In 2015 data center optics market, the 40GbE transceivers is ubiquitous and the market of 40GbE is encouraging. However, with 100GbE rapidly becoming the new standard in transport, the rules of game seems to have changed. A new voice is announcing: 25GbE is more preferred and the death of 40GbE was never in doubt. Why? This tutorial will make a comparison of 25GbE and 40GbE cabling.
40 GbE, namely 40 Gigabit Ethernet, is a standard developed by the IEEE 802.3ba Task Force to support sending Ethernet frames at 40 Gbps (Gigabits per second). The official development of 40GbE standards began most early in January 2008, and the standards were officially approved in June 2010.
IEEE 802.3 Standard Interfaces that Specify 40GbE
|7 m over twinax copper cable||40GBASE-CR4|
|30 m over “Cat.8” twisted pair||40GBASE-T|
|100 m over OM3 MMF||40GBASE-SR4|
|125 m over OM4 MMF|
|2 km over SMF, serial||40GBASE-FR|
|10 km over SMF||40GBASE-LR4|
|40 km over SMF||40GBASE-ER4|
At the heart of the 40GbE network layer is a pair of transceivers connected by a cable—OM4 or OM3 fiber cable. The transceivers, in turn, are plugged into either network servers or a variety of components, including interface cards and switches.
There are several standard form factors of 40GbE transceivers in the whole evolution. The CFP (C Form-Factor Pluggable) transceiver uses 12 Tx and 12 Rx 10Gbps lanes to support one 100GbE port, or up to three 40GbE ports. With its larger size, it can meet the needs of single-mode optics and can easily serve multimode optics or copper. But it is gradually falling behind since the increasing demands for high density. Another form factor is the CXP. It also provides twelve 10Gbps lanes in each direction, but is much smaller than the CFP and serves the needs of multimode optics and copper. At present, the most commonly used 40GbE form factor is the Quad Small Form-Factor Pluggable (QSFP) since it is similar in size to the CXP but can provide four Tx and four Rx lanes to support 40GbE applications for single-mode, multimode fiber and copper.
Fiber optic cabling or copper cabling are both available for 40 GbE. The supportable channel length depends on the cable and the transceiver type. For data center 40GbE fiber optic cabling, OM3 and OM4 multimode cabling is generally recommended because its reach supports a wider range of deployment configurations compared to copper solutions. In addition, compared to single-mode solutions, it costs lower. For connector type, it is no longer the duplex LC in this case. In the 802.3ba standard, MPO/MTP connectors are used at the multimode transceivers to support the multifiber parallel optics channels.
25GbE is a standard developed by IEEE 802.3 Task Force P802.3by in July 2014, using for Ethernet servers and switches connectivity in a datacenter environment. The upcoming IEEE 802.3by 25GbE standard is technically complete and expected to be ratified by June of 2016. Meanwhile, the industry expects that 25GbE hardware will be available as early as 2015 with the standard finalized by 2016.
IEEE 802.3 Standard Interfaces that Specify 25GbE
|Direct Attach Copper||25GBASE-CR|
|Direct Attach Copper||25GBASE-CR-S|
The 25GbE physical interface specification supports two main form factors—SFP28 (1×25 Gbps) and QSFP28 (4×25 Gbps).
The 25GBASE-SR SFP28 is an 850nm VCSEL 25GbE transceiver available in the market. It is designed to transmit and receive optical data over 50/125µm multimode optical fiber (MMF) and support up to 70m on OM3 MMF and 100m on OM4 MMF (LC duplex). In fact, using an SFP28 direct attach copper (DAC) cable for switches direct connection is more commonly used now. In addition, a more cost-effective solution is recommended that is to use a QSFP28 to 4xSFP28 breakout cable to connect a 100GbE QSFP28 switch port to four SFP28 ports. DAC cable lengths are limited to three meters for 25GbE. Thus, the active optic cable (AOC) solutions are also used for longer lengths of application.
Compared to 40 GbE, the 25GbE seems to be more suitable and cost-effective for cloud and web-scale data center applications. Using 25GbE with QSFP28 transceivers, users can deliver a single-lane connection that is similar to existing 10GbE technology, but with 2.5X faster performance. In addition, 25 GbE can provide superior switch port density by requiring just one lane (vs. 4 x lanes with 40 GbE). Thus, it costs less and requires lower power consumption.
|Port Speed||Lane Speed (Gb/s)||Lanes Per Port||Usable Ports||Total BW (Gb/s)|
|Note: Ethernet switch with 3.2 Tbps capacity and 128 ports|
2.5 times the performance of 10 GbE
Greater port density vs 40 GbE (one lane vs. four lanes)
Fewer ToR switches and fewer cables
Lower cost versus 40 GbE
Requires less power, cooling, and footprint
No matter the market research or the attitude of users, 25 GbE seems to be the preferred option in the next step. Actually, coming back to reality, there will be a significant increase in 100GbE and 25GbE port density this year. However, will 40 GbE be replaced and dead? We do not know what will happen in the future. But the trends will always be higher speed, wider band, and higher port density. 25 GbE vs 40 GbE, let’s wait and see how things play out.