基于虚拟机的僵尸网络仿真系统可扩展性优化

发布时间：2018-10-29 16:42

【摘要】：僵尸网络仿真是僵尸网络研究领域的一门新兴技术,近年来日益得到广泛的关注。现有研究中基于虚拟机的大规模僵尸网络实用仿真系统比较缺乏,现有系统缺乏对虚拟机集群的快速部署、多虚拟化(尤其是对轻量级虚拟化)、僵尸网络特性(如僵尸网络的昼夜随机关机开机)模拟、高可扩展性功能的支持。通过对僵尸网络仿真特性的分析,提出了一种基于虚拟机的僵尸网络仿真系统及适用于僵尸网络仿真系统的可扩展性优化技术。实验表明,所提出的基于内存性能优化和CPU性能优化的技术,可以使每个虚拟机的常驻内存比优化前减少77%以上,同一台物理机所能开启的最大虚拟机数量由15台增加到43台,当限制虚拟机的vCPU占用率到100 000时,主机CPU占用率在同样情况下能从100%降低到20%,优化效果显著。
[Abstract]:Botnet simulation is a new technology in the field of botnet research, which has been paid more and more attention in recent years. The practical simulation system of large-scale botnet based on virtual machine is lacking in the existing research, and the existing system lacks the rapid deployment of virtual machine cluster, multi-virtualization (especially for lightweight virtualization). Botnet features (such as night and day random shutdown of botnets) simulation, high scalability support. By analyzing the characteristics of botnet simulation, a botnet simulation system based on virtual machine and its extensibility optimization technology are proposed. Experimental results show that the proposed techniques based on memory performance optimization and CPU performance optimization can reduce the resident memory of each virtual machine by more than 77% compared with those before optimization. The maximum number of virtual machines that can be opened by the same physical machine increases from 15 to 43. When the vCPU occupancy rate of the virtual machine is limited to 100,000, the CPU occupancy of the host can be reduced from 100% to 20% under the same conditions, and the optimization effect is remarkable.
【作者单位】：北京航空航天大学软件开发环境国家重点实验室;北京航空航天大学计算机学院;
【基金】：国家高技术研究发展计划(“863”计划)基金资助项目(No.2011AA01A205) 国家自然科学基金资助项目(No.61003015,No.61232009) 软件开发环境国家重点实验室探索性自主研究课题资助项目(No.SKLSDE-2012ZX-23) 北京市自然科学基金资助项目(No.4122042) 核心电子器件、高端通用芯片及基础软件产品重大专项基金资助项目(No.2010ZX01036-001-001)
【分类号】：TP393.08

【相似文献】