#include "list.h"
#include "packfile.h"
#include "object-store.h"
+#include "dir.h"
#define IN_PACK(obj) oe_in_pack(&to_pack, obj)
#define SIZE(obj) oe_size(&to_pack, obj)
#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size)
+#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj)
#define DELTA(obj) oe_delta(&to_pack, obj)
#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj)
#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj)
#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val)
+#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val)
#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val)
#define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val)
static struct packing_data to_pack;
static struct pack_idx_entry **written_list;
-static uint32_t nr_result, nr_written;
+static uint32_t nr_result, nr_written, nr_seen;
static int non_empty;
static int reuse_delta = 1, reuse_object = 1;
static int local;
static int have_non_local_packs;
static int incremental;
-static int ignore_packed_keep;
+static int ignore_packed_keep_on_disk;
+static int ignore_packed_keep_in_core;
static int allow_ofs_delta;
static struct pack_idx_option pack_idx_opts;
static const char *base_name;
static int exclude_promisor_objects;
static unsigned long delta_cache_size = 0;
-static unsigned long max_delta_cache_size = 256 * 1024 * 1024;
+static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
static unsigned long cache_max_small_delta_size = 1000;
static unsigned long window_memory_limit = 0;
oid_to_hex(&DELTA(entry)->idx.oid));
delta_buf = diff_delta(base_buf, base_size,
buf, size, &delta_size, 0);
- if (!delta_buf || delta_size != entry->delta_size)
+ if (!delta_buf || delta_size != DELTA_SIZE(entry))
die("delta size changed");
free(buf);
free(base_buf);
enum object_type type;
void *buf;
struct git_istream *st = NULL;
+ const unsigned hashsz = the_hash_algo->rawsz;
if (!usable_delta) {
if (oe_type(entry) == OBJ_BLOB &&
FREE_AND_NULL(entry->delta_data);
entry->z_delta_size = 0;
} else if (entry->delta_data) {
- size = entry->delta_size;
+ size = DELTA_SIZE(entry);
buf = entry->delta_data;
entry->delta_data = NULL;
type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
} else {
buf = get_delta(entry);
- size = entry->delta_size;
+ size = DELTA_SIZE(entry);
type = (allow_ofs_delta && DELTA(entry)->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
- if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
} else if (type == OBJ_REF_DELTA) {
/*
* Deltas with a base reference contain
- * an additional 20 bytes for the base sha1.
+ * additional bytes for the base object ID.
*/
- if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ if (limit && hdrlen + hashsz + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
return 0;
}
hashwrite(f, header, hdrlen);
- hashwrite(f, DELTA(entry)->idx.oid.hash, 20);
- hdrlen += 20;
+ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz);
+ hdrlen += hashsz;
} else {
- if (limit && hdrlen + datalen + 20 >= limit) {
+ if (limit && hdrlen + datalen + hashsz >= limit) {
if (st)
close_istream(st);
free(buf);
unsigned char header[MAX_PACK_OBJECT_HEADER],
dheader[MAX_PACK_OBJECT_HEADER];
unsigned hdrlen;
+ const unsigned hashsz = the_hash_algo->rawsz;
unsigned long entry_size = SIZE(entry);
if (DELTA(entry))
dheader[pos] = ofs & 127;
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
- if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
hdrlen += sizeof(dheader) - pos;
reused_delta++;
} else if (type == OBJ_REF_DELTA) {
- if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ if (limit && hdrlen + hashsz + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
hashwrite(f, header, hdrlen);
- hashwrite(f, DELTA(entry)->idx.oid.hash, 20);
- hdrlen += 20;
+ hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz);
+ hdrlen += hashsz;
reused_delta++;
} else {
- if (limit && hdrlen + datalen + 20 >= limit) {
+ if (limit && hdrlen + datalen + hashsz >= limit) {
unuse_pack(&w_curs);
return 0;
}
die_errno("unable to seek in reused packfile");
if (reuse_packfile_offset < 0)
- reuse_packfile_offset = reuse_packfile->pack_size - 20;
+ reuse_packfile_offset = reuse_packfile->pack_size - the_hash_algo->rawsz;
total = to_write = reuse_packfile_offset - sizeof(struct pack_header);
* If so, rewrite it like in fast-import
*/
if (pack_to_stdout) {
- hashclose(f, oid.hash, CSUM_CLOSE);
+ finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE);
} else if (nr_written == nr_remaining) {
- hashclose(f, oid.hash, CSUM_FSYNC);
+ finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE);
} else {
- int fd = hashclose(f, oid.hash, 0);
+ int fd = finalize_hashfile(f, oid.hash, 0);
fixup_pack_header_footer(fd, oid.hash, pack_tmp_name,
nr_written, oid.hash, offset);
close(fd);
* 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 &&
+ if (!ignore_packed_keep_on_disk &&
+ !ignore_packed_keep_in_core &&
(!local || !have_non_local_packs))
return 1;
if (local && !p->pack_local)
return 0;
- if (ignore_packed_keep && p->pack_local && p->pack_keep)
+ if (p->pack_local &&
+ ((ignore_packed_keep_on_disk && p->pack_keep) ||
+ (ignore_packed_keep_in_core && p->pack_keep_in_core)))
return 0;
/* we don't know yet; keep looking for more packs */
int want;
struct list_head *pos;
- if (!exclude && local && has_loose_object_nonlocal(oid->hash))
+ if (!exclude && local && has_loose_object_nonlocal(oid))
return 0;
/*
off_t found_offset = 0;
uint32_t index_pos;
+ display_progress(progress_state, ++nr_seen);
+
if (have_duplicate_entry(oid, exclude, &index_pos))
return 0;
create_object_entry(oid, type, pack_name_hash(name),
exclude, name && no_try_delta(name),
index_pos, found_pack, found_offset);
-
- display_progress(progress_state, nr_result);
return 1;
}
{
uint32_t index_pos;
+ display_progress(progress_state, ++nr_seen);
+
if (have_duplicate_entry(oid, 0, &index_pos))
return 0;
return 0;
create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset);
-
- display_progress(progress_state, nr_result);
return 1;
}
if (reuse_delta && !entry->preferred_base)
base_ref = use_pack(p, &w_curs,
entry->in_pack_offset + used, NULL);
- entry->in_pack_header_size = used + 20;
+ entry->in_pack_header_size = used + the_hash_algo->rawsz;
break;
case OBJ_OFS_DELTA:
buf = use_pack(p, &w_curs,
oe_set_type(entry, entry->in_pack_type);
SET_SIZE(entry, in_pack_size); /* delta size */
SET_DELTA(entry, base_entry);
- entry->delta_size = in_pack_size;
+ SET_DELTA_SIZE(entry, in_pack_size);
entry->delta_sibling_idx = base_entry->delta_child_idx;
SET_DELTA_CHILD(base_entry, entry);
unuse_pack(&w_curs);
unuse_pack(&w_curs);
}
- oe_set_type(entry, oid_object_info(&entry->idx.oid, &canonical_size));
+ oe_set_type(entry,
+ oid_object_info(the_repository, &entry->idx.oid, &canonical_size));
if (entry->type_valid) {
SET_SIZE(entry, canonical_size);
} else {
oi.sizep = &size;
oi.typep = &type;
- if (packed_object_info(IN_PACK(entry), entry->in_pack_offset, &oi) < 0) {
+ if (packed_object_info(the_repository, IN_PACK(entry), 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 oe_type(entry)
* and dealt with in prepare_pack().
*/
- oe_set_type(entry, oid_object_info(&entry->idx.oid, &size));
+ oe_set_type(entry,
+ oid_object_info(the_repository, &entry->idx.oid, &size));
} else {
oe_set_type(entry, type);
}
* is a bug.
*/
if (cur->dfs_state != DFS_NONE)
- die("BUG: confusing delta dfs state in first pass: %d",
+ BUG("confusing delta dfs state in first pass: %d",
cur->dfs_state);
/*
if (cur->dfs_state == DFS_DONE)
break;
else if (cur->dfs_state != DFS_ACTIVE)
- die("BUG: confusing delta dfs state in second pass: %d",
+ BUG("confusing delta dfs state in second pass: %d",
cur->dfs_state);
/*
uint32_t i;
struct object_entry **sorted_by_offset;
+ if (progress)
+ progress_state = start_progress(_("Counting objects"),
+ to_pack.nr_objects);
+
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;
if (entry->type_valid &&
oe_size_greater_than(&to_pack, entry, big_file_threshold))
entry->no_try_delta = 1;
+ display_progress(progress_state, i + 1);
}
+ stop_progress(&progress_state);
/*
* This must happen in a second pass, since we rely on the delta
if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) {
read_lock();
- if (oid_object_info(&e->idx.oid, &size) < 0)
+ if (oid_object_info(the_repository, &e->idx.oid, &size) < 0)
die(_("unable to get size of %s"),
oid_to_hex(&e->idx.oid));
read_unlock();
/* Now some size filtering heuristics. */
trg_size = SIZE(trg_entry);
if (!DELTA(trg_entry)) {
- max_size = trg_size/2 - 20;
+ max_size = trg_size/2 - the_hash_algo->rawsz;
ref_depth = 1;
} else {
- max_size = trg_entry->delta_size;
+ max_size = DELTA_SIZE(trg_entry);
ref_depth = trg->depth;
}
max_size = (uint64_t)max_size * (max_depth - src->depth) /
delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
if (!delta_buf)
return 0;
+ if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
+ free(delta_buf);
+ return 0;
+ }
if (DELTA(trg_entry)) {
/* Prefer only shallower same-sized deltas. */
- if (delta_size == trg_entry->delta_size &&
+ if (delta_size == DELTA_SIZE(trg_entry) &&
src->depth + 1 >= trg->depth) {
free(delta_buf);
return 0;
free(trg_entry->delta_data);
cache_lock();
if (trg_entry->delta_data) {
- delta_cache_size -= trg_entry->delta_size;
+ delta_cache_size -= DELTA_SIZE(trg_entry);
trg_entry->delta_data = NULL;
}
if (delta_cacheable(src_size, trg_size, delta_size)) {
}
SET_DELTA(trg_entry, src_entry);
- trg_entry->delta_size = delta_size;
+ SET_DELTA_SIZE(trg_entry, delta_size);
trg->depth = src->depth + 1;
return 1;
if (entry->delta_data && !pack_to_stdout) {
unsigned long size;
- size = do_compress(&entry->delta_data, entry->delta_size);
+ size = do_compress(&entry->delta_data, DELTA_SIZE(entry));
if (size < (1U << OE_Z_DELTA_BITS)) {
entry->z_delta_size = size;
cache_lock();
- delta_cache_size -= entry->delta_size;
+ delta_cache_size -= DELTA_SIZE(entry);
delta_cache_size += entry->z_delta_size;
cache_unlock();
} else {
struct object_id oid;
struct object *o;
- if (!p->pack_local || p->pack_keep)
+ if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
continue;
if (open_pack_index(p))
die("cannot open pack index");
static int add_loose_object(const struct object_id *oid, const char *path,
void *data)
{
- enum object_type type = oid_object_info(oid, NULL);
+ enum object_type type = oid_object_info(the_repository, oid, NULL);
if (type < 0) {
warning("loose object at %s could not be examined", path);
get_packed_git(the_repository);
while (p) {
- if ((!p->pack_local || p->pack_keep) &&
+ if ((!p->pack_local || p->pack_keep ||
+ p->pack_keep_in_core) &&
find_pack_entry_one(oid->hash, p)) {
last_found = p;
return 1;
struct object_id oid;
for (p = get_packed_git(the_repository); p; p = p->next) {
- if (!p->pack_local || p->pack_keep)
+ if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
continue;
if (open_pack_index(p))
{
return pack_to_stdout &&
allow_ofs_delta &&
- !ignore_packed_keep &&
+ !ignore_packed_keep_on_disk &&
+ !ignore_packed_keep_in_core &&
(!local || !have_non_local_packs) &&
!incremental;
}
oid_array_clear(&recent_objects);
}
+static void add_extra_kept_packs(const struct string_list *names)
+{
+ struct packed_git *p;
+
+ if (!names->nr)
+ return;
+
+ for (p = get_packed_git(the_repository); p; p = p->next) {
+ const char *name = basename(p->pack_name);
+ int i;
+
+ if (!p->pack_local)
+ continue;
+
+ for (i = 0; i < names->nr; i++)
+ if (!fspathcmp(name, names->items[i].string))
+ break;
+
+ if (i < names->nr) {
+ p->pack_keep_in_core = 1;
+ ignore_packed_keep_in_core = 1;
+ continue;
+ }
+ }
+}
+
static int option_parse_index_version(const struct option *opt,
const char *arg, int unset)
{
struct argv_array rp = ARGV_ARRAY_INIT;
int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
int rev_list_index = 0;
+ struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
struct option pack_objects_options[] = {
OPT_SET_INT('q', "quiet", &progress,
N_("do not show progress meter"), 0),
N_("do not create an empty pack output")),
OPT_BOOL(0, "revs", &use_internal_rev_list,
N_("read revision arguments from standard input")),
- { OPTION_SET_INT, 0, "unpacked", &rev_list_unpacked, NULL,
- N_("limit the objects to those that are not yet packed"),
- PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
- { OPTION_SET_INT, 0, "all", &rev_list_all, NULL,
- N_("include objects reachable from any reference"),
- PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
- { OPTION_SET_INT, 0, "reflog", &rev_list_reflog, NULL,
- N_("include objects referred by reflog entries"),
- PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
- { OPTION_SET_INT, 0, "indexed-objects", &rev_list_index, NULL,
- N_("include objects referred to by the index"),
- PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
+ OPT_SET_INT_F(0, "unpacked", &rev_list_unpacked,
+ N_("limit the objects to those that are not yet packed"),
+ 1, PARSE_OPT_NONEG),
+ OPT_SET_INT_F(0, "all", &rev_list_all,
+ N_("include objects reachable from any reference"),
+ 1, PARSE_OPT_NONEG),
+ OPT_SET_INT_F(0, "reflog", &rev_list_reflog,
+ N_("include objects referred by reflog entries"),
+ 1, PARSE_OPT_NONEG),
+ OPT_SET_INT_F(0, "indexed-objects", &rev_list_index,
+ N_("include objects referred to by the index"),
+ 1, PARSE_OPT_NONEG),
OPT_BOOL(0, "stdout", &pack_to_stdout,
N_("output pack to stdout")),
OPT_BOOL(0, "include-tag", &include_tag,
N_("create thin packs")),
OPT_BOOL(0, "shallow", &shallow,
N_("create packs suitable for shallow fetches")),
- OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep,
+ OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk,
N_("ignore packs that have companion .keep file")),
+ OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"),
+ N_("ignore this pack")),
OPT_INTEGER(0, "compression", &pack_compression_level,
N_("pack compression level")),
OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents,
fetch_if_missing = 0;
argv_array_push(&rp, "--exclude-promisor-objects");
}
+ if (unpack_unreachable || keep_unreachable || pack_loose_unreachable)
+ use_internal_rev_list = 1;
if (!reuse_object)
reuse_delta = 0;
if (progress && all_progress_implied)
progress = 2;
- if (ignore_packed_keep) {
+ add_extra_kept_packs(&keep_pack_list);
+ if (ignore_packed_keep_on_disk) {
struct packed_git *p;
for (p = get_packed_git(the_repository); p; p = p->next)
if (p->pack_local && p->pack_keep)
break;
if (!p) /* no keep-able packs found */
- ignore_packed_keep = 0;
+ ignore_packed_keep_on_disk = 0;
}
if (local) {
/*
- * unlike ignore_packed_keep above, we do not want to
- * unset "local" based on looking at packs, as it
- * also covers non-local objects
+ * unlike ignore_packed_keep_on_disk above, we do not
+ * want to unset "local" based on looking at packs, as
+ * it also covers non-local objects
*/
struct packed_git *p;
for (p = get_packed_git(the_repository); p; p = p->next) {
prepare_packing_data(&to_pack);
if (progress)
- progress_state = start_progress(_("Counting objects"), 0);
+ progress_state = start_progress(_("Enumerating objects"), 0);
if (!use_internal_rev_list)
read_object_list_from_stdin();
else {