#include "streaming.h"
#include "thread-utils.h"
#include "pack-bitmap.h"
+#include "delta-islands.h"
#include "reachable.h"
#include "sha1-array.h"
#include "argv-array.h"
#include "packfile.h"
#include "object-store.h"
#include "dir.h"
+#include "midx.h"
#define IN_PACK(obj) oe_in_pack(&to_pack, obj)
#define SIZE(obj) oe_size(&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 struct pack_idx_entry **written_list;
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 depth = 50;
static int delta_search_threads;
static int pack_to_stdout;
+static int thin;
static int num_preferred_base;
static struct progress *progress_state;
static int exclude_promisor_objects;
+static int use_delta_islands;
+
static unsigned long delta_cache_size = 0;
static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;
static unsigned long cache_max_small_delta_size = 1000;
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;
add_descendants_to_write_order(wo, endp, root);
}
-static struct object_entry **compute_write_order(void)
+static void compute_layer_order(struct object_entry **wo, unsigned int *wo_end)
{
- unsigned int i, wo_end, last_untagged;
-
- struct object_entry **wo;
+ unsigned int i, last_untagged;
struct object_entry *objects = to_pack.objects;
for (i = 0; i < to_pack.nr_objects; i++) {
- objects[i].tagged = 0;
- objects[i].filled = 0;
- SET_DELTA_CHILD(&objects[i], NULL);
- SET_DELTA_SIBLING(&objects[i], NULL);
- }
-
- /*
- * Fully connect delta_child/delta_sibling network.
- * Make sure delta_sibling is sorted in the original
- * recency order.
- */
- for (i = to_pack.nr_objects; i > 0;) {
- struct object_entry *e = &objects[--i];
- if (!DELTA(e))
- continue;
- /* Mark me as the first child */
- e->delta_sibling_idx = DELTA(e)->delta_child_idx;
- SET_DELTA_CHILD(DELTA(e), e);
- }
-
- /*
- * Mark objects that are at the tip of tags.
- */
- for_each_tag_ref(mark_tagged, NULL);
-
- /*
- * Give the objects in the original recency order until
- * we see a tagged tip.
- */
- ALLOC_ARRAY(wo, to_pack.nr_objects);
- for (i = wo_end = 0; i < to_pack.nr_objects; i++) {
if (objects[i].tagged)
break;
- add_to_write_order(wo, &wo_end, &objects[i]);
+ add_to_write_order(wo, wo_end, &objects[i]);
}
last_untagged = i;
*/
for (; i < to_pack.nr_objects; i++) {
if (objects[i].tagged)
- add_to_write_order(wo, &wo_end, &objects[i]);
+ add_to_write_order(wo, wo_end, &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]);
+ add_to_write_order(wo, wo_end, &objects[i]);
}
/*
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]);
+ add_to_write_order(wo, wo_end, &objects[i]);
}
/*
* Finally all the rest in really tight order
*/
for (i = last_untagged; i < to_pack.nr_objects; i++) {
- if (!objects[i].filled)
- add_family_to_write_order(wo, &wo_end, &objects[i]);
+ if (!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)
+{
+ uint32_t max_layers = 1;
+ unsigned int i, wo_end;
+
+ struct object_entry **wo;
+ struct object_entry *objects = to_pack.objects;
+
+ for (i = 0; i < to_pack.nr_objects; i++) {
+ objects[i].tagged = 0;
+ objects[i].filled = 0;
+ SET_DELTA_CHILD(&objects[i], NULL);
+ SET_DELTA_SIBLING(&objects[i], NULL);
+ }
+
+ /*
+ * Fully connect delta_child/delta_sibling network.
+ * Make sure delta_sibling is sorted in the original
+ * recency order.
+ */
+ for (i = to_pack.nr_objects; i > 0;) {
+ struct object_entry *e = &objects[--i];
+ if (!DELTA(e))
+ continue;
+ /* Mark me as the first child */
+ e->delta_sibling_idx = DELTA(e)->delta_child_idx;
+ SET_DELTA_CHILD(DELTA(e), e);
+ }
+
+ /*
+ * Mark objects that are at the tip of tags.
+ */
+ for_each_tag_ref(mark_tagged, NULL);
+
+ if (use_delta_islands)
+ max_layers = compute_pack_layers(&to_pack);
+
+ 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),
if (!check)
check = attr_check_initl("delta", NULL);
- if (git_check_attr(path, check))
- return 0;
+ git_check_attr(&the_index, path, check);
if (ATTR_FALSE(check->items[0].value))
return 1;
return 0;
{
int want;
struct list_head *pos;
+ struct multi_pack_index *m;
if (!exclude && local && has_loose_object_nonlocal(oid))
return 0;
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(oid, &e, m)) {
+ struct packed_git *p = e.p;
+ off_t offset;
+
+ 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))
+ continue;
+ *found_offset = offset;
+ *found_pack = p;
+ }
+ want = want_found_object(exclude, p);
+ if (want != -1)
+ return want;
+ }
+ }
+ }
+
list_for_each(pos, get_packed_git_mru(the_repository)) {
struct packed_git *p = list_entry(pos, struct packed_git, mru);
off_t offset;
*/
for (neigh = 0; neigh < 8; neigh++) {
ent = pbase_tree_cache[my_ix];
- if (ent && !oidcmp(&ent->oid, oid)) {
+ if (ent && oideq(&ent->oid, oid)) {
ent->ref++;
return ent;
}
return;
for (it = pbase_tree; it; it = it->next) {
- if (!oidcmp(&it->pcache.oid, &tree_oid)) {
+ if (oideq(&it->pcache.oid, &tree_oid)) {
free(data);
return;
}
done_pbase_paths_num = done_pbase_paths_alloc = 0;
}
+/*
+ * 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 unsigned char *base_sha1,
+ struct object_entry *delta,
+ struct object_entry **base_out)
+{
+ struct object_entry *base;
+
+ if (!base_sha1)
+ return 0;
+
+ /*
+ * First see if we're already sending the base (or it's explicitly in
+ * our "excluded" list).
+ */
+ base = packlist_find(&to_pack, base_sha1, NULL);
+ 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_sha1_in_uninteresting(bitmap_git, base_sha1)) {
+ if (use_delta_islands) {
+ struct object_id base_oid;
+ hashcpy(base_oid.hash, base_sha1);
+ if (!in_same_island(&delta->idx.oid, &base_oid))
+ return 0;
+ }
+ *base_out = NULL;
+ return 1;
+ }
+
+ return 0;
+}
+
static void check_object(struct object_entry *entry)
{
unsigned long canonical_size;
break;
}
- if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) {
- /*
- * If base_ref was set above that means we wish to
- * reuse delta data, and we even found that base
- * 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.
- */
+ if (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(entry, base_entry);
SET_DELTA_SIZE(entry, in_pack_size);
- entry->delta_sibling_idx = base_entry->delta_child_idx;
- SET_DELTA_CHILD(base_entry, entry);
+
+ 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;
}
return -1;
if (a->preferred_base < b->preferred_base)
return 1;
+ if (use_delta_islands) {
+ 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)
return 0;
}
-#ifndef NO_PTHREADS
-
+/* Protect access to object database */
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
-
-#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
-
-#endif
+/*
+ * 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.
+ */
/*
* Return the size of the object without doing any delta
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();
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)"),
- oid_to_hex(&trg_entry->idx.oid), 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) {
oid_to_hex(&src_entry->idx.oid));
}
if (sz != src_size)
- die(_("object %s inconsistent object length (%lu vs %lu)"),
- oid_to_hex(&src_entry->idx.oid), 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) {
delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
if (!delta_buf)
return 0;
- if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
- free(delta_buf);
- return 0;
- }
if (DELTA(trg_entry)) {
/* Prefer only shallower same-sized deltas. */
free(array);
}
-#ifndef NO_PTHREADS
-
static void try_to_free_from_threads(size_t size)
{
read_lock();
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 {
free(p);
}
-#else
-#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p)
-#endif
-
static void add_tag_chain(const struct object_id *oid)
{
struct tag *tag;
if (packlist_find(&to_pack, oid->hash, NULL))
return;
- tag = lookup_tag(oid);
+ tag = lookup_tag(the_repository, oid);
while (1) {
if (!tag || parse_tag(tag) || !tag->tagged)
die(_("unable to pack objects reachable from tag %s"),
uint32_t i, nr_deltas;
unsigned n;
+ if (use_delta_islands)
+ resolve_tree_islands(progress, &to_pack);
+
get_object_details();
/*
if (delta_search_threads < 0)
die(_("invalid number of threads specified (%d)"),
delta_search_threads);
-#ifdef NO_PTHREADS
- if (delta_search_threads != 1) {
+ if (!HAVE_THREADS && delta_search_threads != 1) {
warning(_("no threads support, ignoring %s"), k);
delta_search_threads = 0;
}
-#endif
return 0;
}
if (!strcmp(k, "pack.indexversion")) {
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 char *name, void *data)
add_preferred_base_object(name);
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.hash, NULL);
+ 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)
memset(&in_pack, 0, sizeof(in_pack));
- for (p = get_packed_git(the_repository); p; p = p->next) {
+ for (p = get_all_packs(the_repository); p; p = p->next) {
struct object_id oid;
struct object *o;
struct packed_git *p;
p = (last_found != (void *)1) ? last_found :
- get_packed_git(the_repository);
+ get_all_packs(the_repository);
while (p) {
if ((!p->pack_local || p->pack_keep ||
return 1;
}
if (p == last_found)
- p = get_packed_git(the_repository);
+ p = get_all_packs(the_repository);
else
p = p->next;
if (p == last_found)
uint32_t i;
struct object_id oid;
- for (p = get_packed_git(the_repository); p; p = p->next) {
+ for (p = get_all_packs(the_repository); p; p = p->next) {
if (!p->pack_local || p->pack_keep || p->pack_keep_in_core)
continue;
static int get_object_list_from_bitmap(struct rev_info *revs)
{
- if (prepare_bitmap_walk(revs) < 0)
+ if (!(bitmap_git = prepare_bitmap_walk(revs)))
return -1;
if (pack_options_allow_reuse() &&
!reuse_partial_packfile_from_bitmap(
+ bitmap_git,
&reuse_packfile,
&reuse_packfile_objects,
&reuse_packfile_offset)) {
display_progress(progress_state, nr_result);
}
- traverse_bitmap_commit_list(&add_object_entry_from_bitmap);
+ traverse_bitmap_commit_list(bitmap_git, &add_object_entry_from_bitmap);
return 0;
}
struct rev_info revs;
char line[1000];
int flags = 0;
+ int save_warning;
- init_revisions(&revs, NULL);
+ repo_init_revisions(the_repository, &revs, NULL);
save_commit_buffer = 0;
+ revs.allow_exclude_promisor_objects_opt = 1;
setup_revisions(ac, av, &revs, NULL);
/* make sure shallows are read */
- is_repository_shallow();
+ 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);
struct object_id oid;
if (get_oid_hex(line + 10, &oid))
die("not an SHA-1 '%s'", line + 10);
- register_shallow(&oid);
+ register_shallow(the_repository, &oid);
use_bitmap_index = 0;
continue;
}
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();
+
if (prepare_revision_walk(&revs))
die(_("revision walk setup failed"));
mark_edges_uninteresting(&revs, show_edge);
if (!names->nr)
return;
- for (p = get_packed_git(the_repository); p; p = p->next) {
+ for (p = get_all_packs(the_repository); p; p = p->next) {
const char *name = basename(p->pack_name);
int i;
{
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);
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;
struct argv_array rp = ARGV_ARRAY_INIT;
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]"),
+ { OPTION_CALLBACK, 0, "index-version", NULL, N_("<version>[,<offset>]"),
N_("write the pack index file in the specified idx format version"),
- 0, option_parse_index_version },
+ 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,
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_END(),
};
if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS))
BUG("too many dfs states, increase OE_DFS_STATE_BITS");
- check_replace_refs = 0;
+ read_replace_refs = 0;
reset_pack_idx_option(&pack_idx_opts);
git_config(git_pack_config, NULL);
if (!delta_search_threads) /* --threads=0 means autodetect */
delta_search_threads = online_cpus();
-#ifdef NO_PTHREADS
- if (delta_search_threads != 1)
+ if (!HAVE_THREADS && delta_search_threads != 1)
warning(_("no threads support, ignoring --threads"));
-#endif
if (!pack_to_stdout && !pack_size_limit)
pack_size_limit = pack_size_limit_cfg;
if (pack_to_stdout && pack_size_limit)
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())
+ 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)
+ argv_array_push(&rp, "--topo-order");
+
if (progress && all_progress_implied)
progress = 2;
add_extra_kept_packs(&keep_pack_list);
if (ignore_packed_keep_on_disk) {
struct packed_git *p;
- for (p = get_packed_git(the_repository); p; p = p->next)
+ 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 */
* it also covers non-local objects
*/
struct packed_git *p;
- for (p = get_packed_git(the_repository); p; p = p->next) {
+ for (p = get_all_packs(the_repository); p; p = p->next) {
if (!p->pack_local) {
have_non_local_packs = 1;
break;