Chapter 8 - 11. Congestion Management in TCP Storage Networks

Congestion Notification in TCP Storage Networks

Congestion Notification in TCP storage networks is achieved by Explicit Congestion Notification (ECN), which is standardized by RFC 3168. As explained earlier, iSCSI and NVMe/TCP layers remain unaware of any such mechanisms. TCP 存储网络中的拥塞通知是通过显式拥塞通知 (ECN) 实现的，RFC 3168 对其进行了标准化。如前所述，iSCSI 和 NVMe/TCP 层仍未意识到任何此类机制。

Solution Components

The success of the approach to congestion prevention by notifying the end devices depends upon the following factors: 通过通知终端设备来防止拥塞的方法是否成功取决于以下因素：

1. Congestion detection: A switch (or router) must be able to detect the symptoms of congestion. 交换机（或路由器）必须能够检测到拥塞症状。

2. Sending a notification: After detecting congestion, the switch must be able to inform the end devices about it. 检测到拥塞后，交换机必须能够将拥塞情况通知终端设备。

3. Receiving a notification: The end devices must be able to understand the notification from the switches. 终端设备必须能够理解交换机发出的通知。

4. Congestion prevention action: After being notified about congestion in the network the most important component is for the end devices to take preventive actions, such as reducing their rate. 在收到网络拥塞通知后，最重要的是终端设备采取预防措施，如降低速率。

These are the same components as for Fibre Channel fabrics (explained in Chapter 6) and RoCEv2 networks (explained in Chapter 7). The following sections explain Explicit Congestion Notification in TCP/IP networks using the same components to make it easy to compare the implementation among different transport types and for the users to have a consistent detection and troubleshooting workflow.