fsck: avoid reading every object twice

During verify_pack() all objects are read for SHA-1 check. Then
fsck_sha1() is called on every object, which read the object again
(fsck_sha1 -> parse_object -> read_sha1_file).

Avoid reading an object twice, do fsck_sha1 while we have an object
uncompressed data in verify_pack.

On git.git, with this patch I got:

$ /usr/bin/time ./git fsck >/dev/null
98.97user 0.90system 1:40.01elapsed 99%CPU (0avgtext+0avgdata 616624maxresident)k
0inputs+0outputs (0major+194186minor)pagefaults 0swaps

Without it:

$ /usr/bin/time ./git fsck >/dev/null
231.23user 2.35system 3:53.82elapsed 99%CPU (0avgtext+0avgdata 636688maxresident)k
0inputs+0outputs (0major+461629minor)pagefaults 0swaps

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 25 insertions, 17 deletions

diff --git a/builtin/fsck.c b/builtin/fsck.c
index 4ead98dca..0603f6444 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -282,14 +282,8 @@ static void check_connectivity(void)
 	}
 }
 
-static int fsck_sha1(const unsigned char *sha1)
+static int fsck_obj(struct object *obj)
 {
-	struct object *obj = parse_object(sha1);
-	if (!obj) {
-		errors_found |= ERROR_OBJECT;
-		return error("%s: object corrupt or missing",
-			     sha1_to_hex(sha1));
-	}
 	if (obj->flags & SEEN)
 		return 0;
 	obj->flags |= SEEN;
@@ -332,6 +326,29 @@ static int fsck_sha1(const unsigned char *sha1)
 	return 0;
 }
 
+static int fsck_sha1(const unsigned char *sha1)
+{
+	struct object *obj = parse_object(sha1);
+	if (!obj) {
+		errors_found |= ERROR_OBJECT;
+		return error("%s: object corrupt or missing",
+			     sha1_to_hex(sha1));
+	}
+	return fsck_obj(obj);
+}
+
+static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
+			   unsigned long size, void *buffer, int *eaten)
+{
+	struct object *obj;
+	obj = parse_object_buffer(sha1, type, size, buffer, eaten);
+	if (!obj) {
+		errors_found |= ERROR_OBJECT;
+		return error("%s: object corrupt or missing", sha1_to_hex(sha1));
+	}
+	return fsck_obj(obj);
+}
+
 /*
  * This is the sorting chunk size: make it reasonably
  * big so that we can sort well..
@@ -627,17 +644,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 		prepare_packed_git();
 		for (p = packed_git; p; p = p->next)
 			/* verify gives error messages itself */
-			if (verify_pack(p))
+			if (verify_pack(p, fsck_obj_buffer))
 				errors_found |= ERROR_PACK;
-
-		for (p = packed_git; p; p = p->next) {
-			uint32_t j, num;
-			if (open_pack_index(p))
-				continue;
-			num = p->num_objects;
-			for (j = 0; j < num; j++)
-				fsck_sha1(nth_packed_object_sha1(p, j));
-		}
 	}
 
 	heads = 0;