This page contains a Flash digital edition of a book.
Issue 1, December 2008


big investment announcements already in 2008 each involving hundreds of millions of dollars. IBM is also bringing medium scale data centers to support cloud applications. What we know for now is that it is primarily opting for the large scale mega data centers in which infrastructure will be shared.

IBM defi nes cloud computing as: “Where users can gain access to their applications from anywhere through their connected devices. The applications reside in massively scalable data centers where compute resources can be dynamically provisioned and shared to achieve signifi cant economies of scale. A strong service management platform results in near-zero incremental management costs when more IT resources are added to the cloud.” IBM is working to defi ne a framework for running large scale data centers for hosting a wide range of applications. The framework includes automation of processes for provisioning applications and systems, data center-level virtualisation and support for extremely data intensive workloads.

According to IBM the elements of successful cloud data centers are shared infrastructure, virtualisation, automation, provisioning, management, monitoring and capacity planning. Of these the keys are “virtualisation and the management layer.” (Figure 2)

While Google and Amazon say they already operate cloud data centers, another big player currently constructing cloud data centers around the world is Microsoft. This is part of its reaction to more fl eet of foot rivals who have used networks and the internet to take chunks of its business. built a software as a service applications business right under Microsoft’s nose. Firms like Google have popularised the web as not just an application development but also delivery platform and at the server virtualisation level the Redmond giant is playing catch up with EMC-owned Vmware and competing with open source version Xen.


Like IBM Microsoft is building data centers across the globe to service cloud applications.

It is thundering into the cloud and investing heavily in the data center infrastructure that underpins it. It is building big data centers, albeit in a modular fashion. It’s paper “On Delivering Embarrassingly Distributed Cloud Services” questions the need for very large data centers and instead pushes the case for a modular approach (at a capital expenditure and operational expense level.) Microsoft offers a “back of the envelope comparion” (see fi gure 3).

Figure 1.

Figure 2.

For example, it says mega data centers risk cost escalation and may face power issues. If a mega data center consumes 20MW of power at peak from a given power grid, that grid may be unable or unwilling to sell another 20MW to the same data center operator, the paper says.

“Data centers encounter various diseconomies of scale when they become so large that they require signifi cant investment in infrastructure. In the mega data center this means a very high degree of redundancy at many levels – for example in power delivery

and provisioning. As we cannot afford to lose the entire site owing to power failure or network access failure the mega data center may incur large costs in batteries, generators, diesel fuel and in protected networking design (e.g. over provisoned multiple 10 GE uplinks and/or Sonet ring connectivity to the WAN)... Mircosoft calculates that a new 13.5 MW data center costs $200 million before the 50,000 servers are purchased. “Even if the servers are built from commodities, the data centers themselves are not.”” (See fi gure 3)

It believes that only large cloud service providers (Amazon, Yahoo, Google etc) 39

Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72