Consolidation of Lightly Utilized Servers

Description

  • Until fairly recently, data center operators typically installed at least one physical server per application. When taking into account testing/development, staging, and disaster recovery 3 to 5 servers per application may have been typical.29 The traditional one workload, one box approach means that most servers run at a low "utilization rate" – the fraction of total computing resources engaged in useful work. A 2012 New York Times article cited two sources that estimated the average server utilization rate to be 6 to 12%.30 Another study stated that the one workload, one box approach leads to 90% of all x86 servers running at less than 10% utilization with a typical server running at less than 5% utilization.31
  • For most datacenters, an assessment of all servers and their utilization rates will uncover servers that are performing single, infrequent, or limited tasks. Consolidating these servers will eliminate systems and reduce energy, hardware, and support costs.
  • Server consolidation reduces total number of servers by putting more applications on fewer machines. You can consolidate servers by:
    • Combining applications onto a single server and a single operating system instance. Two or three lightly utilized file servers, for example, can be consolidated onto one machine.
    • Clustering servers.32 Server clustering reduces the number of backup or standby servers needed by a system, improves availability, and uses hardware more efficiently. Traditionally, data centers required one backup server for each primary working server. That no longer is necessary. N+1 server clustering technology allows for only one backup server per cluster of servers. For example, instead of needing six passive servers to back up six active servers, with N+1 clustering you need only one passive server. Applications in the cluster are continuously monitored, and if an application fails on one server, it's activated instantly on another server within the cluster. Advanced clustering software can even include the capability to "direct traffic," or move applications among servers and storage devices to fine-tune performance and maximize workload. This is yet another way to reduce hardware, space, and power consumption.
    • Downsizing the application portfolio. Many large organizations run a number of very similar applications, some of which are underutilized. Fewer servers are needed when redundant applications are eliminated.
    • Virtualize servers. Virtualization allows for consolidation of applications from different operating systems and/or hardware platforms. By creating several virtual servers on one device, you can dramatically reduce the required number of physical servers. In addition to saving space and money, virtualization provides a previously unavailable level of flexibility. For more information on virtualization, see the Server Virtualization section of this document and the Server Virtualization section of this website.

Savings and Costs

  • Generally speaking, consolidation enables you to retire servers and/or defer purchases of new servers, thus decreasing electricity consumption and waste heat. One watt-hour of energy savings at the server level results in roughly 1.9 watt-hour of facility-level energy savings from reducing energy waste in the power infrastructure (power distribution unit, UPS, building transformers) and reducing energy needed to cool the waste heat produced by the server.33
  • According to the Uptime Institute, decommissioning a single 1U rack server can annually save $500 in energy, $500 in operating system licenses, and $1,500 in hardware maintenance costs.34
  • Consolidation makes existing servers far more productive. In addition to cost savings from lower power consumption, less cooling and less maintenance, consolidation helps organizations standardize their systems, allowing for shared infrastructures with more flexibility.
  • Standardization through consolidation means fewer spare parts are needed to keep the data center running. If you are only using two vendors instead of 10, it is much easier to get the replacement cables, power supplies, fans, and other parts you will occasionally need.
  • Labor costs for consolidation include:
    • Conducting a thorough inventory and consulting all potentially interested parties,
    • Migrating applications,
    • Removing old servers and deploying new servers (if necessary), and
    • End-of-life disposal costs for systems that are not repurposed.

Considerations35

  • Take inventory. It is easy to lose track of servers as time goes by, as mergers and acquisitions take place, as people procure servers without going through central IT, or as servers are retired or repurposed. The first step toward consolidation is identifying all servers in the organization. Take an inventory of computing resources and their associated application workloads.
  • Examine current usage. What applications are your servers running? When does utilization peak on each server? To get the most out of your consolidation projects, find patterns of low server utilization and unneeded equipment and software.
  • Watch out for "hot spots". When you consolidate servers into a smaller footprint (with blade servers, for example), you are probably creating "hot spots" in your data center. Work with HVAC experts to ensure an adequate and efficient cooling configuration.
  • Reduce downtime. There is always some risk of downtime when migrating applications and files from an existing server to a new system. Proper preparation can substantially mitigate this risk.

29 The Economics of Virtualization: Moving Toward an Application-Based Cost Model, IDC, 2009. www.vmware.com/files/pdf/Virtualization-application-based-cost-model-WP-EN.pdf (PDF, 213KB)
30 Power, Pollution and the Internet, The New York Times, by James Glanz, 9/22/2012. www.nytimes.com/2012/09/23/technology/data-centers-waste-vast-amounts-of-energy-belying-industry-image.html?pagewanted=all
31 Using Virtualization to Improve Data Center Efficiency, Green Grid White Paper, Editor: Richard Talaber, VMWare, p. 10. www.thegreengrid.org/Global/Content/white-papers/Using-Virtualization-to-Improve-Data-Center-Efficiency
32 A How to Guide for Greening IT in Government, produced by Government Technology, 2009. www.carahsoft.com/greenit/symantec/files/GT09_SymantecGreen.pdf (PDF, 549KB)
33 New Strategies for Cutting Data Center Energy Cost and Boosting Capacity, Emerson Network Power presentation, 2012, p.8. www.emersonnetworkpower.com/documents/en-us/latest-thinking/edc/documents/white%20paper/is03947_2012_energylogic_fin.pdf (PDF, 1.4MB)
34 Important to Recognize the Dramatic Improvement in Data Center Efficiency, Uptime Institute, 9/25/12. blog.uptimeinstitute.com/2012/09/important-to-recognize-the-dramatic-improvement-in-data-center-efficiency/
35 Section was mainly developed examining this document: Using Virtualization to Improve Data Center Efficiency, Green Grid, 2009. www.thegreengrid.org/Global/Content/white-papers/Using-Virtualization-to-Improve-Data-Center-Efficiency