[PATCH v3 4/4] describe: Delay looking up commits until searching for an inexact match

From: Anders Kaseorg <andersk@ksplice.com>
Date: Dec 9, 2010, 06:47 UTC
Message-ID: <alpine.DEB.2.02.1012090146160.23348@dr-wily.mit.edu>
In-Reply-To: <alpine.DEB.2.02.1012090140390.23348@dr-wily.mit.edu>

Now that struct commit.util is not used until after we’ve checked that the argument doesn’t exactly match a tag, we can wait until then to look up the commits for each tag.

This avoids a lot of I/O on --exact-match queries in repositories with many tags. For example, ‘git describe --exact-match HEAD’ becomes about 12 times faster on a cold cache (3.2s instead of 39s) in a linux-2.6 repository with 2000 packed tags. That’s a huge win for the interactivity of the __git_ps1 shell prompt helper when on a detached HEAD.

Signed-off-by: Anders Kaseorg <andersk@ksplice.com>
---

Change from v2: Process the entire hash chain in set_util().

 builtin/describe.c |   37 ++++++++++++++++++++++---------------
 1 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/builtin/describe.c b/builtin/describe.c
index 8149233..a0f52c1 100644
--- a/builtin/describe.c
+++ b/builtin/describe.c
@@ -24,6 +24,7 @@ static int longformat;
 static int abbrev = DEFAULT_ABBREV;
 static int max_candidates = 10;
 static struct hash_table names;
+static int have_util;
 static const char *pattern;
 static int always;
 static const char *dirty;
@@ -62,6 +63,17 @@ static inline struct commit_name *find_commit_name(const unsigned char *peeled)
 	return n;
 }
 
+static int set_util(void *chain)
+{
+	struct commit_name *n;
+	for (n = chain; n; n = n->next) {
+		struct commit *c = lookup_commit_reference_gently(n->peeled, 1);
+		if (c)
+			c->util = n;
+	}
+	return 0;
+}
+
 static int replace_name(struct commit_name *e,
 			       int prio,
 			       const unsigned char *sha1,
@@ -96,18 +108,16 @@ static int replace_name(struct commit_name *e,
 }
 
 static void add_to_known_names(const char *path,
-			       struct commit *commit,
+			       const unsigned char *peeled,
 			       int prio,
 			       const unsigned char *sha1)
 {
-	const unsigned char *peeled = commit->object.sha1;
 	struct commit_name *e = find_commit_name(peeled);
 	struct tag *tag = NULL;
 	if (replace_name(e, prio, sha1, &tag)) {
 		if (!e) {
 			void **pos;
 			e = xmalloc(sizeof(struct commit_name));
-			commit->util = e;
 			hashcpy(e->peeled, peeled);
 			pos = insert_hash(hash_sha1(peeled), e, &names);
 			if (pos) {
@@ -128,8 +138,6 @@ static void add_to_known_names(const char *path,
 static int get_name(const char *path, const unsigned char *sha1, int flag, void *cb_data)
 {
 	int might_be_tag = !prefixcmp(path, "refs/tags/");
-	struct commit *commit;
-	struct object *object;
 	unsigned char peeled[20];
 	int is_tag, prio;
 
@@ -137,16 +145,10 @@ static int get_name(const char *path, const unsigned char *sha1, int flag, void
 		return 0;
 
 	if (!peel_ref(path, peeled) && !is_null_sha1(peeled)) {
-		commit = lookup_commit_reference_gently(peeled, 1);
-		if (!commit)
-			return 0;
-		is_tag = !!hashcmp(sha1, commit->object.sha1);
+		is_tag = !!hashcmp(sha1, peeled);
 	} else {
-		commit = lookup_commit_reference_gently(sha1, 1);
-		object = parse_object(sha1);
-		if (!commit || !object)
-			return 0;
-		is_tag = object->type == OBJ_TAG;
+		hashcpy(peeled, sha1);
+		is_tag = 0;
 	}
 
 	/* If --all, then any refs are used.
@@ -169,7 +171,7 @@ static int get_name(const char *path, const unsigned char *sha1, int flag, void
 		if (!prio)
 			return 0;
 	}
-	add_to_known_names(all ? path + 5 : path + 10, commit, prio, sha1);
+	add_to_known_names(all ? path + 5 : path + 10, peeled, prio, sha1);
 	return 0;
 }
 
@@ -286,6 +288,11 @@ static void describe(const char *arg, int last_one)
 	if (debug)
 		fprintf(stderr, "searching to describe %s\n", arg);
 
+	if (!have_util) {
+		for_each_hash(&names, set_util);
+		have_util = 1;
+	}
+
 	list = NULL;
 	cmit->object.flags = SEEN;
 	commit_list_insert(cmit, &list);

-- 
1.7.3.3