Data Center Tier Levels

Your enterprise's old data center has reached the end of the road, and the whole kit and caboodle is moving to a colocation provider. What should you be looking for in the data center, and just how much uptime comes from within?

A lot of the work measuring data center reliability has been done for you. The Uptime Institute's simple data center Tier levels describe what should be provided in terms of overall availability by the particular technical design of a facility.

There are four Uptime Tiers. Each Tier must meet or exceed the capabilities of the previous Tier. Tier I is the simplest and least highly available, and Tier IV is the most complex and most available.

Tier I: Single non-redundant power distribution paths serve IT equipment with non-redundant capacity components, leading to an availability target of 99.671% uptime. Capacity components include items such as uninterruptable power supply, cooling systems and auxiliary generators. Any capacity component failure will result in downtime for a Tier I data center, as will scheduled maintenance.

Tier II: A redundant site infrastructure with redundant capacity components leads to an availability target of 99.741% uptime. The failure of any capacity component can be manually operated by switching over to a redundant item with a short period of downtime, and scheduled maintenance still requires downtime.

Tier III: Multiple independent distribution paths serve IT equipment; there are at least dual power supplies for all IT equipment and the availability target is 99.982% uptime. Planned maintenance can be carried out without downtime. However, a capacity component failure still requires manual switching to a redundant component, which will result in downtime.

Tier IV: All cooling equipment is dual-powered and a completely fault-tolerant architecture leads to an availability target of 99.995% uptime. Planned maintenance and capacity component outages trigger automated switching to redundant components. Downtime should not occur.

In most cases, costs reflect Tiering -- Tier I should be the cheapest, and Tier IV should be the most expensive. But a well-implemented, well-run Tier III or IV facility could have costs that are comparable to a badly run lower-Tier facility.

Watch out for colocation vendors who say their facility is Tier III- or Tier IV-"compliant"; this is meaningless. Quocirca has even seen instances of facility owners saying they are Tier III+ or Tier 3.5. If they want to use the Tier nomenclature, then they should have become certified by the institute.

Data center design standards bodies

Several organizations produce data center design standards, best practices and guidelines. This glossary lets you keep track of which body produces which standards, and what each acronym means.

ASHRAE: The American Society of Heating, Refrigerating and Air-Conditioning Engineers produces data center standards and recommendations for heating, ventilation and air conditioning installations. The technical committee develops standards for data centers' design, operations, maintenance and energy efficiency. Data center designers should consult all technical documents from ASHRAE TC 9.9: Mission Critical Facilities, Technology Spaces and Electronic Equipment. www.ashrae.org.

BICSI: The Building Industry Consulting Service International Inc. is a global association that covers cabling design and installation. ANSI/BICSI 002-2014, Data Center Design and Implementation Best Practices, covers electrical, mechanical and telecommunications structure in a data center, with comprehensive considerations from fire protection to data center infrastructure management. www.bicsi.org.

BREEAM: The BRE Environmental Assessment Method (BREEAM) is an environmental standard for buildings in the U.K. and nearby countries, covering design, construction and operation. The code is part of a framework for sustainable buildings that takes into account economic and social factors as well as environmental. It is managed by BRE Global, a building science center focused on research and certification. http://www.breeam.org/

The Green Grid Association: The Green Grid Association is well-known for its PUE metric, defined as power usage effectiveness or efficiency. PUE measures how well data centers use power by a ratio of total building power divided by power used by the IT equipment alone. The closer to 1 this ratio comes, the more efficiently a data center is consuming power. Green Grid also publishes metrics for water (WUE) and carbon (CUE) usage effectiveness based on the same concept. www.thegreengrid.org

IDCA: The International Data Center Authority is primarily known as a training institute, but also publishes a holistic data center design and operations ranking system: the Infinity Paradigm. Rankings cover seven layers of data centers, from location and facility through data infrastructure and applications. www.idc-a.org

IEEE: The Institute of Electrical and Electronics Engineers provides more than 1,300 standards and projects for various technological fields. Data center designers and operators rely on the Ethernet network cabling standard IEEE 802.3ba, as well as IEEE 802 standards, for local area networks such as IEEE 802.11 wireless LAN specifications. www.ieee.org

ISO: The International Organization for Standardization is an overarching international conglomeration of standards bodies. The ISO releases a wide spectrum of data center standards, several of which apply to facilities. ISO 9001 measures companies' quality control capabilities. ISO 27001 certifies an operation's security best practices, regarding physical and data security as well as business protection and continuity efforts. Other ISO standards that data center designers may require include environmental practices, such as ISO 14001 and ISO 50001. www.iso.org

LEED: The Leadership in Energy and Environmental Design is an international certification for environmentally conscious buildings and operations managed by the U.S. Green Building Council. Five rating systems -- building design, operations, neighborhood development and other areas -- award a LEED level -- certified, silver, gold or platinum -- based on amassed credits. The organization provides a data-center-specific project checklist, as the LEED standard includes adaptations for the unique requirements of data centers. www.usgbc.org

NFPA: The National Fire Protection Association publishes codes and standards to minimize and avoid damage from hazards, such as fire. No matter how virtualized or cloudified your IT infrastructure, fire regulations still govern your workloads. NFPA 75 and 76 standards dictate how data centers contain cold/cool and hot aisles with obstructions like curtains or walls. NFPA 70 requires an emergency power off button for the data center to protect emergency respondents. www.nfpa.org

NIST: The National Institute of Standards and Technology oversees measurements in the U.S. NIST's mission includes research on nanotechnology for electronics, building integrity and diverse other industries. For data centers, NIST offers recommendations on authorization and access. Refer to special publications 800-53, Recommended Security Controls for Federal Information Systems, and SP 800-63, Electronic Authentication Guideline. www.nist.gov

OCP: The Open Compute Project is known for its server and network design ideas. But OCP, started by Internet giant Facebook to promote open source in hardware, also branches into data center design. OCP's Open Rack and optical interconnect projects call for 21 inch rack slots and intra-rack photonic connections. OCP's data center design optimizes thermal efficiency with 277 Volts AC power and tailored electrical and mechanical components. www.opencompute.org 

OIX: The Open IX Association focuses on Internet peering and interconnect performance from data centers and network operators, along with the content creators, distribution networks and consumers. It publishes technical requirements for Internet exchange points and data centers that support them. The requirements cover designed resiliency and safety of the data center, as well as connectivity and congestion management. www.open-ix.org

Telcordia: Telcordia is part of Ericsson, a communications technology company. The Telcordia GR-3160 Generic Requirements for Telecommunications Data Center Equipment and Spaces particularly relates to telecommunications carriers, but the best practices for network reliability and organizational simplicity can benefit any data center that delivers applications to end users or host applications for third-party operators. The standard deals with environmental protection and testing for hazards, ranging from earthquakes to lightning surges. www.ericsson.com

TIA: The Telecommunications Industry Association produces communications standards that target reliability and interoperability. The group's primary data center standard, ANSI/TIA-942-A, covers network architecture and access security, facility design and location, backups and redundancy, power management and more. TIA certifies data centers to ranking levels on TIA-942, based on redundancy in the cabling system. www.tiaonline.org

The Uptime Institute: The Uptime Institute certifies data center designs, builds and operations on a basis of reliable and redundant operating capability to one of four tier levels. Data center designers can certify plans; constructed facilities earn tier certification after an audit; operating facilities can prove fault tolerance and sustainable practices. Existing facilities, which cannot be designed to meet tier level certifications, can still obtain the Management Operations Stamp of Approval from Uptime. www.uptimeinstitute.com

Five Ways Next-Gen Data Centers Will Be Different from Today’s

Cloud and virtualization will become the normal for the modern data center as new technologies improve density, efficiency and management. There is clear growth in both virtualization and cloud services all over the world.

In fact, a recent Gartner report says that cloud computing will become the bulk of new IT spending by 2016. “In India, cloud services revenue is projected to have a five-year projected compound annual growth rate (CAGR) of 33.2 percent from 2012 through 2017 across all segments of the cloud computing market. Segments such as Software as a Service (SaaS) and Infrastructure as a Service (IaaS) have even higher projected CAGR growth rates of 34.4 percent and 39.8 percent,” said Ed Anderson, research director at Gartner. “Cloud computing continues to grow at rates much higher than IT spending generally. Growth in cloud services is being driven by new IT computing scenarios being deployed using cloud models, as well as the migration of traditional IT services to cloud service alternatives.”

With so much new cloud data traversing the data center – and the increased number of users utilizing cloud services – what will the next-generation data center resemble? What are some of the efficiencies that administrators can utilize? How will the business evolve around new data center demands?

Let’s look at five ways the next-generation data center will evolve.

The software-defined data center (SDDC). Think of this as the logical layer within the data center. Security, storage, networking and even the data center now incorporate the software-defined technologies (SDx) realm. This logical layer allows for even greater control of both physical and virtual resources. Let me give you some specific examples – Storage: Atlantis USX and VMware vSAN. Networking: Cisco NX-OS and VMware NSX. Security: Palo Alto PAN-OS and Juniper Firefly. Data center: VMware SDDC and IO.OS. These are solid platforms which help control many new aspects of cloud computing and the next-generation data center.

Multi-layered data center control. The data center is hosting a number of different systems. With that in mind, the control layer must be extremely diversified. This management console now integrates into APIs to span an ever-growing data center footprint. New integrations allow for big data control, data manipulation, and even resource allocation. Here’s a specific example around the latest release of OpenStack, Havana. The networking component (Neutron) allows administrators to do some pretty amazing things with their cloud model. Now, with direct integration with OpenFlow, Neutron allows for greater levels of multi-tenancy and cloud scaling by adopting various software-defined networking technologies into the stack.

The data center operating systems (DCOS). The spanning data center needs a spanning control layer. Already, global data center providers are deploying data center operating control layers which manage policies, resources, users, VMs, and much more. Most of all, you’re creating a proactive management infrastructure capable of greater scale. For example, IO and their IO.OS environment helps control many of the absolutely critical components – from chip to chiller. The great part is that this DCOS layer has visibility into every critical aspect that a data center has to present.

Infrastructure agnosticism. To be completely honest, the future data center won’t care which hypervisor, storage layer, or server platform you’re running. Layered management tools will be able to pool resources intelligently and present them to workloads. This type of infrastructure and data center agnosticism will allow administrators to scale better and create more powerful cloud platforms. Technologies like BMC begin to explore the concept of agnostic cloud control. By connecting with major control plains and interfacing with solid APIs, the cloud computing concept and everything beneath it can be better abstracted.

Data center automation (and robotics). The next-generation data center will revolve around better workflow orchestration and automation services. Resources will be provisioned and de-provisioned dynamically, users will be load-balanced intelligently, and administrators will be able to focus on providing even greater levels of efficiency. Know what else the next-gen data center might have more of? Robotics. Big robotics makers like FANUC are already developing smaller, smarter and much faster robotics. Here’s another interesting example: a recent article discusses how IBM is actually using robotics to plot the temperature patterns in data centers to improve their energy efficiency. Basically, IBM is using robots based on iRobot Create, a customizable version of the Roomba vacuum cleaner, to measure temperature and humidity in data centers.

There’s really no question that data center technologies are quickly progressing. New ways to integrate at the API layer, improved methods of optimization, and overall density are all impacting data center platforms. It doesn’t stop here though. Trends show that more users are utilizing IT consumerization to process even more through the cloud. This means that data centers will have to evolve even more.

Introducing “6-pack”: the first open hardware modular switch

As Facebook’s infrastructure has scaled, we’ve frequently run up against the limits of traditional networking technologies, which tend to be too closed, too monolithic, and too iterative for the scale at which we operate and the pace at which we move. Over the last few years we’ve been building our own network, breaking down traditional network components and rebuilding them into modular disaggregated systems that provide us with the flexibility, efficiency, and scale we need.

We started by designing a new top-of-rack network switch (code-named “Wedge”) and a Linux-based operating system for that switch (code-named “FBOSS”). Next, we built a data center fabric, a modular network architecture that allows us to scale faster and easier. For both of these projects, we broke apart the hardware and software layers of the stack and opened up greater visibility, automation, and control in the operation of our network.

But even with all that progress, we still had one more step to take. We had a TOR, a fabric, and the software to make it run, but we still lacked a scalable solution for all the modular switches in our fabric. So we built the first open modular switch platform. We call it “6-pack.”

The platform

The “6-pack” platform is the core of our new fabric, and it uses “Wedge” as its basic building block. It is a full mesh non-blocking two-stage switch that includes 12 independent switching elements. Each independent element can switch 1.28Tbps. We have two configurations: One configuration exposes 16x40GE ports to the front and 640G (16x40GE) to the back, and the other is used for aggregation and exposes all 1.28T to the back. Each element runs its own operating system on the local server and is completely independent, from the switching aspects to the low-level board control and cooling system. This means we can modify any part of the system with no system-level impact, software or hardware. We created a unique dual backplane solution that enabled us to create a non-blocking topology.

We run our networks in a split control configuration. Each switching element contains a full local control plane on a microserver that communicates with a centralized controller. This configuration, often called hybrid SDN, provides us with a simple and flexible way to manage and operate the network, leading to great stability and high availability.

The only common elements in the system are the sheet metal shell, the backplanes, and the power supplies, which make it very easy for us to change the shell to create a system of any radix with the same building blocks.

Below you can see the high-level “6-pack” block diagram and the internal network data path topology we picked for the “6-pack” system.

The line card

If you’re familiar with “Wedge,” you probably recognize the central switching element used on that platform as a standalone system utilizing only 640G of the switching capacity. On the “6-pack” line card we leveraged all the “Wedge” development efforts (hardware and software) and simply added the backside 640Gbps Ethernet-based interconnect. The line card has an integrated switching ASIC, a microserver, and a server support logic to make it completely independent and to make it possible for us to manage it like a server.

The fabric card

The fabric card is a combination of two line cards facing the back of the system. It creates the full mesh locally on the fabric card, which in turn enables a very simple backplane design. For convenience, the fabric card also aggregates the out-of-band management network, exposing an external interface for all line cards and fabrics.

Bringing it together

With “6-pack,” we have created an architecture that enables us to build any size switch using a simple set of common building blocks. And because the design is so open and so modular – and so agnostic when it comes to switching technology and software – we hope this is a platform that the entire industry can build on. Here's what we think separates “6-pack” from the traditional approaches to modular switches:

“6-pack” is already in production testing, alongside “Wedge” and “FBOSS.” We plan to propose the “6-pack” design as a contribution to the Open Compute Project, and we will continue working with the OCP community to develop open network technologies that are more flexible, more scalable, and more efficient.

Preparing for the Data Center of the Future

Data center operators are under more pressure than ever to provide the fastest, most reliable data possible while balancing demands for higher computing power and efficiency. Meanwhile, their use of virtualization, cloud architectures, and security techniques, as well as software-defined networking and storage has given rise to increasingly complex environments.

Given this already challenging environment, the term “future-proofing” is often chalked up to vendor-speak, meant to scare customers into buying oversized equipment for just-in-case scenarios that may actually never happen.

However, future-proofing, or the attempt to anticipate future demands, is an important element to data center management and planning. New IT devices are coming to market with unforeseen capabilities at record volume and pace, using more and more data, making it seemingly impossible to anticipate what the future will bring and how it will affect the data center.

Future-Proof Without the Cost

There are ways to future-proof the data center without having to make costly investments, while still ensuring that IT infrastructure can adapt and change over time to meet evolving business needs – even in a rapidly changing, unpredictable landscape.

Through data center infrastructure management (DCIM) software and prefabricated, modular infrastructure, data center operators can stimulate adaptability and flexibility for existing and new facilities. Data centers can anticipate and respond to current and future data center needs by:

• Accounting for increasing demands for processing power and storage capacity
• Applying a more sophisticated level of monitoring, analysis and management
• Enabling system management integration between facilities and IT
• Providing smart energy management and increased control capabilities

This allows data centers to meet evolving company needs, future technologies and the new environmental factors, while extending the service life of existing infrastructure.

Taking Advantage of Prefabricated Data Centers

In January 2014, we looked at the reasons why prefabricated, modular data center infrastructure can help owners and operators meet challenges related to traditional data center builds, such as having too many parties involved, the complexity of long-duration builds, quality and cost inconsistencies and incompatibility of equipment.

However, the biggest advantage of prefabricated, modular data center infrastructure in terms of future-proofing are closely tied to its ability to easily scale up or down capacity. Not only does this reduce both upfront capital and ongoing operational expenses (CAPEX and OPEX), but owners and operators can quickly add power and cooling capacity to meet increasing demands and actual business needs.

This is compared to the traditional method of installing the power and cooling infrastructure as part of the data center building and sizing the facilities according to potential maximum future needs – an almost impossible (and costly) task that uses up valuable real estate, increases utility bills and decreases efficiency – without truly guaranteeing that estimates will ever match actual requirements.

What if facility power, power distribution, cooling and IT physical infrastructure were not built into the building, but instead were prefabricated building blocks that could be deployed and changed as needed throughout the life cycle of the data center? Owners and operators could deploy prefabricated IT building blocks and raise density or availability levels by adding extra matching power and cooling building blocks, or, in the future, even swap out AC-powered prefabricated building blocks to DC-powered prefabricated building blocks, which could possibly be the standard in the future.

Monitor and Manage the Data Center of the Future

Intelligent, informed data center planning with an eye toward future needs can help owners and operators avoid being caught off-guard by unanticipated changes within the IT environment or changing business landscapes. Planning is most effective when decisions are informed by past and real-time data collected from IT and facility systems, which provides actionable insight from the data collected via DCIM solutions.

The ability to use DCIM data as a benchmarking tool in the planning process is perhaps the most effective method for preparing for future data center needs. This is because DCIM solutions can aggregate data collected from both the physical building structure and IT equipment within the facility – from the building down to the server level – not only bridging the all-too-common gap between facilities and IT, but also allowing owners and operators to identify trends, develop action plans and prepare for potential problems or needs down the line.

DCIM solutions also show how adding, moving or changing physical equipment can affect operations, thereby providing accurate insight for common planning questions and optimizing existing infrastructure capacities.

By increasing data center flexibility through prefabricated, modular data center infrastructure and DCIM software, data center operators can transition their facility from a cost center to a business driver enabling organizations to better mitigate risk and prepare for the future.

OTV - Quick Start Guide - Concepts & Configurations

Click Here to Download the Presentation

New Remote Integrated Services Engine (RISE) Enhances L4-7 Appliance Integration with Nexus 7000 Series

Remote Integrated Service Engine (RISE) is a new protocol being added to the Nexus 7000 and 7700 platforms through NX-OS (software upgradeable to existing devices), that integrates service appliances to be attached to Nexus 7000 Series switches with the same benefits as if the appliance was directly connected to the switch backplane, as if it were a dedicated service module. Cisco RISE establishes a communication path between the network data plane and the service appliance, simplifying deployments and optimizing data paths with better traffic visibility within the data center.

Initially, Citrix NetScaler Application Delivery Controllers (ADC) and the Cisco Prime Network Analysis Module (NAM) are the first services appliances that have integrated with RISE, and have been tested and Certified as “RISE-enabled”. With the announcement of RISE, we expect to develop an ecosystem of partners that will work with Cisco to take advantage of this technology, including other application services vendors and firewalls.

The service appliances (e.g., Citrix NetScaler and Cisco Prime NAM) are directly attached by standard network cable to RISE-configured ports on the Nexus 7000 Series switches in a typical virtual Port Channel (VPC) deployment. Appliances can also be attached in indirect mode through any switched (Layer 2) network. Either scenario (direct or indirect connection) allows for device and data path redundancy for fault tolerance.

There are several management advantages to connecting service nodes through RISE. First, RISE can be configured through the Nexus management console or management platform. However, the specific service appliance features are still configured using the existing device management tools.  This ensures separation of duties between the networking and security or application teams, as well as eliminating any additional management complexity from the RISE connection.

A key use case for RISE is for Application Delivery Controllers that are connected in one-arm mode (out of band to the main flow of switch traffic), which alleviates the ADC from being a bottleneck, and allows the ADC to process only traffic that is applicable. However, admins frequently have to manually configure policy-based routes to direct traffic to the ADC, as well as preserve all proper addressing to reverse the inbound path back to the client, which is a tedious process for each new application service, and prone to human error. RISE integration solves this problem with automated policy-based routing (PBR), where the ADC can simply obtain the Cisco Nexus switch parameters it needs to automatically implement the routes dynamically, as new services are provisioned. This significantly simplifies application scaling and cloud deployments by automating the addition and deletion of routes as additional workloads are brought online.

Some key advantages of RISE integration with Citrix NetScaler include:

• Simplified provisioning: Auto-discovery and bootstrap capabilities reduce administrator involvement for NetScaler ADC direct-mode implementations from 30 steps to 8 steps.
• Data-path optimization: Administrators can use Cisco RISE capabilities to configure a broad range of ADC device features to automate and optimize delivery of network services and traffic through the core switch.
• ADC off-load: Cisco RISE integration frees Citrix NetScaler resources from having to manage ADC flows to help ensure that they are routed back through Citrix NetScaler. This feature enables more customers to adopt one-arm configurations, which allows better sizing and scaling of Citrix NetScaler, while preserving client visibility at the application layer.
• Enhanced application availability: Real-time route updates between Citrix NetScaler and the Cisco Nexus 7000 Series Switch eliminate route black-holing when application failures occur. By enabling Citrix NetScaler to deliver route health updates to the Cisco Nexus 7000 Series Switch through Cisco RISE, the solution allows customers to more easily deploy shared services within and across data centers at a significantly reduced cost of operation with greater availability than ever before.
• Integrated multi-tenancy support: Cisco RISE integration spans multi-tenancy features on both platforms: virtual device contexts (VDCs) on Cisco Nexus 7000 Series Switches, and the capability to run up to 80 independent Citrix NetScaler instances on a Citrix NetScaler SDX appliance, and up to 16 RISE clients on NetScaler VPX or MPX. This feature provides comprehensive flexibility to support multitenant scenarios, including the capability to set up Cisco Nexus VDCs and Citrix NetScaler instances in one-to-many, many-to-one, and a countless variety of many-to-many configurations.
• Significant CapEx and OpEx savings: RISE provides enhanced data path optimizations and simplified provisioning that allows customers to witness significant CapEx and OpEx savings thereby providing business continuity and cost reduction.
• Reduced Total cost of Ownership (TCO): Fully integrated with Nexus 7000 switches, RISE fosters simplified manageability, automated operation and increased utilization of application delivery resources.
• Enhanced business resiliency: RISE helps accelerate the speed of application deployment and provides business agility using components that respond in real time to dynamic application requirements and newly provisioned resources.

RISE is available for customers in NX-OS release 6.2(8) on the Nexus 7000 and 7700 platform, and requires the ENHANCED LAYER2 PKG license.

Best Data Center Certifications for 2014

Certified Data Center Management Professional (CDCMP)

In 1996, CNet Training began as an IT training company in the UK but has since grown into a global training organization with data center and network infrastructure courses offered on nearly every continent.

One of the most popular certifications in the CNet cert program is the Certified Data Center Management Professional (CDCMP). Candidates must take CNet Training courses (a core unit and a professional unit) to earn this credential. The required training includes core topics such as basic design principles, physical infrastructure, project management and data center management. The professional unit covers management topics (people, processes, facilities and services), business and IT strategies, audits, regulations and asset management.

In addition to the CDDMP, CNet Training offers numerous other data center-related certifications, such as the Certified Data Center Design Professional (CDCDP), Certified Data Center Energy Professional (CDCEP), Certified Data Center Audit Professional (CDCAP) and the Certified Data Center Technician Professional (CDCTP). The company also offers a credential for telecommunications project management and two data center energy practitioner-level certs. This is a fairly mature and comprehensive data center certification program, all in all.

Table 1: CNet Training CDCMP Facts & Figures

Certification name	Certified Data Centre Management Professional (CDCMP)
Prerequisites/ Required courses	Experience working in a data center environment Completion of CDCMP 7-day full program course Candidates may obtain the Certified Data Center Management (CDCM) credential and then complete the professional unit 4-day course to obtain the CDCMP Recertification required every 3 years; $295 USD, approximately 28 hours of study
Number of exams	Included with course; upon completion of course, candidates gain the CDCMP credential and the Level 5 BETC Advanced Professional Award in Data Center Management qualification
Cost per exam	Full program course:  $5,750 USD
URL	www.cnet-training.com/data-centre-courses/certified-data-centre-management-professional-cdcmp/
Self-study materials	None at this time.

Cisco Certified Network Professional Data Center (CCNP Data Center)

Networking professionals looking to validate their data center skills and achieve a competitive edge in the work place can't go wrong with the Cisco Certified Network Professional (CCNP) Data Center credential.

Cisco certifications continue to be some of the most recognizable and respected credentials in the industry. Geared toward technology architects, along with design and implementation engineers and solutions experts, the CCNP Data Center identifies individuals who can implement Cisco Unified Computing System (UCS) blade and rack-mount servers, and install, configure, manage Cisco Nexus switches. The CCNP Data Center is designed for candidates with 3 to 5 years of experience working with Cisco technologies. 

When pursuing the CCNP Data Center, Cisco lets you choose either a design or troubleshooting track.

Related data center certifications include the Cisco Certified Network Associate (CCNA Data Center), which requires 1 to 3 years of experience, and the Cisco Certified Internetwork Expert (CCIE) Data Center, aimed at professionals with 7 or more years of experience.

Table 2: Cisco CCNP Data Center Facts & Figures

Certification name	Cisco Certified Network Professional Data Center (CCNP Data Center)
Prerequisites/ Required courses	Valid Cisco Certified Network Associate Data Center (CCNA Data Center) certification or any Cisco Certified Internetwork Expert (CCIE) certification Training is recommended but not required
Number of exams	4 exams:    642-999 DCUCI and 642-997 DCUFI    plus    Design track courses: 642-998 DCUCD and 642-996 DCUFD    or    Troubleshooting courses: 642-035 DCUCT and 642-980 DCUFT
Cost per exam	$200 USD per exam; $800 total (price may vary by region)  Exams administered by Pearson VUE
URL	www.cisco.com/web/learning/certifications/professional/ccnp_datacenter/index.html
Self-study materials	Instructor-led, fee-based training is recommended Preparation materials including self-study materials, Cisco Learning Network resources, and available Learning Partner Content:www.cisco.com/web/learning/certifications/professional/ccnp_datacenter/index.html

VMWare Certified Professional 5 – Data Center Virtualization

The VMware VCP5-DCV is one of those credentials that sits firmly on the line between traditional data center networking and cloud management.

VMware offers an extensive certification program with a rigorous Data Center virtualization track, which includes the VCP5-DCV. Candidates must thoroughly understand Domain Name System (DNS), routing and database connectivity techniques, and know how to install, deploy, manage and scale VMware vSphere environments. VMware recommends that candidates have a minimum of 6 months of experience with VMware infrastructure technologies before sitting for the VCP5-DCV exam. 

Table 3: VMware VCP5-DCV Facts & Figures

Certification name	VMWare Certified Professional 5 – Data Center Virtualization
Prerequisites/ Required courses	1. Holders of any valid VCP level certification:       Course: 2 day course on VMware vSphere: What’s New [V5.x] (cost: $1,645 USD); classroom or live online  2. Not VCP4-DCV certified but have completed qualifying course: Same requirements as for those holding any valid VCP level certification 3. Non-VCP credential holders:     Course: One of the following VMware vSphere courses: Install, Configure, Manage [V5.x], Fast Track [V5.x], Optimize and Scale [V5.x], Troubleshooting Workshop [V5.x], or VMWare vSphere with Operations Management Fast Track [V5.1] (cost $3,845 USD); classroom, live online and on site; 5 day course
Number of exams	1 exam Candidates must pass either the VCP510 (based on vSphere 5.0/5.1) or VCP550 (based on vSphere v5.5) exam Exam administered by Pearson VUE
Cost per exam	$225 USD
URL	mylearn.vmware.com/mgrReg/plan.cfm?plan=12457&ui=www_cert
Self-study materials	Practice exams: Free practice exam from VMware: mylearn.vmware.com Fee-based practice exam from MeasureUp starting at $89 USD:www.measureup.com Study guide:The Official VCP5 Certification Guide, Bill Ferguson, VMware Press, 2012; $39.99 USD from Pearson: www.pearsonitcertification.com/store/official-vcp5-certification-guide-9780789749314 Video training: VCP5-DCV Official Cert Training, Bill Ferguson, VMware Press, 2014; Downloadable training video for exam VCP550, $159 USD from Pearson:www.pearsonitcertification.com/store/vcp5-dcv-official-cert-training-video-training-downloadable-9780789753373

Schneider Electric Data Center Certified Associate (DCCA)

The Schneider Electric vendor-neutral DCCA is a terrific entry-level certification for individuals who design, build and manage data centers as part of a data center-centric IT team.

The DCCA certification focuses on proficiency working with physical data center infrastructures, such as power and cooling, racks, cabling, management and security. Schneider Electric offers free training courses through its Energy University, and the DCCA courses can be completed in about 15 hours. The exam itself costs only $250 USD, making the DCCA one of the least expensive data center certifications available. It’s idea for those who design, build, or maintain the physical infrastructure for data centers.

Schneider Electric offers one other cert, the Professional Energy Manager (PEM), which is geared toward folks who perform energy audits/ assessments and recommend measures for making facilities more energy efficient.

Table 4: Schneider Electric DCCA Facts & Figures

Certification name	Schneider Electric Data Center Certified Associate (DCCA)
Prerequisites/ Required courses	16 required learning units, including Exam Overview and Study Guide Learning modules are free
Number of exams	1 exam
Cost per exam	$250 USD
URL	www2.schneider-electric.com/sites/corporate/en/products-services/training/energy-university/data-center-certificate-program.page
Self-study materials	All course materials are self-study

BICSI Data Center Design Consultant (DCDC)

BICSI is a membership association that offers several engineering-oriented IT communications credentials aimed at networking professionals who design and implement optical fiber-, copper-based and wireless infrastructures.

BICSI is perhaps best known for its Registered Communications Distribution Designer (RCDD) and cabling certifications, but it also offers the Registered Information Technology Professional (RITP) and several other certs for telecommunications project management, electronic safety and security design and outside plant design.

A relatively new certification in the BICSI program is the Data Center Design Consultant (DCDC), which is designed for IT professionals with at least 2 years of experience in planning and implementing data centers. This vendor-neutral certification is ideal for data center engineers, architects, designers and consultants.

Table 5: BICSI DCDC Facts & Figures

Certification name	BICSI Data Center Design Consultant (DCDC)
Prerequisites/ Required courses	Minimum of 2 years approved and verifiable experience in design and/or construction of data centers; experience must be current within past 6 years Credential is valid for 3 years; credential holders must earn 24 BICSI continuing education credits (CEC) to recertify
Number of exams	1 exam
Cost per exam	Application fee: Members $245 , nonmembers $370 Exam fee: Members $150 , nonmembers $275 Exam retake fee (if applicable): Members $150 , nonmembers $275 Exam administered by Pearson VUE
URL	www.bicsi.org/double.aspx?l=5194&r=5620
Self-study materials	Multiple BICSI resources are available from the BICSI bookstore atwww.bicsi.org/bookstore.aspx, including:   BICSI 002-2011, Data Center Design and Implementation Best Practices and the Network Systems and Commissioning (NSC) reference, 1st edition;  $360 members/$450 non-members Information Transport Systems Design Standard for K-12 Educational Institutions, $85 members/$105 non-members

A few more data center certs to be aware of come from EMC and Extreme Networks. The EMC Data Center Architect (EMCDCA) Specialist recognizes individuals who plan, architect and deploy storage networking (SAN) solutions, including SANs within a virtualized environment. Extreme Networks offers a Specialist-Data Center Certification (ENS-DC) credential for folks who configure and manage switches and other Extreme Networks data center equipment.

Because of the proliferation of data center virtualization and cloud computing, you can expect the data center networking job market to remain strong in the near future. Achieving a certification can be a real feather in your cap, and open the door to new and better work opportunities.

Understanding Spanning Tree Protocol

Spanning-tree Protocols
802.1d (Standard Spanning-tree)
So the entire goal of spanning-tree is to create a loop free layer 2 domain. There is no TTL in a layer 2 frame so if you don’t have spanning-tree, a frame can loop forever. So the original 802.1d standard set out to fix this. There are a few main pieces to the 802.1d process. They are…

1. Elect a root bridge.
This bridge is the ‘root’ of the spanning-tree. In order to elect a root bridge, all of the switches send out BPDU (Bridge Protocol Data Units). The BPDU has a bridge priority in it which the switches use to determine which switch should be the root. The lowest ID wins. The original standard specified a bridge ID as…

 

As time progressed there became a need to create multiple spanning-trees for multiple VLANs (we’ll get to that later). So, the bridge ID format had to be changed. What they came up with was..

 

 

So, now you know why you need to have a bridge priority that’s in multiples of 4096 (if you don’t.. A total of 4 bits gives you a total of 16 values, 16 * 4096 gives you 65,536 which is the old bridge priority max value – 1).

 

So at this point, we have a mess of switches swarming around with BPDUs. If a switch receives a BPDU with a lower bridge priority it knows that it isn’t the root. At that point, it stops sending out it’s own bridge ID and starts sending out BPDUs with the better (lower) priority that it heard of. In the end, all of the switches will be forwarding BPDUs with the lowest bridge ID. At that point, the switch originating the best(lowest) bridge ID knows that it is the root bridge.

 

2. Each switch selects a root portSo now that we know which switch is the root, every non-root switch needs to select it’s root port. That is, the port with the lowest cost to the root switch. To determine this, the root port sends ‘Hellos’ out of all of it’s port every 2 seconds. When a non-root switch receives the hello, it does a couple of things. First, it reads the ‘cost’ from the hello message and updates it by adding the port cost. So if a hello came in a fast Ethernet port with a cost of 4, the switch would add 19 to it giving you a new cost of 23. After all of the hellos are sent, the switch picks it’s root port by selecting the port which had the lowest calculated cost. Now, a bit about port costs. See the table below…

Interface Speed	Original IEEE Port Cost	New IEEE port Cost
10 Mbps	100	100
100 Mbps	10	19
1000 Mbps	1	4
10000 Mbps	1	2

So as you can see, with the increase in speed came a upgrade to the port costs. Now that we have 40 gig interfaces I’m wondering if they will redo that again. At any rate, if there is a tie, say two ports that have a calculated cost of 23. The switch breaks the tie in the following fashion..

1. Pick the lowest bridge ID of switch that sent the hellos
2. Pick the lowest port priority of the switch that sent the hellos
3. Use the lowest port number of the switch that sent the hellos
(We’ll talk about port priorities in a bit) Now that we have a root port we can move onto step 3.

3. Pick a designated portThis part is pretty easy. Basically, each segment can only have one designated port. The switch that forwards the lowest cost hello onto a particular segment becomes the designated switch and the port that it uses to do that is the designated port. So, that would mean that each port on the root bridge would be a designated port. Then, ports that are neither root ports or designated ports (non-designated ports) go into blocking state. If a tie occurs, the same tiebreaker process occurs as in step 2.

At this point, we have a fully converged spanning-tree!

Normal OperationUnder normal operation the root sends hellos out of all it’s active ports. Each connected switch receives the hellos on their root ports, updates it, and forwards it out of it’s designated port (if it has one). Blocked ports receive the hellos, but never forward them.

Topology Changes
When a switch notices a topology change, it’s responsible for telling all other connected switches about the change. The most effective way to do this, is to tell the root switch so that it can tell all of the other switches. When a switch notices a topology change, it sends a TCN (topology change notification) out it’s root port. The switch will send the TCN every hello time until the upstream switch acknowledges it. The upstream switch acknowledges by sending a hello with a TCA (topology change acknowledgement). This process continues until the root becomes notified. The root will then set the TC flag on it’s hellos. When switches in the tree see the TC set in the hello from the root, they know that there has been a topology change and that they need to age out their CAM tables. Switches aging out their CAM tables is an important part of a topology change and reconvergence.

802.1D Port States

Blocking – The port is blocking all traffic with the exception of receiving STP BPDUs. The port will not forward any frames in this state.
Listening – Same as blocking but will now begin to send BPDUs.
Learning – The switch will begin to learn MAC information in this state.
Forwarding – Normal full up and up port state. Forwarding normal traffic.

TimingThere are a couple of main timers in the STP protocol. These are..
Forward Delay Timer – Default of 15 seconds
Hello – Default of 2 seconds
MaxAge – Default of 20 seconds

Spanning-Tree enhancements (Cisco Proprietary)
PortFast – Immediately puts a port into forwarding mode. Essentially disables the STP process. Should only be used for connecting to end hosts.
UplinkFast – Should be used on access layer switches connecting to distribution. Used to fail over the root port in the case of the primary root port failing. CAM entries are timed out by the access layer generating multicast frames with attached devices MACs as the source for the frames. This is different than the normal TCN process as described earlier. UplinkFast also causes the switch to increase the root priority to 49152 and set all of the ports costs to 3000.
BackboneFast – Used to detect indirect STP failures. This way the switch doesn’t have to wait MaxAge to reconverge. The feature needs to be configured on all switches in order for it to work. The switch queries it’s upstream switches when it sops receiving hellos with a RLQ (Root Link Query). If the upstream switch had a failure it can reply to the local switch so that it can converge to another port without waiting for the MaxAge to expire.

802.1w (Rapid Spanning-Tree)
Rapid spanning-tree takes 802.1d and makes it faster. In addition, they take some of the Cisco proprietary features and standardize them. Here are some of the notable changes that 802.1w makes.

-Switches only wait to miss 3 hellos on their root port prior to reconverging. This number in 802.1d was 10 (MaxAge, or 10 times hello).
-Fewer port states. 802.1w takes the number of port states from 5 (Im counting disabled) down to 3.

The new states are discarding, learning, and forwarding.
-Concept of a backup DP when a switch has multiple ports connected to the same segment.
-Standardization of the Cisco proprietary PortFast, UplinkFast, and BackboneFast.

802.1w Link TypesPoint to Point – Connects a switch to another switch in full duplex mode.
Shared – Connects a switch to a hub using half duplex
Edge – A user access port

802.1w Port roles
Root Port – The same as in 802.1d
Designated Port – The same as in 802.1d
Alternate Port – Same as the uplink fast feature, backup RP connection
Backup Port – Alternate DP port, can take over if the existing DP fails

802.1s (Multiple Spanning-Tree)
Multiple spanning-tree (MST) lets you map VLANs into a particular spanning tree. These VLANs are then considered to be part of the same MST region. MST uses the same features as RSTP for convergence, so if you are running MST, you are by default also running RSTP. Much like any other ‘group’ technology, there are several parameters that must be met before switches/vlans can become part of the same region.

-MST must be globally enabled
-The MST region name must be configured (and the same on each switch)
-Define the MST revision number (and make it the same on each switch)
-Map the same VLANs into each region (or instance)

MST can con-exist with other switches that don’t talk MST. In this case, the entire MST region appears to be a single switch to the other ‘external’ spanning-tree. The spanning-tree that connects the region to the ‘outside’ is considered to be the IST, or Internal Spanning Tree.

Spanning-tree Protection
There are several ‘protection’ mechanisms available that can be implemented in conjunction with spanning-tree to protect the spanning-tree from failure or loops.

BPDU Guard – Should be enabled on all ports that will never connect to anything but an end user port. The configuration will err-disable a port if a BPDU is received on that port. To recover from this condition the port must be shut/no shut.

Root Guard – Protects the switch from choosing the wrong RP. If a superior BPDU is heard on this port the port is placed into root-inconsistent state until the BPDUs are no longer heard.

UDLD – Unidirectional link detection is used to detect when one side (transmit or receive) is lost. States like this can cause loops and loss of connectivity. UDLD functions in two modes, aggressive and normal. Normal mode uses layer 2 messaging to determine if a switches transmission capabilities have failed. If this is detected, the switch with the failed transmit side goes into err-disable. In aggressive mode the switch tries to reconnect with the other side 8 times. If this fails, both sides go into err-disable.

Loop Guard – When a port configured with loop guard stops hearing BPDUs it goes into loop-inconsistent state rather than transitioning into forwarding.