summaryrefslogtreecommitdiff
path: root/builtin/index-pack.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/index-pack.c')
-rw-r--r--builtin/index-pack.c125
1 files changed, 85 insertions, 40 deletions
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 54c7faf6ee..d773809c4c 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -157,11 +157,11 @@ static int input_fd, output_fd;
static const char *curr_pack;
/*
- * local_links is guarded by read_mutex, and record_local_links is read-only in
- * a thread.
+ * outgoing_links is guarded by read_mutex, and record_outgoing_links is
+ * read-only in a thread.
*/
-static struct oidset local_links = OIDSET_INIT;
-static int record_local_links;
+static struct oidset outgoing_links = OIDSET_INIT;
+static int record_outgoing_links;
static struct thread_local_data *thread_data;
static int nr_dispatched;
@@ -814,18 +814,41 @@ static int check_collison(struct object_entry *entry)
return 0;
}
-static void record_if_local_object(const struct object_id *oid)
+static void record_outgoing_link(const struct object_id *oid)
{
- struct object_info info = OBJECT_INFO_INIT;
- if (oid_object_info_extended(the_repository, oid, &info, 0))
- /* Missing; assume it is a promisor object */
- return;
- if (info.whence == OI_PACKED && info.u.packed.pack->pack_promisor)
- return;
- oidset_insert(&local_links, oid);
+ oidset_insert(&outgoing_links, oid);
+}
+
+static void maybe_record_name_entry(const struct name_entry *entry)
+{
+ /*
+ * Checking only trees here results in a significantly faster packfile
+ * indexing, but the drawback is that if the packfile to be indexed
+ * references a local blob only directly (that is, never through a
+ * local tree), that local blob is in danger of being garbage
+ * collected. Such a situation may arise if we push local commits,
+ * including one with a change to a blob in the root tree, and then the
+ * server incorporates them into its main branch through a "rebase" or
+ * "squash" merge strategy, and then we fetch the new main branch from
+ * the server.
+ *
+ * This situation has not been observed yet - we have only noticed
+ * missing commits, not missing trees or blobs. (In fact, if it were
+ * believed that only missing commits are problematic, one could argue
+ * that we should also exclude trees during the outgoing link check;
+ * but it is safer to include them.)
+ *
+ * Due to the rarity of the situation (it has not been observed to
+ * happen in real life), and because the "penalty" in such a situation
+ * is merely to refetch the missing blob when it's needed (and this
+ * happens only once - when refetched, the blob goes into a promisor
+ * pack, so it won't be GC-ed, the tradeoff seems worth it.
+ */
+ if (S_ISDIR(entry->mode))
+ record_outgoing_link(&entry->oid);
}
-static void do_record_local_links(struct object *obj)
+static void do_record_outgoing_links(struct object *obj)
{
if (obj->type == OBJ_TREE) {
struct tree *tree = (struct tree *)obj;
@@ -839,16 +862,17 @@ static void do_record_local_links(struct object *obj)
*/
return;
while (tree_entry_gently(&desc, &entry))
- record_if_local_object(&entry.oid);
+ maybe_record_name_entry(&entry);
} else if (obj->type == OBJ_COMMIT) {
struct commit *commit = (struct commit *) obj;
struct commit_list *parents = commit->parents;
+ record_outgoing_link(get_commit_tree_oid(commit));
for (; parents; parents = parents->next)
- record_if_local_object(&parents->item->object.oid);
+ record_outgoing_link(&parents->item->object.oid);
} else if (obj->type == OBJ_TAG) {
struct tag *tag = (struct tag *) obj;
- record_if_local_object(get_tagged_oid(tag));
+ record_outgoing_link(get_tagged_oid(tag));
}
}
@@ -898,7 +922,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
free(has_data);
}
- if (strict || do_fsck_object || record_local_links) {
+ if (strict || do_fsck_object || record_outgoing_links) {
read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(the_repository, oid);
@@ -930,8 +954,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
die(_("fsck error in packed object"));
if (strict && fsck_walk(obj, NULL, &fsck_options))
die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid));
- if (record_local_links)
- do_record_local_links(obj);
+ if (record_outgoing_links)
+ do_record_outgoing_links(obj);
if (obj->type == OBJ_TREE) {
struct tree *item = (struct tree *) obj;
@@ -1293,7 +1317,7 @@ static void parse_pack_objects(unsigned char *hash)
* recursively checking if the resulting object is used as a base
* for some more deltas.
*/
-static void resolve_deltas(void)
+static void resolve_deltas(struct pack_idx_option *opts)
{
int i;
@@ -1309,7 +1333,7 @@ static void resolve_deltas(void)
nr_ref_deltas + nr_ofs_deltas);
nr_dispatched = 0;
- base_cache_limit = delta_base_cache_limit * nr_threads;
+ base_cache_limit = opts->delta_base_cache_limit * nr_threads;
if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) {
init_thread();
work_lock();
@@ -1534,7 +1558,7 @@ static void write_special_file(const char *suffix, const char *msg,
if (pack_name)
filename = derive_filename(pack_name, "pack", suffix, &name_buf);
else
- filename = odb_pack_name(&name_buf, hash, suffix);
+ filename = odb_pack_name(the_repository, &name_buf, hash, suffix);
fd = odb_pack_keep(filename);
if (fd < 0) {
@@ -1562,7 +1586,7 @@ static void rename_tmp_packfile(const char **final_name,
{
if (!*final_name || strcmp(*final_name, curr_name)) {
if (!*final_name)
- *final_name = odb_pack_name(name, hash, ext);
+ *final_name = odb_pack_name(the_repository, name, hash, ext);
if (finalize_object_file(curr_name, *final_name))
die(_("unable to rename temporary '*.%s' file to '%s'"),
ext, *final_name);
@@ -1607,7 +1631,8 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
if (do_fsck_object) {
struct packed_git *p;
- p = add_packed_git(final_index_name, strlen(final_index_name), 0);
+ p = add_packed_git(the_repository, final_index_name,
+ strlen(final_index_name), 0);
if (p)
install_packed_git(the_repository, p);
}
@@ -1658,6 +1683,10 @@ static int git_index_pack_config(const char *k, const char *v,
else
opts->flags &= ~WRITE_REV;
}
+ if (!strcmp(k, "core.deltabasecachelimit")) {
+ opts->delta_base_cache_limit = git_config_ulong(k, v, ctx->kvi);
+ return 0;
+ }
return git_default_config(k, v, ctx, cb);
}
@@ -1705,7 +1734,8 @@ static void read_v2_anomalous_offsets(struct packed_git *p,
static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
{
- struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+ struct packed_git *p = add_packed_git(the_repository, pack_name,
+ strlen(pack_name), 1);
if (!p)
die(_("Cannot open existing pack file '%s'"), pack_name);
@@ -1781,28 +1811,43 @@ static void repack_local_links(void)
struct strbuf line = STRBUF_INIT;
struct oidset_iter iter;
struct object_id *oid;
- char *base_name;
+ char *base_name = NULL;
- if (!oidset_size(&local_links))
+ if (!oidset_size(&outgoing_links))
return;
- base_name = mkpathdup("%s/pack/pack", repo_get_object_directory(the_repository));
+ oidset_iter_init(&outgoing_links, &iter);
+ while ((oid = oidset_iter_next(&iter))) {
+ struct object_info info = OBJECT_INFO_INIT;
+ if (oid_object_info_extended(the_repository, oid, &info, 0))
+ /* Missing; assume it is a promisor object */
+ continue;
+ if (info.whence == OI_PACKED && info.u.packed.pack->pack_promisor)
+ continue;
- strvec_push(&cmd.args, "pack-objects");
- strvec_push(&cmd.args, "--exclude-promisor-objects-best-effort");
- strvec_push(&cmd.args, base_name);
- cmd.git_cmd = 1;
- cmd.in = -1;
- cmd.out = -1;
- if (start_command(&cmd))
- die(_("could not start pack-objects to repack local links"));
+ if (!cmd.args.nr) {
+ base_name = mkpathdup(
+ "%s/pack/pack",
+ repo_get_object_directory(the_repository));
+ strvec_push(&cmd.args, "pack-objects");
+ strvec_push(&cmd.args,
+ "--exclude-promisor-objects-best-effort");
+ strvec_push(&cmd.args, base_name);
+ cmd.git_cmd = 1;
+ cmd.in = -1;
+ cmd.out = -1;
+ if (start_command(&cmd))
+ die(_("could not start pack-objects to repack local links"));
+ }
- oidset_iter_init(&local_links, &iter);
- while ((oid = oidset_iter_next(&iter))) {
if (write_in_full(cmd.in, oid_to_hex(oid), the_hash_algo->hexsz) < 0 ||
write_in_full(cmd.in, "\n", 1) < 0)
die(_("failed to feed local object to pack-objects"));
}
+
+ if (!cmd.args.nr)
+ return;
+
close(cmd.in);
out = xfdopen(cmd.out, "r");
@@ -1901,7 +1946,7 @@ int cmd_index_pack(int argc,
} else if (skip_to_optional_arg(arg, "--keep", &keep_msg)) {
; /* nothing to do */
} else if (skip_to_optional_arg(arg, "--promisor", &promisor_msg)) {
- record_local_links = 1;
+ record_outgoing_links = 1;
} else if (starts_with(arg, "--threads=")) {
char *end;
nr_threads = strtoul(arg+10, &end, 0);
@@ -2037,7 +2082,7 @@ int cmd_index_pack(int argc,
parse_pack_objects(pack_hash);
if (report_end_of_input)
write_in_full(2, "\0", 1);
- resolve_deltas();
+ resolve_deltas(&opts);
conclude_pack(fix_thin_pack, curr_pack, pack_hash);
free(ofs_deltas);
free(ref_deltas);
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-06 15:45:21 +0000