linux-x64.tar.gz -C /usr/local/
vim /etc/profile
export JAVA_HOME=/usr/local/jdk1.8.0_92
export JRE_HOME=/usr/local/jdk1.8.0_92/jre
export PATH=$JAVA_HOME/bin:$JAVA_HOME/jre/bin:$PATH
export CLASSPATH=$CLASSPATH:.:$JAVA_HOME/lib:$JAVA_HOME/jre/lib
source /etc/profile
 
#Elasticsearch
#(cluster时在其他server安装elasticsearch，并配置相同集群名称，不同节点名称即可)
RPM安装
rpm --import http://packages.elastic.co/GPG-KEY-elasticsearch
wget -c https://download.elastic.co/elasticsearch/elasticsearch/elasticsearch-1.7.2.noarch.rpm
rpm -ivh elasticsearch-1.7.2.noarch.rpm
tar安装
wget -c https://download.elastic.co/elasticsearch/elasticsearch/elasticsearch-1.7.2.tar.gz
tar zxvf elasticsearch-1.7.2.tar.gz -C /usr/local/
 
cd /usr/local/elasticsearch-1.7.2/
mkdir -p /data/{db,logs}
 
vim config/elasticsearch.yml
#cluster.name: elasticsearch 
#node.name: "es-node1" 
#node.master: true  
#node.data: true  
path.data: /data/db
path.logs: /data/logs
network.host: 192.168.28.131
 
#插件安装
cd /usr/local/elasticsearch-1.7.2/
bin/plugin -install mobz/elasticsearch-head
#https://github.com/mobz/elasticsearch-head
bin/plugin -install lukas-vlcek/bigdesk
bin/plugin install lmenezes/elasticsearch-kopf
#会提示版本过低
解决办法就是手动下载该软件，不通过插件安装命令...
cd /usr/local/elasticsearch-1.7.2/plugins
wget https://github.com/lmenezes/elasticsearch-kopf/archive/master.zip
unzip master.zip
mv elasticsearch-kopf-master kopf
以上操作就完全等价于插件的安装命令
cd /usr/local/
chown elk:elk elasticsearch-1.7.2/ -R
chown elk:elk /data/* -R
 
supervisord安装：
yum install supervisor -y
末尾添加针对elasticsearch的配置项
vim /etc/supervisord.conf
[program:elasticsearch]
directory = /usr/local/elasticsearch-1.7.2/
;command = su -c "/usr/local/elasticsearch-1.7.2/bin/elasticsearch" elk
command =/usr/local/elasticsearch-1.7.2/bin/elasticsearch
numprocs = 1
autostart = true
startsecs = 5
autorestart = true
startretries = 3
user = elk
;stdout_logfile_maxbytes = 200MB
;stdout_logfile_backups = 20
;stdout_logfile = /var/log/pvs_elasticsearch_stdout.log
 
#Kibana（注意版本搭配）
https://download.elastic.co/kibana/kibana/kibana-4.1.2-linux-x64.tar.gz
tar zxvf kibana-4.1.2-linux-x64.tar.gz -C /usr/local/
 
cd /usr/local/kibana-4.1.2-linux-x64
vim config/kibana.yml 
port: 5601
host: "192.168.28.131"
elasticsearch_url: "http://192.168.28.131:9200"
./bin/kibana -l /var/log/kibana.log  #启动服务，kibana 4.0开始是以socket服务启动的
 
#cd /etc/init.d &&  curl -o kibana https://gist.githubusercontent.com/thisismitch/8b15ac909aed214ad04a/raw/fc5025c3fc499ad8262aff34ba7fde8c87ead7c0/kibana-4.x-init
#cd /etc/default &&  curl -o kibana https://gist.githubusercontent.com/thisismitch/8b15ac909aed214ad04a/raw/fc5025c3fc499ad8262aff34ba7fde8c87ead7c0/kibana-4.x-default
#修改对应信息，添加可执行权限
或者如下：
cat >> /etc/init.d/kibana <<EOF
#!/bin/bash
### BEGIN INIT INFO
# Provides:          kibana
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: Runs kibana daemon
# Description: Runs the kibana daemon as a non-root user
### END INIT INFO
# Process name
NAME=kibana
DESC="Kibana4"
PROG="/etc/init.d/kibana"
# Configure location of Kibana bin
KIBANA_BIN=/usr/local/kibana-4.1.2-linux-x64/bin
# PID Info
PID_FOLDER=/var/run/kibana/
PID_FILE=/var/run/kibana/$NAME.pid
LOCK_FILE=/var/lock/subsys/$NAME
PATH=/bin:/usr/bin:/sbin:/usr/sbin:$KIBANA_BIN
DAEMON=$KIBANA_BIN/$NAME
# Configure User to run daemon process
DAEMON_USER=root
# Configure logging location
KIBANA_LOG=/var/log/kibana.log
# Begin Script
RETVAL=0
if [ `id -u` -ne 0 ]; then
        echo "You need root privileges to run this script"
        exit 1
fi
# Function library
. /etc/init.d/functions
start() {
        echo -n "Starting $DESC : "
pid=`pidofproc -p $PID_FILE kibana`
        if [ -n "$pid" ] ; then
                echo "Already running."
                exit 0
        else
        # Start Daemon
if [ ! -d "$PID_FOLDER" ] ; then
                        mkdir $PID_FOLDER
                fi
daemon --user=$DAEMON_USER --pidfile=$PID_FILE $DAEMON 1>"$KIBANA_LOG" 2>&1 &
                sleep 2
                pidofproc node > $PID_FILE
                RETVAL=$?
                [[ $? -eq 0 ]] && success || failure
echo
                [ $RETVAL = 0 ] && touch $LOCK_FILE
                return $RETVAL
        fi
}
reload()
{
    echo "Reload command is not implemented for this service."
    return $RETVAL
}
stop() {
        echo -n "Stopping $DESC : "
        killproc -p $PID_FILE $DAEMON
        RETVAL=$?
echo
        [ $RETVAL = 0 ] && rm -f $PID_FILE $LOCK_FILE
}
case "$1" in
  start)
        start
;;
  stop)
        stop
        ;;
  status)
        status -p $PID_FILE $DAEMON
        RETVAL=$?
        ;;
  restart)
        stop
        start
        ;;
  reload)
reload
;;
  *)
# Invalid Arguments, print the following message.
        echo "Usage: $0 {start|stop|status|restart}" >&2
exit 2
        ;;
esac
EOF
chmod +x kibana
mv kibana /etc/init.d/
 
#Nginx
yum install nginx -y
vim /etc/nginx/conf.d/elk.conf
server {
    server_name elk.sudo.com;
    auth_basic "Restricted Access";
    auth_basic_user_file passwd;
 
    location / {
        proxy_pass http://192.168.28.131:5601;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
        proxy_set_header Host $host;
        proxy_cache_bypass $http_upgrade;        
    }
}
#htpsswd添加：yum install httpd-tools –y
echo -n 'sudo:' >> /etc/nginx/passwd #添加用户
openssl passwd elk.sudo.com >> /etc/nginx/passwd #添加密码
cat /etc/nginx/passwd #查看
chkconfig nginx on && service nginx start 
 
#Logstash--Setup
rpm --import https://packages.elasticsearch.org/GPG-KEY-elasticsearch
vi /etc/yum.repos.d/logstash.repo
[logstash-1.5]
name=Logstash repository for 1.5.x packages
baseurl=http://packages.elasticsearch.org/logstash/1.5/centos
gpgcheck=1
gpgkey=http://packages.elasticsearch.org/GPG-KEY-elasticsearch
enabled=1
yum install logstash -y
 
#创建SSL证书（在logstash服务器上生成ssl证书。创建ssl证书有两种方式，一种指定IP地址，一种指定fqdn(dns)）,选其一即可
#1、IP地址
在[ v3_ca ]配置段下设置上面的参数。192.168.28.131是logstash服务端的地址。
vi /etc/pki/tls/openssl.cnf
subjectAltName = IP: 192.168.28.131
 
cd /etc/pki/tls
openssl req -config /etc/pki/tls/openssl.cnf -x509 -days 3650 -batch -nodes -newkey rsa:2048 -keyout private/logstash-forwarder.key -out certs/logstash-forwarder.crt
#注意将-days设置大点，以免证书过期。
#2、fqdn
# 不需要修改openssl.cnf文件。
cd /etc/pki/tls
openssl req -subj '/CN=logstash.sudo.com/' -x509 -days 3650 -batch -nodes -newkey rsa:2048 -keyout private/logstash-forwarder.key -out certs/logstash-forwarder.crt
logstash.sudo.com是我自己测试的域名,所以无需添加logstash.sudo.com的A记录
 
#Logstash-Config
#添加GeoIP数据源
#wget http://geolite.maxmind.com/download/geoip/database/GeoLiteCity.dat.gz
#gzip -d GeoLiteCity.dat.gz && mv GeoLiteCity.dat /etc/logstash/.
logstash配置文件是以json格式设置参数的，配置文件位于/etc/logstash/conf.d目录下，配置包括三个部分：输入端，过滤器和输出。
首先，创建一个01-lumberjack-input.conf文件，设置lumberjack输入，Logstash-Forwarder使用的协议。
vi /etc/logstash/conf.d/01-lumberjack-input.conf
input {
  lumberjack {
    port => 5043
    type => "logs"
    ssl_certificate => "/etc/pki/tls/certs/logstash-forwarder.crt"
    ssl_key => "/etc/pki/tls/private/logstash-forwarder.key"
  }
}
再来创建一个11-nginx.conf用于过滤nginx日志
vi /etc/logstash/conf.d/11-nginx.conf 
filter {
  if [type] == "nginx" {
    grok {
      match => { "message" => "%{IPORHOST:clientip} - %{NOTSPACE:remote_user} \[%{HTTPDATE:timestamp}\] \"(?:%{WORD:method} %{NOTSPACE:request}(?: %{URIPROTO:proto}/%{NUMBER:httpversion})?|%{DATA:rawrequest})\" %{NUMBER:status} (?:%{NUMBER:size}|-) %{QS:referrer} %{QS:a
gent} %{QS:xforwardedfor}" }
      add_field => [ "received_at", "%{@timestamp}" ]
      add_field => [ "received_from", "%{host}" ]
    }
    date {
        match => [ "timestamp" , "dd/MMM/YYYY:HH:mm:ss Z" ]
    }
#   geoip {
#        source => "clientip"
#        add_tag => [ "geoip" ]
#        fields => ["country_name", "country_code2","region_name", "city_name", "real_region_name", "latitude", "longitude"]
#         remove_field => [ "[geoip][longitude]", "[geoip][latitude]" ]
#   }
  }
}
这个过滤器会寻找被标记为“nginx”类型（Logstash-forwarder定义的）的日志，尝试使用“grok”来分析传入的nginx日志，使之结构化和可查询。type要与logstash-forwarder相匹配。
同时，要注意nginx日志格式设置，我这里采用默认log_format。
#负载均衡反向代理时可修改为如下格式：
log_format main '$remote_addr - $remote_user [$time_local] "$request" '   
             '$status $upstream_response_time $request_time $body_bytes_sent '
             '"$http_referer" "$http_user_agent" "$http_x_forwarded_for" "$request_body" '
             '$scheme $upstream_addr';
日志格式不对，grok匹配规则要重写。
可以通过http://grokdebug.herokuapp.com/在线工具进行调试。多数情况下ELK没数据的错误在此处。
#Grok Debug -- http://grokdebug.herokuapp.com/
grok 匹配日志不成功，不要往下看测试。之道匹配成功对为止。可参考ttp://grokdebug.herokuapp.com/patterns#   grok匹配模式，对后面写规则匹配很受益的。
最后，创建一文件，来定义输出。
vi /etc/logstash/conf.d/99-lumberjack-output.conf 
output {
    if "_grokparsefailure" in [tags] {
      file { path => "/var/log/logstash/grokparsefailure-%{type}-%{+YYYY.MM.dd}.log" }
    }
    elasticsearch {
        host => "192.168.28.131"
        protocol => "http"
        index => "logstash-%{type}-%{+YYYY.MM.dd}"
        document_type => "%{type}"
        workers => 5
        template_overwrite => true
    }
    #stdout { codec =>rubydebug }
}
定义结构化的日志存储到elasticsearch，对于不匹配grok的日志写入到文件。注意，后面添加的过滤器文件名要位于01-99之间。因为logstash配置文件有顺序的。
在调试时候，先不将日志存入到elasticsearch，而是标准输出，以便排错。同时，多看看日志，很多错误在日志里有体现，也容易定位错误在哪。
在启动logstash服务之前，最好先进行配置文件检测，如下：
# /opt/logstash/bin/logstash --configtest -f /etc/logstash/conf.d/*
Configuration OK
也可指定文件名检测，直到OK才行。不然，logstash服务器起不起来。最后，就是启动logstash服务了。
 
#logstash-forwarder
需要将在安装logstash时候创建的ssl证书的公钥logstash.crt拷贝到每台logstash-forwarder服务器(需监控日志的server)
wget https://download.elastic.co/logstash-forwarder/binaries/logstash-forwarder-0.4.0-1.x86_64.rpm
rpm -ivh logstash-forwarder-0.4.0-1.x86_64.rpm
vi /etc/logstash-forwarder.conf
{
  "network": {
    "servers": [ "192.168.28.131:5043" ],
    "ssl ca": "/etc/pki/tls/certs/logstash-forwarder.crt",
    "timeout": 30
  },
 
  "files": [
    {
        "paths": [ "/var/log/nginx/*-access.log" ],
        "fields": { "type": "nginx" }
    } 
  ]
}
配置文件是json格式，格式不对logstash-forwarder服务是启动不起来的。
后面就是启动logstash-forwarder服务了
 
echo -e "192.168.28.131 Test1\n192.168.28.130 Test2\n192.168.28.138 Test3">>/etc/hosts  #不添加elasticsearch启动会报错(无法识别Test*)
su - elk
cd /usr/local/elasticsearch-1.7.2
nohup ./bin/elasticsearch &
（可以通过supervisord进行管理，与其他服务一同开机启动）
 
elk:
service logstash restart
service kibana restart
访问http://elk.sudo.com:9200/查询启动是否成功
 
client:
service nginx start &&  service logstash-forwarder start
 
 
 
#使用redis存储日志(队列)，创建对应的配置文件
vi /etc/logstash/conf.d/redis-input.conf 
input {
  lumberjack {
    port => 5043
    type => "logs"
    ssl_certificate => "/etc/pki/tls/certs/logstash-forwarder.crt"
    ssl_key => "/etc/pki/tls/private/logstash-forwarder.key"
  }
}
filter {
  if [type] == "nginx" {
    grok {
      match => { "message" => "%{IPORHOST:clientip} - %{NOTSPACE:remote_user} \[%{HTTPDATE:timestamp}\] \"(?:%{WORD:method} %{NOTSPACE:request}(?: %{URIPROTO:proto}/%{NUMBER:httpversion})?|%{DATA:rawrequest})\" %{NUMBER:status} (?:%{NUMBER:size}|-) %{QS:referrer} %{QS:a
gent} %{QS:xforwardedfor}" }
      add_field => [ "received_at", "%{@timestamp}" ]
      add_field => [ "received_from", "%{host}" ]
    }
    date {
        match => [ "timestamp" , "dd/MMM/YYYY:HH:mm:ss Z" ]
    }
#test
  }
}
output {
    ####将接收的日志放入redis消息队列####
    redis {
        host => "127.0.0.1"
        port => 6379
        data_type => "list"
        key => "logstash:redis"
    }
}
vi /etc/logstash/conf.d/redis-output.conf 
input {
    # 读取redis
    redis {
        data_type => "list"
        key => "logstash:redis"
        host => "192.168.28.131"  #redis-server
        port => 6379
        #threads => 5
	 }
}
output {
    elasticsearch {
        host => "192.168.28.131"
        protocol => "http"
        index => "logstash-%{type}-%{+YYYY.MM.dd}"
        document_type => "%{type}"
        workers => 36
        template_overwrite => true
    }
    #stdout { codec =>rubydebug }
}
# /opt/logstash/bin/logstash --configtest -f /etc/logstash/conf.d/*
Configuration OK
登录redis查询，可以看到日志的对应键值信息已经写入