首页> 外文学位 >A network impairment tool based on the IXDP425 network processor.
【24h】

A network impairment tool based on the IXDP425 network processor.

机译:基于IXDP425网络处理器的网络损害工具。

获取原文
获取原文并翻译 | 示例

摘要

The objective of this thesis is to design and develop a network impairment tool. The tool will manipulate incoming packets to generate network faults such as packet loss, delay, duplication and reordering. Network impairment tools are being used widely in both the commercial and academic worlds to verify and stress test network products and systems. The proposed tool can also be used to emulate a large network to form a realistic and controlled verification environment.; The core component of the impairment system is an Intel IXDP425 network processor (a specialized platform optimized for packet processing) evaluation board. The impairment code is developed on top of the application programming interface provided in the IXDP425. This impairment tool has several improvements over existing tools in term of flexibility, robustness, efficiency, and cost. Two impairment emulation modes are supported: model-based and trace-based. The model-based mode has a powerful set of probability models ready to be used; whereas the trace-based mode permits the user to inject packet entries in a manner similar to traffic logging.; The performance tests show that in most cases, the impairment process imposes negligible overhead. Only when the packet size is very small (i.e. the maximum packet rate is high), then the overhead will run up quickly. In such cases, the internal packet queues reach their capacity; hence the waiting time for each packet becomes higher.
机译:本文的目的是设计和开发一种网络损伤工具。该工具将处理传入的数据包以生成网络故障,例如数据包丢失,延迟,重复和重新排序。网络损害工具已在商业和学术界广泛使用,以验证和测试网络产品和系统并对其进行压力测试。所提出的工具也可以用来模拟一个大型网络,以形成一个现实的,可控的验证环境。减损系统的核心组件是英特尔IXDP425网络处理器(为数据包处理优化的专用平台)评估板。减损代码是在IXDP425提供的应用程序编程接口之上开发的。在灵活性,健壮性,效率和成本方面,此减损工具相对于现有工具有几处改进。支持两种减损仿真模式:基于模型和基于跟踪。基于模型的模式具有一组强大的概率模型可供使用。基于跟踪的模式允许用户以类似于流量记录的方式注入数据包条目。性能测试表明,在大多数情况下,减值过程的开销可忽略不计。只有当数据包大小非常小时(即最大数据包速率很高),开销才会迅速增加。在这种情况下,内部数据包队列达到其容量;因此每个数据包的等待时间变得更长。

著录项

  • 作者

    Pham, Hai.;

  • 作者单位

    University of Manitoba (Canada).;

  • 授予单位 University of Manitoba (Canada).;
  • 学科 Computer Science.
  • 学位 M.Sc.
  • 年度 2005
  • 页码 71 p.
  • 总页数 71
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自动化技术、计算机技术;
  • 关键词

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