Data Center Interconnect (DCI) is an architecture for connecting two or more geographically distributed data center locations. Often when one thinks about DCI what comes to mind is a router sitting at the edge of the Data Center (DC) connected to a DWDM box with a point-to-point connection to a mirror set of equipment at another data center. With modern DCI solutions however, interconnectivity between distributed data centers goes beyond simple point-to-point connectivity to enable seamless unification of multiple data centers; leveraging spine and leaf switches that act in unison through a management and data plane fabric. This approach delivers much more than typical point-to-point DCI and supports high-performance and scale-out architectures that allow multiple data centers to work together more efficiently – dramatically simplifying operations, reducing the potential for human error and increasing resiliency and security.
Six Reasons to Consider Unifying Your Multi-Site Data Centers
- Preparing for Edge Compute – Most enterprises have at least two data centers in a primary and backup architecture. However, as we move towards a world of the internet of things (IoT) and with new applications that require ultra-low latency, data centers are going to need to become more distributed. While it still may be a couple of years off, the topic of the Edge was discussed recently at the Gartner IT Infrastructure, Operations and Cloud Strategy Conference and at the ONF Connect Conference (focused on enterprises and service providers, respectively). Organizations deploying smaller edge compute data centers – either on-premises or with a colocation provider – should take a hard look at deploying a fabric that can unify multiple sites seamlessly and leverage open networking to keep costs under control.
- Growth. For those organizations looking upgrade the capacity and speed inside and between data center locations, it’s an ideal time to look at modernizing the DCI. If traffic has grown from 1G/10G to 25GbE server to top of rack (TOR) uplinks and to 40/100G for TOR to spine uplinks, there is clearly a need to support these higher speeds. As part of this effort, organizations should also look at networking equipment that can unify multiple sites through a fabric. The ultimate goal here is to ensure a good experience for both employees and customers, which requires a level of performance in line with the growth inside the data center.
- Data Center Migration/Consolidation: Many data center owners are migrating workloads to the cloud, but not all workloads. Consequently, they’re still working at making their existing data center infrastructure more efficient, elastic, and resilient. Sometimes this means reducing the number of data center sites from 10s to a handful – Sometimes this means moving DCs to carrier-neutral colocation facilities or to lower risk facilities – migration. In either case this requires either managing two data center locations or migrating from your current data center location to a new location. A high capacity DCI fabric can dramatically simplify the movement of your workloads.
- Simplify Operations: The modern IT organization is focused on automation and orchestration, and for good reason. IT is asked to do more with less. Next-generation DCI solutions are highly programmable and bring a level of automation that dramatically simplifies overall operational complexity. The opportunity here is to make 40 switches look like one switch, with all 40 being controlled from any switch via CLI or from any switch via a REST API with full CLI parity. Well implemented data center fabrics with next-generation software defined networking features can deliver this type of functionality.
- End-of-Life Products. For organizations with DCI network equipment that are older, approaching, or at end of life, a DCI upgrade should be a top priority. These End-of-Life products pose a true operational risk to the business because if one goes down, there is no support. End-of-Life solutions have no software development, no upgrades leading to security vulnerabilities. Dated solutions lack the latest automation capabilities and are therefore difficult to maintain and more expensive to operate. An upgrade might provide critical operational benefits that will benefit the business in several areas.
- Disaster Recovery: The availability and performance of the data center is critical to the business continuity of any organization. Most data center owners should have at least two data center locations for disaster recovery. Whether these are located in colocation facilities or privately built, it is important to have a redundancy strategy. Data center fabrics can make this failover across two or more sites much simpler leveraging technologies like distributed routing with anycast gateway functionality.
Before you do upgrade your DCI, consider this
- Reducing Complexity. The Pluribus Adaptive Cloud Fabric™ makes the DCI solution easier to manage for enterprises and service providers that want network consistency across sites by federating all top of rack and spine switches together and building a VXLAN mesh with distributed anycast routing. With a single pane of glass for management, Pluribus gives you the choice of automation through REST API (with full CLI parity) or Ansible modules, and complete management platform GUI-based through Pluribus UNUM™. Alternatively, Netvisor CLI is an option that is available for enhanced operations and troubleshooting. With Pluribus, you can control the entire fabric from any switch and you choose which management and automation strategy works best for your IT organization.
- Lower Costs. When is cost not a key consideration for an IT decision? Pluribus leverages open networking solutions that are based on disaggregating the hardware and software layers of traditional, legacy switching platforms to open, standards-based, bare-metal hardware with open software like our Netvisor® ONE Network Operating Systems (NOS). The disaggregation of the software from the hardware means that vendor lock-in is no longer an issue, providing greater flexibility to upgrade going forward. Consequently, Pluribus enables organizations like Econocom to assemble the best combination of networking hardware and software to meet their specific deployment requirements.
The world of IT is changing fast and your data center needs to keep up. If you are ready for a change and want to unify your multi-site data center while lowering costs, contact us here or send a note to us at firstname.lastname@example.org
Did you know? Pluribus Networks was named an Innovator by IDC for Datacenter Software-Defined Networking, 2018.
Sign up for our blog digest to get the latest news, business tips, and thought leadership from The Pluribus Blog, every month.
About the Author
Mike is Chief Marketing Officer of Pluribus Networks. Mike has over 20 years of marketing, product management and business development experience in the networking industry. Prior to joining Pluribus, Mike was VP of Global Marketing at Infinera, where he built a world class marketing team and helped drive revenue from $400M to over $800M. Prior to Infinera, Mike led product marketing across Cisco’s $6B service provider routing, switching and optical portfolio and launched iconic products such as the CRS and ASR routers. He has also held senior positions at Juniper Networks, Pacific Broadband and Motorola.