diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 3022 |
1 files changed, 2331 insertions, 691 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index f069462cb0..a01767a384 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1,5 +1,7 @@ #include "builtin.h" #include "cache.h" +#include "repository.h" +#include "config.h" #include "attr.h" #include "object.h" #include "blob.h" @@ -14,60 +16,189 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "list-objects-filter.h" +#include "list-objects-filter-options.h" +#include "pack-objects.h" #include "progress.h" #include "refs.h" #include "streaming.h" #include "thread-utils.h" +#include "pack-bitmap.h" +#include "delta-islands.h" +#include "reachable.h" +#include "oid-array.h" +#include "strvec.h" +#include "list.h" +#include "packfile.h" +#include "object-store.h" +#include "dir.h" +#include "midx.h" +#include "trace2.h" +#include "shallow.h" +#include "promisor-remote.h" + +/* + * 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 packing_data to_pack; + +static inline struct object_entry *oe_delta( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (!e->delta_idx) + return NULL; + if (e->ext_base) + return &pack->ext_bases[e->delta_idx - 1]; + else + return &pack->objects[e->delta_idx - 1]; +} + +static inline unsigned long oe_delta_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_size_valid) + return e->delta_size_; + + /* + * pack->delta_size[] can't be NULL because oe_set_delta_size() + * must have been called when a new delta is saved with + * oe_set_delta(). + * If oe_delta() returns NULL (i.e. default state, which means + * delta_size_valid is also false), then the caller must never + * call oe_delta_size(). + */ + return pack->delta_size[e - pack->objects]; +} + +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e); + +static inline unsigned long oe_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->size_valid) + return e->size_; + + return oe_get_size_slow(pack, e); +} + +static inline void oe_set_delta(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_idx = (delta - pack->objects) + 1; + else + e->delta_idx = 0; +} + +static inline struct object_entry *oe_delta_sibling( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_sibling_idx) + return &pack->objects[e->delta_sibling_idx - 1]; + return NULL; +} + +static inline struct object_entry *oe_delta_child( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_child_idx) + return &pack->objects[e->delta_child_idx - 1]; + return NULL; +} + +static inline void oe_set_delta_child(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_child_idx = (delta - pack->objects) + 1; + else + e->delta_child_idx = 0; +} + +static inline void oe_set_delta_sibling(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_sibling_idx = (delta - pack->objects) + 1; + else + e->delta_sibling_idx = 0; +} + +static inline void oe_set_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + if (size < pack->oe_size_limit) { + e->size_ = size; + e->size_valid = 1; + } else { + e->size_valid = 0; + if (oe_get_size_slow(pack, e) != size) + BUG("'size' is supposed to be the object size!"); + } +} + +static inline void oe_set_delta_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + if (size < pack->oe_delta_size_limit) { + e->delta_size_ = size; + e->delta_size_valid = 1; + } else { + packing_data_lock(pack); + if (!pack->delta_size) + ALLOC_ARRAY(pack->delta_size, pack->nr_alloc); + packing_data_unlock(pack); + + pack->delta_size[e - pack->objects] = size; + e->delta_size_valid = 0; + } +} + +#define IN_PACK(obj) oe_in_pack(&to_pack, obj) +#define SIZE(obj) oe_size(&to_pack, obj) +#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size) +#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj) +#define DELTA(obj) oe_delta(&to_pack, obj) +#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj) +#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj) +#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val) +#define SET_DELTA_EXT(obj, oid) oe_set_delta_ext(&to_pack, obj, oid) +#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val) +#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val) +#define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val) 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]"), + N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), + N_("git pack-objects [<options>...] <base-name> [< <ref-list> | < <object-list>]"), NULL }; -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; - unsigned char tagged; /* near the very tip of refs */ - unsigned char filled; /* assigned write-order */ -}; - -/* - * 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. - */ -static struct object_entry *objects; 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, nr_seen; +static struct bitmap_index *bitmap_git; +static uint32_t write_layer; static int non_empty; static int reuse_delta = 1, reuse_object = 1; static int keep_unreachable, unpack_unreachable, include_tag; -static unsigned long unpack_unreachable_expiration; +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 ignore_packed_keep_on_disk; +static int ignore_packed_keep_in_core; static int allow_ofs_delta; static struct pack_idx_option pack_idx_opts; static const char *base_name; @@ -77,25 +208,55 @@ static unsigned long pack_size_limit; static int depth = 50; static int delta_search_threads; static int pack_to_stdout; +static int sparse; +static int thin; 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 struct bitmap *reuse_packfile_bitmap; + +static int use_bitmap_index_default = 1; +static int use_bitmap_index = -1; +static int allow_pack_reuse = 1; +static enum { + WRITE_BITMAP_FALSE = 0, + WRITE_BITMAP_QUIET, + WRITE_BITMAP_TRUE, +} write_bitmap_index; +static uint16_t write_bitmap_options = BITMAP_OPT_HASH_CACHE; + +static int exclude_promisor_objects; + +static int use_delta_islands; static unsigned long delta_cache_size = 0; -static unsigned long max_delta_cache_size = 256 * 1024 * 1024; +static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE; 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; -static struct object_entry *locate_object_entry(const unsigned char *sha1); +static struct list_objects_filter_options filter_options; + +static struct string_list uri_protocols = STRING_LIST_INIT_NODUP; + +enum missing_action { + MA_ERROR = 0, /* fail if any missing objects are encountered */ + MA_ALLOW_ANY, /* silently allow ALL missing objects */ + MA_ALLOW_PROMISOR, /* silently allow all missing PROMISOR objects */ +}; +static enum missing_action arg_missing_action; +static show_object_fn fn_show_object; + +struct configured_exclusion { + struct oidmap_entry e; + char *pack_hash_hex; + char *uri; +}; +static struct oidmap configured_exclusions; + +static struct oidset excluded_by_config; /* * stats @@ -103,6 +264,22 @@ static struct object_entry *locate_object_entry(const unsigned char *sha1); 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) { @@ -110,16 +287,23 @@ 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_object_file(&entry->idx.oid, &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_object_file(&DELTA(entry)->idx.oid, &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(&DELTA(entry)->idx.oid)); delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) - die("delta size changed"); + /* + * We successfully computed this delta once but dropped it for + * memory reasons. Something is very wrong if this time we + * recompute and create a different delta. + */ + if (!delta_buf || delta_size != DELTA_SIZE(entry)) + BUG("delta size changed"); free(buf); free(base_buf); return delta_buf; @@ -131,7 +315,6 @@ static unsigned long do_compress(void **pptr, unsigned long size) void *in, *out; unsigned long maxsize; - memset(&stream, 0, sizeof(stream)); git_deflate_init(&stream, pack_compression_level); maxsize = git_deflate_bound(&stream, size); @@ -151,15 +334,14 @@ static unsigned long do_compress(void **pptr, unsigned long size) return stream.total_out; } -static unsigned long write_large_blob_data(struct git_istream *st, struct sha1file *f, - const unsigned char *sha1) +static unsigned long write_large_blob_data(struct git_istream *st, struct hashfile *f, + const struct object_id *oid) { git_zstream stream; unsigned char ibuf[1024 * 16]; unsigned char obuf[1024 * 16]; unsigned long olen = 0; - memset(&stream, 0, sizeof(stream)); git_deflate_init(&stream, pack_compression_level); for (;;) { @@ -167,7 +349,7 @@ static unsigned long write_large_blob_data(struct git_istream *st, struct sha1fi int zret = Z_OK; readlen = read_istream(st, ibuf, sizeof(ibuf)); if (readlen == -1) - die(_("unable to read %s"), sha1_to_hex(sha1)); + die(_("unable to read %s"), oid_to_hex(oid)); stream.next_in = ibuf; stream.avail_in = readlen; @@ -176,7 +358,7 @@ static unsigned long write_large_blob_data(struct git_istream *st, struct sha1fi stream.next_out = obuf; stream.avail_out = sizeof(obuf); zret = git_deflate(&stream, readlen ? 0 : Z_FINISH); - sha1write(f, obuf, stream.next_out - obuf); + hashwrite(f, obuf, stream.next_out - obuf); olen += stream.next_out - obuf; } if (stream.avail_in) @@ -221,7 +403,7 @@ static int check_pack_inflate(struct packed_git *p, stream.total_in == len) ? 0 : -1; } -static void copy_pack_data(struct sha1file *f, +static void copy_pack_data(struct hashfile *f, struct packed_git *p, struct pack_window **w_curs, off_t offset, @@ -234,50 +416,64 @@ static void copy_pack_data(struct sha1file *f, in = use_pack(p, w_curs, offset, &avail); if (avail > len) avail = (unsigned long)len; - sha1write(f, in, avail); + hashwrite(f, in, avail); offset += avail; len -= avail; } } +static inline int oe_size_greater_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ > rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 1; + return oe_get_size_slow(pack, lhs) > rhs; +} + /* Return 0 if we will bust the pack-size limit */ -static unsigned long write_no_reuse_object(struct sha1file *f, struct object_entry *entry, +static unsigned long write_no_reuse_object(struct hashfile *f, struct object_entry *entry, unsigned long limit, int usable_delta) { unsigned long size, datalen; - unsigned char header[10], dheader[10]; + 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; + const unsigned hashsz = the_hash_algo->rawsz; if (!usable_delta) { - if (entry->type == OBJ_BLOB && - entry->size > big_file_threshold && - (st = open_istream(entry->idx.sha1, &type, &size, NULL)) != NULL) + if (oe_type(entry) == OBJ_BLOB && + oe_size_greater_than(&to_pack, entry, big_file_threshold) && + (st = open_istream(the_repository, &entry->idx.oid, &type, + &size, NULL)) != NULL) buf = NULL; else { - buf = read_sha1_file(entry->idx.sha1, &type, &size); + buf = read_object_file(&entry->idx.oid, &type, &size); if (!buf) - die(_("unable to read %s"), sha1_to_hex(entry->idx.sha1)); + 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(entry->delta_data); - entry->delta_data = NULL; + FREE_AND_NULL(entry->delta_data); entry->z_delta_size = 0; } else if (entry->delta_data) { - size = entry->delta_size; + size = DELTA_SIZE(entry); buf = entry->delta_data; entry->delta_data = NULL; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + type = (allow_ofs_delta && DELTA(entry)->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) ? + size = DELTA_SIZE(entry); + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } @@ -292,7 +488,8 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent * 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); + hdrlen = encode_in_pack_object_header(header, sizeof(header), + type, size); if (type == OBJ_OFS_DELTA) { /* @@ -300,48 +497,48 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent * 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; + off_t ofs = entry->idx.offset - DELTA(entry)->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 (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); return 0; } - sha1write(f, header, hdrlen); - sha1write(f, dheader + pos, sizeof(dheader) - pos); + hashwrite(f, header, hdrlen); + hashwrite(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. + * additional bytes for the base object ID. */ - if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); return 0; } - sha1write(f, header, hdrlen); - sha1write(f, entry->delta->idx.sha1, 20); - hdrlen += 20; + hashwrite(f, header, hdrlen); + hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); return 0; } - sha1write(f, header, hdrlen); + hashwrite(f, header, hdrlen); } if (st) { - datalen = write_large_blob_data(st, f, entry->idx.sha1); + datalen = write_large_blob_data(st, f, &entry->idx.oid); close_istream(st); } else { - sha1write(f, buf, datalen); + hashwrite(f, buf, datalen); free(buf); } @@ -349,29 +546,39 @@ static unsigned long write_no_reuse_object(struct sha1file *f, struct object_ent } /* Return 0 if we will bust the pack-size limit */ -static unsigned long write_reuse_object(struct sha1file *f, struct object_entry *entry, - unsigned long limit, int usable_delta) +static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, + unsigned long limit, int usable_delta) { - struct packed_git *p = entry->in_pack; + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; - struct revindex_entry *revidx; + uint32_t pos; off_t offset; - enum object_type type = entry->type; - unsigned long datalen; - unsigned char header[10], dheader[10]; + enum object_type type = oe_type(entry); + off_t datalen; + unsigned char header[MAX_PACK_OBJECT_HEADER], + dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; + const unsigned hashsz = the_hash_algo->rawsz; + unsigned long entry_size = SIZE(entry); - if (entry->delta) - type = (allow_ofs_delta && entry->delta->idx.offset) ? + if (DELTA(entry)) + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; - hdrlen = encode_in_pack_object_header(type, entry->size, header); + 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 (offset_to_pack_pos(p, offset, &pos) < 0) + die(_("write_reuse_object: could not locate %s, expected at " + "offset %"PRIuMAX" in pack %s"), + oid_to_hex(&entry->idx.oid), (uintmax_t)offset, + p->pack_name); + datalen = pack_pos_to_offset(p, pos + 1) - 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)); + check_pack_crc(p, &w_curs, offset, datalen, + pack_pos_to_index(p, pos))) { + 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); } @@ -380,41 +587,42 @@ static unsigned long write_reuse_object(struct sha1file *f, struct object_entry 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)); + 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; + off_t ofs = entry->idx.offset - DELTA(entry)->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 (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } - sha1write(f, header, hdrlen); - sha1write(f, dheader + pos, sizeof(dheader) - pos); + hashwrite(f, header, hdrlen); + hashwrite(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) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } - sha1write(f, header, hdrlen); - sha1write(f, entry->delta->idx.sha1, 20); - hdrlen += 20; + hashwrite(f, header, hdrlen); + hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; reused_delta++; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } - sha1write(f, header, hdrlen); + hashwrite(f, header, hdrlen); } copy_pack_data(f, p, &w_curs, offset, datalen); unuse_pack(&w_curs); @@ -423,11 +631,12 @@ static unsigned long write_reuse_object(struct sha1file *f, struct object_entry } /* Return 0 if we will bust the pack-size limit */ -static unsigned long write_object(struct sha1file *f, - struct object_entry *entry, - off_t write_offset) +static off_t write_object(struct hashfile *f, + struct object_entry *entry, + off_t write_offset) { - unsigned long limit, len; + unsigned long limit; + off_t len; int usable_delta, to_reuse; if (!pack_to_stdout) @@ -445,28 +654,29 @@ static unsigned long write_object(struct sha1file *f, else limit = pack_size_limit - write_offset; - if (!entry->delta) + if (!DELTA(entry)) usable_delta = 0; /* no delta */ else if (!pack_size_limit) usable_delta = 1; /* unlimited packfile */ - else if (entry->delta->idx.offset == (off_t)-1) + else if (DELTA(entry)->idx.offset == (off_t)-1) usable_delta = 0; /* base was written to another pack */ - else if (entry->delta->idx.offset) + else if (DELTA(entry)->idx.offset) usable_delta = 1; /* base already exists in this pack */ else usable_delta = 0; /* base could end up in another pack */ if (!reuse_object) to_reuse = 0; /* explicit */ - else if (!entry->in_pack) + else if (!IN_PACK(entry)) to_reuse = 0; /* can't reuse what we don't have */ - else if (entry->type == OBJ_REF_DELTA || entry->type == OBJ_OFS_DELTA) + else if (oe_type(entry) == OBJ_REF_DELTA || + oe_type(entry) == OBJ_OFS_DELTA) /* check_object() decided it for us ... */ to_reuse = usable_delta; /* ... but pack split may override that */ - else if (entry->type != entry->in_pack_type) + else if (oe_type(entry) != entry->in_pack_type) to_reuse = 0; /* pack has delta which is unusable */ - else if (entry->delta) + else if (DELTA(entry)) to_reuse = 0; /* we want to pack afresh */ else to_reuse = 1; /* we have it in-pack undeltified, @@ -495,11 +705,11 @@ enum write_one_status { WRITE_ONE_RECURSIVE = 2 /* already scheduled to be written */ }; -static enum write_one_status write_one(struct sha1file *f, +static enum write_one_status write_one(struct hashfile *f, struct object_entry *e, off_t *offset) { - unsigned long size; + off_t size; int recursing; /* @@ -509,8 +719,8 @@ static enum write_one_status write_one(struct sha1file *f, */ recursing = (e->idx.offset == 1); if (recursing) { - warning("recursive delta detected for object %s", - sha1_to_hex(e->idx.sha1)); + 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. */ @@ -518,12 +728,12 @@ static enum write_one_status write_one(struct sha1file *f, } /* if we are deltified, write out base object first. */ - if (e->delta) { + if (DELTA(e)) { e->idx.offset = 1; /* now recurse */ - switch (write_one(f, e->delta, offset)) { + switch (write_one(f, DELTA(e), offset)) { case WRITE_ONE_RECURSIVE: /* we cannot depend on this one */ - e->delta = NULL; + SET_DELTA(e, NULL); break; default: break; @@ -543,32 +753,40 @@ static enum write_one_status write_one(struct sha1file *f, /* make sure off_t is sufficiently large not to wrap */ if (signed_add_overflows(*offset, size)) - die("pack too large for current definition of off_t"); + die(_("pack too large for current definition of off_t")); *offset += size; return WRITE_ONE_WRITTEN; } -static int mark_tagged(const char *path, const unsigned char *sha1, int flag, +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 = locate_object_entry(sha1); + struct object_id peeled; + struct object_entry *entry = packlist_find(&to_pack, oid); if (entry) entry->tagged = 1; - if (!peel_ref(path, peeled)) { - entry = locate_object_entry(peeled); + if (!peel_iterated_oid(oid, &peeled)) { + entry = packlist_find(&to_pack, &peeled); if (entry) entry->tagged = 1; } return 0; } +static inline unsigned char oe_layer(struct packing_data *pack, + struct object_entry *e) +{ + if (!pack->layer) + return 0; + return pack->layer[e - pack->objects]; +} + static inline void add_to_write_order(struct object_entry **wo, unsigned int *endp, struct object_entry *e) { - if (e->filled) + if (e->filled || oe_layer(&to_pack, e) != write_layer) return; wo[(*endp)++] = e; e->filled = 1; @@ -585,34 +803,34 @@ static void add_descendants_to_write_order(struct object_entry **wo, /* add this node... */ add_to_write_order(wo, endp, e); /* all its siblings... */ - for (s = e->delta_sibling; s; s = s->delta_sibling) { + for (s = DELTA_SIBLING(e); s; s = DELTA_SIBLING(s)) { add_to_write_order(wo, endp, s); } } /* drop down a level to add left subtree nodes if possible */ - if (e->delta_child) { + if (DELTA_CHILD(e)) { add_to_order = 1; - e = e->delta_child; + e = DELTA_CHILD(e); } else { add_to_order = 0; /* our sibling might have some children, it is next */ - if (e->delta_sibling) { - e = e->delta_sibling; + if (DELTA_SIBLING(e)) { + e = DELTA_SIBLING(e); continue; } /* go back to our parent node */ - e = e->delta; - while (e && !e->delta_sibling) { + e = DELTA(e); + while (e && !DELTA_SIBLING(e)) { /* we're on the right side of a subtree, keep * going up until we can go right again */ - e = e->delta; + e = DELTA(e); } if (!e) { /* done- we hit our original root node */ return; } /* pass it off to sibling at this level */ - e = e->delta_sibling; + e = DELTA_SIBLING(e); } }; } @@ -623,22 +841,72 @@ static void add_family_to_write_order(struct object_entry **wo, { struct object_entry *root; - for (root = e; root->delta; root = root->delta) + for (root = e; DELTA(root); root = DELTA(root)) ; /* nothing */ add_descendants_to_write_order(wo, endp, root); } +static void compute_layer_order(struct object_entry **wo, unsigned int *wo_end) +{ + unsigned int i, last_untagged; + struct object_entry *objects = to_pack.objects; + + for (i = 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 (oe_type(&objects[i]) != OBJ_COMMIT && + oe_type(&objects[i]) != 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 (oe_type(&objects[i]) != 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 && oe_layer(&to_pack, &objects[i]) == write_layer) + add_family_to_write_order(wo, wo_end, &objects[i]); + } +} + static struct object_entry **compute_write_order(void) { - unsigned int i, wo_end, last_untagged; + uint32_t max_layers = 1; + unsigned int i, wo_end; - struct object_entry **wo = xmalloc(nr_objects * sizeof(*wo)); + struct object_entry **wo; + struct object_entry *objects = to_pack.objects; - for (i = 0; i < nr_objects; i++) { + 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; + SET_DELTA_CHILD(&objects[i], NULL); + SET_DELTA_SIBLING(&objects[i], NULL); } /* @@ -646,13 +914,13 @@ static struct object_entry **compute_write_order(void) * Make sure delta_sibling is sorted in the original * recency order. */ - for (i = nr_objects; i > 0;) { + for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; - if (!e->delta) + if (!DELTA(e)) continue; /* Mark me as the first child */ - e->delta_sibling = e->delta->delta_child; - e->delta->delta_child = e; + e->delta_sibling_idx = DELTA(e)->delta_child_idx; + SET_DELTA_CHILD(DELTA(e), e); } /* @@ -660,86 +928,266 @@ static struct object_entry **compute_write_order(void) */ for_each_tag_ref(mark_tagged, NULL); - /* - * Give the objects in the original recency order until - * we see a tagged tip. - */ - for (i = wo_end = 0; i < nr_objects; i++) { - if (objects[i].tagged) - break; - add_to_write_order(wo, &wo_end, &objects[i]); - } - last_untagged = i; + if (use_delta_islands) + max_layers = compute_pack_layers(&to_pack); - /* - * Then fill all the tagged tips. - */ - for (; i < nr_objects; i++) { - if (objects[i].tagged) - add_to_write_order(wo, &wo_end, &objects[i]); + ALLOC_ARRAY(wo, to_pack.nr_objects); + wo_end = 0; + + for (; write_layer < max_layers; ++write_layer) + compute_layer_order(wo, &wo_end); + + if (wo_end != to_pack.nr_objects) + die(_("ordered %u objects, expected %"PRIu32), + wo_end, to_pack.nr_objects); + + return wo; +} + + +/* + * A reused set of objects. All objects in a chunk have the same + * relative position in the original packfile and the generated + * packfile. + */ + +static struct reused_chunk { + /* The offset of the first object of this chunk in the original + * packfile. */ + off_t original; + /* The difference for "original" minus the offset of the first object of + * this chunk in the generated packfile. */ + off_t difference; +} *reused_chunks; +static int reused_chunks_nr; +static int reused_chunks_alloc; + +static void record_reused_object(off_t where, off_t offset) +{ + if (reused_chunks_nr && reused_chunks[reused_chunks_nr-1].difference == offset) + return; + + ALLOC_GROW(reused_chunks, reused_chunks_nr + 1, + reused_chunks_alloc); + reused_chunks[reused_chunks_nr].original = where; + reused_chunks[reused_chunks_nr].difference = offset; + reused_chunks_nr++; +} + +/* + * Binary search to find the chunk that "where" is in. Note + * that we're not looking for an exact match, just the first + * chunk that contains it (which implicitly ends at the start + * of the next chunk. + */ +static off_t find_reused_offset(off_t where) +{ + int lo = 0, hi = reused_chunks_nr; + while (lo < hi) { + int mi = lo + ((hi - lo) / 2); + if (where == reused_chunks[mi].original) + return reused_chunks[mi].difference; + if (where < reused_chunks[mi].original) + hi = mi; + else + lo = mi + 1; } /* - * And then all remaining commits and tags. + * The first chunk starts at zero, so we can't have gone below + * there. */ - for (i = last_untagged; i < nr_objects; i++) { - if (objects[i].type != OBJ_COMMIT && - objects[i].type != OBJ_TAG) - continue; - add_to_write_order(wo, &wo_end, &objects[i]); + assert(lo); + return reused_chunks[lo-1].difference; +} + +static void write_reused_pack_one(size_t pos, struct hashfile *out, + struct pack_window **w_curs) +{ + off_t offset, next, cur; + enum object_type type; + unsigned long size; + + offset = pack_pos_to_offset(reuse_packfile, pos); + next = pack_pos_to_offset(reuse_packfile, pos + 1); + + record_reused_object(offset, offset - hashfile_total(out)); + + cur = offset; + type = unpack_object_header(reuse_packfile, w_curs, &cur, &size); + assert(type >= 0); + + if (type == OBJ_OFS_DELTA) { + off_t base_offset; + off_t fixup; + + unsigned char header[MAX_PACK_OBJECT_HEADER]; + unsigned len; + + base_offset = get_delta_base(reuse_packfile, w_curs, &cur, type, offset); + assert(base_offset != 0); + + /* Convert to REF_DELTA if we must... */ + if (!allow_ofs_delta) { + uint32_t base_pos; + struct object_id base_oid; + + if (offset_to_pack_pos(reuse_packfile, base_offset, &base_pos) < 0) + die(_("expected object at offset %"PRIuMAX" " + "in pack %s"), + (uintmax_t)base_offset, + reuse_packfile->pack_name); + + nth_packed_object_id(&base_oid, reuse_packfile, + pack_pos_to_index(reuse_packfile, base_pos)); + + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_REF_DELTA, size); + hashwrite(out, header, len); + hashwrite(out, base_oid.hash, the_hash_algo->rawsz); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } + + /* Otherwise see if we need to rewrite the offset... */ + fixup = find_reused_offset(offset) - + find_reused_offset(base_offset); + if (fixup) { + unsigned char ofs_header[10]; + unsigned i, ofs_len; + off_t ofs = offset - base_offset - fixup; + + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_OFS_DELTA, size); + + i = sizeof(ofs_header) - 1; + ofs_header[i] = ofs & 127; + while (ofs >>= 7) + ofs_header[--i] = 128 | (--ofs & 127); + + ofs_len = sizeof(ofs_header) - i; + + hashwrite(out, header, len); + hashwrite(out, ofs_header + sizeof(ofs_header) - ofs_len, ofs_len); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } + + /* ...otherwise we have no fixup, and can write it verbatim */ } - /* - * And then all the trees. - */ - for (i = last_untagged; i < nr_objects; i++) { - if (objects[i].type != OBJ_TREE) - continue; - add_to_write_order(wo, &wo_end, &objects[i]); + copy_pack_data(out, reuse_packfile, w_curs, offset, next - offset); +} + +static size_t write_reused_pack_verbatim(struct hashfile *out, + struct pack_window **w_curs) +{ + size_t pos = 0; + + while (pos < reuse_packfile_bitmap->word_alloc && + reuse_packfile_bitmap->words[pos] == (eword_t)~0) + pos++; + + if (pos) { + off_t to_write; + + written = (pos * BITS_IN_EWORD); + to_write = pack_pos_to_offset(reuse_packfile, written) + - sizeof(struct pack_header); + + /* We're recording one chunk, not one object. */ + record_reused_object(sizeof(struct pack_header), 0); + hashflush(out); + copy_pack_data(out, reuse_packfile, w_curs, + sizeof(struct pack_header), to_write); + + display_progress(progress_state, written); } + return pos; +} - /* - * Finally all the rest in really tight order - */ - for (i = last_untagged; i < nr_objects; i++) { - if (!objects[i].filled) - add_family_to_write_order(wo, &wo_end, &objects[i]); +static void write_reused_pack(struct hashfile *f) +{ + size_t i = 0; + uint32_t offset; + struct pack_window *w_curs = NULL; + + if (allow_ofs_delta) + i = write_reused_pack_verbatim(f, &w_curs); + + for (; i < reuse_packfile_bitmap->word_alloc; ++i) { + eword_t word = reuse_packfile_bitmap->words[i]; + size_t pos = (i * BITS_IN_EWORD); + + for (offset = 0; offset < BITS_IN_EWORD; ++offset) { + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + write_reused_pack_one(pos + offset, f, &w_curs); + display_progress(progress_state, ++written); + } } - if (wo_end != nr_objects) - die("ordered %u objects, expected %"PRIu32, wo_end, nr_objects); + unuse_pack(&w_curs); +} - return wo; +static void write_excluded_by_configs(void) +{ + struct oidset_iter iter; + const struct object_id *oid; + + oidset_iter_init(&excluded_by_config, &iter); + while ((oid = oidset_iter_next(&iter))) { + struct configured_exclusion *ex = + oidmap_get(&configured_exclusions, oid); + + if (!ex) + BUG("configured exclusion wasn't configured"); + write_in_full(1, ex->pack_hash_hex, strlen(ex->pack_hash_hex)); + write_in_full(1, " ", 1); + write_in_full(1, ex->uri, strlen(ex->uri)); + write_in_full(1, "\n", 1); + } } +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; + struct hashfile *f; off_t offset; 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]; + unsigned char hash[GIT_MAX_RAWSZ]; char *pack_tmp_name = NULL; if (pack_to_stdout) - f = sha1fd_throughput(1, "<stdout>", progress_state); + f = hashfd_throughput(1, "<stdout>", progress_state); else f = create_tmp_packfile(&pack_tmp_name); offset = write_pack_header(f, nr_remaining); - if (!offset) - die_errno("unable to write pack header"); + + if (reuse_packfile) { + assert(pack_to_stdout); + write_reused_pack(f); + offset = hashfile_total(f); + } + nr_written = 0; - for (; i < nr_objects; i++) { + for (; i < to_pack.nr_objects; i++) { struct object_entry *e = write_order[i]; if (write_one(f, e, &offset) == WRITE_ONE_BREAK) break; @@ -751,19 +1199,25 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - sha1close(f, sha1, CSUM_CLOSE); + finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - sha1close(f, sha1, CSUM_FSYNC); + finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = sha1close(f, sha1, 0); - fixup_pack_header_footer(fd, sha1, pack_tmp_name, - nr_written, sha1, offset); + int fd = finalize_hashfile(f, hash, 0); + fixup_pack_header_footer(fd, hash, pack_tmp_name, + nr_written, hash, offset); close(fd); + if (write_bitmap_index) { + if (write_bitmap_index != WRITE_BITMAP_QUIET) + warning(_(no_split_warning)); + write_bitmap_index = 0; + } } if (!pack_to_stdout) { struct stat st; - char tmpname[PATH_MAX]; + struct strbuf tmpname = STRBUF_INIT; + char *idx_tmp_name = NULL; /* * Packs are runtime accessed in their mtime @@ -773,8 +1227,7 @@ static void write_pack_file(void) * to preserve this property. */ if (stat(pack_tmp_name, &st) < 0) { - warning("failed to stat %s: %s", - pack_tmp_name, strerror(errno)); + warning_errno(_("failed to stat %s"), pack_tmp_name); } else if (!last_mtime) { last_mtime = st.st_mtime; } else { @@ -782,19 +1235,43 @@ static void write_pack_file(void) utb.actime = st.st_atime; utb.modtime = --last_mtime; if (utime(pack_tmp_name, &utb) < 0) - warning("failed utime() on %s: %s", - tmpname, strerror(errno)); + warning_errno(_("failed utime() on %s"), pack_tmp_name); + } + + strbuf_addf(&tmpname, "%s-%s.", base_name, + hash_to_hex(hash)); + + if (write_bitmap_index) { + bitmap_writer_set_checksum(hash); + bitmap_writer_build_type_index( + &to_pack, written_list, nr_written); } - /* Enough space for "-<sha-1>.pack"? */ - if (sizeof(tmpname) <= strlen(base_name) + 50) - die("pack base name '%s' too long", base_name); - snprintf(tmpname, sizeof(tmpname), "%s-", base_name); - finish_tmp_packfile(tmpname, pack_tmp_name, + stage_tmp_packfiles(&tmpname, pack_tmp_name, written_list, nr_written, - &pack_idx_opts, sha1); + &pack_idx_opts, hash, &idx_tmp_name); + + if (write_bitmap_index) { + size_t tmpname_len = tmpname.len; + + strbuf_addstr(&tmpname, "bitmap"); + stop_progress(&progress_state); + + bitmap_writer_show_progress(progress); + 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; + strbuf_setlen(&tmpname, tmpname_len); + } + + rename_tmp_packfile_idx(&tmpname, &idx_tmp_name); + + free(idx_tmp_name); + strbuf_release(&tmpname); free(pack_tmp_name); - puts(sha1_to_hex(sha1)); + puts(hash_to_hex(hash)); } /* mark written objects as written to previous pack */ @@ -802,185 +1279,303 @@ 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); + die(_("wrote %"PRIu32" objects while expecting %"PRIu32), + written, nr_result); + trace2_data_intmax("pack-objects", the_repository, + "write_pack_file/wrote", 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); + git_check_attr(the_repository->index, path, check); + 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 struct object_id *oid, + int exclude) { - int i; + struct object_entry *entry; - if (!object_ix_hashsz) - return NULL; + if (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)) + return 1; - i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; -} + entry = packlist_find(&to_pack, oid); + 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(const struct object_id *oid, int exclude, + struct packed_git *p) { - unsigned c, hash = 0; + if (exclude) + return 1; + if (incremental) + return 0; - if (!name) + /* + * 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 possibly 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. + */ + + /* + * Objects in packs borrowed from elsewhere are discarded regardless of + * if they appear in other packs that weren't borrowed. + */ + if (local && !p->pack_local) 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. + * Then handle .keep first, as we have a fast(er) path there. */ - while ((c = *name++) != 0) { - if (isspace(c)) - continue; - hash = (hash >> 2) + (c << 24); + if (ignore_packed_keep_on_disk || ignore_packed_keep_in_core) { + /* + * Set the flags for the kept-pack cache to be the ones we want + * to ignore. + * + * That is, if we are ignoring objects in on-disk keep packs, + * then we want to search through the on-disk keep and ignore + * the in-core ones. + */ + unsigned flags = 0; + if (ignore_packed_keep_on_disk) + flags |= ON_DISK_KEEP_PACKS; + if (ignore_packed_keep_in_core) + flags |= IN_CORE_KEEP_PACKS; + + if (ignore_packed_keep_on_disk && p->pack_keep) + return 0; + if (ignore_packed_keep_in_core && p->pack_keep_in_core) + return 0; + if (has_object_kept_pack(oid, flags)) + return 0; } - return hash; + + /* + * At this point we know definitively that either we don't care about + * keep-packs, or the object is not in one. Keep checking other + * conditions... + */ + if (!local || !have_non_local_packs) + return 1; + + /* we don't know yet; keep looking for more packs */ + return -1; } -static void setup_delta_attr_check(struct git_attr_check *check) +static int want_object_in_pack_one(struct packed_git *p, + const struct object_id *oid, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) { - static struct git_attr *attr_delta; - - if (!attr_delta) - attr_delta = git_attr("delta"); + off_t offset; - check[0].attr = attr_delta; + if (p == *found_pack) + offset = *found_offset; + else + offset = find_pack_entry_one(oid->hash, p); + + if (offset) { + if (!*found_pack) { + if (!is_pack_valid(p)) + return -1; + *found_offset = offset; + *found_pack = p; + } + return want_found_object(oid, exclude, p); + } + 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 struct object_id *oid, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) { - struct git_attr_check check[1]; + int want; + struct list_head *pos; + struct multi_pack_index *m; - setup_delta_attr_check(check); - if (git_check_attr(path, ARRAY_SIZE(check), check)) + if (!exclude && local && has_loose_object_nonlocal(oid)) 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; + /* + * 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(oid, exclude, *found_pack); + if (want != -1) + return want; + } + + for (m = get_multi_pack_index(the_repository); m; m = m->next) { + struct pack_entry e; + if (fill_midx_entry(the_repository, oid, &e, m)) { + want = want_object_in_pack_one(e.p, oid, exclude, found_pack, found_offset); + if (want != -1) + return want; } - return 0; } - if (!exclude && local && has_loose_object_nonlocal(sha1)) - return 0; + list_for_each(pos, get_packed_git_mru(the_repository)) { + struct packed_git *p = list_entry(pos, struct packed_git, mru); + want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset); + if (!exclude && want > 0) + list_move(&p->mru, + get_packed_git_mru(the_repository)); + if (want != -1) + return want; + } - for (p = packed_git; p; p = p->next) { - off_t offset = find_pack_entry_one(sha1, p); - if (offset) { - if (!found_pack) { - if (!is_pack_valid(p)) { - warning("packfile %s cannot be accessed", p->pack_name); - continue; + if (uri_protocols.nr) { + struct configured_exclusion *ex = + oidmap_get(&configured_exclusions, oid); + int i; + const char *p; + + if (ex) { + for (i = 0; i < uri_protocols.nr; i++) { + if (skip_prefix(ex->uri, + uri_protocols.items[i].string, + &p) && + *p == ':') { + oidset_insert(&excluded_by_config, oid); + return 0; } - found_offset = offset; - found_pack = p; } - if (exclude) - break; - if (incremental) - return 0; - if (local && !p->pack_local) - return 0; - if (ignore_packed_keep && p->pack_local && p->pack_keep) - return 0; } } - if (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 struct object_id *oid, + enum object_type type, + uint32_t hash, + int exclude, + int no_try_delta, + struct packed_git *found_pack, + off_t found_offset) +{ + struct object_entry *entry; + + entry = packlist_alloc(&to_pack, oid); entry->hash = hash; - if (type) - entry->type = type; + oe_set_type(entry, type); if (exclude) entry->preferred_base = 1; else nr_result++; if (found_pack) { - entry->in_pack = found_pack; + oe_set_in_pack(&to_pack, entry, found_pack); 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 struct object_id *oid, enum object_type type, + const char *name, int exclude) +{ + struct packed_git *found_pack = NULL; + off_t found_offset = 0; + + display_progress(progress_state, ++nr_seen); - display_progress(progress_state, nr_objects); + if (have_duplicate_entry(oid, exclude)) + return 0; - if (name && no_try_delta(name)) - entry->no_try_delta = 1; + if (!want_object_in_pack(oid, exclude, &found_pack, &found_offset)) { + /* The pack is missing an object, so it will not have closure */ + if (write_bitmap_index) { + if (write_bitmap_index != WRITE_BITMAP_QUIET) + warning(_(no_closure_warning)); + write_bitmap_index = 0; + } + return 0; + } + create_object_entry(oid, type, pack_name_hash(name), + exclude, name && no_try_delta(name), + found_pack, found_offset); + return 1; +} + +static int add_object_entry_from_bitmap(const struct object_id *oid, + enum object_type type, + int flags, uint32_t name_hash, + struct packed_git *pack, off_t offset) +{ + display_progress(progress_state, ++nr_seen); + + if (have_duplicate_entry(oid, 0)) + return 0; + + if (!want_object_in_pack(oid, 0, &pack, &offset)) + return 0; + + create_object_entry(oid, type, name_hash, 0, 0, pack, offset); return 1; } struct pbase_tree_cache { - unsigned char sha1[20]; + struct object_id oid; int ref; int temporary; void *tree_data; @@ -988,9 +1583,9 @@ struct pbase_tree_cache { }; static struct pbase_tree_cache *(pbase_tree_cache[256]); -static int pbase_tree_cache_ix(const unsigned char *sha1) +static int pbase_tree_cache_ix(const struct object_id *oid) { - return sha1[0] % ARRAY_SIZE(pbase_tree_cache); + return oid->hash[0] % ARRAY_SIZE(pbase_tree_cache); } static int pbase_tree_cache_ix_incr(int ix) { @@ -1000,21 +1595,21 @@ 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. */ struct pbase_tree_cache pcache; } *pbase_tree; -static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) +static struct pbase_tree_cache *pbase_tree_get(const struct object_id *oid) { struct pbase_tree_cache *ent, *nent; void *data; unsigned long size; enum object_type type; int neigh; - int my_ix = pbase_tree_cache_ix(sha1); + int my_ix = pbase_tree_cache_ix(oid); int available_ix = -1; /* pbase-tree-cache acts as a limited hashtable. @@ -1023,7 +1618,7 @@ static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) */ for (neigh = 0; neigh < 8; neigh++) { ent = pbase_tree_cache[my_ix]; - if (ent && !hashcmp(ent->sha1, sha1)) { + if (ent && oideq(&ent->oid, oid)) { ent->ref++; return ent; } @@ -1039,7 +1634,7 @@ static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) /* Did not find one. Either we got a bogus request or * we need to read and perhaps cache. */ - data = read_sha1_file(sha1, &type, &size); + data = read_object_file(oid, &type, &size); if (!data) return NULL; if (type != OBJ_TREE) { @@ -1065,7 +1660,7 @@ static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) free(ent->tree_data); nent = ent; } - hashcpy(nent->sha1, sha1); + oidcpy(&nent->oid, oid); nent->tree_data = data; nent->tree_size = size; nent->ref = 1; @@ -1110,7 +1705,7 @@ static void add_pbase_object(struct tree_desc *tree, if (cmp < 0) return; if (name[cmplen] != '/') { - add_object_entry(entry.sha1, + add_object_entry(&entry.oid, object_type(entry.mode), fullname, 1); return; @@ -1121,7 +1716,7 @@ 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); if (!tree) return; init_tree_desc(&sub, tree->tree_data, tree->tree_size); @@ -1140,7 +1735,7 @@ 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) @@ -1153,21 +1748,17 @@ 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; } @@ -1176,7 +1767,7 @@ 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; @@ -1184,7 +1775,7 @@ static void add_preferred_base_object(const char *name) cmplen = name_cmp_len(name); for (it = pbase_tree; it; it = it->next) { if (cmplen == 0) { - add_object_entry(it->pcache.sha1, OBJ_TREE, NULL, 1); + add_object_entry(&it->pcache.oid, OBJ_TREE, NULL, 1); } else { struct tree_desc tree; @@ -1194,32 +1785,33 @@ static void add_preferred_base_object(const char *name) } } -static void add_preferred_base(unsigned char *sha1) +static void add_preferred_base(struct object_id *oid) { struct pbase_tree *it; void *data; unsigned long size; - unsigned char tree_sha1[20]; + struct object_id tree_oid; if (window <= num_preferred_base++) return; - data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); + data = read_object_with_reference(the_repository, oid, + tree_type, &size, &tree_oid); if (!data) return; for (it = pbase_tree; it; it = it->next) { - if (!hashcmp(it->pcache.sha1, tree_sha1)) { + if (oideq(&it->pcache.oid, &tree_oid)) { free(data); return; } } - it = xcalloc(1, sizeof(*it)); + CALLOC_ARRAY(it, 1); it->next = pbase_tree; pbase_tree = it; - hashcpy(it->pcache.sha1, tree_sha1); + oidcpy(&it->pcache.oid, &tree_oid); it->pcache.tree_data = data; it->pcache.tree_size = size; } @@ -1232,36 +1824,106 @@ static void cleanup_preferred_base(void) it = pbase_tree; pbase_tree = NULL; while (it) { - struct pbase_tree *this = it; - it = this->next; - free(this->pcache.tree_data); - free(this); + struct pbase_tree *tmp = it; + it = tmp->next; + free(tmp->pcache.tree_data); + free(tmp); } for (i = 0; i < ARRAY_SIZE(pbase_tree_cache); i++) { 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; } -static void check_object(struct object_entry *entry) +/* + * Return 1 iff the object specified by "delta" can be sent + * literally as a delta against the base in "base_sha1". If + * so, then *base_out will point to the entry in our packing + * list, or NULL if we must use the external-base list. + * + * 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. + */ +static int can_reuse_delta(const struct object_id *base_oid, + struct object_entry *delta, + struct object_entry **base_out) { - if (entry->in_pack) { - struct packed_git *p = entry->in_pack; + struct object_entry *base; + + /* + * First see if we're already sending the base (or it's explicitly in + * our "excluded" list). + */ + base = packlist_find(&to_pack, base_oid); + if (base) { + if (!in_same_island(&delta->idx.oid, &base->idx.oid)) + return 0; + *base_out = base; + return 1; + } + + /* + * Otherwise, reachability bitmaps may tell us if the receiver has it, + * even if it was buried too deep in history to make it into the + * packing list. + */ + if (thin && bitmap_has_oid_in_uninteresting(bitmap_git, base_oid)) { + if (use_delta_islands) { + if (!in_same_island(&delta->idx.oid, base_oid)) + return 0; + } + *base_out = NULL; + return 1; + } + + return 0; +} + +static void prefetch_to_pack(uint32_t object_index_start) { + struct oid_array to_fetch = OID_ARRAY_INIT; + uint32_t i; + + for (i = object_index_start; i < to_pack.nr_objects; i++) { + struct object_entry *entry = to_pack.objects + i; + + if (!oid_object_info_extended(the_repository, + &entry->idx.oid, + NULL, + OBJECT_INFO_FOR_PREFETCH)) + continue; + oid_array_append(&to_fetch, &entry->idx.oid); + } + promisor_remote_get_direct(the_repository, + to_fetch.oid, to_fetch.nr); + oid_array_clear(&to_fetch); +} + +static void check_object(struct object_entry *entry, uint32_t object_index) +{ + unsigned long canonical_size; + enum object_type type; + struct object_info oi = {.typep = &type, .sizep = &canonical_size}; + + if (IN_PACK(entry)) { + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; - const unsigned char *base_ref = NULL; + int have_base = 0; + struct object_id base_ref; struct object_entry *base_entry; unsigned long used, used_0; unsigned long avail; off_t ofs; unsigned char *buf, c; + enum object_type type; + unsigned long in_pack_size; buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail); @@ -1270,11 +1932,15 @@ static void check_object(struct object_entry *entry) * since non-delta representations could still be reused. */ used = unpack_object_header_buffer(buf, avail, - &entry->in_pack_type, - &entry->size); + &type, + &in_pack_size); if (used == 0) goto give_up; + if (type < 0) + BUG("invalid type %d", type); + entry->in_pack_type = type; + /* * Determine if this is a delta and if so whether we can * reuse it or not. Otherwise let's find out as cheaply as @@ -1283,17 +1949,22 @@ static void check_object(struct object_entry *entry) switch (entry->in_pack_type) { default: /* Not a delta hence we've already got all we need. */ - entry->type = entry->in_pack_type; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); entry->in_pack_header_size = used; - if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB) goto give_up; unuse_pack(&w_curs); return; case OBJ_REF_DELTA: - if (reuse_delta && !entry->preferred_base) - base_ref = use_pack(p, &w_curs, - entry->in_pack_offset + used, NULL); - entry->in_pack_header_size = used + 20; + if (reuse_delta && !entry->preferred_base) { + oidread(&base_ref, + use_pack(p, &w_curs, + entry->in_pack_offset + used, + NULL)); + have_base = 1; + } + entry->in_pack_header_size = used + the_hash_algo->rawsz; break; case OBJ_OFS_DELTA: buf = use_pack(p, &w_curs, @@ -1304,8 +1975,8 @@ static void check_object(struct object_entry *entry) while (c & 128) { ofs += 1; if (!ofs || MSB(ofs, 7)) { - error("delta base offset overflow in pack for %s", - sha1_to_hex(entry->idx.sha1)); + error(_("delta base offset overflow in pack for %s"), + oid_to_hex(&entry->idx.oid)); goto give_up; } c = buf[used_0++]; @@ -1313,106 +1984,311 @@ 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)); + error(_("delta base offset out of bound for %s"), + oid_to_hex(&entry->idx.oid)); goto give_up; } if (reuse_delta && !entry->preferred_base) { - struct revindex_entry *revidx; - revidx = find_pack_revindex(p, ofs); - if (!revidx) + uint32_t pos; + if (offset_to_pack_pos(p, ofs, &pos) < 0) goto give_up; - base_ref = nth_packed_object_sha1(p, revidx->nr); + if (!nth_packed_object_id(&base_ref, p, + pack_pos_to_index(p, pos))) + have_base = 1; } entry->in_pack_header_size = used + used_0; break; } - if (base_ref && (base_entry = locate_object_entry(base_ref))) { - /* - * If base_ref was set above that means we wish to - * reuse delta data, and we even found that base - * in the list of objects we want to pack. Goodie! - * - * Depth value does not matter - find_deltas() will - * never consider reused delta as the base object to - * deltify other objects against, in order to avoid - * circular deltas. - */ - entry->type = entry->in_pack_type; - entry->delta = base_entry; - entry->delta_size = entry->size; - entry->delta_sibling = base_entry->delta_child; - base_entry->delta_child = entry; + if (have_base && + can_reuse_delta(&base_ref, entry, &base_entry)) { + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA_SIZE(entry, in_pack_size); + + if (base_entry) { + SET_DELTA(entry, base_entry); + entry->delta_sibling_idx = base_entry->delta_child_idx; + SET_DELTA_CHILD(base_entry, entry); + } else { + SET_DELTA_EXT(entry, &base_ref); + } + unuse_pack(&w_curs); return; } - if (entry->type) { + if (oe_type(entry)) { + off_t delta_pos; + /* * This must be a delta and we already know what the * final object type is. Let's extract the actual * object size from the delta header. */ - entry->size = get_size_from_delta(p, &w_curs, - entry->in_pack_offset + entry->in_pack_header_size); - if (entry->size == 0) + delta_pos = entry->in_pack_offset + entry->in_pack_header_size; + canonical_size = get_size_from_delta(p, &w_curs, delta_pos); + if (canonical_size == 0) goto give_up; + SET_SIZE(entry, canonical_size); unuse_pack(&w_curs); return; } /* * No choice but to fall back to the recursive delta walk - * with sha1_object_info() to find about the object type + * with oid_object_info() to find about the object type * at this point... */ give_up: unuse_pack(&w_curs); } - entry->type = sha1_object_info(entry->idx.sha1, &entry->size); - /* - * The error condition is checked in prepare_pack(). This is - * to permit a missing preferred base object to be ignored - * as a preferred base. Doing so can result in a larger - * pack file, but the transfer will still take place. - */ + if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi, + OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) { + if (has_promisor_remote()) { + prefetch_to_pack(object_index); + if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi, + OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) + type = -1; + } else { + type = -1; + } + } + oe_set_type(entry, type); + if (entry->type_valid) { + SET_SIZE(entry, canonical_size); + } else { + /* + * Bad object type is checked in prepare_pack(). This is + * to permit a missing preferred base object to be ignored + * as a preferred base. Doing so can result in a larger + * pack file, but the transfer will still take place. + */ + } } static int pack_offset_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + const struct packed_git *a_in_pack = IN_PACK(a); + const struct packed_git *b_in_pack = IN_PACK(b); /* avoid filesystem trashing with loose objects */ - if (!a->in_pack && !b->in_pack) - return hashcmp(a->idx.sha1, b->idx.sha1); + if (!a_in_pack && !b_in_pack) + return oidcmp(&a->idx.oid, &b->idx.oid); - if (a->in_pack < b->in_pack) + if (a_in_pack < b_in_pack) return -1; - if (a->in_pack > b->in_pack) + if (a_in_pack > b_in_pack) return 1; return a->in_pack_offset < b->in_pack_offset ? -1 : (a->in_pack_offset > b->in_pack_offset); } +/* + * 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) +{ + unsigned *idx = &to_pack.objects[entry->delta_idx - 1].delta_child_idx; + struct object_info oi = OBJECT_INFO_INIT; + enum object_type type; + unsigned long size; + + while (*idx) { + struct object_entry *oe = &to_pack.objects[*idx - 1]; + + if (oe == entry) + *idx = oe->delta_sibling_idx; + else + idx = &oe->delta_sibling_idx; + } + SET_DELTA(entry, NULL); + entry->depth = 0; + + oi.sizep = &size; + oi.typep = &type; + if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) { + /* + * We failed to get the info from this pack for some reason; + * fall back to oid_object_info, which may find another copy. + * And if that fails, the error will be recorded in oe_type(entry) + * and dealt with in prepare_pack(). + */ + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &size)); + } else { + oe_set_type(entry, type); + } + SET_SIZE(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 = DELTA(cur), 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) + 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 (!DELTA(cur)) { + 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 (DELTA(cur)->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 = DELTA(cur); + + /* + * 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) + 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); + if (progress) + progress_state = start_progress(_("Counting objects"), + to_pack.nr_objects); + + CALLOC_ARRAY(sorted_by_offset, to_pack.nr_objects); + 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 < nr_objects; i++) { + 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) + check_object(entry, i); + if (entry->type_valid && + oe_size_greater_than(&to_pack, entry, big_file_threshold)) entry->no_try_delta = 1; + display_progress(progress_state, i + 1); } + stop_progress(&progress_state); + + /* + * 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); } @@ -1430,10 +2306,14 @@ static int type_size_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + const enum object_type a_type = oe_type(a); + const enum object_type b_type = oe_type(b); + const unsigned long a_size = SIZE(a); + const unsigned long b_size = SIZE(b); - if (a->type > b->type) + if (a_type > b_type) return -1; - if (a->type < b->type) + if (a_type < b_type) return 1; if (a->hash > b->hash) return -1; @@ -1443,9 +2323,14 @@ static int type_size_sort(const void *_a, const void *_b) return -1; if (a->preferred_base < b->preferred_base) return 1; - if (a->size > b->size) + if (use_delta_islands) { + const int island_cmp = island_delta_cmp(&a->idx.oid, &b->idx.oid); + if (island_cmp) + return island_cmp; + } + if (a_size > b_size) return -1; - if (a->size < b->size) + if (a_size < b_size) return 1; return a < b ? -1 : (a > b); /* newest first */ } @@ -1473,30 +2358,85 @@ static int delta_cacheable(unsigned long src_size, unsigned long trg_size, return 0; } -#ifndef NO_PTHREADS - -static pthread_mutex_t read_mutex; -#define read_lock() pthread_mutex_lock(&read_mutex) -#define read_unlock() pthread_mutex_unlock(&read_mutex) - +/* Protect delta_cache_size */ static pthread_mutex_t cache_mutex; #define cache_lock() pthread_mutex_lock(&cache_mutex) #define cache_unlock() pthread_mutex_unlock(&cache_mutex) +/* + * Protect object list partitioning (e.g. struct thread_param) and + * progress_state + */ static pthread_mutex_t progress_mutex; #define progress_lock() pthread_mutex_lock(&progress_mutex) #define progress_unlock() pthread_mutex_unlock(&progress_mutex) -#else +/* + * Access to struct object_entry is unprotected since each thread owns + * a portion of the main object list. Just don't access object entries + * ahead in the list because they can be stolen and would need + * progress_mutex for protection. + */ + +static inline int oe_size_less_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ < rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 0; + return oe_get_size_slow(pack, lhs) < rhs; +} + +static inline void oe_set_tree_depth(struct packing_data *pack, + struct object_entry *e, + unsigned int tree_depth) +{ + if (!pack->tree_depth) + CALLOC_ARRAY(pack->tree_depth, pack->nr_alloc); + pack->tree_depth[e - pack->objects] = tree_depth; +} + +/* + * Return the size of the object without doing any delta + * reconstruction (so non-deltas are true object sizes, but deltas + * return the size of the delta data). + */ +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e) +{ + struct packed_git *p; + struct pack_window *w_curs; + unsigned char *buf; + enum object_type type; + unsigned long used, avail, size; + + if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) { + packing_data_lock(&to_pack); + if (oid_object_info(the_repository, &e->idx.oid, &size) < 0) + die(_("unable to get size of %s"), + oid_to_hex(&e->idx.oid)); + packing_data_unlock(&to_pack); + return size; + } -#define read_lock() (void)0 -#define read_unlock() (void)0 -#define cache_lock() (void)0 -#define cache_unlock() (void)0 -#define progress_lock() (void)0 -#define progress_unlock() (void)0 + p = oe_in_pack(pack, e); + if (!p) + BUG("when e->type is a delta, it must belong to a pack"); -#endif + packing_data_lock(&to_pack); + w_curs = NULL; + buf = use_pack(p, &w_curs, e->in_pack_offset, &avail); + used = unpack_object_header_buffer(buf, avail, &type, &size); + if (used == 0) + die(_("unable to parse object header of %s"), + oid_to_hex(&e->idx.oid)); + + unuse_pack(&w_curs); + packing_data_unlock(&to_pack); + return size; +} static int try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth, unsigned long *mem_usage) @@ -1509,7 +2449,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, void *delta_buf; /* Don't bother doing diffs between different types */ - if (trg_entry->type != src_entry->type) + if (oe_type(trg_entry) != oe_type(src_entry)) return -1; /* @@ -1520,8 +2460,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, * 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 && + if (reuse_delta && IN_PACK(trg_entry) && + IN_PACK(trg_entry) == IN_PACK(src_entry) && !src_entry->preferred_base && trg_entry->in_pack_type != OBJ_REF_DELTA && trg_entry->in_pack_type != OBJ_OFS_DELTA) @@ -1532,48 +2472,52 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, return 0; /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - if (!trg_entry->delta) { - max_size = trg_size/2 - 20; + trg_size = SIZE(trg_entry); + if (!DELTA(trg_entry)) { + max_size = trg_size/2 - the_hash_algo->rawsz; ref_depth = 1; } else { - max_size = trg_entry->delta_size; + max_size = DELTA_SIZE(trg_entry); ref_depth = trg->depth; } max_size = (uint64_t)max_size * (max_depth - src->depth) / (max_depth - ref_depth + 1); if (max_size == 0) return 0; - src_size = src_entry->size; + src_size = SIZE(src_entry); sizediff = src_size < trg_size ? trg_size - src_size : 0; if (sizediff >= max_size) return 0; if (trg_size < src_size / 32) return 0; + if (!in_same_island(&trg->entry->idx.oid, &src->entry->idx.oid)) + return 0; + /* Load data if not already done */ if (!trg->data) { - read_lock(); - trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz); - read_unlock(); + packing_data_lock(&to_pack); + trg->data = read_object_file(&trg_entry->idx.oid, &type, &sz); + packing_data_unlock(&to_pack); if (!trg->data) - die("object %s cannot be read", - sha1_to_hex(trg_entry->idx.sha1)); + die(_("object %s cannot be read"), + 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); + die(_("object %s inconsistent object length (%"PRIuMAX" vs %"PRIuMAX")"), + oid_to_hex(&trg_entry->idx.oid), (uintmax_t)sz, + (uintmax_t)trg_size); *mem_usage += sz; } if (!src->data) { - read_lock(); - src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz); - read_unlock(); + packing_data_lock(&to_pack); + src->data = read_object_file(&src_entry->idx.oid, &type, &sz); + packing_data_unlock(&to_pack); 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)); + warning(_("object %s cannot be read"), + oid_to_hex(&src_entry->idx.oid)); /* * Those objects are not included in the * resulting pack. Be resilient and ignore @@ -1582,12 +2526,13 @@ 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)); + die(_("object %s cannot be read"), + 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); + die(_("object %s inconsistent object length (%"PRIuMAX" vs %"PRIuMAX")"), + oid_to_hex(&src_entry->idx.oid), (uintmax_t)sz, + (uintmax_t)src_size); *mem_usage += sz; } if (!src->index) { @@ -1595,7 +2540,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, if (!src->index) { static int warned = 0; if (!warned++) - warning("suboptimal pack - out of memory"); + warning(_("suboptimal pack - out of memory")); return 0; } *mem_usage += sizeof_delta_index(src->index); @@ -1605,9 +2550,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, if (!delta_buf) return 0; - if (trg_entry->delta) { + if (DELTA(trg_entry)) { /* Prefer only shallower same-sized deltas. */ - if (delta_size == trg_entry->delta_size && + if (delta_size == DELTA_SIZE(trg_entry) && src->depth + 1 >= trg->depth) { free(delta_buf); return 0; @@ -1622,7 +2567,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(trg_entry->delta_data); cache_lock(); if (trg_entry->delta_data) { - delta_cache_size -= trg_entry->delta_size; + delta_cache_size -= DELTA_SIZE(trg_entry); trg_entry->delta_data = NULL; } if (delta_cacheable(src_size, trg_size, delta_size)) { @@ -1634,8 +2579,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(delta_buf); } - trg_entry->delta = src_entry; - trg_entry->delta_size = delta_size; + SET_DELTA(trg_entry, src_entry); + SET_DELTA_SIZE(trg_entry, delta_size); trg->depth = src->depth + 1; return 1; @@ -1643,13 +2588,13 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { - struct object_entry *child = me->delta_child; + struct object_entry *child = DELTA_CHILD(me); unsigned int m = n; while (child) { - unsigned int c = check_delta_limit(child, n + 1); + const unsigned int c = check_delta_limit(child, n + 1); if (m < c) m = c; - child = child->delta_sibling; + child = DELTA_SIBLING(child); } return m; } @@ -1660,9 +2605,8 @@ static unsigned long free_unpacked(struct unpacked *n) free_delta_index(n->index); n->index = NULL; if (n->data) { - freed_mem += n->entry->size; - free(n->data); - n->data = NULL; + freed_mem += SIZE(n->entry); + FREE_AND_NULL(n->data); } n->entry = NULL; n->depth = 0; @@ -1676,7 +2620,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, struct unpacked *array; unsigned long mem_usage = 0; - array = xcalloc(window, sizeof(struct unpacked)); + CALLOC_ARRAY(array, window); for (;;) { struct object_entry *entry; @@ -1702,7 +2646,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, while (window_memory_limit && mem_usage > window_memory_limit && count > 1) { - uint32_t tail = (idx + window - count) % window; + const uint32_t tail = (idx + window - count) % window; mem_usage -= free_unpacked(array + tail); count--; } @@ -1719,7 +2663,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * otherwise they would become too deep. */ max_depth = depth; - if (entry->delta_child) { + if (DELTA_CHILD(entry)) { max_depth -= check_delta_limit(entry, 0); if (max_depth <= 0) goto next; @@ -1757,19 +2701,26 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * between writes at that moment. */ if (entry->delta_data && !pack_to_stdout) { - entry->z_delta_size = do_compress(&entry->delta_data, - entry->delta_size); - cache_lock(); - delta_cache_size -= entry->delta_size; - delta_cache_size += entry->z_delta_size; - cache_unlock(); + unsigned long size; + + size = do_compress(&entry->delta_data, DELTA_SIZE(entry)); + if (size < (1U << OE_Z_DELTA_BITS)) { + entry->z_delta_size = size; + cache_lock(); + delta_cache_size -= DELTA_SIZE(entry); + delta_cache_size += entry->z_delta_size; + cache_unlock(); + } else { + FREE_AND_NULL(entry->delta_data); + entry->z_delta_size = 0; + } } /* if we made n a delta, and if n is already at max * depth, leaving it in the window is pointless. we * should evict it first. */ - if (entry->delta && max_depth <= n->depth) + if (DELTA(entry) && max_depth <= n->depth) continue; /* @@ -1777,7 +2728,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * currently deltified object, to keep it longer. It will * be the first base object to be attempted next. */ - if (entry->delta) { + if (DELTA(entry)) { struct unpacked swap = array[best_base]; int dist = (window + idx - best_base) % window; int dst = best_base; @@ -1804,24 +2755,20 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, free(array); } -#ifndef NO_PTHREADS - -static void try_to_free_from_threads(size_t size) -{ - read_lock(); - release_pack_memory(size, -1); - read_unlock(); -} - -static try_to_free_t old_try_to_free_routine; - /* + * The main object list is split into smaller lists, each is handed to + * one worker. + * * The main thread waits on the condition that (at least) one of the workers * has stopped working (which is indicated in the .working member of * struct thread_params). + * * When a work thread has completed its work, it sets .working to 0 and * signals the main thread and waits on the condition that .data_ready * becomes 1. + * + * The main thread steals half of the work from the worker that has + * most work left to hand it to the idle worker. */ struct thread_params { @@ -1845,18 +2792,14 @@ static pthread_cond_t progress_cond; */ static void init_threaded_search(void) { - init_recursive_mutex(&read_mutex); pthread_mutex_init(&cache_mutex, NULL); pthread_mutex_init(&progress_mutex, NULL); pthread_cond_init(&progress_cond, NULL); - old_try_to_free_routine = set_try_to_free_routine(try_to_free_from_threads); } static void cleanup_threaded_search(void) { - set_try_to_free_routine(old_try_to_free_routine); pthread_cond_destroy(&progress_cond); - pthread_mutex_destroy(&read_mutex); pthread_mutex_destroy(&cache_mutex); pthread_mutex_destroy(&progress_mutex); } @@ -1865,7 +2808,10 @@ 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); @@ -1887,7 +2833,10 @@ 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; } @@ -1900,17 +2849,15 @@ 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(); return; } if (progress > pack_to_stdout) - fprintf(stderr, "Delta compression using up to %d threads.\n", - delta_search_threads); - p = xcalloc(delta_search_threads, sizeof(*p)); + fprintf_ln(stderr, _("Delta compression using up to %d threads"), + delta_search_threads); + CALLOC_ARRAY(p, delta_search_threads); /* Partition the work amongst work threads. */ for (i = 0; i < delta_search_threads; i++) { @@ -1949,7 +2896,7 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, ret = pthread_create(&p[i].thread, NULL, threaded_find_deltas, &p[i]); if (ret) - die("unable to create thread: %s", strerror(ret)); + die(_("unable to create thread: %s"), strerror(ret)); active_threads++; } @@ -2023,18 +2970,48 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, free(p); } -#else -#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p) -#endif +static int obj_is_packed(const struct object_id *oid) +{ + return packlist_find(&to_pack, oid) || + (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)); +} -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; + + /* + * 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 (obj_is_packed(oid)) + return; + + tag = lookup_tag(the_repository, 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, OBJ_TAG, NULL, 0); - if (!prefixcmp(path, "refs/tags/") && /* is a tag? */ - !peel_ref(path, peeled) && /* peelable? */ - locate_object_entry(peeled)) /* object packed? */ - add_object_entry(sha1, OBJ_TAG, NULL, 0); + if (tag->tagged->type != OBJ_TAG) + return; + + tag = (struct tag *)tag->tagged; + } +} + +static int add_ref_tag(const char *tag, const struct object_id *oid, int flag, void *cb_data) +{ + struct object_id peeled; + + if (!peel_iterated_oid(oid, &peeled) && obj_is_packed(&peeled)) + add_tag_chain(oid); return 0; } @@ -2044,6 +3021,9 @@ static void prepare_pack(int window, int depth) uint32_t i, nr_deltas; unsigned n; + if (use_delta_islands) + resolve_tree_islands(the_repository, progress, &to_pack); + get_object_details(); /* @@ -2056,22 +3036,23 @@ 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) + if (DELTA(entry)) /* This happens if we decided to reuse existing * delta from a pack. "reuse_delta &&" is implied. */ continue; - if (entry->size < 50) + if (!entry->type_valid || + oe_size_less_than(&to_pack, entry, 50)) continue; if (entry->no_try_delta) @@ -2079,11 +3060,11 @@ static void prepare_pack(int window, int depth) if (!entry->preferred_base) { nr_deltas++; - if (entry->type < 0) - die("unable to get type of object %s", - sha1_to_hex(entry->idx.sha1)); + if (oe_type(entry) < 0) + die(_("unable to get type of object %s"), + oid_to_hex(&entry->idx.oid)); } else { - if (entry->type < 0) { + if (oe_type(entry) < 0) { /* * This object is not found, but we * don't have to include it anyway. @@ -2097,14 +3078,15 @@ 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) - die("inconsistency with delta count"); + die(_("inconsistency with delta count")); } free(delta_list); } @@ -2123,16 +3105,6 @@ 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; @@ -2141,86 +3113,403 @@ 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.allowpackreuse")) { + allow_pack_reuse = 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)", + die(_("invalid number of threads specified (%d)"), delta_search_threads); -#ifdef NO_PTHREADS - if (delta_search_threads != 1) - warning("no threads support, ignoring %s", k); -#endif + if (!HAVE_THREADS && delta_search_threads != 1) { + warning(_("no threads support, ignoring %s"), k); + delta_search_threads = 0; + } return 0; } if (!strcmp(k, "pack.indexversion")) { pack_idx_opts.version = git_config_int(k, v); if (pack_idx_opts.version > 2) - die("bad pack.indexversion=%"PRIu32, + die(_("bad pack.indexversion=%"PRIu32), pack_idx_opts.version); return 0; } + if (!strcmp(k, "pack.writereverseindex")) { + if (git_config_bool(k, v)) + pack_idx_opts.flags |= WRITE_REV; + else + pack_idx_opts.flags &= ~WRITE_REV; + return 0; + } + if (!strcmp(k, "uploadpack.blobpackfileuri")) { + struct configured_exclusion *ex = xmalloc(sizeof(*ex)); + const char *oid_end, *pack_end; + /* + * Stores the pack hash. This is not a true object ID, but is + * of the same form. + */ + struct object_id pack_hash; + + if (parse_oid_hex(v, &ex->e.oid, &oid_end) || + *oid_end != ' ' || + parse_oid_hex(oid_end + 1, &pack_hash, &pack_end) || + *pack_end != ' ') + die(_("value of uploadpack.blobpackfileuri must be " + "of the form '<object-hash> <pack-hash> <uri>' (got '%s')"), v); + if (oidmap_get(&configured_exclusions, &ex->e.oid)) + die(_("object already configured in another " + "uploadpack.blobpackfileuri (got '%s')"), v); + ex->pack_hash_hex = xcalloc(1, pack_end - oid_end); + memcpy(ex->pack_hash_hex, oid_end + 1, pack_end - oid_end - 1); + ex->uri = xstrdup(pack_end + 1); + oidmap_put(&configured_exclusions, ex); + } return git_default_config(k, v, cb); } +/* Counters for trace2 output when in --stdin-packs mode. */ +static int stdin_packs_found_nr; +static int stdin_packs_hints_nr; + +static int add_object_entry_from_pack(const struct object_id *oid, + struct packed_git *p, + uint32_t pos, + void *_data) +{ + struct rev_info *revs = _data; + struct object_info oi = OBJECT_INFO_INIT; + off_t ofs; + enum object_type type; + + display_progress(progress_state, ++nr_seen); + + if (have_duplicate_entry(oid, 0)) + return 0; + + ofs = nth_packed_object_offset(p, pos); + if (!want_object_in_pack(oid, 0, &p, &ofs)) + return 0; + + oi.typep = &type; + if (packed_object_info(the_repository, p, ofs, &oi) < 0) + die(_("could not get type of object %s in pack %s"), + oid_to_hex(oid), p->pack_name); + else if (type == OBJ_COMMIT) { + /* + * commits in included packs are used as starting points for the + * subsequent revision walk + */ + add_pending_oid(revs, NULL, oid, 0); + } + + stdin_packs_found_nr++; + + create_object_entry(oid, type, 0, 0, 0, p, ofs); + + return 0; +} + +static void show_commit_pack_hint(struct commit *commit, void *_data) +{ + /* nothing to do; commits don't have a namehash */ +} + +static void show_object_pack_hint(struct object *object, const char *name, + void *_data) +{ + struct object_entry *oe = packlist_find(&to_pack, &object->oid); + if (!oe) + return; + + /* + * Our 'to_pack' list was constructed by iterating all objects packed in + * included packs, and so doesn't have a non-zero hash field that you + * would typically pick up during a reachability traversal. + * + * Make a best-effort attempt to fill in the ->hash and ->no_try_delta + * here using a now in order to perhaps improve the delta selection + * process. + */ + oe->hash = pack_name_hash(name); + oe->no_try_delta = name && no_try_delta(name); + + stdin_packs_hints_nr++; +} + +static int pack_mtime_cmp(const void *_a, const void *_b) +{ + struct packed_git *a = ((const struct string_list_item*)_a)->util; + struct packed_git *b = ((const struct string_list_item*)_b)->util; + + /* + * order packs by descending mtime so that objects are laid out + * roughly as newest-to-oldest + */ + if (a->mtime < b->mtime) + return 1; + else if (b->mtime < a->mtime) + return -1; + else + return 0; +} + +static void read_packs_list_from_stdin(void) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list include_packs = STRING_LIST_INIT_DUP; + struct string_list exclude_packs = STRING_LIST_INIT_DUP; + struct string_list_item *item = NULL; + + struct packed_git *p; + struct rev_info revs; + + repo_init_revisions(the_repository, &revs, NULL); + /* + * Use a revision walk to fill in the namehash of objects in the include + * packs. To save time, we'll avoid traversing through objects that are + * in excluded packs. + * + * That may cause us to avoid populating all of the namehash fields of + * all included objects, but our goal is best-effort, since this is only + * an optimization during delta selection. + */ + revs.no_kept_objects = 1; + revs.keep_pack_cache_flags |= IN_CORE_KEEP_PACKS; + revs.blob_objects = 1; + revs.tree_objects = 1; + revs.tag_objects = 1; + revs.ignore_missing_links = 1; + + while (strbuf_getline(&buf, stdin) != EOF) { + if (!buf.len) + continue; + + if (*buf.buf == '^') + string_list_append(&exclude_packs, buf.buf + 1); + else + string_list_append(&include_packs, buf.buf); + + strbuf_reset(&buf); + } + + string_list_sort(&include_packs); + string_list_sort(&exclude_packs); + + for (p = get_all_packs(the_repository); p; p = p->next) { + const char *pack_name = pack_basename(p); + + item = string_list_lookup(&include_packs, pack_name); + if (!item) + item = string_list_lookup(&exclude_packs, pack_name); + + if (item) + item->util = p; + } + + /* + * Arguments we got on stdin may not even be packs. First + * check that to avoid segfaulting later on in + * e.g. pack_mtime_cmp(), excluded packs are handled below. + * + * Since we first parsed our STDIN and then sorted the input + * lines the pack we error on will be whatever line happens to + * sort first. This is lazy, it's enough that we report one + * bad case here, we don't need to report the first/last one, + * or all of them. + */ + for_each_string_list_item(item, &include_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + } + + /* + * Then, handle all of the excluded packs, marking them as + * kept in-core so that later calls to add_object_entry() + * discards any objects that are also found in excluded packs. + */ + for_each_string_list_item(item, &exclude_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + p->pack_keep_in_core = 1; + } + + /* + * Order packs by ascending mtime; use QSORT directly to access the + * string_list_item's ->util pointer, which string_list_sort() does not + * provide. + */ + QSORT(include_packs.items, include_packs.nr, pack_mtime_cmp); + + for_each_string_list_item(item, &include_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + for_each_object_in_pack(p, + add_object_entry_from_pack, + &revs, + FOR_EACH_OBJECT_PACK_ORDER); + } + + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + traverse_commit_list(&revs, + show_commit_pack_hint, + show_object_pack_hint, + NULL); + + trace2_data_intmax("pack-objects", the_repository, "stdin_packs_found", + stdin_packs_found_nr); + trace2_data_intmax("pack-objects", the_repository, "stdin_packs_hints", + stdin_packs_hints_nr); + + strbuf_release(&buf); + string_list_clear(&include_packs, 0); + string_list_clear(&exclude_packs, 0); +} + static void read_object_list_from_stdin(void) { - char line[40 + 1 + PATH_MAX + 2]; - unsigned char sha1[20]; + char line[GIT_MAX_HEXSZ + 1 + PATH_MAX + 2]; + struct object_id oid; + const char *p; for (;;) { if (!fgets(line, sizeof(line), stdin)) { if (feof(stdin)) break; if (!ferror(stdin)) - die("fgets returned NULL, not EOF, not error!"); + die("BUG: fgets returned NULL, not EOF, not error!"); if (errno != EINTR) die_errno("fgets"); clearerr(stdin); continue; } if (line[0] == '-') { - if (get_sha1_hex(line+1, sha1)) - die("expected edge sha1, got garbage:\n %s", + if (get_oid_hex(line+1, &oid)) + die(_("expected edge object ID, got garbage:\n %s"), line); - add_preferred_base(sha1); + add_preferred_base(&oid); continue; } - if (get_sha1_hex(line, sha1)) - die("expected sha1, got garbage:\n %s", line); + if (parse_oid_hex(line, &oid, &p)) + die(_("expected object ID, got garbage:\n %s"), line); - add_preferred_base_object(line+41); - add_object_entry(sha1, 0, line+41, 0); + add_preferred_base_object(p + 1); + add_object_entry(&oid, OBJ_NONE, p + 1, 0); } } +/* Remember to update object flag allocation in object.h */ #define OBJECT_ADDED (1u<<20) 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, OBJ_COMMIT, NULL, 0); commit->object.flags |= OBJECT_ADDED; + + if (write_bitmap_index) + index_commit_for_bitmap(commit); + + if (use_delta_islands) + propagate_island_marks(commit); } -static void show_object(struct object *obj, - const struct name_path *path, const char *last, - void *data) +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, obj->type, name, 0); obj->flags |= OBJECT_ADDED; + if (use_delta_islands) { + const char *p; + unsigned depth; + struct object_entry *ent; + + /* the empty string is a root tree, which is depth 0 */ + depth = *name ? 1 : 0; + for (p = strchr(name, '/'); p; p = strchr(p + 1, '/')) + depth++; + + ent = packlist_find(&to_pack, &obj->oid); + if (ent && depth > oe_tree_depth(&to_pack, ent)) + oe_set_tree_depth(&to_pack, ent, depth); + } +} + +static void show_object__ma_allow_any(struct object *obj, const char *name, void *data) +{ + assert(arg_missing_action == MA_ALLOW_ANY); + + /* + * Quietly ignore ALL missing objects. This avoids problems with + * staging them now and getting an odd error later. + */ + if (!has_object(the_repository, &obj->oid, 0)) + return; + + show_object(obj, name, data); +} + +static void show_object__ma_allow_promisor(struct object *obj, const char *name, void *data) +{ + assert(arg_missing_action == MA_ALLOW_PROMISOR); + /* - * We will have generated the hash from the name, - * but not saved a pointer to it - we can free it + * Quietly ignore EXPECTED missing objects. This avoids problems with + * staging them now and getting an odd error later. */ - free((char *)name); + if (!has_object(the_repository, &obj->oid, 0) && is_promisor_object(&obj->oid)) + return; + + show_object(obj, name, data); +} + +static int option_parse_missing_action(const struct option *opt, + const char *arg, int unset) +{ + assert(arg); + assert(!unset); + + if (!strcmp(arg, "error")) { + arg_missing_action = MA_ERROR; + fn_show_object = show_object; + return 0; + } + + if (!strcmp(arg, "allow-any")) { + arg_missing_action = MA_ALLOW_ANY; + fetch_if_missing = 0; + fn_show_object = show_object__ma_allow_any; + return 0; + } + + if (!strcmp(arg, "allow-promisor")) { + arg_missing_action = MA_ALLOW_PROMISOR; + fetch_if_missing = 0; + fn_show_object = show_object__ma_allow_promisor; + return 0; + } + + die(_("invalid value for --missing")); + return 0; } static void show_edge(struct commit *commit) { - add_preferred_base(commit->object.sha1); + add_preferred_base(&commit->object.oid); } struct in_pack_object { @@ -2229,14 +3518,14 @@ 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++; } @@ -2255,10 +3544,10 @@ 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) +static void add_objects_in_unpacked_packs(void) { struct packed_git *p; struct in_pack in_pack; @@ -2266,22 +3555,22 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) memset(&in_pack, 0, sizeof(in_pack)); - for (p = packed_git; p; p = p->next) { - const unsigned char *sha1; + for (p = get_all_packs(the_repository); p; p = p->next) { + struct object_id oid; struct object *o; - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) - die("cannot open pack index"); + die(_("cannot open pack index")); ALLOC_GROW(in_pack.array, in_pack.nr + p->num_objects, in_pack.alloc); for (i = 0; i < p->num_objects; i++) { - sha1 = nth_packed_object_sha1(p, i); - o = lookup_unknown_object(sha1); + nth_packed_object_id(&oid, p, i); + o = lookup_unknown_object(the_repository, &oid); if (!(o->flags & OBJECT_ADDED)) mark_in_pack_object(o, p, &in_pack); o->flags |= OBJECT_ADDED; @@ -2289,31 +3578,58 @@ 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, o->type, "", 0); } } free(in_pack.array); } -static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) +static int add_loose_object(const struct object_id *oid, const char *path, + void *data) +{ + enum object_type type = oid_object_info(the_repository, oid, NULL); + + if (type < 0) { + warning(_("loose object at %s could not be examined"), path); + return 0; + } + + add_object_entry(oid, 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 struct object_id *oid) { static struct packed_git *last_found = (void *)1; struct packed_git *p; - p = (last_found != (void *)1) ? last_found : packed_git; + p = (last_found != (void *)1) ? last_found : + get_all_packs(the_repository); while (p) { - if ((!p->pack_local || p->pack_keep) && - find_pack_entry_one(sha1, p)) { + if ((!p->pack_local || p->pack_keep || + p->pack_keep_in_core) && + find_pack_entry_one(oid->hash, p)) { last_found = p; return 1; } if (p == last_found) - p = packed_git; + p = get_all_packs(the_repository); else p = p->next; if (p == last_found) @@ -2322,42 +3638,156 @@ static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) return 0; } -static void loosen_unused_packed_objects(struct rev_info *revs) +/* + * 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(void) { struct packed_git *p; uint32_t i; - const unsigned char *sha1; - - for (p = packed_git; p; p = p->next) { - if (!p->pack_local || p->pack_keep) - continue; + uint32_t loosened_objects_nr = 0; + struct object_id oid; - if (unpack_unreachable_expiration && - p->mtime < unpack_unreachable_expiration) + for (p = get_all_packs(the_repository); p; p = p->next) { + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) - die("cannot open pack index"); + die(_("cannot open pack index")); for (i = 0; i < p->num_objects; i++) { - sha1 = nth_packed_object_sha1(p, i); - if (!locate_object_entry(sha1) && - !has_sha1_pack_kept_or_nonlocal(sha1)) - if (force_object_loose(sha1, p->mtime)) - die("unable to force loose object"); + nth_packed_object_id(&oid, p, i); + if (!packlist_find(&to_pack, &oid) && + !has_sha1_pack_kept_or_nonlocal(&oid) && + !loosened_object_can_be_discarded(&oid, p->mtime)) { + if (force_object_loose(&oid, p->mtime)) + die(_("unable to force loose object")); + loosened_objects_nr++; + } } } + + trace2_data_intmax("pack-objects", the_repository, + "loosen_unused_packed_objects/loosened", loosened_objects_nr); +} + +/* + * 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 allow_pack_reuse && + pack_to_stdout && + !ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && + (!local || !have_non_local_packs) && + !incremental; +} + +static int get_object_list_from_bitmap(struct rev_info *revs) +{ + if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options, 0))) + return -1; + + if (pack_options_allow_reuse() && + !reuse_partial_packfile_from_bitmap( + bitmap_git, + &reuse_packfile, + &reuse_packfile_objects, + &reuse_packfile_bitmap)) { + assert(reuse_packfile_objects); + nr_result += reuse_packfile_objects; + nr_seen += reuse_packfile_objects; + display_progress(progress_state, nr_seen); + } + + traverse_bitmap_commit_list(bitmap_git, revs, + &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 int mark_bitmap_preferred_tip(const char *refname, + const struct object_id *oid, int flags, + void *_data) +{ + struct object_id peeled; + struct object *object; + + if (!peel_iterated_oid(oid, &peeled)) + oid = &peeled; + + object = parse_object_or_die(oid, refname); + if (object->type == OBJ_COMMIT) + object->flags |= NEEDS_BITMAP; + + return 0; +} + +static void mark_bitmap_preferred_tips(void) +{ + struct string_list_item *item; + const struct string_list *preferred_tips; + + preferred_tips = bitmap_preferred_tips(the_repository); + if (!preferred_tips) + return; + + for_each_string_list_item(item, preferred_tips) { + for_each_ref_in(item->string, mark_bitmap_preferred_tip, NULL); + } } static void get_object_list(int ac, const char **av) { struct rev_info revs; + struct setup_revision_opt s_r_opt = { + .allow_exclude_promisor_objects = 1, + }; char line[1000]; int flags = 0; + int save_warning; - init_revisions(&revs, NULL); + repo_init_revisions(the_repository, &revs, NULL); save_commit_buffer = 0; - setup_revisions(ac, av, &revs, NULL); + setup_revisions(ac, av, &revs, &s_r_opt); + + /* make sure shallows are read */ + is_repository_shallow(the_repository); + + save_warning = warn_on_object_refname_ambiguity; + warn_on_object_refname_ambiguity = 0; while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); @@ -2368,23 +3798,89 @@ static void get_object_list(int ac, const char **av) if (*line == '-') { if (!strcmp(line, "--not")) { flags ^= UNINTERESTING; + write_bitmap_index = 0; continue; } - die("not a rev '%s'", line); + if (starts_with(line, "--shallow ")) { + struct object_id oid; + if (get_oid_hex(line + 10, &oid)) + die("not an object name '%s'", line + 10); + register_shallow(the_repository, &oid); + use_bitmap_index = 0; + continue; + } + die(_("not a rev '%s'"), line); } if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME)) - die("bad revision '%s'", line); + die(_("bad revision '%s'"), line); } + warn_on_object_refname_ambiguity = save_warning; + + if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) + return; + + if (use_delta_islands) + load_delta_islands(the_repository, progress); + + if (write_bitmap_index) + mark_bitmap_preferred_tips(); + if (prepare_revision_walk(&revs)) - die("revision walk setup failed"); - mark_edges_uninteresting(revs.commits, &revs, show_edge); - traverse_commit_list(&revs, show_commit, show_object, NULL); + die(_("revision walk setup failed")); + mark_edges_uninteresting(&revs, show_edge, sparse); + + if (!fn_show_object) + fn_show_object = show_object; + traverse_commit_list_filtered(&filter_options, &revs, + show_commit, fn_show_object, NULL, + 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); + add_objects_in_unpacked_packs(); + if (pack_loose_unreachable) + add_unreachable_loose_objects(); if (unpack_unreachable) - loosen_unused_packed_objects(&revs); + loosen_unused_packed_objects(); + + oid_array_clear(&recent_objects); +} + +static void add_extra_kept_packs(const struct string_list *names) +{ + struct packed_git *p; + + if (!names->nr) + return; + + for (p = get_all_packs(the_repository); p; p = p->next) { + const char *name = basename(p->pack_name); + int i; + + if (!p->pack_local) + continue; + + for (i = 0; i < names->nr; i++) + if (!fspathcmp(name, names->items[i].string)) + break; + + if (i < names->nr) { + p->pack_keep_in_core = 1; + ignore_packed_keep_in_core = 1; + continue; + } + } } static int option_parse_index_version(const struct option *opt, @@ -2392,6 +3888,9 @@ static int option_parse_index_version(const struct option *opt, { char *c; const char *val = arg; + + BUG_ON_OPT_NEG(unset); + pack_idx_opts.version = strtoul(val, &c, 10); if (pack_idx_opts.version > 2) die(_("unsupported index version %s"), val); @@ -2417,31 +3916,16 @@ static int option_parse_unpack_unreachable(const struct option *opt, return 0; } -static int option_parse_ulong(const struct option *opt, - const char *arg, int unset) -{ - if (unset) - die(_("option %s does not accept negative form"), - opt->long_name); - - if (!git_parse_ulong(arg, opt->value)) - die(_("unable to parse value '%s' for option %s"), - arg, opt->long_name); - return 0; -} - -#define OPT_ULONG(s, l, v, h) \ - { OPTION_CALLBACK, (s), (l), (v), "n", (h), \ - PARSE_OPT_NONEG, option_parse_ulong } - 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; - const char *rp_av[6]; - int rp_ac = 0; + struct strvec rp = STRVEC_INIT; int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; + int rev_list_index = 0; + int stdin_packs = 0; + struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, N_("do not show progress meter"), 0), @@ -2452,19 +3936,19 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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]"), + OPT_CALLBACK_F(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_ULONG(0, "max-pack-size", &pack_size_limit, - N_("maximum size of each output pack file")), + PARSE_OPT_NONEG, 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_ULONG(0, "window-memory", &window_memory_limit, - N_("limit pack window by memory in addition to object limit")), + 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, @@ -2479,41 +3963,82 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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 }, + OPT_SET_INT_F(0, "unpacked", &rev_list_unpacked, + N_("limit the objects to those that are not yet packed"), + 1, PARSE_OPT_NONEG), + OPT_SET_INT_F(0, "all", &rev_list_all, + N_("include objects reachable from any reference"), + 1, PARSE_OPT_NONEG), + OPT_SET_INT_F(0, "reflog", &rev_list_reflog, + N_("include objects referred by reflog entries"), + 1, PARSE_OPT_NONEG), + OPT_SET_INT_F(0, "indexed-objects", &rev_list_index, + N_("include objects referred to by the index"), + 1, PARSE_OPT_NONEG), + OPT_BOOL(0, "stdin-packs", &stdin_packs, + N_("read packs from stdin")), 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")), - { OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"), + OPT_BOOL(0, "pack-loose-unreachable", &pack_loose_unreachable, + N_("pack loose unreachable objects")), + OPT_CALLBACK_F(0, "unpack-unreachable", NULL, N_("time"), N_("unpack unreachable objects newer than <time>"), - PARSE_OPT_OPTARG, option_parse_unpack_unreachable }, + PARSE_OPT_OPTARG, option_parse_unpack_unreachable), + OPT_BOOL(0, "sparse", &sparse, + N_("use the sparse reachability algorithm")), OPT_BOOL(0, "thin", &thin, N_("create thin packs")), - OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep, + OPT_BOOL(0, "shallow", &shallow, + N_("create packs suitable for shallow fetches")), + OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk, N_("ignore packs that have companion .keep file")), + OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), + N_("ignore this pack")), 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_SET_INT(0, "write-bitmap-index", &write_bitmap_index, + N_("write a bitmap index together with the pack index"), + WRITE_BITMAP_TRUE), + OPT_SET_INT_F(0, "write-bitmap-index-quiet", + &write_bitmap_index, + N_("write a bitmap index if possible"), + WRITE_BITMAP_QUIET, PARSE_OPT_HIDDEN), + OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options), + OPT_CALLBACK_F(0, "missing", NULL, N_("action"), + N_("handling for missing objects"), PARSE_OPT_NONEG, + option_parse_missing_action), + OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects, + N_("do not pack objects in promisor packfiles")), + OPT_BOOL(0, "delta-islands", &use_delta_islands, + N_("respect islands during delta compression")), + OPT_STRING_LIST(0, "uri-protocol", &uri_protocols, + N_("protocol"), + N_("exclude any configured uploadpack.blobpackfileuri with this protocol")), OPT_END(), }; + if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) + BUG("too many dfs states, increase OE_DFS_STATE_BITS"); + read_replace_refs = 0; + sparse = git_env_bool("GIT_TEST_PACK_SPARSE", -1); + prepare_repo_settings(the_repository); + if (sparse < 0) + sparse = the_repository->settings.pack_use_sparse; + 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; + if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0)) + pack_idx_opts.flags |= WRITE_REV; progress = isatty(2); argc = parse_options(argc, argv, prefix, pack_objects_options, @@ -2526,77 +4051,192 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (pack_to_stdout != !base_name || argc) usage_with_options(pack_usage, pack_objects_options); - rp_av[rp_ac++] = "pack-objects"; + if (depth < 0) + depth = 0; + if (depth >= (1 << OE_DEPTH_BITS)) { + warning(_("delta chain depth %d is too deep, forcing %d"), + depth, (1 << OE_DEPTH_BITS) - 1); + depth = (1 << OE_DEPTH_BITS) - 1; + } + if (cache_max_small_delta_size >= (1U << OE_Z_DELTA_BITS)) { + warning(_("pack.deltaCacheLimit is too high, forcing %d"), + (1U << OE_Z_DELTA_BITS) - 1); + cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1; + } + if (window < 0) + window = 0; + + strvec_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--objects-edge"; + strvec_push(&rp, shallow + ? "--objects-edge-aggressive" + : "--objects-edge"); } else - rp_av[rp_ac++] = "--objects"; + strvec_push(&rp, "--objects"); if (rev_list_all) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--all"; + strvec_push(&rp, "--all"); } if (rev_list_reflog) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--reflog"; + strvec_push(&rp, "--reflog"); } - if (rev_list_unpacked) { + if (rev_list_index) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--unpacked"; + strvec_push(&rp, "--indexed-objects"); } + if (rev_list_unpacked && !stdin_packs) { + use_internal_rev_list = 1; + strvec_push(&rp, "--unpacked"); + } + + if (exclude_promisor_objects) { + use_internal_rev_list = 1; + fetch_if_missing = 0; + strvec_push(&rp, "--exclude-promisor-objects"); + } + if (unpack_unreachable || keep_unreachable || pack_loose_unreachable) + use_internal_rev_list = 1; 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); -#ifdef NO_PTHREADS - if (delta_search_threads != 1) - warning("no threads support, ignoring --threads"); -#endif + die(_("bad pack compression level %d"), pack_compression_level); + + if (!delta_search_threads) /* --threads=0 means autodetect */ + delta_search_threads = online_cpus(); + + if (!HAVE_THREADS && delta_search_threads != 1) + warning(_("no threads support, ignoring --threads")); if (!pack_to_stdout && !pack_size_limit) pack_size_limit = pack_size_limit_cfg; if (pack_to_stdout && pack_size_limit) - die("--max-pack-size cannot be used to build a pack for transfer."); + die(_("--max-pack-size cannot be used to build a pack for transfer")); if (pack_size_limit && pack_size_limit < 1024*1024) { - warning("minimum pack size limit is 1 MiB"); + warning(_("minimum pack size limit is 1 MiB")); pack_size_limit = 1024*1024; } if (!pack_to_stdout && thin) - die("--thin cannot be used to build an indexable pack."); + die(_("--thin cannot be used to build an indexable pack")); if (keep_unreachable && unpack_unreachable) - die("--keep-unreachable and --unpack-unreachable are incompatible."); + die(_("--keep-unreachable and --unpack-unreachable are incompatible")); + if (!rev_list_all || !rev_list_reflog || !rev_list_index) + unpack_unreachable_expiration = 0; + + if (filter_options.choice) { + if (!pack_to_stdout) + die(_("cannot use --filter without --stdout")); + if (stdin_packs) + die(_("cannot use --filter with --stdin-packs")); + } + + if (stdin_packs && use_internal_rev_list) + die(_("cannot use internal rev list with --stdin-packs")); + + /* + * "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(the_repository)) + use_bitmap_index = 0; + + if (pack_to_stdout || !rev_list_all) + write_bitmap_index = 0; + + if (use_delta_islands) + strvec_push(&rp, "--topo-order"); if (progress && all_progress_implied) progress = 2; - prepare_packed_git(); + add_extra_kept_packs(&keep_pack_list); + if (ignore_packed_keep_on_disk) { + struct packed_git *p; + for (p = get_all_packs(the_repository); p; p = p->next) + if (p->pack_local && p->pack_keep) + break; + if (!p) /* no keep-able packs found */ + ignore_packed_keep_on_disk = 0; + } + if (local) { + /* + * unlike ignore_packed_keep_on_disk 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 = get_all_packs(the_repository); p; p = p->next) { + if (!p->pack_local) { + have_non_local_packs = 1; + break; + } + } + } + + trace2_region_enter("pack-objects", "enumerate-objects", + the_repository); + prepare_packing_data(the_repository, &to_pack); if (progress) - progress_state = start_progress("Counting objects", 0); - if (!use_internal_rev_list) + progress_state = start_progress(_("Enumerating objects"), 0); + if (stdin_packs) { + /* avoids adding objects in excluded packs */ + ignore_packed_keep_in_core = 1; + read_packs_list_from_stdin(); + if (rev_list_unpacked) + add_unreachable_loose_objects(); + } else 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.nr, rp.v); + strvec_clear(&rp); } cleanup_preferred_base(); if (include_tag && nr_result) - for_each_ref(add_ref_tag, NULL); + for_each_tag_ref(add_ref_tag, NULL); stop_progress(&progress_state); + trace2_region_leave("pack-objects", "enumerate-objects", + the_repository); if (non_empty && !nr_result) return 0; - if (nr_result) + if (nr_result) { + trace2_region_enter("pack-objects", "prepare-pack", + the_repository); prepare_pack(window, depth); + trace2_region_leave("pack-objects", "prepare-pack", + the_repository); + } + + trace2_region_enter("pack-objects", "write-pack-file", the_repository); + write_excluded_by_configs(); write_pack_file(); + trace2_region_leave("pack-objects", "write-pack-file", the_repository); + if (progress) - fprintf(stderr, "Total %"PRIu32" (delta %"PRIu32")," - " reused %"PRIu32" (delta %"PRIu32")\n", - written, written_delta, reused, reused_delta); + fprintf_ln(stderr, + _("Total %"PRIu32" (delta %"PRIu32")," + " reused %"PRIu32" (delta %"PRIu32")," + " pack-reused %"PRIu32), + written, written_delta, reused, reused_delta, + reuse_packfile_objects); return 0; } |