The rise of cloud computing and the expansion of the data center are pushing the latest Ethernet speeds up, while big data based on cloud technology has already added to carriers’ workloads. To meet this requirement, the data center extends the bandwidth capabilities that are parallel to existing infrastructure. Rapid growth in the expected 25G and 100G Ethernet deployments is a testament to this trend.
In order to be able to handle the increasing data load, the industry’s largest long-distance cloud companies have together with their core network’s data center operators, to jointly use the 100G Ethernet architecture. However, most operators believe that 100G or even 40G is somewhat excessive for server connections because its workload only needs to be incrementally improved over 10G networks. This is why, although 40G and 100G Ethernet have been introduced, 25G and 50G Ethernet are still one of the reasons for the common choices within the data center. Below we will briefly explain why 25G is more suitable for these applications than 40G.
Several recent Ethernet bandwidth technologies are not designed to set a new high speed, but more to push such network protocols into adjacent markets, especially the data center market. Below we will explain the specific reasons by introducing 25G, 50G and 100G respectively.
25G
The official draft of the IEEE 802.3 draft standard for 25G Ethernet will eventually be completed in 2016, and it will mainly be aimed at servers in cloud data centers. This is a relatively short time frame due to the reusable components of 10G and 100G Ethernet.
40G and 100G already exist, but why use 25G? This confused some operators. The answer lies in the requirements of architecture and performance. The existing 100G standard network system consists of four links, each of which has a bandwidth of 25 Gbps. This four-to-one ratio is equivalent to connecting servers to 25G switches and then converging to 100G uplinks, which helps network operators to more easily expand their data centers.
Similarly, 40G Ethernet is composed of four 10G Ethernet links. However, according to John D’Ambrosia, chairman of the Ethernet Alliance, many data centers have adopted more than 10G servers. This is why a number of chip vendors have provided 25G serial/deserializer transceivers. This will not only make bandwidth convergence for 25G, 50G, and 100G Ethernet more convenient, but also reduce costs due to volume.
50G
Although the implementation of the IEEE standard for 50G Ethernet is still some time away (approximately 2018 to 2020), many industry alliances expect that products will begin to appear in 2016. Similar to 25G technology, 50G Ethernet technology will be the next solution for high-speed connection servers and data centers. According to analyst firm’s Dell’Oro data, over the next few years, servers and high-performance flash storage systems will need to exceed 25G.
To help deliver these accelerated Ethernet technology products faster, the 25G/50G Ethernet Alliance has eliminated the royalty fees for the 25G and 50G Ethernet specifications and is open to all data center ecosystem vendors.
Reusing the 25G components of the existing 100G network can reduce the implementation cost of 50G. For example, the cost structure of 25G cabling is the same as 10G, but its performance is 2.5 times. Similarly, 50G costs half of the 40G cost, but performance can be increased by 25%.
100G
For long-distance carrier networks ranging from hundreds of kilometers to tens of thousands of kilometers, the deployment of 100G Ethernet will continue to grow.
But according to information provided by a new industry alliance, the 100G architecture will be another excellent market alternative. The 100GCLR4 alliance led by Intel and Arista Network believes that 100G is ideal for connecting large “ultra-large” data centers spanning 100 meters to 2 kilometers.
Other companies are also seeking alternative 100G implementations for the data center. Sinovo Telecoms has joined the CWDM4MSA industry consortium, which aims to define a common specification for low-cost 100G optical interfaces within 2 kilometers of data center applications. With the transformation of network infrastructure to 100G data rates, data centers will require long-range, high-density, 100G embedded optical connections. The MSA uses Coarse Wavelength Division Multiplexing (CWDM) technology to provide four 25G single-mode fiber (SMF) link channels. Similarly, the OpenOpTIcsMSA organization initiated by Ranovus and Mellanox Technologies will also focus on developing a data center supporting 2 kilometers of 100G.
In the past, the increase in speed has driven the development of most network components. Today, to handle the massive data flow through the cloud, companies need to seek a balance between speed-up and reuse technology to find a cost-effective solution. Gigalight, as a professional optical transceiver vendor, can provide various kinds of optical transceivers to meet your 25G/50G/100G/200G/400G transmission needs. For more details, please visit its official website.
Post a Comment