Cloud computing models are based on gaining maximum yields for all resources that go into the data center. This is one of the keys to delivering services at a lower cost. And power is one of the biggest bills in a cloud environment. Cloud data centers now consume an estimated 1–2 percent of the world’s energy.[1] Numbers like that tell you the cloud’s success hinges on aggressive power management.

So let’s talk about some of the steps you can take to operate a more efficient cloud:

• Better instrumentation. The basis for intelligent power management in your data center is better instrumentation at the server level. This includes instrumentation for things like CPU temperature, idle and average power, and power and memory states. Your management capabilities begin with access to this sort of data.
  

• Better power management at the server and rack level. Technologies like dynamic power capping and dynamic workload power distribution can help you reduce power consumption and place more servers into your racks. One Intel customer, Baidu.com, increased rack-level capacity by up to 20 percent within the same power envelope when it applied aggregated power management policies. For details, see this white paper.
  

• Better power policies across your data center. Put in place server- and rack-level power policies that work the rest of the policies in your data center. For example, you might allocate more power capacity to a certain set of servers that runs mission-critical workloads, and cap the power allocated to less important workloads. This can help you reduce power consumption while still meeting your service-level agreements.
  

• Better power management at the facilities level. There are lots of things you can do to drive better efficiency across your data center. One of those is better thermal management through the use of hot and cold server aisles. Another is thermal mapping, so you can identify hot and cold spots in your data center and make changes to increase cooling efficiency.
  

Ultimately, the key is to look at power the way you look at all other resources that go into your data center: seek maximum output for all input.

[1] Source: Jonathan Koomey, Lawrence Berkeley National Laboratory scientist, quoted in the New York Times Magazine. “Data Center Overload,” June 8, 2009.

Historically, IT data centers operated like warehouses that focused on housing the equipment brought by application developers. Today, these passive warehouses are being converted into dynamic factories that focus on achieving the maximum “application yield” from all of the resources that go into the factory. This yield is much like that of an auto factory that must produce a variety of models with the same shared set of resources.

There are two fundamental ways to increase the yield from your data center: efficiency by design and efficiency by operations.

Efficiency by design is all about designing for optimal output. One example: As you update your infrastructure over time, your new servers, storage systems, and networking equipment should deliver measurable increases in throughput and power efficiency. With each generation of technology, you should get more yield out of your equipment investments.

Efficiency by operations is all about managing the “resource inventory” of the data center through automation. The key here is to use automated solutions to carry out time-consuming tasks that were previously handled manually. Automation not only helps your administrators increase their productivity, it helps your data center managers ensure that the inventory of compute, storage, and network resources is used to its maximum capacity.

For example, you can use automated tools to:

• Move demanding workloads to systems with excess capacity
  
• Allocate additional storage to applications that are running out of disk space and reduce storage allocated to those applications that are not using it
  
• Cap the power that flows to certain workloads without impacting performance
  
• Update security tools and firewall settings on user systems
  

This is just a small sample or the actions you can take to increase the yield against your data center assets—including people, equipment, software, and power. There are many other things you can do. Just keep your eyes on the factory manager’s prize: maximum output for all resources that go into your facility.

"Automated" is one of the three cornerstones of Cloud 2015 vision. At the highest level, cloud automation means provisioning your workloads automatically with guaranteed service level agreements while optimizing power and compute resources. Automated cloud computing services can be specified, located, and securely provisioned with very little or no human interaction.

Two critical constraints of data centers today are power and network. Here's a brief overview of how to optimize your cloud infrastructure on power and network. You can find out more by reading the white papers. Also, feel free to contact me by posting a comment.

Achieve power aware provisioning with Intel® Node Manager and partner tools

The white paper "Policy Based Power Management with Dell and VMware" describes a policy power management reference architecture based on Intel, VMware*, and Dell*. The goal of policy power management is to get the most out of each watt of power and space in the data center to reduce the total cost of ownership (TCO). This paper shows how Intel® Intelligent Power Node Manager technology, Dell servers, and VMware products provided power savings and rack space optimization through dynamic migration of workloads—something hard to do manually.

We describe these use cases in detail along with the experimental results and data for:

• Real-time server power monitoring
  
• Optimization of rack density
  
• Power-optimized workloads
  
• Disaster recovery/business continuity
  
• Data center energy reduction
  

Simplify the cloud and reduce costs with 10 GbE unified networking

Cloud brings efficiency in compute by consolidating multiple services in a multi-tenant environment. An often-ignored implication of this usage is the increased demand on network bandwidth. Up to 6 to 12 network connections are common in a cloud or virtualized environment today, which impacts data center capex and opex due to the complexity of the arrangement. The transition to 10 Gb Ethernet (10 GbE) allows consolidation of multiple separate Ethernet ports into fewer 10 GbE ports. This greatly simplifies the data center network, reduces costs, and simultaneously provides greater overall platform networking bandwidth capability. If Fibre Channel has been used in the past, this additional Ethernet capacity can be effectively used to consolidate separate storage network traffic onto a common 10 GbE unified networking infrastructure, which drives an even simpler and more cost effective data center.

If you are part of an IT organization tasked with building a cloud storage solution, this white paper should be of interest: "Unified Networking with NetApp: 10 GbE FCoE and iSCSI". Intel and NetApp* worked together to implement and test cloud storage architecture. The white paper is a complete, step-by-step guide to building the two most common block-level storage protocols, Fibre Channel over Ethernet (FCoE) and Internet Small Computer System Interface (iSCSI), run over 10 GbE from end to end. Today, most IT departments deploy separate LAN and storage networks, with storage often divided between network-attached storage (NAS) for file-based applications, and SAN fibre channel and iSCSI for block-based applications. The goal of unified networking is to allow a single-fabric infrastructure, based on 10 GbE, to carry all of these disparate traffic types.

*Other names and brands may be claimed as the property of others.