本文主要是介绍Chapter 8 - 7. Congestion Management in TCP Storage Networks,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
TCP Flow Monitoring versus I/O Flow Monitoring
TCP flow monitoring shouldn’t be confused with I/O flow monitoring because of the following reasons: TCP 流量监控不应与 I/O 流量监控混淆,原因如下:
1. TCP belongs to the transport layer (layer 4) of the OSI model. It is not aware of the functions of the upper layer protocols such as SCSI and NVMe. TCP 属于 OSI 模型的传输层(第 4 层)。它不了解 SCSI 和 NVMe 等上层协议的功能。
2. Many I/O operations may travel in a single TCP flow. These I/O operations may belong to different I/O flows. Refer to Chapter 5, the section on I/O Flows versus I/O Operations. 许多 I/O 操作可能在一个 TCP 流量中传输。这些 I/O 操作可能属于不同的 I/O 流。请参阅第 5 章 "I/O 流与 I/O 操作 "一节。
3. As mentioned, a TCP flow has its own performance monitoring metrics, such as packets transferred per second, throughput, number of active TCP connections, time taken to establish a TCP connection, etc. This is different from the performance monitoring of I/O flows, such as IOPS, I/O throughput, time taken to complete I/O operations, I/O size, etc. 如前所述,TCP 流量有自己的性能监控指标,如每秒传输的数据包、吞吐量、活动 TCP 连接的数量、建立 TCP 连接所需的时间等。这与 I/O 流量的性能监控指标(如 IOPS、I/O 吞吐量、完成 I/O 操作所需的时间、I/O 大小等)不同。
Unavailability of I/O Flow Monitoring in TCP Storage Networks
这篇关于Chapter 8 - 7. Congestion Management in TCP Storage Networks的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!