<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=192364217926708&amp;ev=PageView&amp;noscript=1">
Contact an Expert

Modern Data Centers - Supporting an Application Super-Storm

AdobeStock_78071686-611468-edited.jpeg

Your employees require applications to do their jobs, while customers rely on them to connect with your business and advance their own. Your users demand immediate, uninterrupted, and secure access to the applications they need. Expectations are high.

In fact, according to one source, on average, businesses will deploy 17 new application services to support this application explosion over the next 12 months.  

Networking and data centers have become so important, thattraditionally hands-off C-suite executives are being forced to speak the same language as Information Technology teams and understand the issues IT routinely faces. In order to meet the needs of IT, these managers must address budget constraints, and understand the necessity of advanced tools like automation within the environment.

With a deeper knowledge base and operational understanding of the data center and how IT teams operate, organizations will be better equipped to serve their customers -- both internally and externally.

This engagement from senior management has been a progression that has paced with our network and data centers technology. At a time when we relied on mainframes and client/server environments, networks and data centers have been something left to the technologists. And while it wasn't long ago that we saw MPLS as the key to the future, 56.1% of businesses expected to see their need for storage capacity increase by 25% or more just over a year ago, with some businesses expecting a 100 - 200% increase over the last year.

It's no revelation that business today is almost unilaterally affected by data networks:

  • The number of Facebook users has surpassed 1.5 billion
  • While 500,000 smartphones shipped in 2011, more than 1.5 billion were sent out in recent years
  • Goldman Sachs has predicted a compound annual growth rate of 30% thru 2018 for the cloud
  • According to the IDC, the Internet of Things is set to grow from $655.8 billion in 2014 to $1.7 trillion in 2020

And, while numbers like these are astounding, we can find comparable data points like these for every business regardless of size. These numbers are remarkable today, but with the influence of emerging markets and the proliferation of technology, it won't be long before we look at these statistics with the same “remember when?” nostalgia conjured presently at the idea of the first TVs or desktop PCs.

When things unexpectedly come to a halt, whether it’s because of a natural disaster, cyber attack or just lack of capacity, functionality and service can falter with dire consequences. A recent estimate of the cost of downtime (whatever the reason), was about $9,000 per minute.   Consider this and it becomes clear why the C-suite is so interested in what we do with our data centers and networks.

Businesses today need cost-effective solutions for resource-intensive computing and collaboration applications. They need complete network and data center technology solutions that offer reliability, performance and cost-effectiveness.

While networks and data centers are our lifeblood, technology has adapted to meet our needs. Advancements have been made which, if adopted, will create better user experiences.

Need proof? Already, we're beginning to see companies shift the bulk of their investments to implementing solutions that enable data to be utilized where it’s generated and where business processes occur—at the edge. And, we no longer need to worry about that.

Most modern data center switching design is built on a Spine/Leaf architecture. You create some core spine switches and then every leaf is connected to every spine in a full mesh topology. What’s nice about this architecture, and the reason why it is so often deployed is that it is feature rich, particularly when deployed with switches such as the Cisco Nexus series. In a nutshell, you get:

  • Architectural flexibility: Energy efficient three-tier or leaf-spine architecture. They also support scalable virtual extensible LAN (VXLAN) multi-tenancy.
  • Programmability: Use an open-object API model to provision Layer 2 and 3 features.
  • Real-time visibility and telemetry: Built-in sensors support rich traffic flow telemetry and line-rate data collection and tracking of application traffic patterns.
  • Scalability: Segment routing facilitates scalability and virtualization.
  • High availability: Switches have fully redundant and hot-swappable components. ASICs improve reliability and performance.
  • Investment protection: An existing 10 GE cabling plant can be reused for 40 GE with a 40-Gbps bidirectional transceiver. FCoE support provides fabric convergence for LAN and SAN, lowering TCO.

Over the last few years, storage and infrastructure teams have been asked to do more with fewer resources at their disposal. While data at many organizations continues to collect at an alarming rate, budgets are not growing at the same pace. This indicates that storage professionals can no longer rely on bulk purchases of traditional disk systems to get by.

Organizations must look beyond their existing storage and infrastructure strategies to find more efficient ways to contain data growth, while accelerating the delivery of storage services to stakeholders.

In the past three to five years, hyper converged platforms have become legitimate alternatives to traditional storage systems. They have shown that storage does not have to be confined to proprietary external arrays.

Hyper-converged solutions combine computation, networking, and storage resources into an easy-to-use system.  These tightly coupled elements comprise a hyper converged infrastructure that brings new levels of speed and efficiency to an IT organization. Hyper-converged solutions enable rapid deployment of new services and applications.  They also carry the benefits of converged infrastructure, including a single shared resource pool. Hyper-convergence goes far beyond servers and storage, bringing into the convergence fold many services that make some legacy services obsolete, such as dedicated storage arrays, de-duplication, and data protection.

Hyper-convergence doesn’t necessarily require you to replace existing infrastructure in order to be of immediate value.  These platforms are designed for independent scaling of computation, caching, and capacity, all while providing data optimization, giving you full flexibility to scale your environment based on evolving business needs.

Want to learn more about how the IT infrastructure market is changing? Download our free whitepaper "The Evolution of Convergence" to learn more!

Comments

See what ShoreGroup can do for you
Contact an Expert