Improve the cache hit/miss ratio by canonicalising the url key. hostname's

are matched case-insensitively, port-based vhosts are catered for and the
scheme included for future multi-scheme caching compatibility.

git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@239407 13f79535-47bb-0310-9956-ffa450edef68

diff --git a/modules/cache/cache_storage.c b/modules/cache/cache_storage.c
index 74beb182c0a217336c064c4183b57d6a363025b4..e949847fe81b0406f01850736ebe2edc58972652 100644 (file)
--- a/modules/cache/cache_storage.c
+++ b/modules/cache/cache_storage.c
@@ -320,12 +320,82 @@ int cache_select_url(request_rec *r, char *url)
 apr_status_t cache_generate_key_default(request_rec *r, apr_pool_t* p,
                                         char**key)
 {
-    if (r->hostname) {
-        *key = apr_pstrcat(p, r->hostname, r->uri, "?", r->args, NULL);
+    char *port_str, *scheme, *hn;
+    const char * hostname;
+    int i;
+
+    /* Use the canonical name to improve cache hit rate, but only if this is
+     * not a proxy request. 
+     */ 
+    if (!r->proxyreq) {
+        /* Use _default_ as the hostname if none present, as in mod_vhost */
+        hostname =  ap_get_server_name(r);
+        if (!hostname) {
+            hostname = "_default_";
+        }
+    }
+    else if(r->parsed_uri.hostname) {
+        /* Copy the parsed uri hostname */
+        hn = apr_pcalloc(p, strlen(r->parsed_uri.hostname) + 1);
+        for (i = 0; r->parsed_uri.hostname[i]; i++) {
+            hn[i] = apr_tolower(r->parsed_uri.hostname[i]);
+        }
+        /* const work-around */
+        hostname = hn;
+    }
+    else {
+        /* We are a proxied request, with no hostname. Unlikely
+         * to get very far - but just in case */
+        hostname = "_default_";
+    }
+
+    /* Copy the scheme, ensuring that it is lower case. If the parsed uri
+     * contains no string or if this is not a proxy request.
+     */
+    if (r->proxyreq && r->parsed_uri.scheme) {
+        /* Copy the scheme */
+        scheme = apr_pcalloc(p, strlen(r->parsed_uri.scheme) + 1);
+        for (i = 0; r->parsed_uri.scheme[i]; i++) {
+            scheme[i] = apr_tolower(r->parsed_uri.scheme[i]);
+        }
+    }
+    else {
+        scheme = "http";
     }
+
+    /* If the content is locally generated, use the port-number of the
+     * current server. Otherwise. copy the URI's port-string (which may be a
+     * service name). If the URI contains no port-string, use apr-util's
+     * notion of the default port for that scheme - if available.
+     */
+    if(r->proxyreq) {
+        if (r->parsed_uri.port_str) {
+            port_str = apr_pcalloc(p, strlen(r->parsed_uri.port_str) + 2);
+            port_str[0] = ':';
+            for (i = 0; r->parsed_uri.port_str[i]; i++) {
+                port_str[i + 1] = apr_tolower(r->parsed_uri.port_str[i]);
+            }
+        }
+        else if (apr_uri_port_of_scheme(scheme)) {
+            port_str = apr_psprintf(p, ":%u", apr_uri_port_of_scheme(scheme));
+        }
+        else {
+            /* No port string given in the AbsoluteUri, and we have no
+             * idea what the default port for the scheme is. Leave it
+             * blank and live with the inefficiency of some extra cached
+             * entities.
+             */
+            port_str = "";
+        }       
+    }       
     else {
-        *key = apr_pstrcat(p, r->uri, "?", r->args, NULL);
+        /* Use the server port */
+        port_str = apr_psprintf(p, ":%u", ap_get_server_port(r));
     }
+
+    /* Key format is a URI */
+    *key = apr_pstrcat(p, scheme, "://", hostname, port_str,
+                       r->parsed_uri.path, "?", r->args, NULL);
+
     return APR_SUCCESS;
 }
-