如何測(cè)試Nginx的高性能
簡(jiǎn)介
Nginx ("engine x") 是一個(gè)高性能的HTTP和反向代理服務(wù)器,也是一個(gè)IMAP/POP3/SMTP代理服務(wù)器;
作為一款輕量級(jí)的Web服務(wù)器,具有占有內(nèi)存少,并發(fā)能力強(qiáng)等優(yōu)勢(shì),是高連接并發(fā)場(chǎng)景下Apache的不錯(cuò)的替代品;
本篇主要介紹Nginx作為Web服務(wù)器時(shí),相對(duì)于Apache的性能優(yōu)勢(shì);
下一篇將會(huì)介紹Nginx作為方向代理服務(wù)器的實(shí)現(xiàn);
重要特點(diǎn)
非阻塞:數(shù)據(jù)復(fù)制時(shí),磁盤(pán)I/O的第一階段是非阻塞的;
事件驅(qū)動(dòng):通信機(jī)制采用epoll模型,支持更大的并發(fā)連接;
master/worker結(jié)構(gòu):一個(gè)master進(jìn)程,生成一個(gè)或多個(gè)worker進(jìn)程;
基礎(chǔ)架構(gòu)
Nginx如何實(shí)現(xiàn)高并發(fā):
I/O模型采用異步非阻塞的事件驅(qū)動(dòng)機(jī)制,由進(jìn)程循環(huán)處理多個(gè)準(zhǔn)備好的事件,如epoll機(jī)制;
Nginx與Apache對(duì)高并發(fā)處理上的區(qū)別:
對(duì)于Apache,每個(gè)請(qǐng)求都會(huì)獨(dú)占一個(gè)工作線程,當(dāng)并發(fā)量增大時(shí),也會(huì)產(chǎn)生大量的工作線程,導(dǎo)致內(nèi)存占用急劇上升,同時(shí)線程的上下文切換也會(huì)導(dǎo)致CPU開(kāi)銷增大,導(dǎo)致在高并發(fā)場(chǎng)景下性能下降嚴(yán)重;
對(duì)于Nginx,一個(gè)worker進(jìn)程只有一個(gè)主線程,通過(guò)事件驅(qū)動(dòng)機(jī)制,實(shí)現(xiàn)循環(huán)處理多個(gè)準(zhǔn)備好的事件,從而實(shí)現(xiàn)輕量級(jí)和高并發(fā);
部署配置
安裝
yum -y groupinstall “Development tools” yum -y groupinstall “Server Platform Development” yum install gcc openssl-devel pcre-devel zlib-devel groupadd -r nginx useradd -r -g nginx -s /sbin/nologin -M nginx tar xf nginx-1.4.7.tar.gz cd nginx-1.4.7 mkdir -pv /var/tmp/nginx ./configure \ --prefix=/usr \ --sbin-path=/usr/sbin/nginx \ --conf-path=/etc/nginx/nginx.conf \ --error-log-path=/var/log/nginx/error.log \ --http-log-path=/var/log/nginx/access.log \ --pid-path=/var/run/nginx/nginx.pid \ --lock-path=/var/lock/nginx.lock \ --user=nginx \ --group=nginx \ --with-http_ssl_module \ --with-http_flv_module \ --with-http_stub_status_module \ --with-http_gzip_static_module \ --http-client-body-temp-path=/var/tmp/nginx/client/ \ --http-proxy-temp-path=/var/tmp/nginx/proxy/ \ --http-fastcgi-temp-path=/var/tmp/nginx/fcgi/ \ --http-uwsgi-temp-path=/var/tmp/nginx/uwsgi \ --http-scgi-temp-path=/var/tmp/nginx/scgi \ --with-pcre make && make install |
配置:
vi /etc/init.d/nginx # 配置服務(wù)腳本 #!/bin/sh # # nginx - this script starts and stops the nginx daemon # # chkconfig: - 85 15 # description: Nginx is an HTTP(S) server, HTTP(S) reverse \ # proxy and IMAP/POP3 proxy server # processname: nginx # config: /etc/nginx/nginx.conf # config: /etc/sysconfig/nginx # pidfile: /var/run/nginx.pid # Source function library. . /etc/rc.d/init.d/functions # Source networking configuration. . /etc/sysconfig/network # Check that networking is up. [ "$NETWORKING" = "no" ] && exit 0 nginx="/usr/sbin/nginx" prog=$(basename $nginx) NGINX_CONF_FILE="/etc/nginx/nginx.conf" [ -f /etc/sysconfig/nginx ] && . /etc/sysconfig/nginx lockfile=/var/lock/subsys/nginx make_dirs() { # make required directories user=`nginx -V 2>&1 | grep "configure arguments:" | sed 's/[^*]*--user=\([^ ]*\).*/\1/g' -` options=`$nginx -V 2>&1 | grep 'configure arguments:'` for opt in $options; do if [ `echo $opt | grep '.*-temp-path'` ]; then value=`echo $opt | cut -d "=" -f 2` if [ ! -d "$value" ]; then # echo "creating" $value mkdir -p $value && chown -R $user $value fi fi done } start() { [ -x $nginx ] || exit 5 [ -f $NGINX_CONF_FILE ] || exit 6 make_dirs echo -n $"Starting $prog: " daemon $nginx -c $NGINX_CONF_FILE retval=$? echo [ $retval -eq 0 ] && touch $lockfile return $retval } stop() { echo -n $"Stopping $prog: " killproc $prog -QUIT retval=$? echo [ $retval -eq 0 ] && rm -f $lockfile return $retval } restart() { configtest || return $? stop sleep 1 start } reload() { configtest || return $? echo -n $"Reloading $prog: " killproc $nginx -HUP RETVAL=$? echo } force_reload() { restart } configtest() { $nginx -t -c $NGINX_CONF_FILE } rh_status() { status $prog } rh_status_q() { rh_status >/dev/null 2>&1 } case "$1" in start) rh_status_q && exit 0 $1 ;; stop) rh_status_q || exit 0 $1 ;; restart|configtest) $1 ;; reload) rh_status_q || exit 7 $1 ;; force-reload) force_reload ;; status) rh_status ;; condrestart|try-restart) rh_status_q || exit 0 ;; *) echo $"Usage: $0 {start|stop|status|restart|condrestart|try-restart|reload|force-reload|configtest}" exit 2 esac chmod +x /etc/init.d/nginx # 復(fù)***務(wù)腳本執(zhí)行權(quán)限 vi /etc/nginx/nginx.conf # 編輯主配置文件 worker_processes 2; error_log /var/log/nginx/nginx.error.log; pid /var/run/nginx.pid; events { worker_connections 1024; } http { include mime.types; default_type application/octet-stream; log_format main '$remote_addr - $remote_user [$time_local] "$request" ' '$status $body_bytes_sent "$http_referer" ' '"$http_user_agent" "$http_x_forwarded_for"'; sendfile on; keepalive_timeout 65; server { listen 80; server_name xxrenzhe.lnmmp.com; access_log /var/log/nginx/nginx.access.log main; location / { root /www/lnmmp.com; index index.php index.html index.htm; } error_page 404 /404.html; error_page 500 502 503 504 /50x.html; location = /50x.html { root /www/lnmmp.com; } location ~ \.php$ { root /www/lnmmp.com; fastcgi_pass 127.0.0.1:9000; fastcgi_index index.php; fastcgi_param SCRIPT_FILENAME $document_root$fastcgi_script_name; include fastcgi_params; } } } vi /etc/nginx/fastcgi_params # 編輯fastcgi參數(shù)文件 fastcgi_param GATEWAY_INTERFACE CGI/1.1; fastcgi_param SERVER_SOFTWARE nginx; fastcgi_param QUERY_STRING $query_string; fastcgi_param REQUEST_METHOD $request_method; fastcgi_param CONTENT_TYPE $content_type; fastcgi_param CONTENT_LENGTH $content_length; fastcgi_param SCRIPT_FILENAME $document_root$fastcgi_script_name; fastcgi_param SCRIPT_NAME $fastcgi_script_name; fastcgi_param REQUEST_URI $request_uri; fastcgi_param DOCUMENT_URI $document_uri; fastcgi_param DOCUMENT_ROOT $document_root; fastcgi_param SERVER_PROTOCOL $server_protocol; fastcgi_param REMOTE_ADDR $remote_addr; fastcgi_param REMOTE_PORT $remote_port; fastcgi_param SERVER_ADDR $server_addr; fastcgi_param SERVER_PORT $server_port; fastcgi_param SERVER_NAME $server_name; |
啟動(dòng)服務(wù):
service nginx configtest # 服務(wù)啟動(dòng)前先驗(yàn)證配置文件是否正確
service nginx start
ps -ef |grep nginx # 檢查nginx進(jìn)程,尤其是worker進(jìn)程是否與worker_processes值一致
ss -antupl |grep 80 # 檢查服務(wù)端口是否啟動(dòng)
性能測(cè)試
測(cè)試說(shuō)明
每次測(cè)試都進(jìn)行3次,最后數(shù)據(jù)取平均值;
對(duì)比測(cè)試中的Apache采用event的MPM機(jī)制,最大化提高Apache的并發(fā)性能;
每次測(cè)試后,都需重新啟動(dòng)服務(wù)(httpd或nginx),以防止多次測(cè)試數(shù)據(jù)不準(zhǔn);
測(cè)試工具:webbench
優(yōu)點(diǎn):比ab能更好的模擬并發(fā)請(qǐng)求,最大支持模擬30000并發(fā)連接;
測(cè)試方法
# 安裝wenbench wget http://blog.s135.com/soft/linux/webbench/webbench-1.5.tar.gz tar xf webbench-1.5.tar.gz cd webbench-1.5 make && make install # 測(cè)試 webbench -c 100 -t 30 http://172.16.25.112/nginx.html # 測(cè)試靜態(tài)文件訪問(wèn) webbench -c 20 -t 30 http://172.16.25.112/test_mem.php # 測(cè)試動(dòng)態(tài)文件訪問(wèn) |
測(cè)試數(shù)據(jù)
分析趨勢(shì)圖
靜態(tài)文件訪問(wèn)趨勢(shì)圖
動(dòng)態(tài)文件訪問(wèn)趨勢(shì)圖
總結(jié)
綜合上面測(cè)試得出的趨勢(shì)圖可以看出:
靜態(tài)文件測(cè)試時(shí),低并發(fā)(200以下)情況下,Nginx和Apach的處理能力相當(dāng)(2000pages/sec左右),當(dāng)并發(fā)數(shù)超過(guò)200后,則 Apache的處理能力開(kāi)始下降,而Nginx保持穩(wěn)定;同時(shí)隨著并發(fā)量的增大,Apache令人詬病的內(nèi)存占用和負(fù)載開(kāi)始急劇上升,與此同 時(shí),Nginx在內(nèi)存占用和負(fù)載方面的略微提升則可以忽略不計(jì)了;
動(dòng)態(tài)文件測(cè)試時(shí),低并發(fā) (100以下)情況下,Nginx和Apache的處理能力相當(dāng)(650pages/sec左右),但Nginx的內(nèi)存占用和負(fù)載峰值只有Apache的 50%左右;在高并發(fā)情況下(100以上),Apach的動(dòng)態(tài)處理能力開(kāi)始下滑,當(dāng)并發(fā)達(dá)到500時(shí),開(kāi)始出現(xiàn)失敗的請(qǐng)求,說(shuō)明此時(shí)已達(dá)到的Apache 的處理上限了,而反觀Nginx,雖然處理動(dòng)態(tài)請(qǐng)求會(huì)消耗更多的內(nèi)存,但其處理能力隨著并發(fā)量的上升而上升,即使并發(fā)1000動(dòng)態(tài)請(qǐng)求,也未達(dá)到其處理能 力上限;
故不管是在靜態(tài)文件請(qǐng)求還是動(dòng)態(tài)文件請(qǐng)求方面,Nginx的性能都是強(qiáng)勢(shì)優(yōu)于Apache的;雖然可以通過(guò)系統(tǒng)調(diào)優(yōu)的方式提高Apache的處理性能,但和Nginx相比,還是不足以打動(dòng)技術(shù)狂熱份子的吧,哈哈!
posted on 2014-05-23 10:04 順其自然EVO 閱讀(2380) 評(píng)論(0) 編輯 收藏 所屬分類: 測(cè)試學(xué)習(xí)專欄