Cloud Builder Forum

2 Posts authored by: Nikhil Sharma

"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.

No doubt you've been following Intel's Cloud 2015 vision announcements. A core element of our strategy is the notion of "federated." The federated cloud simply means that enterprises can procure compute capacity on demand and safely share data and compute across internal and external clouds. There are three key steps to enabling a federated cloud.

 

  • First: Move your applications and data to the cloud or between clouds.
  • Second: Have scale-out storage to recognize dispersion of data to need.
  • Third: Ensure that your environment is secure and compliant.

 

Move your application and data to the cloud or between clouds

Your enterprise may see a sudden surge in demand or may need to move its compute environment for business continuity. Traditionally to address such needs we would have to build redundancy or excess capacity in our environment. With a federated cloud one can move data and applications to the cloud or between clouds to address such needs, without building excess or redundant capacity. The reference architecture on cloud onboarding explains how we accomplish this critical business need via Cloud On-Boarding with Citrix OpenCloud* on the Intel platform.

 

Scale-out storage can be implemented with Xeon-based servers and Ethernet

Federated cloud and explosion of data volumes are requiring a different paradigm in storage that requires efficiency of storage. Traditional storage architectures based on SAN or NAS have limited ability to meet these new usage models, due to efficiencies & flexibility required in meeting volume scale & storage location requirements (i.e. in a remote data center or cloud service). The way to achieve the goal of efficiency and flexibility is to use scale-out storage architecture that federates the storage according to end-user need and tracks the split (or federation) of the storage using metadata. Scale-out storage is not a new concept but is being commonly used by large Internet portals such as Google and Facebook. With digital content doubling every year and the advent of the federated cloud, scale-out storage is quickly becoming the wave of the future. Such storage can now be deployed using standard Xeon-based servers and Ethernet fabric.

 

For a detailed description, the reference architecture "Scale-out Storage with EMC Atmos*" gathers in one place the essentials of a scale-out storage architecture based on EMC Atmos and Xeon servers. It provides you a recipe to embark on new storage architectures to achieve true cloud federation.

 

Achieve security and transparency with Intel® TXT

Federation brings good things, but it also brings the underlying concern of security of a federated environment. How do I know if my remote or federated cloud is secure and compliant to my requirements? One way to achieve security and transparency in a federated infrastructure is to use Intel® Trusted Execution Technology (Intel® TXT). TXT establishes a root of trust in the infrastructure by measuring compliance of platform components, like BIOS, OS, and VMMs (virtual machine managers), during boot. This root is extremely difficult to defeat or subvert and substantially reduces the security risks of using a remote infrastructure. This third reference architecture explains how we built a cloud with VMware vCenter Server*, VMware vSphere Hypervisor*, Intel® Xeon® processor 5600 series-based server platforms, and a plug-in designed to interface with TXT.

 

Within Intel Cloud Builders, there is a wealth of real-world examples. Many more white papers and case studies detail how Intel technologies are utilized as the foundation for storage and security for federated clouds. Look around and let us know if we can help you build a new federated cloud architecture or modify and rework an existing one. Feel free to ask me questions.

 

 

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

Filter Blog

By author:
By date: By tag: