Data center management

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Data center management[1] is the collection of tasks performed by those responsible for managing ongoing operation of a data center[2] This includes planning for the future.

Historically, data center management was seen as something performed by employees, with the help of tools collectively called Data Center Infrastructure Management (DCIM) tools.[3] Now an outsourcing option exists: Data-center Management As A Service - DMaaS.[4]

Coopetition[edit]

Data center management is a growing major topic for a growing list of large companies who both compete and cooperate:

Hardware/software vendors who are willing to live with coopetition are working on projects such as "The Distributed Management Task Force" (DMTF)[8] with a goal of learning to "more effectively manage mixed Linux, Windows and cloud environments."

With the DMTF a decade old, the list of companies is growing, and also includes companies much smaller than IBM, Microsoft, et al.[9]

Focus[edit]

Among the topics currently being explored are:[10]

  • Scalability
  • Securing Data Center Networks
  • Disaster Recovery
  • Government restrictions[11]
  • Estimated cost of downtime regarding:
    • Personnel & productivity[12]
    • Customer dissatisfaction and business loss[13]

Newer developments[edit]

Remote Data Center Management[14] allows offsite experts to watch for situations needing their timely intervention at a lower cost than having such staff be onsite 24/7/365.

Furthermore, there is more recognition that while some requirements for on-site hardware have been reduced,[15] spending in other hardware areas such as UPS may have to increase.[16]

Data center infrastructure management[edit]

Data center infrastructure management (DCIM) is the integration[17] of information technology (IT) and facility management disciplines[18] to centralize monitoring, management and intelligent capacity planning of a data center's critical systems. Achieved through the implementation of specialized software, hardware and sensors, DCIM enables common, real-time monitoring and management platform for all interdependent systems across IT and facility infrastructures.

Depending on the type of implementation, DCIM products can help data center managers identify and eliminate sources of risk to increase availability of critical IT systems. DCIM products also can be used to identify interdependencies between facility and IT infrastructures to alert the facility manager to gaps in system redundancy, and provide dynamic, holistic benchmarks on power consumption and efficiency to measure the effectiveness of "green IT" initiatives.

It's important to measure and understand data center efficiency metrics. A lot of the discussion in this area has focused on energy issues, but other metrics beyond the PUE can give a more detailed picture of the data center operations. Server, storage, and staff utilization metrics can contribute to a more complete view of an enterprise data center. In many cases, disc capacity goes unused and in many instances the organizations run their servers at 20% utilization or less.[19] More effective automation tools can also improve the number of servers or virtual machines that a single admin can handle.

DCIM providers are increasingly linking with computational fluid dynamics providers to predict complex airflow patterns in the data center. The CFD component is necessary to quantify the impact of planned future changes on cooling resilience, capacity and efficiency.[20]

Preventive maintenance[edit]

Preventive maintenance (or preventative maintenance (PM) ) is ongoing scheduled[21] inspection[22] intended to detect and correct incipient failures either before they occur or before they develop into major problemssuch as downtime.

Managing the capacity of a data center[edit]

Capacity of a datacenter - Life Cycle

With the increasing use of "the cloud" and what has been called "the Era of Infinite Capacity",[23] there is still a need for professional Data Center Capacity Planners.[24]

Several parameters may limit the capacity of a data center. For long term usage, the main limitations will be available area, then available power. In the first stage of its life cycle, a data center will see its occupied space growing more rapidly than consumed energy. With constant densification of new IT technologies, the need in energy is going to become dominant, equaling then overcoming the need in area (second then third phase of cycle).

It is important to define a data center strategy before being cornered. The decision, conception and building cycle lasts several years, hence it is imperative to initiate this strategic consideration when the data center reaches about 50% of its power capacity.

Maximum occupation of a data center needs to be stabilized around 85%, be it in power or occupied area. Resources thus managed will allow a rotation zone for managing hardware replacement and will allow temporary cohabitation of old and new generations. In the case where this limit would be overcrossed durably, it would not be possible to proceed to material replacements, which would invariably lead to smothering the information system. The data center is a resource in its own right[25] with its own constraints of time and management (life span of 25 years), it therefore needs to be taken into consideration in the framework of the SI midterm planning (between 3 and 5 years).

Top data centers and service providers[edit]

According to Cloudscene’s Leaderboard for Q1 2018, data center operators are ranked “based on both data center density (total operated data centers)", as well as "the number of listed service providers in the facility". Cloud service providers are ranked based on "connectivity (the total number of PoPs) for the region.” Chosen from a pool of more than 6,000 providers, the rankings are as follows:[26]

Q1, 2018 Top Data Center Operators Worldwide
Rank North America EMEA Oceania Asia
1 Equinix Equinix Equinix Equinix
2 Digital Realty Interxion NEXTDC Global Switch
3 CoreSite Telehouse Vocus Communications NTT Communications
4 Zayo Digital Realty Global Switch GPX Global Systems
5 Level 3 Communications Global Switch YourDC ST Telemedia Global Data Centres
6 Cologix Level 3 Communications Macquarie Telecom Netmagic Solutions
7 Cyxtera itconic iseek AIMS
8 TierPoint Colt Technology Services Interactive Digital Realty
9 Netrality Properties Nikhef Datacom Telstra
10 QTS Realty Trust Orange Business Services Data Centre Limited OneAsia Network
Q1, 2018 Top Service Providers Worldwide
Rank North America EMEA Oceania Asia
1 Zayo Colt Technology Services Telstra Colt Technology Services
2 Level 3 Communications EuNetworks Vocus Communications PCCW Solutions
3 Verizon Cogent Communications PIPE Networks Tata Communications
4 Crown Castle Zayo Optus PCCW Global
5 AT&T Level 3 Communications NextGen Group Telstra
6 Cogent Communications BT AAPT NTT Communications
7 CenturyLink Interoute Megaport Superloop
8 XO Communications Verizon Superloop Zenlayer
9 Comcast Orange Business Services Zencross Connect China Telecom
10 TW Telecom NL-IX Uecomm Singtel

See also[edit]

References[edit]

  1. ^ "What Startups in Amazon's Ecosystem Should Learn From VMware". The New York Times. their existing data center management ...
  2. ^ "Data Center Management".
  3. ^ Ann Bednarz (May 24, 2018). "Data center management - What does DMaaS deliver that DCIM doesn't". Network World.
  4. ^ "The future of Data Center Management: From DCIM to DMaaS". EnterpriseTech.com. June 15, 2018.
  5. ^ "Dell Makes Moves to Survive in Cloud-Centric World". NYTimes.com. August 21, 2012.
  6. ^ a b "Google and I.B.M. Join in 'Cloud Computing' Research". The New York Times. October 8, 2007.
  7. ^ a b c "Yahoo, Intel and HP Form Cloud Computing Labs". The New York Times. July 29, 2008.
  8. ^ "Meeting virtualization management challenges". The New York Times. October 27, 2008.
  9. ^ The Times article mentions "a crop of next-tier vendors, start-ups and open source players."
  10. ^ "Data Center Management". The Data Center Journal. Retrieved October 28, 2018.
  11. ^ Matt Hancock (October 26, 2018). "Power struggle". Computer Weekly. a row is brewing over an EU plan to curb datacentre energy use
  12. ^ David Gewirtz (May 30, 2017). "The astonishing hidden and personal costs of IT downtime (and how predictive analytics might help)".
  13. ^ "Flights Cancelled for more than 75,000 passengers".
  14. ^ "Remote Data Center Management".
  15. ^ Quentin Hardy (November 17, 2012). "Hard Times Could Create a Tech Boom".
  16. ^ "In 2014, Proactive UPS Maintenance is Essential for all Data Center Managers" (PDF). UPS-redundant configurations, providing backups for backups that have their own backups.
  17. ^ "Tracking All the Data: Data Center Infrastructure Management ..." ECmag. (DCIM) software enables ... integration ...
  18. ^ "Data Center Infrastructure Management - Data Center Handbook".
  19. ^ "Measuring Data Center Efficiency: Easier Said Than Done". Dell.com. Archived from the original on 2010-10-27. Retrieved 2012-06-25.
  20. ^ "Computational-Fluid-Dynamic (CFD) Analysis | Gartner IT Glossary". gartner.com. Retrieved 2014-08-27.
  21. ^ "What is Preventive Maintenance?". MicroMain.com.
  22. ^ "What is preventive maintenance?". BusinessDictionary.com.
  23. ^ Samir Mehra (September 11, 2018). "Capacity Planning in the Era of Infinite Capacity".
  24. ^ "Data Center Capacity Planner Jobs, Employment". indeed.com (job search). 293 Data Center Capacity Planner jobs available on Indeed.com
  25. ^ J Xu; M Zhao; J Fortes; R Carpenter (2007). "On the use of fuzzy modeling in virtualized data center management". IEEE.org.
  26. ^ "Cloudscene Rankings: Top Data Centers & Service Providers Worldwide". Cloudscene.