#include "diff.h"
#include "revision.h"
#include "list-objects.h"
+#include "progress.h"
static const char pack_usage[] = "\
git-pack-objects [{ -q | --progress | --all-progress }] \n\
[--local] [--incremental] [--window=N] [--depth=N] \n\
- [--no-reuse-delta] [--delta-base-offset] [--non-empty] \n\
- [--revs [--unpacked | --all]*] [--reflog] [--stdout | base-name] \n\
- [<ref-list | <object-list]";
+ [--no-reuse-delta] [--no-reuse-object] [--delta-base-offset] \n\
+ [--non-empty] [--revs [--unpacked | --all]*] [--reflog] \n\
+ [--stdout | base-name] [<ref-list | <object-list]";
struct object_entry {
unsigned char sha1[20];
* expanded). nr_objects & nr_alloc controls this array. They are stored
* in the order we see -- typically rev-list --objects order that gives us
* nice "minimum seek" order.
- *
- * sorted-by-sha ans sorted-by-type are arrays of pointers that point at
- * elements in the objects array. The former is used to build the pack
- * index (lists object names in the ascending order to help offset lookup),
- * and the latter is used to group similar things together by try_delta()
- * heuristics.
*/
+static struct object_entry *objects;
+static uint32_t nr_objects, nr_alloc, nr_result;
static int non_empty;
-static int no_reuse_delta;
+static int no_reuse_delta, no_reuse_object;
static int local;
static int incremental;
static int allow_ofs_delta;
-
-static struct object_entry *objects;
-static uint32_t nr_objects, nr_alloc, nr_result;
static const char *pack_tmp_name, *idx_tmp_name;
static char tmpname[PATH_MAX];
static unsigned char pack_file_sha1[20];
static int progress = 1;
-static volatile sig_atomic_t progress_update;
static int window = 10;
+static int depth = 50;
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;
/*
* The object names in objects array are hashed with this hashtable,
- * to help looking up the entry by object name. Binary search from
- * sorted_by_sha is also possible but this was easier to code and faster.
+ * to help looking up the entry by object name.
* This hashtable is built after all the objects are seen.
*/
static int *object_ix;
}
}
-static int check_loose_inflate(unsigned char *data, unsigned long len, unsigned long expect)
-{
- z_stream stream;
- unsigned char fakebuf[4096];
- int st;
-
- memset(&stream, 0, sizeof(stream));
- stream.next_in = data;
- stream.avail_in = len;
- stream.next_out = fakebuf;
- stream.avail_out = sizeof(fakebuf);
- inflateInit(&stream);
-
- while (1) {
- st = inflate(&stream, Z_FINISH);
- if (st == Z_STREAM_END || st == Z_OK) {
- st = (stream.total_out == expect &&
- stream.total_in == len) ? 0 : -1;
- break;
- }
- if (st != Z_BUF_ERROR) {
- st = -1;
- break;
- }
- stream.next_out = fakebuf;
- stream.avail_out = sizeof(fakebuf);
- }
- inflateEnd(&stream);
- return st;
-}
-
-static int revalidate_loose_object(struct object_entry *entry,
- unsigned char *map,
- unsigned long mapsize)
-{
- /* we already know this is a loose object with new type header. */
- enum object_type type;
- unsigned long size, used;
-
- if (pack_to_stdout)
- return 0;
-
- used = unpack_object_header_gently(map, mapsize, &type, &size);
- if (!used)
- return -1;
- map += used;
- mapsize -= used;
- return check_loose_inflate(map, mapsize, size);
-}
-
static unsigned long write_object(struct sha1file *f,
struct object_entry *entry)
{
crc32_begin(f);
obj_type = entry->type;
- if (! entry->in_pack)
+ if (no_reuse_object)
+ to_reuse = 0; /* explicit */
+ else if (!entry->in_pack)
to_reuse = 0; /* can't reuse what we don't have */
else if (obj_type == OBJ_REF_DELTA || obj_type == OBJ_OFS_DELTA)
to_reuse = 1; /* check_object() decided it for us */
* and we do not need to deltify it.
*/
- if (!entry->in_pack && !entry->delta) {
- unsigned char *map;
- unsigned long mapsize;
- map = map_sha1_file(entry->sha1, &mapsize);
- if (map && !legacy_loose_object(map)) {
- /* We can copy straight into the pack file */
- if (revalidate_loose_object(entry, map, mapsize))
- die("corrupt loose object %s",
- sha1_to_hex(entry->sha1));
- sha1write(f, map, mapsize);
- munmap(map, mapsize);
- written++;
- reused++;
- return mapsize;
- }
- if (map)
- munmap(map, mapsize);
- }
-
if (!to_reuse) {
buf = read_sha1_file(entry->sha1, &type, &size);
if (!buf)
sha1write(f, entry->delta->sha1, 20);
hdrlen += 20;
}
- datalen = sha1write_compressed(f, buf, size);
+ datalen = sha1write_compressed(f, buf, size, pack_compression_level);
free(buf);
}
else {
return offset + size;
}
+static int open_object_dir_tmp(const char *path)
+{
+ snprintf(tmpname, sizeof(tmpname), "%s/%s", get_object_directory(), path);
+ return mkstemp(tmpname);
+}
+
static off_t write_pack_file(void)
{
uint32_t i;
struct sha1file *f;
off_t offset, last_obj_offset = 0;
struct pack_header hdr;
- unsigned last_percent = 999;
int do_progress = progress;
if (pack_to_stdout) {
f = sha1fd(1, "<stdout>");
do_progress >>= 1;
} else {
- int fd;
- snprintf(tmpname, sizeof(tmpname), "tmp_pack_XXXXXX");
- fd = mkstemp(tmpname);
+ int fd = open_object_dir_tmp("tmp_pack_XXXXXX");
if (fd < 0)
die("unable to create %s: %s\n", tmpname, strerror(errno));
pack_tmp_name = xstrdup(tmpname);
}
if (do_progress)
- fprintf(stderr, "Writing %u objects.\n", nr_result);
+ start_progress(&progress_state, "Writing %u objects...", "", nr_result);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(PACK_VERSION);
for (i = 0; i < nr_objects; i++) {
last_obj_offset = offset;
offset = write_one(f, objects + i, offset);
- if (do_progress) {
- unsigned percent = written * 100 / nr_result;
- if (progress_update || percent != last_percent) {
- fprintf(stderr, "%4u%% (%u/%u) done\r",
- percent, written, nr_result);
- progress_update = 0;
- last_percent = percent;
- }
- }
+ if (do_progress)
+ display_progress(&progress_state, written);
}
if (do_progress)
- fputc('\n', stderr);
+ stop_progress(&progress_state);
done:
if (written != nr_result)
die("wrote %u objects while expecting %u", written, nr_result);
uint32_t array[256];
uint32_t i, index_version;
SHA_CTX ctx;
- int fd;
- snprintf(tmpname, sizeof(tmpname), "tmp_idx_XXXXXX");
- fd = mkstemp(tmpname);
+ int fd = open_object_dir_tmp("tmp_idx_XXXXXX");
if (fd < 0)
die("unable to create %s: %s\n", tmpname, strerror(errno));
idx_tmp_name = xstrdup(tmpname);
return hash;
}
-static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude)
+static int add_object_entry(const unsigned char *sha1, enum object_type type,
+ unsigned hash, int exclude)
{
struct object_entry *entry;
struct packed_git *p, *found_pack = NULL;
return 0;
}
- if (!exclude) {
- for (p = packed_git; p; p = p->next) {
- off_t offset = find_pack_entry_one(sha1, p);
- if (offset) {
- if (incremental)
- return 0;
- if (local && !p->pack_local)
- return 0;
- if (!found_pack) {
- found_offset = offset;
- found_pack = p;
- }
+ for (p = packed_git; p; p = p->next) {
+ off_t offset = find_pack_entry_one(sha1, p);
+ if (offset) {
+ if (!found_pack) {
+ found_offset = offset;
+ found_pack = p;
}
+ if (exclude)
+ break;
+ if (incremental)
+ return 0;
+ if (local && !p->pack_local)
+ return 0;
}
}
memset(entry, 0, sizeof(*entry));
hashcpy(entry->sha1, sha1);
entry->hash = hash;
+ if (type)
+ entry->type = type;
if (exclude)
entry->preferred_base = 1;
else
else
object_ix[-1 - ix] = nr_objects;
- if (progress_update) {
- fprintf(stderr, "Counting objects...%u\r", nr_objects);
- progress_update = 0;
- }
+ if (progress)
+ display_progress(&progress_state, nr_objects);
return 1;
}
return;
if (name[cmplen] != '/') {
unsigned hash = name_hash(fullname);
- add_object_entry(entry.sha1, hash, 1);
+ add_object_entry(entry.sha1,
+ S_ISDIR(entry.mode) ? OBJ_TREE : OBJ_BLOB,
+ hash, 1);
return;
}
if (S_ISDIR(entry.mode)) {
cmplen = name_cmp_len(name);
for (it = pbase_tree; it; it = it->next) {
if (cmplen == 0) {
- add_object_entry(it->pcache.sha1, 0, 1);
+ add_object_entry(it->pcache.sha1, OBJ_TREE, 0, 1);
}
else {
struct tree_desc tree;
static void check_object(struct object_entry *entry)
{
- if (entry->in_pack && !entry->preferred_base) {
+ if (entry->in_pack) {
struct packed_git *p = entry->in_pack;
struct pack_window *w_curs = NULL;
- unsigned long size, used;
+ const unsigned char *base_ref = NULL;
+ struct object_entry *base_entry;
+ unsigned long used, used_0;
unsigned int avail;
- unsigned char *buf;
- struct object_entry *base_entry = NULL;
+ off_t ofs;
+ unsigned char *buf, c;
buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail);
- /* We want in_pack_type even if we do not reuse delta.
- * There is no point not reusing non-delta representations.
+ /*
+ * We want in_pack_type even if we do not reuse delta
+ * since non-delta representations could still be reused.
*/
used = unpack_object_header_gently(buf, avail,
- &entry->in_pack_type, &size);
+ &entry->in_pack_type,
+ &entry->size);
- /* Check if it is delta, and the base is also an object
- * we are going to pack. If so we will reuse the existing
- * delta.
+ /*
+ * Determine if this is a delta and if so whether we can
+ * reuse it or not. Otherwise let's find out as cheaply as
+ * possible what the actual type and size for this object is.
*/
- if (!no_reuse_delta) {
- unsigned char c;
- const unsigned char *base_name;
- off_t ofs;
- unsigned long used_0;
- /* there is at least 20 bytes left in the pack */
- switch (entry->in_pack_type) {
- case OBJ_REF_DELTA:
- base_name = use_pack(p, &w_curs,
- entry->in_pack_offset + used, NULL);
- used += 20;
- break;
- case OBJ_OFS_DELTA:
- buf = use_pack(p, &w_curs,
- entry->in_pack_offset + used, NULL);
- used_0 = 0;
- c = buf[used_0++];
- ofs = c & 127;
- while (c & 128) {
- ofs += 1;
- if (!ofs || MSB(ofs, 7))
- die("delta base offset overflow in pack for %s",
- sha1_to_hex(entry->sha1));
- c = buf[used_0++];
- ofs = (ofs << 7) + (c & 127);
- }
- if (ofs >= entry->in_pack_offset)
- die("delta base offset out of bound for %s",
+ switch (entry->in_pack_type) {
+ default:
+ /* Not a delta hence we've already got all we need. */
+ entry->type = entry->in_pack_type;
+ entry->in_pack_header_size = used;
+ unuse_pack(&w_curs);
+ return;
+ case OBJ_REF_DELTA:
+ if (!no_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;
+ break;
+ case OBJ_OFS_DELTA:
+ buf = use_pack(p, &w_curs,
+ entry->in_pack_offset + used, NULL);
+ used_0 = 0;
+ c = buf[used_0++];
+ ofs = c & 127;
+ while (c & 128) {
+ ofs += 1;
+ if (!ofs || MSB(ofs, 7))
+ die("delta base offset overflow in pack for %s",
sha1_to_hex(entry->sha1));
- ofs = entry->in_pack_offset - ofs;
- base_name = find_packed_object_name(p, ofs);
- used += used_0;
- break;
- default:
- base_name = NULL;
+ c = buf[used_0++];
+ ofs = (ofs << 7) + (c & 127);
}
- if (base_name)
- base_entry = locate_object_entry(base_name);
+ if (ofs >= entry->in_pack_offset)
+ die("delta base offset out of bound for %s",
+ sha1_to_hex(entry->sha1));
+ ofs = entry->in_pack_offset - ofs;
+ if (!no_reuse_delta && !entry->preferred_base)
+ base_ref = find_packed_object_name(p, ofs);
+ entry->in_pack_header_size = used + used_0;
+ break;
}
- unuse_pack(&w_curs);
- entry->in_pack_header_size = used;
- if (base_entry) {
-
- /* Depth value does not matter - find_deltas()
- * will never consider reused delta as the
- * base object to deltify other objects
- * against, in order to avoid circular deltas.
+ if (base_ref && (base_entry = locate_object_entry(base_ref))) {
+ /*
+ * If base_ref was set above that means we wish to
+ * reuse delta data, and we even found that base
+ * in the list of objects we want to pack. Goodie!
+ *
+ * Depth value does not matter - find_deltas() will
+ * never consider reused delta as the base object to
+ * deltify other objects against, in order to avoid
+ * circular deltas.
*/
-
- /* uncompressed size of the delta data */
- entry->size = size;
- entry->delta = base_entry;
entry->type = entry->in_pack_type;
-
+ entry->delta = base_entry;
entry->delta_sibling = base_entry->delta_child;
base_entry->delta_child = entry;
+ unuse_pack(&w_curs);
+ return;
+ }
+ if (entry->type) {
+ /*
+ * This must be a delta and we already know what the
+ * final object type is. Let's extract the actual
+ * object size from the delta header.
+ */
+ entry->size = get_size_from_delta(p, &w_curs,
+ entry->in_pack_offset + entry->in_pack_header_size);
+ unuse_pack(&w_curs);
return;
}
- /* Otherwise we would do the usual */
+
+ /*
+ * No choice but to fall back to the recursive delta walk
+ * with sha1_object_info() to find about the object type
+ * at this point...
+ */
+ unuse_pack(&w_curs);
}
entry->type = sha1_object_info(entry->sha1, &entry->size);
sha1_to_hex(entry->sha1));
}
+static int pack_offset_sort(const void *_a, const void *_b)
+{
+ const struct object_entry *a = *(struct object_entry **)_a;
+ const struct object_entry *b = *(struct object_entry **)_b;
+
+ /* avoid filesystem trashing with loose objects */
+ if (!a->in_pack && !b->in_pack)
+ return hashcmp(a->sha1, b->sha1);
+
+ if (a->in_pack < b->in_pack)
+ return -1;
+ if (a->in_pack > b->in_pack)
+ return 1;
+ return a->in_pack_offset < b->in_pack_offset ? -1 :
+ (a->in_pack_offset > b->in_pack_offset);
+}
+
static void get_object_details(void)
{
uint32_t i;
- struct object_entry *entry;
+ struct object_entry **sorted_by_offset;
+
+ sorted_by_offset = xcalloc(nr_objects, sizeof(struct object_entry *));
+ for (i = 0; i < nr_objects; i++)
+ sorted_by_offset[i] = objects + i;
+ qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
prepare_pack_ix();
- for (i = 0, entry = objects; i < nr_objects; i++, entry++)
- check_object(entry);
+ for (i = 0; i < nr_objects; i++)
+ check_object(sorted_by_offset[i]);
+ free(sorted_by_offset);
}
static int type_size_sort(const void *_a, const void *_b)
uint32_t i = nr_objects, idx = 0, processed = 0;
unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array;
- unsigned last_percent = 999;
int max_depth;
if (!nr_objects)
array = xmalloc(array_size);
memset(array, 0, array_size);
if (progress)
- fprintf(stderr, "Deltifying %u objects.\n", nr_result);
+ start_progress(&progress_state, "Deltifying %u objects...", "", nr_result);
do {
struct object_entry *entry = list[--i];
if (!entry->preferred_base)
processed++;
- if (progress) {
- unsigned percent = processed * 100 / nr_result;
- if (percent != last_percent || progress_update) {
- fprintf(stderr, "%4u%% (%u/%u) done\r",
- percent, processed, nr_result);
- progress_update = 0;
- last_percent = percent;
- }
- }
+ if (progress)
+ display_progress(&progress_state, processed);
if (entry->delta)
/* This happens if we decided to reuse existing
} while (i > 0);
if (progress)
- fputc('\n', stderr);
+ stop_progress(&progress_state);
for (i = 0; i < window; ++i) {
free_delta_index(array[i].index);
free(delta_list);
}
-static void progress_interval(int signum)
-{
- progress_update = 1;
-}
-
-static void setup_progress_signal(void)
-{
- struct sigaction sa;
- struct itimerval v;
-
- memset(&sa, 0, sizeof(sa));
- sa.sa_handler = progress_interval;
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_RESTART;
- sigaction(SIGALRM, &sa, NULL);
-
- v.it_interval.tv_sec = 1;
- v.it_interval.tv_usec = 0;
- v.it_value = v.it_interval;
- setitimer(ITIMER_REAL, &v, NULL);
-}
-
static int git_pack_config(const char *k, const char *v)
{
if(!strcmp(k, "pack.window")) {
window = git_config_int(k, v);
return 0;
}
+ if(!strcmp(k, "pack.depth")) {
+ 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;
+ }
return git_default_config(k, v);
}
hash = name_hash(line+41);
add_preferred_base_object(line+41, hash);
- add_object_entry(sha1, hash, 0);
+ add_object_entry(sha1, 0, hash, 0);
}
}
static void show_commit(struct commit *commit)
{
- add_object_entry(commit->object.sha1, 0, 0);
+ add_object_entry(commit->object.sha1, OBJ_COMMIT, 0, 0);
}
static void show_object(struct object_array_entry *p)
{
unsigned hash = name_hash(p->name);
add_preferred_base_object(p->name, hash);
- add_object_entry(p->item->sha1, hash, 0);
+ add_object_entry(p->item->sha1, p->item->type, hash, 0);
}
static void show_edge(struct commit *commit)
traverse_commit_list(&revs, show_commit, show_object);
}
+static int adjust_perm(const char *path, mode_t mode)
+{
+ if (chmod(path, mode))
+ return -1;
+ return adjust_shared_perm(path);
+}
+
int cmd_pack_objects(int argc, const char **argv, const char *prefix)
{
- int depth = 10;
int use_internal_rev_list = 0;
int thin = 0;
uint32_t i;
rp_ac = 2;
git_config(git_pack_config);
+ if (!pack_compression_seen && core_compression_seen)
+ pack_compression_level = core_compression_level;
progress = isatty(2);
for (i = 1; i < argc; i++) {
incremental = 1;
continue;
}
+ if (!prefixcmp(arg, "--compression=")) {
+ char *end;
+ int level = strtoul(arg+14, &end, 0);
+ if (!arg[14] || *end)
+ usage(pack_usage);
+ 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;
+ continue;
+ }
if (!prefixcmp(arg, "--window=")) {
char *end;
window = strtoul(arg+9, &end, 0);
no_reuse_delta = 1;
continue;
}
+ if (!strcmp("--no-reuse-object", arg)) {
+ no_reuse_object = no_reuse_delta = 1;
+ continue;
+ }
if (!strcmp("--delta-base-offset", arg)) {
allow_ofs_delta = 1;
continue;
prepare_packed_git();
- if (progress) {
- fprintf(stderr, "Generating pack...\n");
- setup_progress_signal();
- }
-
+ if (progress)
+ start_progress(&progress_state, "Generating pack...",
+ "Counting objects: ", 0);
if (!use_internal_rev_list)
read_object_list_from_stdin();
else {
rp_av[rp_ac] = NULL;
get_object_list(rp_ac, rp_av);
}
-
- if (progress)
+ if (progress) {
+ stop_progress(&progress_state);
fprintf(stderr, "Done counting %u objects.\n", nr_objects);
+ }
+
if (non_empty && !nr_result)
return 0;
if (progress && (nr_objects != nr_result))
fprintf(stderr, "Result has %u objects.\n", nr_result);
if (nr_result)
prepare_pack(window, depth);
- if (progress == 1 && pack_to_stdout) {
- /* the other end usually displays progress itself */
- struct itimerval v = {{0,},};
- setitimer(ITIMER_REAL, &v, NULL);
- signal(SIGALRM, SIG_IGN );
- progress_update = 0;
- }
last_obj_offset = write_pack_file();
if (!pack_to_stdout) {
unsigned char object_list_sha1[20];
+ mode_t mode = umask(0);
+
+ umask(mode);
+ mode = 0444 & ~mode;
+
write_index_file(last_obj_offset, object_list_sha1);
snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
base_name, sha1_to_hex(object_list_sha1));
+ if (adjust_perm(pack_tmp_name, mode))
+ die("unable to make temporary pack file readable: %s",
+ strerror(errno));
if (rename(pack_tmp_name, tmpname))
die("unable to rename temporary pack file: %s",
strerror(errno));
snprintf(tmpname, sizeof(tmpname), "%s-%s.idx",
base_name, sha1_to_hex(object_list_sha1));
+ if (adjust_perm(idx_tmp_name, mode))
+ die("unable to make temporary index file readable: %s",
+ strerror(errno));
if (rename(idx_tmp_name, tmpname))
die("unable to rename temporary index file: %s",
strerror(errno));