摘要
从动态服务发现和容错两个角度对现有DCPS DDS中间件进行了改进。将目前的发布/订阅模型的信息集中存储结构修改为分布式P2P分布式结构,并利用Chord协议实现主题信息的发布和匹配查询,从而实现了自适应能力。在传统心跳检测模型的基础上,提出了加速推拉模型,以提高失效节点的检测效率。最后通过对实现的中间件进行测试,验证了其在相对动态变化不很频繁的情况下,具有实时、容错、自适应的特点。
An adaptive DDS middleware was implemented by improving the DCPS DDS middleware on data service fin- ding and fault-tolerance, which achieves adaptability by modifying the centralized information store model with peer-tc~ peer model and applying chord protocol for data publication and subscription. Based on the traditional heart-beating model,a heart-beating accelerate push-pull model was proposed for enhancing the node failure detecting efficiency. Finally, a middleware was implemented. The test result shows that the implemented middleware is characterized with real- time ability, fault-tolerance and adaptalility.
出处
《计算机科学》
CSCD
北大核心
2012年第7期36-38,73,共4页
Computer Science
基金
南京航空航天大学基本科研业务费专项科研项目(NS2010092)资助
关键词
数据分发服务
动态自适应
容错
中间件
Data distributed service, Dynamic adaptive, Fault-tolerance, Middleware
