@matheusbsbs / matheus-bagliano / commits / 33d4221c79

write_sha1_file: freshen existing objects

When we try to write a loose object file, we first check whether that object already exists. If so, we skip the write as an optimization. However, this can interfere with prune's strategy of using mtimes to mark files in progress. For example, if a branch contains a particular tree object and is deleted, that tree object may become unreachable, and have an old mtime. If a new operation then tries to write the same tree, this ends up as a noop; we notice we already have the object and do nothing. A prune running simultaneously with this operation will see the object as old, and may delete it. We can solve this by "freshening" objects that we avoid writing by updating their mtime. The algorithm for doing so is essentially the same as that of has_sha1_file. Therefore we provide a new (static) interface "check_and_freshen", which finds and optionally freshens the object. It's trivial to implement freshening and simple checking by tweaking a single parameter. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Jeff King committed Oct 15, 2014 at 18:42 UTC 33d4221c79c89844bed6b9558cc2bc497251ef70

2 files changed +71 -7

sha1_file.c

+44 -7

@@ -442,27 +442,53 @@ void prepare_alt_odb(void)

442 read_info_alternates(get_object_directory(), 0);

443 }

444

445 -static int has_loose_object_local(const unsigned char *sha1)

445 +static int freshen_file(const char *fn)

446 {

447 - return !access(sha1_file_name(sha1), F_OK);

447 + struct utimbuf t;

448 + t.actime = t.modtime = time(NULL);

449 + return !utime(fn, &t);

450 }

451

450 -int has_loose_object_nonlocal(const unsigned char *sha1)

452 +static int check_and_freshen_file(const char *fn, int freshen)

453 +{

454 + if (access(fn, F_OK))

455 + return 0;

456 + if (freshen && freshen_file(fn))

457 + return 0;

458 + return 1;

459 +}

460 +

461 +static int check_and_freshen_local(const unsigned char *sha1, int freshen)

462 +{

463 + return check_and_freshen_file(sha1_file_name(sha1), freshen);

464 +}

465 +

466 +static int check_and_freshen_nonlocal(const unsigned char *sha1, int freshen)

467 {

468 struct alternate_object_database *alt;

469 prepare_alt_odb();

470 for (alt = alt_odb_list; alt; alt = alt->next) {

471 fill_sha1_path(alt->name, sha1);

456 - if (!access(alt->base, F_OK))

472 + if (check_and_freshen_file(alt->base, freshen))

473 return 1;

474 }

475 return 0;

476 }

477

478 +static int check_and_freshen(const unsigned char *sha1, int freshen)

479 +{

480 + return check_and_freshen_local(sha1, freshen) ||

481 + check_and_freshen_nonlocal(sha1, freshen);

482 +}

483 +

484 +int has_loose_object_nonlocal(const unsigned char *sha1)

485 +{

486 + return check_and_freshen_nonlocal(sha1, 0);

487 +}

488 +

489 static int has_loose_object(const unsigned char *sha1)

490 {

464 - return has_loose_object_local(sha1) ||

465 - has_loose_object_nonlocal(sha1);

491 + return check_and_freshen(sha1, 0);

492 }

493

494 static unsigned int pack_used_ctr;

@@ -2965,6 +2991,17 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,

2991 return move_temp_to_file(tmp_file, filename);

2992 }

2993

2994 +static int freshen_loose_object(const unsigned char *sha1)

2995 +{

2996 + return check_and_freshen(sha1, 1);

2997 +}

2998 +

2999 +static int freshen_packed_object(const unsigned char *sha1)

3000 +{

3001 + struct pack_entry e;

3002 + return find_pack_entry(sha1, &e) && freshen_file(e.p->pack_name);

3003 +}

3004 +

3005 int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)

3006 {

3007 unsigned char sha1[20];

@@ -2977,7 +3014,7 @@ int write_sha1_file(const void *buf, unsigned long len, const char *type, unsign

3014 write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);

3015 if (returnsha1)

3016 hashcpy(returnsha1, sha1);

2980 - if (has_sha1_file(sha1))

3017 + if (freshen_loose_object(sha1) || freshen_packed_object(sha1))

3018 return 0;

3019 return write_loose_object(sha1, hdr, hdrlen, buf, len, 0);

3020 }

t/t6501-freshen-objects.sh

+27

@@ -100,6 +100,33 @@ for repack in '' true; do

100 test_expect_success "repository passes fsck ($title)" '

101 git fsck

102 '

103 +

104 + test_expect_success "abandon objects again ($title)" '

105 + git reset --hard HEAD^ &&

106 + find .git/objects -type f |

107 + xargs test-chmtime -v -86400

108 + '

109 +

110 + test_expect_success "start writing new commit with same tree ($title)" '

111 + tree=$(

112 + GIT_INDEX_FILE=index.tmp &&

113 + export GIT_INDEX_FILE &&

114 + git read-tree HEAD &&

115 + add abandon &&

116 + add unrelated &&

117 + git write-tree

118 + )

119 + '

120 +

121 + test_expect_success "simultaneous gc ($title)" '

122 + git gc --prune=12.hours.ago

123 + '

124 +

125 + # tree should have been refreshed by write-tree

126 + test_expect_success "finish writing out commit ($title)" '

127 + commit=$(echo foo | git commit-tree -p HEAD $tree) &&

128 + git update-ref HEAD $commit

129 + '

130 done

131

132 test_done