容器将应用和支持软件、库文件等封装为镜像，通过发布新版本镜像实现应用升级，导致不同版本之间存在大量相同数据。镜像加载消耗大量时间，使容器启动时间从毫秒级延迟为秒级甚至是分钟级。复用不同版本之间的相同数据有利于减少容器加载时间。当前容器镜像采用继承和分层加载机制，有效实现了支持软件、库文件等数据的复用，但对于应用内部数据还没有一种可靠的复用机制。本课题拟研究一种基于分片复用的多版本容器镜像加载方法，通过复用不同版本之间的相同数据，提升镜像加载效率。研究分为3个方面：1）针对容器镜像数量较多、相同数据查找效率低下的问题，研究一种基于启发式聚类的相似镜像查找方法；2）针对不同版本之间重复数据分布碎片化问题，研究一种基于重写的数据自组织优化方法；3）针对数据复用过程中瓶颈资源不同导致复用效果难以预测的问题，研究一种效用最大化的镜像加载策略决策方法。最后通过原型系统实现，完成对以上方法的检验。

Container encapsulates the application, the supporting software and the operating system libraries as an image. The application is updated through publishing a newer image version. That would lead a certain degree of duplications between the neighboring versions. The loading process of container image is time-consuming and delays the starting time of a container from milliseconds to seconds or minutes. Reusing the same data of previous versions can help to reduce the loading time. The layered loading and inheritance features adopted by docker can help to reuse the supporting software and the operating system libraries effectively in image loading. However, reusing the application data is currently not supported. This study will make a research on container image loading methodology based on chunking reuse of older versions to improve the image loading performance. There are three key points: 1) A large number images coexisting in a runtime host cause a large same data search space which could lower the lookup performance. To address this issue, we will propose a clustering based image lookup method. 2) To address the data fragment problem, we will study a self-organized optimization method based on data rewritten. 3) To resolve the utility unpredictable problem caused by the bottleneck changing, we will study a maximum utility based strategy decision method. All the proposed methods will be tested in a prototype system implementation.