JSON (GLib) 序列化泄漏 GHashTable 的内存答案

【问题标题】：JSON (GLib) serialization leaks memory for a GHashTableJSON (GLib) 序列化泄漏 GHashTable 的内存
【发布时间】：2019-07-11 01:03:03
【问题描述】：

我正在尝试在 JSON 中序列化和反序列化 GHashTable 和 valgrind 报告由于这样做而肯定丢失的内存。他们分发的glib.suppressions 文件中有g_hash_table_new 的抑制，但g_hash_table_new_full 没有，这是我看到的一堆。我的哈希表是一个使用g_param_spec_pointer设置的GObject属性，序列化它的函数是：

static JsonNode *
foo_obj_serialize_property (JsonSerializable *serializable,
                            const gchar      *name,
                            const GValue     *value,
                            GParamSpec       *pspec)
{
  JsonNode *retval = NULL;

  if (g_strcmp0 (name, "list") == 0)
    {
      GHashTable *list = NULL;
      GHashTableIter iter;
      JsonArray *arr = NULL;
      gpointer key, val;

      retval = json_node_new (JSON_NODE_ARRAY);

      g_return_val_if_fail (value != NULL, retval);
      g_return_val_if_fail (G_VALUE_HOLDS_POINTER (value), retval);

      list = g_value_get_pointer (value);

      arr = json_array_new ();

      if (list != NULL)
        {
          g_hash_table_iter_init (&iter, list);
          while (g_hash_table_iter_next (&iter, &key, &val))
            {
              JsonNode *node = NULL;
              JsonObject *obj = NULL;
              FooItem *item;

              item = FOO_ITEM (val);
              node = json_gobject_serialize (G_OBJECT (item));

              if (JSON_NODE_HOLDS_OBJECT (node))
                {
                  obj = json_node_get_object (node);
                  json_array_add_object_element (arr, obj);
                }
            }
        }

      json_node_take_array (retval, arr);
    }

  return retval;
}

反序列化是：

static gboolean
foo_obj_deserialize_property (JsonSerializable *serializable,
                              const gchar      *name,
                              GValue           *value,
                              GParamSpec       *pspec,
                              JsonNode         *property_node)
{
  gboolean retval = FALSE;

  if (g_strcmp0 (name, "list") == 0)
    {
      GHashTable *list;
      JsonArray *arr;

      arr = json_node_get_array (property_node);
      list = g_hash_table_new_full (g_str_hash,
                                    g_str_equal,
                                    g_free,
                                    NULL);

      for (gint i = 0; i < json_array_get_length (arr); i++)
        {
          g_autoptr (FooItem) item = NULL;
          JsonNode *node = NULL;

          node = json_array_get_element (arr, i);

          item = FOO_ITEM (json_gobject_deserialize (FOO_TYPE_ITEM, node));
          g_return_val_if_fail (FOO_IS_ITEM (item), FALSE);
          g_object_ref (item);
          g_hash_table_insert (list,
                               g_strdup (foo_item_get_key (item)),
                               item);
        }

      g_value_set_pointer (value, list);

      retval = TRUE;
    }

  return retval;
}

我的GObject 类属性获取/设置函数是：

static void
foo_obj_get_property (GObject    *object,
                      guint       prop_id,
                      GValue     *value,
                      GParamSpec *pspec)
{
  FooObj *self = FOO_OBJ (object);

  switch (prop_id)
    {
    case PROP_LIST:
      g_value_set_pointer (value, self->list);
      break;

    default:
      G_OBJECT_WARN_INVALID_PROPERTY_ID (object, prop_id, pspec);
    }
}

static void
foo_obj_set_property (GObject      *object,
                      guint         prop_id,
                      const GValue *value,
                      GParamSpec   *pspec)
{
  FooObj *self = FOO_OBJ (object);

  switch (prop_id)
    {
    case PROP_LIST:
      foo_obj_set_list (self, g_value_get_pointer (value));
      break;

    default:
      G_OBJECT_WARN_INVALID_PROPERTY_ID (object, prop_id, pspec);
    }
}

最后是类 getter/setter：

GHashTable *
foo_obj_get_list (FooObj *self)
{
  GHashTable *list;

  g_return_val_if_fail (FOO_IS_OBJ (self), NULL);

  g_object_get (self, "list", &list, NULL);

  return list;
}

void
foo_obj_set_list (FooObj     *self,
                  GHashTable *list)
{
  g_return_if_fail (FOO_IS_OBJ (self));

  if (self->list == list)
    return;

  if (list)
    g_hash_table_ref (list);

  if (self->list)
    g_hash_table_unref (self->list);

  self->list = list;

  g_object_notify_by_pspec (G_OBJECT (self), properties [PROP_LIST]);
}

我正在使用 valgrind --tool=memcheck --leak-check=full --show-leak-kinds=all --leak-resolution=high --num-callers=20 --suppressions=../tests/glib.supp foo 运行内存检查，并收到有关丢失内存的消息以进行序列化显示：

==24303== 32 bytes in 1 blocks are definitely lost in loss record 1,029 of 1,852
==24303==    at 0x483877F: malloc (vg_replace_malloc.c:299)
==24303==    by 0x494CAB1: g_malloc (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x492C8E4: g_slice_alloc (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x4933839: g_slice_alloc0 (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x4D72CEE: json_node_alloc (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D72D37: json_node_new (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D77B37: json_gobject_serialize (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4867AC9: foo_item_serialize_property (foo-item.c:71)
==24303==    by 0x4D779C1: ??? (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D77B42: json_gobject_serialize (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4861681: foo_obj_serialize_property (foo-obj.c:146)
==24303==    by 0x4D779C1: ??? (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D77B42: json_gobject_serialize (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D77B82: json_gobject_to_data (in /usr/lib/libjson-glib-1.0.so.0.400.4)

反序列化：

==24303== 184 (88 direct, 96 indirect) bytes in 1 blocks are definitely lost in loss record 1,774 of 1,852
==24303==    at 0x483877F: malloc (vg_replace_malloc.c:299)
==24303==    by 0x494CAB1: g_malloc (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x492C8E4: g_slice_alloc (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x4966C5E: g_hash_table_new_full (in /usr/lib/libglib-2.0.so.0.6000.4)
==24303==    by 0x4861AB2: foo_obj_deserialize_property (foo-obj.c:264)
==24303==    by 0x4D77F00: ??? (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4D7826B: json_gobject_from_data (in /usr/lib/libjson-glib-1.0.so.0.400.4)
==24303==    by 0x4862BEE: foo_obj_deserialize (foo-obj.c:472)

我很难看到我错过了什么，并且各种清除指针的尝试导致双重释放或关于 ref count == 0 的错误。我知道有很多 GLib 抑制，因为它处理内存，但我不知道这些是否属于该范围。

我可能可以通过使用json-glib 注册一个函数来装箱哈希表并简化序列化，但除非我需要，否则我不想朝那个方向发展。

【问题讨论】：

标签： c memory-leaks glib gobject

【解决方案1】：

node = json_gobject_serialize (G_OBJECT (item));

在这行之后，您对node 不做任何事情，既不将其存储在某个地方，也不免费。这会导致内存泄漏。另请注意，JsonNode 是 GBoxed，而不是 GObject。使用json-node-free 释放它。

我还建议您阅读有关引用计数和analysing valgrind output 的内容。

堆栈跟踪会告诉您泄漏内存的分配位置。不幸的是，Memcheck 无法告诉您内存泄漏的原因。

对于deserialize 方法，它被分配在(foo-obj.c:264)，即g_hash_table_new_full。您创建一个哈希表，但不要破坏它。

【讨论】：

如果你指的是foo_obj_serialize_property thd line obj = json_node_get_object (node); 后面使用node。如果我按照建议释放node，我会收到关于引用计数的错误，但将其更改为json_node_dup_object 可以修复该问题以及序列化中的任何剩余泄漏。反序列化是产生 valgrind 消息的原因，我还不确定。