A Closer Look Into 40G Ethernet Switch
“The higher the bandwidth, the better” has always been the wish for enterprises and data centers. Apparently, the 10 Gigabit Ethernet network can no longer support explosive network applications. Thus, 40G Ethernet and 100G Ethernet have almost arrived at the same time. 40G Ethernet is a preferred choice in most enterprise networks as an upgrading solution for legacy 10G networks. This post takes a closer look at the 40G Ethernet switch to explain its applications and future trends.
40G Ethernet Overview
In 2007, the 40G Ethernet (40GbE) was first proposed as a project for higher-speed Ethernet by the IEEE 802.3ba Task Force. Later in 2010, 40G Ethernet was officially approved as the IEEE 802.3ba standard. The standard enables Ethernet frames to be transmitted at a rate of 40 Gbit/s. At the same time, it addresses physical layer specifications for communication across backplanes, copper cabling, multimode fiber, and single-mode fiber. With the development of 40G Ethernet, many new standards have been carried out to complement the 802.3ba standard, such as 802.3bg-2011, 802.3bj-2014, and 802.3bm-2015 standards.
|802.3ba||2010-06||40Gbit/s over 1m backplane, 100m over MMF 100m of MMF or 10km over SMF|
|802.3bg||2011-03||Provide a 40 Gbit/s PMD which is optically compatible with existing carrier SMF 40 Gbit/s client interfaces (OTU3/STM-256/OC-768/40G POS)|
|802.3bm||2015-02||40G Ethernet for optical fiber|
|802.3bq||2016-06||40GBASE-T for 4-pair balanced twisted-pair cabling with 2 connectors over 30m distances|
Applying the 40 Gigabit Ethernet in the network layer, it usually involves a pair of QSFP+ transceivers connected by a cable, like OM4 or OM3 fiber cable. The 40GbE transceivers, in turn, are plugged into either network servers or a variety of components such as 40Gb switches. Among all the 40G applications, 40GbE cables, 40GbE transceivers, and 40GbE switches are regarded as the top three leading 40G Ethernet-based network applications.
What is 40G Ethernet Switch?
A 40G Ethernet switch generally refers to a switch with ports of data speeds of 40 Gb/s. The overall switching capacity of a 40G Ethernet switch might be much higher depending on the total number of ports and the power of the switching fabric itself.
" Also check - 25G vs 40G Ethernet: How to Choose?
With technological gains in chips and cabling, data networking technology has been increasing regularly. 40G switches are now hitting their most rapid growth. They're widely adopted in data centers and enterprise networks with performance sandwiched between 10G and 100G switches.
40G Switch Use Case
40G switches usually act as core/spine switches for small and medium enterprises, while as aggregation/leaf switches for data centers. The most typical 40G switch use case is a 10G to 40G migration path. In such architecture, 10G SFP+ modules, 40G QSFP+ modules, and cabling systems will be utilized to enable data transfer. The following figure shows the typical connection between a 10G switch and a 40G switch.
In traditional 3-tier architecture, as links to access switches move to 10 Gigabit Ethernet, customers need interfaces greater than 10 Gigabit to link the aggregation and core layers together. Thus, 40G switches are usually used on the aggregation or core layer. For example, FS N5850-48S6Q 40G switches can act as a TOR (Top-of-Rack) or Leaf switch in a compact 1U with 48x 10Gb SFP+ and 6x 40Gb QSFP+ ports, providing high-density availability and uplink options.
" Also check - N5850-48S6Q, 48-Port L3 Data Center Switch
Look into the Future
40G switches are still widely used in campus networks and data centers. But 25G switches, as a new emerging technology, are a strong competitor in the market. Since 25G is delivered using single-lane 25G SerDes (Serializer-Deserializer) technology, it provides greater switch port density and network scalability compared to 40G, which uses four 10G lanes.
" Also check - Getting the Future Trends from 40G/100G Network to 400G
On one hand, 100G QSFP+ modules support a parallel channel rate of 10×10G. Because the single-channel rate is based on 10G, the 10G-40G-100G migration path requires more fibers, resulting in more complicated cabling and higher cost.
On the other hand, 40G QSFP+ modules integrate 4 channels of 10G into one optical fiber link through wavelength division multiplexing (WDM). It is part of the reason why the cost of QSFP optical modules remains high, especially for 40G modules with a longer transmission distance. This also increases the cost of a 10G network upgrade.
In a word, 40G switches are still a good choice for a 10G-40G upgrade path. But the 10G-25G-100G migration path is gaining momentum. Also, as the average annual growth rate of Internet traffic remains at a high level, more and more enterprises and data centers will upgrade from 40G/100G to 400G.