社区微信群开通啦,扫一扫抢先加入社区官方微信群
社区微信群
对于互联网公司来说,nginx的请求日志简直就是一座金矿,如果不能充分利用,简直太可惜了。
初期一般都是输出到日志文件,要查什么就awkgrepuniqsort...,能满足不少统计需求,但最大的缺点是不直观,不方便监控(目前虽然用了ELK,但是有些信息我还是用shell统计,两者互补)。
整理下实施ELK最起码要实现的需求:
nginx需要配置syslog协议输出;
logstash作为syslog服务器,收集日志,输出2个方向:elastersearch入库,本地文件;
elasticsearch需要设计好模型,目的:支持不同字段的查找需求(精确或模糊,甚至某个字段同时要支持精确+模糊,不过我没用到)、空间不浪费;
kibana可视化,主要是配置DiscoveryVisualize;
elastalert,配置各种规则,实现实时监控需求。
nginx.conf
日志以json格式输出,方便logstash解析;
因为syslog协议一条消息最大2K,因此有些变了做了阶段(_short后缀的变量);
level1domain、level2domain分别指一级域名、二级域名;
log_format main_json '{"project":"${level1domain}","domain":"${level1domain}_${level2domain}","real_ip":"$real_ip","http_x_forwarded_for":"$http_x_forwarded_for","time_local":"$time_iso8601","
request":"$request_short","request_body":"$request_body_short","status":$status,"body_bytes_sent":"$body_bytes_sent","http_referer":"$http_referer_short","upstream_response_time":"$upstream_re
sponse_time","request_time":"$request_time","http_user_agent":"$http_user_agent"}';
location.conf
#取前750个字节
if ( $request ~ "^(.{0,750})" ) {
set $request_short $1;
}
#取前750个字节
if ( $request_body ~ "^(.{0,750})" ) {
set $request_body_short $1;
}
#取前100个字节
set $http_referer_short "-";
if ( $http_referer ~ "^(.{1,100})" ) {
set $http_referer_short $1;
}
#从$http_x_forward_for中获取第一个IP,作为客户端实际IP
set $real_ip $remote_addr;
if ( $http_x_forwarded_for ~ "^(d+.d+.d+.d+)" ) {
set $real_ip $1;
}
#server_name的格式是:N级域名.……三级域名.二级域名.一级域名.com或cn,或者一级域名.com或cn;
#解析一级域名部分为$level1domain
#解析一级域名之前的部分为$level2domain
set $level1domain unparse;
set $level2domain unparse;
if ( $server_name ~ "^(.+).([0-9a-zA-Z]+).(com|cn)$" ) {
set $level1domain $2;
set $level2domain $1;
}
if ( $server_name ~ "^([0-9a-zA-Z]+).(com|cn)$" ) {
set $level1domain $1;
set $level2domain none;
}
#syslog输出配置
access_log syslog:local7:info:logstash_ip:515:nginx main_json;
安装:
安装jdk8
解压logstash-6.2.1.tar.gz
查看插件:
./logstash-plugin list | grep syslog
安装非默认插件
./logstash-plugin install logstash-filter-alter
测试:
# ./logstash -e 'input { stdin { } } output { stdout {} }'
启动:
启动logstash:nohup ./bin/logstash -f mylogstash.conf & disown
配置:
mylogstash.conf
input {
syslog {
type => "system-syslog"
port => 515
}
}
filter {
#在json化之前,使用mutte对\x字符串进行替换,防止以下错误:ParserError: Unrecognized character escape 'x' (code 120)
mutate {
gsub => ["message", "\x", "\x"]
}
json {
source => "message"
#删除无用字段,节约空间
remove_field => "message"
remove_field => "severity"
remove_field => "pid"
remove_field => "logsource"
remove_field => "timestamp"
remove_field => "facility_label"
remove_field => "type"
remove_field => "facility"
remove_field => "@version"
remove_field => "priority"
remove_field => "severity_label"
}
date {
#用nginx请求时间替换logstash生成的时间
match => ["time_local", "ISO8601"]
target => "@timestamp"
}
grok {
#从时间中获取day
match => { "time_local" => "(?<day>.{10})" }
}
grok {
#将request解析成2个字段:methodurl
match => { "request" => "%{WORD:method} (?<url>.* )" }
}
grok {
#截取http_referer问号前的部分,问号后的信息无价值,浪费空间
match => { "http_referer" => "(?<referer>-|%{URIPROTO}://(?:%{USER}(?::[^@]*)?@)?(?:%{URIHOST})?)" }
}
mutate {
#解析出新的字段后,原字段丢弃
remove_field => "request"
remove_field => "http_referer"
rename => { "http_user_agent" => "agent" }
rename => { "upstream_response_time" => "response_time" }
rename => { "host" => "log_source" }
rename => { "http_x_forwarded_for" => "x_forwarded_for" }
#以下2个字段以逗号分隔后,以数组形式入库
split => { "x_forwarded_for" => ", " }
split => { "response_time" => ", " }
}
alter {
#不满足elasticsearch索引模型的,入库会失败,因此做以下数据转换
condrewrite => [
"x_forwarded_for", "-", "0.0.0.0",
"x_forwarded_for", "unknown", "0.0.0.0",
"response_time", "-", "0",
"real_ip", "", "0.0.0.0"
]
}
}
output {
#入库,以template指定的模型作为索引模型
elasticsearch {
hosts => ["elasticsearch_ip:9200"]
index => "nginx-%{day}"
manage_template => true
template_overwrite => true
template_name => "mynginx"
template => "/root/logstash/mynginxtemplate.json"
codec => json
}
#本地文件放一份,作为ELK的补充
file {
flush_interval => 600
path => '/nginxlog/%{day}/%{domain}.log'
codec => line { format => '<%{time_local}> <%{real_ip}> <%{method}> <%{url}> <%{status}> <%{request_time}> <%{response_time}> <%{body_bytes_sent}> <%{request_body}> <%{referer}> <%{x_f
orwarded_for}> <%{log_source}> <%{agent}>'}
}
}
mynginxtemplate.json
{
"template": "nginx-*",
"settings": {
"index.number_of_shards": 8,
"number_of_replicas": 0,
"analysis": {
"analyzer": {
#自定义stop关键字,不收集http等字段的索引
"stop_url": {
"type": "stop",
"stopwords": ["http","https","www","com","cn","net"]
}
}
}
},
"mappings" : {
"doc" : {
"properties" : {
# index:true 分词、生产搜索引擎
# analyzer:指定索引分析器
"referer": {
"type": "text",
"norms": false,
"index": true,
"analyzer": "stop_url"
},
"agent": {
"type": "text",
"norms": false,
"index": true
},
# IP字段类型
"real_ip": {
"type": "ip"
},
"x_forwarded_for": {
"type": "ip"
},
# keyword,作为完整字段索引,不可分词索引
"status": {
"type": "keyword"
},
"method": {
"type": "keyword"
},
"url": {
"type": "text",
"norms": false,
"index": true,
"analyzer": "stop_url"
},
"status": {
"type": "keyword"
},
"response_time": {
"type": "half_float"
},
"request_time": {
"type": "half_float"
},
"domain": {
"type": "keyword"
},
"project": {
"type": "keyword"
},
"request_body": {
"type": "text",
"norms": false,
"index": true
},
"body_bytes_sent": {
"type": "long"
},
"log_source": {
"type": "ip"
},
"@timestamp" : {
"type" : "date",
"format" : "dateOptionalTime",
"doc_values" : true
},
"time_local": {
"enabled": false
},
"day": {
"enabled": false
}
}
}
}
}
elasticsearch.yml
cluster.name: nginxelastic
# 节点名称,每个节点不同
node.name: node1
bootstrap.system_call_filter: false
bootstrap.memory_lock: true
# 本节点IP
network.host: 10.10.10.1
http.port: 9200
transport.tcp.port: 9300
# 单播自动发现,配置集群中其他节点的IP+端口,host1:port1,host2:port2,本例中只有2个节点,因此只配置另一个节点的IP和端口
discovery.zen.ping.unicast.hosts: ["other_node_ip:9300"]
# 一个节点需要看到的具有master节点资格的最小数量,推荐(N/2)+1
discovery.zen.minimum_master_nodes: 2
http.cors.enabled: true
http.cors.allow-origin: /.*/
path.data: /elastic/data
path.logs: /elastic/logs
jvm.options# jvm初始和最大内存,建议设置为服务器内存的一半
-Xms8g
-Xmx8g
crontab自动删除历史数据del_index.sh
#!/bin/bash
DELINDEX="nginx-"`date -d "-30 day" +%Y-%m-%d`
curl -H "Content-Type: application/json" -XDELETE 'http://10.10.10.1:9200/'"${DELINDEX}"
kibana.yml
server.port: 80
server.host: 10.10.10.3
elasticsearch.url: "http://10.10.10.1:9200"
elasticsearch.username: "kibana"
elasticsearch.password: "mypwd"
界面设置:
management -> advanced settings:
dateFormat(日期格式):YYYYMMDD HH:mm:ss
defaultColumns(默认字段): method, url, status, request_time, real_ip
查询某域名下耗时超过1秒的请求
查询过去24小时各域名请流量柱状图
官方有个watcher可用于实时监控ELK收集的日志,可惜是商业版的,想用免费的,elastalert是个不错的方案。
https://github.com/Yelp/elastalert
elastalert常用的监控类型有frequencyspike等(http://elastalert.readthedocs.io/en/latest/ruletypes.html#rule-types)
这里以frequency类型的监控为例,实时监控500状态错误。
config.yaml
# 指定es地址
es_host: 10.10.10.1
es_port: 9200
freq-500.yaml
#文件名自定义,容易区分即可
es_host: 10.10.10.1
es_port: 9200
name: elk-nginx-freq-500
type: frequency
index: nginx-*
# 周期内出现10次以上则报警
num_events: 10
# 周期1分钟
timeframe:
minutes: 1
# 查询条件
# status in (500,501,502,503,504)
# domain 不包含test,即测试域名下的事件忽略
filter:
- bool:
must:
- terms:
status: ["500","501","502","503","504"]
must_not:
- wildcard:
domain: "*test*"
# 对每个domain单独计算num_events,最多计算10个domain,某个domain的num_events达到10个,才会报警
use_terms_query: true
doc_type: doc
terms_size: 10
query_key: domain
# 分别以domain和status列出top5的keys数量,报警邮件中提高top 5 domain和top 5 status
top_count_keys:
- domain
- status
top_count_number: 5
raw_count_keys: false
# 10分钟内不重复报警
realert:
minutes: 10
# 分别通过command(短信)和email报警
alert:
- command
- email
# 自己写的调用短信接口的命令发生短信,短信内容比较简单,通知什么域名出现500状态报警
new_style_string_format: true
command: ["/root/elastalert-0.1.29/myalert/sms.sh", "15800000000", "elk nginx warning - freq 500 exceed, domain: {match[domain]}"]
# 以下是elastalert封装好的email报警配置
# smtp_auth_file.yaml中配置邮件的用户名密码
smtp_host: smtp.exmail.qq.com
smtp_port: 465
smtp_ssl : true
from_addr: "elastalert@mydomain.com"
smtp_auth_file: "/root/elastalert-0.1.29/myalert/smtp_auth_file.yaml"
email:
- "myemail@mydomain.com"
alert_subject: "elk nginx warning - freq 500 exceed, domain: {0}"
alert_subject_args:
- domain
启动监控:python -m elastalert.elastalert --verbose --rule freq-500.yaml >> freq-500.log 2>&1 & disown
报警邮件
如果觉得我的文章对您有用,请随意打赏。你的支持将鼓励我继续创作!