The Data Centre Arms Race - Causes

HANOVER, GERMANY - MARCH 05: A worker connects IBM Intelligent Cluster modules, including servers and data storage devices, of a Data Center at the IBM stand the day before the CeBIT 2012 technology trade fair officially opens to the public on March 5, 2012 in Hanover, Germany. CeBIT 2012, the world's largest information technology trade fair, will run from March 6-10, and advances in cloud computing are a major feature this year. (Image credit: Getty Images via @daylife)

This trilogy of articles looks at the development of bigger and better data centres across the world. It considers what is driving this construction boom, some of the challenges it faces and examples of how it is being implemented.

For a number of years the buzz word in the IT industry has been “cloud”. The word represents a shift in way all of us access and carry out our computing needs with an increased reliance on the internet. The term has even crossed into mainstream parlance thanks to services such as Apple’s iCloud. The idea behind cloud computing is that users can access computing resources, such as applications or storage space, on remote computers, via the internet rather than on local individual machines. The advantages are plentiful as consumers can access just the services they need as and when they need them (akin to traditional utilities) and from a multitude of devices and locations.

Many of us use explicitly labelled cloud services but the majority of those used, particularly in the private market, don’t necessarily prompt the same recognition. For example, the massively popular social media tools, Twitter and Facebook, allow us to share communications and media by storing it on remote servers where it can be accessed by anyone with whom we wish to share it via the internet, i.e., through the cloud.

In a sense, cloud computing is a natural evolution of the concept of the world wide web, which was intended to provide a network of shared documents, however with the wide availability of higher bandwidth internet connections and the adoption of Web 2.0, including the idea of user generated content, the old simple documents have evolved into complex web based applications and rich media.

The flexibility, scalability and cost effectiveness of cloud computing offers considerable benefits for both private and enterprise consumers compared to ‘traditional’ one-off installations on individual devices and therefore adoption rates continue to rise. The concepts can appear fairly ephemeral to the consumer, as they access all of their computing resource via the internet but, ultimately, all of that digital information does need to be stored somewhere. As the services get more and more popular, so social network providers, cloud storage providers, cloud application providers and IaaS (Infrastructure as a Service) providers need to find more and more physical capacity and recent years have therefore seen what has been described by some as a data centre arms race to build more and bigger data centre facilities.

The struggle therefore for data centre providers is to build bigger, to reach the capacity they need, but at the same time, minimise the power that they consume and the impact that they have on the surrounding environment. Power consumption is measured by a PUE (Power Usage Effectiveness) score which indicates the energy consumed by supporting infrastructure (mainly heat management) versus that required to power the core servers. The industry benchmark is a PUE score of 2.0 which represents one unit of power consumed on infrastructure for every one on servers, whilst the ultimate efficiency would be a PUE of 1. Not only does a more efficient facility prove greener and more sustainable but, for the provider, it minimises cost and increases the scope for raising capacity. Consequently data centre constructors are increasingly looking to new and innovative ways to bring this score below 2 and as close to 1 as possible.

The subsequent installments of this trilogy of articles looks at the scale of some of the biggest data centres in the world to illustrate how the need for digital data storage has changed the landscape of industrial complexes around the world.

© Stuart Mitchell 2012

A Brief History of Dermatology

The following article takes a look at the history of the area of medicine known today as dermatology, including its earliest incarnations in classical cultures.

What is Dermatology?
Before looking at the history of dermatology as a profession and as a term it is a worth briefly summarising what it actually involves. In a very basic sense dermatology is the area of medicine that relates to the skin. As a result it can cover practices which deal with diseases, cancers, infections, allergies and hormonal reactions that affect the skin, as well as purely cosmetic alterations and/or the treatment of ‘blemishes’. These practices can therefore involve areas such as surgery and pathology (diagnosis and treatment of diseases). Practitioners in the field are called dermatologists with more specific titles depending on their areas of expertise (e.g., a dermatolopathologist will specialise in dermatolopathology - the pathology of skin).

Ancient Dermatology
Dermatology as a defined concept really came into being around the end of the 18th and start of the 19th century despite the fact that skin conditions would have been treated and acknowledged throughout the course of human history. The coining of the term gave a formal label to a branch of medicine which included treatments and practices that would have been performed for thousands of years. In fact some of the earliest accounts of advanced skin treatment date back to the ancient Egyptians. Everyone knows the stories of Cleopatra bathing in ass’s milk, and the effects on the skin of the lactic acid in the milk are still recognised today. However, the Egyptians were known to use other substances to alter the appearance of their skin such as alabaster, oils and salt. They even applied some chemicals to the skin for medical rather than cosmetic purposes with arsenic, for example, being used in an attempt to treat skin cancers.

The forerunners of many other non-invasive dermatological practices which are still being explored today can also be traced back to the Egyptians. Techniques such as dermabrasion could be identified in the use of sandpaper to smooth down rough skin and scars, whilst they even realised the benefits of exposing skin to light (a practice which carried on through the ages), in their case natural sunlight.

The cosmetic benefits of skin treatments continued to be appreciated throughout the ancient world. The Greek and Roman cultures used a mixture of substances such as natural oils and resins (e.g., myrrh and frankincense) with pumices to smooth and exfoliate the skin. Across Asia, in India, they replaced the natural resins with urine to achieve the same results and rather drastically the ancient Turks achieved their exfoliation by actually singeing the skin.

The Birth of Modern Dermatology
The term dermatology itself Comes from the Greek for “skin” derma and “to learn” logy via first the French dermologie and subsequently the latinised term dermatologia. In fact the French were early practitioners in the modern field or dermatology, opening the first school in Paris at the Hôpital Saint-Louis in 1801. What we now consider as dermatology though can be traced back to the early 16th century in Europe and much of this early work focused on the use of chemicals from classical practices as well as sunlight on conditions such as eczema and psoriasis.

20th Century Dermatology
The start of the 20th century saw greater innovations in skin treatment using electrosurgery (treatment with electrical currents) and cryosurgery (the use of extreme cold) with subsequent developments in liposculpture (removal of fats from under the skin surface) and hair transplants taking place in the first half of the century. The early 1900s also witnessed the introduction of peels to strip away dead skin and expose new healthier skin, through the use of Phenol peels in particular.

In the 1950s, the use of light treatments evolved into the development of lasers and in turn these techniques progressed in the latter half the 20th century to deal with the removal of hair and certain cosmetic blemishes. Indeed, laser treatments are still being developed with current advances centering around the treatment of issues such as stretch marks and the tightening of the skin. The late 20th century also saw the further developments in peeling techniques to replenish the skin using trichloracetic and alpha-hydroxy acids, which hark right back to the earliest Egyptian practices.

© Stuart Mitchell 2012
If you want to find out more about how Dermatology can benefit you then you can visit Dermatologist London.

Explaining SI Unit for Computer Storage

English: This chart shows the growing percentage of the difference between decimal and binary interpretations of the unit prefixes plotted against the logarithm of storage size. Example uses multiple units of bytes. (Photo credit: Wikipedia)

Most of us who use computers either in our personal or professional lives will be familiar with the idea of computer storage and some of the units which are used to designate storage capacity at the lower end of the spectrum. The following article provides an overview of all of the units that have, as of present, been classified as SI units (International System of Units) including the familiar kilo-, mega- and gigabytes.

Before looking at its multiples it is worth becoming familiar with the concept of a byte (B) and what it represents. The fundamental unit of computer information storage is actually a bit (short for a binary digit) which is a binary concept in that it exist in one of two states, 1 or 0. A byte in turn is derived from eight bits because that was generally the number needed to form the smallest unit of meaningful data - a single character of text. Therefore, a byte is usually now equivalent to an ‘octet’ of bits although it can and has varied depending on the hardware in question. The word itself actually originated in 1956 as an intentionally incorrect spelling of the word bite to avoid corruption back to its smaller constituent, the bit.

Bytes can be measured in decimal (multiples of ten) or binary (multiples of two), again depending on the manufacturer of the hardware in question and unofficial convention. The following are decimal multiples as specified by the SI classification but the binary use of the terms is actually far more prevalent in practice. For every 1,000 bytes, the nearest binary equivalent would be 1,024 bytes. As binary systems us the concept of two states (e.g., true/false, off/on, 1/0, positive/negative) to represent information the binary multiples use doubling rather than factors of ten. To achieve the nearest equivalent value to 1,000 therefore the sequence 2, 4, 8, 16, 32, 64, 128, 256, 512, 1,024 is used; 1,024 being two to the power of ten (i.e., 210). At the lower end of the scale, binary and decimal equivalents are fairly close to each other (1,000 vs 1,024 is different by 2.4%), but as the scales grow the difference is magnified to the extent that the nearest equivalent multiples are almost 21% apart when considering 280 and 1024.

To avoid confusion between decimal and binary values, binary specific units have been standardised by the International Electrotechnical Commission (IEC) although the SI terms are still most frequently used to refer to the binary values.

Kilobyte

• kB (KB for binary)
• Number of bytes:
• Decimal - 103
• Binary - 210
• Difference between decimal and binary figures - 2.40%
• IEC equivalent:
• Prefix - Kibi-
• Symbol - KiB
• Example Storage: A text file of approximately 150 words (i.e., approx 1,000 characters)
• First Used: “kilo-” 1940s; “kilobyte” circa mid 1960s

Megabyte

• MB
• Number of bytes:
• Dec. - 106
• Bin. - 220
• Diff. - 4.86%
• IEC:
• Mebi-
• MiB
• Example Storage:
• A text file/book of approximately 500 pages of 2,000 characters per page.
• (If 8 bits per pixel, i.e., 256 colour depth) A 1,024x1,024 resolution image
• First Used: “mega-” 1940s

Gigabyte

• GB
• Number of bytes:
• Dec. - 109
• Bin. - 230
• Diff. - 7.37%
• IEC:
• Gibi-
• GiB
• Example Storage: One hour of standard definition video
• First Used: “giga-” defined in 1960

Terabyte

• TB
• Number of bytes:
• Dec. - 1012
• Bin. - 240
• Diff. - 9.95%
• IEC:
• Tebi-
• TiB
• Example Storage: Around 17,000 hours of compressed audio
• First Used: “terra-” defined in 1960

Petabyte

• PB
• Number of bytes:
• Dec. - 1015
• Bin. - 250
• Diff. - 12.59%
• IEC:
• Pebi-
• PiB
• Example Storage: The entire video storage of Netflix
• First Used: “peta-” defined in 1975

Exabyte

• EB
• Number of bytes:
• Dec. - 1018
• Bin. - 260
• Diff. - 15.29%
• IEC:
• Exbi-
• EiB
• Example Storage: 
• Estimated internet traffic per day in 2010
• Estimated cloud based hosting capacity of Amazon
• First Used: “exa-” defined in 1975

Zettabyte

• ZB
• Number of bytes:
• Dec. - 1021
• Bin. - 270
• Diff. - 18.06%
• IEC:
• Zebi-
• ZiB
• Example Storage: All human speech ever spoken could be stored as an estimated 42ZB of compressed audio
• First Used: “zetta-” defined in 1991

Yottabyte

• YB
• Number of bytes:
• Dec. - 1024
• Bin. - 280
• Diff. - 20.89%
• IEC:
• Yobi-
• YiB
• Example Storage:
• All human speech in approx. 0.042 YB
• By some estimations the entire digital data stored on earth
• First Used: “yotta-” defined in 1991

© Stuart Mitchell 2012

Invaluable Uses of Fast Ethernet

Yellow Ethernet plug, filtered (Photo credit: Jonathan Ah Kit)

The following is an article that explores the potential (and frequently realised) uses of Fast Ethernet in both the personal sphere and that of business.

Strictly speaking Fast Ethernet is a term that is applied to Ethernet connections with a rate of 100Mb/s (i.e., 100 megabits, or 100,000,000 bits, per second). These Ethernet connections are termed as such because they are 10 times faster than the original Ethernet. In practice the term can also be applied to speeds which reach a thousand times faster than that.

Fast Ethernet allows the transfer of large amounts of data at a faster rate and it is this feature that has led to its various uses, as it improves the capabilities of existing technologies as well as unlocking opportunities previously prohibited by the limits of traditional Ethernet speeds.

Wide Area Networks
Fast Ethernet is essential for the capabilities of Wide Area Networks (WANs) which allow businesses to operate securely across multiple office locations, providing them with private networks interconnected using leased lines or secure protocols (e.g., encrypted data packets). Whilst there are obvious efficiencies to centralising operations on a single site most businesses will be unable to avoid the necessity of having multiple sites such as branches. Fast Ethernet enabled WANs increase the feasibility of employees working seamlessly across such networks by allowing greater amounts of data to be transferred and therefore more complex IT functions to be performed which rely on these high data transfers. Importantly of course it will also increase the rate at which all transfers occur and therefore the speed of business operations.

Website Hosting
In short, websites are hosted, or stored, on servers which ‘serve’ the web page to the end user across the internet when they request it. As websites become more advanced they are including and displaying far more content than ever before whilst they are also increasingly relying on technologies which allow individual elements of the page to be updated after the web page has loaded. What’s more, there are more people using the internet than ever before and so successful websites will be hoping to attract thousands of these visitors. All this data flowing between the server and the multitude of end users at any given time puts more pressure on the networks that connect the servers up and connect the data centres (where servers are stored) to the rest of the internet. Again faster Ethernet connections can allow this data flow, prevent failed attempts to serve the web page and speed up loading times for the end users. The website visitor can access more content and functionality, more reliably and quickly; the website owner can keep their customers happier, providing them with more engaging services whilst exploring more profitable e-commerce avenues.

Gaming & Home Entertainment
Gaming requires the streaming of video and information data across networks, whether its streaming across a Local Area Network (LAN), or via cloud based gaming services which will run on remote server networks, accessed via the internet. Similarly, streaming of video, movies and TV for example, from central home media hubs or from cloud based providers is growing in popularity, as people look to access and store their video media in the digital world. Video in particular requires a very large amount of data to be transferred per second, especially when the video being streamed is high definition. Fast Ethernet networks, at both the home network and service provider levels, are vital to facilitate collaborative gaming and on demand home entertainment by allowing the video, audio and interactive game-play to be responsive as the mass of data is exchanged between the central servers and each player or consumer. Fast Ethernet networks, at both the home network and service provider levels, are vital to facilitate collaborative gaming and on demand home entertainment by allowing the video, audio and interactive game-play to be responsive as the mass of data is exchanged between the central servers and each player or consumer.

Video Conferencing
Rich video conferencing as part of a unified communications package requires the streaming of video, again preferably high definition, together with voice data (VoIP - Voice over the Internet Protocol) and complimentary services such as instant messaging and document collaboration. With such services, enterprise users can communicate effectively and timely, whilst saving them the lost time and productivity of travelling between locations. Businesses that use the technology are empowered to operate across disparate offices and engage with customers and suppliers across the globe.

© Stuart Mitchell 2012