Data Center Tech Blog
Victoria Koepnick

Product Marketing, Software Solutions

Cloud Plus imageI came across the Cisco Global Cloud Index and found the data center virtualization and cloud computing transition interesting.

Data center virtualization and cloud computing transition:

• The ratio of workloads to non-virtualized traditional servers will increase from 1.7 in 2012 to 2.3 by 2017.

• The ratio of workloads to non-virtualized cloud servers will increase from 6.5 in 2012 to 16.7 by 2017.

• By 2017, nearly two-thirds of all workloads will be processed in the cloud.

Table 3. Workload Shift from Traditional Data Centers to Cloud Data Centers

Global Data Center Workloads in Millions

2012

2013

2014

2015

2016

2017

CAGR
2012-2017

Traditional data center workloads

51.2

53.5

58.4

62.3

66.3

69.7

6%

Cloud data center workloads

32.2

45.7

61.1

78.1

96.8

118.5

30%

Total data center workloads

83.4

99.3

119.5

140.4

163.2

188.2

18%

Cloud workloads as a percentage of total data center workloads

39%

46%

51%

56%

59%

63%

NA

Traditional workloads as a percentage of total data center workloads

61%

54%

49%

44%

41%

37%

NA

Source: Cisco Global Cloud Index, 2013

One of the main factors affecting this migration of workloads from traditional data centers to cloud data centers is the greater degree of virtualization in the cloud space, which allows dynamic deployment of workloads in the cloud to meet the dynamic demand of cloud services. The ratio of workloads to non-virtualized cloud servers will grow from 6.5 in 2012 to nearly 16.7 by 2017. In comparison, the ratio of workloads to non-virtualized traditional data center servers will grow from 1.7 in 2012 to 2.3 in 2017.

According to the Index, 2014 will be the year of the tipping point with cloud workloads surpassing traditional workloads. With so many data center workloads moving to the cloud, ensuring the performance and elasticity of cloud resources to meet the demands of these workloads will be increasingly important. Cloud service providers will need the building blocks to readily scale infrastructure to meet performance and capacity demands of a variety of customer workloads.

Virtualization is certainly one tool that helps make it easier to scale compute resources, however, virtualization does not address the scalability of primary storage and in many cases can increase the complexity and cost of storage. For Cloud infrastructure, addressing cost-effective scalability and performance of storage resources can be accomplished using flash optimization software and solid-state devices deployed in the server. Particularly for workloads constrained by storage latency, deploying SSDs and flash optimization software, such as FlashSoft, in the server reduces the I/O load on the primary storage resources and eliminates latency associated with traversing the network, going through storage controllers, and the inherent latencies of spinning disk. And because FlashSoft is transparent to the primary storage it doesn’t require upgrades to the primary storage and can quickly and easily be deployed without disrupting existing data management and data protection policies.

For FlashSoft customer Cloud Plus, a leading Australian private cloud service provider, FlashSoft is the building block that helps ensure top performance at peak demand for their customer 1-300-Flowers, Australia’s leading florist network. Cloud Plus demonstrates the value of deploying flash optimization software to deliver required service levels to critical workloads. Through the deployment of FlashSoft Cloud Plus is able to build a cloud platform that delivers the performance and scalability necessary for clients’ most demanding workloads. See FlashSoft  Software for VMware® vSphere® Enables Cloud Plus, Inc. to Deliver Uptime During Peak Demand for all the details.

ULLtraDIMM, Customers – and Their Applications

Open Hardware = Faster Product Cycles: Next-Gen Architectures at OCP 2014

Subscribe Today!

Get our latest posts via email and enjoy data center insights in a flash