index-pack: Honor core.deltaBaseCacheLimit when resolving deltas

diff --git a/index-pack.c b/index-pack.c
index 8162265a63fca67f6a08bfca1047d3e45350b2fa..c359f8c9dfda90344277a0c4f0cc8098d6936f3e 100644 (file)
--- a/index-pack.c
+++ b/index-pack.c
@@ -27,6 +27,9 @@ union delta_base {
 };
 
 struct base_data {
+       struct base_data *base;
+       struct base_data *child;
+       struct object_entry *obj;
        void *data;
        unsigned long size;
 };
@@ -48,6 +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;
@@ -215,6 +220,46 @@ 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;
@@ -430,6 +475,30 @@ static void sha1_object(const void *data, unsigned long size,
        }
 }
 
+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)
 {
@@ -442,7 +511,7 @@ static void resolve_delta(struct object_entry *delta_obj,
        delta_obj->real_type = type;
        delta_data = get_data_from_pack(delta_obj);
        delta_size = delta_obj->size;
-       result.data = patch_delta(base_obj->data, base_obj->size,
+       result.data = patch_delta(get_base_data(base_obj), base_obj->size,
                             delta_data, delta_size,
                             &result.size);
        free(delta_data);
@@ -451,6 +520,9 @@ static void resolve_delta(struct object_entry *delta_obj,
        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++) {
@@ -470,7 +542,7 @@ static void resolve_delta(struct object_entry *delta_obj,
                }
        }
 
-       free(result.data);
+       unlink_base_data(&result);
 }
 
 static int compare_delta_entry(const void *a, const void *b)
@@ -561,6 +633,8 @@ static void parse_pack_objects(unsigned char *sha1)
                        continue;
                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++) {
@@ -574,7 +648,7 @@ static void parse_pack_objects(unsigned char *sha1)
                                if (child->real_type == OBJ_OFS_DELTA)
                                        resolve_delta(child, &base_obj, obj->type);
                        }
-               free(base_obj.data);
+               unlink_base_data(&base_obj);
                display_progress(progress, nr_resolved_deltas);
        }
 }
@@ -605,7 +679,8 @@ 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++];
@@ -626,6 +701,7 @@ 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)
@@ -670,6 +746,13 @@ static void fix_unresolved_deltas(int nr_unresolved)
                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;
@@ -677,12 +760,7 @@ static void fix_unresolved_deltas(int nr_unresolved)
                                resolve_delta(child, &base_obj, type);
                }
 
-               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));
-               append_obj_to_pack(d->base.sha1, base_obj.data,
-                       base_obj.size, type);
-               free(base_obj.data);
+               unlink_base_data(&base_obj);
                display_progress(progress, nr_resolved_deltas);
        }
        free(sorted_by_pos);