X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=pack-objects.c;h=7d6247791d9374986c6fb85159433ecd91b9ccec;hb=687dd75c95f9212244b6cf4fe60b40db44de01ba;hp=8864a31cc14f4c57fe0115a0bfe73904fdb1ae12;hpb=56fc63193975edd4b9f520b6c65c2b97ecd8ee38;p=git.git diff --git a/pack-objects.c b/pack-objects.c index 8864a31c..7d624779 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -3,22 +3,48 @@ #include "delta.h" #include "pack.h" #include "csum-file.h" +#include +#include -static const char pack_usage[] = "git-pack-objects [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; +static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; struct object_entry { unsigned char sha1[20]; - unsigned long size; - unsigned long offset; - unsigned int depth; - unsigned int hash; + unsigned long size; /* uncompressed size */ + unsigned long offset; /* offset into the final pack file; + * nonzero if already written. + */ + unsigned int depth; /* delta depth */ + unsigned int delta_limit; /* base adjustment for in-pack delta */ + unsigned int hash; /* name hint hash */ enum object_type type; - unsigned long delta_size; - struct object_entry *delta; + enum object_type in_pack_type; /* could be delta */ + unsigned long delta_size; /* delta data size (uncompressed) */ + struct object_entry *delta; /* delta base object */ + struct packed_git *in_pack; /* already in pack */ + unsigned int in_pack_offset; + struct object_entry *delta_child; /* delitified objects who bases me */ + struct object_entry *delta_sibling; /* other deltified objects who + * uses the same base as me + */ }; +/* + * Objects we are going to pack are colected in objects array (dynamically + * 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 unsigned char object_list_sha1[20]; static int non_empty = 0; +static int no_reuse_delta = 0; static int local = 0; static int incremental = 0; static struct object_entry **sorted_by_sha, **sorted_by_type; @@ -26,6 +52,139 @@ static struct object_entry *objects = NULL; static int nr_objects = 0, nr_alloc = 0; static const char *base_name; static unsigned char pack_file_sha1[20]; +static int progress = 1; +static volatile sig_atomic_t progress_update = 0; + +/* + * The object names in objects array are hashed with this hashtable, + * 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. + * This hashtable is built after all the objects are seen. + */ +static int *object_ix = NULL; +static int object_ix_hashsz = 0; + +/* + * 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). 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 an ordered list of offsets, so if you + * know the offset of an object, next offset is where its packed + * representation ends. + */ +struct pack_revindex { + struct packed_git *p; + unsigned long *revindex; +} *pack_revindex = NULL; +static int pack_revindex_hashsz = 0; + +/* + * stats + */ +static int written = 0; +static int written_delta = 0; +static int reused = 0; +static int reused_delta = 0; + +static int pack_revindex_ix(struct packed_git *p) +{ + unsigned int ui = (unsigned int) 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) +{ + 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_) +{ + unsigned long a = *(unsigned long *) a_; + unsigned long b = *(unsigned long *) b_; + if (a < b) + return -1; + else if (a == b) + return 0; + else + return 1; +} + +/* + * 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; + void *index = p->index_base + 256; + + rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); + for (i = 0; i < num_ent; i++) { + long hl = *((long *)(index + 24 * i)); + rix->revindex[i] = ntohl(hl); + } + /* This knows the pack format -- the 20-byte trailer + * follows immediately after the last object data. + */ + rix->revindex[num_ent] = p->pack_size - 20; + qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); +} + +static unsigned long find_packed_object_size(struct packed_git *p, + unsigned long ofs) +{ + int num; + int lo, hi; + struct pack_revindex *rix; + unsigned long *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] == ofs) { + return revindex[mi+1] - ofs; + } + else if (ofs < revindex[mi]) + hi = mi; + else + lo = mi + 1; + } while (lo < hi); + die("internal error: pack revindex corrupt"); +} static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) { @@ -76,35 +235,69 @@ static unsigned long write_object(struct sha1file *f, struct object_entry *entry { unsigned long size; char type[10]; - void *buf = read_sha1_file(entry->sha1, type, &size); + void *buf; unsigned char header[10]; unsigned hdrlen, datalen; enum object_type obj_type; + int to_reuse = 0; - 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); - - /* - * The object header is a byte of 'type' followed by zero or - * more bytes of length. For deltas, the 20 bytes of delta sha1 - * follows that. - */ obj_type = entry->type; - if (entry->delta) { - buf = delta_against(buf, size, entry); - size = entry->delta_size; - obj_type = OBJ_DELTA; + if (! entry->in_pack) + to_reuse = 0; /* can't reuse what we don't have */ + else if (obj_type == OBJ_DELTA) + to_reuse = 1; /* check_object() decided it for us */ + else if (obj_type != entry->in_pack_type) + to_reuse = 0; /* pack has delta which is unusable */ + else if (entry->delta) + to_reuse = 0; /* we want to pack afresh */ + else + to_reuse = 1; /* we have it in-pack undeltified, + * and we do not need to deltify it. + */ + + if (! to_reuse) { + buf = read_sha1_file(entry->sha1, type, &size); + if (!buf) + die("unable to read %s", sha1_to_hex(entry->sha1)); + 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 = OBJ_DELTA; + } + /* + * The object header is a byte of 'type' followed by zero or + * more bytes of length. For deltas, the 20 bytes of delta + * sha1 follows that. + */ + hdrlen = encode_header(obj_type, size, header); + sha1write(f, header, hdrlen); + + if (entry->delta) { + sha1write(f, entry->delta, 20); + hdrlen += 20; + } + datalen = sha1write_compressed(f, buf, size); + free(buf); } - hdrlen = encode_header(obj_type, size, header); - sha1write(f, header, hdrlen); - if (entry->delta) { - sha1write(f, entry->delta, 20); - hdrlen += 20; + else { + struct packed_git *p = entry->in_pack; + use_packed_git(p); + + datalen = find_packed_object_size(p, entry->in_pack_offset); + buf = p->pack_base + entry->in_pack_offset; + sha1write(f, buf, datalen); + unuse_packed_git(p); + hdrlen = 0; /* not really */ + if (obj_type == OBJ_DELTA) + reused_delta++; + reused++; } - datalen = sha1write_compressed(f, buf, size); - free(buf); + if (obj_type == OBJ_DELTA) + written_delta++; + written++; return hdrlen + datalen; } @@ -119,7 +312,7 @@ static unsigned long write_one(struct sha1file *f, return offset; e->offset = offset; offset += write_object(f, e); - /* if we are delitified, write out its base object. */ + /* if we are deltified, write out its base object. */ if (e->delta) offset = write_one(f, e->delta, offset); return offset; @@ -130,24 +323,41 @@ static void write_pack_file(void) int i; struct sha1file *f; unsigned long offset; - unsigned long mb; struct pack_header hdr; + unsigned last_percent = 999; + int do_progress = 0; if (!base_name) f = sha1fd(1, ""); - else - f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack"); + else { + f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "pack"); + do_progress = progress; + } + if (do_progress) + fprintf(stderr, "Writing %d objects.\n", nr_objects); + hdr.hdr_signature = htonl(PACK_SIGNATURE); hdr.hdr_version = htonl(PACK_VERSION); hdr.hdr_entries = htonl(nr_objects); sha1write(f, &hdr, sizeof(hdr)); offset = sizeof(hdr); - for (i = 0; i < nr_objects; i++) + for (i = 0; i < nr_objects; i++) { offset = write_one(f, objects + i, offset); + if (do_progress) { + unsigned percent = written * 100 / nr_objects; + if (progress_update || percent != last_percent) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, written, nr_objects); + progress_update = 0; + last_percent = percent; + } + } + } + if (do_progress) + fputc('\n', stderr); sha1close(f, pack_file_sha1, 1); - mb = offset >> 20; - offset &= 0xfffff; } static void write_index_file(void) @@ -194,18 +404,20 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash) { unsigned int idx = nr_objects; struct object_entry *entry; - - if (incremental || local) { - struct packed_git *p; - - for (p = packed_git; p; p = p->next) { - struct pack_entry e; - - if (find_pack_entry_one(sha1, &e, p)) { - if (incremental) - return 0; - if (local && !p->pack_local) - return 0; + struct packed_git *p; + unsigned int found_offset = 0; + struct packed_git *found_pack = NULL; + + for (p = packed_git; p; p = p->next) { + struct pack_entry e; + if (find_pack_entry_one(sha1, &e, p)) { + if (incremental) + return 0; + if (local && !p->pack_local) + return 0; + if (!found_pack) { + found_offset = e.offset; + found_pack = e.p; } } } @@ -219,39 +431,143 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash) memset(entry, 0, sizeof(*entry)); memcpy(entry->sha1, sha1, 20); entry->hash = hash; + if (found_pack) { + entry->in_pack = found_pack; + entry->in_pack_offset = found_offset; + } nr_objects = idx+1; return 1; } +static int locate_object_entry_hash(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 (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) + return i; + if (++i == object_ix_hashsz) + i = 0; + } + return -1 - i; +} + +static struct object_entry *locate_object_entry(unsigned char *sha1) +{ + int i = locate_object_entry_hash(sha1); + if (0 <= i) + return &objects[object_ix[i]-1]; + return NULL; +} + static void check_object(struct object_entry *entry) { char type[20]; - if (!sha1_object_info(entry->sha1, type, &entry->size)) { - if (!strcmp(type, "commit")) { - entry->type = OBJ_COMMIT; - } else if (!strcmp(type, "tree")) { - entry->type = OBJ_TREE; - } else if (!strcmp(type, "blob")) { - entry->type = OBJ_BLOB; - } else if (!strcmp(type, "tag")) { - entry->type = OBJ_TAG; - } else - die("unable to pack object %s of type %s", - sha1_to_hex(entry->sha1), type); + if (entry->in_pack) { + unsigned char base[20]; + unsigned long size; + struct object_entry *base_entry; + + /* We want in_pack_type even if we do not reuse delta. + * There is no point not reusing non-delta representations. + */ + check_reuse_pack_delta(entry->in_pack, + entry->in_pack_offset, + base, &size, + &entry->in_pack_type); + + /* Check if it is delta, and the base is also an object + * we are going to pack. If so we will reuse the existing + * delta. + */ + if (!no_reuse_delta && + entry->in_pack_type == OBJ_DELTA && + (base_entry = locate_object_entry(base))) { + + /* 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 = entry->delta_size = size; + entry->delta = base_entry; + entry->type = OBJ_DELTA; + + entry->delta_sibling = base_entry->delta_child; + base_entry->delta_child = entry; + + return; + } + /* Otherwise we would do the usual */ } - else + + if (sha1_object_info(entry->sha1, type, &entry->size)) die("unable to get type of object %s", sha1_to_hex(entry->sha1)); + + if (!strcmp(type, "commit")) { + entry->type = OBJ_COMMIT; + } else if (!strcmp(type, "tree")) { + entry->type = OBJ_TREE; + } else if (!strcmp(type, "blob")) { + entry->type = OBJ_BLOB; + } else if (!strcmp(type, "tag")) { + entry->type = OBJ_TAG; + } else + die("unable to pack object %s of type %s", + sha1_to_hex(entry->sha1), type); +} + +static void hash_objects(void) +{ + int i; + struct object_entry *oe; + + object_ix_hashsz = nr_objects * 2; + object_ix = xcalloc(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) { + error("the same object '%s' added twice", + sha1_to_hex(oe->sha1)); + continue; + } + ix = -1 - ix; + object_ix[ix] = i + 1; + } +} + +static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) +{ + struct object_entry *child = me->delta_child; + unsigned int m = n; + while (child) { + unsigned int c = check_delta_limit(child, n + 1); + if (m < c) + m = c; + child = child->delta_sibling; + } + return m; } static void get_object_details(void) { int i; - struct object_entry *entry = objects; + struct object_entry *entry; - for (i = 0; i < nr_objects; i++) - check_object(entry++); + hash_objects(); + prepare_pack_ix(); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + check_object(entry); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + if (!entry->delta && entry->delta_child) + entry->delta_limit = + check_delta_limit(entry, 1); } typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); @@ -324,6 +640,16 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de if (cur_entry->type != old_entry->type) return -1; + /* If the current object is at edge, take the depth the objects + * that depend on the current object into account -- otherwise + * they would become too deep. + */ + if (cur_entry->delta_child) { + if (max_depth <= cur_entry->delta_limit) + return 0; + max_depth -= cur_entry->delta_limit; + } + size = cur_entry->size; if (size < 50) return -1; @@ -357,15 +683,25 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de return 0; } +static void progress_interval(int signum) +{ + progress_update = 1; +} + static void find_deltas(struct object_entry **list, int window, int depth) { int i, idx; unsigned int array_size = window * sizeof(struct unpacked); struct unpacked *array = xmalloc(array_size); + unsigned processed = 0; + unsigned last_percent = 999; memset(array, 0, array_size); i = nr_objects; idx = 0; + if (progress) + fprintf(stderr, "Deltifying %d objects.\n", nr_objects); + while (--i >= 0) { struct object_entry *entry = list[i]; struct unpacked *n = array + idx; @@ -373,11 +709,29 @@ static void find_deltas(struct object_entry **list, int window, int depth) char type[10]; int j; + processed++; + if (progress) { + unsigned percent = processed * 100 / nr_objects; + if (percent != last_percent || progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, processed, nr_objects); + progress_update = 0; + last_percent = percent; + } + } + + if (entry->delta) + /* This happens if we decided to reuse existing + * delta from a pack. "!no_reuse_delta &&" is implied. + */ + continue; + free(n->data); n->entry = entry; n->data = read_sha1_file(entry->sha1, type, &size); if (size != entry->size) die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size); + j = window; while (--j > 0) { unsigned int other_idx = idx + j; @@ -395,6 +749,9 @@ static void find_deltas(struct object_entry **list, int window, int depth) idx = 0; } + if (progress) + fputc('\n', stderr); + for (i = 0; i < window; ++i) free(array[i].data); free(array); @@ -403,13 +760,9 @@ static void find_deltas(struct object_entry **list, int window, int depth) static void prepare_pack(int window, int depth) { get_object_details(); - - fprintf(stderr, "Packing %d objects\n", nr_objects); - sorted_by_type = create_sorted_list(type_size_sort); if (window && depth) find_deltas(sorted_by_type, window+1, depth); - write_pack_file(); } static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) @@ -432,8 +785,9 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) } } - fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, - sha1_to_hex(sha1)); + if (progress) + fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, + sha1_to_hex(sha1)); if (pack_to_stdout) { if (copy_fd(ifd, 1)) @@ -465,6 +819,23 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) return 1; } +static void setup_progress_signal(void) +{ + struct sigaction sa; + struct itimerval v; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = progress_interval; + sigemptyset(&sa.sa_mask); + sa.sa_flags = SA_RESTART; + sigaction(SIGALRM, &sa, NULL); + + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + setitimer(ITIMER_REAL, &v, NULL); +} + int main(int argc, char **argv) { SHA_CTX ctx; @@ -473,6 +844,8 @@ int main(int argc, char **argv) struct object_entry **list; int i; + setup_git_directory(); + for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -503,6 +876,14 @@ int main(int argc, char **argv) usage(pack_usage); continue; } + if (!strcmp("-q", arg)) { + progress = 0; + continue; + } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } if (!strcmp("--stdout", arg)) { pack_to_stdout = 1; continue; @@ -518,11 +899,32 @@ int main(int argc, char **argv) usage(pack_usage); prepare_packed_git(); - while (fgets(line, sizeof(line), stdin) != NULL) { + + if (progress) { + fprintf(stderr, "Generating pack...\n"); + setup_progress_signal(); + } + + for (;;) { unsigned int hash; char *p; unsigned char sha1[20]; + if (!fgets(line, sizeof(line), stdin)) { + if (feof(stdin)) + break; + if (!ferror(stdin)) + die("fgets returned NULL, not EOF, not error!"); + if (errno != EINTR) + die("fgets: %s", strerror(errno)); + clearerr(stdin); + continue; + } + + if (progress_update) { + fprintf(stderr, "Counting objects...%d\r", nr_objects); + progress_update = 0; + } if (get_sha1_hex(line, sha1)) die("expected sha1, got garbage:\n %s", line); hash = 0; @@ -535,6 +937,8 @@ int main(int argc, char **argv) } add_object_entry(sha1, hash); } + if (progress) + fprintf(stderr, "Done counting %d objects.\n", nr_objects); if (non_empty && !nr_objects) return 0; @@ -551,10 +955,21 @@ int main(int argc, char **argv) ; else { prepare_pack(window, depth); + if (progress && pack_to_stdout) { + /* the other end usually displays progress itself */ + struct itimerval v = {{0,},}; + setitimer(ITIMER_REAL, &v, NULL); + signal(SIGALRM, SIG_IGN ); + progress_update = 0; + } + write_pack_file(); if (!pack_to_stdout) { write_index_file(); puts(sha1_to_hex(object_list_sha1)); } } + if (progress) + fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", + nr_objects, written, written_delta, reused, reused_delta); return 0; }