The Wellcome Trust Sanger Institute is one of the largest genomics data centers in the world. In "The Hum and the Genome," the Scientist writes about the IT infrastructure needed to handle the avalanche of data that researchers have to analyze. With its 2,000 processors and its 300 terabytes of storage, the data center uses today about 0.75 megawatts (MW) of power at a cost of €140,000 per year (about $170K). But the data center will need more than a petabyte of storage within three years, and its yearly electricity bill will reach €500,000 (more than $600K) for about 1.4 MW, enough to power more than a thousand homes. Read more.
Below is a small diagram showing the current IT infrastructure of the Wellcome Trust Sanger Institute, used by the Human Genome Project (Credit: Wellcome Trust Sanger Institute).
Here is a link to a larger version of this chart.
Now, let's look at this IT infrastructure in detail.
Computers
Today: The datacenter hosts about 2,000 Alpha processors, originally designed by Digital Equipment (DEC), before its acquisition by Compaq, and later by Hewlett-Packard (HP).
Tomorrow: The Sanger Institute is looking at cheaper solutions, especially now that HP has officially stopped any development on the Alpha front.
Storage
Today: Three different computer rooms have a total capacity of about 300 terabytes.
Today we have naming of parts. Yesterday,
We had daily cleaning. And tomorrow morning,
We shall have what to do after firing. But today,
Today we have naming of parts.
—Henry Reed (1914–1986)
Tomorrow: The IT management forecasts about a petabyte within three years -- at least.
Databases
Today: There are about 40 different databases, and only two of them are in the 50 terabytes area.
Tomorrow: One of the databases, the Trace sequence archive currently contains about 700 million entries, and it doubles every 10 months.
Power bills
Today: The current equipment needs about 0.75 megawatts for a cost of €140,000 per year (about $170K).
Tomorrow: The new setup will need about 1.4 megawatts, which will raise the yearly bill to about €500,000 (about $615K today).
The supercomputer vendors can say all they want about diminishing costs. But they almost never talk about the power bills.
Sources: Stuart Blackman, The Scientist, Volume 19, Issue 11, Page 15, June 6, 2005; and various websites
Travelling, gentlemen, is medieval, today we have means of communication, not to speak of tomorrow and the day after, means of communication that bring the world into our homes, to travel from one place to another is atavistic.
—Max Frisch (1911–1991)
Related stories can be found in the following categories.
Databases
Energy
Genetics
IT
Storage
Supercomputers.