摘要
针对远程通信服务器需要并行处理多级别数据报文的特点,结合Java NIO、数据批处理、数据库连接池、锁机制等技术,提出一种高并发UDP通信服务器模型。详细设计了数据报接收、处理、发送以及数据采集、入库等一系列过程,并在其中引入一种优先级动态切换的多队列线程池机制。根据负载情况的不同,该多队列线程池的性能比传统线程池的性能提高了15.1%~21.58%。在沈阳蓝光集团实际应用中的效果表明,该服务器模型运行稳定,能满足大规模多优先级任务的底层通信,具有很好的通用性。
Since the remote communication server needs to parallelly handle a large number of datagrams with different levels,by using Java NIO,batch data processing,database connection pool and java synchronization,a high concurrency UDP communication server model was proposed.The receiving and sending of datagrams,data acquisition and storage were completed in detail,and a multi-queue thread pool was designed with dynamic priority.The simulation results show that the performance of multi-queue thread pool increases by 15%to 21.58%than the traditional thread pool The practical application effect of the system in Shenyang bluelight group shows that the server model is stable to work for large-scale underlying communication of multi-priority task and has very good generality.
出处
《计算机科学》
CSCD
北大核心
2017年第4期157-160,共4页
Computer Science
基金
辽宁"百千万人才工程"项目(2012921041)资助
关键词
物联网
电梯监控系统
高并发通信
动态优先级
多队列线程池
实时数据处理
Internet of things
Elevator remote monitoring
High concurrency communication
Dynamic priority
Multi-queue thread pool
Real-time data processing