十一、nginx的日志及favicon.ico

nginx的日志分为log_format和access_log两个控制参数

log_format 用来定义记录日志的格式（可以定义多种日志格式，取不同的名字）。
access_log 用来指定日志文件的路径及使用何种日志格式记录日志。

语法格式

Syntax:    access_log path [format [buffer=size] [gzip[=level]] [flush=time] [if=condition]];
access_log off;
Default:    access_log logs/access.log combined;
Context:    http, server, location, if in location, limit_except

案例配置

log_format compression '$remote_addr - $remote_user [$time_local] '
                       '"$request" $status $bytes_sent '
                       '"$http_referer" "$http_user_agent" "$gzip_ratio"';

access_log /spool/logs/nginx-access.log compression buffer=32k;

测试案例

nginx.conf的配置文件

user  www;
worker_processes  1;

events {
    worker_connections  1024;
}


http {
    include       mime.types;
    default_type  application/octet-stream;

    log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '
                      '$status $body_bytes_sent "$http_referer" '
                      '"$http_user_agent" "$http_x_forwarded_for"';

    access_log  logs/access.log  main;
    sendfile        on;
    #tcp_nopush     on;
    #keepalive_timeout  0;
    keepalive_timeout  65;
    #gzip  on;
    server {
        listen       80;
        server_name  localhost;
        location / {
            root   html;
            index  index.html index.htm;
        }

        error_page   500 502 503 504  /50x.html;
        location = /50x.html {
            root   html;
        }
    }
}
       

重新加载配置文件后，访问nginx,nginx日志的内容

[root@node1 conf]# cat /usr/local/nginx/logs/access.log 
10.0.0.1 - - [07/Sep/2020:21:21:32 +0800] "GET / HTTP/1.1" 200 612 "-" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36"
10.0.0.1 - - [07/Sep/2020:21:21:32 +0800] "GET /favicon.ico HTTP/1.1" 404 555 "http://10.0.0.101/" "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36"
10.0.0.101 - - [08/Sep/2020:19:23:58 +0800] "GET / HTTP/1.1" 200 612 "-" "curl/7.29.0"
10.0.0.101 - - [08/Sep/2020:19:24:03 +0800] "GET /bbs HTTP/1.1" 404 153 "-" "curl/7.29.0"
10.0.0.101 - - [08/Sep/2020:19:24:08 +0800] "GET /bbs HTTP/1.1" 404 153 "-" "curl/7.29.0"
10.0.0.101 - - [08/Sep/2020:19:24:16 +0800] "GET /bbs HTTP/1.1" 301 169 "-" "curl/7.29.0"
10.0.0.101 - - [08/Sep/2020:19:24:24 +0800] "GET /bbs HTTP/1.1" 301 169 "-" "curl/7.29.0"
10.0.0.101 - - [08/Sep/2020:19:24:24 +0800] "GET /bbs/ HTTP/1.1" 200 5 "-" "curl/7.29.0"
10.0.0.102 - - [09/Sep/2020:16:48:33 +0800] "GET / HTTP/1.1" 200 16 "-" "curl/7.29.0"
10.0.0.102 - - [09/Sep/2020:16:50:30 +0800] "GET / HTTP/1.1" 200 16 "-" "curl/7.29.0"
10.0.0.103 - - [09/Sep/2020:16:52:45 +0800] "GET / HTTP/1.1" 200 16 "-" "curl/7.29.0"
10.0.0.103 - - [09/Sep/2020:16:54:27 +0800] "GET / HTTP/1.1" 403 153 "-" "curl/7.29.0"

定义json日志格式

nginx 的默认访问日志记录内容相对比较单一，默认的格式也不方便后期做日志统计分析，生产环境中通常将nginx日志转换为json日志，然后配合使用ELK做日志收集-统计-分析

自定义json日志格式

log_format access_json '{"@timestamp":"$time_iso8601",'
'"host":"$server_addr",'
'"clientip":"$remote_addr",'
'"size":$body_bytes_sent,'
'"responsetime":$request_time,'
'"upstreamtime":"$upstream_response_time",'
'"upstreamhost":"$upstream_addr",'
'"http_host":"$host",'
'"uri":"$uri",'
'"domain":"$host",'
'"xff":"$http_x_forwarded_for",'
'"referer":"$http_referer",'
'"tcp_xff":"$proxy_protocol_addr",'
'"http_user_agent":"$http_user_agent",'
'"status":"$status"}';
access_log /apps/nginx/logs/access_json.log access_json;

json格式的访问日志示例：

{"@timestamp":"2019-02-
22T08:55:32+08:00","host":"192.168.7.102","clientip":"192.168.0.1","size":162,"resp
onsetime":0.000,"upstreamtime":"-","upstreamhost":"-
","http_host":"www.magedu.net","uri":"/favicon.ico","domain":"www.magedu.net","xff"
:"-","referer":"-","tcp_xff":"","http_user_agent":"Mozilla/5.0 (Windows NT 6.1;
Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0","status":"404"}

json格式的日志访问统计

#cat nginx_json.py
#!/usr/bin/env python
#coding:utf-8
status_200= []
status_404= []
with open("access_json.log") as f:
for line in f.readlines():
line = eval(line)
if line.get("status") == "200":
status_200.append(line.get)
elif line.get("status") == "404":
status_404.append(line.get)
else:
print("状态码 ERROR")
f.close()
print "状态码200的有--:",len(status_200)
print "状态码404的有--:",len(status_404)
# python nginx_json.py
状态码200的有--: 1910
状态码404的有--: 13

nginx日志缓存

Syntax:    open_log_file_cache max=N [inactive=time] [min_uses=N] [valid=time];
open_log_file_cache off;
Default:    open_log_file_cache off;
Context:    http, server, location

定义一个缓存，用于存储名称中包含变量的常用日志的文件描述符

max：缓存的最大文件描述符数量
min_uses：在inactive指定的时长内访问大于等于此值方可被当作活动项
inactive：非活动时长
valid：验证缓存中各缓存项是否为活动项的时间间隔

关于favicon.ico

favicon.ico 文件是浏览器收藏网址时显示的图标，当使用浏览器访问页面时，浏览器会自己主动发起请求获取页面的favicon.ico文件，但是当浏览器请求的favicon.ico文件不存在时，服务器会记录404日志，而且浏览器也会显示404报错
解决方案：
服务器不记录访问日志：
location = /favicon.ico {
log_not_found off; #文件没发现事件不记录error_log
access_log off; #不记录access_log
}
将图标保存到指定目录访问：
#location ~ ^/favicon\.ico$ {
location = /favicon.ico {
root /data/nginx/html/pc/images;
}