Large Hadron Collider Week – Day 2

CERN has a reputation for being at the forefront of networking technology – “where the Web was born” is the lab’s motto. When it comes to Grid technology, this is particularly true: CERN is leading some of the most ambitious Grid projects in the world.

CERN has chosen Grid technology to solve a huge data storage and analysis challenge it will face in 2008, when the Large Hadron Collider, the biggest scientific instrument in the world, starts running. At that time, thousands of physicists around the world will start clamouring for access to the streams of data that will come out of the instrument. The data will be a goldmine for finding traces of new exotic fundamental particles of matter, which in turn will tell physicists a lot more about how the Universe was formed and what its future might be.

The data will be produced at about 10 Petabytes a year. That is more than 1000x the amount of information in book form printed every year around the world , and nearly 1% of all information that humans produce on the planet each year – including digital images, photos and what have you. In short, that is a LOT of information.

The only reasonable way to access this amount of information (actually, much more than this, since the cumulative data over more than a decade of operation will have to be stored) seems to be Grid technology.

So CERN has taken a big gamble on Grid technology, and is pushing the technology forward in several ways, in order to make the 2008 LHC deadline.

From the Gridcafe website (http://gridcafe.web.cern.ch/gridcafe/GridatCERN/gridatcern.html)

10 Petabytes. Like our last post, it is hard to imagine something this size. Lets try to put this is perspective.

If we put all of that data on 700MB CD-Rs, how high would the stack of CD-R’s be?

Lets assemble our data first:

CD-R capacity: 700 MB

CD-R Height: 1.2mm

1 Petabyte (PB) = 1,024 Terabytes

1 Terabyte (TB) = 1,024 Gigabytes

1 Gigabyte (GB) = 1,024 Megabytes (MB)

1 km = 1,000 m

1m = 1,000 mm

First, we should convert 10 Petabytes into Megabytes.

There are 1024 Megabytes in a Gigabyte. Since there are 1024 Gigabytes in a Terabyte:

There are 1024 * 1024 Megabytes in a Terabyte. Since there are 1024 Terabytes in a Petabyte:

There are 1024 * 1024 * 1024 Megabytes in a Petabyte.

That equals 1,073,741,824 Megabytes in a Petabyte. Since we want 10 Petabytes in total:

That means we are looking at a total of 10,737,418,240 Megabytes.

Next we need to know how many CD-Rs we would need to hold that much data.

Since 700 Megabytes fit on 1 CD-R, we simply need to divide that large number by 700.

10,737,418,240 / 700 = 15,339,168.91 CD-Rs.

Since we cannot have .91 of a CD-R, we round up.

15,339,169 CD-R’s

Next we need to convert 1.2 mm to km so we will not be working with astronomically large numbers.

There are 1000 millimeters in a meter. Since there are 1000 meters in a kilometer:

There are 1000 * 1000 millimeters in a kilometer.

There are 1,000,000 millimeters in a kilometer.

1.2 mm equals how many kilometers?

1.2 / 1,000,000 = .0000012 km.

So we know that we have 15,339,169 CD-R’s at a height of .0000012 km each. If we stacked them all up, how tall would it be?

We simply need to multiply these two numbers and that will equal our height in kilometers.

15,339,169 * .0000012 = 18.407 km.

Our stack would be approximately 18.4 kilometers tall.

That’s very tall considering Mount Everest is only 8.848 km tall. Our stack of CD-R’s will be over twice the height of the tallest mountain on the planet!

I hope that puts how much data the LHC will generate in perspective.

Please note that if you click the link below the article above, they state that the height will be approximately 20 km tall. There are a few reasons why our answers might be different. They might have rounded 18.4 to 20. They might have had a more precise number about the amount of data (example, 10.45 petabytes.) They might have had smaller CD-R’s in terms of data capacity. Or they might have had a more accurate measurement for the height of a CD-R (example, 1.24 mm). All of these would affect the potential height of our stack of CD-Rs. Regardless, the mathematical technique to find the height would be the same. Check back later this week for the conclusion to Large Hadron Collider Week!

CD