Mainframe > Administrator > Systems Management

Consolidate to the Cloud

System z10 consolidation ratios make it an ideal platform for internal cloud computing.

System z10 consolidation ratios make it an ideal platform for internal cloud computing.

Editor’s Note: This article is based in part on an internal IBM study, conducted in June by Scott A. Bain, Andrew J Bradfield, Justo Guizan, Innes Read, Roger W. Rogers, John J. Shedletsky, John J. Thomas and Barry Willner.

Many companies are finding their need for greater business agility frustrated by an increasingly costly and rigid IT infrastructure. The culprits are many, including maintenance requirements, operational expenses that exceed acquisition costs, low utilization rates and more. As a result, line-of-business units are beginning to go outside the data center to public cloud providers like Amazon in hopes of lowering their costs and improving their responsiveness. Instead of seeking relief outside the IT environment, IT needs to re-invent the data center and move toward a more Dynamic Infrastructure–one that utilizes consolidation and virtualization, and embraces a private cloud model.

A key requirement to building a private cloud service is deep virtualization. The number of workloads you can consolidate dictate what cost savings can be achieved with the cloud model. This article outlines the results of a technical study that compares different virtualization platforms for implementing a private cloud. It presents benchmarks that demonstrate consolidation ratios that can be achieved on these platforms. Additionally, results are refined to account for real-world, workload-demand variations. The numbers show utilizing z/VM on System z provides an industry-leading virtualization platform, capable of achieving very high consolidation ratios.

Creating A Virtualization Benchmark

A number of factors influence what consolidation ratios can be achieved in practice. The efficiency of the platform hypervisor in each of the major dimensions–CPU, memory and I/O–impacts the results. Hypervisor overhead reduces consolidation ratios. Other factors include variability in workload demand and the application of Service Level Agreements (SLAs).

John J. Thomas is a consulting engineer with the IBM Software Group Project Office.


comments powered by Disqus
Buyers Guide

Advertisement

Active Energy Manager Pulls Resources Together

Integration with InfraStruXure Centeral provides single management interface.

Amplifying Your Energy Efficiency

IBM BladeCenter and virtualization team up for greener data centers

IBM Systems Magazine Subscribe Box Read Now Link Subscribe Now Link iPad App Google Play Store
AIX News Sign Up Today! Past News Letters

Advertisement