Pages

Friday 4 October 2013

Data Center Management, Virtualization, Tools, Design, Cooling and Power Issues

Data Center Management, Virtualization, Tools, Design, Cooling and Power Issues

In this article on data center management, I will focus on the basic need of data center management, virtualization of data centers and what are the tools available for data center management? What should be the ideal design of data center in order to provide high efficiency and combat power/electricity and cooling issues? How can we optimize and automate data center management solution by using best breed of tools? What are the various data center cooling strategies? How to reduce power consumption of data centers? What should be the optimized design of data centers?

What is Data Center Management?

Data center management is monitoring and managing the performance of servers in a data center. Data center management aims to optimize the performance of data center servers by tracking key metrics, such as CPU load and memory usage, for each server. Data center management may require administrators to have visibility into both virtual and physical servers in the data center.

Data center management includes management of Servers, Operating Systems, Databases, Storage Space, Middleware Management, Productions Operations and Mainframe Services etc. 

In other words, we can say Data Center Infrastructure Management integrates facets of system management with building management and energy management, with a focus on IT assets and the physical infrastructure needed to support them.

Need Data Center Management Services

In this era, businesses are increasingly dependent on IT for mission critical applications to achieve their business goals. Organizations want to ensure that IT is managed effectively and efficiently. IT is made up of different technology elements and it is extremely crucial to identify a partner who can manage a complex IT environment seamlessly. Organizations are also looking to lower operation costs, increase use of automation, use best of breed tools and processes, provide high application availability, and manage service levels.

As business dependency on IT grows, organizations need to ensure that data centers have the flexibility to address ever-changing business demand. Industry trends show that most customers have issues related to data growth, system performance and scalability, effective utilization of resources, energy consumption, tracking and handling of assets, migration to new environment and network congestion to name a few. 

Data Center Management Tools

Data Center Management Tools enable you to quickly detect, diagnose, and resolve network performance problems and outages—before you start getting calls asking if the network is down. There are many data center management tools that help you to do all kind of data center management. That means you can spend your time actually managing your network, not supporting your network management softwares. There are many data center management tools like Physical Infrastructure Manager (PIM) software, EMC, IO.AR, ManageEngine OpManager, Quest Big Brother, Schneider Electric StruxureWare Operations, IT Manager from Smarter Apps Inc which can help you a lot in the management of your data center.

Data Center Virtualization

Data center virtualization encompasses a range of virtualization activities aimed at creating a virtualized computing environment, such as for use in cloud computing, within a data center. Data center virtualization typically focuses on server virtualization to enable, for example, Software as a Service, Platform as a Service, or Infrastructure as a Service solutions.

There are many Data Center Virtualization Management Tools which deliver integrated VMware and Microsoft Hyper-V capacity planning, performance monitoring, VM sprawl control, configuration management, and chargeback automation etc. to help you out in data center virtualization management.

Data Center Management Design

The data center management should be designed to provide security, physical environment, and networking capability which support even the most mission-critical and complex applications. The data center management design should be able to address the organization needs in terms of Hosting, Consolidation, Virtualization, Business continuity planning, Cloud computing and Mainframe services.

A true Data Center Infrastructure Management solution can scale to manage hundreds of thousands – if not millions – of assets sitting in the world’s largest global IT infrastructure environments. 

Data Center Power / Electricity Management Problems

Energy costs are the fastest-rising cost element in the data center. Power consumption is one of major concerns of these facilities, clouds and large IT Enterprises. Often it is not clear if energy savings is a responsibility of Facility Manager or IT Manager. Servers consume most of the energy which is owned by the IT division. Facility teams sometimes deploy solutions to measure and manage Power at Rack and PDU levels, but have little visibility at the server level. There are also challenges in managing power at the appropriate times.

A good data center power management tool can help address various electricity related issues with data centers:

1. Power and thermal monitoring allows you to get real-time, accurate power and thermal consumption data, manage data center hot spots, plan and forecast power usage and replace costly intelligent power strips.

2. Increasing rack density to maximize server count per rack in a fixed rack power envelope to increase data center utilization.

3. Power optimizations on specific workload types allows you to provide the optimized power profile per server/rack/floor or workload/application and cut electricity costs.

4. Business continuity allows to continue or prolong operation during power outage

Data Center Cooling

Driven by rising power densities and heat levels, data center cooling strategies have changed dramatically over time. Until relatively recently, most cooling schemes relied on so-called ‘chaos’ air distribution methodologies, in which perimeter computer room air conditioning (CRAC) units pumped out massive volumes of chilled air that both cooled IT equipment and helped push hot server exhaust air towards the facility’s return air ducts.  Chaos air distribution, however, commonly results in a wide range of significant inefficiencies, including:

Re-circulation – Typically caused by poor rack hygiene and insufficient cool air available at the face of the rack, hot exhaust air can find its way back into server air intakes, heating IT equipment to dangerous temperatures.

Air stratification – In an attempt to provide cooler air at the top of the face of the rack, the natural tendency of air to mass in different temperature-based layers can force set points on precision cooling equipment to be lower than recommended. Often, in an attempt to re-mediate air stratification, technicians increase the fan speed of CRAC units to deliver more cool air to the room, which can result in bypass air.

Bypass air – The velocity of the cool air stream exceeds the ability of the server fans to draw in the cool air; as a result, the cool air shoots beyond the face of the IT rack.  Cool supply air can join the return air stream before passing through servers, weakening cooling efficiency.

Eager to combat the inefficiencies above and keep pace with steadily climbing data center temperatures, businesses often adopt hot aisle/cold aisle rack orientation arrangements, in which only hot air exhausts and cool air intakes face each other in a given row of server racks.

Such configurations generate convection currents that produce improved airflow. Although superior to chaos air distribution, hot aisle/cold aisle strategies have proven only marginally more capable of cooling today’s increasingly dense data centers, largely because both approaches ultimately share a common, fatal flaw: they allow air to move freely throughout the data center.

This flaw eventually led to the introduction of containment cooling strategies. Designed to organize and control air streams, containment solutions enclose server racks in sealed structures that capture hot exhaust air, vent it to the CRAC units and deliver chilled air directly to the server equipment’s air intakes. This results in a series of important benefits:

Improved cooling efficiency – By preventing the supply and return air streams from intermingling, well-designed containment solutions eliminate wasteful re-circulation, air stratification and bypass airflow.

Increased reliability – Eliminating re-circulation spares servers from exposure to potentially dangerous warm air that can result in thermal stress which decreases the life of IT equipment

Lower energy spending – To counteract the effects of re-circulated exhaust air, legacy cooling schemes typically chill return air to 55ºF/12.78ºC. Containment-based cooling systems completely isolate return air, however, so they can safely deliver supply air at 65ºF/18.34ºC or higher. As a result, containment cooling strategies typically reduce CRAC unit power consumption by an average of 16%.

Greater floor plan flexibility – To generate the cooling convection currents that make hot aisle/cold aisle strategies work, companies must place their server racks in rigidly aligned, uniformly arranged, rows. Containment strategies don’t rely on convection, however, so they empower data center designers to position enclosures in any configuration that best fits their needs.

No comments:

Post a Comment

About the Author

I have more than 10 years of experience in IT industry. Linkedin Profile

I am currently messing up with neural networks in deep learning. I am learning Python, TensorFlow and Keras.

Author: I am an author of a book on deep learning.

Quiz: I run an online quiz on machine learning and deep learning.