Caching Varnish 4 VCL-条带定义的查询字符串参数

我目前正在使用Varnish 4作为网站上的反向代理缓存。但是我注意到，当使用查询字符串参数调用url时，它会绕过varnish缓存

例如：

• www.mywebsite.com=缓存命中率
• www.mywebsite.com？gclid=123=Cache 错过

我希望varnish在确定页面匹配项（如Google的跟踪参数）时忽略几个查询字符串参数

我在我的VCL文件中添加了以下内容，但是当我加载一个url（如www.mywebsite.com？gclid=123）时，我看到一个404页面，因此有些地方不太正确

# Normalize request url parameters before determining a page match.
set req.url = regsuball(req.url, "((\?)|&)(gclid|gclsrc|utm_content|utm_term|utm_campaign|utm_medium|utm_source|_ga)=[^&]*", "");
set req.url = regsub(req.url, "(\?&|\?|&)$", "");

任何帮助都将不胜感激

以下是完整的VCL文件：

vcl 4.0;

import std;
# The minimal Varnish version is 4.0
# For SSL offloading, pass the following header in your proxy server or load balancer: 'X-Forwarded-Proto: https'

backend default {
    .host = "127.2.0.1";
    .port = "80";
    .first_byte_timeout = 6s;
}

acl purge {
    "localhost";
}

sub vcl_recv {
    if (req.method == "PURGE") {
        if (client.ip !~ purge) {
            return (synth(405, "Method not allowed"));
        }
        # To use the X-Pool header for purging varnish during automated deployments, make sure the X-Pool header
        # has been added to the response in your backend server config. This is used, for example, by the
        # capistrano-magento2 gem for purging old content from varnish during it's deploy routine.
        if (!req.http.X-Magento-Tags-Pattern && !req.http.X-Pool) {
            return (synth(400, "X-Magento-Tags-Pattern or X-Pool header required"));
        }
        if (req.http.X-Magento-Tags-Pattern) {
          ban("obj.http.X-Magento-Tags ~ " + req.http.X-Magento-Tags-Pattern);
        }
        if (req.http.X-Pool) {
          ban("obj.http.X-Pool ~ " + req.http.X-Pool);
        }
        return (synth(200, "Purged"));
    }

    if (req.method != "GET" &&
        req.method != "HEAD" &&
        req.method != "PUT" &&
        req.method != "POST" &&
        req.method != "TRACE" &&
        req.method != "OPTIONS" &&
        req.method != "DELETE") {
          /* Non-RFC2616 or CONNECT which is weird. */
          return (pipe);
    }

    # We only deal with GET and HEAD by default
    if (req.method != "GET" && req.method != "HEAD") {
        return (pass);
    }

    # Bypass shopping cart, checkout and search requests
    if (req.url ~ "/checkout" || req.url ~ "/catalogsearch") {
        return (pass);
    }

    # Bypass health check requests
    if (req.url ~ "/pub/health_check.php") {
        return (pass);
    }

    # Set initial grace period usage status
    set req.http.grace = "none";

    # normalize url in case of leading HTTP scheme and domain
    set req.url = regsub(req.url, "^http[s]?://", "");

    # Normalize request url parameters before determining a page match.
    # strip normalized parameters from query string
    set req.url = regsuball(req.url, "((\?)|&)(gclid|gclsrc|utm_content|utm_term|utm_campaign|utm_medium|utm_source|_ga)=[^&]*", "");
    set req.url = regsub(req.url, "(\?&|\?|&)$", "");

    # collect all cookies
    std.collect(req.http.Cookie);

    # Compression filter. See https://www.varnish-cache.org/trac/wiki/FAQ/Compression
    if (req.http.Accept-Encoding) {
        if (req.url ~ "\.(jpg|jpeg|png|gif|gz|tgz|bz2|tbz|mp3|ogg|swf|flv)$") {
            # No point in compressing these
            unset req.http.Accept-Encoding;
        } elsif (req.http.Accept-Encoding ~ "gzip") {
            set req.http.Accept-Encoding = "gzip";
        } elsif (req.http.Accept-Encoding ~ "deflate" && req.http.user-agent !~ "MSIE") {
            set req.http.Accept-Encoding = "deflate";
        } else {
            # unkown algorithm
            unset req.http.Accept-Encoding;
        }
    }

    # Static files caching
    if (req.url ~ "^/(pub/)?(media|static)/") {
        # Static files should not be cached by default
        return (pass);

        # But if you use a few locales and don't use CDN you can enable caching static files by commenting previous line (#return (pass);) and uncommenting next 3 lines
        #unset req.http.Https;
        #unset req.http.X-Forwarded-Proto;
        #unset req.http.Cookie;
    }

    return (hash);
}

sub vcl_hash {
    if (req.http.cookie ~ "X-Magento-Vary=") {
        hash_data(regsub(req.http.cookie, "^.*?X-Magento-Vary=([^;]+);*.*$", "\1"));
    }

    # For multi site configurations to not cache each other's content
    if (req.http.host) {
        hash_data(req.http.host);
    } else {
        hash_data(server.ip);
    }

    # To make sure http users don't see ssl warning
    if (req.http.X-Forwarded-Proto) {
        hash_data(req.http.X-Forwarded-Proto);
    }

}

sub vcl_backend_response {

    set beresp.grace = 3d;

    if (beresp.http.content-type ~ "text") {
        set beresp.do_esi = true;
    }

    if (bereq.url ~ "\.js$" || beresp.http.content-type ~ "text") {
        set beresp.do_gzip = true;
    }

    if (beresp.http.X-Magento-Debug) {
        set beresp.http.X-Magento-Cache-Control = beresp.http.Cache-Control;
    }

    # cache only successfully responses and 404s
    if (beresp.status != 200 && beresp.status != 404) {
        set beresp.ttl = 0s;
        set beresp.uncacheable = true;
        return (deliver);
    } elsif (beresp.http.Cache-Control ~ "private") {
        set beresp.uncacheable = true;
        set beresp.ttl = 86400s;
        return (deliver);
    }

    # validate if we need to cache it and prevent from setting cookie
    if (beresp.ttl > 0s && (bereq.method == "GET" || bereq.method == "HEAD")) {
        unset beresp.http.set-cookie;
    }

   # If page is not cacheable then bypass varnish for 2 minutes as Hit-For-Pass
   if (beresp.ttl <= 0s ||
       beresp.http.Surrogate-control ~ "no-store" ||
       (!beresp.http.Surrogate-Control &&
       beresp.http.Cache-Control ~ "no-cache|no-store") ||
       beresp.http.Vary == "*") {
       # Mark as Hit-For-Pass for the next 2 minutes
        set beresp.ttl = 120s;
        set beresp.uncacheable = true;
    }

    return (deliver);
}

sub vcl_deliver {
  set resp.http.X-Magento-Cache-Debug-Request-Url = req.url;
    if (resp.http.X-Magento-Debug) {
      # set the normalized request url as a http header if magento is in debug mode for easy debugging

        if (resp.http.x-varnish ~ " ") {
            set resp.http.X-Magento-Cache-Debug = "HIT";
            set resp.http.Grace = req.http.grace;
        } else {
            set resp.http.X-Magento-Cache-Debug = "MISS";
        }
    } else {
        unset resp.http.Age;
    }

    # unset resp.http.X-Magento-Debug;
    # unset resp.http.X-Magento-Tags;
    # unset resp.http.X-Powered-By;
    # unset resp.http.Server;
    # unset resp.http.X-Varnish;
    # unset resp.http.Via;
    # unset resp.http.Link;
}

sub vcl_hit {
    if (obj.ttl >= 0s) {
        # Hit within TTL period
        return (deliver);
    }
    if (std.healthy(req.backend_hint)) {
        if (obj.ttl + 300s > 0s) {
            # Hit after TTL expiration, but within grace period
            set req.http.grace = "normal (healthy server)";
            return (deliver);
        } else {
            # Hit after TTL and grace expiration
            return (fetch);
        }
    } else {
        # server is not healthy, retrieve from cache
        set req.http.grace = "unlimited (unhealthy server)";
        return (deliver);
    }
}

vcl4.0；
进口性病；
#最低的清漆版本是4.0
#对于SSL卸载，请在代理服务器或负载平衡器中传递以下标头：“X-Forwarded-Proto:https”
后端默认值{
.host=“127.2.0.1”；
.port=“80”；
.第一字节超时=6s；
}
acl清除{
“本地主机”；
}
子vcl_recv{
如果（请求方法==“清除”）{
如果（client.ip！~purge）{
返回（synth（405，“不允许使用方法”）；
}
#要在自动部署期间使用X-Pool标头清除清漆，请确保X-Pool标头
#已添加到后端服务器配置中的响应中。例如
#capistrano-magento2 gem，用于在部署例程期间从varnish中清除旧内容。
if（！req.http.X-Magento-Tags-Pattern&&！req.http.X-Pool）{
返回（synth（400，“需要X-Magento-Tags-Pattern或X-Pool标头”）；
}
if（请求http.X-Magento-Tags-Pattern）{
ban（“obj.http.X-Magento-Tags~”+req.http.X-Magento-Tags-Pattern）；
}
if（请求http.X-Pool）{
ban（“obj.http.X-Pool~”+req.http.X-Pool）；
}
返回（synth（200，“净化”）；
}
如果（请求方法！=“获取”&&
请求方法！=“头”&&
请求方法！=“放置”&&
请求方法！=“POST”&&
请求方法！=“跟踪”&&
请求方法！=“选项”&&
请求方法！=“删除”）{
/*非RFC2616或连接，这很奇怪*/
回流管；
}
#默认情况下，我们只处理GET和HEAD
如果（请求方法！=“GET”&&req方法！=“HEAD”）{
返回（通行证）；
}
#绕过购物车、结帐和搜索请求
if（req.url~“/checkout”| | req.url~“/catalogsearch”）{
返回（通行证）；
}
#绕过健康检查请求
if（req.url~“/pub/health\u check.php”）{
返回（通行证）；
}
#设置初始宽限期使用状态
设置req.http.grace=“无”；
#在领先的HTTP方案和域的情况下规范url
设置req.url=regsub（req.url“^http[s]？：/”，”）；
#在确定页面匹配之前规范化请求url参数。
#从查询字符串中剥离规范化参数
set req.url=regsuball（req.url，（\？）|和）（gclid | gclsrc | utm|u内容| utm|u术语| utm|u活动| utm|u媒体| utm| u源| u ga）=[^&]*，”；
设置req.url=regsub（req.url，“（\？&\？&\？&）$”，“）；
#收集所有饼干
std.collect（请求http.Cookie）；
#压缩过滤器。请参阅https://www.varnish-cache.org/trac/wiki/FAQ/Compression
if（请求http接受编码）{
如果（req.url~“\（jpg | jpeg | png | gif | gz | tgz | bz2 | tbz | mp3 | ogg | swf | flv）$”）{
#压缩这些没有意义
unset req.http.Accept-Encoding；
}elsif（req.http.Accept-Encoding~“gzip”）{
设置req.http.Accept-Encoding=“gzip”；
}elsif（req.http.Accept-Encoding~“deflate”&&req.http.user-agent！~“MSIE”）{
设置req.http.Accept-Encoding=“deflate”；
}否则{
#未知算法
unset req.http.Accept-Encoding；
}
}
#静态文件缓存
如果（req.url~“^/（pub/）？（媒体|静态）/”）{
#默认情况下不应缓存静态文件
返回（通行证）；
#但是，如果您使用一些区域设置而不使用CDN，则可以通过注释前一行（#return（pass）；）和取消注释后3行来启用静态文件的缓存
#unset req.http.Https；
#unset req.http.X-Forwarded-Proto；
#unset req.http.Cookie；
}
返回（散列）；
}
子vcl_散列{
如果（req.http.cookie~“X-Magento-Vary=”）{
散列数据（regsub（req.http.cookie，“^.*？”X-Magento-Vary=（[^；]+）；****$”，“\1”）；
}
#多站点配置不缓存彼此的内容
if（req.http.host）{
散列数据（请求http.host）；
}否则{
散列数据（server.ip）；
}
#确保http用户看不到ssl警告
if（请求http.X-Forwarded-Proto）{
哈希_数据（请求http.X-Forwarded-Proto）；
}
}
子vcl_后端_响应{
设置beresp.grace=3d；
if（beresp.http.content-type~“text”）{
设置beresp.do_esi=true；
}
if（bereq.url~“\.js$”| | beresp.http.content-type~“text”）{
设置beresp.do_gzip=true；
}
if（beresp.http.X-Magento-Debug）{
设置beresp.http.X-Magento-Cache-Control=beresp.http.Cache-Control；
}
#仅缓存成功的响应和404
如果（beresp.status！=200&&beresp.status！=404）{
设置beresp.ttl=0s；
设置beresp.uncacheable=true；
归还（交付）；
}elsif（beresp.http.Cache-Control~“private”）{
设置beresp.uncacheable=true；
设置beresp.ttl=86400s；
归还（交付）；
}
#验证是否需要缓存它并防止设置cookie
如果（beresp.ttl>0s&&（bereq.method==“GET”| | bereq.method==“HEAD”））{
unset beresp.http.set-cookie；
}
#若页面不可缓存，则绕过清漆2分钟，作为点击通过
如果（beresp.ttl=0s）{
#在TTL周期内命中
归还（交付）；
}
if（标准健康（要求后端提示））{
如果（obj.ttl+300s>0s）{
#TTL过期后命中，但在gr内