Merge commit 'refs/pull/2028/head' of https://github.com/magento/magento2 into MAGETWO-49876

Author: Hayder Sharhan

app/code/Magento/PageCache/etc/varnish4.vcl

@@ -1,8 +1,8 @@
 vcl 4.0;
- 
+
 import std;
 # The minimal Varnish version is 4.0
- 
+
 backend default {
     .host = "/* {{ host }} */";
     .port = "/* {{ port }} */";
@@ -23,7 +23,7 @@ sub vcl_recv {
         ban("obj.http.X-Magento-Tags ~ " + req.http.X-Magento-Tags-Pattern);
         return (synth(200, "Purged"));
     }
- 
+
     if (req.method != "GET" &&
         req.method != "HEAD" &&
         req.method != "PUT" &&
@@ -34,7 +34,7 @@ sub vcl_recv {
           /* 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);
@@ -51,6 +51,30 @@ sub vcl_recv {
     # collect all cookies
     std.collect(req.http.Cookie);
 
+    # Even though there are few possible values for Accept-Encoding, Varnish treats
+    # them literally rather than semantically, so even a small difference which makes
+    # no difference to the backend can reduce cache efficiency by making Varnish cache
+    # too many different versions of an object.
+    # https://www.varnish-cache.org/trac/wiki/FAQ/Compression
+    if (req.http.Accept-Encoding) {
+        if (req.url ~ "\.(jpg|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 are always cacheable. remove SSL flag and cookie
         if (req.url ~ "^/(pub/)?(media|static)/.*\.(ico|css|js|jpg|jpeg|png|gif|tiff|bmp|mp3|ogg|svg|swf|woff|woff2|eot|ttf|otf)$") {
         unset req.http.Https;
@@ -64,6 +88,21 @@ sub vcl_hash {
     if (req.http.cookie ~ "X-Magento-Vary=") {
         hash_data(regsub(req.http.cookie, "^.*?X-Magento-Vary=([^;]+);*.*$", "\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);
+    }
+
+    # mainly to make sure, if the site was cached via a http connection and a visitor opens the
+    # https version, they won't see an ssl warning about mixed content (if the site was cached via http
+    # connection, the external resources like css, js will be opened via an http connection as well
+    # instead of https
+    if (req.http.X-Forwarded-Proto) {
+        hash_data(req.http.X-Forwarded-Proto);
+    }
     /* {{ design_exceptions_code }} */
 }
 
@@ -75,7 +114,7 @@ sub vcl_backend_response {
     if (bereq.url ~ "\.js$" || beresp.http.content-type ~ "text") {
         set beresp.do_gzip = true;
     }
- 
+
     # cache only successfully responses and 404s
     if (beresp.status != 200 && beresp.status != 404) {
         set beresp.ttl = 0s;