#include "builtin.h"
#include "cache.h"
+#include "attr.h"
#include "object.h"
#include "blob.h"
#include "commit.h"
#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]";
+ [--max-pack-size=N] [--local] [--incremental] \n\
+ [--window=N] [--window-memory=N] [--depth=N] \n\
+ [--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];
+ struct pack_idx_entry idx;
unsigned long size; /* uncompressed size */
- off_t 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) */
-#define in_pack_header_size delta_size /* only when reusing pack data */
- struct object_entry *delta; /* delta base object */
struct packed_git *in_pack; /* already in pack */
off_t in_pack_offset;
+ struct object_entry *delta; /* delta base object */
struct object_entry *delta_child; /* deltified objects who bases me */
struct object_entry *delta_sibling; /* other deltified objects who
* uses the same base as me
*/
- int preferred_base; /* we do not pack this, but is encouraged to
- * be used as the base objectto delta huge
- * objects against.
- */
+ void *delta_data; /* cached delta (uncompressed) */
+ unsigned long delta_size; /* delta data size (uncompressed) */
+ unsigned int hash; /* name hint hash */
+ enum object_type type;
+ enum object_type in_pack_type; /* could be delta */
+ unsigned char in_pack_header_size;
+ unsigned char preferred_base; /* we do not pack this, but is available
+ * to be used as the base object to delta
+ * objects against.
+ */
+ unsigned char no_try_delta;
};
/*
* 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 struct object_entry **written_list;
+static uint32_t nr_objects, nr_alloc, nr_result, nr_written;
-static unsigned char object_list_sha1[20];
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 **sorted_by_sha, **sorted_by_type;
-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 const char *base_name;
-static unsigned char pack_file_sha1[20];
static int progress = 1;
-static volatile sig_atomic_t progress_update;
static int window = 10;
+static uint32_t pack_size_limit;
+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;
+
+static unsigned long delta_cache_size = 0;
+static unsigned long max_delta_cache_size = 0;
+static unsigned long cache_max_small_delta_size = 1000;
+
+static unsigned long window_memory_usage = 0;
+static unsigned long window_memory_limit = 0;
/*
* 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 void prepare_pack_revindex(struct pack_revindex *rix)
{
struct packed_git *p = rix->p;
- int num_ent = num_packed_objects(p);
+ int num_ent = p->num_objects;
int i;
const char *index = p->index_data;
- index += 4 * 256;
rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
- for (i = 0; i < num_ent; i++) {
- uint32_t hl = *((uint32_t *)(index + 24 * i));
- rix->revindex[i].offset = ntohl(hl);
- rix->revindex[i].nr = i;
+ index += 4 * 256;
+
+ if (p->index_version > 1) {
+ const uint32_t *off_32 =
+ (uint32_t *)(index + 8 + p->num_objects * (20 + 4));
+ const uint32_t *off_64 = off_32 + p->num_objects;
+ for (i = 0; i < num_ent; i++) {
+ uint32_t off = ntohl(*off_32++);
+ if (!(off & 0x80000000)) {
+ rix->revindex[i].offset = off;
+ } else {
+ rix->revindex[i].offset =
+ ((uint64_t)ntohl(*off_64++)) << 32;
+ rix->revindex[i].offset |=
+ ntohl(*off_64++);
+ }
+ rix->revindex[i].nr = i;
+ }
+ } else {
+ for (i = 0; i < num_ent; i++) {
+ uint32_t hl = *((uint32_t *)(index + 24 * i));
+ rix->revindex[i].offset = ntohl(hl);
+ rix->revindex[i].nr = i;
+ }
}
+
/* This knows the pack format -- the 20-byte trailer
* follows immediately after the last object data.
*/
prepare_pack_revindex(rix);
revindex = rix->revindex;
lo = 0;
- hi = num_packed_objects(p) + 1;
+ hi = p->num_objects + 1;
do {
int mi = (lo + hi) / 2;
if (revindex[mi].offset == ofs) {
die("internal error: pack revindex corrupt");
}
-static off_t find_packed_object_size(struct packed_git *p, off_t ofs)
-{
- struct revindex_entry *entry = find_packed_object(p, ofs);
- return entry[1].offset - ofs;
-}
-
static const unsigned char *find_packed_object_name(struct packed_git *p,
off_t ofs)
{
{
unsigned long othersize, delta_size;
enum object_type type;
- void *otherbuf = read_sha1_file(entry->delta->sha1, &type, &othersize);
+ void *otherbuf = read_sha1_file(entry->delta->idx.sha1, &type, &othersize);
void *delta_buf;
if (!otherbuf)
- die("unable to read %s", sha1_to_hex(entry->delta->sha1));
+ die("unable to read %s", sha1_to_hex(entry->delta->idx.sha1));
delta_buf = diff_delta(otherbuf, othersize,
buf, size, &delta_size, 0);
if (!delta_buf || delta_size != entry->delta_size)
- die("delta size changed");
+ die("delta size changed");
free(buf);
free(otherbuf);
return delta_buf;
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,
}
}
-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 off_t write_object(struct sha1file *f,
- struct object_entry *entry)
+static unsigned long write_object(struct sha1file *f,
+ struct object_entry *entry,
+ off_t write_offset)
{
unsigned long size;
enum object_type type;
void *buf;
unsigned char header[10];
+ unsigned char dheader[10];
unsigned hdrlen;
off_t datalen;
enum object_type obj_type;
int to_reuse = 0;
+ /* write limit if limited packsize and not first object */
+ unsigned long limit = pack_size_limit && nr_written ?
+ pack_size_limit - write_offset : 0;
+ /* no if no delta */
+ int usable_delta = !entry->delta ? 0 :
+ /* yes if unlimited packfile */
+ !pack_size_limit ? 1 :
+ /* no if base written to previous pack */
+ entry->delta->idx.offset == (off_t)-1 ? 0 :
+ /* otherwise double-check written to this
+ * pack, like we do below
+ */
+ entry->delta->idx.offset ? 1 : 0;
+
+ if (!pack_to_stdout)
+ 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 */
+ /* check_object() decided it for us ... */
+ to_reuse = usable_delta;
+ /* ... but pack split may override that */
else if (obj_type != entry->in_pack_type)
to_reuse = 0; /* pack has delta which is unusable */
else if (entry->delta)
* 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)
- die("unable to read %s", sha1_to_hex(entry->sha1));
- if (size != entry->size)
- die("object %s size inconsistency (%lu vs %lu)",
- sha1_to_hex(entry->sha1), size, entry->size);
- if (entry->delta) {
+ z_stream stream;
+ unsigned long maxsize;
+ void *out;
+ if (!usable_delta) {
+ buf = read_sha1_file(entry->idx.sha1, &obj_type, &size);
+ if (!buf)
+ die("unable to read %s", sha1_to_hex(entry->idx.sha1));
+ } else if (entry->delta_data) {
+ size = entry->delta_size;
+ buf = entry->delta_data;
+ entry->delta_data = NULL;
+ obj_type = (allow_ofs_delta && entry->delta->idx.offset) ?
+ OBJ_OFS_DELTA : OBJ_REF_DELTA;
+ } else {
+ buf = read_sha1_file(entry->idx.sha1, &type, &size);
+ if (!buf)
+ die("unable to read %s", sha1_to_hex(entry->idx.sha1));
buf = delta_against(buf, size, entry);
size = entry->delta_size;
- obj_type = (allow_ofs_delta && entry->delta->offset) ?
+ obj_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;
+ deflateEnd(&stream);
/*
* The object header is a byte of 'type' followed by zero or
* more bytes of length.
*/
hdrlen = encode_header(obj_type, size, header);
- sha1write(f, header, hdrlen);
if (obj_type == OBJ_OFS_DELTA) {
/*
* encoding of the relative offset for the delta
* base from this object's position in the pack.
*/
- off_t ofs = entry->offset - entry->delta->offset;
- unsigned pos = sizeof(header) - 1;
- header[pos] = ofs & 127;
+ off_t ofs = entry->idx.offset - entry->delta->idx.offset;
+ unsigned pos = sizeof(dheader) - 1;
+ dheader[pos] = ofs & 127;
while (ofs >>= 7)
- header[--pos] = 128 | (--ofs & 127);
- sha1write(f, header + pos, sizeof(header) - pos);
- hdrlen += sizeof(header) - pos;
+ dheader[--pos] = 128 | (--ofs & 127);
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+ free(out);
+ free(buf);
+ return 0;
+ }
+ sha1write(f, header, hdrlen);
+ sha1write(f, dheader + pos, sizeof(dheader) - pos);
+ hdrlen += sizeof(dheader) - pos;
} else if (obj_type == OBJ_REF_DELTA) {
/*
* Deltas with a base reference contain
* an additional 20 bytes for the base sha1.
*/
- sha1write(f, entry->delta->sha1, 20);
+ if (limit && hdrlen + 20 + datalen + 20 >= limit) {
+ free(out);
+ free(buf);
+ return 0;
+ }
+ sha1write(f, header, hdrlen);
+ sha1write(f, entry->delta->idx.sha1, 20);
hdrlen += 20;
+ } else {
+ if (limit && hdrlen + datalen + 20 >= limit) {
+ free(out);
+ free(buf);
+ return 0;
+ }
+ sha1write(f, header, hdrlen);
}
- datalen = sha1write_compressed(f, buf, size);
+ sha1write(f, out, datalen);
+ free(out);
free(buf);
}
else {
struct packed_git *p = entry->in_pack;
struct pack_window *w_curs = NULL;
+ struct revindex_entry *revidx;
off_t offset;
if (entry->delta) {
- obj_type = (allow_ofs_delta && entry->delta->offset) ?
+ obj_type = (allow_ofs_delta && entry->delta->idx.offset) ?
OBJ_OFS_DELTA : OBJ_REF_DELTA;
reused_delta++;
}
hdrlen = encode_header(obj_type, entry->size, header);
- sha1write(f, header, hdrlen);
+ offset = entry->in_pack_offset;
+ revidx = find_packed_object(p, offset);
+ datalen = revidx[1].offset - offset;
+ if (!pack_to_stdout && p->index_version > 1 &&
+ check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
+ die("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
+ offset += entry->in_pack_header_size;
+ datalen -= entry->in_pack_header_size;
if (obj_type == OBJ_OFS_DELTA) {
- off_t ofs = entry->offset - entry->delta->offset;
- unsigned pos = sizeof(header) - 1;
- header[pos] = ofs & 127;
+ off_t ofs = entry->idx.offset - entry->delta->idx.offset;
+ unsigned pos = sizeof(dheader) - 1;
+ dheader[pos] = ofs & 127;
while (ofs >>= 7)
- header[--pos] = 128 | (--ofs & 127);
- sha1write(f, header + pos, sizeof(header) - pos);
- hdrlen += sizeof(header) - pos;
+ dheader[--pos] = 128 | (--ofs & 127);
+ if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit)
+ return 0;
+ sha1write(f, header, hdrlen);
+ sha1write(f, dheader + pos, sizeof(dheader) - pos);
+ hdrlen += sizeof(dheader) - pos;
} else if (obj_type == OBJ_REF_DELTA) {
- sha1write(f, entry->delta->sha1, 20);
+ if (limit && hdrlen + 20 + datalen + 20 >= limit)
+ return 0;
+ sha1write(f, header, hdrlen);
+ sha1write(f, entry->delta->idx.sha1, 20);
hdrlen += 20;
+ } else {
+ if (limit && hdrlen + datalen + 20 >= limit)
+ return 0;
+ sha1write(f, header, hdrlen);
}
- offset = entry->in_pack_offset + entry->in_pack_header_size;
- datalen = find_packed_object_size(p, entry->in_pack_offset)
- - entry->in_pack_header_size;
- if (!pack_to_stdout && check_pack_inflate(p, &w_curs,
- offset, datalen, entry->size))
- die("corrupt delta in pack %s", sha1_to_hex(entry->sha1));
+ if (!pack_to_stdout && p->index_version == 1 &&
+ check_pack_inflate(p, &w_curs, offset, datalen, entry->size))
+ die("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
copy_pack_data(f, p, &w_curs, offset, datalen);
unuse_pack(&w_curs);
reused++;
}
- if (entry->delta)
+ if (usable_delta)
written_delta++;
written++;
+ if (!pack_to_stdout)
+ entry->idx.crc32 = crc32_end(f);
return hdrlen + datalen;
}
struct object_entry *e,
off_t offset)
{
- if (e->offset || e->preferred_base)
- /* offset starts from header size and cannot be zero
- * if it is written already.
- */
+ unsigned long size;
+
+ /* offset is non zero if object is written already. */
+ if (e->idx.offset || e->preferred_base)
return offset;
- /* if we are deltified, write out its base object first. */
- if (e->delta)
+
+ /* if we are deltified, write out base object first. */
+ if (e->delta) {
offset = write_one(f, e->delta, offset);
- e->offset = offset;
- return offset + write_object(f, e);
+ if (!offset)
+ return 0;
+ }
+
+ e->idx.offset = offset;
+ size = write_object(f, e, offset);
+ if (!size) {
+ e->idx.offset = 0;
+ return 0;
+ }
+ written_list[nr_written++] = e;
+
+ /* make sure off_t is sufficiently large not to wrap */
+ if (offset > offset + size)
+ die("pack too large for current definition of off_t");
+ 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);
}
+/* forward declaration for write_pack_file */
+static int adjust_perm(const char *path, mode_t mode);
+
static void write_pack_file(void)
{
- uint32_t i;
+ uint32_t i = 0, j;
struct sha1file *f;
- off_t offset;
+ off_t offset, offset_one, last_obj_offset = 0;
struct pack_header hdr;
- unsigned last_percent = 999;
- int do_progress = progress;
+ int do_progress = progress >> pack_to_stdout;
+ uint32_t nr_remaining = nr_result;
- if (!base_name) {
- f = sha1fd(1, "<stdout>");
- do_progress >>= 1;
- }
- else
- f = sha1create("%s-%s.%s", base_name,
- sha1_to_hex(object_list_sha1), "pack");
if (do_progress)
- fprintf(stderr, "Writing %u objects.\n", nr_result);
-
- hdr.hdr_signature = htonl(PACK_SIGNATURE);
- hdr.hdr_version = htonl(PACK_VERSION);
- hdr.hdr_entries = htonl(nr_result);
- sha1write(f, &hdr, sizeof(hdr));
- offset = sizeof(hdr);
- if (!nr_result)
- goto done;
- for (i = 0; i < nr_objects; i++) {
- 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)
- fputc('\n', stderr);
- done:
- if (written != nr_result)
- die("wrote %u objects while expecting %u", written, nr_result);
- sha1close(f, pack_file_sha1, 1);
-}
+ start_progress(&progress_state, "Writing %u objects...", "", nr_result);
+ written_list = xmalloc(nr_objects * sizeof(struct object_entry *));
-static void write_index_file(void)
-{
- uint32_t i;
- struct sha1file *f = sha1create("%s-%s.%s", base_name,
- sha1_to_hex(object_list_sha1), "idx");
- struct object_entry **list = sorted_by_sha;
- struct object_entry **last = list + nr_result;
- uint32_t array[256];
+ do {
+ unsigned char sha1[20];
+
+ if (pack_to_stdout) {
+ f = sha1fd(1, "<stdout>");
+ } else {
+ 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);
+ f = sha1fd(fd, pack_tmp_name);
+ }
- /*
- * Write the first-level table (the list is sorted,
- * but we use a 256-entry lookup to be able to avoid
- * having to do eight extra binary search iterations).
- */
- for (i = 0; i < 256; i++) {
- struct object_entry **next = list;
- while (next < last) {
- struct object_entry *entry = *next;
- if (entry->sha1[0] != i)
+ hdr.hdr_signature = htonl(PACK_SIGNATURE);
+ hdr.hdr_version = htonl(PACK_VERSION);
+ hdr.hdr_entries = htonl(nr_remaining);
+ sha1write(f, &hdr, sizeof(hdr));
+ offset = sizeof(hdr);
+ nr_written = 0;
+ for (; i < nr_objects; i++) {
+ last_obj_offset = offset;
+ offset_one = write_one(f, objects + i, offset);
+ if (!offset_one)
break;
- next++;
+ offset = offset_one;
+ if (do_progress)
+ display_progress(&progress_state, written);
}
- array[i] = htonl(next - sorted_by_sha);
- list = next;
- }
- sha1write(f, array, 256 * 4);
+ /*
+ * 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);
+ } else {
+ sha1close(f, sha1, 0);
+ fixup_pack_header_footer(f->fd, sha1, pack_tmp_name, nr_written);
+ close(f->fd);
+ }
+
+ if (!pack_to_stdout) {
+ mode_t mode = umask(0);
+
+ umask(mode);
+ mode = 0444 & ~mode;
+
+ idx_tmp_name = write_idx_file(NULL,
+ (struct pack_idx_entry **) written_list, nr_written, sha1);
+ snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
+ base_name, sha1_to_hex(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(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));
+ puts(sha1_to_hex(sha1));
+ }
+
+ /* mark written objects as written to previous pack */
+ for (j = 0; j < nr_written; j++) {
+ written_list[j]->idx.offset = (off_t)-1;
+ }
+ nr_remaining -= nr_written;
+ } while (nr_remaining && i < nr_objects);
+
+ free(written_list);
+ if (do_progress)
+ stop_progress(&progress_state);
+ if (written != nr_result)
+ die("wrote %u objects while expecting %u", written, nr_result);
/*
- * Write the actual SHA1 entries..
+ * We have scanned through [0 ... i). Since we have written
+ * the correct number of objects, the remaining [i ... nr_objects)
+ * items must be either already written (due to out-of-order delta base)
+ * or a preferred base. Count those which are neither and complain if any.
*/
- list = sorted_by_sha;
- for (i = 0; i < nr_result; i++) {
- struct object_entry *entry = *list++;
- uint32_t offset = htonl(entry->offset);
- sha1write(f, &offset, 4);
- sha1write(f, entry->sha1, 20);
+ for (j = 0; i < nr_objects; i++) {
+ struct object_entry *e = objects + i;
+ j += !e->idx.offset && !e->preferred_base;
}
- sha1write(f, pack_file_sha1, 20);
- sha1close(f, NULL, 1);
+ if (j)
+ die("wrote %u objects as expected but %u unwritten", written, j);
}
static int locate_object_entry_hash(const unsigned char *sha1)
memcpy(&ui, sha1, sizeof(unsigned int));
i = ui % object_ix_hashsz;
while (0 < object_ix[i]) {
- if (!hashcmp(sha1, objects[object_ix[i] - 1].sha1))
+ if (!hashcmp(sha1, objects[object_ix[i] - 1].idx.sha1))
return i;
if (++i == object_ix_hashsz)
i = 0;
object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
memset(object_ix, 0, sizeof(int) * object_ix_hashsz);
for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
- int ix = locate_object_entry_hash(oe->sha1);
+ int ix = locate_object_entry_hash(oe->idx.sha1);
if (0 <= ix)
continue;
ix = -1 - ix;
unsigned char c;
unsigned hash = 0;
+ if (!name)
+ return 0;
+
/*
* This effectively just creates a sortable number from the
* last sixteen non-whitespace characters. Last characters
return hash;
}
-static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude)
+static void setup_delta_attr_check(struct git_attr_check *check)
+{
+ static struct git_attr *attr_delta;
+
+ if (!attr_delta)
+ attr_delta = git_attr("delta", 5);
+
+ check[0].attr = attr_delta;
+}
+
+static int no_try_delta(const char *path)
+{
+ struct git_attr_check check[1];
+
+ setup_delta_attr_check(check);
+ if (git_checkattr(path, ARRAY_SIZE(check), check))
+ return 0;
+ if (ATTR_FALSE(check->value))
+ return 1;
+ return 0;
+}
+
+static int add_object_entry(const unsigned char *sha1, enum object_type type,
+ const char *name, int exclude)
{
- uint32_t idx = nr_objects;
struct object_entry *entry;
- struct packed_git *p;
+ struct packed_git *p, *found_pack = NULL;
off_t found_offset = 0;
- struct packed_git *found_pack = NULL;
- int ix, status = 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;
- }
+ int ix;
+ unsigned hash = name_hash(name);
+
+ ix = nr_objects ? locate_object_entry_hash(sha1) : -1;
+ if (ix >= 0) {
+ if (exclude) {
+ entry = objects + object_ix[ix] - 1;
+ if (!entry->preferred_base)
+ nr_result--;
+ entry->preferred_base = 1;
+ }
+ return 0;
+ }
+
+ 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;
}
}
- if ((entry = locate_object_entry(sha1)) != NULL)
- goto already_added;
- if (idx >= nr_alloc) {
- nr_alloc = (idx + 1024) * 3 / 2;
+ if (nr_objects >= nr_alloc) {
+ nr_alloc = (nr_alloc + 1024) * 3 / 2;
objects = xrealloc(objects, nr_alloc * sizeof(*entry));
}
- entry = objects + idx;
- nr_objects = idx + 1;
+
+ entry = objects + nr_objects++;
memset(entry, 0, sizeof(*entry));
- hashcpy(entry->sha1, sha1);
+ hashcpy(entry->idx.sha1, sha1);
entry->hash = hash;
+ if (type)
+ entry->type = type;
+ if (exclude)
+ entry->preferred_base = 1;
+ else
+ nr_result++;
+ if (found_pack) {
+ entry->in_pack = found_pack;
+ entry->in_pack_offset = found_offset;
+ }
if (object_ix_hashsz * 3 <= nr_objects * 4)
rehash_objects();
- else {
- ix = locate_object_entry_hash(entry->sha1);
- if (0 <= ix)
- die("internal error in object hashing.");
- object_ix[-1 - ix] = idx + 1;
- }
- status = 1;
+ else
+ object_ix[-1 - ix] = nr_objects;
- already_added:
- if (progress_update) {
- fprintf(stderr, "Counting objects...%u\r", nr_objects);
- progress_update = 0;
- }
- if (exclude)
- entry->preferred_base = 1;
- else {
- if (found_pack) {
- entry->in_pack = found_pack;
- entry->in_pack_offset = found_offset;
- }
- }
- return status;
+ if (progress)
+ display_progress(&progress_state, nr_objects);
+
+ if (name && no_try_delta(name))
+ entry->no_try_delta = 1;
+
+ return 1;
}
struct pbase_tree_cache {
const char *fullname)
{
struct name_entry entry;
+ int cmp;
while (tree_entry(tree,&entry)) {
- unsigned long size;
- enum object_type type;
-
- if (tree_entry_len(entry.path, entry.sha1) != cmplen ||
- memcmp(entry.path, name, cmplen) ||
- !has_sha1_file(entry.sha1) ||
- (type = sha1_object_info(entry.sha1, &size)) < 0)
+ cmp = tree_entry_len(entry.path, entry.sha1) != cmplen ? 1 :
+ memcmp(name, entry.path, cmplen);
+ if (cmp > 0)
continue;
+ if (cmp < 0)
+ 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,
+ fullname, 1);
return;
}
- if (type == OBJ_TREE) {
+ if (S_ISDIR(entry.mode)) {
struct tree_desc sub;
struct pbase_tree_cache *tree;
const char *down = name+cmplen+1;
return 0;
}
-static void add_preferred_base_object(const char *name, unsigned hash)
+static void add_preferred_base_object(const char *name)
{
struct pbase_tree *it;
- int cmplen = name_cmp_len(name);
+ int cmplen;
+ unsigned hash = name_hash(name);
- if (check_pbase_path(hash))
+ if (!num_preferred_base || check_pbase_path(hash))
return;
+ cmplen = name_cmp_len(name);
for (it = pbase_tree; it; it = it->next) {
if (cmplen == 0) {
- hash = name_hash("");
- add_object_entry(it->pcache.sha1, hash, 1);
+ add_object_entry(it->pcache.sha1, OBJ_TREE, NULL, 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;
+ 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->idx.sha1));
c = buf[used_0++];
- ofs = c & 127;
- while (c & 128) {
- ofs += 1;
- if (!ofs || ofs & ~(~0UL >> 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",
- 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;
+ 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->idx.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);
+ entry->type = sha1_object_info(entry->idx.sha1, &entry->size);
if (entry->type < 0)
die("unable to get type of object %s",
- sha1_to_hex(entry->sha1));
-}
-
-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;
+ sha1_to_hex(entry->idx.sha1));
}
-static void get_object_details(void)
+static int pack_offset_sort(const void *_a, const void *_b)
{
- uint32_t i;
- struct object_entry *entry;
-
- prepare_pack_ix();
- for (i = 0, entry = objects; i < nr_objects; i++, entry++)
- check_object(entry);
-
- if (nr_objects == nr_result) {
- /*
- * Depth of objects that depend on the entry -- this
- * is subtracted from depth-max to break too deep
- * delta chain because of delta data reusing.
- * However, we loosen this restriction when we know we
- * are creating a thin pack -- it will have to be
- * expanded on the other end anyway, so do not
- * artificially cut the delta chain and let it go as
- * deep as it wants.
- */
- for (i = 0, entry = objects; i < nr_objects; i++, entry++)
- if (!entry->delta && entry->delta_child)
- entry->delta_limit =
- check_delta_limit(entry, 1);
- }
-}
+ const struct object_entry *a = *(struct object_entry **)_a;
+ const struct object_entry *b = *(struct object_entry **)_b;
-typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *);
+ /* avoid filesystem trashing with loose objects */
+ if (!a->in_pack && !b->in_pack)
+ return hashcmp(a->idx.sha1, b->idx.sha1);
-static entry_sort_t current_sort;
-
-static int sort_comparator(const void *_a, const void *_b)
-{
- struct object_entry *a = *(struct object_entry **)_a;
- struct object_entry *b = *(struct object_entry **)_b;
- return current_sort(a,b);
+ 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 struct object_entry **create_sorted_list(entry_sort_t sort)
+static void get_object_details(void)
{
- struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *));
uint32_t i;
+ struct object_entry **sorted_by_offset;
+ sorted_by_offset = xcalloc(nr_objects, sizeof(struct object_entry *));
for (i = 0; i < nr_objects; i++)
- list[i] = objects + i;
- current_sort = sort;
- qsort(list, nr_objects, sizeof(struct object_entry *), sort_comparator);
- return list;
-}
+ sorted_by_offset[i] = objects + i;
+ qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
-static int sha1_sort(const struct object_entry *a, const struct object_entry *b)
-{
- return hashcmp(a->sha1, b->sha1);
+ prepare_pack_ix();
+ for (i = 0; i < nr_objects; i++)
+ check_object(sorted_by_offset[i]);
+ free(sorted_by_offset);
}
-static struct object_entry **create_final_object_list(void)
+static int type_size_sort(const void *_a, const void *_b)
{
- struct object_entry **list;
- uint32_t i, j;
-
- for (i = nr_result = 0; i < nr_objects; i++)
- if (!objects[i].preferred_base)
- nr_result++;
- list = xmalloc(nr_result * sizeof(struct object_entry *));
- for (i = j = 0; i < nr_objects; i++) {
- if (!objects[i].preferred_base)
- list[j++] = objects + i;
- }
- current_sort = sha1_sort;
- qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator);
- return list;
-}
+ const struct object_entry *a = *(struct object_entry **)_a;
+ const struct object_entry *b = *(struct object_entry **)_b;
-static int type_size_sort(const struct object_entry *a, const struct object_entry *b)
-{
if (a->type < b->type)
return -1;
if (a->type > b->type)
return -1;
if (a->size > b->size)
return 1;
- return a < b ? -1 : (a > b);
+ return a > b ? -1 : (a < b); /* newest last */
}
struct unpacked {
struct object_entry *entry;
void *data;
struct delta_index *index;
+ unsigned depth;
};
+static int delta_cacheable(struct unpacked *trg, struct unpacked *src,
+ unsigned long src_size, unsigned long trg_size,
+ unsigned long delta_size)
+{
+ if (max_delta_cache_size && delta_cache_size + delta_size > max_delta_cache_size)
+ return 0;
+
+ if (delta_size < cache_max_small_delta_size)
+ return 1;
+
+ /* cache delta, if objects are large enough compared to delta size */
+ if ((src_size >> 20) + (trg_size >> 21) > (delta_size >> 10))
+ return 1;
+
+ return 0;
+}
+
/*
* We search for deltas _backwards_ in a list sorted by type and
* by size, so that we see progressively smaller and smaller files.
struct object_entry *trg_entry = trg->entry;
struct object_entry *src_entry = src->entry;
unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz;
+ unsigned ref_depth;
enum object_type type;
void *delta_buf;
trg_entry->in_pack_type != OBJ_OFS_DELTA)
return 0;
- /*
- * If the current object is at pack edge, take the depth the
- * objects that depend on the current object into account --
- * otherwise they would become too deep.
- */
- if (trg_entry->delta_child) {
- if (max_depth <= trg_entry->delta_limit)
- return 0;
- max_depth -= trg_entry->delta_limit;
- }
- if (src_entry->depth >= max_depth)
+ /* Let's not bust the allowed depth. */
+ if (src->depth >= max_depth)
return 0;
/* Now some size filtering heuristics. */
trg_size = trg_entry->size;
- max_size = trg_size/2 - 20;
- max_size = max_size * (max_depth - src_entry->depth) / max_depth;
+ if (!trg_entry->delta) {
+ max_size = trg_size/2 - 20;
+ ref_depth = 1;
+ } else {
+ max_size = trg_entry->delta_size;
+ ref_depth = trg->depth;
+ }
+ max_size = max_size * (max_depth - src->depth) /
+ (max_depth - ref_depth + 1);
if (max_size == 0)
return 0;
- if (trg_entry->delta && trg_entry->delta_size <= max_size)
- max_size = trg_entry->delta_size-1;
src_size = src_entry->size;
sizediff = src_size < trg_size ? trg_size - src_size : 0;
if (sizediff >= max_size)
return 0;
+ if (trg_size < src_size / 32)
+ return 0;
/* Load data if not already done */
if (!trg->data) {
- trg->data = read_sha1_file(trg_entry->sha1, &type, &sz);
+ trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz);
if (sz != trg_size)
die("object %s inconsistent object length (%lu vs %lu)",
- sha1_to_hex(trg_entry->sha1), sz, trg_size);
+ sha1_to_hex(trg_entry->idx.sha1), sz, trg_size);
+ window_memory_usage += sz;
}
if (!src->data) {
- src->data = read_sha1_file(src_entry->sha1, &type, &sz);
+ src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz);
if (sz != src_size)
die("object %s inconsistent object length (%lu vs %lu)",
- sha1_to_hex(src_entry->sha1), sz, src_size);
+ sha1_to_hex(src_entry->idx.sha1), sz, src_size);
+ window_memory_usage += sz;
}
if (!src->index) {
src->index = create_delta_index(src->data, src_size);
- if (!src->index)
- die("out of memory");
+ if (!src->index) {
+ static int warned = 0;
+ if (!warned++)
+ warning("suboptimal pack - out of memory");
+ return 0;
+ }
+ window_memory_usage += sizeof_delta_index(src->index);
}
delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
if (!delta_buf)
return 0;
+ if (trg_entry->delta_data) {
+ /* Prefer only shallower same-sized deltas. */
+ if (delta_size == trg_entry->delta_size &&
+ src->depth + 1 >= trg->depth) {
+ free(delta_buf);
+ return 0;
+ }
+ delta_cache_size -= trg_entry->delta_size;
+ free(trg_entry->delta_data);
+ trg_entry->delta_data = NULL;
+ }
trg_entry->delta = src_entry;
trg_entry->delta_size = delta_size;
- trg_entry->depth = src_entry->depth + 1;
- free(delta_buf);
+ trg->depth = src->depth + 1;
+
+ if (delta_cacheable(src, trg, src_size, trg_size, delta_size)) {
+ trg_entry->delta_data = xrealloc(delta_buf, delta_size);
+ delta_cache_size += trg_entry->delta_size;
+ } else
+ free(delta_buf);
return 1;
}
-static void progress_interval(int signum)
+static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
{
- progress_update = 1;
+ 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 free_unpacked(struct unpacked *n)
+{
+ window_memory_usage -= sizeof_delta_index(n->index);
+ free_delta_index(n->index);
+ n->index = NULL;
+ if (n->data) {
+ free(n->data);
+ n->data = NULL;
+ window_memory_usage -= n->entry->size;
+ }
+ n->entry = NULL;
+ n->depth = 0;
}
static void find_deltas(struct object_entry **list, int window, int depth)
{
- uint32_t i = nr_objects, idx = 0, processed = 0;
+ uint32_t i = nr_objects, idx = 0, count = 0, processed = 0;
unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array;
- unsigned last_percent = 999;
+ int max_depth;
if (!nr_objects)
return;
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
if (entry->size < 50)
continue;
- free_delta_index(n->index);
- n->index = NULL;
- free(n->data);
- n->data = NULL;
+
+ if (entry->no_try_delta)
+ continue;
+
+ free_unpacked(n);
n->entry = entry;
+ while (window_memory_limit &&
+ window_memory_usage > window_memory_limit &&
+ count > 1) {
+ uint32_t tail = (idx + window - count) % window;
+ free_unpacked(array + tail);
+ count--;
+ }
+
+ /*
+ * If the current object is at pack edge, take the depth the
+ * objects that depend on the current object into account
+ * otherwise they would become too deep.
+ */
+ max_depth = depth;
+ if (entry->delta_child) {
+ max_depth -= check_delta_limit(entry, 0);
+ if (max_depth <= 0)
+ goto next;
+ }
+
j = window;
while (--j > 0) {
uint32_t other_idx = idx + j;
m = array + other_idx;
if (!m->entry)
break;
- if (try_delta(n, m, depth) < 0)
+ if (try_delta(n, m, max_depth) < 0)
break;
}
+
/* 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 <= entry->depth)
+ if (entry->delta && depth <= n->depth)
continue;
+ next:
idx++;
+ if (count + 1 < window)
+ count++;
if (idx >= window)
idx = 0;
} while (i > 0);
if (progress)
- fputc('\n', stderr);
+ stop_progress(&progress_state);
for (i = 0; i < window; ++i) {
free_delta_index(array[i].index);
static void prepare_pack(int window, int depth)
{
- get_object_details();
- sorted_by_type = create_sorted_list(type_size_sort);
- if (window && depth)
- find_deltas(sorted_by_type, window+1, depth);
-}
-
-static int reuse_cached_pack(unsigned char *sha1)
-{
- static const char cache[] = "pack-cache/pack-%s.%s";
- char *cached_pack, *cached_idx;
- int ifd, ofd, ifd_ix = -1;
-
- cached_pack = git_path(cache, sha1_to_hex(sha1), "pack");
- ifd = open(cached_pack, O_RDONLY);
- if (ifd < 0)
- return 0;
-
- if (!pack_to_stdout) {
- cached_idx = git_path(cache, sha1_to_hex(sha1), "idx");
- ifd_ix = open(cached_idx, O_RDONLY);
- if (ifd_ix < 0) {
- close(ifd);
- return 0;
- }
- }
-
- if (progress)
- fprintf(stderr, "Reusing %u objects pack %s\n", nr_objects,
- sha1_to_hex(sha1));
+ struct object_entry **delta_list;
+ uint32_t i;
- if (pack_to_stdout) {
- if (copy_fd(ifd, 1))
- exit(1);
- close(ifd);
- }
- else {
- char name[PATH_MAX];
- snprintf(name, sizeof(name),
- "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack");
- ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
- if (ofd < 0)
- die("unable to open %s (%s)", name, strerror(errno));
- if (copy_fd(ifd, ofd))
- exit(1);
- close(ifd);
-
- snprintf(name, sizeof(name),
- "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx");
- ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
- if (ofd < 0)
- die("unable to open %s (%s)", name, strerror(errno));
- if (copy_fd(ifd_ix, ofd))
- exit(1);
- close(ifd_ix);
- puts(sha1_to_hex(sha1));
- }
+ get_object_details();
- return 1;
-}
+ if (!window || !depth)
+ return;
-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);
+ delta_list = xmalloc(nr_objects * sizeof(*delta_list));
+ for (i = 0; i < nr_objects; i++)
+ delta_list[i] = objects + i;
+ qsort(delta_list, nr_objects, sizeof(*delta_list), type_size_sort);
+ find_deltas(delta_list, window+1, depth);
+ free(delta_list);
}
static int git_pack_config(const char *k, const char *v)
window = git_config_int(k, v);
return 0;
}
+ if (!strcmp(k, "pack.windowmemory")) {
+ window_memory_limit = git_config_ulong(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;
+ }
+ if (!strcmp(k, "pack.deltacachesize")) {
+ max_delta_cache_size = git_config_int(k, v);
+ return 0;
+ }
+ if (!strcmp(k, "pack.deltacachelimit")) {
+ cache_max_small_delta_size = git_config_int(k, v);
+ return 0;
+ }
return git_default_config(k, v);
}
{
char line[40 + 1 + PATH_MAX + 2];
unsigned char sha1[20];
- unsigned hash;
for (;;) {
if (!fgets(line, sizeof(line), stdin)) {
if (get_sha1_hex(line, sha1))
die("expected sha1, got garbage:\n %s", line);
- hash = name_hash(line+41);
- add_preferred_base_object(line+41, hash);
- add_object_entry(sha1, hash, 0);
+ add_preferred_base_object(line+41);
+ add_object_entry(sha1, 0, line+41, 0);
}
}
static void show_commit(struct commit *commit)
{
- unsigned hash = name_hash("");
- add_preferred_base_object("", hash);
- add_object_entry(commit->object.sha1, hash, 0);
+ add_object_entry(commit->object.sha1, OBJ_COMMIT, NULL, 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_preferred_base_object(p->name);
+ add_object_entry(p->item->sha1, p->item->type, p->name, 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)
{
- SHA_CTX ctx;
- int depth = 10;
- struct object_entry **list;
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, "--max-pack-size=")) {
+ char *end;
+ pack_size_limit = strtoul(arg+16, &end, 0) * 1024 * 1024;
+ if (!arg[16] || *end)
+ usage(pack_usage);
+ continue;
+ }
if (!prefixcmp(arg, "--window=")) {
char *end;
window = strtoul(arg+9, &end, 0);
usage(pack_usage);
continue;
}
+ if (!prefixcmp(arg, "--window-memory=")) {
+ if (!git_parse_ulong(arg+16, &window_memory_limit))
+ usage(pack_usage);
+ continue;
+ }
if (!prefixcmp(arg, "--depth=")) {
char *end;
depth = strtoul(arg+8, &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;
rp_av[1] = "--objects-edge";
continue;
}
+ if (!prefixcmp(arg, "--index-version=")) {
+ char *c;
+ pack_idx_default_version = strtoul(arg + 16, &c, 10);
+ if (pack_idx_default_version > 2)
+ die("bad %s", arg);
+ if (*c == ',')
+ pack_idx_off32_limit = strtoul(c+1, &c, 0);
+ if (*c || pack_idx_off32_limit & 0x80000000)
+ die("bad %s", arg);
+ continue;
+ }
usage(pack_usage);
}
if (pack_to_stdout != !base_name)
usage(pack_usage);
+ if (pack_to_stdout && pack_size_limit)
+ die("--max-pack-size cannot be used to build a pack for transfer.");
+
if (!pack_to_stdout && thin)
die("--thin cannot be used to build an indexable pack.");
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);
- sorted_by_sha = create_final_object_list();
+ }
+
if (non_empty && !nr_result)
return 0;
-
- SHA1_Init(&ctx);
- list = sorted_by_sha;
- for (i = 0; i < nr_result; i++) {
- struct object_entry *entry = *list++;
- SHA1_Update(&ctx, entry->sha1, 20);
- }
- SHA1_Final(object_list_sha1, &ctx);
if (progress && (nr_objects != nr_result))
fprintf(stderr, "Result has %u objects.\n", nr_result);
-
- if (reuse_cached_pack(object_list_sha1))
- ;
- else {
- 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;
- }
- write_pack_file();
- if (!pack_to_stdout) {
- write_index_file();
- puts(sha1_to_hex(object_list_sha1));
- }
- }
+ if (nr_result)
+ prepare_pack(window, depth);
+ write_pack_file();
if (progress)
fprintf(stderr, "Total %u (delta %u), reused %u (delta %u)\n",
written, written_delta, reused, reused_delta);