Merge branch 'sp/maint-index-pack'

* sp/maint-index-pack:
  index-pack: Honor core.deltaBaseCacheLimit when resolving deltas
  index-pack: Track the object_entry that creates each base_data
  index-pack: Chain the struct base_data on the stack for traversal
  index-pack: Refactor base arguments of resolve_delta into a struct

1 files changed, 113 insertions, 29 deletions

diff --git a/index-pack.c b/index-pack.c
index 25db5db24..b4ec73617 100644
--- a/index-pack.c
+++ b/index-pack.c
@@ -26,6 +26,14 @@ union delta_base {
 	off_t offset;
 };
 
+struct base_data {
+	struct base_data *base;
+	struct base_data *child;
+	struct object_entry *obj;
+	void *data;
+	unsigned long size;
+};
+
 /*
  * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
  * to memcmp() only the first 20 bytes.
@@ -43,6 +51,8 @@ struct delta_entry
 
 static struct object_entry *objects;
 static struct delta_entry *deltas;
+static struct base_data *base_cache;
+static size_t base_cache_used;
 static int nr_objects;
 static int nr_deltas;
 static int nr_resolved_deltas;
@@ -211,6 +221,46 @@ static void bad_object(unsigned long offset, const char *format, ...)
 	die("pack has bad object at offset %lu: %s", offset, buf);
 }
 
+static void prune_base_data(struct base_data *retain)
+{
+	struct base_data *b = base_cache;
+	for (b = base_cache;
+	     base_cache_used > delta_base_cache_limit && b;
+	     b = b->child) {
+		if (b->data && b != retain) {
+			free(b->data);
+			b->data = NULL;
+			base_cache_used -= b->size;
+		}
+	}
+}
+
+static void link_base_data(struct base_data *base, struct base_data *c)
+{
+	if (base)
+		base->child = c;
+	else
+		base_cache = c;
+
+	c->base = base;
+	c->child = NULL;
+	base_cache_used += c->size;
+	prune_base_data(c);
+}
+
+static void unlink_base_data(struct base_data *c)
+{
+	struct base_data *base = c->base;
+	if (base)
+		base->child = NULL;
+	else
+		base_cache = NULL;
+	if (c->data) {
+		free(c->data);
+		base_cache_used -= c->size;
+	}
+}
+
 static void *unpack_entry_data(unsigned long offset, unsigned long size)
 {
 	z_stream stream;
@@ -426,33 +476,60 @@ static void sha1_object(const void *data, unsigned long size,
 	}
 }
 
-static void resolve_delta(struct object_entry *delta_obj, void *base_data,
-			  unsigned long base_size, enum object_type type)
+static void *get_base_data(struct base_data *c)
+{
+	if (!c->data) {
+		struct object_entry *obj = c->obj;
+
+		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+			void *base = get_base_data(c->base);
+			void *raw = get_data_from_pack(obj);
+			c->data = patch_delta(
+				base, c->base->size,
+				raw, obj->size,
+				&c->size);
+			free(raw);
+			if (!c->data)
+				bad_object(obj->idx.offset, "failed to apply delta");
+		} else
+			c->data = get_data_from_pack(obj);
+
+		base_cache_used += c->size;
+		prune_base_data(c);
+	}
+	return c->data;
+}
+
+static void resolve_delta(struct object_entry *delta_obj,
+			  struct base_data *base_obj, enum object_type type)
 {
 	void *delta_data;
 	unsigned long delta_size;
-	void *result;
-	unsigned long result_size;
 	union delta_base delta_base;
 	int j, first, last;
+	struct base_data result;
 
 	delta_obj->real_type = type;
 	delta_data = get_data_from_pack(delta_obj);
 	delta_size = delta_obj->size;
-	result = patch_delta(base_data, base_size, delta_data, delta_size,
-			     &result_size);
+	result.data = patch_delta(get_base_data(base_obj), base_obj->size,
+			     delta_data, delta_size,
+			     &result.size);
 	free(delta_data);
-	if (!result)
+	if (!result.data)
 		bad_object(delta_obj->idx.offset, "failed to apply delta");
-	sha1_object(result, result_size, type, delta_obj->idx.sha1);
+	sha1_object(result.data, result.size, type, delta_obj->idx.sha1);
 	nr_resolved_deltas++;
 
+	result.obj = delta_obj;
+	link_base_data(base_obj, &result);
+
 	hashcpy(delta_base.sha1, delta_obj->idx.sha1);
 	if (!find_delta_children(&delta_base, &first, &last)) {
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_REF_DELTA)
-				resolve_delta(child, result, result_size, type);
+				resolve_delta(child, &result, type);
 		}
 	}
 
@@ -462,11 +539,11 @@ static void resolve_delta(struct object_entry *delta_obj, void *base_data,
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_OFS_DELTA)
-				resolve_delta(child, result, result_size, type);
+				resolve_delta(child, &result, type);
 		}
 	}
 
-	free(result);
+	unlink_base_data(&result);
 }
 
 static int compare_delta_entry(const void *a, const void *b)
@@ -481,7 +558,6 @@ static void parse_pack_objects(unsigned char *sha1)
 {
 	int i;
 	struct delta_entry *delta = deltas;
-	void *data;
 	struct stat st;
 
 	/*
@@ -496,7 +572,7 @@ static void parse_pack_objects(unsigned char *sha1)
 				nr_objects);
 	for (i = 0; i < nr_objects; i++) {
 		struct object_entry *obj = &objects[i];
-		data = unpack_raw_entry(obj, &delta->base);
+		void *data = unpack_raw_entry(obj, &delta->base);
 		obj->real_type = obj->type;
 		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
 			nr_deltas++;
@@ -545,6 +621,7 @@ static void parse_pack_objects(unsigned char *sha1)
 		struct object_entry *obj = &objects[i];
 		union delta_base base;
 		int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last;
+		struct base_data base_obj;
 
 		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
 			continue;
@@ -555,22 +632,24 @@ static void parse_pack_objects(unsigned char *sha1)
 		ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
 		if (!ref && !ofs)
 			continue;
-		data = get_data_from_pack(obj);
+		base_obj.data = get_data_from_pack(obj);
+		base_obj.size = obj->size;
+		base_obj.obj = obj;
+		link_base_data(NULL, &base_obj);
+
 		if (ref)
 			for (j = ref_first; j <= ref_last; j++) {
 				struct object_entry *child = objects + deltas[j].obj_no;
 				if (child->real_type == OBJ_REF_DELTA)
-					resolve_delta(child, data,
-						      obj->size, obj->type);
+					resolve_delta(child, &base_obj, obj->type);
 			}
 		if (ofs)
 			for (j = ofs_first; j <= ofs_last; j++) {
 				struct object_entry *child = objects + deltas[j].obj_no;
 				if (child->real_type == OBJ_OFS_DELTA)
-					resolve_delta(child, data,
-						      obj->size, obj->type);
+					resolve_delta(child, &base_obj, obj->type);
 			}
-		free(data);
+		unlink_base_data(&base_obj);
 		display_progress(progress, nr_resolved_deltas);
 	}
 }
@@ -601,7 +680,8 @@ static int write_compressed(int fd, void *in, unsigned int size, uint32_t *obj_c
 	return size;
 }
 
-static void append_obj_to_pack(const unsigned char *sha1, void *buf,
+static struct object_entry *append_obj_to_pack(
+			       const unsigned char *sha1, void *buf,
 			       unsigned long size, enum object_type type)
 {
 	struct object_entry *obj = &objects[nr_objects++];
@@ -622,6 +702,7 @@ static void append_obj_to_pack(const unsigned char *sha1, void *buf,
 	obj[1].idx.offset = obj[0].idx.offset + n;
 	obj[1].idx.offset += write_compressed(output_fd, buf, size, &obj[0].idx.crc32);
 	hashcpy(obj->idx.sha1, sha1);
+	return obj;
 }
 
 static int delta_pos_compare(const void *_a, const void *_b)
@@ -656,28 +737,31 @@ static void fix_unresolved_deltas(int nr_unresolved)
 
 	for (i = 0; i < n; i++) {
 		struct delta_entry *d = sorted_by_pos[i];
-		void *data;
-		unsigned long size;
 		enum object_type type;
 		int j, first, last;
+		struct base_data base_obj;
 
 		if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
 			continue;
-		data = read_sha1_file(d->base.sha1, &type, &size);
-		if (!data)
+		base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
+		if (!base_obj.data)
 			continue;
 
+		if (check_sha1_signature(d->base.sha1, base_obj.data,
+				base_obj.size, typename(type)))
+			die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
+		base_obj.obj = append_obj_to_pack(d->base.sha1, base_obj.data,
+			base_obj.size, type);
+		link_base_data(NULL, &base_obj);
+
 		find_delta_children(&d->base, &first, &last);
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
 			if (child->real_type == OBJ_REF_DELTA)
-				resolve_delta(child, data, size, type);
+				resolve_delta(child, &base_obj, type);
 		}
 
-		if (check_sha1_signature(d->base.sha1, data, size, typename(type)))
-			die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
-		append_obj_to_pack(d->base.sha1, data, size, type);
-		free(data);
+		unlink_base_data(&base_obj);
 		display_progress(progress, nr_resolved_deltas);
 	}
 	free(sorted_by_pos);