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>
Nguyễn Thái Ngọc Duy committed
Nov 7, 2011 at 09:59 UTC
c9486eb04dd99fc00df3e68f9b908f9ad7ff9728
3 files changed
+39
-21
builtin/fsck.c
+25
-17
@@ -282,14 +282,8 @@ static void check_connectivity(void)
282
}
283
}
284
285
-static int fsck_sha1(const unsigned char *sha1)
285
+static int fsck_obj(struct object *obj)
286
{
287
- struct object *obj = parse_object(sha1);
288
- if (!obj) {
289
- errors_found |= ERROR_OBJECT;
290
- return error("%s: object corrupt or missing",
291
- sha1_to_hex(sha1));
292
- }
287
if (obj->flags & SEEN)
288
return 0;
289
obj->flags |= SEEN;
@@ -332,6 +326,29 @@ static int fsck_sha1(const unsigned char *sha1)
326
return 0;
327
}
328
329
+static int fsck_sha1(const unsigned char *sha1)
330
+{
331
+ struct object *obj = parse_object(sha1);
332
+ if (!obj) {
333
+ errors_found |= ERROR_OBJECT;
334
+ return error("%s: object corrupt or missing",
335
+ sha1_to_hex(sha1));
336
+ }
337
+ return fsck_obj(obj);
338
+}
339
+
340
+static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
341
+ unsigned long size, void *buffer, int *eaten)
342
+{
343
+ struct object *obj;
344
+ obj = parse_object_buffer(sha1, type, size, buffer, eaten);
345
+ if (!obj) {
346
+ errors_found |= ERROR_OBJECT;
347
+ return error("%s: object corrupt or missing", sha1_to_hex(sha1));
348
+ }
349
+ return fsck_obj(obj);
350
+}
351
+
352
/*
353
* This is the sorting chunk size: make it reasonably
354
* big so that we can sort well..
@@ -627,17 +644,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
644
prepare_packed_git();
645
for (p = packed_git; p; p = p->next)
646
/* verify gives error messages itself */
630
- if (verify_pack(p))
647
+ if (verify_pack(p, fsck_obj_buffer))
648
errors_found |= ERROR_PACK;
632
-
633
- for (p = packed_git; p; p = p->next) {
634
- uint32_t j, num;
635
- if (open_pack_index(p))
636
- continue;
637
- num = p->num_objects;
638
- for (j = 0; j < num; j++)
639
- fsck_sha1(nth_packed_object_sha1(p, j));
640
- }
649
}
650
651
heads = 0;
pack-check.c
+10
-3
@@ -42,7 +42,8 @@ int check_pack_crc(struct packed_git *p, struct pack_window **w_curs,
42
}
43
44
static int verify_packfile(struct packed_git *p,
45
- struct pack_window **w_curs)
45
+ struct pack_window **w_curs,
46
+ verify_fn fn)
47
{
48
off_t index_size = p->index_size;
49
const unsigned char *index_base = p->index_data;
@@ -120,6 +121,12 @@ static int verify_packfile(struct packed_git *p,
121
else if (check_sha1_signature(entries[i].sha1, data, size, typename(type)))
122
err = error("packed %s from %s is corrupt",
123
sha1_to_hex(entries[i].sha1), p->pack_name);
124
+ else if (fn) {
125
+ int eaten = 0;
126
+ fn(entries[i].sha1, type, size, data, &eaten);
127
+ if (eaten)
128
+ data = NULL;
129
+ }
130
free(data);
131
}
132
free(entries);
@@ -150,7 +157,7 @@ int verify_pack_index(struct packed_git *p)
157
return err;
158
}
159
153
-int verify_pack(struct packed_git *p)
160
+int verify_pack(struct packed_git *p, verify_fn fn)
161
{
162
int err = 0;
163
struct pack_window *w_curs = NULL;
@@ -159,7 +166,7 @@ int verify_pack(struct packed_git *p)
166
if (!p->index_data)
167
return -1;
168
162
- err |= verify_packfile(p, &w_curs);
169
+ err |= verify_packfile(p, &w_curs, fn);
170
unuse_pack(&w_curs);
171
172
return err;
pack.h
+4
-1
@@ -70,10 +70,13 @@ struct pack_idx_entry {
70
off_t offset;
71
};
72
73
+
74
+typedef int (*verify_fn)(const unsigned char*, enum object_type, unsigned long, void*, int*);
75
+
76
extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, const struct pack_idx_option *, unsigned char *sha1);
77
extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
78
extern int verify_pack_index(struct packed_git *);
76
-extern int verify_pack(struct packed_git *);
79
+extern int verify_pack(struct packed_git *, verify_fn fn);
80
extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);
81
extern char *index_pack_lockfile(int fd);
82
extern int encode_in_pack_object_header(enum object_type, uintmax_t, unsigned char *);