初探ELK-以收集 nginx 日志为例示范搭建一个 ELK 环境的基本步骤
初探ELK-以收集 nginx 日志为例示范搭建一个 ELK 环境的基本步骤
2017/2/15
一、环境
1、RPM
1）收集 rpm 包
wget https://download.elastic.co/logstash/logstash/packages/centos/logstash-2.4.0.noarch.rpm
wget https://download.elastic.co/elasticsearch/release/org/elasticsearch/distribution/rpm/elasticsearch/2.4.0/elasticsearch-2.4.0.rpm
wget https://download.elastic.co/kibana/kibana/kibana-4.6.1-x86_64.rpm
wget https://download.elastic.co/beats/filebeat/filebeat-1.3.1-x86_64.rpm
2）缓存rpm包到本地yum源
2、安装
【服务端】
1）ELK
[root@vm220 ~]# yum install elasticsearch kibana logstash -y
2）jdk
（略）
【客户端】
1）filebeat
[root@vm49 ~]# yum install filebeat -y
3、前提
假设要收集下面2个域名的 access 和 error 日志：
www.test.com
www.work.com
其中 access 日志的格式如下：
log_format online '$remote_addr [$time_local] "$request" '
'"$http_content_type" "$request_body" "$http_referer" '
'$status $request_time $body_bytes_sent';
而 error 日志采取默认的级别（error）。
且要求：为每个域名使用独立的 index
二、ELK 服务端配置
1、配置 elasticsearch 服务【存储数据（来自 logstash ）】
1）配置文件
[root@vm220 ~]# mkdir -p /data/elasticsearch
[root@vm220 ~]# chown elasticsearch:elasticsearch /data/elasticsearch
[root@vm220 ~]# cp -a /etc/elasticsearch/elasticsearch.yml{,.bak}
调整配置文件：
【如果 ES 是单节点】
[root@vm220 ~]# grep ^[^#] /etc/elasticsearch/elasticsearch.yml
cluster.name: es-cluster-test
node.name: node-vm220
path.data: /data/elasticsearch
path.logs: /var/log/elasticsearch
network.host: 0.0.0.0
【如果 elasticsearch 是集群】
[root@vm220 ~]# grep ^[^#] /etc/elasticsearch/elasticsearch.yml
cluster.name: es-cluster-test
node.name: node-vm220
path.data: /data/elasticsearch
path.logs: /var/log/elasticsearch
network.host: 0.0.0.0
discovery.zen.ping.unicast.hosts: ["10.50.200.218", "10.50.200.219", "10.50.200.220"]
discovery.zen.minimum_master_nodes: 3
其他节点类似
2）启动服务
[root@vm220 ~]# service elasticsearch start
[root@vm220 ~]# chkconfig elasticsearch on
2、配置 kibana 服务【展示数据（来自 elasticsearch ）】
1）配置文件
[root@vm220 ~]# service kibana start
2）启动服务
[root@vm220 ~]# chkconfig kibana on
3）访问
http://10.50.200.220:5601/app/kibana
3、配置 logstash 服务【过滤数据（来自 filebeat 发往 elasticsearch）】
1）配置自定义的 pattern
[root@vm220 ~]# mkdir -p /etc/logstash/patterns.d
[root@vm220 ~]# cat /etc/logstash/patterns.d/extra_patterns
NGINXACCESS %{IPORHOST:clientip} [%{HTTPDATE:timestamp}] "%{WORD:verb} %{URIPATHPARAM:request} HTTP/%{NUMBER:httpversion}" (?:%{QS:content_type}|-) (?:%{QS:request_body}|-) (?:"(?:%{URI:referrer}|-)"|%{QS:referrer}) %{NUMBER:response} %{BASE16FLOAT:request_time} (?:%{NUMBER:bytes}|-)
NGINXERROR_DATESTAMP %{YEAR}/%{MONTHNUM}/%{MONTHDAY} %{TIME}
NGINXERROR_PID (?:[0-9]+#[0-9]+:)
NGINXERROR_TID (?:*[0-9]+)
NGINXERROR %{NGINXERROR_DATESTAMP:timestamp} [%{LOGLEVEL:loglevel}] %{NGINXERROR_PID:pid} %{NGINXERROR_TID:tid} %{GREEDYDATA:errormsg}, client: %{IPORHOST:clientip}, server: %{HOSTNAME:server}, request: %{QS:request}(?:, upstream: %{QS:upstream})?, host: \"%{HOSTNAME:hostname}\"(?:, referrer: (?:"(?:%{URI:referrer}|-)"|%{QS:referrer}))?
2）调整配置文件
[root@vm220 ~]# cat /etc/logstash/conf.d/filebeat.conf
input {
beats {
port => "5044"
}
}
filter {
if[type] =~ "NginxAccess-" {
grok {
patterns_dir => ["/etc/logstash/patterns.d"]
match => {
"message" => "%{NGINXACCESS}"
}
}
date {
match => [ "timestamp", "dd/MMM/YYYY:HH:mm:ss Z" ]
remove_field => [ "timestamp" ]
}
}
if[type] =~ "NginxError-" {
grok {
patterns_dir => ["/etc/logstash/patterns.d"]
match => {
"message" => "%{NGINXERROR}"
}
}
date {
match => [ "timestamp", "YYYY/MM/dd HH:mm:ss" ]
remove_field => [ "timestamp" ]
}
}
}
output {
if[type] == "NginxAccess-www.test.com" {
elasticsearch {
hosts =>"10.50.200.220:9200"
manage_template => false
index => "%{[@metadata][beat]}-nginxaccess-www.test.com-%{+YYYY.MM.dd}"
document_type => "%{[@metadata][type]}"
}
}
if[type] == "NginxAccess-www.work.com" {
elasticsearch {
hosts =>"10.50.200.220:9200"
manage_template => false
index => "%{[@metadata][beat]}-nginxaccess-www.work.com-%{+YYYY.MM.dd}"
document_type => "%{[@metadata][type]}"
}
}
if[type] == "NginxError-www.test.com" {
elasticsearch {
hosts =>"10.50.200.220:9200"
manage_template => false
index => "%{[@metadata][beat]}-nginxerror-www.test.com-%{+YYYY.MM.dd}"
document_type => "%{[@metadata][type]}"
}
}
if[type] == "NginxError-www.work.com" {
elasticsearch {
hosts =>"10.50.200.220:9200"
manage_template => false
index => "%{[@metadata][beat]}-nginxerror-www.work.com-%{+YYYY.MM.dd}"
document_type => "%{[@metadata][type]}"
}
}
}
【如果 elasticsearch 是集群】
将：
hosts =>"10.50.200.220:9200"
调整为：
hosts => ["10.50.200.218:9200", "10.50.200.219:9200", "10.50.200.220:9200"]
3）启动服务
[root@vm220 ~]# service logstash restart
[root@vm220 ~]# chkconfig logstash on
三、使用 filebeat 在客户端收集日志。
1）配置 filebeat 服务
[root@vm49 ~]# cp /etc/filebeat/filebeat.yml{,.bak}
[root@vm49 ~]# cat /etc/filebeat/filebeat.yml |grep -Ev '^(#| #| #| #| #|$)'
filebeat:
prospectors:
-
paths:
- /var/log/nginx/access_www.test.com*.log
input_type: log
document_type: NginxAccess-www.test.com
-
paths:
- /var/log/nginx/access_www.work.com*.log
input_type: log
document_type: NginxAccess-www.work.com
-
paths:
- /var/log/nginx/error_www.test.com*.log
input_type: log
document_type: NginxError-www.test.com
-
paths:
- /var/log/nginx/error_www.work.com*.log
input_type: log
document_type: NginxError-www.work.com
registry_file: /var/lib/filebeat/registry
output:
logstash:
hosts: ["10.50.200.220:5044"]
shipper:
logging:
to_files: true
files:
path: /var/log/filebeat
name: filebeat
rotateeverybytes: 10485760 # = 10MB
2）导入安装 filebeat 时，自带的模版
模版路径：/etc/filebeat/filebeat.template.json
自己可以在默认的模版的基础上做调整，例如，对比默认配置，新增的内容为：
"dynamic_templates": [
{
"template1": {
"mapping": {
"doc_values": true,
"ignore_above": 1024,
"index": "not_analyzed",
"type": "{dynamic_type}"
},
"match": "*"
}
}
],
（略）
"type" : {
"type" : "string",
"index": "not_analyzed"
},
"input_type" : {
"type" : "string",
"index": "no"
},
"beat" : {
"properties" : {
"hostname" : {
"type" : "string",
"index": "not_analyzed",
"doc_values": "true"
},
"name" : {
"type" : "string",
"index": "not_analyzed",
"doc_values": "true"
}
}
},
"source" : {
"type" : "string",
"index": "no"
},
"offset": {
"type": "long",
"index": "no"
},
"count" : {
"type" : "long",
"index": "no"
},
"host" : {
"type" : "string",
"index": "not_analyzed"
},
"tags" : {
"type" : "string",
"index": "not_analyzed"
},
"bytes" : {
"type" : "long",
"index": "not_analyzed"
},
"geoip" : {
"properties" : {
"location" : {
"type" : "geo_point",
"index": "not_analyzed"
}
}
}
（略）
a、导入模版
[root@vm220 ~]# curl -XPUT 'http://10.50.200.220:9200/_template/filebeat?pretty' -d@/etc/filebeat/filebeat.template.json
b、查看模版
[root@vm220 ~]# curl 'http://10.50.200.220:9200/_template/filebeat?pretty'
c、清理旧的 index（如果是新配置的服务，没有生成任何 index 因此也不需要清理，可略过这一步）
先查看现有的 index
[root@vm220 ~]# curl '10.50.200.220:9200/_cat/indices?v'
删除 filebeat-* 匹配的所有 index
[root@vm220 ~]# curl -XDELETE 'http://10.50.200.220:9200/filebeat-*?pretty'
再次查看，确认一下结果是否符合预期：
[root@vm220 ~]# curl '10.50.200.220:9200/_cat/indices?v'
3）启动服务
[root@vm49 ~]# service filebeat restart
[root@vm49 ~]# chkconfig filebeat on