Method and node device for constructing data center switching network

Abstract

The invention relates to the network and optical switching technical field and provides a method of constructing a data center switching network and a node apparatus. The method comprises the step S1 of selecting a regular polygonal crystal lattice physical topology according to a preset network scale and application demands. Each dot in the regular polygonal crystal lattice physical topology is corresponding to one optical switching node. Each side is corresponding to one or more fibers. The method further comprises the step S2 of acquiring a logical topology complying with small-world network characteristics in line with the application demands according to the regular polygonal crystal lattice physical topology. The logical topology comprises two logical planes. The first logical plane is a regular crystal plane. The second logical plane is a random graph plane composed of random sides. A data center inner switching network constructed through the method achieves any large-scale port number, random expansion and simple wiring. While the method makes a large scale and flexible expansion achieved, the method further guarantees a relatively high Internet bandwidth and a relatively low average time delay between any two servers.

Description

technical field [0001] The invention relates to the technical field of network and optical switching, in particular to a method and a node device for constructing a data center switching network. Background technique [0002] The main task of the switching network in the data center is to provide arbitrary interconnection between thousands of servers. The primary feature of this kind of network is that the port scale is huge, usually on the order of thousands or even hundreds of thousands; secondly, it requires high throughput and the lowest possible end-to-end delay; in addition, it needs to have good scalability, so that Support the expansion requirements of higher speed and larger port size in the future. [0003] In order to build such a data communication network, the current most common way is to cascade packet switching devices to form a multi-layer tree structure. Such as figure 1 As shown, the ToR switch (Top of RackSwitch) is directly connected to a server in a ...

AI Technical Summary

Problems solved by technology

[0008] In terms of data exchange delay, since the interconnection between servers far away in the tree network structure must go through many hops, the store-and-forward process of each hop introduces a certain delay, and this delay occurs when the network is congested. It will worsen, resulting in uncontrollable end-to-end delay on the whole, which greatly affects the performance of upper-layer applications

[0009] In terms of energy consumption, the greater the number of ports supported by electrical switching equipment and the higher the processing speed, the overall energy consumption of the switching network will increase correspondingly super-linearly, because not only the energy consumption of the chip itself increases, but also the ventilation and heat dissipation are improved. and cooling energy consumption

Images