@matheusbsbs / matheus-bagliano / commits / 30b939c33a

fast-export: do not load blob objects twice

When fast-export wants to export a blob object, it first calls parse_object to get a "struct object" and check whether we have already shown the object. If we haven't shown it, we then use read_sha1_file to pull it from disk and write it out. That means we load each blob from disk twice: once for parse_object to find its type and check its sha1, and a second time when we actually output it. We can drop this to a single load by using lookup_object to check the SHOWN flag, and then checking the signature on and outputting a single buffer. This provides modest speedups on git.git (best-of-five, "git fast-export HEAD >/dev/null"): [before] [after] real 0m14.347s real 0m13.780s user 0m14.084s user 0m13.620s sys 0m0.208s sys 0m0.100s and somewhat more on more blob-heavy repos (this is a repository full of media files): [before] [after] real 0m52.236s real 0m44.451s user 0m50.568s user 0m43.000s sys 0m1.536s sys 0m1.284s Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Jeff King committed Mar 17, 2013 at 04:38 UTC 30b939c33ad5b8a9dfbe3fe5aafc36d89c40409f

1 file changed +10 -6

builtin/fast-export.c

+10 -6

@@ -119,6 +119,7 @@ static void export_blob(const unsigned char *sha1)

119 enum object_type type;

120 char *buf;

121 struct object *object;

122 + int eaten;

123

124 if (no_data)

125 return;

@@ -126,16 +127,18 @@ static void export_blob(const unsigned char *sha1)

127 if (is_null_sha1(sha1))

128 return;

129

129 - object = parse_object(sha1);

130 - if (!object)

131 - die ("Could not read blob %s", sha1_to_hex(sha1));

132 -

133 - if (object->flags & SHOWN)

130 + object = lookup_object(sha1);

131 + if (object && object->flags & SHOWN)

132 return;

133

134 buf = read_sha1_file(sha1, &type, &size);

135 if (!buf)

136 die ("Could not read blob %s", sha1_to_hex(sha1));

137 + if (check_sha1_signature(sha1, buf, size, typename(type)) < 0)

138 + die("sha1 mismatch in blob %s", sha1_to_hex(sha1));

139 + object = parse_object_buffer(sha1, type, size, buf, &eaten);

140 + if (!object)

141 + die("Could not read blob %s", sha1_to_hex(sha1));

142

143 mark_next_object(object);

144

@@ -147,7 +150,8 @@ static void export_blob(const unsigned char *sha1)

150 show_progress();

151

152 object->flags |= SHOWN;

150 - free(buf);

153 + if (!eaten)

154 + free(buf);

155 }

156

157 static int depth_first(const void *a_, const void *b_)