summaryrefslogtreecommitdiff
path: root/builtin/pack-objects.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/pack-objects.c')
-rw-r--r--builtin/pack-objects.c386
1 files changed, 307 insertions, 79 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 4a63398960..16517f2637 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -23,6 +23,7 @@
#include "reachable.h"
#include "sha1-array.h"
#include "argv-array.h"
+#include "mru.h"
static const char *pack_usage[] = {
N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"),
@@ -60,14 +61,13 @@ static int delta_search_threads;
static int pack_to_stdout;
static int num_preferred_base;
static struct progress *progress_state;
-static int pack_compression_level = Z_DEFAULT_COMPRESSION;
-static int pack_compression_seen;
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;
@@ -718,7 +718,7 @@ static off_t write_reused_pack(struct sha1file *f)
if (!is_pack_valid(reuse_packfile))
die("packfile is invalid: %s", reuse_packfile->pack_name);
- fd = git_open_noatime(reuse_packfile->pack_name);
+ fd = git_open(reuse_packfile->pack_name);
if (fd < 0)
die_errno("unable to open packfile for reuse: %s",
reuse_packfile->pack_name);
@@ -894,24 +894,15 @@ static void write_pack_file(void)
written, nr_result);
}
-static void setup_delta_attr_check(struct git_attr_check *check)
-{
- static struct git_attr *attr_delta;
-
- if (!attr_delta)
- attr_delta = git_attr("delta");
-
- check[0].attr = attr_delta;
-}
-
static int no_try_delta(const char *path)
{
- struct git_attr_check check[1];
+ static struct attr_check *check;
- setup_delta_attr_check(check);
- if (git_check_attr(path, ARRAY_SIZE(check), check))
+ if (!check)
+ check = attr_check_initl("delta", NULL);
+ if (git_check_attr(path, check))
return 0;
- if (ATTR_FALSE(check->value))
+ if (ATTR_FALSE(check->items[0].value))
return 1;
return 0;
}
@@ -945,29 +936,80 @@ 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,
struct packed_git **found_pack,
off_t *found_offset)
{
- struct packed_git *p;
+ struct mru_entry *entry;
+ 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 (entry = packed_git_mru->head; entry; entry = entry->next) {
+ struct packed_git *p = entry->item;
+ off_t offset;
+
+ if (p == *found_pack)
+ offset = *found_offset;
+ else
+ offset = find_pack_entry_one(sha1, p);
- for (p = packed_git; p; p = p->next) {
- off_t offset = find_pack_entry_one(sha1, p);
if (offset) {
if (!*found_pack) {
if (!is_pack_valid(p))
@@ -975,31 +1017,11 @@ 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 (!exclude && want > 0)
+ mru_mark(packed_git_mru, entry);
+ if (want != -1)
+ return want;
}
}
@@ -1040,8 +1062,8 @@ 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 +1096,9 @@ 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);
@@ -1495,6 +1520,170 @@ static int pack_offset_sort(const void *_a, const void *_b)
(a->in_pack_offset > b->in_pack_offset);
}
+/*
+ * Drop an on-disk delta we were planning to reuse. Naively, this would
+ * just involve blanking out the "delta" field, but we have to deal
+ * with some extra book-keeping:
+ *
+ * 1. Removing ourselves from the delta_sibling linked list.
+ *
+ * 2. Updating our size/type to the non-delta representation. These were
+ * either not recorded initially (size) or overwritten with the delta type
+ * (type) when check_object() decided to reuse the delta.
+ *
+ * 3. Resetting our delta depth, as we are now a base object.
+ */
+static void drop_reused_delta(struct object_entry *entry)
+{
+ struct object_entry **p = &entry->delta->delta_child;
+ struct object_info oi = OBJECT_INFO_INIT;
+
+ while (*p) {
+ if (*p == entry)
+ *p = (*p)->delta_sibling;
+ else
+ p = &(*p)->delta_sibling;
+ }
+ entry->delta = NULL;
+ entry->depth = 0;
+
+ oi.sizep = &entry->size;
+ oi.typep = &entry->type;
+ if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) {
+ /*
+ * We failed to get the info from this pack for some reason;
+ * fall back to sha1_object_info, which may find another copy.
+ * And if that fails, the error will be recorded in entry->type
+ * and dealt with in prepare_pack().
+ */
+ entry->type = sha1_object_info(entry->idx.sha1, &entry->size);
+ }
+}
+
+/*
+ * Follow the chain of deltas from this entry onward, throwing away any links
+ * that cause us to hit a cycle (as determined by the DFS state flags in
+ * the entries).
+ *
+ * We also detect too-long reused chains that would violate our --depth
+ * limit.
+ */
+static void break_delta_chains(struct object_entry *entry)
+{
+ /*
+ * The actual depth of each object we will write is stored as an int,
+ * as it cannot exceed our int "depth" limit. But before we break
+ * changes based no that limit, we may potentially go as deep as the
+ * number of objects, which is elsewhere bounded to a uint32_t.
+ */
+ uint32_t total_depth;
+ struct object_entry *cur, *next;
+
+ for (cur = entry, total_depth = 0;
+ cur;
+ cur = cur->delta, total_depth++) {
+ if (cur->dfs_state == DFS_DONE) {
+ /*
+ * We've already seen this object and know it isn't
+ * part of a cycle. We do need to append its depth
+ * to our count.
+ */
+ total_depth += cur->depth;
+ break;
+ }
+
+ /*
+ * We break cycles before looping, so an ACTIVE state (or any
+ * other cruft which made its way into the state variable)
+ * is a bug.
+ */
+ if (cur->dfs_state != DFS_NONE)
+ die("BUG: confusing delta dfs state in first pass: %d",
+ cur->dfs_state);
+
+ /*
+ * Now we know this is the first time we've seen the object. If
+ * it's not a delta, we're done traversing, but we'll mark it
+ * done to save time on future traversals.
+ */
+ if (!cur->delta) {
+ cur->dfs_state = DFS_DONE;
+ break;
+ }
+
+ /*
+ * Mark ourselves as active and see if the next step causes
+ * us to cycle to another active object. It's important to do
+ * this _before_ we loop, because it impacts where we make the
+ * cut, and thus how our total_depth counter works.
+ * E.g., We may see a partial loop like:
+ *
+ * A -> B -> C -> D -> B
+ *
+ * Cutting B->C breaks the cycle. But now the depth of A is
+ * only 1, and our total_depth counter is at 3. The size of the
+ * error is always one less than the size of the cycle we
+ * broke. Commits C and D were "lost" from A's chain.
+ *
+ * If we instead cut D->B, then the depth of A is correct at 3.
+ * We keep all commits in the chain that we examined.
+ */
+ cur->dfs_state = DFS_ACTIVE;
+ if (cur->delta->dfs_state == DFS_ACTIVE) {
+ drop_reused_delta(cur);
+ cur->dfs_state = DFS_DONE;
+ break;
+ }
+ }
+
+ /*
+ * And now that we've gone all the way to the bottom of the chain, we
+ * need to clear the active flags and set the depth fields as
+ * appropriate. Unlike the loop above, which can quit when it drops a
+ * delta, we need to keep going to look for more depth cuts. So we need
+ * an extra "next" pointer to keep going after we reset cur->delta.
+ */
+ for (cur = entry; cur; cur = next) {
+ next = cur->delta;
+
+ /*
+ * We should have a chain of zero or more ACTIVE states down to
+ * a final DONE. We can quit after the DONE, because either it
+ * has no bases, or we've already handled them in a previous
+ * call.
+ */
+ if (cur->dfs_state == DFS_DONE)
+ break;
+ else if (cur->dfs_state != DFS_ACTIVE)
+ die("BUG: confusing delta dfs state in second pass: %d",
+ cur->dfs_state);
+
+ /*
+ * If the total_depth is more than depth, then we need to snip
+ * the chain into two or more smaller chains that don't exceed
+ * the maximum depth. Most of the resulting chains will contain
+ * (depth + 1) entries (i.e., depth deltas plus one base), and
+ * the last chain (i.e., the one containing entry) will contain
+ * whatever entries are left over, namely
+ * (total_depth % (depth + 1)) of them.
+ *
+ * Since we are iterating towards decreasing depth, we need to
+ * decrement total_depth as we go, and we need to write to the
+ * entry what its final depth will be after all of the
+ * snipping. Since we're snipping into chains of length (depth
+ * + 1) entries, the final depth of an entry will be its
+ * original depth modulo (depth + 1). Any time we encounter an
+ * entry whose final depth is supposed to be zero, we snip it
+ * from its delta base, thereby making it so.
+ */
+ cur->depth = (total_depth--) % (depth + 1);
+ if (!cur->depth)
+ drop_reused_delta(cur);
+
+ cur->dfs_state = DFS_DONE;
+ }
+}
+
static void get_object_details(void)
{
uint32_t i;
@@ -1503,7 +1692,7 @@ static void get_object_details(void)
sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *));
for (i = 0; i < to_pack.nr_objects; i++)
sorted_by_offset[i] = to_pack.objects + i;
- qsort(sorted_by_offset, to_pack.nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
+ QSORT(sorted_by_offset, to_pack.nr_objects, pack_offset_sort);
for (i = 0; i < to_pack.nr_objects; i++) {
struct object_entry *entry = sorted_by_offset[i];
@@ -1512,6 +1701,13 @@ static void get_object_details(void)
entry->no_try_delta = 1;
}
+ /*
+ * This must happen in a second pass, since we rely on the delta
+ * information for the whole list being completed.
+ */
+ for (i = 0; i < to_pack.nr_objects; i++)
+ break_delta_chains(&to_pack.objects[i]);
+
free(sorted_by_offset);
}
@@ -2123,6 +2319,35 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size,
#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p)
#endif
+static void add_tag_chain(const struct object_id *oid)
+{
+ struct tag *tag;
+
+ /*
+ * We catch duplicates already in add_object_entry(), but we'd
+ * prefer to do this extra check to avoid having to parse the
+ * tag at all if we already know that it's being packed (e.g., if
+ * it was included via bitmaps, we would not have parsed it
+ * previously).
+ */
+ if (packlist_find(&to_pack, oid->hash, NULL))
+ return;
+
+ tag = lookup_tag(oid->hash);
+ while (1) {
+ if (!tag || parse_tag(tag) || !tag->tagged)
+ die("unable to pack objects reachable from tag %s",
+ oid_to_hex(oid));
+
+ add_object_entry(tag->object.oid.hash, OBJ_TAG, NULL, 0);
+
+ if (tag->tagged->type != OBJ_TAG)
+ return;
+
+ tag = (struct tag *)tag->tagged;
+ }
+}
+
static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data)
{
struct object_id peeled;
@@ -2130,7 +2355,7 @@ static int add_ref_tag(const char *path, const struct object_id *oid, int flag,
if (starts_with(path, "refs/tags/") && /* is a tag? */
!peel_ref(path, peeled.hash) && /* peelable? */
packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */
- add_object_entry(oid->hash, OBJ_TAG, NULL, 0);
+ add_tag_chain(oid);
return 0;
}
@@ -2196,7 +2421,7 @@ static void prepare_pack(int window, int depth)
if (progress)
progress_state = start_progress(_("Compressing objects"),
nr_deltas);
- qsort(delta_list, n, sizeof(*delta_list), type_size_sort);
+ QSORT(delta_list, n, type_size_sort);
ll_find_deltas(delta_list, n, window+1, depth, &nr_done);
stop_progress(&progress_state);
if (nr_done != nr_deltas)
@@ -2219,16 +2444,6 @@ static int git_pack_config(const char *k, const char *v, void *cb)
depth = git_config_int(k, v);
return 0;
}
- if (!strcmp(k, "pack.compression")) {
- int level = git_config_int(k, v);
- if (level == -1)
- level = Z_DEFAULT_COMPRESSION;
- else if (level < 0 || level > Z_BEST_COMPRESSION)
- die("bad pack compression level %d", level);
- pack_compression_level = level;
- pack_compression_seen = 1;
- return 0;
- }
if (!strcmp(k, "pack.deltacachesize")) {
max_delta_cache_size = git_config_int(k, v);
return 0;
@@ -2244,7 +2459,7 @@ 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")) {
@@ -2388,8 +2603,7 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs)
}
if (in_pack.nr) {
- qsort(in_pack.array, in_pack.nr, sizeof(in_pack.array[0]),
- ofscmp);
+ QSORT(in_pack.array, in_pack.nr, ofscmp);
for (i = 0; i < in_pack.nr; i++) {
struct object *o = in_pack.array[i].object;
add_object_entry(o->oid.hash, o->type, "", 0);
@@ -2398,17 +2612,17 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs)
free(in_pack.array);
}
-static int add_loose_object(const unsigned char *sha1, const char *path,
+static int add_loose_object(const struct object_id *oid, const char *path,
void *data)
{
- enum object_type type = sha1_object_info(sha1, NULL);
+ enum object_type type = sha1_object_info(oid->hash, NULL);
if (type < 0) {
warning("loose object at %s could not be examined", path);
return 0;
}
- add_object_entry(sha1, type, "", 0);
+ add_object_entry(oid->hash, type, "", 0);
return 0;
}
@@ -2493,13 +2707,13 @@ 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)
@@ -2721,8 +2935,6 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
- if (!pack_compression_seen && core_compression_seen)
- pack_compression_level = core_compression_level;
progress = isatty(2);
argc = parse_options(argc, argv, prefix, pack_objects_options,
@@ -2792,7 +3004,23 @@ 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)
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-30 15:18:53 +0000