diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 2102 |
1 files changed, 1425 insertions, 677 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index b0503b202a..6e77dfd444 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "config.h" #include "attr.h" #include "object.h" #include "blob.h" @@ -14,73 +15,63 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "pack-objects.h" #include "progress.h" #include "refs.h" +#include "streaming.h" #include "thread-utils.h" - -static const char pack_usage[] = - "git pack-objects [ -q | --progress | --all-progress ]\n" - " [--all-progress-implied]\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]]\n" - " [--reflog] [--stdout | base-name] [--include-tag]\n" - " [--keep-unreachable | --unpack-unreachable]\n" - " [< ref-list | < object-list]"; - -struct object_entry { - struct pack_idx_entry idx; - unsigned long size; /* uncompressed size */ - 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 - */ - 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; +#include "pack-bitmap.h" +#include "reachable.h" +#include "sha1-array.h" +#include "argv-array.h" +#include "mru.h" +#include "packfile.h" + +static const char *pack_usage[] = { + N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), + N_("git pack-objects [<options>...] <base-name> [< <ref-list> | < <object-list>]"), + NULL }; /* - * Objects we are going to pack are collected 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. + * Objects we are going to pack are collected in the `to_pack` structure. + * It contains an array (dynamically expanded) of the object data, and a map + * that can resolve SHA1s to their position in the array. */ -static struct object_entry *objects; +static struct packing_data to_pack; + static struct pack_idx_entry **written_list; -static uint32_t nr_objects, nr_alloc, nr_result, nr_written; +static uint32_t nr_result, nr_written; static int non_empty; static int reuse_delta = 1, reuse_object = 1; static int keep_unreachable, unpack_unreachable, include_tag; +static timestamp_t unpack_unreachable_expiration; +static int pack_loose_unreachable; static int local; +static int have_non_local_packs; static int incremental; static int ignore_packed_keep; static int allow_ofs_delta; +static struct pack_idx_option pack_idx_opts; static const char *base_name; static int progress = 1; static int window = 10; -static unsigned long pack_size_limit, pack_size_limit_cfg; +static unsigned long pack_size_limit; 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 struct packed_git *reuse_packfile; +static uint32_t reuse_packfile_objects; +static off_t reuse_packfile_offset; + +static int use_bitmap_index_default = 1; +static int use_bitmap_index = -1; +static int write_bitmap_index; +static uint16_t write_bitmap_options; static unsigned long delta_cache_size = 0; static unsigned long max_delta_cache_size = 256 * 1024 * 1024; @@ -89,19 +80,27 @@ 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. - * This hashtable is built after all the objects are seen. - */ -static int *object_ix; -static int object_ix_hashsz; - -/* * stats */ static uint32_t written, written_delta; static uint32_t reused, reused_delta; +/* + * Indexed commits + */ +static struct commit **indexed_commits; +static unsigned int indexed_commits_nr; +static unsigned int indexed_commits_alloc; + +static void index_commit_for_bitmap(struct commit *commit) +{ + if (indexed_commits_nr >= indexed_commits_alloc) { + indexed_commits_alloc = (indexed_commits_alloc + 32) * 2; + REALLOC_ARRAY(indexed_commits, indexed_commits_alloc); + } + + indexed_commits[indexed_commits_nr++] = commit; +} static void *get_delta(struct object_entry *entry) { @@ -109,12 +108,14 @@ static void *get_delta(struct object_entry *entry) void *buf, *base_buf, *delta_buf; enum object_type type; - buf = read_sha1_file(entry->idx.sha1, &type, &size); + buf = read_sha1_file(entry->idx.oid.hash, &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); + die("unable to read %s", oid_to_hex(&entry->idx.oid)); + base_buf = read_sha1_file(entry->delta->idx.oid.hash, &type, + &base_size); if (!base_buf) - die("unable to read %s", sha1_to_hex(entry->delta->idx.sha1)); + die("unable to read %s", + oid_to_hex(&entry->delta->idx.oid)); delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); if (!delta_buf || delta_size != entry->delta_size) @@ -126,13 +127,12 @@ static void *get_delta(struct object_entry *entry) static unsigned long do_compress(void **pptr, unsigned long size) { - z_stream stream; + git_zstream stream; void *in, *out; unsigned long maxsize; - memset(&stream, 0, sizeof(stream)); - deflateInit(&stream, pack_compression_level); - maxsize = deflateBound(&stream, size); + git_deflate_init(&stream, pack_compression_level); + maxsize = git_deflate_bound(&stream, size); in = *pptr; out = xmalloc(maxsize); @@ -142,14 +142,53 @@ static unsigned long do_compress(void **pptr, unsigned long size) stream.avail_in = size; stream.next_out = out; stream.avail_out = maxsize; - while (deflate(&stream, Z_FINISH) == Z_OK) + while (git_deflate(&stream, Z_FINISH) == Z_OK) ; /* nothing */ - deflateEnd(&stream); + git_deflate_end(&stream); free(in); return stream.total_out; } +static unsigned long write_large_blob_data(struct git_istream *st, struct sha1file *f, + const unsigned char *sha1) +{ + git_zstream stream; + unsigned char ibuf[1024 * 16]; + unsigned char obuf[1024 * 16]; + unsigned long olen = 0; + + git_deflate_init(&stream, pack_compression_level); + + for (;;) { + ssize_t readlen; + int zret = Z_OK; + readlen = read_istream(st, ibuf, sizeof(ibuf)); + if (readlen == -1) + die(_("unable to read %s"), sha1_to_hex(sha1)); + + stream.next_in = ibuf; + stream.avail_in = readlen; + while ((stream.avail_in || readlen == 0) && + (zret == Z_OK || zret == Z_BUF_ERROR)) { + stream.next_out = obuf; + stream.avail_out = sizeof(obuf); + zret = git_deflate(&stream, readlen ? 0 : Z_FINISH); + sha1write(f, obuf, stream.next_out - obuf); + olen += stream.next_out - obuf; + } + if (stream.avail_in) + die(_("deflate error (%d)"), zret); + if (readlen == 0) { + if (zret != Z_STREAM_END) + die(_("deflate error (%d)"), zret); + break; + } + } + git_deflate_end(&stream); + return olen; +} + /* * we are going to reuse the existing object data as is. make * sure it is not corrupt. @@ -160,7 +199,7 @@ static int check_pack_inflate(struct packed_git *p, off_t len, unsigned long expect) { - z_stream stream; + git_zstream stream; unsigned char fakebuf[4096], *in; int st; @@ -187,34 +226,219 @@ static void copy_pack_data(struct sha1file *f, off_t len) { unsigned char *in; - unsigned int avail; + unsigned long avail; while (len) { in = use_pack(p, w_curs, offset, &avail); if (avail > len) - avail = (unsigned int)len; + avail = (unsigned long)len; sha1write(f, in, avail); offset += avail; len -= avail; } } -static unsigned long write_object(struct sha1file *f, - struct object_entry *entry, - off_t write_offset) +/* Return 0 if we will bust the pack-size limit */ +static unsigned long write_no_reuse_object(struct sha1file *f, struct object_entry *entry, + unsigned long limit, int usable_delta) { - unsigned long size, limit, datalen; - void *buf; - unsigned char header[10], dheader[10]; + unsigned long size, datalen; + unsigned char header[MAX_PACK_OBJECT_HEADER], + dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; enum object_type type; + void *buf; + struct git_istream *st = NULL; + + if (!usable_delta) { + if (entry->type == OBJ_BLOB && + entry->size > big_file_threshold && + (st = open_istream(entry->idx.oid.hash, &type, &size, NULL)) != NULL) + buf = NULL; + else { + buf = read_sha1_file(entry->idx.oid.hash, &type, + &size); + if (!buf) + die(_("unable to read %s"), + oid_to_hex(&entry->idx.oid)); + } + /* + * make sure no cached delta data remains from a + * previous attempt before a pack split occurred. + */ + FREE_AND_NULL(entry->delta_data); + entry->z_delta_size = 0; + } else if (entry->delta_data) { + size = entry->delta_size; + 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 (st) /* large blob case, just assume we don't compress well */ + datalen = size; + else 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_in_pack_object_header(header, sizeof(header), + type, size); + + 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->idx.offset - entry->delta->idx.offset; + unsigned pos = sizeof(dheader) - 1; + dheader[pos] = ofs & 127; + while (ofs >>= 7) + dheader[--pos] = 128 | (--ofs & 127); + if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + if (st) + close_istream(st); + 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. + */ + if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (st) + close_istream(st); + free(buf); + return 0; + } + sha1write(f, header, hdrlen); + sha1write(f, entry->delta->idx.oid.hash, 20); + hdrlen += 20; + } else { + if (limit && hdrlen + datalen + 20 >= limit) { + if (st) + close_istream(st); + free(buf); + return 0; + } + sha1write(f, header, hdrlen); + } + if (st) { + datalen = write_large_blob_data(st, f, entry->idx.oid.hash); + close_istream(st); + } else { + sha1write(f, buf, datalen); + free(buf); + } + + return hdrlen + datalen; +} + +/* Return 0 if we will bust the pack-size limit */ +static off_t write_reuse_object(struct sha1file *f, struct object_entry *entry, + unsigned long limit, int usable_delta) +{ + struct packed_git *p = entry->in_pack; + struct pack_window *w_curs = NULL; + struct revindex_entry *revidx; + off_t offset; + enum object_type type = entry->type; + off_t datalen; + unsigned char header[MAX_PACK_OBJECT_HEADER], + dheader[MAX_PACK_OBJECT_HEADER]; + unsigned hdrlen; + + if (entry->delta) + type = (allow_ofs_delta && entry->delta->idx.offset) ? + OBJ_OFS_DELTA : OBJ_REF_DELTA; + hdrlen = encode_in_pack_object_header(header, sizeof(header), + type, entry->size); + + 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", + oid_to_hex(&entry->idx.oid)); + unuse_pack(&w_curs); + return write_no_reuse_object(f, entry, limit, usable_delta); + } + + 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", + oid_to_hex(&entry->idx.oid)); + unuse_pack(&w_curs); + return write_no_reuse_object(f, entry, limit, usable_delta); + } + + 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) + 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.oid.hash, 20); + hdrlen += 20; + reused_delta++; + } else { + if (limit && hdrlen + datalen + 20 >= limit) { + unuse_pack(&w_curs); + return 0; + } + sha1write(f, header, hdrlen); + } + copy_pack_data(f, p, &w_curs, offset, datalen); + unuse_pack(&w_curs); + reused++; + return hdrlen + datalen; +} + +/* Return 0 if we will bust the pack-size limit */ +static off_t write_object(struct sha1file *f, + struct object_entry *entry, + off_t write_offset) +{ + unsigned long limit; + off_t len; int usable_delta, to_reuse; if (!pack_to_stdout) crc32_begin(f); - type = entry->type; - /* apply size limit if limited packsize and not first object */ if (!pack_size_limit || !nr_written) limit = 0; @@ -242,11 +466,11 @@ static unsigned long write_object(struct sha1file *f, to_reuse = 0; /* explicit */ else if (!entry->in_pack) to_reuse = 0; /* can't reuse what we don't have */ - else if (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA) + else if (entry->type == OBJ_REF_DELTA || entry->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) + else if (entry->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 */ @@ -255,174 +479,71 @@ static unsigned long write_object(struct sha1file *f, * and we do not need to deltify it. */ - if (!to_reuse) { - 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; - 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_in_pack_object_header(type, size, header); - - 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->idx.offset - entry->delta->idx.offset; - unsigned pos = sizeof(dheader) - 1; - dheader[pos] = ofs & 127; - while (ofs >>= 7) - 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. - */ - 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); - } - 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) - type = (allow_ofs_delta && entry->delta->idx.offset) ? - OBJ_OFS_DELTA : OBJ_REF_DELTA; - hdrlen = encode_in_pack_object_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; - } + if (!to_reuse) + len = write_no_reuse_object(f, entry, limit, usable_delta); + else + len = write_reuse_object(f, entry, limit, usable_delta); + if (!len) + return 0; - 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) - 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); - } - copy_pack_data(f, p, &w_curs, offset, datalen); - unuse_pack(&w_curs); - reused++; - } if (usable_delta) written_delta++; written++; if (!pack_to_stdout) entry->idx.crc32 = crc32_end(f); - return hdrlen + datalen; + return len; } -static int write_one(struct sha1file *f, - struct object_entry *e, - off_t *offset) +enum write_one_status { + WRITE_ONE_SKIP = -1, /* already written */ + WRITE_ONE_BREAK = 0, /* writing this will bust the limit; not written */ + WRITE_ONE_WRITTEN = 1, /* normal */ + WRITE_ONE_RECURSIVE = 2 /* already scheduled to be written */ +}; + +static enum write_one_status write_one(struct sha1file *f, + struct object_entry *e, + off_t *offset) { - unsigned long size; + off_t size; + int recursing; - /* offset is non zero if object is written already. */ - if (e->idx.offset || e->preferred_base) - return -1; + /* + * we set offset to 1 (which is an impossible value) to mark + * the fact that this object is involved in "write its base + * first before writing a deltified object" recursion. + */ + recursing = (e->idx.offset == 1); + if (recursing) { + warning("recursive delta detected for object %s", + oid_to_hex(&e->idx.oid)); + return WRITE_ONE_RECURSIVE; + } else if (e->idx.offset || e->preferred_base) { + /* offset is non zero if object is written already. */ + return WRITE_ONE_SKIP; + } /* if we are deltified, write out base object first. */ - if (e->delta && !write_one(f, e->delta, offset)) - return 0; + if (e->delta) { + e->idx.offset = 1; /* now recurse */ + switch (write_one(f, e->delta, offset)) { + case WRITE_ONE_RECURSIVE: + /* we cannot depend on this one */ + e->delta = NULL; + break; + default: + break; + case WRITE_ONE_BREAK: + e->idx.offset = recursing; + return WRITE_ONE_BREAK; + } + } e->idx.offset = *offset; size = write_object(f, e, *offset); if (!size) { - e->idx.offset = 0; - return 0; + e->idx.offset = recursing; + return WRITE_ONE_BREAK; } written_list[nr_written++] = &e->idx; @@ -430,45 +551,269 @@ static int write_one(struct sha1file *f, if (signed_add_overflows(*offset, size)) die("pack too large for current definition of off_t"); *offset += size; - return 1; + return WRITE_ONE_WRITTEN; +} + +static int mark_tagged(const char *path, const struct object_id *oid, int flag, + void *cb_data) +{ + unsigned char peeled[20]; + struct object_entry *entry = packlist_find(&to_pack, oid->hash, NULL); + + if (entry) + entry->tagged = 1; + if (!peel_ref(path, peeled)) { + entry = packlist_find(&to_pack, peeled, NULL); + if (entry) + entry->tagged = 1; + } + return 0; +} + +static inline void add_to_write_order(struct object_entry **wo, + unsigned int *endp, + struct object_entry *e) +{ + if (e->filled) + return; + wo[(*endp)++] = e; + e->filled = 1; +} + +static void add_descendants_to_write_order(struct object_entry **wo, + unsigned int *endp, + struct object_entry *e) +{ + int add_to_order = 1; + while (e) { + if (add_to_order) { + struct object_entry *s; + /* add this node... */ + add_to_write_order(wo, endp, e); + /* all its siblings... */ + for (s = e->delta_sibling; s; s = s->delta_sibling) { + add_to_write_order(wo, endp, s); + } + } + /* drop down a level to add left subtree nodes if possible */ + if (e->delta_child) { + add_to_order = 1; + e = e->delta_child; + } else { + add_to_order = 0; + /* our sibling might have some children, it is next */ + if (e->delta_sibling) { + e = e->delta_sibling; + continue; + } + /* go back to our parent node */ + e = e->delta; + while (e && !e->delta_sibling) { + /* we're on the right side of a subtree, keep + * going up until we can go right again */ + e = e->delta; + } + if (!e) { + /* done- we hit our original root node */ + return; + } + /* pass it off to sibling at this level */ + e = e->delta_sibling; + } + }; +} + +static void add_family_to_write_order(struct object_entry **wo, + unsigned int *endp, + struct object_entry *e) +{ + struct object_entry *root; + + for (root = e; root->delta; root = root->delta) + ; /* nothing */ + add_descendants_to_write_order(wo, endp, root); +} + +static struct object_entry **compute_write_order(void) +{ + unsigned int i, wo_end, last_untagged; + + struct object_entry **wo; + struct object_entry *objects = to_pack.objects; + + for (i = 0; i < to_pack.nr_objects; i++) { + objects[i].tagged = 0; + objects[i].filled = 0; + objects[i].delta_child = NULL; + objects[i].delta_sibling = NULL; + } + + /* + * Fully connect delta_child/delta_sibling network. + * Make sure delta_sibling is sorted in the original + * recency order. + */ + for (i = to_pack.nr_objects; i > 0;) { + struct object_entry *e = &objects[--i]; + if (!e->delta) + continue; + /* Mark me as the first child */ + e->delta_sibling = e->delta->delta_child; + e->delta->delta_child = e; + } + + /* + * Mark objects that are at the tip of tags. + */ + for_each_tag_ref(mark_tagged, NULL); + + /* + * Give the objects in the original recency order until + * we see a tagged tip. + */ + ALLOC_ARRAY(wo, to_pack.nr_objects); + for (i = wo_end = 0; i < to_pack.nr_objects; i++) { + if (objects[i].tagged) + break; + add_to_write_order(wo, &wo_end, &objects[i]); + } + last_untagged = i; + + /* + * Then fill all the tagged tips. + */ + for (; i < to_pack.nr_objects; i++) { + if (objects[i].tagged) + add_to_write_order(wo, &wo_end, &objects[i]); + } + + /* + * And then all remaining commits and tags. + */ + for (i = last_untagged; i < to_pack.nr_objects; i++) { + if (objects[i].type != OBJ_COMMIT && + objects[i].type != OBJ_TAG) + continue; + add_to_write_order(wo, &wo_end, &objects[i]); + } + + /* + * And then all the trees. + */ + for (i = last_untagged; i < to_pack.nr_objects; i++) { + if (objects[i].type != OBJ_TREE) + continue; + add_to_write_order(wo, &wo_end, &objects[i]); + } + + /* + * Finally all the rest in really tight order + */ + for (i = last_untagged; i < to_pack.nr_objects; i++) { + if (!objects[i].filled) + add_family_to_write_order(wo, &wo_end, &objects[i]); + } + + if (wo_end != to_pack.nr_objects) + die("ordered %u objects, expected %"PRIu32, wo_end, to_pack.nr_objects); + + return wo; +} + +static off_t write_reused_pack(struct sha1file *f) +{ + unsigned char buffer[8192]; + off_t to_write, total; + int fd; + + if (!is_pack_valid(reuse_packfile)) + die("packfile is invalid: %s", reuse_packfile->pack_name); + + fd = git_open(reuse_packfile->pack_name); + if (fd < 0) + die_errno("unable to open packfile for reuse: %s", + reuse_packfile->pack_name); + + if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1) + die_errno("unable to seek in reused packfile"); + + if (reuse_packfile_offset < 0) + reuse_packfile_offset = reuse_packfile->pack_size - 20; + + total = to_write = reuse_packfile_offset - sizeof(struct pack_header); + + while (to_write) { + int read_pack = xread(fd, buffer, sizeof(buffer)); + + if (read_pack <= 0) + die_errno("unable to read from reused packfile"); + + if (read_pack > to_write) + read_pack = to_write; + + sha1write(f, buffer, read_pack); + to_write -= read_pack; + + /* + * We don't know the actual number of objects written, + * only how many bytes written, how many bytes total, and + * how many objects total. So we can fake it by pretending all + * objects we are writing are the same size. This gives us a + * smooth progress meter, and at the end it matches the true + * answer. + */ + written = reuse_packfile_objects * + (((double)(total - to_write)) / total); + display_progress(progress_state, written); + } + + close(fd); + written = reuse_packfile_objects; + display_progress(progress_state, written); + return reuse_packfile_offset - sizeof(struct pack_header); } +static const char no_split_warning[] = N_( +"disabling bitmap writing, packs are split due to pack.packSizeLimit" +); + static void write_pack_file(void) { uint32_t i = 0, j; struct sha1file *f; off_t offset; - struct pack_header hdr; uint32_t nr_remaining = nr_result; time_t last_mtime = 0; + struct object_entry **write_order; if (progress > pack_to_stdout) - progress_state = start_progress("Writing objects", nr_result); - written_list = xmalloc(nr_objects * sizeof(*written_list)); + progress_state = start_progress(_("Writing objects"), nr_result); + ALLOC_ARRAY(written_list, to_pack.nr_objects); + write_order = compute_write_order(); do { unsigned char sha1[20]; char *pack_tmp_name = NULL; - if (pack_to_stdout) { + 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); + else + f = create_tmp_packfile(&pack_tmp_name); + + offset = write_pack_header(f, nr_remaining); + + if (reuse_packfile) { + off_t packfile_size; + assert(pack_to_stdout); + + packfile_size = write_reused_pack(f); + offset += packfile_size; } - 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)) + for (; i < to_pack.nr_objects; i++) { + struct object_entry *e = write_order[i]; + if (write_one(f, e, &offset) == WRITE_ONE_BREAK) break; display_progress(progress_state, written); } @@ -486,23 +831,15 @@ static void write_pack_file(void) fixup_pack_header_footer(fd, sha1, pack_tmp_name, nr_written, sha1, offset); close(fd); + if (write_bitmap_index) { + warning(_(no_split_warning)); + write_bitmap_index = 0; + } } if (!pack_to_stdout) { struct stat st; - const char *idx_tmp_name; - char tmpname[PATH_MAX]; - - 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_shared_perm(pack_tmp_name)) - die_errno("unable to make temporary pack file readable"); - if (rename(pack_tmp_name, tmpname)) - die_errno("unable to rename temporary pack file"); + struct strbuf tmpname = STRBUF_INIT; /* * Packs are runtime accessed in their mtime @@ -511,28 +848,44 @@ static void write_pack_file(void) * 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)); + if (stat(pack_tmp_name, &st) < 0) { + warning_errno("failed to stat %s", pack_tmp_name); } 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)); + if (utime(pack_tmp_name, &utb) < 0) + warning_errno("failed utime() on %s", pack_tmp_name); + } + + strbuf_addf(&tmpname, "%s-", base_name); + + if (write_bitmap_index) { + bitmap_writer_set_checksum(sha1); + bitmap_writer_build_type_index(written_list, nr_written); } - snprintf(tmpname, sizeof(tmpname), "%s-%s.idx", - base_name, sha1_to_hex(sha1)); - if (adjust_shared_perm(idx_tmp_name)) - die_errno("unable to make temporary index file readable"); - if (rename(idx_tmp_name, tmpname)) - die_errno("unable to rename temporary index file"); + finish_tmp_packfile(&tmpname, pack_tmp_name, + written_list, nr_written, + &pack_idx_opts, sha1); + + if (write_bitmap_index) { + strbuf_addf(&tmpname, "%s.bitmap", sha1_to_hex(sha1)); + + stop_progress(&progress_state); + + bitmap_writer_show_progress(progress); + bitmap_writer_reuse_bitmaps(&to_pack); + bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1); + bitmap_writer_build(&to_pack); + bitmap_writer_finish(written_list, nr_written, + tmpname.buf, write_bitmap_options); + write_bitmap_index = 0; + } - free((void *) idx_tmp_name); + strbuf_release(&tmpname); free(pack_tmp_name); puts(sha1_to_hex(sha1)); } @@ -542,153 +895,162 @@ static void write_pack_file(void) written_list[j]->offset = (off_t)-1; } nr_remaining -= nr_written; - } while (nr_remaining && i < nr_objects); + } while (nr_remaining && i < to_pack.nr_objects); free(written_list); + free(write_order); stop_progress(&progress_state); if (written != nr_result) die("wrote %"PRIu32" objects while expecting %"PRIu32, written, nr_result); } -static int locate_object_entry_hash(const unsigned char *sha1) +static int no_try_delta(const char *path) { - 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].idx.sha1)) - return i; - if (++i == object_ix_hashsz) - i = 0; - } - return -1 - i; + static struct attr_check *check; + + if (!check) + check = attr_check_initl("delta", NULL); + if (git_check_attr(path, check)) + return 0; + if (ATTR_FALSE(check->items[0].value)) + return 1; + return 0; } -static struct object_entry *locate_object_entry(const unsigned char *sha1) +/* + * When adding an object, check whether we have already added it + * to our packing list. If so, we can skip. However, if we are + * being asked to excludei t, but the previous mention was to include + * it, make sure to adjust its flags and tweak our numbers accordingly. + * + * As an optimization, we pass out the index position where we would have + * found the item, since that saves us from having to look it up again a + * few lines later when we want to add the new entry. + */ +static int have_duplicate_entry(const unsigned char *sha1, + int exclude, + uint32_t *index_pos) { - int i; - - if (!object_ix_hashsz) - return NULL; + struct object_entry *entry; - i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; -} + entry = packlist_find(&to_pack, sha1, index_pos); + if (!entry) + return 0; -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->idx.sha1); - if (0 <= ix) - continue; - ix = -1 - ix; - object_ix[ix] = i + 1; + if (exclude) { + if (!entry->preferred_base) + nr_result--; + entry->preferred_base = 1; } + + return 1; } -static unsigned name_hash(const char *name) +static int want_found_object(int exclude, struct packed_git *p) { - unsigned c, hash = 0; - - if (!name) + if (exclude) + return 1; + if (incremental) return 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. + * When asked to do --local (do not include an object that appears in a + * pack we borrow from elsewhere) or --honor-pack-keep (do not include + * an object that appears in a pack marked with .keep), finding a pack + * that matches the criteria is sufficient for us to decide to omit it. + * However, even if this pack does not satisfy the criteria, we need to + * make sure no copy of this object appears in _any_ pack that makes us + * to omit the object, so we need to check all the packs. + * + * We can however first check whether these options can possible matter; + * if they do not matter we know we want the object in generated pack. + * Otherwise, we signal "-1" at the end to tell the caller that we do + * not know either way, and it needs to check more packs. */ - while ((c = *name++) != 0) { - if (isspace(c)) - continue; - hash = (hash >> 2) + (c << 24); - } - return hash; -} - -static void setup_delta_attr_check(struct git_attr_check *check) -{ - static struct git_attr *attr_delta; + if (!ignore_packed_keep && + (!local || !have_non_local_packs)) + return 1; - if (!attr_delta) - attr_delta = git_attr("delta"); + if (local && !p->pack_local) + return 0; + if (ignore_packed_keep && p->pack_local && p->pack_keep) + return 0; - check[0].attr = attr_delta; + /* we don't know yet; keep looking for more packs */ + return -1; } -static int no_try_delta(const char *path) +/* + * Check whether we want the object in the pack (e.g., we do not want + * objects found in non-local stores if the "--local" option was used). + * + * If the caller already knows an existing pack it wants to take the object + * from, that is passed in *found_pack and *found_offset; otherwise this + * function finds if there is any pack that has the object and returns the pack + * and its offset in these variables. + */ +static int want_object_in_pack(const unsigned char *sha1, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) { - struct git_attr_check check[1]; + struct mru_entry *entry; + int want; - setup_delta_attr_check(check); - if (git_checkattr(path, ARRAY_SIZE(check), check)) + if (!exclude && local && has_loose_object_nonlocal(sha1)) 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) -{ - struct object_entry *entry; - struct packed_git *p, *found_pack = NULL; - off_t found_offset = 0; - int ix; - unsigned hash = name_hash(name); - - ix = nr_objects ? locate_object_entry_hash(sha1) : -1; - if (ix >= 0) { - if (exclude) { - entry = objects + object_ix[ix] - 1; - if (!entry->preferred_base) - nr_result--; - entry->preferred_base = 1; - } - return 0; + /* + * If we already know the pack object lives in, start checks from that + * pack - in the usual case when neither --local was given nor .keep files + * are present we will determine the answer right now. + */ + if (*found_pack) { + want = want_found_object(exclude, *found_pack); + if (want != -1) + return want; } - if (!exclude && local && has_loose_object_nonlocal(sha1)) - return 0; + for (entry = packed_git_mru.head; entry; entry = entry->next) { + struct packed_git *p = entry->item; + off_t offset; + + if (p == *found_pack) + offset = *found_offset; + else + offset = find_pack_entry_one(sha1, p); - 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 (!*found_pack) { + if (!is_pack_valid(p)) + continue; + *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; + want = want_found_object(exclude, p); + if (!exclude && want > 0) + mru_mark(&packed_git_mru, entry); + if (want != -1) + return want; } } - if (nr_objects >= nr_alloc) { - nr_alloc = (nr_alloc + 1024) * 3 / 2; - objects = xrealloc(objects, nr_alloc * sizeof(*entry)); - } + return 1; +} - entry = objects + nr_objects++; - memset(entry, 0, sizeof(*entry)); - hashcpy(entry->idx.sha1, sha1); +static void create_object_entry(const unsigned char *sha1, + enum object_type type, + uint32_t hash, + int exclude, + int no_try_delta, + uint32_t index_pos, + struct packed_git *found_pack, + off_t found_offset) +{ + struct object_entry *entry; + + entry = packlist_alloc(&to_pack, sha1, index_pos); entry->hash = hash; if (type) entry->type = type; @@ -701,16 +1063,56 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type, entry->in_pack_offset = found_offset; } - if (object_ix_hashsz * 3 <= nr_objects * 4) - rehash_objects(); - else - object_ix[-1 - ix] = nr_objects; + entry->no_try_delta = no_try_delta; +} + +static const char no_closure_warning[] = N_( +"disabling bitmap writing, as some objects are not being packed" +); + +static int add_object_entry(const unsigned char *sha1, enum object_type type, + const char *name, int exclude) +{ + struct packed_git *found_pack = NULL; + off_t found_offset = 0; + uint32_t index_pos; + + if (have_duplicate_entry(sha1, exclude, &index_pos)) + return 0; + + if (!want_object_in_pack(sha1, exclude, &found_pack, &found_offset)) { + /* The pack is missing an object, so it will not have closure */ + if (write_bitmap_index) { + warning(_(no_closure_warning)); + write_bitmap_index = 0; + } + return 0; + } + + create_object_entry(sha1, type, pack_name_hash(name), + exclude, name && no_try_delta(name), + index_pos, found_pack, found_offset); + + display_progress(progress_state, nr_result); + return 1; +} - display_progress(progress_state, nr_objects); +static int add_object_entry_from_bitmap(const unsigned char *sha1, + enum object_type type, + int flags, uint32_t name_hash, + struct packed_git *pack, off_t offset) +{ + uint32_t index_pos; - if (name && no_try_delta(name)) - entry->no_try_delta = 1; + if (have_duplicate_entry(sha1, 0, &index_pos)) + return 0; + if (!want_object_in_pack(sha1, 0, &pack, &offset)) + return 0; + + create_object_entry(sha1, type, name_hash, 0, 0, index_pos, pack, offset); + + display_progress(progress_state, nr_result); return 1; } @@ -735,7 +1137,7 @@ static int pbase_tree_cache_ix_incr(int ix) 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() + * going to evict it or find it through _get() * mechanism -- this is for the toplevel node that * would almost always change with any commit. */ @@ -838,14 +1240,14 @@ static void add_pbase_object(struct tree_desc *tree, while (tree_entry(tree,&entry)) { if (S_ISGITLINK(entry.mode)) continue; - cmp = tree_entry_len(entry.path, entry.sha1) != cmplen ? 1 : + cmp = tree_entry_len(&entry) != cmplen ? 1 : memcmp(name, entry.path, cmplen); if (cmp > 0) continue; if (cmp < 0) return; if (name[cmplen] != '/') { - add_object_entry(entry.sha1, + add_object_entry(entry.oid->hash, object_type(entry.mode), fullname, 1); return; @@ -856,7 +1258,7 @@ static void add_pbase_object(struct tree_desc *tree, const char *down = name+cmplen+1; int downlen = name_cmp_len(down); - tree = pbase_tree_get(entry.sha1); + tree = pbase_tree_get(entry.oid->hash); if (!tree) return; init_tree_desc(&sub, tree->tree_data, tree->tree_size); @@ -875,7 +1277,7 @@ 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; + int mi = lo + (hi - lo) / 2; if (done_pbase_paths[mi] == hash) return mi; if (done_pbase_paths[mi] < hash) @@ -888,21 +1290,17 @@ static int done_pbase_path_pos(unsigned hash) static int check_pbase_path(unsigned hash) { - int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash); + int pos = 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)); - } + ALLOC_GROW(done_pbase_paths, + done_pbase_paths_num + 1, + done_pbase_paths_alloc); 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)); + MOVE_ARRAY(done_pbase_paths + pos + 1, done_pbase_paths + pos, + done_pbase_paths_num - pos - 1); done_pbase_paths[pos] = hash; return 0; } @@ -911,7 +1309,7 @@ static void add_preferred_base_object(const char *name) { struct pbase_tree *it; int cmplen; - unsigned hash = name_hash(name); + unsigned hash = pack_name_hash(name); if (!num_preferred_base || check_pbase_path(hash)) return; @@ -977,12 +1375,10 @@ static void cleanup_preferred_base(void) if (!pbase_tree_cache[i]) continue; free(pbase_tree_cache[i]->tree_data); - free(pbase_tree_cache[i]); - pbase_tree_cache[i] = NULL; + FREE_AND_NULL(pbase_tree_cache[i]); } - free(done_pbase_paths); - done_pbase_paths = NULL; + FREE_AND_NULL(done_pbase_paths); done_pbase_paths_num = done_pbase_paths_alloc = 0; } @@ -994,7 +1390,7 @@ static void check_object(struct object_entry *entry) const unsigned char *base_ref = NULL; struct object_entry *base_entry; unsigned long used, used_0; - unsigned int avail; + unsigned long avail; off_t ofs; unsigned char *buf, c; @@ -1040,7 +1436,7 @@ static void check_object(struct object_entry *entry) ofs += 1; if (!ofs || MSB(ofs, 7)) { error("delta base offset overflow in pack for %s", - sha1_to_hex(entry->idx.sha1)); + oid_to_hex(&entry->idx.oid)); goto give_up; } c = buf[used_0++]; @@ -1049,7 +1445,7 @@ static void check_object(struct object_entry *entry) 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)); + oid_to_hex(&entry->idx.oid)); goto give_up; } if (reuse_delta && !entry->preferred_base) { @@ -1063,7 +1459,7 @@ static void check_object(struct object_entry *entry) break; } - if (base_ref && (base_entry = locate_object_entry(base_ref))) { + if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) { /* * If base_ref was set above that means we wish to * reuse delta data, and we even found that base @@ -1106,7 +1502,7 @@ static void check_object(struct object_entry *entry) unuse_pack(&w_curs); } - entry->type = sha1_object_info(entry->idx.sha1, &entry->size); + entry->type = sha1_object_info(entry->idx.oid.hash, &entry->size); /* * The error condition is checked in prepare_pack(). This is * to permit a missing preferred base object to be ignored @@ -1122,7 +1518,7 @@ static int pack_offset_sort(const void *_a, const void *_b) /* avoid filesystem trashing with loose objects */ if (!a->in_pack && !b->in_pack) - return hashcmp(a->idx.sha1, b->idx.sha1); + return oidcmp(&a->idx.oid, &b->idx.oid); if (a->in_pack < b->in_pack) return -1; @@ -1132,18 +1528,194 @@ static int pack_offset_sort(const void *_a, const void *_b) (a->in_pack_offset > b->in_pack_offset); } +/* + * Drop an on-disk delta we were planning to reuse. Naively, this would + * just involve blanking out the "delta" field, but we have to deal + * with some extra book-keeping: + * + * 1. Removing ourselves from the delta_sibling linked list. + * + * 2. Updating our size/type to the non-delta representation. These were + * either not recorded initially (size) or overwritten with the delta type + * (type) when check_object() decided to reuse the delta. + * + * 3. Resetting our delta depth, as we are now a base object. + */ +static void drop_reused_delta(struct object_entry *entry) +{ + struct object_entry **p = &entry->delta->delta_child; + struct object_info oi = OBJECT_INFO_INIT; + + while (*p) { + if (*p == entry) + *p = (*p)->delta_sibling; + else + p = &(*p)->delta_sibling; + } + entry->delta = NULL; + entry->depth = 0; + + oi.sizep = &entry->size; + oi.typep = &entry->type; + if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) { + /* + * We failed to get the info from this pack for some reason; + * fall back to sha1_object_info, which may find another copy. + * And if that fails, the error will be recorded in entry->type + * and dealt with in prepare_pack(). + */ + entry->type = sha1_object_info(entry->idx.oid.hash, + &entry->size); + } +} + +/* + * Follow the chain of deltas from this entry onward, throwing away any links + * that cause us to hit a cycle (as determined by the DFS state flags in + * the entries). + * + * We also detect too-long reused chains that would violate our --depth + * limit. + */ +static void break_delta_chains(struct object_entry *entry) +{ + /* + * The actual depth of each object we will write is stored as an int, + * as it cannot exceed our int "depth" limit. But before we break + * changes based no that limit, we may potentially go as deep as the + * number of objects, which is elsewhere bounded to a uint32_t. + */ + uint32_t total_depth; + struct object_entry *cur, *next; + + for (cur = entry, total_depth = 0; + cur; + cur = cur->delta, total_depth++) { + if (cur->dfs_state == DFS_DONE) { + /* + * We've already seen this object and know it isn't + * part of a cycle. We do need to append its depth + * to our count. + */ + total_depth += cur->depth; + break; + } + + /* + * We break cycles before looping, so an ACTIVE state (or any + * other cruft which made its way into the state variable) + * is a bug. + */ + if (cur->dfs_state != DFS_NONE) + die("BUG: confusing delta dfs state in first pass: %d", + cur->dfs_state); + + /* + * Now we know this is the first time we've seen the object. If + * it's not a delta, we're done traversing, but we'll mark it + * done to save time on future traversals. + */ + if (!cur->delta) { + cur->dfs_state = DFS_DONE; + break; + } + + /* + * Mark ourselves as active and see if the next step causes + * us to cycle to another active object. It's important to do + * this _before_ we loop, because it impacts where we make the + * cut, and thus how our total_depth counter works. + * E.g., We may see a partial loop like: + * + * A -> B -> C -> D -> B + * + * Cutting B->C breaks the cycle. But now the depth of A is + * only 1, and our total_depth counter is at 3. The size of the + * error is always one less than the size of the cycle we + * broke. Commits C and D were "lost" from A's chain. + * + * If we instead cut D->B, then the depth of A is correct at 3. + * We keep all commits in the chain that we examined. + */ + cur->dfs_state = DFS_ACTIVE; + if (cur->delta->dfs_state == DFS_ACTIVE) { + drop_reused_delta(cur); + cur->dfs_state = DFS_DONE; + break; + } + } + + /* + * And now that we've gone all the way to the bottom of the chain, we + * need to clear the active flags and set the depth fields as + * appropriate. Unlike the loop above, which can quit when it drops a + * delta, we need to keep going to look for more depth cuts. So we need + * an extra "next" pointer to keep going after we reset cur->delta. + */ + for (cur = entry; cur; cur = next) { + next = cur->delta; + + /* + * We should have a chain of zero or more ACTIVE states down to + * a final DONE. We can quit after the DONE, because either it + * has no bases, or we've already handled them in a previous + * call. + */ + if (cur->dfs_state == DFS_DONE) + break; + else if (cur->dfs_state != DFS_ACTIVE) + die("BUG: confusing delta dfs state in second pass: %d", + cur->dfs_state); + + /* + * If the total_depth is more than depth, then we need to snip + * the chain into two or more smaller chains that don't exceed + * the maximum depth. Most of the resulting chains will contain + * (depth + 1) entries (i.e., depth deltas plus one base), and + * the last chain (i.e., the one containing entry) will contain + * whatever entries are left over, namely + * (total_depth % (depth + 1)) of them. + * + * Since we are iterating towards decreasing depth, we need to + * decrement total_depth as we go, and we need to write to the + * entry what its final depth will be after all of the + * snipping. Since we're snipping into chains of length (depth + * + 1) entries, the final depth of an entry will be its + * original depth modulo (depth + 1). Any time we encounter an + * entry whose final depth is supposed to be zero, we snip it + * from its delta base, thereby making it so. + */ + cur->depth = (total_depth--) % (depth + 1); + if (!cur->depth) + drop_reused_delta(cur); + + cur->dfs_state = DFS_DONE; + } +} + static void get_object_details(void) { 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++) - sorted_by_offset[i] = objects + i; - qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); + sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); + for (i = 0; i < to_pack.nr_objects; i++) + sorted_by_offset[i] = to_pack.objects + i; + QSORT(sorted_by_offset, to_pack.nr_objects, pack_offset_sort); + + for (i = 0; i < to_pack.nr_objects; i++) { + struct object_entry *entry = sorted_by_offset[i]; + check_object(entry); + if (big_file_threshold < entry->size) + entry->no_try_delta = 1; + } - for (i = 0; i < nr_objects; i++) - check_object(sorted_by_offset[i]); + /* + * This must happen in a second pass, since we rely on the delta + * information for the whole list being completed. + */ + for (i = 0; i < to_pack.nr_objects; i++) + break_delta_chains(&to_pack.objects[i]); free(sorted_by_offset); } @@ -1244,11 +1816,16 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, return -1; /* - * We do not bother to try a delta that we discarded - * on an earlier try, but only when reusing delta data. + * We do not bother to try a delta that we discarded on an + * earlier try, but only when reusing delta data. Note that + * src_entry that is marked as the preferred_base should always + * be considered, as even if we produce a suboptimal delta against + * it, we will still save the transfer cost, as we already know + * the other side has it and we won't send src_entry at all. */ if (reuse_delta && trg_entry->in_pack && trg_entry->in_pack == src_entry->in_pack && + !src_entry->preferred_base && trg_entry->in_pack_type != OBJ_REF_DELTA && trg_entry->in_pack_type != OBJ_OFS_DELTA) return 0; @@ -1280,26 +1857,29 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, /* Load data if not already done */ if (!trg->data) { read_lock(); - trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz); + trg->data = read_sha1_file(trg_entry->idx.oid.hash, &type, + &sz); read_unlock(); if (!trg->data) die("object %s cannot be read", - sha1_to_hex(trg_entry->idx.sha1)); + oid_to_hex(&trg_entry->idx.oid)); if (sz != trg_size) die("object %s inconsistent object length (%lu vs %lu)", - sha1_to_hex(trg_entry->idx.sha1), sz, trg_size); + oid_to_hex(&trg_entry->idx.oid), sz, + trg_size); *mem_usage += sz; } if (!src->data) { read_lock(); - src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz); + src->data = read_sha1_file(src_entry->idx.oid.hash, &type, + &sz); read_unlock(); if (!src->data) { if (src_entry->preferred_base) { static int warned = 0; if (!warned++) warning("object %s cannot be read", - sha1_to_hex(src_entry->idx.sha1)); + oid_to_hex(&src_entry->idx.oid)); /* * Those objects are not included in the * resulting pack. Be resilient and ignore @@ -1309,11 +1889,12 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, return 0; } die("object %s cannot be read", - sha1_to_hex(src_entry->idx.sha1)); + oid_to_hex(&src_entry->idx.oid)); } if (sz != src_size) die("object %s inconsistent object length (%lu vs %lu)", - sha1_to_hex(src_entry->idx.sha1), sz, src_size); + oid_to_hex(&src_entry->idx.oid), sz, + src_size); *mem_usage += sz; } if (!src->index) { @@ -1387,8 +1968,7 @@ static unsigned long free_unpacked(struct unpacked *n) n->index = NULL; if (n->data) { freed_mem += n->entry->size; - free(n->data); - n->data = NULL; + FREE_AND_NULL(n->data); } n->entry = NULL; n->depth = 0; @@ -1535,7 +2115,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, static void try_to_free_from_threads(size_t size) { read_lock(); - release_pack_memory(size, -1); + release_pack_memory(size); read_unlock(); } @@ -1591,7 +2171,10 @@ static void *threaded_find_deltas(void *arg) { struct thread_params *me = arg; + progress_lock(); while (me->remaining) { + progress_unlock(); + find_deltas(me->list, &me->remaining, me->window, me->depth, me->processed); @@ -1613,7 +2196,10 @@ static void *threaded_find_deltas(void *arg) pthread_cond_wait(&me->cond, &me->mutex); me->data_ready = 0; pthread_mutex_unlock(&me->mutex); + + progress_lock(); } + progress_unlock(); /* leave ->working 1 so that this doesn't get more work assigned */ return NULL; } @@ -1626,8 +2212,6 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, init_threaded_search(); - if (!delta_search_threads) /* --threads=0 means autodetect */ - delta_search_threads = online_cpus(); if (delta_search_threads <= 1) { find_deltas(list, &list_size, window, depth, processed); cleanup_threaded_search(); @@ -1753,15 +2337,43 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, #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) +static void add_tag_chain(const struct object_id *oid) { - unsigned char peeled[20]; + struct tag *tag; - 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); + /* + * We catch duplicates already in add_object_entry(), but we'd + * prefer to do this extra check to avoid having to parse the + * tag at all if we already know that it's being packed (e.g., if + * it was included via bitmaps, we would not have parsed it + * previously). + */ + if (packlist_find(&to_pack, oid->hash, NULL)) + return; + + tag = lookup_tag(oid); + while (1) { + if (!tag || parse_tag(tag) || !tag->tagged) + die("unable to pack objects reachable from tag %s", + oid_to_hex(oid)); + + add_object_entry(tag->object.oid.hash, OBJ_TAG, NULL, 0); + + if (tag->tagged->type != OBJ_TAG) + return; + + tag = (struct tag *)tag->tagged; + } +} + +static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data) +{ + struct object_id peeled; + + if (starts_with(path, "refs/tags/") && /* is a tag? */ + !peel_ref(path, peeled.hash) && /* peelable? */ + packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */ + add_tag_chain(oid); return 0; } @@ -1783,14 +2395,14 @@ static void prepare_pack(int window, int depth) if (!pack_to_stdout) do_check_packed_object_crc = 1; - if (!nr_objects || !window || !depth) + if (!to_pack.nr_objects || !window || !depth) return; - delta_list = xmalloc(nr_objects * sizeof(*delta_list)); + ALLOC_ARRAY(delta_list, to_pack.nr_objects); nr_deltas = n = 0; - for (i = 0; i < nr_objects; i++) { - struct object_entry *entry = objects + i; + for (i = 0; i < to_pack.nr_objects; i++) { + struct object_entry *entry = to_pack.objects + i; if (entry->delta) /* This happens if we decided to reuse existing @@ -1808,7 +2420,7 @@ static void prepare_pack(int window, int depth) nr_deltas++; if (entry->type < 0) die("unable to get type of object %s", - sha1_to_hex(entry->idx.sha1)); + oid_to_hex(&entry->idx.oid)); } else { if (entry->type < 0) { /* @@ -1825,9 +2437,9 @@ static void prepare_pack(int window, int depth) if (nr_deltas && n > 1) { unsigned nr_done = 0; if (progress) - progress_state = start_progress("Compressing objects", + progress_state = start_progress(_("Compressing objects"), nr_deltas); - qsort(delta_list, n, sizeof(*delta_list), type_size_sort); + QSORT(delta_list, n, type_size_sort); ll_find_deltas(delta_list, n, window+1, depth, &nr_done); stop_progress(&progress_state); if (nr_done != nr_deltas) @@ -1850,16 +2462,6 @@ static int git_pack_config(const char *k, const char *v, void *cb) 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; @@ -1868,26 +2470,34 @@ static int git_pack_config(const char *k, const char *v, void *cb) cache_max_small_delta_size = git_config_int(k, v); return 0; } + if (!strcmp(k, "pack.writebitmaphashcache")) { + if (git_config_bool(k, v)) + write_bitmap_options |= BITMAP_OPT_HASH_CACHE; + else + write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE; + } + if (!strcmp(k, "pack.usebitmaps")) { + use_bitmap_index_default = git_config_bool(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); #ifdef NO_PTHREADS - if (delta_search_threads != 1) + if (delta_search_threads != 1) { warning("no threads support, ignoring %s", k); + delta_search_threads = 0; + } #endif return 0; } if (!strcmp(k, "pack.indexversion")) { - pack_idx_default_version = git_config_int(k, v); - if (pack_idx_default_version > 2) + pack_idx_opts.version = git_config_int(k, v); + if (pack_idx_opts.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); + pack_idx_opts.version); return 0; } return git_default_config(k, v, cb); @@ -1928,28 +2538,23 @@ static void read_object_list_from_stdin(void) static void show_commit(struct commit *commit, void *data) { - add_object_entry(commit->object.sha1, OBJ_COMMIT, NULL, 0); + add_object_entry(commit->object.oid.hash, OBJ_COMMIT, NULL, 0); commit->object.flags |= OBJECT_ADDED; + + if (write_bitmap_index) + index_commit_for_bitmap(commit); } -static void show_object(struct object *obj, const struct name_path *path, const char *last) +static void show_object(struct object *obj, const char *name, void *data) { - char *name = path_name(path, last); - add_preferred_base_object(name); - add_object_entry(obj->sha1, obj->type, name, 0); + add_object_entry(obj->oid.hash, 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) { - add_preferred_base(commit->object.sha1); + add_preferred_base(commit->object.oid.hash); } struct in_pack_object { @@ -1958,14 +2563,14 @@ struct in_pack_object { }; struct in_pack { - int alloc; - int nr; + unsigned int alloc; + unsigned 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].offset = find_pack_entry_one(object->oid.hash, p); in_pack->array[in_pack->nr].object = object; in_pack->nr++; } @@ -1984,7 +2589,7 @@ static int ofscmp(const void *a_, const void *b_) else if (a->offset > b->offset) return 1; else - return hashcmp(a->object->sha1, b->object->sha1); + return oidcmp(&a->object->oid, &b->object->oid); } static void add_objects_in_unpacked_packs(struct rev_info *revs) @@ -2018,16 +2623,41 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) } if (in_pack.nr) { - qsort(in_pack.array, in_pack.nr, sizeof(in_pack.array[0]), - ofscmp); + QSORT(in_pack.array, in_pack.nr, 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); + add_object_entry(o->oid.hash, o->type, "", 0); } } free(in_pack.array); } +static int add_loose_object(const struct object_id *oid, const char *path, + void *data) +{ + enum object_type type = sha1_object_info(oid->hash, NULL); + + if (type < 0) { + warning("loose object at %s could not be examined", path); + return 0; + } + + add_object_entry(oid->hash, type, "", 0); + return 0; +} + +/* + * We actually don't even have to worry about reachability here. + * add_object_entry will weed out duplicates, so we just add every + * loose object we find. + */ +static void add_unreachable_loose_objects(void) +{ + for_each_loose_file_in_objdir(get_object_directory(), + add_loose_object, + NULL, NULL, NULL); +} + static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) { static struct packed_git *last_found = (void *)1; @@ -2051,11 +2681,32 @@ static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) return 0; } +/* + * Store a list of sha1s that are should not be discarded + * because they are either written too recently, or are + * reachable from another object that was. + * + * This is filled by get_object_list. + */ +static struct oid_array recent_objects; + +static int loosened_object_can_be_discarded(const struct object_id *oid, + timestamp_t mtime) +{ + if (!unpack_unreachable_expiration) + return 0; + if (mtime > unpack_unreachable_expiration) + return 0; + if (oid_array_lookup(&recent_objects, oid) >= 0) + return 0; + return 1; +} + static void loosen_unused_packed_objects(struct rev_info *revs) { struct packed_git *p; uint32_t i; - const unsigned char *sha1; + struct object_id oid; for (p = packed_git; p; p = p->next) { if (!p->pack_local || p->pack_keep) @@ -2065,15 +2716,61 @@ static void loosen_unused_packed_objects(struct rev_info *revs) 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)) + nth_packed_object_oid(&oid, p, i); + if (!packlist_find(&to_pack, oid.hash, NULL) && + !has_sha1_pack_kept_or_nonlocal(oid.hash) && + !loosened_object_can_be_discarded(&oid, p->mtime)) + if (force_object_loose(oid.hash, p->mtime)) die("unable to force loose object"); } } } +/* + * This tracks any options which pack-reuse code expects to be on, or which a + * reader of the pack might not understand, and which would therefore prevent + * blind reuse of what we have on disk. + */ +static int pack_options_allow_reuse(void) +{ + return pack_to_stdout && + allow_ofs_delta && + !ignore_packed_keep && + (!local || !have_non_local_packs) && + !incremental; +} + +static int get_object_list_from_bitmap(struct rev_info *revs) +{ + if (prepare_bitmap_walk(revs) < 0) + return -1; + + if (pack_options_allow_reuse() && + !reuse_partial_packfile_from_bitmap( + &reuse_packfile, + &reuse_packfile_objects, + &reuse_packfile_offset)) { + assert(reuse_packfile_objects); + nr_result += reuse_packfile_objects; + display_progress(progress_state, nr_result); + } + + traverse_bitmap_commit_list(&add_object_entry_from_bitmap); + return 0; +} + +static void record_recent_object(struct object *obj, + const char *name, + void *data) +{ + oid_array_append(&recent_objects, &obj->oid); +} + +static void record_recent_commit(struct commit *commit, void *data) +{ + oid_array_append(&recent_objects, &commit->object.oid); +} + static void get_object_list(int ac, const char **av) { struct rev_info revs; @@ -2084,6 +2781,9 @@ static void get_object_list(int ac, const char **av) save_commit_buffer = 0; setup_revisions(ac, av, &revs, NULL); + /* make sure shallows are read */ + is_repository_shallow(); + while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); if (len && line[len - 1] == '\n') @@ -2093,222 +2793,224 @@ static void get_object_list(int ac, const char **av) if (*line == '-') { if (!strcmp(line, "--not")) { flags ^= UNINTERESTING; + write_bitmap_index = 0; + continue; + } + if (starts_with(line, "--shallow ")) { + struct object_id oid; + if (get_oid_hex(line + 10, &oid)) + die("not an SHA-1 '%s'", line + 10); + register_shallow(&oid); + use_bitmap_index = 0; continue; } die("not a rev '%s'", line); } - if (handle_revision_arg(line, &revs, flags, 1)) + if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME)) die("bad revision '%s'", line); } + if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) + return; + if (prepare_revision_walk(&revs)) die("revision walk setup failed"); - mark_edges_uninteresting(revs.commits, &revs, show_edge); + mark_edges_uninteresting(&revs, show_edge); traverse_commit_list(&revs, show_commit, show_object, NULL); + if (unpack_unreachable_expiration) { + revs.ignore_missing_links = 1; + if (add_unseen_recent_objects_to_traversal(&revs, + unpack_unreachable_expiration)) + die("unable to add recent objects"); + if (prepare_revision_walk(&revs)) + die("revision walk setup failed"); + traverse_commit_list(&revs, record_recent_commit, + record_recent_object, NULL); + } + if (keep_unreachable) add_objects_in_unpacked_packs(&revs); + if (pack_loose_unreachable) + add_unreachable_loose_objects(); if (unpack_unreachable) loosen_unused_packed_objects(&revs); + + oid_array_clear(&recent_objects); +} + +static int option_parse_index_version(const struct option *opt, + const char *arg, int unset) +{ + char *c; + const char *val = arg; + pack_idx_opts.version = strtoul(val, &c, 10); + if (pack_idx_opts.version > 2) + die(_("unsupported index version %s"), val); + if (*c == ',' && c[1]) + pack_idx_opts.off32_limit = strtoul(c+1, &c, 0); + if (*c || pack_idx_opts.off32_limit & 0x80000000) + die(_("bad index version '%s'"), val); + return 0; +} + +static int option_parse_unpack_unreachable(const struct option *opt, + const char *arg, int unset) +{ + if (unset) { + unpack_unreachable = 0; + unpack_unreachable_expiration = 0; + } + else { + unpack_unreachable = 1; + if (arg) + unpack_unreachable_expiration = approxidate(arg); + } + return 0; } int cmd_pack_objects(int argc, const char **argv, const char *prefix) { int use_internal_rev_list = 0; int thin = 0; + int shallow = 0; int all_progress_implied = 0; - uint32_t i; - const char **rp_av; - int rp_ac_alloc = 64; - int rp_ac; - - read_replace_refs = 0; - - 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; - + struct argv_array rp = ARGV_ARRAY_INIT; + int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; + int rev_list_index = 0; + struct option pack_objects_options[] = { + OPT_SET_INT('q', "quiet", &progress, + N_("do not show progress meter"), 0), + OPT_SET_INT(0, "progress", &progress, + N_("show progress meter"), 1), + OPT_SET_INT(0, "all-progress", &progress, + N_("show progress meter during object writing phase"), 2), + OPT_BOOL(0, "all-progress-implied", + &all_progress_implied, + N_("similar to --all-progress when progress meter is shown")), + { OPTION_CALLBACK, 0, "index-version", NULL, N_("version[,offset]"), + N_("write the pack index file in the specified idx format version"), + 0, option_parse_index_version }, + OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, + N_("maximum size of each output pack file")), + OPT_BOOL(0, "local", &local, + N_("ignore borrowed objects from alternate object store")), + OPT_BOOL(0, "incremental", &incremental, + N_("ignore packed objects")), + OPT_INTEGER(0, "window", &window, + N_("limit pack window by objects")), + OPT_MAGNITUDE(0, "window-memory", &window_memory_limit, + N_("limit pack window by memory in addition to object limit")), + OPT_INTEGER(0, "depth", &depth, + N_("maximum length of delta chain allowed in the resulting pack")), + OPT_BOOL(0, "reuse-delta", &reuse_delta, + N_("reuse existing deltas")), + OPT_BOOL(0, "reuse-object", &reuse_object, + N_("reuse existing objects")), + OPT_BOOL(0, "delta-base-offset", &allow_ofs_delta, + N_("use OFS_DELTA objects")), + OPT_INTEGER(0, "threads", &delta_search_threads, + N_("use threads when searching for best delta matches")), + OPT_BOOL(0, "non-empty", &non_empty, + N_("do not create an empty pack output")), + OPT_BOOL(0, "revs", &use_internal_rev_list, + N_("read revision arguments from standard input")), + { OPTION_SET_INT, 0, "unpacked", &rev_list_unpacked, NULL, + N_("limit the objects to those that are not yet packed"), + PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, + { OPTION_SET_INT, 0, "all", &rev_list_all, NULL, + N_("include objects reachable from any reference"), + PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, + { OPTION_SET_INT, 0, "reflog", &rev_list_reflog, NULL, + N_("include objects referred by reflog entries"), + PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, + { OPTION_SET_INT, 0, "indexed-objects", &rev_list_index, NULL, + N_("include objects referred to by the index"), + PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, + OPT_BOOL(0, "stdout", &pack_to_stdout, + N_("output pack to stdout")), + OPT_BOOL(0, "include-tag", &include_tag, + N_("include tag objects that refer to objects to be packed")), + OPT_BOOL(0, "keep-unreachable", &keep_unreachable, + N_("keep unreachable objects")), + OPT_BOOL(0, "pack-loose-unreachable", &pack_loose_unreachable, + N_("pack loose unreachable objects")), + { OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"), + N_("unpack unreachable objects newer than <time>"), + PARSE_OPT_OPTARG, option_parse_unpack_unreachable }, + OPT_BOOL(0, "thin", &thin, + N_("create thin packs")), + OPT_BOOL(0, "shallow", &shallow, + N_("create packs suitable for shallow fetches")), + OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep, + N_("ignore packs that have companion .keep file")), + OPT_INTEGER(0, "compression", &pack_compression_level, + N_("pack compression level")), + OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents, + N_("do not hide commits by grafts"), 0), + OPT_BOOL(0, "use-bitmap-index", &use_bitmap_index, + N_("use a bitmap index if available to speed up counting objects")), + OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index, + N_("write a bitmap index together with the pack index")), + OPT_END(), + }; + + check_replace_refs = 0; + + reset_pack_idx_option(&pack_idx_opts); 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++) { - const char *arg = argv[i]; - - if (*arg != '-') - break; + argc = parse_options(argc, argv, prefix, pack_objects_options, + pack_usage, 0); - if (!strcmp("--non-empty", arg)) { - non_empty = 1; - continue; - } - if (!strcmp("--local", arg)) { - local = 1; - continue; - } - if (!strcmp("--incremental", arg)) { - 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=")) { - pack_size_limit_cfg = 0; - if (!git_parse_ulong(arg+16, &pack_size_limit)) - usage(pack_usage); - continue; - } - if (!prefixcmp(arg, "--window=")) { - char *end; - window = strtoul(arg+9, &end, 0); - if (!arg[9] || *end) - 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); -#ifdef NO_PTHREADS - 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); - 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("--all-progress-implied", arg)) { - all_progress_implied = 1; - continue; - } - if (!strcmp("-q", arg)) { - progress = 0; - continue; - } - if (!strcmp("--no-reuse-delta", arg)) { - reuse_delta = 0; - continue; - } - if (!strcmp("--no-reuse-object", arg)) { - reuse_object = reuse_delta = 0; - 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("--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) || - !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; - } - 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); + if (argc) { + base_name = argv[0]; + argc--; + } + if (pack_to_stdout != !base_name || argc) + usage_with_options(pack_usage, pack_objects_options); + + argv_array_push(&rp, "pack-objects"); + if (thin) { + use_internal_rev_list = 1; + argv_array_push(&rp, shallow + ? "--objects-edge-aggressive" + : "--objects-edge"); + } else + argv_array_push(&rp, "--objects"); + + if (rev_list_all) { + use_internal_rev_list = 1; + argv_array_push(&rp, "--all"); + } + if (rev_list_reflog) { + use_internal_rev_list = 1; + argv_array_push(&rp, "--reflog"); + } + if (rev_list_index) { + use_internal_rev_list = 1; + argv_array_push(&rp, "--indexed-objects"); + } + if (rev_list_unpacked) { + use_internal_rev_list = 1; + argv_array_push(&rp, "--unpacked"); } - /* 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 <refs...> - * - * 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 (!reuse_object) + reuse_delta = 0; + if (pack_compression_level == -1) + pack_compression_level = Z_DEFAULT_COMPRESSION; + else if (pack_compression_level < 0 || pack_compression_level > Z_BEST_COMPRESSION) + die("bad pack compression level %d", pack_compression_level); - if (pack_to_stdout != !base_name) - usage(pack_usage); + if (!delta_search_threads) /* --threads=0 means autodetect */ + delta_search_threads = online_cpus(); +#ifdef NO_PTHREADS + if (delta_search_threads != 1) + warning("no threads support, ignoring --threads"); +#endif if (!pack_to_stdout && !pack_size_limit) pack_size_limit = pack_size_limit_cfg; if (pack_to_stdout && pack_size_limit) @@ -2323,19 +3025,65 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (keep_unreachable && unpack_unreachable) die("--keep-unreachable and --unpack-unreachable are incompatible."); + if (!rev_list_all || !rev_list_reflog || !rev_list_index) + unpack_unreachable_expiration = 0; + + /* + * "soft" reasons not to use bitmaps - for on-disk repack by default we want + * + * - to produce good pack (with bitmap index not-yet-packed objects are + * packed in suboptimal order). + * + * - to use more robust pack-generation codepath (avoiding possible + * bugs in bitmap code and possible bitmap index corruption). + */ + if (!pack_to_stdout) + use_bitmap_index_default = 0; + + if (use_bitmap_index < 0) + use_bitmap_index = use_bitmap_index_default; + + /* "hard" reasons not to use bitmaps; these just won't work at all */ + if (!use_internal_rev_list || (!pack_to_stdout && write_bitmap_index) || is_repository_shallow()) + use_bitmap_index = 0; + + if (pack_to_stdout || !rev_list_all) + write_bitmap_index = 0; if (progress && all_progress_implied) progress = 2; prepare_packed_git(); + if (ignore_packed_keep) { + struct packed_git *p; + for (p = packed_git; p; p = p->next) + if (p->pack_local && p->pack_keep) + break; + if (!p) /* no keep-able packs found */ + ignore_packed_keep = 0; + } + if (local) { + /* + * unlike ignore_packed_keep above, we do not want to + * unset "local" based on looking at packs, as it + * also covers non-local objects + */ + struct packed_git *p; + for (p = packed_git; p; p = p->next) { + if (!p->pack_local) { + have_non_local_packs = 1; + break; + } + } + } if (progress) - progress_state = start_progress("Counting objects", 0); + 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); + get_object_list(rp.argc, rp.argv); + argv_array_clear(&rp); } cleanup_preferred_base(); if (include_tag && nr_result) |