Leviton on Architecture's Impact on 40/100G Migration

Demand for faster speeds and greater bandwidth is always increasing, along with the exponentially increasing number of network connections. Equipment architecture trends are also changing, and thus TIA standards must accommodate. 

TIA Standards Highlight New Switch Fabrics
Last year, the Telecommunications Industry Association (TIA) published addendums (ANSI/TIA-942-A-1) specifying recommendations for telecommunications cabling to support new switch fabrics.

The Traditional 3-Tier Architecture Model
The traditional 3-tier architecture is no longer the most ideal solution for accomodating network growth. Disadvantages include higher latency and higher energy requirements. Newer solutions are better designed to optimize performance.

Image Source: Leviton

Fat-Tree Architecture (also known as Leaf Spine) 
Fat-tree architecture is one of the emerging switch architectures that is quickly replacing traditional solutions. Fat-tree architecture is typically used in large data centers which benefit from features including:

• multiple connections between interconnection switches (spine switches) and access switches (leaf switches) to support high-performance computer clustering
• a non-blocking, low-latency fabric

Image Source: Leviton

In the fat-tree diagram below, the interconnection switch is connected directly to the access switch through the use of 12- or 24-fiber MTP® Trunks with either a conversion module (24-fiber) or MTP® adapter panel (12-fiber). Compared to traditional 3-tier architecture, you can see that fat-tree architecture uses fewer aggregation switches and redundant paths to support 40GBASE-SR between the access and interconnection switches, thus reducing latency and energy requirements. 

Image Source: Leviton

Other new switch fabric architectures also provide lower latency, higher bandwidth, and include non-blocking ports between any two points in a data center. Additional examples of emerging architectures included in the ANSI/TIA-942-A-1 published standard include:

• Full-mesh- all switches must be connected to every other switch. Often used in small data centers and metropolitan networks. 
• Interconnected-mesh- similar to full-mesh; highly scalable, less costly, easy to add to as a company grows. Typically maintains 1-3 interconnection switches, and is non-blocking within each full-mesh POD. 
• Centralized- server is connected to all fabric switches, creating low latency. Often managed by a single server. Easy to maintain with a small staff. Port limitations can prohibit from scaling well, thus typically used in small data centers. 
• Virtual-switch- similar to centralized; uses interconnected switches to form a single virtual switch. Each server is connected to multiple switches for redundancy, causing potentially higher latench. Does not scale well unless fat-tree or full-mesh is implemented between virtual switches. 

Impact

Pre-terminated 12- or 24-fiber MPO/MTP® cabling is ideal for supporting higher bandwidth requirements in data centers using these architectures. It ensures cabling design maximizes fiber utilization throughout the infrastructure, and also promotes an easy migration path to support current or future IEEE 40G and 100G bandwidth as required by ANSI/TIA-942-A-1 standards.

New, lower-cost transceiver technology has recently been developed to work in tandem with pre-terminated 12- or 24-fiber MPO/MTP® cabling to support higher levels of performance and accommodate data center links over 150 meters. These multimode transceivers can transmit longer distances using the same cable (up to 300 meters over OM3 and 400 meters over OM4).

Using pre-terminated MTP® cabling and connectivity, Leviton performed active testing at customer data centers with Cisco and Arista switches that include these transceivers, and confirmed that 10G and 40G channels both worked at stated distances with zero errors and no lost data packets.

To support new architectures and scalability, IEEE is working on new physical layer requirements. The IEEE P802.3bm task force is currently developing standards to support next generation 40/100GbE technologies that lower costs, reduce power consumption, and increase density. 

It is critical to understand the impact of these new architectures and standards on your data center and prepare a migration strategy for moving to 40G, 100G, and beyond. To learn more about migration and these new architectures, contact Accu-Tech today. 

To read Leviton's full news release, click here.