赵宗义的专栏

在本文中我会总结一些论文相关论文中关于网络中丢包的原因的论述.网络中的丢包可以分为如下几个类型:拥塞: 这个比较好理解, 就是交换机/路由器中多个端口向一个端口发送数据包, 最后导致数据包数量超过了这个端口的缓冲区的容量, 从而导致丢包. [1]持续性的黑洞: 在交换机中, 和特定模式匹配的所有数据包都会丢失. 这种现象的成因是匹配-动作表的损毁或者控制器造成的转发规则配置错误. [1]暂时性的黑洞: 在交换机中, 在一段较短的时间内, 和特定模式匹配的所有数据包都会丢失. 这种现象的成因是, 转

DRAM的访问时间为数十纳秒. [1]参考文献\textbf{参考文献}参考文献[1] Y. Lu, A. Montanari, B. Prabhakar, S. Dharmapurikar, and A. Kabbani, “Counter Braids: A Novel Counter Architecture for Per-flow Measurement,” in Proceedings of the 2008 ACM SIGMETRICS International Conference .

文章目录The values in the table show stark differences between applications, both in terms of utilization and of IPG.Bandwidth is the link utilization multiplied by 10 Gbps.

文章目录文章信息信息摘录文章信息J. Woodruff, A. W. Moore, and N. Zilberman, “Measuring Burstiness in Data Center Applications,” in Proceedings of the 2019 Workshop on Buffer Sizing, Palo Alto, CA, USA, Dec. 2019, pp. 1–6, doi: 10.1145/3375235.3375240.信息摘录微突发流量 (microb

文章目录文章信息阅读笔记文章信息R. R. Kompella, K. Levchenko, A. C. Snoeren, and G. Varghese, “Every Microsecond Counts: Tracking Fine-Grain Latencies with a Lossy Difference Aggregator,” in ACM SIGCOMM Computer Communication Review, 2009, vol. 39, pp. 255–266.阅读笔记大多数

FET: flow event telemetryPDP: programmable data plane

文章目录文章信息文章信息D. Eppstein, M. T. Goodrich, F. Uyeda, and G. Varghese, “What’s the Difference? Efficient Set Reconciliation without Prior Context,” in Proceedings of the ACM SIGCOMM 2011 conference, Toronto, Ontario, Canada, Aug. 2011, pp. 218–229, doi: 10.