summaryrefslogtreecommitdiff
path: root/builtin/pack-objects.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2016-09-21 22:15:21 (GMT)
committerJunio C Hamano <gitster@pobox.com>2016-09-21 22:15:21 (GMT)
commit7f109ef54e96ac7ae7e036487b881432170a3817 (patch)
tree51778e47095d0451da9cf187a94da67177fe57d7 /builtin/pack-objects.c
parentf0a84de2770361d21115f6768b2c4746519dbf62 (diff)
parent645c432d6196903bcd9e8a82d150aac1428ccf34 (diff)
downloadgit-7f109ef54e96ac7ae7e036487b881432170a3817.zip
git-7f109ef54e96ac7ae7e036487b881432170a3817.tar.gz
git-7f109ef54e96ac7ae7e036487b881432170a3817.tar.bz2
Merge branch 'ks/pack-objects-bitmap'
Some codepaths in "git pack-objects" were not ready to use an existing pack bitmap; now they are and as the result they have become faster. * ks/pack-objects-bitmap: pack-objects: use reachability bitmap index when generating non-stdout pack pack-objects: respect --local/--honor-pack-keep/--incremental when bitmap is in use
Diffstat (limited to 'builtin/pack-objects.c')
-rw-r--r--builtin/pack-objects.c128
1 files changed, 88 insertions, 40 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 0954375..166e52c 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -67,7 +67,8 @@ static struct packed_git *reuse_packfile;
static uint32_t reuse_packfile_objects;
static off_t reuse_packfile_offset;
-static int use_bitmap_index = 1;
+static int use_bitmap_index_default = 1;
+static int use_bitmap_index = -1;
static int write_bitmap_index;
static uint16_t write_bitmap_options;
@@ -945,13 +946,48 @@ static int have_duplicate_entry(const unsigned char *sha1,
return 1;
}
+static int want_found_object(int exclude, struct packed_git *p)
+{
+ if (exclude)
+ return 1;
+ if (incremental)
+ return 0;
+
+ /*
+ * When asked to do --local (do not include an object that appears in a
+ * pack we borrow from elsewhere) or --honor-pack-keep (do not include
+ * an object that appears in a pack marked with .keep), finding a pack
+ * that matches the criteria is sufficient for us to decide to omit it.
+ * However, even if this pack does not satisfy the criteria, we need to
+ * make sure no copy of this object appears in _any_ pack that makes us
+ * to omit the object, so we need to check all the packs.
+ *
+ * We can however first check whether these options can possible matter;
+ * if they do not matter we know we want the object in generated pack.
+ * Otherwise, we signal "-1" at the end to tell the caller that we do
+ * not know either way, and it needs to check more packs.
+ */
+ if (!ignore_packed_keep &&
+ (!local || !have_non_local_packs))
+ return 1;
+
+ if (local && !p->pack_local)
+ return 0;
+ if (ignore_packed_keep && p->pack_local && p->pack_keep)
+ return 0;
+
+ /* we don't know yet; keep looking for more packs */
+ return -1;
+}
+
/*
* Check whether we want the object in the pack (e.g., we do not want
* objects found in non-local stores if the "--local" option was used).
*
- * As a side effect of this check, we will find the packed version of this
- * object, if any. We therefore pass out the pack information to avoid having
- * to look it up again later.
+ * If the caller already knows an existing pack it wants to take the object
+ * from, that is passed in *found_pack and *found_offset; otherwise this
+ * function finds if there is any pack that has the object and returns the pack
+ * and its offset in these variables.
*/
static int want_object_in_pack(const unsigned char *sha1,
int exclude,
@@ -959,15 +995,30 @@ static int want_object_in_pack(const unsigned char *sha1,
off_t *found_offset)
{
struct packed_git *p;
+ int want;
if (!exclude && local && has_loose_object_nonlocal(sha1))
return 0;
- *found_pack = NULL;
- *found_offset = 0;
+ /*
+ * If we already know the pack object lives in, start checks from that
+ * pack - in the usual case when neither --local was given nor .keep files
+ * are present we will determine the answer right now.
+ */
+ if (*found_pack) {
+ want = want_found_object(exclude, *found_pack);
+ if (want != -1)
+ return want;
+ }
for (p = packed_git; p; p = p->next) {
- off_t offset = find_pack_entry_one(sha1, p);
+ off_t offset;
+
+ if (p == *found_pack)
+ offset = *found_offset;
+ else
+ offset = find_pack_entry_one(sha1, p);
+
if (offset) {
if (!*found_pack) {
if (!is_pack_valid(p))
@@ -975,31 +1026,9 @@ static int want_object_in_pack(const unsigned char *sha1,
*found_offset = offset;
*found_pack = p;
}
- if (exclude)
- return 1;
- if (incremental)
- return 0;
-
- /*
- * When asked to do --local (do not include an
- * object that appears in a pack we borrow
- * from elsewhere) or --honor-pack-keep (do not
- * include an object that appears in a pack marked
- * with .keep), we need to make sure no copy of this
- * object come from in _any_ pack that causes us to
- * omit it, and need to complete this loop. When
- * neither option is in effect, we know the object
- * we just found is going to be packed, so break
- * out of the loop to return 1 now.
- */
- if (!ignore_packed_keep &&
- (!local || !have_non_local_packs))
- break;
-
- if (local && !p->pack_local)
- return 0;
- if (ignore_packed_keep && p->pack_local && p->pack_keep)
- return 0;
+ want = want_found_object(exclude, p);
+ if (want != -1)
+ return want;
}
}
@@ -1040,8 +1069,8 @@ static const char no_closure_warning[] = N_(
static int add_object_entry(const unsigned char *sha1, enum object_type type,
const char *name, int exclude)
{
- struct packed_git *found_pack;
- off_t found_offset;
+ struct packed_git *found_pack = NULL;
+ off_t found_offset = 0;
uint32_t index_pos;
if (have_duplicate_entry(sha1, exclude, &index_pos))
@@ -1074,6 +1103,9 @@ static int add_object_entry_from_bitmap(const unsigned char *sha1,
if (have_duplicate_entry(sha1, 0, &index_pos))
return 0;
+ if (!want_object_in_pack(sha1, 0, &pack, &offset))
+ return 0;
+
create_object_entry(sha1, type, name_hash, 0, 0, index_pos, pack, offset);
display_progress(progress_state, nr_result);
@@ -2273,7 +2305,7 @@ static int git_pack_config(const char *k, const char *v, void *cb)
write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE;
}
if (!strcmp(k, "pack.usebitmaps")) {
- use_bitmap_index = git_config_bool(k, v);
+ use_bitmap_index_default = git_config_bool(k, v);
return 0;
}
if (!strcmp(k, "pack.threads")) {
@@ -2522,13 +2554,13 @@ static void loosen_unused_packed_objects(struct rev_info *revs)
}
/*
- * This tracks any options which a reader of the pack might
- * not understand, and which would therefore prevent blind reuse
- * of what we have on disk.
+ * This tracks any options which pack-reuse code expects to be on, or which a
+ * reader of the pack might not understand, and which would therefore prevent
+ * blind reuse of what we have on disk.
*/
static int pack_options_allow_reuse(void)
{
- return allow_ofs_delta;
+ return pack_to_stdout && allow_ofs_delta;
}
static int get_object_list_from_bitmap(struct rev_info *revs)
@@ -2821,7 +2853,23 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
if (!rev_list_all || !rev_list_reflog || !rev_list_index)
unpack_unreachable_expiration = 0;
- if (!use_internal_rev_list || !pack_to_stdout || is_repository_shallow())
+ /*
+ * "soft" reasons not to use bitmaps - for on-disk repack by default we want
+ *
+ * - to produce good pack (with bitmap index not-yet-packed objects are
+ * packed in suboptimal order).
+ *
+ * - to use more robust pack-generation codepath (avoiding possible
+ * bugs in bitmap code and possible bitmap index corruption).
+ */
+ if (!pack_to_stdout)
+ use_bitmap_index_default = 0;
+
+ if (use_bitmap_index < 0)
+ use_bitmap_index = use_bitmap_index_default;
+
+ /* "hard" reasons not to use bitmaps; these just won't work at all */
+ if (!use_internal_rev_list || (!pack_to_stdout && write_bitmap_index) || is_repository_shallow())
use_bitmap_index = 0;
if (pack_to_stdout || !rev_list_all)