#include "reachable.h"
#include "sha1-array.h"
#include "argv-array.h"
+#include "mru.h"
static const char *pack_usage[] = {
N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"),
}
/* 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 sha1file *f, struct object_entry *entry,
+ unsigned long limit, int usable_delta)
{
struct packed_git *p = entry->in_pack;
struct pack_window *w_curs = NULL;
struct revindex_entry *revidx;
off_t offset;
enum object_type type = entry->type;
- unsigned long datalen;
+ off_t datalen;
unsigned char header[10], dheader[10];
unsigned hdrlen;
}
/* 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 sha1file *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)
struct object_entry *e,
off_t *offset)
{
- unsigned long size;
+ off_t size;
int recursing;
/*
if (!is_pack_valid(reuse_packfile))
die("packfile is invalid: %s", reuse_packfile->pack_name);
- fd = git_open_noatime(reuse_packfile->pack_name);
+ fd = git_open(reuse_packfile->pack_name);
if (fd < 0)
die_errno("unable to open packfile for reuse: %s",
reuse_packfile->pack_name);
struct packed_git **found_pack,
off_t *found_offset)
{
- struct packed_git *p;
+ struct mru_entry *entry;
int want;
if (!exclude && local && has_loose_object_nonlocal(sha1))
return want;
}
- for (p = packed_git; p; p = p->next) {
+ for (entry = packed_git_mru->head; entry; entry = entry->next) {
+ struct packed_git *p = entry->item;
off_t offset;
if (p == *found_pack)
*found_pack = p;
}
want = want_found_object(exclude, p);
+ if (!exclude && want > 0)
+ mru_mark(packed_git_mru, entry);
if (want != -1)
return want;
}
(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.
+ */
+static void drop_reused_delta(struct object_entry *entry)
+{
+ struct object_entry **p = &entry->delta->delta_child;
+ struct object_info oi = OBJECT_INFO_INIT;
+
+ while (*p) {
+ if (*p == entry)
+ *p = (*p)->delta_sibling;
+ else
+ p = &(*p)->delta_sibling;
+ }
+ entry->delta = NULL;
+
+ oi.sizep = &entry->size;
+ oi.typep = &entry->type;
+ if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) {
+ /*
+ * We failed to get the info from this pack for some reason;
+ * fall back to sha1_object_info, which may find another copy.
+ * And if that fails, the error will be recorded in entry->type
+ * and dealt with in prepare_pack().
+ */
+ entry->type = sha1_object_info(entry->idx.sha1, &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).
+ */
+static void break_delta_chains(struct object_entry *entry)
+{
+ /* If it's not a delta, it can't be part of a cycle. */
+ if (!entry->delta) {
+ entry->dfs_state = DFS_DONE;
+ return;
+ }
+
+ switch (entry->dfs_state) {
+ case DFS_NONE:
+ /*
+ * This is the first time we've seen the object. We mark it as
+ * part of the active potential cycle and recurse.
+ */
+ entry->dfs_state = DFS_ACTIVE;
+ break_delta_chains(entry->delta);
+ entry->dfs_state = DFS_DONE;
+ break;
+
+ case DFS_DONE:
+ /* object already examined, and not part of a cycle */
+ break;
+
+ case DFS_ACTIVE:
+ /*
+ * We found a cycle that needs broken. It would be correct to
+ * break any link in the chain, but it's convenient to
+ * break this one.
+ */
+ drop_reused_delta(entry);
+ entry->dfs_state = DFS_DONE;
+ break;
+ }
+}
+
static void get_object_details(void)
{
uint32_t i;
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);
+ QSORT(sorted_by_offset, to_pack.nr_objects, pack_offset_sort);
for (i = 0; i < to_pack.nr_objects; i++) {
struct object_entry *entry = sorted_by_offset[i];
entry->no_try_delta = 1;
}
+ /*
+ * 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);
}
#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;
+
+ /*
+ * We catch duplicates already in add_object_entry(), but we'd
+ * prefer to do this extra check to avoid having to parse the
+ * tag at all if we already know that it's being packed (e.g., if
+ * it was included via bitmaps, we would not have parsed it
+ * previously).
+ */
+ if (packlist_find(&to_pack, oid->hash, NULL))
+ return;
+
+ tag = lookup_tag(oid->hash);
+ while (1) {
+ if (!tag || parse_tag(tag) || !tag->tagged)
+ die("unable to pack objects reachable from tag %s",
+ oid_to_hex(oid));
+
+ add_object_entry(tag->object.oid.hash, OBJ_TAG, NULL, 0);
+
+ if (tag->tagged->type != OBJ_TAG)
+ return;
+
+ tag = (struct tag *)tag->tagged;
+ }
+}
+
static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data)
{
struct object_id peeled;
if (starts_with(path, "refs/tags/") && /* is a tag? */
!peel_ref(path, peeled.hash) && /* peelable? */
packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */
- add_object_entry(oid->hash, OBJ_TAG, NULL, 0);
+ add_tag_chain(oid);
return 0;
}
if (progress)
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)
}
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->oid.hash, o->type, "", 0);