diff options
Diffstat (limited to 'builtin/index-pack.c')
| -rw-r--r-- | builtin/index-pack.c | 651 |
1 files changed, 393 insertions, 258 deletions
diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 31046c7a0a..8336466865 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -14,9 +14,10 @@ #include "thread-utils.h" #include "packfile.h" #include "object-store.h" +#include "promisor-remote.h" static const char index_pack_usage[] = -"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])"; +"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])"; struct object_entry { struct pack_idx_entry idx; @@ -32,19 +33,61 @@ struct object_stat { }; struct base_data { + /* Initialized by make_base(). */ struct base_data *base; - struct base_data *child; struct object_entry *obj; - void *data; - unsigned long size; int ref_first, ref_last; int ofs_first, ofs_last; + /* + * Threads should increment retain_data if they are about to call + * patch_delta() using this struct's data as a base, and decrement this + * when they are done. While retain_data is nonzero, this struct's data + * will not be freed even if the delta base cache limit is exceeded. + */ + int retain_data; + /* + * The number of direct children that have not been fully processed + * (entered work_head, entered done_head, left done_head). When this + * number reaches zero, this struct base_data can be freed. + */ + int children_remaining; + + /* Not initialized by make_base(). */ + struct list_head list; + void *data; + unsigned long size; }; +/* + * Stack of struct base_data that have unprocessed children. + * threaded_second_pass() uses this as a source of work (the other being the + * objects array). + * + * Guarded by work_mutex. + */ +static LIST_HEAD(work_head); + +/* + * Stack of struct base_data that have children, all of whom have been + * processed or are being processed, and at least one child is being processed. + * These struct base_data must be kept around until the last child is + * processed. + * + * Guarded by work_mutex. + */ +static LIST_HEAD(done_head); + +/* + * All threads share one delta base cache. + * + * base_cache_used is guarded by work_mutex, and base_cache_limit is read-only + * in a thread. + */ +static size_t base_cache_used; +static size_t base_cache_limit; + struct thread_local { pthread_t thread; - struct base_data *base_cache; - size_t base_cache_used; int pack_fd; }; @@ -77,7 +120,7 @@ static int nr_threads; static int from_stdin; static int strict; static int do_fsck_object; -static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT; +static struct fsck_options fsck_options = FSCK_OPTIONS_MISSING_GITMODULES; static int verbose; static int show_resolving_progress; static int show_stat; @@ -116,10 +159,6 @@ static pthread_mutex_t deepest_delta_mutex; #define deepest_delta_lock() lock_mutex(&deepest_delta_mutex) #define deepest_delta_unlock() unlock_mutex(&deepest_delta_mutex) -static pthread_mutex_t type_cas_mutex; -#define type_cas_lock() lock_mutex(&type_cas_mutex) -#define type_cas_unlock() unlock_mutex(&type_cas_mutex) - static pthread_key_t key; static inline void lock_mutex(pthread_mutex_t *mutex) @@ -143,11 +182,10 @@ static void init_thread(void) init_recursive_mutex(&read_mutex); pthread_mutex_init(&counter_mutex, NULL); pthread_mutex_init(&work_mutex, NULL); - pthread_mutex_init(&type_cas_mutex, NULL); if (show_stat) pthread_mutex_init(&deepest_delta_mutex, NULL); pthread_key_create(&key, NULL); - thread_data = xcalloc(nr_threads, sizeof(*thread_data)); + CALLOC_ARRAY(thread_data, nr_threads); for (i = 0; i < nr_threads; i++) { thread_data[i].pack_fd = open(curr_pack, O_RDONLY); if (thread_data[i].pack_fd == -1) @@ -166,7 +204,6 @@ static void cleanup_thread(void) pthread_mutex_destroy(&read_mutex); pthread_mutex_destroy(&counter_mutex); pthread_mutex_destroy(&work_mutex); - pthread_mutex_destroy(&type_cas_mutex); if (show_stat) pthread_mutex_destroy(&deepest_delta_mutex); for (i = 0; i < nr_threads; i++) @@ -175,7 +212,8 @@ static void cleanup_thread(void) free(thread_data); } -static int mark_link(struct object *obj, int type, void *data, struct fsck_options *options) +static int mark_link(struct object *obj, enum object_type type, + void *data, struct fsck_options *options) { if (!obj) return -1; @@ -219,8 +257,16 @@ static unsigned check_objects(void) unsigned i, max, foreign_nr = 0; max = get_max_object_index(); - for (i = 0; i < max; i++) + + if (verbose) + progress = start_delayed_progress(_("Checking objects"), max); + + for (i = 0; i < max; i++) { foreign_nr += check_object(get_indexed_object(i)); + display_progress(progress, i + 1); + } + + stop_progress(&progress); return foreign_nr; } @@ -323,9 +369,7 @@ static void parse_pack_header(void) use(sizeof(struct pack_header)); } -static NORETURN void bad_object(off_t offset, const char *format, - ...) __attribute__((format (printf, 2, 3))); - +__attribute__((format (printf, 2, 3))) static NORETURN void bad_object(off_t offset, const char *format, ...) { va_list params; @@ -355,56 +399,42 @@ static void set_thread_data(struct thread_local *data) pthread_setspecific(key, data); } -static struct base_data *alloc_base_data(void) -{ - struct base_data *base = xcalloc(1, sizeof(struct base_data)); - base->ref_last = -1; - base->ofs_last = -1; - return base; -} - static void free_base_data(struct base_data *c) { if (c->data) { FREE_AND_NULL(c->data); - get_thread_data()->base_cache_used -= c->size; + base_cache_used -= c->size; } } static void prune_base_data(struct base_data *retain) { - struct base_data *b; - struct thread_local *data = get_thread_data(); - for (b = data->base_cache; - data->base_cache_used > delta_base_cache_limit && b; - b = b->child) { - if (b->data && b != retain) - free_base_data(b); - } -} + struct list_head *pos; -static void link_base_data(struct base_data *base, struct base_data *c) -{ - if (base) - base->child = c; - else - get_thread_data()->base_cache = c; + if (base_cache_used <= base_cache_limit) + return; - c->base = base; - c->child = NULL; - if (c->data) - get_thread_data()->base_cache_used += c->size; - prune_base_data(c); -} + list_for_each_prev(pos, &done_head) { + struct base_data *b = list_entry(pos, struct base_data, list); + if (b->retain_data || b == retain) + continue; + if (b->data) { + free_base_data(b); + if (base_cache_used <= base_cache_limit) + return; + } + } -static void unlink_base_data(struct base_data *c) -{ - struct base_data *base = c->base; - if (base) - base->child = NULL; - else - get_thread_data()->base_cache = NULL; - free_base_data(c); + list_for_each_prev(pos, &work_head) { + struct base_data *b = list_entry(pos, struct base_data, list); + if (b->retain_data || b == retain) + continue; + if (b->data) { + free_base_data(b); + if (base_cache_used <= base_cache_limit) + return; + } + } } static int is_delta_type(enum object_type type) @@ -457,7 +487,7 @@ static void *unpack_entry_data(off_t offset, unsigned long size, bad_object(offset, _("inflate returned %d"), status); git_inflate_end(&stream); if (oid) - the_hash_algo->final_fn(oid->hash, &c); + the_hash_algo->final_oid_fn(oid, &c); return buf == fixed_buf ? NULL : buf; } @@ -492,7 +522,7 @@ static void *unpack_raw_entry(struct object_entry *obj, switch (obj->type) { case OBJ_REF_DELTA: - hashcpy(ref_oid->hash, fill(the_hash_algo->rawsz)); + oidread(ref_oid, fill(the_hash_algo->rawsz)); use(the_hash_algo->rawsz); break; case OBJ_OFS_DELTA: @@ -605,7 +635,7 @@ static int compare_ofs_delta_bases(off_t offset1, off_t offset2, 0; } -static int find_ofs_delta(const off_t offset, enum object_type type) +static int find_ofs_delta(const off_t offset) { int first = 0, last = nr_ofs_deltas; @@ -615,7 +645,8 @@ static int find_ofs_delta(const off_t offset, enum object_type type) int cmp; cmp = compare_ofs_delta_bases(offset, delta->offset, - type, objects[delta->obj_no].type); + OBJ_OFS_DELTA, + objects[delta->obj_no].type); if (!cmp) return next; if (cmp < 0) { @@ -628,10 +659,9 @@ static int find_ofs_delta(const off_t offset, enum object_type type) } static void find_ofs_delta_children(off_t offset, - int *first_index, int *last_index, - enum object_type type) + int *first_index, int *last_index) { - int first = find_ofs_delta(offset, type); + int first = find_ofs_delta(offset); int last = first; int end = nr_ofs_deltas - 1; @@ -659,7 +689,7 @@ static int compare_ref_delta_bases(const struct object_id *oid1, return oidcmp(oid1, oid2); } -static int find_ref_delta(const struct object_id *oid, enum object_type type) +static int find_ref_delta(const struct object_id *oid) { int first = 0, last = nr_ref_deltas; @@ -669,7 +699,8 @@ static int find_ref_delta(const struct object_id *oid, enum object_type type) int cmp; cmp = compare_ref_delta_bases(oid, &delta->oid, - type, objects[delta->obj_no].type); + OBJ_REF_DELTA, + objects[delta->obj_no].type); if (!cmp) return next; if (cmp < 0) { @@ -682,10 +713,9 @@ static int find_ref_delta(const struct object_id *oid, enum object_type type) } static void find_ref_delta_children(const struct object_id *oid, - int *first_index, int *last_index, - enum object_type type) + int *first_index, int *last_index) { - int first = find_ref_delta(oid, type); + int first = find_ref_delta(oid); int last = first; int end = nr_ref_deltas - 1; @@ -748,7 +778,8 @@ static int check_collison(struct object_entry *entry) memset(&data, 0, sizeof(data)); data.entry = entry; - data.st = open_istream(&entry->idx.oid, &type, &size, NULL); + data.st = open_istream(the_repository, &entry->idx.oid, &type, &size, + NULL); if (!data.st) return -1; if (size != entry->size || type != entry->type) @@ -856,26 +887,15 @@ static void sha1_object(const void *data, struct object_entry *obj_entry, } /* - * This function is part of find_unresolved_deltas(). There are two - * walkers going in the opposite ways. - * - * The first one in find_unresolved_deltas() traverses down from - * parent node to children, deflating nodes along the way. However, - * memory for deflated nodes is limited by delta_base_cache_limit, so - * at some point parent node's deflated content may be freed. - * - * The second walker is this function, which goes from current node up - * to top parent if necessary to deflate the node. In normal - * situation, its parent node would be already deflated, so it just - * needs to apply delta. + * Ensure that this node has been reconstructed and return its contents. * - * In the worst case scenario, parent node is no longer deflated because - * we're running out of delta_base_cache_limit; we need to re-deflate - * parents, possibly up to the top base. - * - * All deflated objects here are subject to be freed if we exceed - * delta_base_cache_limit, just like in find_unresolved_deltas(), we - * just need to make sure the last node is not freed. + * In the typical and best case, this node would already be reconstructed + * (through the invocation to resolve_delta() in threaded_second_pass()) and it + * would not be pruned. However, if pruning of this node was necessary due to + * reaching delta_base_cache_limit, this function will find the closest + * ancestor with reconstructed data that has not been pruned (or if there is + * none, the ultimate base object), and reconstruct each node in the delta + * chain in order to generate the reconstructed data for this node. */ static void *get_base_data(struct base_data *c) { @@ -892,7 +912,7 @@ static void *get_base_data(struct base_data *c) if (!delta_nr) { c->data = get_data_from_pack(obj); c->size = obj->size; - get_thread_data()->base_cache_used += c->size; + base_cache_used += c->size; prune_base_data(c); } for (; delta_nr > 0; delta_nr--) { @@ -908,7 +928,7 @@ static void *get_base_data(struct base_data *c) free(raw); if (!c->data) bad_object(obj->idx.offset, _("failed to apply delta")); - get_thread_data()->base_cache_used += c->size; + base_cache_used += c->size; prune_base_data(c); } free(delta); @@ -916,10 +936,27 @@ static void *get_base_data(struct base_data *c) return c->data; } -static void resolve_delta(struct object_entry *delta_obj, - struct base_data *base, struct base_data *result) +static struct base_data *make_base(struct object_entry *obj, + struct base_data *parent) { - void *base_data, *delta_data; + struct base_data *base = xcalloc(1, sizeof(struct base_data)); + base->base = parent; + base->obj = obj; + find_ref_delta_children(&obj->idx.oid, + &base->ref_first, &base->ref_last); + find_ofs_delta_children(obj->idx.offset, + &base->ofs_first, &base->ofs_last); + base->children_remaining = base->ref_last - base->ref_first + + base->ofs_last - base->ofs_first + 2; + return base; +} + +static struct base_data *resolve_delta(struct object_entry *delta_obj, + struct base_data *base) +{ + void *delta_data, *result_data; + struct base_data *result; + unsigned long result_size; if (show_stat) { int i = delta_obj - objects; @@ -932,113 +969,26 @@ static void resolve_delta(struct object_entry *delta_obj, obj_stat[i].base_object_no = j; } delta_data = get_data_from_pack(delta_obj); - base_data = get_base_data(base); - result->obj = delta_obj; - result->data = patch_delta(base_data, base->size, - delta_data, delta_obj->size, &result->size); + assert(base->data); + result_data = patch_delta(base->data, base->size, + delta_data, delta_obj->size, &result_size); free(delta_data); - if (!result->data) + if (!result_data) bad_object(delta_obj->idx.offset, _("failed to apply delta")); - hash_object_file(result->data, result->size, + hash_object_file(the_hash_algo, result_data, result_size, type_name(delta_obj->real_type), &delta_obj->idx.oid); - sha1_object(result->data, NULL, result->size, delta_obj->real_type, + sha1_object(result_data, NULL, result_size, delta_obj->real_type, &delta_obj->idx.oid); + + result = make_base(delta_obj, base); + result->data = result_data; + result->size = result_size; + counter_lock(); nr_resolved_deltas++; counter_unlock(); -} - -/* - * Standard boolean compare-and-swap: atomically check whether "*type" is - * "want"; if so, swap in "set" and return true. Otherwise, leave it untouched - * and return false. - */ -static int compare_and_swap_type(signed char *type, - enum object_type want, - enum object_type set) -{ - enum object_type old; - - type_cas_lock(); - old = *type; - if (old == want) - *type = set; - type_cas_unlock(); - - return old == want; -} - -static struct base_data *find_unresolved_deltas_1(struct base_data *base, - struct base_data *prev_base) -{ - if (base->ref_last == -1 && base->ofs_last == -1) { - find_ref_delta_children(&base->obj->idx.oid, - &base->ref_first, &base->ref_last, - OBJ_REF_DELTA); - - find_ofs_delta_children(base->obj->idx.offset, - &base->ofs_first, &base->ofs_last, - OBJ_OFS_DELTA); - - if (base->ref_last == -1 && base->ofs_last == -1) { - free(base->data); - return NULL; - } - - link_base_data(prev_base, base); - } - - if (base->ref_first <= base->ref_last) { - struct object_entry *child = objects + ref_deltas[base->ref_first].obj_no; - struct base_data *result = alloc_base_data(); - - if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA, - base->obj->real_type)) - BUG("child->real_type != OBJ_REF_DELTA"); - - resolve_delta(child, base, result); - if (base->ref_first == base->ref_last && base->ofs_last == -1) - free_base_data(base); - base->ref_first++; - return result; - } - - if (base->ofs_first <= base->ofs_last) { - struct object_entry *child = objects + ofs_deltas[base->ofs_first].obj_no; - struct base_data *result = alloc_base_data(); - - assert(child->real_type == OBJ_OFS_DELTA); - child->real_type = base->obj->real_type; - resolve_delta(child, base, result); - if (base->ofs_first == base->ofs_last) - free_base_data(base); - - base->ofs_first++; - return result; - } - - unlink_base_data(base); - return NULL; -} - -static void find_unresolved_deltas(struct base_data *base) -{ - struct base_data *new_base, *prev_base = NULL; - for (;;) { - new_base = find_unresolved_deltas_1(base, prev_base); - - if (new_base) { - prev_base = base; - base = new_base; - } else { - free(base); - base = prev_base; - if (!base) - return; - prev_base = base->base; - } - } + return result; } static int compare_ofs_delta_entry(const void *a, const void *b) @@ -1059,34 +1009,135 @@ static int compare_ref_delta_entry(const void *a, const void *b) return oidcmp(&delta_a->oid, &delta_b->oid); } -static void resolve_base(struct object_entry *obj) -{ - struct base_data *base_obj = alloc_base_data(); - base_obj->obj = obj; - base_obj->data = NULL; - find_unresolved_deltas(base_obj); -} - static void *threaded_second_pass(void *data) { - set_thread_data(data); + if (data) + set_thread_data(data); for (;;) { - int i; + struct base_data *parent = NULL; + struct object_entry *child_obj; + struct base_data *child; + counter_lock(); display_progress(progress, nr_resolved_deltas); counter_unlock(); + work_lock(); - while (nr_dispatched < nr_objects && - is_delta_type(objects[nr_dispatched].type)) - nr_dispatched++; - if (nr_dispatched >= nr_objects) { - work_unlock(); - break; + if (list_empty(&work_head)) { + /* + * Take an object from the object array. + */ + while (nr_dispatched < nr_objects && + is_delta_type(objects[nr_dispatched].type)) + nr_dispatched++; + if (nr_dispatched >= nr_objects) { + work_unlock(); + break; + } + child_obj = &objects[nr_dispatched++]; + } else { + /* + * Peek at the top of the stack, and take a child from + * it. + */ + parent = list_first_entry(&work_head, struct base_data, + list); + + if (parent->ref_first <= parent->ref_last) { + int offset = ref_deltas[parent->ref_first++].obj_no; + child_obj = objects + offset; + if (child_obj->real_type != OBJ_REF_DELTA) + die("REF_DELTA at offset %"PRIuMAX" already resolved (duplicate base %s?)", + (uintmax_t) child_obj->idx.offset, + oid_to_hex(&parent->obj->idx.oid)); + child_obj->real_type = parent->obj->real_type; + } else { + child_obj = objects + + ofs_deltas[parent->ofs_first++].obj_no; + assert(child_obj->real_type == OBJ_OFS_DELTA); + child_obj->real_type = parent->obj->real_type; + } + + if (parent->ref_first > parent->ref_last && + parent->ofs_first > parent->ofs_last) { + /* + * This parent has run out of children, so move + * it to done_head. + */ + list_del(&parent->list); + list_add(&parent->list, &done_head); + } + + /* + * Ensure that the parent has data, since we will need + * it later. + * + * NEEDSWORK: If parent data needs to be reloaded, this + * prolongs the time that the current thread spends in + * the mutex. A mitigating factor is that parent data + * needs to be reloaded only if the delta base cache + * limit is exceeded, so in the typical case, this does + * not happen. + */ + get_base_data(parent); + parent->retain_data++; } - i = nr_dispatched++; work_unlock(); - resolve_base(&objects[i]); + if (parent) { + child = resolve_delta(child_obj, parent); + if (!child->children_remaining) + FREE_AND_NULL(child->data); + } else { + child = make_base(child_obj, NULL); + if (child->children_remaining) { + /* + * Since this child has its own delta children, + * we will need this data in the future. + * Inflate now so that future iterations will + * have access to this object's data while + * outside the work mutex. + */ + child->data = get_data_from_pack(child_obj); + child->size = child_obj->size; + } + } + + work_lock(); + if (parent) + parent->retain_data--; + if (child->data) { + /* + * This child has its own children, so add it to + * work_head. + */ + list_add(&child->list, &work_head); + base_cache_used += child->size; + prune_base_data(NULL); + } else { + /* + * This child does not have its own children. It may be + * the last descendant of its ancestors; free those + * that we can. + */ + struct base_data *p = parent; + + while (p) { + struct base_data *next_p; + + p->children_remaining--; + if (p->children_remaining) + break; + + next_p = p->base; + free_base_data(p); + list_del(&p->list); + free(p); + + p = next_p; + } + } + work_unlock(); } return NULL; } @@ -1187,6 +1238,7 @@ static void resolve_deltas(void) nr_ref_deltas + nr_ofs_deltas); nr_dispatched = 0; + base_cache_limit = delta_base_cache_limit * nr_threads; if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) { init_thread(); for (i = 0; i < nr_threads; i++) { @@ -1201,15 +1253,7 @@ static void resolve_deltas(void) cleanup_thread(); return; } - - for (i = 0; i < nr_objects; i++) { - struct object_entry *obj = &objects[i]; - - if (is_delta_type(obj->type)) - continue; - resolve_base(obj); - display_progress(progress, nr_resolved_deltas); - } + threaded_second_pass(¬hread_data); } /* @@ -1312,7 +1356,7 @@ static struct object_entry *append_obj_to_pack(struct hashfile *f, obj[1].idx.offset += write_compressed(f, buf, size); obj[0].idx.crc32 = crc32_end(f); hashflush(f); - hashcpy(obj->idx.oid.hash, sha1); + oidread(&obj->idx.oid, sha1); return obj; } @@ -1343,38 +1387,63 @@ static void fix_unresolved_deltas(struct hashfile *f) sorted_by_pos[i] = &ref_deltas[i]; QSORT(sorted_by_pos, nr_ref_deltas, delta_pos_compare); + if (has_promisor_remote()) { + /* + * Prefetch the delta bases. + */ + struct oid_array to_fetch = OID_ARRAY_INIT; + for (i = 0; i < nr_ref_deltas; i++) { + struct ref_delta_entry *d = sorted_by_pos[i]; + if (!oid_object_info_extended(the_repository, &d->oid, + NULL, + OBJECT_INFO_FOR_PREFETCH)) + continue; + oid_array_append(&to_fetch, &d->oid); + } + promisor_remote_get_direct(the_repository, + to_fetch.oid, to_fetch.nr); + oid_array_clear(&to_fetch); + } + for (i = 0; i < nr_ref_deltas; i++) { struct ref_delta_entry *d = sorted_by_pos[i]; enum object_type type; - struct base_data *base_obj = alloc_base_data(); + void *data; + unsigned long size; if (objects[d->obj_no].real_type != OBJ_REF_DELTA) continue; - base_obj->data = read_object_file(&d->oid, &type, - &base_obj->size); - if (!base_obj->data) + data = read_object_file(&d->oid, &type, &size); + if (!data) continue; - if (check_object_signature(&d->oid, base_obj->data, - base_obj->size, type_name(type))) + if (check_object_signature(the_repository, &d->oid, + data, size, + type_name(type))) die(_("local object %s is corrupt"), oid_to_hex(&d->oid)); - base_obj->obj = append_obj_to_pack(f, d->oid.hash, - base_obj->data, base_obj->size, type); - find_unresolved_deltas(base_obj); + + /* + * Add this as an object to the objects array and call + * threaded_second_pass() (which will pick up the added + * object). + */ + append_obj_to_pack(f, d->oid.hash, data, size, type); + threaded_second_pass(NULL); + display_progress(progress, nr_resolved_deltas); } free(sorted_by_pos); } -static const char *derive_filename(const char *pack_name, const char *suffix, - struct strbuf *buf) +static const char *derive_filename(const char *pack_name, const char *strip, + const char *suffix, struct strbuf *buf) { size_t len; - if (!strip_suffix(pack_name, ".pack", &len)) - die(_("packfile name '%s' does not end with '.pack'"), - pack_name); + if (!strip_suffix(pack_name, strip, &len) || !len || + pack_name[len - 1] != '.') + die(_("packfile name '%s' does not end with '.%s'"), + pack_name, strip); strbuf_add(buf, pack_name, len); - strbuf_addch(buf, '.'); strbuf_addstr(buf, suffix); return buf->buf; } @@ -1389,7 +1458,7 @@ static void write_special_file(const char *suffix, const char *msg, int msg_len = strlen(msg); if (pack_name) - filename = derive_filename(pack_name, suffix, &name_buf); + filename = derive_filename(pack_name, "pack", suffix, &name_buf); else filename = odb_pack_name(&name_buf, hash, suffix); @@ -1414,12 +1483,14 @@ static void write_special_file(const char *suffix, const char *msg, static void final(const char *final_pack_name, const char *curr_pack_name, const char *final_index_name, const char *curr_index_name, + const char *final_rev_index_name, const char *curr_rev_index_name, const char *keep_msg, const char *promisor_msg, unsigned char *hash) { const char *report = "pack"; struct strbuf pack_name = STRBUF_INIT; struct strbuf index_name = STRBUF_INIT; + struct strbuf rev_index_name = STRBUF_INIT; int err; if (!from_stdin) { @@ -1454,6 +1525,16 @@ static void final(const char *final_pack_name, const char *curr_pack_name, } else chmod(final_index_name, 0444); + if (curr_rev_index_name) { + if (final_rev_index_name != curr_rev_index_name) { + if (!final_rev_index_name) + final_rev_index_name = odb_pack_name(&rev_index_name, hash, "rev"); + if (finalize_object_file(curr_rev_index_name, final_rev_index_name)) + die(_("cannot store reverse index file")); + } else + chmod(final_rev_index_name, 0444); + } + if (do_fsck_object) { struct packed_git *p; p = add_packed_git(final_index_name, strlen(final_index_name), 0); @@ -1462,11 +1543,11 @@ static void final(const char *final_pack_name, const char *curr_pack_name, } if (!from_stdin) { - printf("%s\n", sha1_to_hex(hash)); + printf("%s\n", hash_to_hex(hash)); } else { struct strbuf buf = STRBUF_INIT; - strbuf_addf(&buf, "%s\t%s\n", report, sha1_to_hex(hash)); + strbuf_addf(&buf, "%s\t%s\n", report, hash_to_hex(hash)); write_or_die(1, buf.buf, buf.len); strbuf_release(&buf); @@ -1483,6 +1564,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name, } } + strbuf_release(&rev_index_name); strbuf_release(&index_name); strbuf_release(&pack_name); } @@ -1508,6 +1590,12 @@ static int git_index_pack_config(const char *k, const char *v, void *cb) } return 0; } + if (!strcmp(k, "pack.writereverseindex")) { + if (git_config_bool(k, v)) + opts->flags |= WRITE_REV; + else + opts->flags &= ~WRITE_REV; + } return git_default_config(k, v, cb); } @@ -1524,14 +1612,10 @@ static void read_v2_anomalous_offsets(struct packed_git *p, { const uint32_t *idx1, *idx2; uint32_t i; - const uint32_t hashwords = the_hash_algo->rawsz / sizeof(uint32_t); /* The address of the 4-byte offset table */ - idx1 = (((const uint32_t *)p->index_data) - + 2 /* 8-byte header */ - + 256 /* fan out */ - + hashwords * p->num_objects /* object ID table */ - + p->num_objects /* CRC32 table */ + idx1 = (((const uint32_t *)((const uint8_t *)p->index_data + p->crc_offset)) + + (size_t)p->num_objects /* CRC32 table */ ); /* The address of the 8-byte offset table */ @@ -1575,7 +1659,7 @@ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name) /* * Get rid of the idx file as we do not need it anymore. * NEEDSWORK: extract this bit from free_pack_by_name() in - * sha1-file.c, perhaps? It shouldn't matter very much as we + * object-file.c, perhaps? It shouldn't matter very much as we * know we haven't installed this pack (hence we never have * read anything from it). */ @@ -1589,7 +1673,7 @@ static void show_pack_info(int stat_only) unsigned long *chain_histogram = NULL; if (deepest_delta) - chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long)); + CALLOC_ARRAY(chain_histogram, deepest_delta); for (i = 0; i < nr_objects; i++) { struct object_entry *obj = &objects[i]; @@ -1629,21 +1713,26 @@ static void show_pack_info(int stat_only) int cmd_index_pack(int argc, const char **argv, const char *prefix) { - int i, fix_thin_pack = 0, verify = 0, stat_only = 0; + int i, fix_thin_pack = 0, verify = 0, stat_only = 0, rev_index; const char *curr_index; - const char *index_name = NULL, *pack_name = NULL; + const char *curr_rev_index = NULL; + const char *index_name = NULL, *pack_name = NULL, *rev_index_name = NULL; const char *keep_msg = NULL; const char *promisor_msg = NULL; struct strbuf index_name_buf = STRBUF_INIT; + struct strbuf rev_index_name_buf = STRBUF_INIT; struct pack_idx_entry **idx_objects; struct pack_idx_option opts; unsigned char pack_hash[GIT_MAX_RAWSZ]; unsigned foreign_nr = 1; /* zero is a "good" value, assume bad */ int report_end_of_input = 0; + int hash_algo = 0; /* - * index-pack never needs to fetch missing objects, since it only - * accesses the repo to do hash collision checks + * index-pack never needs to fetch missing objects except when + * REF_DELTA bases are missing (which are explicitly handled). It only + * accesses the repo to do hash collision checks and to check which + * REF_DELTA bases need to be fetched. */ fetch_if_missing = 0; @@ -1658,6 +1747,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) if (prefix && chdir(prefix)) die(_("Cannot come back to cwd")); + if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0)) + rev_index = 1; + else + rev_index = !!(opts.flags & (WRITE_REV_VERIFY | WRITE_REV)); + for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -1731,6 +1825,15 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) die(_("bad %s"), arg); } else if (skip_prefix(arg, "--max-input-size=", &arg)) { max_input_size = strtoumax(arg, NULL, 10); + } else if (skip_prefix(arg, "--object-format=", &arg)) { + hash_algo = hash_algo_by_name(arg); + if (hash_algo == GIT_HASH_UNKNOWN) + die(_("unknown hash algorithm '%s'"), arg); + repo_set_hash_algo(the_repository, hash_algo); + } else if (!strcmp(arg, "--rev-index")) { + rev_index = 1; + } else if (!strcmp(arg, "--no-rev-index")) { + rev_index = 0; } else usage(index_pack_usage); continue; @@ -1747,8 +1850,19 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) die(_("--fix-thin cannot be used without --stdin")); if (from_stdin && !startup_info->have_repository) die(_("--stdin requires a git repository")); + if (from_stdin && hash_algo) + die(_("--object-format cannot be used with --stdin")); if (!index_name && pack_name) - index_name = derive_filename(pack_name, "idx", &index_name_buf); + index_name = derive_filename(pack_name, "pack", "idx", &index_name_buf); + + opts.flags &= ~(WRITE_REV | WRITE_REV_VERIFY); + if (rev_index) { + opts.flags |= verify ? WRITE_REV_VERIFY : WRITE_REV; + if (index_name) + rev_index_name = derive_filename(index_name, + "idx", "rev", + &rev_index_name_buf); + } if (verify) { if (!index_name) @@ -1761,17 +1875,30 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) if (HAVE_THREADS && !nr_threads) { nr_threads = online_cpus(); - /* An experiment showed that more threads does not mean faster */ - if (nr_threads > 3) - nr_threads = 3; + /* + * Experiments show that going above 20 threads doesn't help, + * no matter how many cores you have. Below that, we tend to + * max at half the number of online_cpus(), presumably because + * half of those are hyperthreads rather than full cores. We'll + * never reduce the level below "3", though, to match a + * historical value that nobody complained about. + */ + if (nr_threads < 4) + ; /* too few cores to consider capping */ + else if (nr_threads < 6) + nr_threads = 3; /* historic cap */ + else if (nr_threads < 40) + nr_threads /= 2; + else + nr_threads = 20; /* hard cap */ } curr_pack = open_pack_file(pack_name); parse_pack_header(); - objects = xcalloc(st_add(nr_objects, 1), sizeof(struct object_entry)); + CALLOC_ARRAY(objects, st_add(nr_objects, 1)); if (show_stat) - obj_stat = xcalloc(st_add(nr_objects, 1), sizeof(struct object_stat)); - ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry)); + CALLOC_ARRAY(obj_stat, st_add(nr_objects, 1)); + CALLOC_ARRAY(ofs_deltas, nr_objects); parse_pack_objects(pack_hash); if (report_end_of_input) write_in_full(2, "\0", 1); @@ -1789,11 +1916,16 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) for (i = 0; i < nr_objects; i++) idx_objects[i] = &objects[i].idx; curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash); + if (rev_index) + curr_rev_index = write_rev_file(rev_index_name, idx_objects, + nr_objects, pack_hash, + opts.flags); free(idx_objects); if (!verify) final(pack_name, curr_pack, index_name, curr_index, + rev_index_name, curr_rev_index, keep_msg, promisor_msg, pack_hash); else @@ -1804,10 +1936,13 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) free(objects); strbuf_release(&index_name_buf); + strbuf_release(&rev_index_name_buf); if (pack_name == NULL) free((void *) curr_pack); if (index_name == NULL) free((void *) curr_index); + if (rev_index_name == NULL) + free((void *) curr_rev_index); /* * Let the caller know this pack is not self contained |