Collecting statistics is a time- and resource-consuming operation in database systems. It is even more challenging to efficiently collect statistics without affecting system performance, meanwhile keeping correctness in distributed database. Traditional strategies usually consider one dimension during collecting statistics, which is lack of adaptiveness. In this paper, we propose an adaptive strategy for statistics collecting(ASC), which well balances collecting efficiency, correctness of statistics and effect to system performance. We formally define the procedure of collecting statistics and abstract the relationships among collecting efficiency, correctness of statistics and effect to system performance, and introduce an elastic structure(ESI) storing necessary information generated during proceeding our strategy. ASC can pick appropriate time to trigger collecting action and filter unnecessary tasks, meanwhile reasonably allocating collecting tasks to appropriate executing locations with right executing models through the information stored at ESI. We implement and evaluate our strategy in a distributed database. Experiments show that our solutions generally improve the efficiency and correctness of collecting statistics, moreover, reduce the negative effect to system performance comparing with other strategies.

中文翻译：

---

分布式数据库中统计信息的自适应策略

在数据库系统中，收集统计信息是一项耗时和资源消耗的操作。有效地收集统计信息而不影响系统性能，同时保持分布式数据库的正确性甚至更具挑战性。传统策略通常在收集统计数据时考虑一个维度，这是缺乏适应性的。在本文中，我们提出了一种自适应的统计收集策略（ASC），该策略很好地平衡了收集效率，统计的正确性和对系统性能的影响。我们正式定义了收集统计数据的过程，并抽象了收集效率，统计数据正确性和对系统性能的影响之间的关系，并引入了一种弹性结构（ESI），用于存储在执行我们的策略期间生成的必要信息。ASC可以选择适当的时间来触发收集动作并过滤不必要的任务，同时通过ESI中存储的信息将收集任务合理地分配到具有正确执行模型的适当执行位置。我们在分布式数据库中实施和评估我们的策略。实验表明，与其他策略相比，我们的解决方案总体上提高了收集统计信息的效率和正确性，并减少了对系统性能的负面影响。