From: Julian Phillips <julian@quantumfyre.co.uk>
Date: Sun, 25 Oct 2009 21:28:11 +0000 (+0000)
Subject: remote: Make ref_remove_duplicates faster for large numbers of refs
X-Git-Tag: v1.6.6-rc0~35^2~2
X-Git-Url: https://git.tokkee.org/?a=commitdiff_plain;h=73cf0822b2a4ffa7ad559d1f0772e39718fc7776;p=git.git

remote: Make ref_remove_duplicates faster for large numbers of refs

The ref_remove_duplicates function was very slow at dealing with very
large numbers of refs.  This is because it was using a linear search
through all remaining refs to find any duplicates of the current ref.

Rewriting it to use a string list to keep track of which refs have
already been seen and removing duplicates when they are found is much
more efficient.

Signed-off-by: Julian Phillips <julian@quantumfyre.co.uk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

diff --git a/remote.c b/remote.c
index 73d33f258..4f9f0ccc7 100644
--- a/remote.c
+++ b/remote.c
@@ -6,6 +6,7 @@
 #include "revision.h"
 #include "dir.h"
 #include "tag.h"
+#include "string-list.h"
 
 static struct refspec s_tag_refspec = {
 	0,
@@ -734,29 +735,31 @@ int for_each_remote(each_remote_fn fn, void *priv)
 
 void ref_remove_duplicates(struct ref *ref_map)
 {
-	struct ref **posn;
-	struct ref *next;
-	for (; ref_map; ref_map = ref_map->next) {
+	struct string_list refs = { NULL, 0, 0, 0 };
+	struct string_list_item *item = NULL;
+	struct ref *prev = NULL, *next = NULL;
+	for (; ref_map; prev = ref_map, ref_map = next) {
+		next = ref_map->next;
 		if (!ref_map->peer_ref)
 			continue;
-		posn = &ref_map->next;
-		while (*posn) {
-			if ((*posn)->peer_ref &&
-			    !strcmp((*posn)->peer_ref->name,
-				    ref_map->peer_ref->name)) {
-				if (strcmp((*posn)->name, ref_map->name))
-					die("%s tracks both %s and %s",
-					    ref_map->peer_ref->name,
-					    (*posn)->name, ref_map->name);
-				next = (*posn)->next;
-				free((*posn)->peer_ref);
-				free(*posn);
-				*posn = next;
-			} else {
-				posn = &(*posn)->next;
-			}
+
+		item = string_list_lookup(ref_map->peer_ref->name, &refs);
+		if (item) {
+			if (strcmp(((struct ref *)item->util)->name,
+				   ref_map->name))
+				die("%s tracks both %s and %s",
+				    ref_map->peer_ref->name,
+				    ((struct ref *)item->util)->name,
+				    ref_map->name);
+			prev->next = ref_map->next;
+			free(ref_map->peer_ref);
+			free(ref_map);
 		}
+
+		item = string_list_insert(ref_map->peer_ref->name, &refs);
+		item->util = ref_map;
 	}
+	string_list_clear(&refs, 0);
 }
 
 int remote_has_url(struct remote *remote, const char *url)