如何让Varnish Cache永久保留缓存页面？排查随机失效问题

我们在Magento站点前端部署了Varnish缓存服务器，每日通过缓存预热工具抓取站点地图并访问所有页面，确保用户访问时页面已缓存。但目前出现部分已缓存页面随机失效、需要重新缓存的问题：

• 已通过VCL禁用Magento的URL清理功能
• TTL设置为365天
• 通过varnishstat确认无n_lru_nuked指标，排除内存不足导致的缓存回收

附上当前使用的VCL配置文件，请问：

1. VCL配置是否存在遗漏或问题？
2. 若VCL无问题，还有哪些外部因素可能引发该问题？

# VCL version 5.0 is not supported so it should be 4.0 even though actually used Varnish version is 5
vcl 4.0;

import std;
# The minimal Varnish version is 5.0
# For SSL offloading, pass the following header in your proxy server or load balancer: 'X-Forwarded-Proto: https'

backend default {
    .host = "127.0.0.1";
    .port = "8181";
    .first_byte_timeout = 600s;
    .probe = {
        .url = "/pub/health_check.php";
        .timeout = 2s;
        .interval = 5s;
        .window = 10;
        .threshold = 5;
   }
}

#acl purge {
#    "127.0.0.1";
#}

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]?://", "");

    # 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 {
            # unknown algorithm
            unset req.http.Accept-Encoding;
        }
    }

    # Remove Google gclid parameters to minimize the cache objects
    set req.url = regsuball(req.url,"\?gclid=[^&]+$",""); # strips when QS = "?gclid=AAA"
    set req.url = regsuball(req.url,"\?gclid=[^&]+&","?"); # strips when QS = "?gclid=AAA&foo=bar"
    set req.url = regsuball(req.url,"&gclid=[^&]+",""); # strips when QS = "?foo=bar&gclid=AAA" or QS = "?foo=bar&gclid=AAA&bar=baz"

    # 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 = 365d;

    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 = 365d;
        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 {
    #if (resp.http.X-Magento-Debug) {
        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;
    #}

    # Not letting browser to cache non-static files.
    if (resp.http.Cache-Control !~ "private" && req.url !~ "^/(pub/)?(media|static)/") {
        set resp.http.Pragma = "no-cache";
        set resp.http.Expires = "-1";
        set resp.http.Cache-Control = "no-store, no-cache, must-revalidate, max-age=0";
    }

    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 (miss);
        }
    } else {
        # server is not healthy, retrieve from cache
        set req.http.grace = "unlimited (unhealthy server)";
        return (deliver);
    }
}

VCL配置检查 #

1. 缺失全局TTL设置 #

当前VCL仅针对非200/404响应、私有缓存页面设置了TTL，但对于正常可缓存的200响应，没有显式覆盖后端返回的TTL值。如果Magento后端返回的Cache-Control头包含的max-age小于365天，Varnish会优先使用后端值，导致缓存提前过期。

建议在vcl_backend_response开头添加全局TTL设置：

# 全局设置TTL为365天，覆盖后端返回的短时效值
set beresp.ttl = 365d;

2. 其他配置无明显问题 #

• Purge/Ban相关代码已全部注释，确实不会触发主动清理操作
• vcl_hash包含了host和X-Forwarded-Proto，避免多站点或HTTP/HTTPS缓存冲突
• Hit-For-Pass逻辑仅影响不可缓存页面的短期请求，不会导致已缓存页面失效

外部因素排查方向 #

如果修正VCL后问题仍存在，建议排查以下点：

• Magento隐性缓存清理：检查Magento的var/log/system.log和var/log/exception.log，确认是否有第三方扩展、自定义代码直接调用Varnish API或触发缓存清理
• Varnish进程异常：查看系统日志（如/var/log/syslog），检查是否有Varnish意外重启记录（重启会清空全部缓存）
• 预热工具请求不一致：对比预热工具的请求Header（如Cookie、Accept-Encoding）与用户实际请求的差异，避免生成重复缓存对象
• 存储介质问题：如果Varnish使用文件系统存储缓存，检查磁盘IO状态、文件系统完整性，避免缓存文件损坏丢失
• 上层代理/CDN干扰：若前端有CDN或反向代理，排查是否是CDN层缓存失效导致请求未到达Varnish
• 系统时间异常：检查服务器时间是否正常同步（NTP），时间跳变会导致Varnish的TTL计算错误

内容的提问来源于stack exchange，提问作者Daniel Black