Add a "max_size" parameter to diff_delta()

Anything that generates a delta to see if two objects are close usually
isn't interested in the delta ends up being bigger than some specified
size, and this allows us to stop delta generation early when that
happens.

7 files changed, 28 insertions, 17 deletions

diff --git a/delta.h b/delta.h
index df97ff84f..ccc0c9ece 100644
--- a/delta.h
+++ b/delta.h
@@ -4,7 +4,7 @@
 /* handling of delta buffers */
 extern void *diff_delta(void *from_buf, unsigned long from_size,
 			void *to_buf, unsigned long to_size,
-		        unsigned long *delta_size);
+		        unsigned long *delta_size, unsigned long max_size);
 extern void *patch_delta(void *src_buf, unsigned long src_size,
 			 void *delta_buf, unsigned long delta_size,
 			 unsigned long *dst_size);
diff --git a/diff-delta.c b/diff-delta.c
index 480f03cd1..fd9b37f49 100644
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -203,7 +203,8 @@ static void delta_cleanup(bdfile_t *bdf)
 
 void *diff_delta(void *from_buf, unsigned long from_size,
 		 void *to_buf, unsigned long to_size,
-		 unsigned long *delta_size)
+		 unsigned long *delta_size,
+		 unsigned long max_size)
 {
 	int i, outpos, outsize, inscnt, csize, msize, moff;
 	unsigned int fp;
@@ -312,6 +313,11 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 		}
 
 		/* next time around the largest possible output is 1 + 4 + 3 */
+		if (max_size && outpos > max_size) {
+			free(out);
+			delta_cleanup(&bdf);
+			return NULL;
+		}
 		if (outpos > outsize - 8) {
 			void *tmp = out;
 			outsize = outsize * 3 / 2;
diff --git a/diffcore-break.c b/diffcore-break.c
index 920062bfd..9852f9716 100644
--- a/diffcore-break.c
+++ b/diffcore-break.c
@@ -65,7 +65,7 @@ static int should_break(struct diff_filespec *src,
 
 	delta = diff_delta(src->data, src->size,
 			   dst->data, dst->size,
-			   &delta_size);
+			   &delta_size, ~0UL);
 
 	/* Estimate the edit size by interpreting delta. */
 	if (count_delta(delta, delta_size,
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 8fb45f0b8..29609c74b 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -165,7 +165,7 @@ static int estimate_similarity(struct diff_filespec *src,
 
 	delta = diff_delta(src->data, src->size,
 			   dst->data, dst->size,
-			   &delta_size);
+			   &delta_size, ~0UL);
 
 	/* A delta that has a lot of literal additions would have
 	 * big delta_size no matter what else it does.
diff --git a/mkdelta.c b/mkdelta.c
index 6470a94e5..d4c5f3b4e 100644
--- a/mkdelta.c
+++ b/mkdelta.c
@@ -278,7 +278,8 @@ int main(int argc, char **argv)
 				continue;
 			}
 			delta_buf = diff_delta(ref[r].buf, ref[r].size,
-					       trg.buf, trg.size, &delta_size);
+					       trg.buf, trg.size,
+					       &delta_size, ~0UL);
 			if (!delta_buf)
 				die("out of memory");
 			if (trg.depth < max_depth &&
diff --git a/pack-objects.c b/pack-objects.c
index dfa9d44a1..d9328a98d 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -83,8 +83,8 @@ static void *delta_against(void *buf, unsigned long size, struct object_entry *e
 
 	if (!otherbuf)
 		die("unable to read %s", sha1_to_hex(entry->delta->sha1));
-        delta_buf = diff_delta(buf, size, otherbuf, othersize, &delta_size);
-        if (delta_size != entry->delta_size)
+        delta_buf = diff_delta(buf, size, otherbuf, othersize, &delta_size, ~0UL);
+        if (!delta_buf || delta_size != entry->delta_size)
         	die("delta size changed");
         free(buf);
         free(otherbuf);
@@ -292,6 +292,7 @@ static int try_delta(struct unpacked *cur, struct unpacked *old)
 	struct object_entry *cur_entry = cur->entry;
 	struct object_entry *old_entry = old->entry;
 	unsigned long size, oldsize, delta_size;
+	long max_size;
 	void *delta_buf;
 
 	/* Don't bother doing diffs between different types */
@@ -300,6 +301,8 @@ static int try_delta(struct unpacked *cur, struct unpacked *old)
 
 	/* Size is guaranteed to be larger than or equal to oldsize */
 	size = cur_entry->size;
+	if (size < 50)
+		return -1;
 	oldsize = old_entry->size;
 	if (size - oldsize > oldsize / 4)
 		return -1;
@@ -311,15 +314,14 @@ static int try_delta(struct unpacked *cur, struct unpacked *old)
 	 * more space-efficient (deletes don't have to say _what_ they
 	 * delete).
 	 */
-	delta_buf = diff_delta(cur->data, size, old->data, oldsize, &delta_size);
+	max_size = size / 2 - 20;
+	if (cur_entry->delta)
+		max_size = cur_entry->delta_size-1;
+	delta_buf = diff_delta(cur->data, size, old->data, oldsize, &delta_size, max_size);
 	if (!delta_buf)
-		die("unable to create delta");
-	if (delta_size + 20 < size / 2) {
-		if (!cur_entry->delta || cur_entry->delta_size > delta_size) {
-			cur_entry->delta = old_entry;
-			cur_entry->delta_size = delta_size;
-		}
-	}
+		return 0;
+	cur_entry->delta = old_entry;
+	cur_entry->delta_size = delta_size;
 	free(delta_buf);
 	return 0;
 }
diff --git a/test-delta.c b/test-delta.c
index 8751e27c6..da51efc24 100644
--- a/test-delta.c
+++ b/test-delta.c
@@ -60,10 +60,12 @@ int main(int argc, char *argv[])
 
 	if (argv[1][1] == 'd')
 		out_buf = diff_delta(from_buf, from_size,
-				     data_buf, data_size, &out_size);
+				     data_buf, data_size,
+				     &out_size, ~0UL);
 	else
 		out_buf = patch_delta(from_buf, from_size,
-				      data_buf, data_size, &out_size);
+				      data_buf, data_size,
+				      &out_size);
 	if (!out_buf) {
 		fprintf(stderr, "delta operation failed (returned NULL)\n");
 		return 1;