Metagyre was engaged to develop the return on investment analysis for consolidating Client’s seven data centers and then move their main data center from one Seattle, WA. location which they had out grown to a new Seattle location. The project consisted of selecting and building out a new 6,000 sf data center followed by moving their equipment and applications into the new facilities. Their computational environment included 1,000+ virtual and physical servers, 1.5 petabytes of EMC storage, mainframe, tape backup and Cisco network. Client’s main data center supports their entire on-line e-commerce mission critical applications and approximately 200 different systems. Client’s business required that the equipment, applications and data move without disrupting their 24×7 ability to accept and fulfill revenue generation.

Client uses a number of technologies to deliver world class on-line services to their customers. These included: EMC Storage, Cisco, Checkpoint, F5, IBM Mainframe, IBM Storage, IBM Blade Centers, IBM xSeries, HP servers, HP Storage, Sun Solaris, VMware, Linux, Microsoft Windows 200X, MS SQL, Oracle, and Microsoft Exchange.

Design and Build Out
Metagyre partnered with Client’s senior management to structure the project and budget required to complete the data center design, procurement and build out. The major components we developed in this stage included:

• Technical site reviews and contract redline activities side by side with Client’s senior management.
• Design and build out the new data center facility including structured cabling, electrical and floor layouts.
• Design,procure and integrate network connectivity for the new data center and build a dark fiber backbone back to their existing main data center.
• Source and develop criteria for selecting sub-contractors as well as working with sub-contractors to design and implement power, fire suppression, cooling, lighting and structured cabling.
• Extend the network across the two data center sites.
• Designate rack layouts, server placement, port assignments and in-rack cable standards.
• Lead workshops with client staff and EMC to establish SAN and storage requirements, procurement contracts and implementation.
• Secure stakeholder agreement of plans, designs and procurements.
• Schedule and manage all professional services and sub-contracts for activities requiring third party activities or equipment purchases.
• Test core data center infrastructure, redundant power and networking.
• Stage, test and verify seed servers and storage.

System Migration
Metagyre worked with Client’s system engineers to develop the detailed plans to formalize application and data move tasks. These detailed plans called short interval schedules included test, go/no go and roll back procedures for each component of the application. We engaged the stakeholders to gain plan approvals and schedule around business needs. Metagyre engineered and implemented several unique migration strategies based on complex system and data business requirements.

Client’s virtual machines were migrated using VMware’s VMotion over the dark fiber backbone and reintroduced into production running on an ESX cluster in the new data center. In the case of redundant physical clusters, the cluster was split, one of the servers brought up in the new data center to re-establish the cluster and then the cluster was failed over to the server in the new data center.

By advancing the purchases of other project’s planned equipment refreshes, the seed equipment was acquired with minimal additional cost. The seed equipment was staged as necessary in the new data center prior to system migration. Following the migration of a system, the equipment in the old data center was moved to the new data center to serve as the seed equipment for the next system.

Obstacles
Client’s systems are tied closely to high profile events such as the Grammys, World Cup, and breaking news. Metagyre’s responsibility was to develop a flexible migration schedule that could respond quickly to Client’s business needs. When changes in world events dictated a scheduled migration had to be placed on hold, we were able to substitute and fill the schedule with another system migration container. Metagyre’s migration process allowed Client to retain the flexibility needed to meet changing business requirements while meeting the scheduled end date.

Project Summary
The main Client data center was successfully relocated within the allotted time frame and budget while maintaining the business continuity needs of their enterprise. Following the move, older equipment whose services were migrated to new seed gear was repurposed in support of their development and test environments or to expand disaster recovery capacity.

With this data center move and system migration, Client was able to significantly lower their monthly costs by consolidating the number of sites managed and increase the capabilities they provided to their internal business customers through its improved design features.

Need help with your data center infrastructure? Contact theData Center Solutions experts at Metagyre, Inc. Data center management to data center consolidation putting business value in the data center.

Data Center Strategy, Design, Build Out and Move

One of the most quoted portions of the standard is the “Tiered Reliability”, which was intended as a means for determining specific data center needs required to lessen the time a data center was taken off-line.  The tier breakdown assists designers with a method to quantify certain aspects and to objectively compare one center to another.

Tier I – Basic Components

• single path for power and cooling with no redundant components (N)
• susceptible to disruptions from both planned maintenance activities and unplanned events
• may or may not have back up generator, UPS (uninterrupted power supply) or raised floor
• 99.671% availability – 28.8 hours (statistically) of annual downtime

Tier II – Redundant Maintainable

• single path for power and cooling with redundant components (N+1)
• less susceptible to planned and unplanned disruptions.  Planned infrastructure maintenance may require a processing shutdown
• includes generator, UPS, and raised floors
• 99.749% availability – 22.0 hours (statistically) of annual downtime

Tier III – Concurrently Tolerant

• multiple paths for power and cooling with only one active at any time (active/passive – N+1)
• planned infrastructure maintenance can be performed without disruption.  Unplanned events may cause disruptions
• includes raised floor, generator, UPS with each power and cooling path capable of carrying the full data center load
• 99.982% availability – 1.6 hours (statistically) of annual downtime

Tier IV – Fault Tolerant

• multiple active power and cooling distribution paths including redundant components (2(N+1) S+S) for example each path has UPS in an N+1 configuration
• can sustain planned maintenance activities and at least  one unplanned event without a critical impact on load
• includes raised floors, multiple generators, multiple UPS and other multiple distribution components
• 99.995% availability – 0.4 hours (statistically) of annual downtime

The standards went a long way to elevate the need for specific elements in the data center and the best practices for their usage.  Unfortunately, once the marketing spin took off, numerous collocation vendors began touting their facilities as a Tier III or Tier IV without regard for the full spectrum of component requirements or the processes supporting those components.  In addition the design standards cover other elements including:

• cable and fiber designs
• network distribution
• rack and cabinets layout
• space utilization and pathways
• air flow design

Many commercial collocation facilities claiming higher fault tolerance, achieve this mark by maintaining a lower power density requirement on their tenants driving up customer costs and reducing cabinet layout efficiencies. Even when the power plant supports high electrical draws, floor load ratings may limit the cabinet’s capacity.  Other times, best practices must be completely rethought, for example the best hot and cold aisle layout will fail to achieve design goals if the collocation facility locates the client in a cage space which does not support air flow management. Of course occasionally collocation customers themselves lower the reliability by failing to incorporate proper redundancy practices within their private suite or cage space.

Each business has unique up-time, cost, networking and processing density goals in mind when they establish a data center.  In order to reach those goals, a balance between requirements and design standards must be struck.  While the tiered data center may be an over used marketing myth, the ANSI/TIA-942-2005 provides a solid base template.  This template, along with skilled engineering and management practices can go a long way to facilitate a data center build out that delivers on technical design goals at an agreed upon business price point.

Need help with your data center infrastructure? Contact theData Center Solutions experts at Metagyre, Inc. Data center management to data center consolidation putting business value in the data center.

Collocation Facilities And The Myth Of The Tiered Data Center

At a high level there are three areas of guidance for a data center migration. Those areas are Data Center Move, Data Center Design and ongoing Data Center Management. Although their are some universals ideals, each company has to develop their own guiding principles. Individualized guiding principles are required since they reflect corporate culture, technology strategy and business goals. For a good start on developing your own data center migration guiding principles consider the following:

Data Center Move Principles:

1. Business Drivers:
   1. Contract renewals are driving the completion date Production cut over must be on or before the current contract expiration date
   2. Down time is expensive and taken as a last resort
   3. The data is the asset and needs to be protected
   4. One-time use equipment or service should be minimized
2. A team approach will be used in the move so that all disciplines are represented on the team.
   1. Storage: design, document, perform and sign-off on all storage component activities. Include vendor management for physical move of the storage component
   2. Networking: design, document perform and sign-off on all network component activities
   3. Systems: design, document, perform and sign-off on all systems component activities
   4. Back office: design, document, perform and sign-off on all back office component activities.
   5. Application Development: provide information, documentation, guidance and sign-off on all application component activities.
   6. Software QA: Test and sign-off on all functionality
   7. NOC (network operations center): Gatekeeper for documentation, escalation and monitoring of move activities
   8. Business Owner: Sign-off and approval of all move activities
3. Extend the network so both spaces look like one
4. Extend the SAN so storage in both spaces looks like one. Vendors will be enlisted in moving and ensuring proper turn up of their storage systems. New storage equipment will be used as a temporary landing zone for data in order to move it off of a subsystem prior to its move and then back onto it after its move
5. Pools of resources will be split and moved in stages. One resource should not need to know the physical location of another resource
6. Designs will be published, reviewed, challenged and revised prior to the move. During the move designs and scripts will be followed

Data Center Design Principles:

1. Plan Ahead:
   1. Data center plans and designs are to support the next three (3) years of anticipated growth.  This growth is estimated at 20% year over year
   2. Environmental monitoring is required in unmanned facilities
   3. Equipment will be maintained on a five (5) year life cycle
2. Keep it Simple:
   1. Aggregate cabling where possible to segregate patching
   2. Standardize on the rack, ladder system, PDUs, Patch Panels and cabinet layout.
   3. Priority deployment of standard computing:
      1. Virtual server on x86 architecture
      2. Blade Center
      3. Standardized x86 based server platform
      4. Other architecture
3. Remain Flexible
   1. Equipment can be placed in the next available cabinet.  There is no intelligence built into the floor plan
   2. New standards should be carried forward and retrofitted only where it makes business sense
4. Think Modular:
   1. Two cabinets make a non-blade center module to be deployed when additional resources are required
   2. One cabinet makes a blade center module to be deployed when additional resources are required
   3. Cabinet modules are outfitted the same for network and cabling
5. Keep things covered, bundled and out of sight:
   1. Cabinets have doors and sidewalls
   2. Copper cables are patched within the cabinets using the provided cable management
   3. Cables follow standard paths and do not cut across cabinets
   4. Fiber and copper cables are kept in separate trays
   5. Blanking panels will be used

Data Center Management Principles:

1. Label Everything:
   1. Racks, PDUs, and environmental monitoring devices are labeled with name as it appears in the book of record
   2. Servers are labeled with name as it appears in the book of record
   3. Network equipment and patch panels are labeled with name as it appears in the book of record
   4. Storage is labeled with name as it appears in the book of record
   5. Fiber, copper and power cables have a matching serialized label at both terminating ends. (should track in the book of record what cable attached to equipment)
2. Configuration Management is paramount:  the book of record contains information on all physical and virtual servers, network equipment, storage systems, racks, PDUs and environmental devices
3. Change Control:
   1. The change approval board ensures the inventory is updated
   2. All work requires a change control
4. Access is Locked Down:
   1. Only 3-5 people have physical access to the data center
   2. The Facilities group manages access to the data center
   3. Change control approval is required to perform work in the data center
   4. The NOC is aware of data center access through the daily production schedule and notices
5. Audit the work: Audits are conducted on
   1. The book of record against the physical data center
   2. Data center sign-in against daily production schedule
   3. The NOC is the Gate Keeper for data center management process adherence

These data center migration principles valid when moving into or out of a collocation facility or an in-house data center.

Need help with your data center infrastructure? Contact theData Center Solutions experts at Metagyre, Inc. Data center management to data center consolidation putting business value in the data center.

Data Center Migration Principles

Is a Boeing 747 three times “faster” than a Boeing 737?  They both cruise at around 500 miles per hour. The difference is that the 747 carries 500 passengers where as the 737 only carries 150. The Boeing 747 is three times bigger (more bandwidth) than the Boeing 737, not faster.  And like an airplane, as long as you have fewer files (passengers) than the network can carry at any one time, increasing the bandwidth will not reduce presentation times.

From a physical perspective, in order to increase the speed at which web pages or other data are presented to customers on the Internet you need to reduce the distance.  There are two strategies to reduce distance.  Regional data center (RDC) or content delivery network  (CDN) strategies both reduce the distance data travels to customers.

In this discussion we will look at the effects of an regional data center design architecture for reducing the time it takes data to reach customers. With an RDC strategy, you have multiple data centers (or collocation facilities) strategically placed around the globe to service those areas closest to the RDC.  For this analysis we simulated an RDC in Seattle, London and Hong Kong.

In order to expose the base Internet latency a test was run sending one packet of data over the Internet and measuring its round trip time.  This is referred to as a ping test.  As you can see the following chart shows latency increasing over distance from Seattle.

By moving the data and servers closer to the customer and establishing a regional presence, delivery times experienced by the total customer base becomes more consistent regardless of their location.  In order to simulate an regional data center presence the ping test was repeated with Asia Pacific locations measuring latency times to Hong Kong and European locations measuring latency to London.  The chart below shows the results of that regional data center simulated ping test.  The distances and the latency are from the initiating location to the simulated regional data center.  There was a 65% improvement in the average response time utilizing the regional data center model.

Conclusion:
While big network pipes will push more data out the data center door, it will not always deliver it to Internet customers faster.  In order to reduce latency, move your data and presentation services closer to your customers.  Depending on application solutions or systems, significant reduction in latency can be achieved through the strategic use of regional data centers.

The tests run for this analysis accurately assess latency with for simple data requests.  This investigation does not represent a specific customer experience and results will vary depending on variables such as time of day, network provider and other public network activity.

Need help with your data center infrastructure? Contact theData Center Solutions experts at Metagyre, Inc. Data center management to data center consolidation putting business value in the data center.

Data Center Design: When Bandwidth Will Not Do