nginx request_time

Posted by 夏泽民

1、request_time 官网描述:request processing time in seconds with a milliseconds resolution; time elapsed between the first bytes were read from the client and the log write after the last bytes were sent to the client 。 指的就是从接受用户请求的第一个字节到发送完响应数据的时间,即包括接收请求数据时间、程序响应时间、输出响应数据时间。

2、upstream_response_time 官网描述:keeps times of responses obtained from upstream servers; times are kept in seconds with a milliseconds resolution. Several response times are separated by commas and colons like addresses in the $upstream_addr variable

是指从Nginx向后端(php-cgi)建立连接开始到接受完数据然后关闭连接为止的时间。

从上面的描述可以看出,$request_time肯定大于等于$upstream_response_time,特别是使用POST方式传递参数时,因为Nginx会把request body缓存住,接受完毕后才会把数据一起发给后端。所以如果用户网络较差,或者传递数据较大时,$request_time会比$upstream_response_time大很多。

所以如果使用nginx的accesslog查看php程序中哪些接口比较慢的话,记得在log_format中加入$upstream_response_time。

根据引贴对官网描述的翻译: upstream_response_time:从 Nginx 建立连接 到 接收完数据并关闭连接 request_time:从 接受用户请求的第一个字节 到 发送完响应数据



mysql instant add colum

Posted by 夏泽民

“Instant ADD COLUMN”,即“瞬加字段功能” 鹅厂工程师通过扩展MySQL InnoDB的存储格式,可以把原来几个小时才能完成的给表加字段命令,在1秒之内执行完成,更新TB级的表都是毛毛雨,有效地提高了数据库的管理效率,降低运维成本。 随着MySQL新版本的发布,陈福荣和梁飞龙将该特性提交到MySQL 8.0.12



mysql ddl-ghost

Posted by 夏泽民

GHOST工作原理:



TIME_WAIT和CLOSE_WAIT

Posted by 夏泽民
netstat -n awk ‘/^tcp/ {++S[$NF]} END {for(a in S) print a, S[a]}’


netpoller

Posted by 夏泽民

Go中网络交互采用多路复用的技术,具体到各个平台,即Kqueue、Epoll、Select、Poll等,下面以Linux下的Epoll实现为例进行分析。



Search

Popular posts

Anything in here will be replaced on browsers that support the canvas element

Recent posts

This blog is maintained by 夏泽民

Get in touch with me at [email protected]

Subscribe to our mailing list

* indicates required