[PATCH 2/3] bulk-checkin: do not write the same object twice
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
bulk-checkin.c | 28 ++++++++++++++++++++++++----
t/t1050-large.sh | 20 +++++++++++++-------
2 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/bulk-checkin.c b/bulk-checkin.c
index c7e693e..82166ba 100644
--- a/bulk-checkin.c
+++ b/bulk-checkin.c
@@ -52,6 +52,17 @@ static void finish_bulk_checkin(struct bulk_checkin_state *state)
reprepare_packed_git();
}
+static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
+{
+ int i;
+
+ /* Might want to keep the list sorted */
+ for (i = 0; i < state->nr_written; i++)
+ if (!hashcmp(state->written[i]->sha1, sha1))
+ return 1;
+ return 0;
+}
+
static void deflate_to_pack(struct bulk_checkin_state *state,
unsigned char sha1[],
int fd, size_t size, enum object_type type,
@@ -64,6 +75,7 @@ static void deflate_to_pack(struct bulk_checkin_state *state,
int write_object = (flags & HASH_WRITE_OBJECT);
int status = Z_OK;
struct pack_idx_entry *idx = NULL;
+ struct sha1file_checkpoint checkpoint;
hdrlen = sprintf((char *)obuf, "%s %" PRIuMAX,
typename(type), (uintmax_t)size) + 1;
@@ -73,6 +85,7 @@ static void deflate_to_pack(struct bulk_checkin_state *state,
if (write_object) {
idx = xcalloc(1, sizeof(*idx));
idx->offset = state->offset;
+ sha1file_checkpoint(state->f, &checkpoint);
crc32_begin(state->f);
}
memset(&s, 0, sizeof(s));
@@ -121,10 +134,17 @@ static void deflate_to_pack(struct bulk_checkin_state *state,
git_SHA1_Final(sha1, &ctx);
if (write_object) {
idx->crc32 = crc32_end(state->f);
- hashcpy(idx->sha1, sha1);
- ALLOC_GROW(state->written,
- state->nr_written + 1, state->alloc_written);
- state->written[state->nr_written++] = idx;
+
+ if (already_written(state, sha1)) {
+ sha1file_truncate(state->f, &checkpoint);
+ state->offset = checkpoint.offset;
+ free(idx);
+ } else {
+ hashcpy(idx->sha1, sha1);
+ ALLOC_GROW(state->written,
+ state->nr_written + 1, state->alloc_written);
+ state->written[state->nr_written++] = idx;
+ }
}
}
diff --git a/t/t1050-large.sh b/t/t1050-large.sh
index 36def25..fbd5ced 100755
--- a/t/t1050-large.sh
+++ b/t/t1050-large.sh
@@ -7,22 +7,28 @@ test_description='adding and checking out large blobs'
test_expect_success setup '
git config core.bigfilethreshold 200k &&
- echo X | dd of=large bs=1k seek=2000 &&
+ echo X | dd of=large1 bs=1k seek=2000 &&
+ echo X | dd of=large2 bs=1k seek=2000 &&
echo Y | dd of=huge bs=1k seek=2500
'
test_expect_success 'add a large file or two' '
- git add large huge &&
+ git add large1 huge large2 &&
# make sure we got a single packfile and no loose objects
- bad= count=0 &&
+ bad= count=0 idx= &&
for p in .git/objects/pack/pack-*.pack
do
count=$(( $count + 1 ))
- test -f "$p" && continue
+ if test -f "$p" && idx=${p%.pack}.idx && test -f "$idx"
+ then
+ continue
+ fi
bad=t
done &&
test -z "$bad" &&
test $count = 1 &&
+ cnt=$(git show-index <"$idx" | wc -l) &&
+ test $cnt = 2 &&
for l in .git/objects/??/??????????????????????????????????????
do
test -f "$l" || continue
@@ -32,10 +38,10 @@ test_expect_success 'add a large file or two' '
'
test_expect_success 'checkout a large file' '
- large=$(git rev-parse :large) &&
- git update-index --add --cacheinfo 100644 $large another &&
+ large1=$(git rev-parse :large1) &&
+ git update-index --add --cacheinfo 100644 $large1 another &&
git checkout another &&
- cmp large another ;# this must not be test_cmp
+ cmp large1 another ;# this must not be test_cmp
'
test_done
--
1.7.8.rc3.111.g7d421
Junio C Hamano <gitster@pobox.com>