40G QSFP+ Transceiver Provides Sufficient Bandwidth for Data Center

With each passing day, the volume of digital information flowing through the world’s data networks grows at an ever increasing rate. The growth of server virtualization, cloud computing, and trend toward network convergence is forcing today’s Data Center networks to be faster and more efficient than ever. Legacy 1 Gigabit per second (Gbps) Ethernet access links are being replaced by 10 Gbps links due to the increases in server utilization obtained through Virtualization. Wireless computing needs that rely on applications served from cloud computing and the convergence of storage area and local area networking are driving data centers to reduce traffic latency by implementing cut-through switching and flatter network architectures.

By implementing a flatter (i.e. two-tier) switching architecture, a data center can reduce latency by an order of magnitude.

To keep up, higher performance switching hardware is needed to provide sufficient I/O bandwidth to avoid blocking. To accommodate the new demands for bandwidth, many newer access switches offer 48-ports of 10Gb Ethernet for connection to downstream servers and 2- or 4-ports of 40G Ethernet for connection to the core switches. These 40G interconnects, which are often implemented using QSFP+ transceivers, provide sufficient bandwidth to enable fully non-blocking switch fabrics.

The release of the IEEE 802.3ba physical layer standard for 40 and 100Gb Ethernet specifies the Optical and Electrical requirements for various physical layer link implementations.

The 40GBASE-SR4 physical medium dependent (PMD) variant defines a 4 lane parallel optical interconnect for operation over OM3 MMF up to 100 meters in length. Each of the four lanes operates at a data rate of 10.3125 Gbps which is the same serial bit rate that was defined for 10Gb Ethernet links in the IEEE 802.3ae standard ratified in 2002.

The 40GBASE-SR4 PMD addresses the modern need for 40 Gbps interconnects in the data center and takes advantage of lower cost 850 nm Vertical Cavity Surface Emitting Laser (VCSEL) technology that is widely deployed throughout networking industries. As each of the 4 lanes in 40GBASE-SR4 operates at the same serial bit rate as a 10Gb Ethernet link, there is an opportunity for switching hardware vendors to utilize 40GBASE-SR4 as 4 separate 10Gb Ethernet interconnects.

The net result is a further increase in I/O bandwidth and density with the QSFP+ mechanical form factor.

40Gb/s QSFP+ IR4 Optical Transceiver

Unfortunately, while this new 40GBASE-SR4 standard provides an opportunity to further address the growing need for bandwidth, it is not defined to be backward compatible with the preceding 10Gb Ethernet short reach interconnect standard.

As a result, although both 10Gb Ethernet and 40Gb Ethernet included a PMD definition for short reach VCSEL based optical links operating at 10.3125 Gbps per lane, interoperability cannot be guaranteed.

For more info, please browse our website.

You May Like:

1.25G 1490/1310nm GEPON Fiber Optic Transceiver Module	1.25G 1310/1490nm GEPON Fiber Optic Transceiver Module	1.25G 1310/1550nm 20km SM BIDI 1X9 Transceiver	155M/OC3 1310nm 2km MM SFP Fiber Optic Module