DC Backbone Solutions

What is Virtual Cluster Switching?

Virtual Top-of-Rack Architecture in a Data Center

Using MPLS to Connect Data Centers

Multi-Chassis Trunking

Data Centers continue to evolve. Server virtualization is transforming the way businesses deliver applications to end users. Data growth and network traffic are increasing at an exponential rate. Organizations face increasing requirements for uptime, application flexibility and rapid application deployment. New technologies such as cloud computing are being introduced to the date center to provide IT with maximum flexibility, reduced capital and operational costs, reduced application deployment time yet increased agility. Data centers are going to evolve so they can deliver any application, anywhere at a moments notice.

DealFlow Networks has partnered with Brocade to deliver a suite of data center solutions unmatched in the industry. Brocade has been providing data center solutions for over a decade and currently has solutions deployed in over 90% of the Fortune 1000 corporations. You don't have to be a Fortune 1000 company, however, to benefit from these advanced data center technologies. Here are some of the many benefits your company can achieve with DealFlow and Brocade.

A breakthrough technology called Virtual Cluster Switching provides cloud computing in your data center. VCS creates an Ethernet fabric in your data center that provides unmatched simplicity, non-stop networking, investment protection and application optimization.
Unmached scalability and density that includes over 15 terabits per second of capacity, 256 10G ports, 32 100G ports or 1536 1G ports in a single chassis, all at wirespeed.
Comprehensive hardware redundancy for the management modules, power supplies, and cooling system.
Improved network resiliency that includes hitless management failover with OSPF and IP multicast non-stop routing, BGP graceful restart capabilities, as well as hitless (in-service) software upgrades to further enhance both system availability and overall network availability. The Multi-Chassis Trunking (MCT) feature allows all links to remain active and forward traffic, and provides instantaneous link or node failover.
Networks that are greener than the competition – lower power consumption & significantly lower thermal output.
Some of the lowest ongoing maintenance costs in the world. Your TCO will be reduced.

Brocade Virtual Cluster Switching Provides a Cloud-Optimized Network

With the introduction of Brocade Virtual Cluster Switching (VCS™) technology for the data center, Brocade has transformed classic Ethernet into an Ethernet fabric. As shown in Figure 2, a Brocade VCS Ethernet fabric flattens the data center network and connects to the core routers, which can be Brocade MLX Series or other vendor routers. Storage traffic from the Ethernet fabric will access the Brocade DCX® Backbone family of storage network switches. Via core routers, Brocade ServerIron® ADX Series of high-performance application delivery controllers provides secure, scalable, and efficient client access to applications. In the future, Brocade VCS Dynamic Services will integrate Brocade ServerIron ADX functionality into the Ethernet fabric along with firewall and encryption services, simplifying placement and management of these essential functions. Brocade VCS Dynamic Services will also provide Ethernet fabric extension between data centers so applications can easily move between private and public cloud services.

With Brocade VCS technology, Brocade is the first vendor to deliver an Ethernet fabric for a cloud-optimized network, a network that is ready for deployment in both the public and private cloud data centers.

Virtual Top-of-Rack Architecture in a Data Center

At the access layer of the network, the Brocade MLX Series is deployed in a middle-of-row or end-of-row architecture and can be directly connected to up to 1536 servers in a single chassis. The Brocade MLX Series 48-T-A module is deployed in an end-of-row Virtual Top-of-Rack (VToR) architecture. Each 48-T module supports 8 x MRJ-21 connectors (consolidates 6 x RJ45 connectors for each MRJ-21) equivalent to 48 access ports (10/100/1000) per Brocade MLX module. Passive patch panels (meaning no power consumption) are placed in the top of each rack where the MRJ-21 cables connect and the servers are then cabled to the patch panels. The MRJ21 cables can be dual-homed to two Brocade MLX Series chassis in active-active Layer2/3 using MCT to deliver higher resiliency and performance in a simplified architecture.

This architecture combines the access and aggregation layer, and helps improve performance by decreasing latency due to a reduced number of hops. It also helps lower capital expenditures by reducing the number of devices and cables needed, and helps lower operating expenses by simplifying management and increasing availability. Finally, organizations can extend Layer 3 functionality, including Multi-VRF and MPLS, all the way to the edge.

Using MPLS to Connect Data Centers

Today's organizations must be able to ensure high availability between geographically dispersed data centers and migrate virtual machines between data centers. These requirements are driving the need to extend Layer 2 VLANs across the WAN. To meet this need, the Brocade MLX Series offers point-to-point Layer 2 MPLS VPNs (Virtual Leased Lines, or VLLs) and multipoint Layer 2 MPLS VPNs (Virtual Private LAN Service, or VPLS).

Both solutions offer a viable alternative for organizations that are averse to deploying loop-mitigating protocols (such as RSTP or MSTP) across large Layer 2 domains. In addition, these low-latency, highly resilient solutions are based on proven standards and help provide significant cost savings while meeting the requirements of connecting geographically dispersed data centers.

Multi-Chassis Trunking

Brocade MLX Series delivers Multi-Chassis Trunking (MCT), which is an enhancements to Link Aggregation Groups (LAGs)---IEEE 802.3ad (802/1ax)--providing nodal redundancy and physical and modular redundancy with sub-second recovery in case of a failed link in the group. Based on the concept of MCT peers, two Brocade MLX Series switches act as one logical switch with access switches or servers (called "MCT clients") connected via LAGs divided across the MCT pair. With the MCT pair appearing as a single logical switch, as shown in Figure 2, a loop-free topology is achieved; in which all links are active/active with sub-second recovery, eliminating the need for spanning tree protocols. Since the MCT protocol is based on standard LAG, the edge node (access switch or server) is transparent to the MCT protocol, which supports any third party vendor device that supports LAG. By deploying the Brocade MLX Series with MCT, network simplicity and higher resiliency is achieved together with full use of all network links.