How to Cut Costs When Migrating to the Cloud

 
 
By Karen A. Frenkel  |  Posted 02-20-2017 Email
 
 
 
 
 
 
 
 
 
  • Previous
    How to Cut Costs When Migrating to the Cloud
    Next

    How to Cut Costs When Migrating to the Cloud

    This study measures whether it's more economical to run workloads on-premise or in the cloud, and whether to refresh technology or migrate to the cloud.
  • Previous
    Economics of Virtualized OS Instances
    Next

    Economics of Virtualized OS Instances

    45% of virtualized OS instances could run more economically in the cloud if they were migrated as is, without any changes to cloud-optimized applications.
  • Previous
    Migrating Virtualized OS Instances
    Next

    Migrating Virtualized OS Instances

    Migrating those 45% of virtualized OSs would generate an overall cost savings of 43% annually.
  • Previous
    Over-Provisioned OS Instances
    Next

    Over-Provisioned OS Instances

    Based on the historical utilization patterns of thousands of workloads that were sampled, 26% of OS instances are over-provisioned.
  • Previous
    Generating Cost Reductions
    Next

    Generating Cost Reductions

    Migrating those 26% of over-provisioned OS instances to cloud instances sized for utilization would generate a 36% cost reduction compared to provisioning them in the cloud exactly as they are provisioned on-premise.
  • Previous
    Aging Servers
    Next

    Aging Servers

    TSO's anonymized statistical analysis of 10,000 servers found that 25% are more than three years old.
  • Previous
    Power Gains
    Next

    Power Gains

    Comparing just the processing power, the same workloads that run on Generation 5 servers could run on 30% fewer Generation 9 servers.
  • Previous
    Upgrading Older Servers
    Next

    Upgrading Older Servers

    By upgrading older servers to modern hardware and provisioning them based on historical utilization, the same workloads could be supported with 54% fewer servers.
  • Previous
    Results Caveat
    Next

    Results Caveat

    These results are a top-line analysis. They don't take into account other advantages of cloud migration or changes organizations can make to applications that would make them more economical.
  • Previous
    Low-Hanging Fruit
    Next

    Low-Hanging Fruit

    The results do show that there is probably significant low-hanging fruit that IT executives can identify and migrate, resulting in significant financial gain.
 

A statistical analysis of operating system instances—the creation of objects each time a program runs—offers insights into the economics behind cloud migration. The fine-grained, algorithmic analysis attempts to answer questions such as these: Is it more economical to run workloads on-premise or in the cloud? Should companies invest in refreshing their technology or in cloud migration? Often, businesses rely on spreadsheets and high-level financial models to make these decisions. This statistical method, performed by TSO Logic, uses anonymized data that includes hundreds of millions of data points from more than 10,000 servers, including hypervisors and non-hypervisors. There were 25,000 virtual OS instances from which the authors compiled a sample. Other questions addressed were: What is the cost of running OS instances as currently provisioned? How much is each instance used historically? How well do currently provisioned resources match up to utilization? And which of these workloads would be economically more viable in future environments, including cloud or server refresh? Following are the study findings.

 
 
 
 
 
Karen A. Frenkel writes about technology and innovation and lives in New York City.

 
 
 
 
 
 

Submit a Comment

Loading Comments...
 
Manage your Newsletters: Login Register