@matheusbsbs / matheus-bagliano / commits / e6c587c733

abbrev: auto size the default abbreviation

In fairly early days we somehow decided to abbreviate object names down to 7-hexdigits, but as projects grow, it is becoming more and more likely to see such a short object names made in earlier days and recorded in the log messages no longer unique. Currently the Linux kernel project needs 11 to 12 hexdigits, while Git itself needs 10 hexdigits to uniquely identify the objects they have, while many smaller projects may still be fine with the original 7-hexdigit default. One-size does not fit all projects. Introduce a mechanism, where we estimate the number of objects in the repository upon the first request to abbreviate an object name with the default setting and come up with a sane default for the repository. Based on the expectation that we would see collision in a repository with 2^(2N) objects when using object names shortened to first N bits, use sufficient number of hexdigits to cover the number of objects in the repository. Each hexdigit (4-bits) we add to the shortened name allows us to have four times (2-bits) as many objects in the repository. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Linus Torvalds committed Sep 30, 2016 at 17:19 UTC e6c587c733b4634030b353f4024794b08bc86892

3 files changed +29 -2

cache.h

@@ -1204,6 +1204,7 @@ struct object_context {

1204 #define GET_SHA1_TREEISH 020

1205 #define GET_SHA1_BLOB 040

1206 #define GET_SHA1_FOLLOW_SYMLINKS 0100

1207 +#define GET_SHA1_AUTOMATIC 0200

1208 #define GET_SHA1_ONLY_TO_DIE 04000

1209

1210 #define GET_SHA1_DISAMBIGUATORS \

environment.c

+1 -1

@@ -16,7 +16,7 @@ int trust_executable_bit = 1;

16 int trust_ctime = 1;

17 int check_stat = 1;

18 int has_symlinks = 1;

19 -int minimum_abbrev = 4, default_abbrev = FALLBACK_DEFAULT_ABBREV;

19 +int minimum_abbrev = 4, default_abbrev = -1;

20 int ignore_case;

21 int assume_unchanged;

22 int prefer_symlink_refs;

sha1_name.c

+27 -1

@@ -15,6 +15,7 @@ typedef int (*disambiguate_hint_fn)(const unsigned char *, void *);

16 struct disambiguate_state {

17 int len; /* length of prefix in hex chars */

18 + unsigned int nrobjects;

19 char hex_pfx[GIT_SHA1_HEXSZ + 1];

20 unsigned char bin_pfx[GIT_SHA1_RAWSZ];

@@ -118,6 +119,14 @@ static void find_short_object_filename(struct disambiguate_state *ds)

119

120 if (strlen(de->d_name) != 38)

121 continue;

122 +

123 + /*

124 + * We only look at the one subdirectory, and we assume

125 + * each subdirectory is roughly similar, so each

126 + * object we find probably has 255 other objects in

127 + * the other fan-out directories.

128 + */

129 + ds->nrobjects += 256;

130 if (memcmp(de->d_name, ds->hex_pfx + 2, ds->len - 2))

131 continue;

132 memcpy(hex + 2, de->d_name, 38);

@@ -151,6 +160,7 @@ static void unique_in_pack(struct packed_git *p,

160

161 open_pack_index(p);

162 num = p->num_objects;

163 + ds->nrobjects += num;

164 last = num;

165 while (first < last) {

166 uint32_t mid = (first + last) / 2;

@@ -380,6 +390,9 @@ static int show_ambiguous_object(const unsigned char *sha1, void *data)

390 return 0;

391 }

392

393 +/* start from our historical default before the automatic abbreviation */

394 +static int default_automatic_abbrev = FALLBACK_DEFAULT_ABBREV;

395 +

396 static int get_short_sha1(const char *name, int len, unsigned char *sha1,

397 unsigned flags)

398 {

@@ -426,6 +439,14 @@ static int get_short_sha1(const char *name, int len, unsigned char *sha1,

439 for_each_abbrev(ds.hex_pfx, show_ambiguous_object, &ds);

440 }

441

442 + if (len < 16 && !status && (flags & GET_SHA1_AUTOMATIC)) {

443 + unsigned int expect_collision = 1 << (len * 2);

444 + if (ds.nrobjects > expect_collision) {

445 + default_automatic_abbrev = len+1;

446 + return SHORT_NAME_AMBIGUOUS;

447 + }

448 + }

449 +

450 return status;

451 }

452

@@ -458,14 +479,19 @@ int for_each_abbrev(const char *prefix, each_abbrev_fn fn, void *cb_data)

479 int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len)

480 {

481 int status, exists;

482 + int flags = GET_SHA1_QUIETLY;

483

484 + if (len < 0) {

485 + flags |= GET_SHA1_AUTOMATIC;

486 + len = default_automatic_abbrev;

487 + }

488 sha1_to_hex_r(hex, sha1);

489 if (len == 40 || !len)

490 return 40;

491 exists = has_sha1_file(sha1);

492 while (len < 40) {

493 unsigned char sha1_ret[20];

468 - status = get_short_sha1(hex, len, sha1_ret, GET_SHA1_QUIETLY);

494 + status = get_short_sha1(hex, len, sha1_ret, flags);

495 if (exists

496 ? !status

497 : status == SHORT_NAME_NOT_FOUND) {