Varnish soft purge

[eli-l]

We could utilize Varnish soft purge for better performance/usability, however Magento does not support that approach out of the box.

TODO
Decide on application implementation

** Varnish config (v5.2+)**

vcl 4.0;

import std;

import purge;
# 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 = "nginx";
    .port = "8090";
    .first_byte_timeout = 600s;
}

acl purgeacl {
    "localhost";
    "172.0.0.0"/8;
    "192.168.0.0/16";
}

sub vcl_recv {
    if (req.method == "PURGE") {
        if (client.ip !~ purgeacl) {
            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 (hash);
//            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);
    }

    # Bypass graphql requests - disable for persisted query
//    if (req.url ~ "/graphql") {
//      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 {
            # unkown 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 = 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
    # images, css and js are cacheable by default so we have to remove cookie also
    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 custom_purge {
    set req.http.purged = purge.soft(0s, 300s, 300s);
    if (req.http.purged == "0") {
        return (synth(404));
    }
    else {
        return (synth(200));
    }
}

sub vcl_hit {
    if (req.method == "PURGE") {
        call custom_purge;
    }

    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);
    }
}

sub vcl_miss {
    if (req.method == "PURGE") {
        call custom_purge;
    }
}

sub vcl_synth {
    if (req.method == "PURGE") {
        if (req.http.purged) {
            set resp.http.purged = req.http.purged;
        }
        return (deliver);
    }
}```

[choussamaster]

HI @eli-l
Did you tried this on a production environment please?
Thank you

[eli-l]

Hi @choussamaster
It's been a while ago and no, this approach was not supported by application itself. However it is possible from Varnish perspective. If you are able to properly track changes and invalidate specific entries this approach allows partial invalidation. If I remember correctly it is all about properly tagging documents in Varnish.