diff options
Diffstat (limited to 'builtin-pack-objects.c')
| -rw-r--r-- | builtin-pack-objects.c | 2216 |
1 files changed, 1417 insertions, 799 deletions
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c index 45ac3e482a..ef4bf6bc14 100644 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "attr.h" #include "object.h" #include "blob.h" #include "commit.h" @@ -7,43 +8,52 @@ #include "tree.h" #include "delta.h" #include "pack.h" +#include "pack-revindex.h" #include "csum-file.h" #include "tree-walk.h" #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "progress.h" +#include "refs.h" + +#ifdef THREADED_DELTA_SEARCH +#include "thread-utils.h" +#include <pthread.h> +#endif 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\ +git pack-objects [{ -q | --progress | --all-progress }] \n\ + [--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\ + [--threads=N] [--non-empty] [--revs [--unpacked | --all]*] [--reflog] \n\ + [--stdout | base-name] [--include-tag] \n\ + [--keep-unreachable | --unpack-unreachable] \n\ [<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 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 */ + 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; }; /* @@ -51,196 +61,96 @@ struct object_entry { * 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 pack_idx_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 reuse_delta = 1, reuse_object = 1; +static int keep_unreachable, unpack_unreachable, include_tag; static int local; static int incremental; +static int ignore_packed_keep; 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 *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, pack_size_limit_cfg; +static int depth = 50; +static int delta_search_threads; 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_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 int object_ix_hashsz; /* - * Pack index for existing packs give us easy access to the offsets into - * corresponding pack file where each object's data starts, but the entries - * do not store the size of the compressed representation (uncompressed - * size is easily available by examining the pack entry header). It is - * also rather expensive to find the sha1 for an object given its offset. - * - * We build a hashtable of existing packs (pack_revindex), and keep reverse - * index here -- pack index file is sorted by object name mapping to offset; - * this pack_revindex[].revindex array is a list of offset/index_nr pairs - * ordered by offset, so if you know the offset of an object, next offset - * is where its packed representation ends and the index_nr can be used to - * get the object sha1 from the main index. - */ -struct revindex_entry { - off_t offset; - unsigned int nr; -}; -struct pack_revindex { - struct packed_git *p; - struct revindex_entry *revindex; -}; -static struct pack_revindex *pack_revindex; -static int pack_revindex_hashsz; - -/* * stats */ static uint32_t written, written_delta; static uint32_t reused, reused_delta; -static int pack_revindex_ix(struct packed_git *p) -{ - unsigned long ui = (unsigned long)p; - int i; - ui = ui ^ (ui >> 16); /* defeat structure alignment */ - i = (int)(ui % pack_revindex_hashsz); - while (pack_revindex[i].p) { - if (pack_revindex[i].p == p) - return i; - if (++i == pack_revindex_hashsz) - i = 0; - } - return -1 - i; -} - -static void prepare_pack_ix(void) +static void *get_delta(struct object_entry *entry) { - int num; - struct packed_git *p; - for (num = 0, p = packed_git; p; p = p->next) - num++; - if (!num) - return; - pack_revindex_hashsz = num * 11; - pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz); - for (p = packed_git; p; p = p->next) { - num = pack_revindex_ix(p); - num = - 1 - num; - pack_revindex[num].p = p; - } - /* revindex elements are lazily initialized */ -} - -static int cmp_offset(const void *a_, const void *b_) -{ - const struct revindex_entry *a = a_; - const struct revindex_entry *b = b_; - return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0; -} - -/* - * Ordered list of offsets of objects in the pack. - */ -static void prepare_pack_revindex(struct pack_revindex *rix) -{ - struct packed_git *p = rix->p; - int num_ent = num_packed_objects(p); - int i; - const char *index = p->index_data; + unsigned long size, base_size, delta_size; + void *buf, *base_buf, *delta_buf; + enum object_type type; - 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; - } - /* This knows the pack format -- the 20-byte trailer - * follows immediately after the last object data. - */ - rix->revindex[num_ent].offset = p->pack_size - 20; - rix->revindex[num_ent].nr = -1; - qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset); + buf = read_sha1_file(entry->idx.sha1, &type, &size); + if (!buf) + die("unable to read %s", sha1_to_hex(entry->idx.sha1)); + base_buf = read_sha1_file(entry->delta->idx.sha1, &type, &base_size); + if (!base_buf) + die("unable to read %s", sha1_to_hex(entry->delta->idx.sha1)); + delta_buf = diff_delta(base_buf, base_size, + buf, size, &delta_size, 0); + if (!delta_buf || delta_size != entry->delta_size) + die("delta size changed"); + free(buf); + free(base_buf); + return delta_buf; } -static struct revindex_entry * find_packed_object(struct packed_git *p, - off_t ofs) +static unsigned long do_compress(void **pptr, unsigned long size) { - int num; - int lo, hi; - struct pack_revindex *rix; - struct revindex_entry *revindex; - num = pack_revindex_ix(p); - if (num < 0) - die("internal error: pack revindex uninitialized"); - rix = &pack_revindex[num]; - if (!rix->revindex) - prepare_pack_revindex(rix); - revindex = rix->revindex; - lo = 0; - hi = num_packed_objects(p) + 1; - do { - int mi = (lo + hi) / 2; - if (revindex[mi].offset == ofs) { - return revindex + mi; - } - else if (ofs < revindex[mi].offset) - hi = mi; - else - lo = mi + 1; - } while (lo < hi); - die("internal error: pack revindex corrupt"); -} + z_stream stream; + void *in, *out; + unsigned long maxsize; -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; -} + memset(&stream, 0, sizeof(stream)); + deflateInit(&stream, pack_compression_level); + maxsize = deflateBound(&stream, size); -static const unsigned char *find_packed_object_name(struct packed_git *p, - off_t ofs) -{ - struct revindex_entry *entry = find_packed_object(p, ofs); - return nth_packed_object_sha1(p, entry->nr); -} + in = *pptr; + out = xmalloc(maxsize); + *pptr = out; -static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) -{ - unsigned long othersize, delta_size; - enum object_type type; - void *otherbuf = read_sha1_file(entry->delta->sha1, &type, &othersize); - void *delta_buf; + 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); - if (!otherbuf) - die("unable to read %s", sha1_to_hex(entry->delta->sha1)); - delta_buf = diff_delta(otherbuf, othersize, - buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) - die("delta size changed"); - free(buf); - free(otherbuf); - return delta_buf; + free(in); + return stream.total_out; } /* @@ -285,16 +195,16 @@ static int check_pack_inflate(struct packed_git *p, int st; memset(&stream, 0, sizeof(stream)); - inflateInit(&stream); + git_inflate_init(&stream); do { in = use_pack(p, w_curs, offset, &stream.avail_in); stream.next_in = in; stream.next_out = fakebuf; stream.avail_out = sizeof(fakebuf); - st = inflate(&stream, Z_FINISH); + st = git_inflate(&stream, Z_FINISH); offset += stream.next_in - in; } while (st == Z_OK || st == Z_BUF_ERROR); - inflateEnd(&stream); + git_inflate_end(&stream); return (st == Z_STREAM_END && stream.total_out == expect && stream.total_in == len) ? 0 : -1; @@ -319,74 +229,54 @@ static void copy_pack_data(struct sha1file *f, } } -static int check_loose_inflate(unsigned char *data, unsigned long len, unsigned long expect) +static unsigned long write_object(struct sha1file *f, + struct object_entry *entry, + off_t write_offset) { - 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. */ + unsigned long size, limit, datalen; + void *buf; + unsigned char header[10], dheader[10]; + unsigned hdrlen; enum object_type type; - unsigned long size, used; + int usable_delta, to_reuse; - if (pack_to_stdout) - return 0; + if (!pack_to_stdout) + crc32_begin(f); - used = unpack_object_header_gently(map, mapsize, &type, &size); - if (!used) - return -1; - map += used; - mapsize -= used; - return check_loose_inflate(map, mapsize, size); -} + type = entry->type; -static off_t write_object(struct sha1file *f, - struct object_entry *entry) -{ - unsigned long size; - enum object_type type; - void *buf; - unsigned char header[10]; - unsigned hdrlen; - off_t datalen; - enum object_type obj_type; - int to_reuse = 0; + /* write limit if limited packsize and not first object */ + if (!pack_size_limit || !nr_written) + limit = 0; + else if (pack_size_limit <= write_offset) + /* + * the earlier object did not fit the limit; avoid + * mistaking this with unlimited (i.e. limit = 0). + */ + limit = 1; + else + limit = pack_size_limit - write_offset; - obj_type = entry->type; - if (! entry->in_pack) + if (!entry->delta) + usable_delta = 0; /* no delta */ + else if (!pack_size_limit) + usable_delta = 1; /* unlimited packfile */ + else if (entry->delta->idx.offset == (off_t)-1) + usable_delta = 0; /* base was written to another pack */ + else if (entry->delta->idx.offset) + usable_delta = 1; /* base already exists in this pack */ + else + usable_delta = 0; /* base could end up in another pack */ + + if (!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 */ - else if (obj_type != entry->in_pack_type) + else if (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA) + /* check_object() decided it for us ... */ + to_reuse = usable_delta; + /* ... but pack split may override that */ + else if (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 */ @@ -395,211 +285,319 @@ static off_t write_object(struct sha1file *f, * 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) { - buf = delta_against(buf, size, entry); + no_reuse: + 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 occurred. + */ + free(entry->delta_data); + entry->delta_data = NULL; + entry->z_delta_size = 0; + } else if (entry->delta_data) { size = entry->delta_size; - obj_type = (allow_ofs_delta && entry->delta->offset) ? + buf = entry->delta_data; + entry->delta_data = NULL; + type = (allow_ofs_delta && entry->delta->idx.offset) ? + OBJ_OFS_DELTA : OBJ_REF_DELTA; + } else { + buf = get_delta(entry); + size = entry->delta_size; + type = (allow_ofs_delta && entry->delta->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } + + 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 * more bytes of length. */ - hdrlen = encode_header(obj_type, size, header); - sha1write(f, header, hdrlen); + hdrlen = encode_header(type, size, header); - if (obj_type == OBJ_OFS_DELTA) { + if (type == OBJ_OFS_DELTA) { /* * Deltas with relative base contain an additional * 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; - } else if (obj_type == OBJ_REF_DELTA) { + dheader[--pos] = 128 | (--ofs & 127); + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + free(buf); + return 0; + } + sha1write(f, header, hdrlen); + sha1write(f, dheader + pos, sizeof(dheader) - pos); + hdrlen += sizeof(dheader) - pos; + } else if (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(buf); + return 0; + } + sha1write(f, header, hdrlen); + sha1write(f, entry->delta->idx.sha1, 20); hdrlen += 20; + } else { + if (limit && hdrlen + datalen + 20 >= limit) { + free(buf); + return 0; + } + sha1write(f, header, hdrlen); } - datalen = sha1write_compressed(f, buf, size); + sha1write(f, buf, datalen); 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) ? + if (entry->delta) + type = (allow_ofs_delta && entry->delta->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; - reused_delta++; + hdrlen = encode_header(type, entry->size, header); + + offset = entry->in_pack_offset; + revidx = find_pack_revindex(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)) { + error("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1)); + unuse_pack(&w_curs); + goto no_reuse; + } + + offset += entry->in_pack_header_size; + datalen -= entry->in_pack_header_size; + if (!pack_to_stdout && p->index_version == 1 && + check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { + error("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1)); + unuse_pack(&w_curs); + goto no_reuse; } - hdrlen = encode_header(obj_type, entry->size, header); - sha1write(f, header, hdrlen); - if (obj_type == OBJ_OFS_DELTA) { - off_t ofs = entry->offset - entry->delta->offset; - unsigned pos = sizeof(header) - 1; - header[pos] = ofs & 127; + + if (type == OBJ_OFS_DELTA) { + 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; - } else if (obj_type == OBJ_REF_DELTA) { - sha1write(f, entry->delta->sha1, 20); + dheader[--pos] = 128 | (--ofs & 127); + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + unuse_pack(&w_curs); + return 0; + } + sha1write(f, header, hdrlen); + sha1write(f, dheader + pos, sizeof(dheader) - pos); + hdrlen += sizeof(dheader) - pos; + reused_delta++; + } else if (type == OBJ_REF_DELTA) { + if (limit && hdrlen + 20 + datalen + 20 >= limit) { + unuse_pack(&w_curs); + return 0; + } + sha1write(f, header, hdrlen); + sha1write(f, entry->delta->idx.sha1, 20); hdrlen += 20; + reused_delta++; + } else { + if (limit && hdrlen + datalen + 20 >= limit) { + unuse_pack(&w_curs); + 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)); 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; } -static off_t write_one(struct sha1file *f, +static int write_one(struct sha1file *f, struct object_entry *e, - off_t offset) + off_t *offset) { - if (e->offset || e->preferred_base) - /* offset starts from header size and cannot be zero - * if it is written already. - */ - return offset; - /* if we are deltified, write out its base object first. */ - if (e->delta) - offset = write_one(f, e->delta, offset); - e->offset = offset; - return offset + write_object(f, e); + unsigned long size; + + /* offset is non zero if object is written already. */ + if (e->idx.offset || e->preferred_base) + return 1; + + /* if we are deltified, write out base object first. */ + if (e->delta && !write_one(f, e->delta, 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->idx; + + /* make sure off_t is sufficiently large not to wrap */ + if (*offset > *offset + size) + die("pack too large for current definition of off_t"); + *offset += size; + return 1; } +/* 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; struct pack_header hdr; - unsigned last_percent = 999; - int do_progress = progress; + uint32_t nr_remaining = nr_result; + time_t last_mtime = 0; - 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); + if (progress > pack_to_stdout) + progress_state = start_progress("Writing objects", nr_result); + written_list = xmalloc(nr_objects * sizeof(*written_list)); - 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); -} + do { + unsigned char sha1[20]; + char *pack_tmp_name = NULL; -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]; + if (pack_to_stdout) { + f = sha1fd_throughput(1, "<stdout>", progress_state); + } else { + char tmpname[PATH_MAX]; + int fd; + fd = odb_mkstemp(tmpname, sizeof(tmpname), + "pack/tmp_pack_XXXXXX"); + 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++) { + if (!write_one(f, objects + i, &offset)) break; - next++; + display_progress(progress_state, written); + } + + /* + * Did we write the wrong # entries in the header? + * If so, rewrite it like in fast-import + */ + 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, sha1, 0); + fixup_pack_header_footer(fd, sha1, pack_tmp_name, + nr_written, sha1, offset); + close(fd); + } + + if (!pack_to_stdout) { + mode_t mode = umask(0); + struct stat st; + char *idx_tmp_name, tmpname[PATH_MAX]; + + umask(mode); + mode = 0444 & ~mode; + + idx_tmp_name = write_idx_file(NULL, written_list, + nr_written, sha1); + + snprintf(tmpname, sizeof(tmpname), "%s-%s.pack", + base_name, sha1_to_hex(sha1)); + free_pack_by_name(tmpname); + if (adjust_perm(pack_tmp_name, mode)) + die_errno("unable to make temporary pack file readable"); + if (rename(pack_tmp_name, tmpname)) + die_errno("unable to rename temporary pack file"); + + /* + * Packs are runtime accessed in their mtime + * order since newer packs are more likely to contain + * younger objects. So if we are creating multiple + * packs then we should modify the mtime of later ones + * to preserve this property. + */ + if (stat(tmpname, &st) < 0) { + warning("failed to stat %s: %s", + tmpname, strerror(errno)); + } else if (!last_mtime) { + last_mtime = st.st_mtime; + } else { + struct utimbuf utb; + utb.actime = st.st_atime; + utb.modtime = --last_mtime; + if (utime(tmpname, &utb) < 0) + warning("failed utime() on %s: %s", + tmpname, strerror(errno)); + } + + snprintf(tmpname, sizeof(tmpname), "%s-%s.idx", + base_name, sha1_to_hex(sha1)); + if (adjust_perm(idx_tmp_name, mode)) + die_errno("unable to make temporary index file readable"); + if (rename(idx_tmp_name, tmpname)) + die_errno("unable to rename temporary index file"); + + free(idx_tmp_name); + free(pack_tmp_name); + puts(sha1_to_hex(sha1)); } - array[i] = htonl(next - sorted_by_sha); - list = next; - } - sha1write(f, array, 256 * 4); + /* mark written objects as written to previous pack */ + for (j = 0; j < nr_written; j++) { + written_list[j]->offset = (off_t)-1; + } + nr_remaining -= nr_written; + } while (nr_remaining && i < nr_objects); + + free(written_list); + stop_progress(&progress_state); + if (written != nr_result) + die("wrote %"PRIu32" objects while expecting %"PRIu32, + 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 %"PRIu32" objects as expected but %"PRIu32 + " unwritten", written, j); } static int locate_object_entry_hash(const unsigned char *sha1) @@ -609,7 +607,7 @@ 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; @@ -641,7 +639,7 @@ static void rehash_objects(void) 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; @@ -651,8 +649,10 @@ static void rehash_objects(void) static unsigned name_hash(const char *name) { - unsigned char c; - unsigned hash = 0; + unsigned c, hash = 0; + + if (!name) + return 0; /* * This effectively just creates a sortable number from the @@ -667,67 +667,100 @@ static unsigned name_hash(const char *name) 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; + int ix; + unsigned hash = name_hash(name); - 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; - } + 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; + } + + if (!exclude && local && has_loose_object_nonlocal(sha1)) + 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 (ignore_packed_keep && p->pack_local && p->pack_keep) + 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; + display_progress(progress_state, nr_objects); + + if (name && no_try_delta(name)) + entry->no_try_delta = 1; + + return 1; } struct pbase_tree_cache { @@ -849,22 +882,24 @@ static void add_pbase_object(struct tree_desc *tree, 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) + if (S_ISGITLINK(entry.mode)) + continue; + 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, + object_type(entry.mode), + 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; @@ -921,18 +956,19 @@ static int check_pbase_path(unsigned hash) 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; @@ -974,222 +1010,254 @@ static void add_preferred_base(unsigned char *sha1) 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); + used = unpack_object_header_buffer(buf, avail, + &entry->in_pack_type, + &entry->size); + if (used == 0) + goto give_up; - /* 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 || 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); + 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; + if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + goto give_up; + unuse_pack(&w_curs); + return; + case OBJ_REF_DELTA: + if (reuse_delta && !entry->preferred_base) + base_ref = use_pack(p, &w_curs, + entry->in_pack_offset + used, NULL); + entry->in_pack_header_size = used + 20; + 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)) { + error("delta base offset overflow in pack for %s", + sha1_to_hex(entry->idx.sha1)); + goto give_up; } - 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; + c = buf[used_0++]; + ofs = (ofs << 7) + (c & 127); + } + ofs = entry->in_pack_offset - ofs; + if (ofs <= 0 || ofs >= entry->in_pack_offset) { + error("delta base offset out of bound for %s", + sha1_to_hex(entry->idx.sha1)); + goto give_up; + } + if (reuse_delta && !entry->preferred_base) { + struct revindex_entry *revidx; + revidx = find_pack_revindex(p, ofs); + if (!revidx) + goto give_up; + base_ref = nth_packed_object_sha1(p, revidx->nr); } - if (base_name) - base_entry = locate_object_entry(base_name); + 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_size = entry->size; entry->delta_sibling = base_entry->delta_child; base_entry->delta_child = entry; - + unuse_pack(&w_curs); return; } - /* Otherwise we would do the usual */ - } - - entry->type = sha1_object_info(entry->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; -} -static void get_object_details(void) -{ - uint32_t i; - struct object_entry *entry; - - prepare_pack_ix(); - for (i = 0, entry = objects; i < nr_objects; i++, entry++) - check_object(entry); + 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); + if (entry->size == 0) + goto give_up; + unuse_pack(&w_curs); + return; + } - 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. + * No choice but to fall back to the recursive delta walk + * with sha1_object_info() to find about the object type + * at this point... */ - for (i = 0, entry = objects; i < nr_objects; i++, entry++) - if (!entry->delta && entry->delta_child) - entry->delta_limit = - check_delta_limit(entry, 1); + give_up: + unuse_pack(&w_curs); } + + entry->type = sha1_object_info(entry->idx.sha1, &entry->size); + /* + * The error condition is checked in prepare_pack(). This is + * to permit a missing preferred base object to be ignored + * as a preferred base. Doing so can result in a larger + * pack file, but the transfer will still take place. + */ } -typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); +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; -static entry_sort_t current_sort; + /* avoid filesystem trashing with loose objects */ + if (!a->in_pack && !b->in_pack) + return hashcmp(a->idx.sha1, b->idx.sha1); -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); -} - -static struct object_entry **create_final_object_list(void) -{ - struct object_entry **list; - uint32_t i, j; + for (i = 0; i < nr_objects; i++) + check_object(sorted_by_offset[i]); - 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; + free(sorted_by_offset); } -static int type_size_sort(const struct object_entry *a, const struct object_entry *b) +/* + * We search for deltas in a list sorted by type, by filename hash, and then + * by size, so that we see progressively smaller and smaller files. + * That's because we prefer deltas to be from the bigger file + * to the smaller -- deletes are potentially cheaper, but perhaps + * more importantly, the bigger file is likely the more recent + * one. The deepest deltas are therefore the oldest objects which are + * less susceptible to be accessed often. + */ +static int type_size_sort(const void *_a, const void *_b) { - if (a->type < b->type) - return -1; + const struct object_entry *a = *(struct object_entry **)_a; + const struct object_entry *b = *(struct object_entry **)_b; + if (a->type > b->type) - return 1; - if (a->hash < b->hash) return -1; - if (a->hash > b->hash) + if (a->type < b->type) return 1; - if (a->preferred_base < b->preferred_base) + if (a->hash > b->hash) return -1; - if (a->preferred_base > b->preferred_base) + if (a->hash < b->hash) return 1; - if (a->size < b->size) + if (a->preferred_base > b->preferred_base) return -1; + if (a->preferred_base < b->preferred_base) + return 1; if (a->size > b->size) + return -1; + if (a->size < b->size) return 1; - return a < b ? -1 : (a > b); + return a < b ? -1 : (a > b); /* newest first */ } struct unpacked { struct object_entry *entry; void *data; struct delta_index *index; + unsigned depth; }; -/* - * We search for deltas _backwards_ in a list sorted by type and - * by size, so that we see progressively smaller and smaller files. - * That's because we prefer deltas to be from the bigger file - * to the smaller - deletes are potentially cheaper, but perhaps - * more importantly, the bigger file is likely the more recent - * one. - */ +static int delta_cacheable(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; +} + +#ifdef THREADED_DELTA_SEARCH + +static pthread_mutex_t read_mutex = PTHREAD_MUTEX_INITIALIZER; +#define read_lock() pthread_mutex_lock(&read_mutex) +#define read_unlock() pthread_mutex_unlock(&read_mutex) + +static pthread_mutex_t cache_mutex = PTHREAD_MUTEX_INITIALIZER; +#define cache_lock() pthread_mutex_lock(&cache_mutex) +#define cache_unlock() pthread_mutex_unlock(&cache_mutex) + +static pthread_mutex_t progress_mutex = PTHREAD_MUTEX_INITIALIZER; +#define progress_lock() pthread_mutex_lock(&progress_mutex) +#define progress_unlock() pthread_mutex_unlock(&progress_mutex) + +#else + +#define read_lock() (void)0 +#define read_unlock() (void)0 +#define cache_lock() (void)0 +#define cache_unlock() (void)0 +#define progress_lock() (void)0 +#define progress_unlock() (void)0 + +#endif + static int try_delta(struct unpacked *trg, struct unpacked *src, - unsigned max_depth) + unsigned max_depth, unsigned long *mem_usage) { 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; @@ -1197,131 +1265,203 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, if (trg_entry->type != src_entry->type) return -1; - /* We do not compute delta to *create* objects we are not - * going to pack. - */ - if (trg_entry->preferred_base) - return -1; - /* * We do not bother to try a delta that we discarded * on an earlier try, but only when reusing delta data. */ - if (!no_reuse_delta && trg_entry->in_pack && + if (reuse_delta && trg_entry->in_pack && trg_entry->in_pack == src_entry->in_pack && trg_entry->in_pack_type != OBJ_REF_DELTA && 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 = (uint64_t)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); + read_lock(); + trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz); + read_unlock(); + if (!trg->data) + die("object %s cannot be read", + sha1_to_hex(trg_entry->idx.sha1)); 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); + *mem_usage += sz; } if (!src->data) { - src->data = read_sha1_file(src_entry->sha1, &type, &sz); + read_lock(); + src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz); + read_unlock(); + if (!src->data) + die("object %s cannot be read", + sha1_to_hex(src_entry->idx.sha1)); 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); + *mem_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; + } + *mem_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) { + /* Prefer only shallower same-sized deltas. */ + if (delta_size == trg_entry->delta_size && + src->depth + 1 >= trg->depth) { + free(delta_buf); + return 0; + } + } + + /* + * Handle memory allocation outside of the cache + * accounting lock. Compiler will optimize the strangeness + * away when THREADED_DELTA_SEARCH is not defined. + */ + free(trg_entry->delta_data); + cache_lock(); + if (trg_entry->delta_data) { + delta_cache_size -= trg_entry->delta_size; + trg_entry->delta_data = NULL; + } + if (delta_cacheable(src_size, trg_size, delta_size)) { + delta_cache_size += delta_size; + cache_unlock(); + trg_entry->delta_data = xrealloc(delta_buf, delta_size); + } else { + cache_unlock(); + free(delta_buf); + } + 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; + 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 unsigned long free_unpacked(struct unpacked *n) +{ + unsigned long freed_mem = sizeof_delta_index(n->index); + free_delta_index(n->index); + n->index = NULL; + if (n->data) { + freed_mem += n->entry->size; + free(n->data); + n->data = NULL; + } + n->entry = NULL; + n->depth = 0; + return freed_mem; } -static void find_deltas(struct object_entry **list, int window, int depth) +static void find_deltas(struct object_entry **list, unsigned *list_size, + int window, int depth, unsigned *processed) { - uint32_t i = nr_objects, idx = 0, processed = 0; - unsigned int array_size = window * sizeof(struct unpacked); + uint32_t i, idx = 0, count = 0; struct unpacked *array; - unsigned last_percent = 999; + unsigned long mem_usage = 0; - if (!nr_objects) - return; - array = xmalloc(array_size); - memset(array, 0, array_size); - if (progress) - fprintf(stderr, "Deltifying %u objects.\n", nr_result); + array = xcalloc(window, sizeof(struct unpacked)); - do { - struct object_entry *entry = list[--i]; + for (;;) { + struct object_entry *entry; struct unpacked *n = array + idx; - int j; + int j, max_depth, best_base = -1; - if (!entry->preferred_base) - processed++; + progress_lock(); + if (!*list_size) { + progress_unlock(); + break; + } + entry = *list++; + (*list_size)--; + if (!entry->preferred_base) { + (*processed)++; + display_progress(progress_state, *processed); + } + progress_unlock(); - 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; - } + mem_usage -= free_unpacked(n); + n->entry = entry; + + while (window_memory_limit && + mem_usage > window_memory_limit && + count > 1) { + uint32_t tail = (idx + window - count) % window; + mem_usage -= free_unpacked(array + tail); + count--; } - if (entry->delta) - /* This happens if we decided to reuse existing - * delta from a pack. "!no_reuse_delta &&" is implied. - */ - continue; + /* We do not compute delta to *create* objects we are not + * going to pack. + */ + if (entry->preferred_base) + goto next; - if (entry->size < 50) - continue; - free_delta_index(n->index); - n->index = NULL; - free(n->data); - n->data = NULL; - n->entry = entry; + /* + * 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) { + int ret; uint32_t other_idx = idx + j; struct unpacked *m; if (other_idx >= window) @@ -1329,23 +1469,67 @@ static void find_deltas(struct object_entry **list, int window, int depth) m = array + other_idx; if (!m->entry) break; - if (try_delta(n, m, depth) < 0) + ret = try_delta(n, m, max_depth, &mem_usage); + if (ret < 0) break; + else if (ret > 0) + 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 <= entry->depth) + if (entry->delta && max_depth <= n->depth) continue; + /* + * Move the best delta base up in the window, after the + * currently deltified object, to keep it longer. It will + * be the first base object to be attempted next. + */ + if (entry->delta) { + struct unpacked swap = array[best_base]; + int dist = (window + idx - best_base) % window; + int dst = best_base; + while (dist--) { + int src = (dst + 1) % window; + array[dst] = array[src]; + dst = src; + } + array[dst] = swap; + } + + next: idx++; + if (count + 1 < window) + count++; if (idx >= window) idx = 0; - } while (i > 0); - - if (progress) - fputc('\n', stderr); + } for (i = 0; i < window; ++i) { free_delta_index(array[i].index); @@ -1354,99 +1538,335 @@ static void find_deltas(struct object_entry **list, int window, int depth) free(array); } -static void prepare_pack(int window, int depth) +#ifdef THREADED_DELTA_SEARCH + +/* + * The main thread waits on the condition that (at least) one of the workers + * has stopped working (which is indicated in the .working member of + * struct thread_params). + * When a work thread has completed its work, it sets .working to 0 and + * signals the main thread and waits on the condition that .data_ready + * becomes 1. + */ + +struct thread_params { + pthread_t thread; + struct object_entry **list; + unsigned list_size; + unsigned remaining; + int window; + int depth; + int working; + int data_ready; + pthread_mutex_t mutex; + pthread_cond_t cond; + unsigned *processed; +}; + +static pthread_cond_t progress_cond = PTHREAD_COND_INITIALIZER; + +static void *threaded_find_deltas(void *arg) { - get_object_details(); - sorted_by_type = create_sorted_list(type_size_sort); - if (window && depth) - find_deltas(sorted_by_type, window+1, depth); + struct thread_params *me = arg; + + while (me->remaining) { + find_deltas(me->list, &me->remaining, + me->window, me->depth, me->processed); + + progress_lock(); + me->working = 0; + pthread_cond_signal(&progress_cond); + progress_unlock(); + + /* + * We must not set ->data_ready before we wait on the + * condition because the main thread may have set it to 1 + * before we get here. In order to be sure that new + * work is available if we see 1 in ->data_ready, it + * was initialized to 0 before this thread was spawned + * and we reset it to 0 right away. + */ + pthread_mutex_lock(&me->mutex); + while (!me->data_ready) + pthread_cond_wait(&me->cond, &me->mutex); + me->data_ready = 0; + pthread_mutex_unlock(&me->mutex); + } + /* leave ->working 1 so that this doesn't get more work assigned */ + return NULL; } -static int reuse_cached_pack(unsigned char *sha1) +static void ll_find_deltas(struct object_entry **list, unsigned list_size, + int window, int depth, unsigned *processed) { - 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; + struct thread_params p[delta_search_threads]; + int i, ret, active_threads = 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 (delta_search_threads <= 1) { + find_deltas(list, &list_size, window, depth, processed); + return; } + if (progress > pack_to_stdout) + fprintf(stderr, "Delta compression using up to %d threads.\n", + delta_search_threads); - if (progress) - fprintf(stderr, "Reusing %u objects pack %s\n", nr_objects, - sha1_to_hex(sha1)); + /* Partition the work amongst work threads. */ + for (i = 0; i < delta_search_threads; i++) { + unsigned sub_size = list_size / (delta_search_threads - i); - if (pack_to_stdout) { - if (copy_fd(ifd, 1)) - exit(1); - close(ifd); + /* don't use too small segments or no deltas will be found */ + if (sub_size < 2*window && i+1 < delta_search_threads) + sub_size = 0; + + p[i].window = window; + p[i].depth = depth; + p[i].processed = processed; + p[i].working = 1; + p[i].data_ready = 0; + + /* try to split chunks on "path" boundaries */ + while (sub_size && sub_size < list_size && + list[sub_size]->hash && + list[sub_size]->hash == list[sub_size-1]->hash) + sub_size++; + + p[i].list = list; + p[i].list_size = sub_size; + p[i].remaining = sub_size; + + list += sub_size; + list_size -= sub_size; } - 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)); + /* Start work threads. */ + for (i = 0; i < delta_search_threads; i++) { + if (!p[i].list_size) + continue; + pthread_mutex_init(&p[i].mutex, NULL); + pthread_cond_init(&p[i].cond, NULL); + ret = pthread_create(&p[i].thread, NULL, + threaded_find_deltas, &p[i]); + if (ret) + die("unable to create thread: %s", strerror(ret)); + active_threads++; } - return 1; + /* + * Now let's wait for work completion. Each time a thread is done + * with its work, we steal half of the remaining work from the + * thread with the largest number of unprocessed objects and give + * it to that newly idle thread. This ensure good load balancing + * until the remaining object list segments are simply too short + * to be worth splitting anymore. + */ + while (active_threads) { + struct thread_params *target = NULL; + struct thread_params *victim = NULL; + unsigned sub_size = 0; + + progress_lock(); + for (;;) { + for (i = 0; !target && i < delta_search_threads; i++) + if (!p[i].working) + target = &p[i]; + if (target) + break; + pthread_cond_wait(&progress_cond, &progress_mutex); + } + + for (i = 0; i < delta_search_threads; i++) + if (p[i].remaining > 2*window && + (!victim || victim->remaining < p[i].remaining)) + victim = &p[i]; + if (victim) { + sub_size = victim->remaining / 2; + list = victim->list + victim->list_size - sub_size; + while (sub_size && list[0]->hash && + list[0]->hash == list[-1]->hash) { + list++; + sub_size--; + } + if (!sub_size) { + /* + * It is possible for some "paths" to have + * so many objects that no hash boundary + * might be found. Let's just steal the + * exact half in that case. + */ + sub_size = victim->remaining / 2; + list -= sub_size; + } + target->list = list; + victim->list_size -= sub_size; + victim->remaining -= sub_size; + } + target->list_size = sub_size; + target->remaining = sub_size; + target->working = 1; + progress_unlock(); + + pthread_mutex_lock(&target->mutex); + target->data_ready = 1; + pthread_cond_signal(&target->cond); + pthread_mutex_unlock(&target->mutex); + + if (!sub_size) { + pthread_join(target->thread, NULL); + pthread_cond_destroy(&target->cond); + pthread_mutex_destroy(&target->mutex); + active_threads--; + } + } } -static void setup_progress_signal(void) +#else +#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p) +#endif + +static int add_ref_tag(const char *path, const unsigned char *sha1, int flag, void *cb_data) { - struct sigaction sa; - struct itimerval v; + unsigned char peeled[20]; + + if (!prefixcmp(path, "refs/tags/") && /* is a tag? */ + !peel_ref(path, peeled) && /* peelable? */ + !is_null_sha1(peeled) && /* annotated tag? */ + locate_object_entry(peeled)) /* object packed? */ + add_object_entry(sha1, OBJ_TAG, NULL, 0); + return 0; +} + +static void prepare_pack(int window, int depth) +{ + struct object_entry **delta_list; + uint32_t i, nr_deltas; + unsigned n; + + get_object_details(); + + /* + * If we're locally repacking then we need to be doubly careful + * from now on in order to make sure no stealth corruption gets + * propagated to the new pack. Clients receiving streamed packs + * should validate everything they get anyway so no need to incur + * the additional cost here in that case. + */ + if (!pack_to_stdout) + do_check_packed_object_crc = 1; + + if (!nr_objects || !window || !depth) + return; + + delta_list = xmalloc(nr_objects * sizeof(*delta_list)); + nr_deltas = n = 0; + + for (i = 0; i < nr_objects; i++) { + struct object_entry *entry = objects + i; + + if (entry->delta) + /* This happens if we decided to reuse existing + * delta from a pack. "reuse_delta &&" is implied. + */ + continue; + + if (entry->size < 50) + continue; + + if (entry->no_try_delta) + continue; + + if (!entry->preferred_base) { + nr_deltas++; + if (entry->type < 0) + die("unable to get type of object %s", + sha1_to_hex(entry->idx.sha1)); + } else { + if (entry->type < 0) { + /* + * This object is not found, but we + * don't have to include it anyway. + */ + continue; + } + } - memset(&sa, 0, sizeof(sa)); - sa.sa_handler = progress_interval; - sigemptyset(&sa.sa_mask); - sa.sa_flags = SA_RESTART; - sigaction(SIGALRM, &sa, NULL); + delta_list[n++] = entry; + } - v.it_interval.tv_sec = 1; - v.it_interval.tv_usec = 0; - v.it_value = v.it_interval; - setitimer(ITIMER_REAL, &v, NULL); + if (nr_deltas && n > 1) { + unsigned nr_done = 0; + if (progress) + progress_state = start_progress("Compressing objects", + nr_deltas); + qsort(delta_list, n, sizeof(*delta_list), type_size_sort); + ll_find_deltas(delta_list, n, window+1, depth, &nr_done); + stop_progress(&progress_state); + if (nr_done != nr_deltas) + die("inconsistency with delta count"); + } + 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); return 0; } - return git_default_config(k, v); + 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; + } + if (!strcmp(k, "pack.threads")) { + delta_search_threads = git_config_int(k, v); + if (delta_search_threads < 0) + die("invalid number of threads specified (%d)", + delta_search_threads); +#ifndef THREADED_DELTA_SEARCH + if (delta_search_threads != 1) + warning("no threads support, ignoring %s", k); +#endif + return 0; + } + if (!strcmp(k, "pack.indexversion")) { + pack_idx_default_version = git_config_int(k, v); + if (pack_idx_default_version > 2) + 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, cb); } static void read_object_list_from_stdin(void) { char line[40 + 1 + PATH_MAX + 2]; unsigned char sha1[20]; - unsigned hash; for (;;) { if (!fgets(line, sizeof(line), stdin)) { @@ -1455,7 +1875,7 @@ static void read_object_list_from_stdin(void) if (!ferror(stdin)) die("fgets returned NULL, not EOF, not error!"); if (errno != EINTR) - die("fgets: %s", strerror(errno)); + die_errno("fgets"); clearerr(stdin); continue; } @@ -1469,24 +1889,32 @@ static void read_object_list_from_stdin(void) 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) +#define OBJECT_ADDED (1u<<20) + +static void show_commit(struct commit *commit, void *data) { - 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); + commit->object.flags |= OBJECT_ADDED; } -static void show_object(struct object_array_entry *p) +static void show_object(struct object *obj, const struct name_path *path, const char *last) { - unsigned hash = name_hash(p->name); - add_preferred_base_object(p->name, hash); - add_object_entry(p->item->sha1, hash, 0); + char *name = path_name(path, last); + + add_preferred_base_object(name); + add_object_entry(obj->sha1, obj->type, name, 0); + obj->flags |= OBJECT_ADDED; + + /* + * We will have generated the hash from the name, + * but not saved a pointer to it - we can free it + */ + free((char *)name); } static void show_edge(struct commit *commit) @@ -1494,6 +1922,128 @@ static void show_edge(struct commit *commit) add_preferred_base(commit->object.sha1); } +struct in_pack_object { + off_t offset; + struct object *object; +}; + +struct in_pack { + int alloc; + int nr; + struct in_pack_object *array; +}; + +static void mark_in_pack_object(struct object *object, struct packed_git *p, struct in_pack *in_pack) +{ + in_pack->array[in_pack->nr].offset = find_pack_entry_one(object->sha1, p); + in_pack->array[in_pack->nr].object = object; + in_pack->nr++; +} + +/* + * Compare the objects in the offset order, in order to emulate the + * "git rev-list --objects" output that produced the pack originally. + */ +static int ofscmp(const void *a_, const void *b_) +{ + struct in_pack_object *a = (struct in_pack_object *)a_; + struct in_pack_object *b = (struct in_pack_object *)b_; + + if (a->offset < b->offset) + return -1; + else if (a->offset > b->offset) + return 1; + else + return hashcmp(a->object->sha1, b->object->sha1); +} + +static void add_objects_in_unpacked_packs(struct rev_info *revs) +{ + struct packed_git *p; + struct in_pack in_pack; + uint32_t i; + + memset(&in_pack, 0, sizeof(in_pack)); + + for (p = packed_git; p; p = p->next) { + const unsigned char *sha1; + struct object *o; + + if (!p->pack_local || p->pack_keep) + continue; + if (open_pack_index(p)) + die("cannot open pack index"); + + ALLOC_GROW(in_pack.array, + in_pack.nr + p->num_objects, + in_pack.alloc); + + for (i = 0; i < p->num_objects; i++) { + sha1 = nth_packed_object_sha1(p, i); + o = lookup_unknown_object(sha1); + if (!(o->flags & OBJECT_ADDED)) + mark_in_pack_object(o, p, &in_pack); + o->flags |= OBJECT_ADDED; + } + } + + if (in_pack.nr) { + qsort(in_pack.array, in_pack.nr, sizeof(in_pack.array[0]), + ofscmp); + for (i = 0; i < in_pack.nr; i++) { + struct object *o = in_pack.array[i].object; + add_object_entry(o->sha1, o->type, "", 0); + } + } + free(in_pack.array); +} + +static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) +{ + static struct packed_git *last_found = (void *)1; + struct packed_git *p; + + p = (last_found != (void *)1) ? last_found : packed_git; + + while (p) { + if ((!p->pack_local || p->pack_keep) && + find_pack_entry_one(sha1, p)) { + last_found = p; + return 1; + } + if (p == last_found) + p = packed_git; + else + p = p->next; + if (p == last_found) + p = p->next; + } + return 0; +} + +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) { + if (!p->pack_local || p->pack_keep) + 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) && + !has_sha1_pack_kept_or_nonlocal(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; @@ -1502,12 +2052,11 @@ static void get_object_list(int ac, const char **av) init_revisions(&revs, NULL); save_commit_buffer = 0; - track_object_refs = 0; setup_revisions(ac, av, &revs, NULL); while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); - if (line[len - 1] == '\n') + if (len && line[len - 1] == '\n') line[--len] = 0; if (!len) break; @@ -1522,16 +2071,26 @@ static void get_object_list(int ac, const char **av) die("bad revision '%s'", line); } - prepare_revision_walk(&revs); + if (prepare_revision_walk(&revs)) + die("revision walk setup failed"); mark_edges_uninteresting(revs.commits, &revs, show_edge); - traverse_commit_list(&revs, show_commit, show_object); + traverse_commit_list(&revs, show_commit, show_object, NULL); + + 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) +{ + 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; @@ -1545,7 +2104,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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; progress = isatty(2); for (i = 1; i < argc; i++) { @@ -1566,6 +2127,30 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) incremental = 1; continue; } + if (!strcmp("--honor-pack-keep", arg)) { + ignore_packed_keep = 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_cfg = 0; + 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); @@ -1573,6 +2158,23 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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, "--threads=")) { + char *end; + delta_search_threads = strtoul(arg+10, &end, 0); + if (!arg[10] || *end || delta_search_threads < 0) + usage(pack_usage); +#ifndef THREADED_DELTA_SEARCH + if (delta_search_threads != 1) + warning("no threads support, " + "ignoring %s", arg); +#endif + continue; + } if (!prefixcmp(arg, "--depth=")) { char *end; depth = strtoul(arg+8, &end, 0); @@ -1593,7 +2195,11 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) continue; } if (!strcmp("--no-reuse-delta", arg)) { - no_reuse_delta = 1; + reuse_delta = 0; + continue; + } + if (!strcmp("--no-reuse-object", arg)) { + reuse_object = reuse_delta = 0; continue; } if (!strcmp("--delta-base-offset", arg)) { @@ -1608,8 +2214,19 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) use_internal_rev_list = 1; continue; } + if (!strcmp("--keep-unreachable", arg)) { + keep_unreachable = 1; + continue; + } + if (!strcmp("--unpack-unreachable", arg)) { + unpack_unreachable = 1; + continue; + } + if (!strcmp("--include-tag", arg)) { + include_tag = 1; + continue; + } if (!strcmp("--unpacked", arg) || - !prefixcmp(arg, "--unpacked=") || !strcmp("--reflog", arg) || !strcmp("--all", arg)) { use_internal_rev_list = 1; @@ -1627,6 +2244,21 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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; + } + if (!strcmp(arg, "--keep-true-parents")) { + grafts_replace_parents = 0; + continue; + } usage(pack_usage); } @@ -1649,59 +2281,45 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (pack_to_stdout != !base_name) usage(pack_usage); + if (!pack_to_stdout && !pack_size_limit) + pack_size_limit = pack_size_limit_cfg; + + 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 (keep_unreachable && unpack_unreachable) + die("--keep-unreachable and --unpack-unreachable are incompatible."); - if (progress) { - fprintf(stderr, "Generating pack...\n"); - setup_progress_signal(); - } +#ifdef THREADED_DELTA_SEARCH + if (!delta_search_threads) /* --threads=0 means autodetect */ + delta_search_threads = online_cpus(); +#endif + + prepare_packed_git(); + if (progress) + progress_state = start_progress("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 (include_tag && nr_result) + for_each_ref(add_ref_tag, NULL); + stop_progress(&progress_state); - if (progress) - 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", + fprintf(stderr, "Total %"PRIu32" (delta %"PRIu32")," + " reused %"PRIu32" (delta %"PRIu32")\n", written, written_delta, reused, reused_delta); return 0; } |