An executive view: Data Reduction improves the case for the cloud for telecommunications companies
By Wayne Salpietro and Louis Imershein
You probably have already made a commitment to the cloud because it enables you to flexibly deliver your computing resources more quickly and at a lower cost. Entities are steadily shifting towards cloud-first strategies where they can rapidly adapt to market dynamics as they are no longer bound by legacy computing constraints. Public, private, or hybrid clouds are choices every C-level executive is making today. Each are different - for example, public cloud is shared with other businesses to yield economies of scale in Amazon Web Services (AWS), Google, Microsoft, while private cloud is either on-premises or hosted by a public cloud provider. Hybrid is a mix of both approaches, with different workloads deployed in each based on need. IDC reports that clouds are rapidly evolving to become more trusted, more intelligent, and more specialized for particular industries and workloads.
The cloud's raison d'être, regardless of the deployment model used, is its ability to deliver overall agility, deployment flexibility, and elasticity. Cloud priorities today include moving more workloads to the cloud, optimizing existing cloud utilization, leveraging innovation, and enabling multi-cloud deployments.
As telecommunications companies deploy cloud infrastructures, they embrace efficiency techniques that have been developed and used by Amazon, Google, and Microsoft to control their public cloud data center costs. They deploy efficiency models that increase data density and reduce footprint requirements, while dropping operating costs for power and cooling. As these extremely efficient models are deployed, legacy purpose-built hardware is being replaced with software-defined data centers running on industry-standard servers
Software-defined data centers usher in new opportunities to maximize efficiency in software. One such feature, which is particularly effective and critical in cloud environments, is inline data reduction which includes deduplication and compression. In addition to the platforms and software efficiency of cloud, data reduction delivers a substantial impact on your state and local government and your budget by reducing the amount of data stored. Data reduction shrinks the amount of storage consumed, increases data density further, and lowers the costs of data at rest and in flight over your networks. No matter which cloud deployment you use, data reduction delivers economic benefits that make the cloud business case more compelling.
If you are deploying in a public cloud
Every day new workloads are being deployed in public clouds. Worldwide public IT cloud service revenue in 2018 is predicted to be $127B. The economics that public cloud delivers are undeniable. Amazon, Google, and Microsoft growth in the public cloud is testament.
As you deploy a public cloud environment, consider that data reduction technology shrinks public cloud costs. For example, data reduction technology (deduplication and compression) typically cut capacity requirements of block storage in enterprise public cloud deployments by up to 85% (6:1). Take your cloud block storage bill, divide by 6, and that is the business case.
The following Amazon cloud deployment example employing data reduction demonstrates how data reduction delivers substantial savings:
- If you provision 300 TB of General Purpose SSD storage for 12 hours per day over a 30-day month in a region that charges $0.10 per GB-month, you would be charged $15,000 for the storage.
- With 6:1 data reduction, that monthly cost of $15,000 would be reduced to $2,500. Over a 12 month period you will save $150,000.
Bottom line, data reduction reduces costs of public cloud deployments.
If you are deploying in a private cloud environment
Organizations see similar benefits when they deploy data reduction in private clouds. IDC predicts $17.2B in infrastructure spending for private cloud in 2017. This demand reflects requirements for cloud's increased efficiency, flexibility, privacy, performance, and security.
The telecommunications case for data reduction in private cloud is based on reducing the cost of both storage hardware and excessive annual software licensing. For example, Software-Defined Storage (SDS) solutions are typically licensed by capacity and their costs are directly proportional to storage device expenses. Data reduction decreases storage costs because it reduces storage consumption, as demonstrated in the following example:
- You deploy a private cloud configuration with 1 PB of storage infrastructure and SDS. Assuming a current hardware cost of $500 per TB for commodity server-based storage infrastructure with datacenter-class SSDs and a cost of $56,000 per 512 TB for the SDS component, you would pay $612,000 in the first year. In addition, annual software subscriptions over three years cost $836,000 for 1 PB of storage and $1,060,000 over five years,.
- In comparison, the same configuration with 6:1 data reduction over five years will cost $176,667 for hardware and software, resulting in $883,333 savings.
If you are deploying a hybrid cloud
Hybrid cloud is the preferred cloud deployment approach today because it addresses data security concerns while still leveraging cloud efficiency. On-premises resources (private cloud) combined with colocation and multiple public clouds result in a highly redundant data environment. For example, IDC's FutureScape report finds "Over 80% of enterprise organizations will commit to hybrid cloud architectures, encompassing multiple public cloud services, as well as private clouds by the end of 2017." (IDC 259840)
One consideration is whether to depend on a single cloud storage provider, which can pose a significant risk to Service Level Agreement targets. Consider the widespread AWS S3 storage errors that occurred on February 28th 2017, where data was not available to clients for several hours. Businesses lost millions of dollars of revenue due to loss of data access. This highlighted requirements for a "Cloud of Clouds" approach where data is redundantly distributed across multiple clouds for data safety and near continuous accessibility. IDC forecasts that 85% of cloud deployments will be multi-cloud by 2018. Unfortunately, the Cloud of Clouds approach increases storage capacity cost (by having redundant copies in multiple clouds), and adds the networking cost to move and sync data between cloud deployments.
That's where data reduction comes in, as demonstrated in the following example:
- In hybrid cloud deployments where data is replicated to the participating clouds, data reduction multiplies capacity and cost savings. If three copies of the data are kept in three different clouds, three times as much data is saved and data movement between clouds to sync them can be costly.
- Take the private cloud example above where data reduction drove down the costs of a 1 PB deployment to $176,667, resulting in $883,333 in savings over five years. If that PB of data is replicated in three different clouds, the savings would be multiplied by three times for a total savings of $2,649,999.
Data reduction described
One data reduction application that can readily be applied in public, private, and hybrid clouds is Permabit's Virtual Disk Optimizer (VDO), a pre-packaged software solution that installs and deploys in minutes on Linux operating systems. Because it is deployed directly with Linux, it can be easily deployed in any public or private cloud today.
OS-based data reduction solutions such as Permabit VDO address public cloud, private cloud (including on-premises and hosted private clouds), and the bandwidth challenges faced in hybrid cloud environments. Data reduction can reduce storage requirements and network bandwidth consumption by as much as 85% (6:1 data reduction).
Data reduction solutions generally combine a number of techniques to reduce data footprint. For example, Permabit VDO applies three reduction techniques:
- Zero-block elimination uses pattern matching techniques to eliminate zero data blocks
- Inline Deduplication eliminates duplicate data blocks
- HIOPS Compression(tm) compresses the remaining data blocks
The graphic below visually demonstrates how simple data reduction really is and its impact on storing data.
Data reduction delivers compelling cost reduction that substantially improves the government case in every cloud deployment model. No matter which cloud approach you choose, the cost savings benefits from data reduction should not be ignored and must be a component of your cloud strategy.
Telecommunications businesses are finding that the future of their computing infrastructure lies in the cloud. Data reduction technologies enable clouds - public, private, and hybrid - to deliver agility and elasticity at the lowest possible cost, making cloud the deployment model of choice for IT infrastructure going forward.