#include "builtin.h" #include "cache.h" #include "object.h" #include "blob.h" #include "commit.h" #include "tag.h" #include "tree.h" #include "delta.h" #include "pack.h" #include "csum-file.h" #include "tree-walk.h" #include "diff.h" #include "revision.h" #include "list-objects.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\ [> 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) { 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 = p->num_objects; int i; const char *index = p->index_data; rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1)); 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. */ 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); } static struct revindex_entry * find_packed_object(struct packed_git *p, off_t ofs) { 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 = p->num_objects + 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"); } 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) { struct revindex_entry *entry = find_packed_object(p, ofs); return nth_packed_object_sha1(p, entry->nr); } 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; 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; } /* * The per-object header is a pretty dense thing, which is * - first byte: low four bits are "size", then three bits of "type", * and the high bit is "size continues". * - each byte afterwards: low seven bits are size continuation, * with the high bit being "size continues" */ static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr) { int n = 1; unsigned char c; if (type < OBJ_COMMIT || type > OBJ_REF_DELTA) die("bad type %d", type); c = (type << 4) | (size & 15); size >>= 4; while (size) { *hdr++ = c | 0x80; c = size & 0x7f; size >>= 7; n++; } *hdr = c; return n; } /* * we are going to reuse the existing object data as is. make * sure it is not corrupt. */ static int check_pack_inflate(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned long expect) { z_stream stream; unsigned char fakebuf[4096], *in; int st; memset(&stream, 0, sizeof(stream)); inflateInit(&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); offset += stream.next_in - in; } while (st == Z_OK || st == Z_BUF_ERROR); inflateEnd(&stream); return (st == Z_STREAM_END && stream.total_out == expect && stream.total_in == len) ? 0 : -1; } static void copy_pack_data(struct sha1file *f, struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len) { unsigned char *in; unsigned int avail; while (len) { in = use_pack(p, w_curs, offset, &avail); if (avail > len) avail = (unsigned int)len; sha1write(f, in, avail); offset += avail; len -= avail; } } static int check_loose_inflate(unsigned char *data, unsigned long len, unsigned long expect) { z_stream stream; unsigned char fakebuf[4096]; int st; memset(&stream, 0, sizeof(stream)); stream.next_in = data; stream.avail_in = len; stream.next_out = fakebuf; stream.avail_out = sizeof(fakebuf); inflateInit(&stream); while (1) { st = inflate(&stream, Z_FINISH); if (st == Z_STREAM_END || st == Z_OK) { st = (stream.total_out == expect && stream.total_in == len) ? 0 : -1; break; } if (st != Z_BUF_ERROR) { st = -1; break; } stream.next_out = fakebuf; stream.avail_out = sizeof(fakebuf); } inflateEnd(&stream); return st; } static int revalidate_loose_object(struct object_entry *entry, unsigned char *map, unsigned long mapsize) { /* we already know this is a loose object with new type header. */ enum object_type type; unsigned long size, used; if (pack_to_stdout) return 0; used = unpack_object_header_gently(map, mapsize, &type, &size); if (!used) return -1; map += used; mapsize -= used; return check_loose_inflate(map, mapsize, size); } static unsigned long write_object(struct sha1file *f, struct object_entry *entry) { 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; if (!pack_to_stdout) crc32_begin(f); obj_type = entry->type; 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) to_reuse = 0; /* pack has delta which is unusable */ else if (entry->delta) to_reuse = 0; /* we want to pack afresh */ else to_reuse = 1; /* we have it in-pack undeltified, * and we do not need to deltify it. */ if (!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); size = entry->delta_size; obj_type = (allow_ofs_delta && entry->delta->offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } /* * 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) { /* * 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; 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) { /* * Deltas with a base reference contain * an additional 20 bytes for the base sha1. */ sha1write(f, entry->delta->sha1, 20); hdrlen += 20; } datalen = sha1write_compressed(f, buf, size); free(buf); } else { struct packed_git *p = entry->in_pack; struct pack_window *w_curs = NULL; off_t offset; if (entry->delta) { obj_type = (allow_ofs_delta && entry->delta->offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; reused_delta++; } 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; 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); hdrlen += 20; } 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) written_delta++; written++; if (!pack_to_stdout) entry->crc32 = crc32_end(f); return hdrlen + datalen; } static off_t write_one(struct sha1file *f, struct object_entry *e, off_t offset) { unsigned long size; /* offset is non zero if object is written already. */ if (e->offset || e->preferred_base) return offset; /* if we are deltified, write out base object first. */ if (e->delta) offset = write_one(f, e->delta, offset); e->offset = offset; size = write_object(f, 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 off_t write_pack_file(void) { uint32_t i; struct sha1file *f; off_t offset, last_obj_offset = 0; struct pack_header hdr; unsigned last_percent = 999; int do_progress = progress; if (!base_name) { f = sha1fd(1, ""); 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++) { last_obj_offset = offset; offset = write_one(f, objects + i, offset); if (do_progress) { unsigned percent = written * 100 / nr_result; if (progress_update || percent != last_percent) { fprintf(stderr, "%4u%% (%u/%u) done\r", percent, written, nr_result); progress_update = 0; last_percent = percent; } } } if (do_progress) fputc('\n', stderr); done: if (written != nr_result) die("wrote %u objects while expecting %u", written, nr_result); sha1close(f, pack_file_sha1, 1); return last_obj_offset; } static void write_index_file(off_t last_obj_offset) { 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]; uint32_t index_version; /* if last object's offset is >= 2^31 we should use index V2 */ index_version = (last_obj_offset >> 31) ? 2 : 1; /* index versions 2 and above need a header */ if (index_version >= 2) { struct pack_idx_header hdr; hdr.idx_signature = htonl(PACK_IDX_SIGNATURE); hdr.idx_version = htonl(index_version); sha1write(f, &hdr, sizeof(hdr)); } /* * 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) break; next++; } array[i] = htonl(next - sorted_by_sha); list = next; } sha1write(f, array, 256 * 4); /* * Write the actual SHA1 entries.. */ list = sorted_by_sha; for (i = 0; i < nr_result; i++) { struct object_entry *entry = *list++; if (index_version < 2) { uint32_t offset = htonl(entry->offset); sha1write(f, &offset, 4); } sha1write(f, entry->sha1, 20); } if (index_version >= 2) { unsigned int nr_large_offset = 0; /* write the crc32 table */ list = sorted_by_sha; for (i = 0; i < nr_objects; i++) { struct object_entry *entry = *list++; uint32_t crc32_val = htonl(entry->crc32); sha1write(f, &crc32_val, 4); } /* write the 32-bit offset table */ list = sorted_by_sha; for (i = 0; i < nr_objects; i++) { struct object_entry *entry = *list++; uint32_t offset = (entry->offset <= 0x7fffffff) ? entry->offset : (0x80000000 | nr_large_offset++); offset = htonl(offset); sha1write(f, &offset, 4); } /* write the large offset table */ list = sorted_by_sha; while (nr_large_offset) { struct object_entry *entry = *list++; uint64_t offset = entry->offset; if (offset > 0x7fffffff) { uint32_t split[2]; split[0] = htonl(offset >> 32); split[1] = htonl(offset & 0xffffffff); sha1write(f, split, 8); nr_large_offset--; } } } sha1write(f, pack_file_sha1, 20); sha1close(f, NULL, 1); } static int locate_object_entry_hash(const unsigned char *sha1) { int i; unsigned int ui; 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)) return i; if (++i == object_ix_hashsz) i = 0; } return -1 - i; } static struct object_entry *locate_object_entry(const unsigned char *sha1) { int i; if (!object_ix_hashsz) return NULL; i = locate_object_entry_hash(sha1); if (0 <= i) return &objects[object_ix[i]-1]; return NULL; } static void rehash_objects(void) { uint32_t i; struct object_entry *oe; object_ix_hashsz = nr_objects * 3; if (object_ix_hashsz < 1024) object_ix_hashsz = 1024; 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); if (0 <= ix) continue; ix = -1 - ix; object_ix[ix] = i + 1; } } static unsigned name_hash(const char *name) { unsigned char c; unsigned hash = 0; /* * This effectively just creates a sortable number from the * last sixteen non-whitespace characters. Last characters * count "most", so things that end in ".c" sort together. */ while ((c = *name++) != 0) { if (isspace(c)) continue; hash = (hash >> 2) + (c << 24); } return hash; } static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude) { uint32_t idx = nr_objects; struct object_entry *entry; struct packed_git *p; 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; } } } } if ((entry = locate_object_entry(sha1)) != NULL) goto already_added; if (idx >= nr_alloc) { nr_alloc = (idx + 1024) * 3 / 2; objects = xrealloc(objects, nr_alloc * sizeof(*entry)); } entry = objects + idx; nr_objects = idx + 1; memset(entry, 0, sizeof(*entry)); hashcpy(entry->sha1, sha1); entry->hash = hash; 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; 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; } struct pbase_tree_cache { unsigned char sha1[20]; int ref; int temporary; void *tree_data; unsigned long tree_size; }; static struct pbase_tree_cache *(pbase_tree_cache[256]); static int pbase_tree_cache_ix(const unsigned char *sha1) { return sha1[0] % ARRAY_SIZE(pbase_tree_cache); } static int pbase_tree_cache_ix_incr(int ix) { return (ix+1) % ARRAY_SIZE(pbase_tree_cache); } static struct pbase_tree { struct pbase_tree *next; /* This is a phony "cache" entry; we are not * going to evict it nor find it through _get() * mechanism -- this is for the toplevel node that * would almost always change with any commit. */ struct pbase_tree_cache pcache; } *pbase_tree; static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) { struct pbase_tree_cache *ent, *nent; void *data; unsigned long size; enum object_type type; int neigh; int my_ix = pbase_tree_cache_ix(sha1); int available_ix = -1; /* pbase-tree-cache acts as a limited hashtable. * your object will be found at your index or within a few * slots after that slot if it is cached. */ for (neigh = 0; neigh < 8; neigh++) { ent = pbase_tree_cache[my_ix]; if (ent && !hashcmp(ent->sha1, sha1)) { ent->ref++; return ent; } else if (((available_ix < 0) && (!ent || !ent->ref)) || ((0 <= available_ix) && (!ent && pbase_tree_cache[available_ix]))) available_ix = my_ix; if (!ent) break; my_ix = pbase_tree_cache_ix_incr(my_ix); } /* Did not find one. Either we got a bogus request or * we need to read and perhaps cache. */ data = read_sha1_file(sha1, &type, &size); if (!data) return NULL; if (type != OBJ_TREE) { free(data); return NULL; } /* We need to either cache or return a throwaway copy */ if (available_ix < 0) ent = NULL; else { ent = pbase_tree_cache[available_ix]; my_ix = available_ix; } if (!ent) { nent = xmalloc(sizeof(*nent)); nent->temporary = (available_ix < 0); } else { /* evict and reuse */ free(ent->tree_data); nent = ent; } hashcpy(nent->sha1, sha1); nent->tree_data = data; nent->tree_size = size; nent->ref = 1; if (!nent->temporary) pbase_tree_cache[my_ix] = nent; return nent; } static void pbase_tree_put(struct pbase_tree_cache *cache) { if (!cache->temporary) { cache->ref--; return; } free(cache->tree_data); free(cache); } static int name_cmp_len(const char *name) { int i; for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++) ; return i; } static void add_pbase_object(struct tree_desc *tree, const char *name, int cmplen, const char *fullname) { struct name_entry entry; 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) continue; if (name[cmplen] != '/') { unsigned hash = name_hash(fullname); add_object_entry(entry.sha1, hash, 1); return; } if (type == OBJ_TREE) { struct tree_desc sub; struct pbase_tree_cache *tree; const char *down = name+cmplen+1; int downlen = name_cmp_len(down); tree = pbase_tree_get(entry.sha1); if (!tree) return; init_tree_desc(&sub, tree->tree_data, tree->tree_size); add_pbase_object(&sub, down, downlen, fullname); pbase_tree_put(tree); } } } static unsigned *done_pbase_paths; static int done_pbase_paths_num; static int done_pbase_paths_alloc; static int done_pbase_path_pos(unsigned hash) { int lo = 0; int hi = done_pbase_paths_num; while (lo < hi) { int mi = (hi + lo) / 2; if (done_pbase_paths[mi] == hash) return mi; if (done_pbase_paths[mi] < hash) hi = mi; else lo = mi + 1; } return -lo-1; } static int check_pbase_path(unsigned hash) { int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash); if (0 <= pos) return 1; pos = -pos - 1; if (done_pbase_paths_alloc <= done_pbase_paths_num) { done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc); done_pbase_paths = xrealloc(done_pbase_paths, done_pbase_paths_alloc * sizeof(unsigned)); } done_pbase_paths_num++; if (pos < done_pbase_paths_num) memmove(done_pbase_paths + pos + 1, done_pbase_paths + pos, (done_pbase_paths_num - pos - 1) * sizeof(unsigned)); done_pbase_paths[pos] = hash; return 0; } static void add_preferred_base_object(const char *name, unsigned hash) { struct pbase_tree *it; int cmplen = name_cmp_len(name); if (check_pbase_path(hash)) return; for (it = pbase_tree; it; it = it->next) { if (cmplen == 0) { hash = name_hash(""); add_object_entry(it->pcache.sha1, hash, 1); } else { struct tree_desc tree; init_tree_desc(&tree, it->pcache.tree_data, it->pcache.tree_size); add_pbase_object(&tree, name, cmplen, name); } } } static void add_preferred_base(unsigned char *sha1) { struct pbase_tree *it; void *data; unsigned long size; unsigned char tree_sha1[20]; if (window <= num_preferred_base++) return; data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); if (!data) return; for (it = pbase_tree; it; it = it->next) { if (!hashcmp(it->pcache.sha1, tree_sha1)) { free(data); return; } } it = xcalloc(1, sizeof(*it)); it->next = pbase_tree; pbase_tree = it; hashcpy(it->pcache.sha1, tree_sha1); it->pcache.tree_data = data; it->pcache.tree_size = size; } static void check_object(struct object_entry *entry) { if (entry->in_pack && !entry->preferred_base) { struct packed_git *p = entry->in_pack; struct pack_window *w_curs = NULL; unsigned long size, used; unsigned int avail; unsigned char *buf; struct object_entry *base_entry = NULL; 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. */ used = unpack_object_header_gently(buf, avail, &entry->in_pack_type, &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. */ if (!no_reuse_delta) { unsigned char c; const unsigned char *base_name; off_t ofs; unsigned long used_0; /* there is at least 20 bytes left in the pack */ switch (entry->in_pack_type) { case OBJ_REF_DELTA: base_name = use_pack(p, &w_curs, entry->in_pack_offset + used, NULL); used += 20; break; case OBJ_OFS_DELTA: buf = use_pack(p, &w_curs, entry->in_pack_offset + used, NULL); used_0 = 0; c = buf[used_0++]; ofs = c & 127; while (c & 128) { ofs += 1; if (!ofs || MSB(ofs, 7)) die("delta base offset overflow in pack for %s", sha1_to_hex(entry->sha1)); c = buf[used_0++]; ofs = (ofs << 7) + (c & 127); } if (ofs >= entry->in_pack_offset) die("delta base offset out of bound for %s", 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; } if (base_name) base_entry = locate_object_entry(base_name); } 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. */ /* uncompressed size of the delta data */ entry->size = size; entry->delta = base_entry; entry->type = entry->in_pack_type; entry->delta_sibling = base_entry->delta_child; base_entry->delta_child = entry; 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 (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); } } typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); 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); } static struct object_entry **create_sorted_list(entry_sort_t sort) { struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *)); uint32_t i; 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; } 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 = 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; } 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->hash < b->hash) return -1; if (a->hash > b->hash) return 1; 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); } struct unpacked { struct object_entry *entry; void *data; struct delta_index *index; }; /* * 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 try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth) { 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; enum object_type type; void *delta_buf; /* Don't bother doing diffs between different types */ 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 && 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) 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 (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; /* Load data if not already done */ if (!trg->data) { trg->data = read_sha1_file(trg_entry->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); } if (!src->data) { src->data = read_sha1_file(src_entry->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); } if (!src->index) { src->index = create_delta_index(src->data, src_size); if (!src->index) die("out of memory"); } delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); if (!delta_buf) return 0; trg_entry->delta = src_entry; trg_entry->delta_size = delta_size; trg_entry->depth = src_entry->depth + 1; free(delta_buf); return 1; } static void progress_interval(int signum) { progress_update = 1; } static void find_deltas(struct object_entry **list, int window, int depth) { uint32_t i = nr_objects, idx = 0, processed = 0; unsigned int array_size = window * sizeof(struct unpacked); struct unpacked *array; unsigned last_percent = 999; if (!nr_objects) return; array = xmalloc(array_size); memset(array, 0, array_size); if (progress) fprintf(stderr, "Deltifying %u objects.\n", nr_result); do { struct object_entry *entry = list[--i]; struct unpacked *n = array + idx; int j; 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 (entry->delta) /* This happens if we decided to reuse existing * delta from a pack. "!no_reuse_delta &&" is implied. */ continue; if (entry->size < 50) continue; free_delta_index(n->index); n->index = NULL; free(n->data); n->data = NULL; n->entry = entry; j = window; while (--j > 0) { uint32_t other_idx = idx + j; struct unpacked *m; if (other_idx >= window) other_idx -= window; m = array + other_idx; if (!m->entry) break; if (try_delta(n, m, 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) continue; idx++; 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); free(array[i].data); } free(array); } 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)); 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)); } return 1; } static void setup_progress_signal(void) { struct sigaction sa; struct itimerval v; memset(&sa, 0, sizeof(sa)); sa.sa_handler = progress_interval; sigemptyset(&sa.sa_mask); sa.sa_flags = SA_RESTART; sigaction(SIGALRM, &sa, NULL); v.it_interval.tv_sec = 1; v.it_interval.tv_usec = 0; v.it_value = v.it_interval; setitimer(ITIMER_REAL, &v, NULL); } static int git_pack_config(const char *k, const char *v) { if(!strcmp(k, "pack.window")) { window = git_config_int(k, v); return 0; } return git_default_config(k, v); } 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)) { if (feof(stdin)) break; if (!ferror(stdin)) die("fgets returned NULL, not EOF, not error!"); if (errno != EINTR) die("fgets: %s", strerror(errno)); clearerr(stdin); continue; } if (line[0] == '-') { if (get_sha1_hex(line+1, sha1)) die("expected edge sha1, got garbage:\n %s", line); add_preferred_base(sha1); continue; } 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); } } static void show_commit(struct commit *commit) { unsigned hash = name_hash(""); add_preferred_base_object("", hash); add_object_entry(commit->object.sha1, hash, 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); } static void show_edge(struct commit *commit) { add_preferred_base(commit->object.sha1); } static void get_object_list(int ac, const char **av) { struct rev_info revs; char line[1000]; int flags = 0; 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') line[--len] = 0; if (!len) break; if (*line == '-') { if (!strcmp(line, "--not")) { flags ^= UNINTERESTING; continue; } die("not a rev '%s'", line); } if (handle_revision_arg(line, &revs, flags, 1)) die("bad revision '%s'", line); } prepare_revision_walk(&revs); mark_edges_uninteresting(revs.commits, &revs, show_edge); traverse_commit_list(&revs, show_commit, show_object); } 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; const char **rp_av; int rp_ac_alloc = 64; int rp_ac; rp_av = xcalloc(rp_ac_alloc, sizeof(*rp_av)); rp_av[0] = "pack-objects"; rp_av[1] = "--objects"; /* --thin will make it --objects-edge */ rp_ac = 2; git_config(git_pack_config); progress = isatty(2); for (i = 1; i < argc; i++) { const char *arg = argv[i]; if (*arg != '-') break; if (!strcmp("--non-empty", arg)) { non_empty = 1; continue; } if (!strcmp("--local", arg)) { local = 1; continue; } if (!strcmp("--incremental", arg)) { incremental = 1; continue; } if (!prefixcmp(arg, "--window=")) { char *end; window = strtoul(arg+9, &end, 0); if (!arg[9] || *end) usage(pack_usage); continue; } if (!prefixcmp(arg, "--depth=")) { char *end; depth = strtoul(arg+8, &end, 0); if (!arg[8] || *end) usage(pack_usage); continue; } if (!strcmp("--progress", arg)) { progress = 1; continue; } if (!strcmp("--all-progress", arg)) { progress = 2; continue; } if (!strcmp("-q", arg)) { progress = 0; continue; } if (!strcmp("--no-reuse-delta", arg)) { no_reuse_delta = 1; continue; } if (!strcmp("--delta-base-offset", arg)) { allow_ofs_delta = 1; continue; } if (!strcmp("--stdout", arg)) { pack_to_stdout = 1; continue; } if (!strcmp("--revs", arg)) { use_internal_rev_list = 1; continue; } if (!strcmp("--unpacked", arg) || !prefixcmp(arg, "--unpacked=") || !strcmp("--reflog", arg) || !strcmp("--all", arg)) { use_internal_rev_list = 1; if (rp_ac >= rp_ac_alloc - 1) { rp_ac_alloc = alloc_nr(rp_ac_alloc); rp_av = xrealloc(rp_av, rp_ac_alloc * sizeof(*rp_av)); } rp_av[rp_ac++] = arg; continue; } if (!strcmp("--thin", arg)) { use_internal_rev_list = 1; thin = 1; rp_av[1] = "--objects-edge"; continue; } usage(pack_usage); } /* Traditionally "pack-objects [options] base extra" failed; * we would however want to take refs parameter that would * have been given to upstream rev-list ourselves, which means * we somehow want to say what the base name is. So the * syntax would be: * * pack-objects [options] base * * in other words, we would treat the first non-option as the * base_name and send everything else to the internal revision * walker. */ if (!pack_to_stdout) base_name = argv[i++]; if (pack_to_stdout != !base_name) usage(pack_usage); 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 (!use_internal_rev_list) read_object_list_from_stdin(); else { rp_av[rp_ac] = NULL; get_object_list(rp_ac, rp_av); } 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 { off_t last_obj_offset; if (nr_result) prepare_pack(window, depth); if (progress == 1 && pack_to_stdout) { /* the other end usually displays progress itself */ struct itimerval v = {{0,},}; setitimer(ITIMER_REAL, &v, NULL); signal(SIGALRM, SIG_IGN ); progress_update = 0; } last_obj_offset = write_pack_file(); if (!pack_to_stdout) { write_index_file(last_obj_offset); puts(sha1_to_hex(object_list_sha1)); } } if (progress) fprintf(stderr, "Total %u (delta %u), reused %u (delta %u)\n", written, written_delta, reused, reused_delta); return 0; }