#include "pack.h"
#include "csum-file.h"
#include <sys/time.h>
+#include <signal.h>
-static const char pack_usage[] = "git-pack-objects [-q] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
+static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
struct object_entry {
unsigned char sha1[20];
unsigned long size; /* uncompressed size */
- unsigned long offset; /* offset into the final pack file (nonzero if already written) */
+ unsigned long offset; /* offset into the final pack file;
+ * nonzero if already written.
+ */
unsigned int depth; /* delta depth */
+ unsigned int delta_limit; /* base adjustment for in-pack delta */
unsigned int hash; /* name hint hash */
enum object_type type;
+ enum object_type in_pack_type; /* could be delta */
unsigned long delta_size; /* delta data size (uncompressed) */
struct object_entry *delta; /* delta base object */
struct packed_git *in_pack; /* already in pack */
- enum object_type in_pack_type; /* could be delta */
unsigned int in_pack_offset;
+ struct object_entry *delta_child; /* delitified objects who bases me */
+ struct object_entry *delta_sibling; /* other deltified objects who
+ * uses the same base as me
+ */
};
/*
static unsigned char object_list_sha1[20];
static int non_empty = 0;
+static int no_reuse_delta = 0;
static int local = 0;
static int incremental = 0;
static struct object_entry **sorted_by_sha, **sorted_by_type;
static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;
+static volatile sig_atomic_t progress_update = 0;
/*
* The object names in objects array are hashed with this hashtable,
* stats
*/
static int written = 0;
+static int written_delta = 0;
static int reused = 0;
+static int reused_delta = 0;
static int pack_revindex_ix(struct packed_git *p)
{
unsigned char header[10];
unsigned hdrlen, datalen;
enum object_type obj_type;
+ int to_reuse = 0;
obj_type = entry->type;
- if (!entry->in_pack ||
- (obj_type != entry->in_pack_type)) {
+ if (! entry->in_pack)
+ to_reuse = 0; /* can't reuse what we don't have */
+ else if (obj_type == OBJ_DELTA)
+ to_reuse = 1; /* check_object() decided it for us */
+ else if (obj_type != entry->in_pack_type)
+ to_reuse = 0; /* pack has delta which is unusable */
+ else if (entry->delta)
+ to_reuse = 0; /* we want to pack afresh */
+ else
+ to_reuse = 1; /* we have it in-pack undeltified,
+ * and we do not need to deltify it.
+ */
+
+ if (! to_reuse) {
buf = read_sha1_file(entry->sha1, type, &size);
if (!buf)
die("unable to read %s", sha1_to_hex(entry->sha1));
sha1write(f, buf, datalen);
unuse_packed_git(p);
hdrlen = 0; /* not really */
+ if (obj_type == OBJ_DELTA)
+ reused_delta++;
reused++;
}
+ if (obj_type == OBJ_DELTA)
+ written_delta++;
written++;
return hdrlen + datalen;
}
int i;
struct sha1file *f;
unsigned long offset;
- unsigned long mb;
struct pack_header hdr;
+ unsigned last_percent = 999;
+ int do_progress = 0;
if (!base_name)
f = sha1fd(1, "<stdout>");
- else
- f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack");
+ else {
+ f = sha1create("%s-%s.%s", base_name,
+ sha1_to_hex(object_list_sha1), "pack");
+ do_progress = progress;
+ }
+ if (do_progress)
+ fprintf(stderr, "Writing %d objects.\n", nr_objects);
+
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(PACK_VERSION);
hdr.hdr_entries = htonl(nr_objects);
sha1write(f, &hdr, sizeof(hdr));
offset = sizeof(hdr);
- for (i = 0; i < nr_objects; i++)
+ for (i = 0; i < nr_objects; i++) {
offset = write_one(f, objects + i, offset);
+ if (do_progress) {
+ unsigned percent = written * 100 / nr_objects;
+ if (progress_update || percent != last_percent) {
+ fprintf(stderr, "%4u%% (%u/%u) done\r",
+ percent, written, nr_objects);
+ progress_update = 0;
+ last_percent = percent;
+ }
+ }
+ }
+ if (do_progress)
+ fputc('\n', stderr);
sha1close(f, pack_file_sha1, 1);
}
unsigned int idx = nr_objects;
struct object_entry *entry;
struct packed_git *p;
- unsigned int found_offset;
- struct packed_git *found_pack;
+ unsigned int found_offset = 0;
+ struct packed_git *found_pack = NULL;
- found_pack = NULL;
for (p = packed_git; p; p = p->next) {
struct pack_entry e;
if (find_pack_entry_one(sha1, &e, p)) {
char type[20];
if (entry->in_pack) {
+ unsigned char base[20];
+ unsigned long size;
+ struct object_entry *base_entry;
+
+ /* We want in_pack_type even if we do not reuse delta.
+ * There is no point not reusing non-delta representations.
+ */
+ check_reuse_pack_delta(entry->in_pack,
+ entry->in_pack_offset,
+ base, &size,
+ &entry->in_pack_type);
+
/* 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.
*/
- unsigned char base[20];
- unsigned long size;
- struct object_entry *base_entry;
- if (!check_reuse_pack_delta(entry->in_pack,
- entry->in_pack_offset,
- base, &size,
- &entry->in_pack_type) &&
+ if (!no_reuse_delta &&
+ entry->in_pack_type == OBJ_DELTA &&
(base_entry = locate_object_entry(base))) {
- /* We do not know depth at this point, but it
- * does not matter. Getting delta_chain_length
- * with packed_object_info_detail() is not so
- * expensive, so we could do that later if we
- * wanted to. Calling sha1_object_info to get
- * the true size (and later an uncompressed
- * representation) of deeply deltified object
- * is quite expensive.
+
+ /* 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.
*/
- entry->depth = 1;
- /* uncompressed size */
+
+ /* uncompressed size of the delta data */
entry->size = entry->delta_size = size;
entry->delta = base_entry;
entry->type = OBJ_DELTA;
+
+ entry->delta_sibling = base_entry->delta_child;
+ base_entry->delta_child = entry;
+
return;
}
/* Otherwise we would do the usual */
}
}
+static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
+{
+ struct object_entry *child = me->delta_child;
+ unsigned int m = n;
+ while (child) {
+ unsigned int c = check_delta_limit(child, n + 1);
+ if (m < c)
+ m = c;
+ child = child->delta_sibling;
+ }
+ return m;
+}
+
static void get_object_details(void)
{
int i;
- struct object_entry *entry = objects;
+ struct object_entry *entry;
hash_objects();
prepare_pack_ix();
- for (i = 0; i < nr_objects; i++)
- check_object(entry++);
+ for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+ check_object(entry);
+ for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+ if (!entry->delta && entry->delta_child)
+ entry->delta_limit =
+ check_delta_limit(entry, 1);
}
typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *);
if (cur_entry->type != old_entry->type)
return -1;
+ /* If the current object is at edge, take the depth the objects
+ * that depend on the current object into account -- otherwise
+ * they would become too deep.
+ */
+ if (cur_entry->delta_child) {
+ if (max_depth <= cur_entry->delta_limit)
+ return 0;
+ max_depth -= cur_entry->delta_limit;
+ }
+
size = cur_entry->size;
if (size < 50)
return -1;
return 0;
}
+static void progress_interval(int signum)
+{
+ progress_update = 1;
+}
+
static void find_deltas(struct object_entry **list, int window, int depth)
{
int i, idx;
unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array = xmalloc(array_size);
- int eye_candy;
+ unsigned processed = 0;
+ unsigned last_percent = 999;
memset(array, 0, array_size);
i = nr_objects;
idx = 0;
- eye_candy = i - (nr_objects / 20);
+ if (progress)
+ fprintf(stderr, "Deltifying %d objects.\n", nr_objects);
while (--i >= 0) {
struct object_entry *entry = list[i];
char type[10];
int j;
- if (progress && i <= eye_candy) {
- eye_candy -= nr_objects / 20;
- fputc('.', stderr);
+ processed++;
+ if (progress) {
+ unsigned percent = processed * 100 / nr_objects;
+ if (percent != last_percent || progress_update) {
+ fprintf(stderr, "%4u%% (%u/%u) done\r",
+ percent, processed, nr_objects);
+ progress_update = 0;
+ last_percent = percent;
+ }
}
if (entry->delta)
/* This happens if we decided to reuse existing
- * delta from a pack.
+ * delta from a pack. "!no_reuse_delta &&" is implied.
*/
continue;
n->data = read_sha1_file(entry->sha1, type, &size);
if (size != entry->size)
die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+
j = window;
while (--j > 0) {
unsigned int other_idx = idx + j;
idx = 0;
}
+ if (progress)
+ fputc('\n', stderr);
+
for (i = 0; i < window; ++i)
free(array[i].data);
free(array);
static void prepare_pack(int window, int depth)
{
- if (progress)
- fprintf(stderr, "Packing %d objects", nr_objects);
get_object_details();
- if (progress)
- fprintf(stderr, ".");
-
sorted_by_type = create_sorted_list(type_size_sort);
if (window && depth)
find_deltas(sorted_by_type, window+1, depth);
- if (progress)
- fputc('\n', stderr);
- write_pack_file();
}
static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
}
}
- fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
- sha1_to_hex(sha1));
+ if (progress)
+ fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+ sha1_to_hex(sha1));
if (pack_to_stdout) {
if (copy_fd(ifd, 1))
return 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);
+}
+
int main(int argc, char **argv)
{
SHA_CTX ctx;
int window = 10, depth = 10, pack_to_stdout = 0;
struct object_entry **list;
int i;
- struct timeval prev_tv;
- int eye_candy = 0;
- int eye_candy_incr = 500;
-
setup_git_directory();
progress = 0;
continue;
}
+ if (!strcmp("--no-reuse-delta", arg)) {
+ no_reuse_delta = 1;
+ continue;
+ }
if (!strcmp("--stdout", arg)) {
pack_to_stdout = 1;
continue;
usage(pack_usage);
prepare_packed_git();
+
if (progress) {
fprintf(stderr, "Generating pack...\n");
- gettimeofday(&prev_tv, NULL);
+ setup_progress_signal();
}
- while (fgets(line, sizeof(line), stdin) != NULL) {
+
+ for (;;) {
unsigned int hash;
char *p;
unsigned char sha1[20];
- if (progress && (eye_candy <= nr_objects)) {
+ if (!fgets(line, sizeof(line), stdin)) {
+ if (feof(stdin))
+ break;
+ if (!ferror(stdin))
+ die("fgets returned NULL, not EOF, not error!");
+ if (errno != EINTR)
+ die("fgets: %s", strerror(errno));
+ clearerr(stdin);
+ continue;
+ }
+
+ if (progress_update) {
fprintf(stderr, "Counting objects...%d\r", nr_objects);
- if (eye_candy && (50 <= eye_candy_incr)) {
- struct timeval tv;
- int time_diff;
- gettimeofday(&tv, NULL);
- time_diff = (tv.tv_sec - prev_tv.tv_sec);
- time_diff <<= 10;
- time_diff += (tv.tv_usec - prev_tv.tv_usec);
- if ((1 << 9) < time_diff)
- eye_candy_incr += 50;
- else if (50 < eye_candy_incr)
- eye_candy_incr -= 50;
- }
- eye_candy += eye_candy_incr;
+ progress_update = 0;
}
if (get_sha1_hex(line, sha1))
die("expected sha1, got garbage:\n %s", line);
;
else {
prepare_pack(window, depth);
+ if (progress && 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;
+ }
+ write_pack_file();
if (!pack_to_stdout) {
write_index_file();
puts(sha1_to_hex(object_list_sha1));
}
}
- fprintf(stderr, "Total %d, written %d, reused %d\n",
- nr_objects, written, reused);
+ if (progress)
+ fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
+ nr_objects, written, written_delta, reused, reused_delta);
return 0;
}