diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 69ac27788b37c89ede1dadf293c13de05fb03e82..2dadec1630c266bbaf42e84810f7059ed5c43b1e 100644 (file)
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
[--window=N] [--window-memory=N] [--depth=N] \n\
[--no-reuse-delta] [--no-reuse-object] [--delta-base-offset] \n\
[--threads=N] [--non-empty] [--revs [--unpacked | --all]*] [--reflog] \n\
- [--stdout | base-name] [--include-tag] [--keep-unreachable] \n\
+ [--stdout | base-name] [--include-tag] \n\
+ [--keep-unreachable | --unpack-unreachable] \n\
[<ref-list | <object-list]";
struct object_entry {
*/
void *delta_data; /* cached delta (uncompressed) */
unsigned long delta_size; /* delta data size (uncompressed) */
+ unsigned long z_delta_size; /* delta data size (compressed) */
unsigned int hash; /* name hint hash */
enum object_type type;
enum object_type in_pack_type; /* could be delta */
static int non_empty;
static int reuse_delta = 1, reuse_object = 1;
-static int keep_unreachable, include_tag;
+static int keep_unreachable, unpack_unreachable, include_tag;
static int local;
static int incremental;
static int allow_ofs_delta;
return delta_buf;
}
+static unsigned long do_compress(void **pptr, unsigned long size)
+{
+ z_stream stream;
+ void *in, *out;
+ unsigned long maxsize;
+
+ memset(&stream, 0, sizeof(stream));
+ deflateInit(&stream, pack_compression_level);
+ maxsize = deflateBound(&stream, size);
+
+ in = *pptr;
+ out = xmalloc(maxsize);
+ *pptr = out;
+
+ stream.next_in = in;
+ stream.avail_in = size;
+ stream.next_out = out;
+ stream.avail_out = maxsize;
+ while (deflate(&stream, Z_FINISH) == Z_OK)
+ ; /* nothing */
+ deflateEnd(&stream);
+
+ free(in);
+ return stream.total_out;
+}
+
/*
* The per-object header is a pretty dense thing, which is
* - first byte: low four bits are "size", then three bits of "type",
stream.total_in == len) ? 0 : -1;
}
-static int check_pack_crc(struct packed_git *p, struct pack_window **w_curs,
- off_t offset, off_t len, unsigned int nr)
-{
- const uint32_t *index_crc;
- uint32_t data_crc = crc32(0, Z_NULL, 0);
-
- do {
- unsigned int avail;
- void *data = use_pack(p, w_curs, offset, &avail);
- if (avail > len)
- avail = len;
- data_crc = crc32(data_crc, data, avail);
- offset += avail;
- len -= avail;
- } while (len);
-
- index_crc = p->index_data;
- index_crc += 2 + 256 + p->num_objects * (20/4) + nr;
-
- return data_crc != ntohl(*index_crc);
-}
-
static void copy_pack_data(struct sha1file *f,
struct packed_git *p,
struct pack_window **w_curs,
struct object_entry *entry,
off_t write_offset)
{
- unsigned long size, limit;
+ unsigned long size, limit, datalen;
void *buf;
unsigned char header[10], dheader[10];
unsigned hdrlen;
- off_t datalen;
enum object_type type;
int usable_delta, to_reuse;
*/
if (!to_reuse) {
- z_stream stream;
- unsigned long maxsize;
- void *out;
if (!usable_delta) {
buf = read_sha1_file(entry->idx.sha1, &type, &size);
if (!buf)
die("unable to read %s", sha1_to_hex(entry->idx.sha1));
+ /*
+ * make sure no cached delta data remains from a
+ * previous attempt before a pack split occured.
+ */
+ free(entry->delta_data);
+ entry->delta_data = NULL;
+ entry->z_delta_size = 0;
} else if (entry->delta_data) {
size = entry->delta_size;
buf = entry->delta_data;
type = (allow_ofs_delta && entry->delta->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
}
- /* compress the data to store and put compressed length in datalen */
- memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, pack_compression_level);
- maxsize = deflateBound(&stream, size);
- out = xmalloc(maxsize);
- /* Compress it */
- stream.next_in = buf;
- stream.avail_in = size;
- stream.next_out = out;
- stream.avail_out = maxsize;
- while (deflate(&stream, Z_FINISH) == Z_OK)
- /* nothing */;
- deflateEnd(&stream);
- datalen = stream.total_out;
+
+ if (entry->z_delta_size)
+ datalen = entry->z_delta_size;
+ else
+ datalen = do_compress(&buf, size);
/*
* The object header is a byte of 'type' followed by zero or
while (ofs >>= 7)
dheader[--pos] = 128 | (--ofs & 127);
if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
- free(out);
free(buf);
return 0;
}
* an additional 20 bytes for the base sha1.
*/
if (limit && hdrlen + 20 + datalen + 20 >= limit) {
- free(out);
free(buf);
return 0;
}
hdrlen += 20;
} else {
if (limit && hdrlen + datalen + 20 >= limit) {
- free(out);
free(buf);
return 0;
}
sha1write(f, header, hdrlen);
}
- sha1write(f, out, datalen);
- free(out);
+ sha1write(f, buf, datalen);
free(buf);
}
else {
* Did we write the wrong # entries in the header?
* If so, rewrite it like in fast-import
*/
- if (pack_to_stdout || nr_written == nr_remaining) {
- sha1close(f, sha1, 1);
+ if (pack_to_stdout) {
+ sha1close(f, sha1, CSUM_CLOSE);
+ } else if (nr_written == nr_remaining) {
+ sha1close(f, sha1, CSUM_FSYNC);
} else {
int fd = sha1close(f, NULL, 0);
fixup_pack_header_footer(fd, sha1, pack_tmp_name, nr_written);
+ fsync_or_die(fd, pack_tmp_name);
close(fd);
}
free(written_list);
stop_progress(&progress_state);
if (written != nr_result)
- die("wrote %u objects while expecting %u", written, nr_result);
+ die("wrote %"PRIu32" objects while expecting %"PRIu32,
+ written, nr_result);
/*
* We have scanned through [0 ... i). Since we have written
* the correct number of objects, the remaining [i ... nr_objects)
j += !e->idx.offset && !e->preferred_base;
}
if (j)
- die("wrote %u objects as expected but %u unwritten", written, j);
+ die("wrote %"PRIu32" objects as expected but %"PRIu32
+ " unwritten", written, j);
}
static int locate_object_entry_hash(const unsigned char *sha1)
sorted_by_offset[i] = objects + i;
qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
- init_pack_revindex();
-
for (i = 0; i < nr_objects; i++)
check_object(sorted_by_offset[i]);
best_base = other_idx;
}
+ /*
+ * If we decided to cache the delta data, then it is best
+ * to compress it right away. First because we have to do
+ * it anyway, and doing it here while we're threaded will
+ * save a lot of time in the non threaded write phase,
+ * as well as allow for caching more deltas within
+ * the same cache size limit.
+ * ...
+ * But only if not writing to stdout, since in that case
+ * the network is most likely throttling writes anyway,
+ * and therefore it is best to go to the write phase ASAP
+ * instead, as we can afford spending more time compressing
+ * between writes at that moment.
+ */
+ if (entry->delta_data && !pack_to_stdout) {
+ entry->z_delta_size = do_compress(&entry->delta_data,
+ entry->delta_size);
+ cache_lock();
+ delta_cache_size -= entry->delta_size;
+ delta_cache_size += entry->z_delta_size;
+ cache_unlock();
+ }
+
/* if we made n a delta, and if n is already at max
* depth, leaving it in the window is pointless. we
* should evict it first.
*/
- if (entry->delta && depth <= n->depth)
+ if (entry->delta && max_depth <= n->depth)
continue;
/*
@@ -1674,7 +1696,8 @@ static int add_ref_tag(const char *path, const unsigned char *sha1, int flag, vo
static void prepare_pack(int window, int depth)
{
struct object_entry **delta_list;
- uint32_t i, n, nr_deltas;
+ uint32_t i, nr_deltas;
+ unsigned n;
get_object_details();
free(delta_list);
}
-static int git_pack_config(const char *k, const char *v)
+static int git_pack_config(const char *k, const char *v, void *cb)
{
if(!strcmp(k, "pack.window")) {
window = git_config_int(k, v);
if (!strcmp(k, "pack.indexversion")) {
pack_idx_default_version = git_config_int(k, v);
if (pack_idx_default_version > 2)
- die("bad pack.indexversion=%d", pack_idx_default_version);
+ die("bad pack.indexversion=%"PRIu32,
+ pack_idx_default_version);
return 0;
}
if (!strcmp(k, "pack.packsizelimit")) {
pack_size_limit_cfg = git_config_ulong(k, v);
return 0;
}
- return git_default_config(k, v);
+ return git_default_config(k, v, cb);
}
static void read_object_list_from_stdin(void)
free(in_pack.array);
}
+static void loosen_unused_packed_objects(struct rev_info *revs)
+{
+ struct packed_git *p;
+ uint32_t i;
+ const unsigned char *sha1;
+
+ for (p = packed_git; p; p = p->next) {
+ for (i = 0; i < revs->num_ignore_packed; i++) {
+ if (matches_pack_name(p, revs->ignore_packed[i]))
+ break;
+ }
+ if (revs->num_ignore_packed <= i)
+ continue;
+
+ if (open_pack_index(p))
+ die("cannot open pack index");
+
+ for (i = 0; i < p->num_objects; i++) {
+ sha1 = nth_packed_object_sha1(p, i);
+ if (!locate_object_entry(sha1))
+ if (force_object_loose(sha1, p->mtime))
+ die("unable to force loose object");
+ }
+ }
+}
+
static void get_object_list(int ac, const char **av)
{
struct rev_info revs;
if (keep_unreachable)
add_objects_in_unpacked_packs(&revs);
+ if (unpack_unreachable)
+ loosen_unused_packed_objects(&revs);
}
static int adjust_perm(const char *path, mode_t mode)
rp_av[1] = "--objects"; /* --thin will make it --objects-edge */
rp_ac = 2;
- git_config(git_pack_config);
+ git_config(git_pack_config, NULL);
if (!pack_compression_seen && core_compression_seen)
pack_compression_level = core_compression_level;
keep_unreachable = 1;
continue;
}
+ if (!strcmp("--unpack-unreachable", arg)) {
+ unpack_unreachable = 1;
+ continue;
+ }
if (!strcmp("--include-tag", arg)) {
include_tag = 1;
continue;
if (!pack_to_stdout && thin)
die("--thin cannot be used to build an indexable pack.");
+ if (keep_unreachable && unpack_unreachable)
+ die("--keep-unreachable and --unpack-unreachable are incompatible.");
+
#ifdef THREADED_DELTA_SEARCH
if (!delta_search_threads) /* --threads=0 means autodetect */
delta_search_threads = online_cpus();
prepare_pack(window, depth);
write_pack_file();
if (progress)
- fprintf(stderr, "Total %u (delta %u), reused %u (delta %u)\n",
+ fprintf(stderr, "Total %"PRIu32" (delta %"PRIu32"),"
+ " reused %"PRIu32" (delta %"PRIu32")\n",
written, written_delta, reused, reused_delta);
return 0;
}