Data Centers are Sitting on a Mountain of Unused Data Storage

by VideoCoin | August 22, 2018

Our world is thoroughly connected and eminently digital. There are 2.5 quintillion bytes of data created each day. As we consider the issue of data storage allocation, let’s examine some stats to get an idea of how much data is contained in that 2.5 quintillion bytes.

Every minute:

  • Snapchat users share 527,760 photos
  • Users watch 4,146,600 YouTube videos
  • 456,000 tweets are sent on Twitter
  • Instagram users post 46,740 photos
  • Each day 95 million photos and videos are shared on Instagram

Consider the volume of communication we send out every minute:

  • We send 16 million text messages
  • We send 156 million emails
  • 15,000 GIFs are sent via Facebook messenger
  • Every minute there are 103,447,520 spam emails sent
  • There are 154,200 calls on Skype

Add to that the number of digital medical records, financial transaction data, customer personal information, and countless categories of business data. Where does all that data go? It’s all stored in a data center somewhere, of course.

After examining these numbers, it would seem there wouldn’t be enough data storage allocation. But in fact, it’s just the opposite: data centers worldwide are sitting on a behemoth of unused data storage.

Data Storage Allocation – Where Does it all Go?

Enter the data center. It seems that in the eyes of most companies, their view of data centers is parallel to John D. Rockefeller’s view of money. How much is enough? “Just a little bit more.”

In the State of the Data Center 2018 Survey conducted by AFCOM (originally the Association for Computer Operations Management), respondents were asked about data center growth. The survey revealed that ownership, renovations, and building were growing.

  • 58% of responding companies own 2-9 data center facilities
  • 19% said they own 10 or more data centers.
  • Responding companies indicated that 7.8 data centers will be renovated over 12 months

A more interesting set of statistics revealed that new data center construction will grow more than five times over the next three years.

  • The average number of data centers to be built sits at around 2.2 per organization  
  • That number increases to 4.5 over the course of 12 months
  • Three years out, the average number of data centers to be built is 10.3 per organization

These statistics fall into line with findings from the latest Cisco Visual Networking Index which indicates some interesting trends going into 2021:

  • Annual global IP traffic will reach 3.3 zettabytes by 2021. In 2016, global IP traffic was 1.2 ZB per year or 96 exabytes (one billion gigabytes) per month.
  • Global IP traffic will increase nearly threefold over the next five years, and will have increased 127-fold from 2005 to 2021.

 

Today and beyond, new solutions concerning data center architecture will force businesses and IT professionals to look for better ways to utilize existing data storage allocation in order to handle rising amounts of data.

How Much Data Storage Allocation is Underutilized?

As far back as 2010, there were estimates that 60% to 70% of data capacity remained unused in data centers because of over-estimating needs for applications and misconfiguring data storage systems.

More recently, the Anthesis Group, working in partnership with Stanford University and TSO Logic, released a report that suggested there were 10 million physical servers deployed inside data centers around the world that were not actually being used. The report referred to these idle servers as “comatose.”

Jonathan Koomey, research fellow at Stanford’s Steyer-Taylor Center for Energy Policy and Finance, says, “Roughly 30% of the servers deployed worldwide have not delivered information or computing services in the last six months.”

Most recently, the IDC study entitled Quantifying Datacenter Inefficiency: Making the Case for Composable Infrastructure also found that in most enterprise data centers, infrastructure is:

  • 45% provisioned: This is total capacity available in the infrastructure versus what is made available to the physical or virtual machines running applications.
  • 45% utilized: This is the amount of idle compute hours and unused storage capacity for provisioned components.
  • 30% agile: This is the perceived time it takes to provision new computing and storage instances or make changes to existing instances.
  • 40% compliant: This is the perceived confidence in the ability to meet stated service-level agreements (SLAs) for infrastructure and its components, such as requisite redundancy and resiliency.

Why is So Much Data Storage Allocation Being Wasted?

Reasons for the waste in data storage allocation vary, depending on which IT expert you ask, but among recent publications, the following issues keep appearing.

Lack of Communication  

Lack of communication between teams results in deployment of IT infrastructure that ultimately gets wasted. Changing the way enterprise data centers are managed and appointing one boss, one team, and one budget allows a unified approach to IT that doesn’t waste resources.

Lack of Analytical Capabilities

Many IT departments lack access to analytics tools, meaning they don’t have much visibility into what resources are actually being used by applications. The ability to analyze resources in real-time allows for accurate estimations of need and usage, and prevents waste.

Overestimating Needs

Most IT departments overestimate their needs for server capacity, “just in case.” Anticipated or dreamed future need becomes the norm. However, projections rarely live up to reality, and must is left unused and wasted.

How Can Unused Data Storage Allocation be Recycled?

With the massive amounts of data being produced each day, and the exponential increase in storage-hungry video content, is there a way to use all that wasted data storage? Until now, servers have remained a fixed asset. Virtualization solutions have helped single servers become more usable, except when faced with unpredictable workloads and overwhelming data sets. Here are two viable solutions.

Composable Infrastructure

Data centers need to be agile. Current-generation IT infrastructure is generally rigid and siloed, making it difficult to embrace necessary changes. Composable infrastructure means shifting from a static and inflexible infrastructure to one that is highly utilized, agile, and automated.

Storage Reclamation

Another way to combat poor utilization rates is storage reclamation. This is where unused data blocks are identified and then placed back into a pool of available storage. Some large providers already have storage reclamation algorithms in place to help find available space for enterprise data.

The VideoCoin Network

This is a decentralized video encoding, storage, and content distribution system that will allow for unused storage across the internet to be allocated. Video storage, encoding, retrieval, and distribution are handled through the VideoCoin Network by the use of miners. More storage, more control, less waste.



Participate

Related Articles



How to Solve the Intense Compute Require...

by VideoCoin | October 17, 2018

How VideoCoin Will Help Vlogging

by VideoCoin | September 20, 2018

Shocking realities of streaming live VR ...

by VideoCoin | September 11, 2018