【24h】

Object Replication On-Demand in DDBMS for Load Balance Cluster for SCI 2001 / ISAS 2001

机译:DDBMS中按需复制SCI 2001 / ISAS 2001的负载平衡群集的对象

获取原文
获取原文并翻译 | 示例

摘要

In recent years a significant growth of network traffic and processing load, mainly in database servers, was verified. Many factors have been responsible for this growth, as we may see from multimedia application, e.g.: growth of on demand information availability, and increase of both the size and quantity of stored information. A solution for the problem of processing large volumes of information is the use of cluster based servers working together with distributed database systems. This type of solution allows for parallel manipulation of great quantities of information. Although multiprocessing in clusters systems is in fact being used more and more due to high performance low cost and high scalability characteristics, we verified that specific database systems for these architectures present some restrictions in relation to data replication, and load balance. The main objective of this work is the study and implementation of a mechanism that allows better cluster load balance during the periods of high information demand. This mechanism replicates the most requested object in a Multimedia Distributed Database Management System (DDBMS). The complete copy generation process is autonomous and it uses dynamic distribution of replicas for idle or less loaded nodes.
机译:近年来,主要在数据库服务器中的网络流量和处理负载得到了显着增长。正如我们从多媒体应用中可以看到的,许多因素是造成这种增长的原因,例如:随需应变信息可用性的增长,以及存储信息的大小和数量的增长。解决大量信息问题的一种解决方案是使用基于群集的服务器与分布式数据库系统一起工作。这种类型的解决方案允许并行处理大量信息。尽管实际上由于高性能,低成本和高可伸缩性特性,越来越多地使用集群系统中的多处理,但是我们验证了用于这些体系结构的特定数据库系统在数据复制和负载平衡方面存在一些限制。这项工作的主要目标是研究和实现一种机制,该机制可以在信息需求较高时更好地平衡群集负载。此机制在多媒体分布式数据库管理系统(DDBMS)中复制请求最多的对象。完整的副本生成过程是自主的,它使用副本的动态分发来分配空闲或负载较少的节点。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号