Multiuser fair sharing of clusters is a classic problem in cluster construction. However, the cluster computing system for hybrid big data applications has the characteristics of heterogeneous requirements, which makes more and more cluster resource managers support fine-grained multidimensional learning resource management. In this context, it is oriented to multiusers of multidimensional learning resources. Shared clusters have become a new topic. A single consideration of a fair-shared cluster will result in a huge waste of resources in the context of discrete and dynamic resource allocation. Fairness and efficiency of cluster resource sharing for multidimensional learning resources are equally important. This paper studies big data processing technology and representative systems and analyzes multidimensional analysis and performance optimization technology. This article discusses the importance of discrete multidimensional learning resource allocation optimization in dynamic scenarios. At the same time, in view of the fact that most of the resources of the big data application cluster system are supplied to large jobs that account for a small proportion of job submissions, while the small jobs that account for a large proportion only use the characteristics of a small part of the system’s resources, the expected residual multidimensionality of large-scale work is proposed. The server with the least learning resources is allocated first, and only fair strategies are considered for small assignments. The topic index is distributed and stored on the system to realize the parallel processing of search to improve the efficiency of search processing. The effectiveness of RDIBT is verified through experimental simulation. The results show that RDIBT has higher performance than LSII index technology in index creation speed and search response speed. In addition, RDIBT can also ensure the scalability of the index system.
展开▼
