This is part 5 of an on-going series.  Part 1: Virtualization isn’t the next big thing (NBT) because it was the last big thing (LBT); part 2: data center IP traffic growth; part 3: data center IP traffic sources; part 4: cloud workloads.

In our final post on next generation data center trends, we thought we’d simply show you as of mid-2014 estimates of the number of servers in some of the largest and best known data centers – and discuss trends associated with more servers with fewer IT staff.

Next Generation Data Center and Cloud Trends - 2014 Largest Data Centers

Server counts are a closely held secret at many of the largest data centers – so you end up having to piece together and extrapolate the number of servers within these data centers.  Google has an estimated one to two million servers operating; Microsoft has an estimated million servers; and Amazon has an estimated 500,000 servers.  You can find Akamai, Facebook, Intel, Yahoo, Godaddy, Rackspace, Ebay, and others as well on this chart.  Google has stated publicly that they are planning their infrastructure to support ten million servers.

The most important thing to note here is that the number of servers, while interesting, is relatively meaningless.    The generation of server, and thus the core count, memory, I/O backplane, and other attributes of the servers means that comparing a server built in 2010 versus a server built in 2014 isn’t a very constructive exercise.

What’s more interesting is the sheer number of servers per operations personnel.  Facebook has confirmed as of 2013 that each of its operation personnel manages on average 20,000 servers – and some personnel manage as many as 26,000 servers.  This is handled through the automation of most data center tasks.  Facebook has developed its own software, which they call CYBORG, which detects server problems and attempts to resolve those problems.  If automated repair attempts fail, CYBORG sends a ticket so that a human being can become involved.

In SMB (Small and Medium Business), where the average number of assets supported per IT staff is 30:1, the number of servers being supported per operations person seems daunting.  But the answer is relatively straightforward: automation.

That’s all we’re going to talk about in this series regarding trends; in the next set of posts in this series we’ll begin discussing strategies for building next generation data centers today.


This is part 4 of an on-going series.  Part 1: Virtualization isn’t the next big thing (NBT) because it was the last big thing (LBT); part 2: data center IP traffic growth; part 3: data center IP traffic sources.

We’ve reviewed the trends associated with data center IP traffic growth and the sources of that growth; now let’s look at the trends associated with the workloads running in data centers.

Next Generation Data Center and Cloud Trends - Data Center Virtualization

As per the chart above derived from the Cisco Global Cloud Index, 2012-2017, cloud workloads will grow 500% faster than traditional workloads from 2012 to 2017.  The ratio of workloads to non-virtualized traditional servers increases from 1.7 to 2.3 while the ratio of workloads to non-virtualized cloud servers will increase will increase from 6.5 to 16.7 during that same time period.

The bottom line: by 2017, almost two-thirds of all workloads will be processed via cloud servers.  The drivers for this are the ability to increase capacity or add functionality and capabilities dynamically (on the fly) via subscription-based or pay-per-use services.  Virtualization of course begat the cloud; the technology is the foundation for the modern cloud movement due to its ability to better handle the dynamic deployment of services.

This growth explains why the concept of the software-defined data center (SDDC) has been promoted so heavily.  SDDC extends virtualization concepts of abstraction, pooling, and automation from compute to all of the resources of the data center.  This includes but is not limited to the virtualization of storage (software-defined storage, or SDS) and  networking (software-defined networking, or SDN.)

In the next part of this series, we’ll finish our discussions of data center trends by looking at estimates of the sheer number of servers in some of the largest data centers.


Backup, Virtualization, and the Next Big Thing: Data Center Traffic Sources [Part3]

July 28, 2014

This is part 3 of an on-going series.  Part 1: Virtualization isn’t the next big thing (NBT) because it was the last big thing (LBT); part 2: Data center IP traffic growth. With data center IP traffic growing at a 25% annual rate to a projected 7.7 zettabytes per year by 2016, the obvious question is […]

Read the full article →

Backup, Virtualization, and the Next Big Thing: Data Traffic Growth [Part 2]

July 25, 2014

In part 1 of this series, we gave an overview of a simple yet powerful concept: virtualization isn’t the next big thing (NBT) because it was the last big thing (LBT) – virtualization is our foundation.   If your planning for your data center and the backup of that data center assumes that virtualization is in effect […]

Read the full article →

What is BC/DR Link?

July 24, 2014

Unitrends just released a free BC/DR planning tool called BC/DR Link , and we wanted to tell you a bit more about it.  It’s a free online service tool that helps you build and customize a Disaster Recovery (DR) plan so you can be confident in your ability to respond to a disaster or outage rapidly and […]

Read the full article →

Backup, Virtualization, and the Next Big Thing: Overview [Part 1]

July 24, 2014

Preface: Greg Shields recently hosted a webinar for 600+ registered webinar attendees for a fireside chat in which I was the invited speaker.  We talked about a variety of topics – from agility, automation, and adaptability to virtualization and software-defined data centers – from containers and Dockers to the internet of things.  What I’m going […]

Read the full article →

Gartner’s Magic Quadrant for Enterprise Backup and Integrated Appliances – Unitrends, CommVault, EMC, IBM, and Symantec

July 15, 2014

Gartner has been seeing a steady rise in client inquiry and deployment of these integrated backup appliances in midsize and large enterprises. [Gartner's 2014 Magic Quadrant for Enterprise Backup and Integrated Appliances] The reception in the market to Unitrends being included for the first time in Gartner’s 2014 Magic Quadrant for Enterprise Backup and Integrated […]

Read the full article →

Seagate’s EVault, DRaaS, Iron-Clad SLAs, Opinions, and Facts

July 11, 2014

Recently Seagate’s EVault subsidiary took offense with our press release announcing our providing our customers with DRaaS (Disaster Recovery as a Service.)  The press release, entitled “Unitrends Delivers Industry’s Only Iron-Clad Disaster Recovery Assurance to Customers“, appears to have touched a nerve.  I thought this part of EVault’s blog post in particular was interesting: To Unitrends – welcome to […]

Read the full article →

Announcing Unitrends Hybrid Cloud: DRaaS and Recovery Assurance

July 10, 2014

“Brands are temporary fads. Functionality is forever.” [Douglas Rushkoff] I don’t always agree with Douglas Rushkoff, but I’ve always liked this quote.  I think it’s aspirational in terms of high-technology companies.  It certainly describes where we are taking Unitrends.  Or to put this another way: recovery assurance is forever. Which brings me to our latest Unitrends Cloud […]

Read the full article →

Backup Per-Job Deduplication Versus…Well…Real Deduplication

July 1, 2014

Actual Unitrends and REDACTED VMware vSphere 5.5 Storage Deduplication for a Single VM and a Single VMDK [Preface: Note that the although the data is real, the name of our competitor has been obscured, changed, and otherwise redacted to avoid hurting anyone's feelings.  The original post in this series describes this in more detail.  The second post […]

Read the full article →