summaryrefslogtreecommitdiff
path: root/pack-objects.c
diff options
context:
space:
mode:
authorJunio C Hamano <junkio@cox.net>2006-05-09 16:40:28 -0700
committerJunio C Hamano <junkio@cox.net>2006-05-09 16:40:28 -0700
commit4edd44725c621b3a2c6c9c4d8f130ceea2ba355a (patch)
tree8b8d2a6591053eb738933ac97c952a93f6ecebaf /pack-objects.c
parent2fc240a7b21c060529c1d2e19d6b483361f81f2a (diff)
parent06a9f9203570d21f9ef5fe219cdde527dcdf0990 (diff)
downloadgit-4edd44725c621b3a2c6c9c4d8f130ceea2ba355a.tar.gz
Merge branch 'np/delta'
* np/delta: improve diff-delta with sparse and/or repetitive data tiny optimization to diff-delta replace adler32 with Rabin's polynomial in diff-delta use delta index data when finding best delta matches split the diff-delta interface
Diffstat (limited to 'pack-objects.c')
-rw-r--r--pack-objects.c74
1 files changed, 39 insertions, 35 deletions
diff --git a/pack-objects.c b/pack-objects.c
index 53caed42dd..523a1c7da8 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -994,6 +994,7 @@ static int type_size_sort(const struct object_entry *a, const struct object_entr
struct unpacked {
struct object_entry *entry;
void *data;
+ struct delta_index *index;
};
/*
@@ -1004,61 +1005,56 @@ struct unpacked {
* more importantly, the bigger file is likely the more recent
* one.
*/
-static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_depth)
+static int try_delta(struct unpacked *trg, struct unpacked *src,
+ struct delta_index *src_index, unsigned max_depth)
{
- struct object_entry *cur_entry = cur->entry;
- struct object_entry *old_entry = old->entry;
- unsigned long size, oldsize, delta_size, sizediff;
- long max_size;
+ struct object_entry *trg_entry = trg->entry;
+ struct object_entry *src_entry = src->entry;
+ unsigned long size, src_size, delta_size, sizediff, max_size;
void *delta_buf;
/* Don't bother doing diffs between different types */
- if (cur_entry->type != old_entry->type)
+ if (trg_entry->type != src_entry->type)
return -1;
/* We do not compute delta to *create* objects we are not
* going to pack.
*/
- if (cur_entry->preferred_base)
+ if (trg_entry->preferred_base)
return -1;
- /* If the current object is at pack edge, take the depth the
+ /*
+ * If the current object is at pack edge, take the depth the
* objects that depend on the current object into account --
* otherwise they would become too deep.
*/
- if (cur_entry->delta_child) {
- if (max_depth <= cur_entry->delta_limit)
+ if (trg_entry->delta_child) {
+ if (max_depth <= trg_entry->delta_limit)
return 0;
- max_depth -= cur_entry->delta_limit;
+ max_depth -= trg_entry->delta_limit;
}
-
- if (old_entry->depth >= max_depth)
+ if (src_entry->depth >= max_depth)
return 0;
- /*
- * NOTE!
- *
- * We always delta from the bigger to the smaller, since that's
- * more space-efficient (deletes don't have to say _what_ they
- * delete).
- */
- size = cur_entry->size;
+ /* Now some size filtering euristics. */
+ size = trg_entry->size;
max_size = size / 2 - 20;
- if (cur_entry->delta)
- max_size = cur_entry->delta_size-1;
- oldsize = old_entry->size;
- sizediff = oldsize < size ? size - oldsize : 0;
+ if (trg_entry->delta)
+ max_size = trg_entry->delta_size-1;
+ src_size = src_entry->size;
+ sizediff = src_size < size ? size - src_size : 0;
if (sizediff >= max_size)
return 0;
- delta_buf = diff_delta(old->data, oldsize,
- cur->data, size, &delta_size, max_size);
+
+ delta_buf = create_delta(src_index, trg->data, size, &delta_size, max_size);
if (!delta_buf)
return 0;
- cur_entry->delta = old_entry;
- cur_entry->delta_size = delta_size;
- cur_entry->depth = old_entry->depth + 1;
+
+ trg_entry->delta = src_entry;
+ trg_entry->delta_size = delta_size;
+ trg_entry->depth = src_entry->depth + 1;
free(delta_buf);
- return 0;
+ return 1;
}
static void progress_interval(int signum)
@@ -1108,12 +1104,17 @@ static void find_deltas(struct object_entry **list, int window, int depth)
if (entry->size < 50)
continue;
-
+ if (n->index)
+ free_delta_index(n->index);
free(n->data);
n->entry = entry;
n->data = read_sha1_file(entry->sha1, type, &size);
if (size != entry->size)
- die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+ die("object %s inconsistent object length (%lu vs %lu)",
+ sha1_to_hex(entry->sha1), size, entry->size);
+ n->index = create_delta_index(n->data, size);
+ if (!n->index)
+ die("out of memory");
j = window;
while (--j > 0) {
@@ -1124,7 +1125,7 @@ static void find_deltas(struct object_entry **list, int window, int depth)
m = array + other_idx;
if (!m->entry)
break;
- if (try_delta(n, m, depth) < 0)
+ if (try_delta(n, m, m->index, depth) < 0)
break;
}
#if 0
@@ -1144,8 +1145,11 @@ static void find_deltas(struct object_entry **list, int window, int depth)
if (progress)
fputc('\n', stderr);
- for (i = 0; i < window; ++i)
+ for (i = 0; i < window; ++i) {
+ if (array[i].index)
+ free_delta_index(array[i].index);
free(array[i].data);
+ }
free(array);
}