#include "diff.h"
#include "revision.h"
#include "list-objects.h"
+#include "pack-objects.h"
#include "progress.h"
#include "refs.h"
#include "streaming.h"
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.
+ * Objects we are going to pack are collected in the `to_pack` structure.
+ * It contains an array (dynamically expanded) of the object data, and a map
+ * that can resolve SHA1s to their position in the array.
*/
-static struct object_entry *objects;
+static struct packing_data to_pack;
+
static struct pack_idx_entry **written_list;
-static uint32_t nr_objects, nr_alloc, nr_result, nr_written;
+static uint32_t nr_result, nr_written;
static int non_empty;
static int reuse_delta = 1, reuse_object = 1;
static 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);
-
/*
* stats
*/
static uint32_t written, written_delta;
static uint32_t reused, reused_delta;
-
static void *get_delta(struct object_entry *entry)
{
unsigned long size, base_size, delta_size;
void *cb_data)
{
unsigned char peeled[20];
- struct object_entry *entry = locate_object_entry(sha1);
+ struct object_entry *entry = packlist_find(&to_pack, sha1, NULL);
if (entry)
entry->tagged = 1;
if (!peel_ref(path, peeled)) {
- entry = locate_object_entry(peeled);
+ entry = packlist_find(&to_pack, peeled, NULL);
if (entry)
entry->tagged = 1;
}
{
unsigned int i, wo_end, last_untagged;
- struct object_entry **wo = xmalloc(nr_objects * sizeof(*wo));
+ struct object_entry **wo = xmalloc(to_pack.nr_objects * sizeof(*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;
* 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)
continue;
* Give the objects in the original recency order until
* we see a tagged tip.
*/
- for (i = wo_end = 0; i < nr_objects; i++) {
+ 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]);
/*
* Then fill all the tagged tips.
*/
- for (; i < nr_objects; i++) {
+ 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 < nr_objects; i++) {
+ for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (objects[i].type != OBJ_COMMIT &&
objects[i].type != OBJ_TAG)
continue;
/*
* And then all the trees.
*/
- for (i = last_untagged; i < nr_objects; i++) {
+ for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (objects[i].type != OBJ_TREE)
continue;
add_to_write_order(wo, &wo_end, &objects[i]);
/*
* Finally all the rest in really tight order
*/
- for (i = last_untagged; i < nr_objects; i++) {
+ for (i = last_untagged; i < to_pack.nr_objects; i++) {
if (!objects[i].filled)
add_family_to_write_order(wo, &wo_end, &objects[i]);
}
- if (wo_end != nr_objects)
- die("ordered %u objects, expected %"PRIu32, wo_end, nr_objects);
+ if (wo_end != to_pack.nr_objects)
+ die("ordered %u objects, expected %"PRIu32, wo_end, to_pack.nr_objects);
return wo;
}
if (progress > pack_to_stdout)
progress_state = start_progress("Writing objects", nr_result);
- written_list = xmalloc(nr_objects * sizeof(*written_list));
+ written_list = xmalloc(to_pack.nr_objects * sizeof(*written_list));
write_order = compute_write_order();
do {
if (!offset)
die_errno("unable to write pack header");
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;
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);
written, nr_result);
}
-static int locate_object_entry_hash(const unsigned char *sha1)
-{
- int i;
- unsigned int ui;
- memcpy(&ui, sha1, sizeof(unsigned int));
- i = ui % object_ix_hashsz;
- while (0 < object_ix[i]) {
- if (!hashcmp(sha1, objects[object_ix[i] - 1].idx.sha1))
- return i;
- if (++i == object_ix_hashsz)
- i = 0;
- }
- return -1 - i;
-}
-
-static struct object_entry *locate_object_entry(const unsigned char *sha1)
-{
- int i;
-
- if (!object_ix_hashsz)
- return NULL;
-
- i = locate_object_entry_hash(sha1);
- if (0 <= i)
- return &objects[object_ix[i]-1];
- return NULL;
-}
-
-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;
- }
-}
-
-static unsigned name_hash(const char *name)
-{
- unsigned c, hash = 0;
-
- if (!name)
- 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.
- */
- while ((c = *name++) != 0) {
- if (isspace(c))
- continue;
- hash = (hash >> 2) + (c << 24);
- }
- return hash;
-}
-
static void setup_delta_attr_check(struct git_attr_check *check)
{
static struct git_attr *attr_delta;
return 0;
}
-static int add_object_entry(const unsigned char *sha1, enum object_type type,
- const char *name, int exclude)
+/*
+ * When adding an object, check whether we have already added it
+ * to our packing list. If so, we can skip. However, if we are
+ * being asked to excludei t, but the previous mention was to include
+ * it, make sure to adjust its flags and tweak our numbers accordingly.
+ *
+ * As an optimization, we pass out the index position where we would have
+ * found the item, since that saves us from having to look it up again a
+ * few lines later when we want to add the new entry.
+ */
+static int have_duplicate_entry(const unsigned char *sha1,
+ int exclude,
+ uint32_t *index_pos)
{
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;
- }
+
+ entry = packlist_find(&to_pack, sha1, index_pos);
+ if (!entry)
return 0;
+
+ if (exclude) {
+ if (!entry->preferred_base)
+ nr_result--;
+ entry->preferred_base = 1;
}
+ return 1;
+}
+
+/*
+ * 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).
+ *
+ * As a side effect of this check, we will find the packed version of this
+ * object, if any. We therefore pass out the pack information to avoid having
+ * to look it up again later.
+ */
+static int want_object_in_pack(const unsigned char *sha1,
+ int exclude,
+ struct packed_git **found_pack,
+ off_t *found_offset)
+{
+ struct packed_git *p;
+
if (!exclude && local && has_loose_object_nonlocal(sha1))
return 0;
+ *found_pack = NULL;
+ *found_offset = 0;
+
for (p = packed_git; p; p = p->next) {
off_t offset = find_pack_entry_one(sha1, p);
if (offset) {
- if (!found_pack) {
+ if (!*found_pack) {
if (!is_pack_valid(p)) {
warning("packfile %s cannot be accessed", p->pack_name);
continue;
}
- found_offset = offset;
- found_pack = p;
+ *found_offset = offset;
+ *found_pack = p;
}
if (exclude)
- break;
+ return 1;
if (incremental)
return 0;
if (local && !p->pack_local)
}
}
- if (nr_objects >= nr_alloc) {
- nr_alloc = (nr_alloc + 1024) * 3 / 2;
- objects = xrealloc(objects, nr_alloc * sizeof(*entry));
- }
+ return 1;
+}
- entry = objects + nr_objects++;
- memset(entry, 0, sizeof(*entry));
- hashcpy(entry->idx.sha1, sha1);
+static void create_object_entry(const unsigned char *sha1,
+ enum object_type type,
+ uint32_t hash,
+ int exclude,
+ int no_try_delta,
+ uint32_t index_pos,
+ struct packed_git *found_pack,
+ off_t found_offset)
+{
+ struct object_entry *entry;
+
+ entry = packlist_alloc(&to_pack, sha1, index_pos);
entry->hash = hash;
if (type)
entry->type = type;
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 int add_object_entry(const unsigned char *sha1, enum object_type type,
+ const char *name, int exclude)
+{
+ struct packed_git *found_pack;
+ off_t found_offset;
+ uint32_t index_pos;
+
+ if (have_duplicate_entry(sha1, exclude, &index_pos))
+ return 0;
- display_progress(progress_state, nr_objects);
+ if (!want_object_in_pack(sha1, exclude, &found_pack, &found_offset))
+ return 0;
- if (name && no_try_delta(name))
- entry->no_try_delta = 1;
+ create_object_entry(sha1, type, pack_name_hash(name),
+ exclude, name && no_try_delta(name),
+ index_pos, found_pack, found_offset);
+ display_progress(progress_state, to_pack.nr_objects);
return 1;
}
{
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;
break;
}
- if (base_ref && (base_entry = locate_object_entry(base_ref))) {
+ if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) {
/*
* If base_ref was set above that means we wish to
* reuse delta data, and we even found that base
uint32_t i;
struct object_entry **sorted_by_offset;
- sorted_by_offset = xcalloc(nr_objects, sizeof(struct object_entry *));
- for (i = 0; i < nr_objects; i++)
- sorted_by_offset[i] = objects + i;
- qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort);
+ sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *));
+ for (i = 0; i < to_pack.nr_objects; i++)
+ sorted_by_offset[i] = to_pack.objects + i;
+ qsort(sorted_by_offset, to_pack.nr_objects, sizeof(*sorted_by_offset), 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)
if (!prefixcmp(path, "refs/tags/") && /* is a tag? */
!peel_ref(path, peeled) && /* peelable? */
- locate_object_entry(peeled)) /* object packed? */
+ packlist_find(&to_pack, peeled, NULL)) /* object packed? */
add_object_entry(sha1, OBJ_TAG, NULL, 0);
return 0;
}
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));
+ delta_list = xmalloc(to_pack.nr_objects * sizeof(*delta_list));
nr_deltas = n = 0;
- for (i = 0; i < nr_objects; i++) {
- struct object_entry *entry = objects + i;
+ for (i = 0; i < to_pack.nr_objects; i++) {
+ struct object_entry *entry = to_pack.objects + i;
if (entry->delta)
/* This happens if we decided to reuse existing
for (i = 0; i < p->num_objects; i++) {
sha1 = nth_packed_object_sha1(p, i);
- if (!locate_object_entry(sha1) &&
+ if (!packlist_find(&to_pack, sha1, NULL) &&
!has_sha1_pack_kept_or_nonlocal(sha1))
if (force_object_loose(sha1, p->mtime))
die("unable to force loose object");
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
- mark_edges_uninteresting(revs.commits, &revs, show_edge);
+ mark_edges_uninteresting(&revs, show_edge);
traverse_commit_list(&revs, show_commit, show_object, NULL);
if (keep_unreachable)