Nginx 代理 varnish 的姿势

转载

mb60b79a6396b63 2022-02-21 17:26:38 博主文章分类：系统架构

文章标签 varnish Nginx nginx php html 文章分类 代码人生

以前做网站的时候遇到了网站的访问量很大，而导致后端处理程序响应超时而导致的一些问题。当时采用的架构是nginx+php-fastcgi，同事想到了用nginx-proxycache来做页面缓存，效果也还行。下面我想介绍一下varnish的使用技巧

准备

varnish严格来说是可以当作一个代理服务器的软件，直接将HTTP请求转发到php-cgi,然后交给php处理,varnish会获取经过php处理后的数据,最后返回给浏览器。如图

但是，现在php-fastcgi已经被逐渐淘汰了，也就是说我们一般情况下不会使用php-fastcgi，那么我们不能直接将varnish与php组合，因为php-fpm的交互方式为socket，而不再是监听本机的9000端口所以我们必须找一个的媒介,连接varnish和php-fpm,nginx可以扮演这个媒介,如下图：

那么问题来了，根据研究发现，varnish处理http请求不如nginx那么高效。所以如果我们让nginx做前锋，这样就更完美了。那我们需要怎么才能达到这个目的呢，下面我们来整理一下流程

下面就来实现一下图三的架构吧。

事先需要准备nginx,varnish,php-fpm,php这些软件，OS是ubuntu，所有软件都可以用apt-get install来安装，不了解包名全称的话可以先apt-get update，更新一下源，然后再用apt-cache search xxx来查找软件包名安装完varnish后，可以使用service varnish回车，查看可操作选项* Usage: /etc/init.d/varnish {start|stop|restart|reload|force-reload|configtest},一般安装完毕后，系统会自动启动varnish的,nginx也是一样,便不赘述了

配置

安装完所需的软件后，下面需要配置这些软件，来实现这个架构

nginx部分

vi /etc/nginx/nginx.conf

http {
    ## proxy global setting
    proxy_connect_timeout 5;
    proxy_read_timeout 60;
    proxy_send_timeout 5;
    proxy_buffer_size 16k;
    proxy_buffers 4 64k;
    proxy_busy_buffers_size 128k;
    ##END
    ## cache proxy pass
    upstream cache {
            server  127.0.0.1:6081;
    }
    ##END
    ## php proxy pass
    upstream php { 
            server  127.0.0.1:8080;
    }
    ##END
    # Basic Settings
    sendfile on;
    tcp_nopush on;
    tcp_nodelay on;
    keepalive_timeout 65;
    types_hash_max_size 2048;
    server_tokens off;
    #depend on nginx-extras 需要安装nginx-extras才能定义Server
    more_set_headers 'Server: Bird-shark';
    # server_names_hash_bucket_size 64;
    # server_name_in_redirect off;
    include /etc/nginx/mime.types;
    default_type application/octet-stream;
    ##
    # SSL Settings
    ##
    ssl_protocols TLSv1 TLSv1.1 TLSv1.2; # Dropping SSLv3, ref: POODLE
    ssl_prefer_server_ciphers on;
    ##
    # Logging Settings
    ##
    access_log /var/log/nginx/access.log;
    error_log /var/log/nginx/error.log;
    ##
    # Gzip Settings
    ##
    gzip on;
    gzip_disable "msie6";
    gzip_vary on;
    gzip_proxied any;
    gzip_comp_level 6;
    gzip_buffers 16 8k;
    gzip_http_version 1.1;
    gzip_types text/plain text/css application/json application/javascript text/xml application/xml application/xml+rss text/javascript;
    ##
    # Virtual Host Configs
    ##
    include /etc/nginx/conf.d/*.conf;
    include /etc/nginx/sites-enabled/*;  
}

vi /etc/nginx/sites-available/default

server {
    listen 80 default_server;
    listen [::]:80 default_server;
    index index.html index.htm index.php;
    server_name localhost;
    location ~ .*\.(gif|jpg|png|css|js|flv|ico|swf|html)$ {
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_pass http://cache;
    }
    # pass the PHP scripts to FastCGI server listening on 127.0.0.1:9000
    #
    location / {
        proxy_pass http://php;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_pass_header Server;
    }
}
server {
    listen 8080;
    root /var/www/html;
    index  index.html index.htm index.php;
    location / {
        if (!-e $request_filename){
            rewrite  ^(.*)$  /index.php?s=$1  last;
            break;
        }
        try_files $uri $uri/ =404;
    }
    location ~ ^(.+\.php)(.*)$ {
        fastcgi_pass unix:/var/run/php5-fpm.sock;
        fastcgi_intercept_errors on;
        fastcgi_buffers 8 128k;
        fastcgi_index  index.php;
        fastcgi_param  SCRIPT_FILENAME $document_root$fastcgi_script_name;
        include        fastcgi_params;
    }
}

varnish部分

vi /etc/varnish/default.vcl

vcl 4.0;

# Default backend definition. Set this to point to your content server.
backend default {
    .host = "127.0.0.1";
    .port = "8080";
}
acl purgers {
    "localhost";
    #"103.22.188.169";
}
sub vcl_recv {
    # Happens before we check if we have this in cache already.
    #
    # Typically you clean up the request here, removing cookies you don't need,
    # rewriting the request, etc.
    if (req.restarts == 0) {
        unset req.http.X-Purger;
    }
    if(req.method == "PURGE"){
        if(!client.ip ~ purgers){
            return(synth(405,"Not Allowed."));
        }
        return (purge);
        #ban("obj.http.x-url ~ " + req.url);
    }
    if(req.method == "GET" && req.url ~ "\.(js|css|jpg|png|gif|swf|jpeg|ico)$"){
        unset req.http.cookie;
    }
}

sub vcl_backend_response {
    #set beresp.http.x-url = bereq.url;
    if (bereq.url ~ "\.(js|css|jpg|png|gif|swf|jpeg|ico)$") {
        unset beresp.http.Cache-Control;
        unset beresp.http.set-cookie;
        set beresp.ttl = 10h;
        set beresp.http.Cache-Control = "max-age=36000";
        set beresp.do_gzip = true;
    }
    if(bereq.url ~ "\.html$"){
        set beresp.ttl = 10m;
        set beresp.do_gzip = true;
        unset beresp.http.Cache-Control;
        unset beresp.http.Pragma;
        set beresp.http.Cache-Control = "max-age=600";
        unset beresp.http.Expires;
    }
}

sub vcl_deliver {
    if (obj.hits > 0) {
        set resp.http.X-Cache = "HIT from " + req.http.host;
        #set resp.http.X-Cache-Hits = obj.hits;
    } else {
        set resp.http.X-Cache = "MISS from " + req.http.host;
    }
    if (req.http.X-Purger) {
        set resp.http.X-Purger = req.http.X-Purger;
    }
    unset resp.http.X-Powered-By;
    unset resp.http.Server;

    unset resp.http.Via;
    unset resp.http.X-Varnish;

    unset resp.http.Age;
    #unset resp.http.x-url; # Optional
}
sub vcl_hit {
    if (req.method == "PURGE") {
        return (synth(200,"Purged."));
    }
}
sub vcl_miss {
    if (req.method == "PURGE") {
        return (synth(404,"Purged."));
    }
}
sub vcl_purge {
    if (req.method == "PURGE") {
        #set req.http.X-Purge = "Purged";
        ban("req.url ~ "+req.url);
        #return (restart);
        set req.method = "GET";
        set req.http.X-Purger = "Purged";
        return (restart);
    }
}
sub vcl_hash {
    hash_data(req.url);
    if (req.http.host) {
        hash_data(req.http.host);
    } else {
        hash_data(server.ip);
    }
    if (req.http.cookie) {
        hash_data(req.http.cookie);
    }
    if (req.http.Accept-Encoding ~ "gzip") {
        hash_data("gzip");
    } elseif (req.http.Accept-Encoding ~ "deflate") {
        hash_data("deflate");
    }
}

测试&分析

1. 在不使用缓存模块的情况下

vi /etc/nginx/sites-available/default

#location ~ .*\.(gif|jpg|png|css|js|flv|ico|swf|html)$ {
#    proxy_set_header Host $host;
#    proxy_set_header X-Real-IP $remote_addr;
#    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
#    proxy_pass http://cache;
#}

先用chrome浏览器访问查看请求头

我们再使用curl,在服务器上执行以下命令

curl -k -v 'http://192.168.99.1/Public/Home/images/t_navigation_logo.png' -H 'Pragma: no-cache' -H 'Accept-Encoding: gzip, deflate, sdch' -H 'Accept-Language: zh,en;q=0.8,zh-CN;q=0.6' -H 'Upgrade-Insecure-Requests: 1' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' -H 'Connection: keep-alive' --compressed

发现有输出内容。

然后，反选disable cache

然后在服务器上执行以下命令

curl  -k -v 'http://192.168.99.1/Public/Home/images/t_navigation_logo.png' -H 'If-None-Match: "57c6b733-1962"' -H 'Accept-Encoding: gzip, deflate, sdch' -H 'Accept-Language: zh,en;q=0.8,zh-CN;q=0.6' -H 'Upgrade-Insecure-Requests: 1' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' -H 'Connection: keep-alive' -H 'If-Modified-Since: Wed, 31 Aug 2016 10:53:39 GMT' --compressed

发现只返回了头部信息，然而没有内容返回

然后我们比较两个命令发现区别就在-H 'Pragma: no-cache'和 -H 'If-Modified-Since: Wed, 31 Aug 2016 10:53:39 GMT' -H 'If-None-Match: "57c6b733-1962"'57c6b733-1962这串字符对应的是服务器响应给浏览器的ETag部分的内容，然后我们修改一下部分的内容

curl  -k -v 'http://192.168.99.1/Public/Home/images/t_navigation_logo.png' -H 'If-None-Match: "57c6b733-1234"' -H 'Accept-Encoding: gzip, deflate, sdch' -H 'Accept-Language: zh,en;q=0.8,zh-CN;q=0.6' -H 'Upgrade-Insecure-Requests: 1' -H 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' -H 'Connection: keep-alive' -H 'If-Modified-Since: Wed, 31 Aug 2016 10:53:39 GMT' --compressed

在服务器端执行一下。发现有内容返回，所以这个ETag相当于token，它不是由nginx随便生成的，且跟请求链接应是一一对应的，用来标识缓存的,当服务器返回的状态为304的时候,这时候我们浏览器会直接找到本地的缓存数据

2. 在使用缓存模块的情况下

vi /etc/nginx/sites-available/default

location ~ .*\.(gif|jpg|png|css|js|flv|ico|swf|html)$ {
    proxy_set_header Host $host;
    proxy_set_header X-Real-IP $remote_addr;
    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
    proxy_pass http://cache;
}

用浏览器查看响应头

发现X-Cache:MISS from 192.168.99.1.这表示缓存未命中，然后我们刷新X-Cache:HIT from 192.168.99.1，这时候发现已经命中了。

对于已经命中的资源文件，我们如果将其删除会出现什么效果呢，答案是，其依然可以访问，除非重启或者将缓存清除

但是对PURGE显然是不对外公开的,以下是服务器端用curl清除varnish缓存的命令

curl -v -k -X PURGE http://localhost/Public/Home/css/t_navigation.css

结语

varnish是一款内存类型的缓存软件，而非nginx扩展proxy_cache那种物理缓存类型的软件，存取速度比较快,但是也有弊端，重启后所有缓存得重写。不管怎么说，什么架子都适用的场景，要想满足业务需求还是得捣鼓透彻，而我也只是将我想到的给实现出来，毕竟资源和精力都是有限的，也就随便玩玩，诸位看客看看就好，别太认真，知道怎么回事儿就行。