Spoilt’s blog

50,000 processor cores and counting.. about half of these cores will be used to deal with data from the LHC which will generate about 15 petabytes of data by colliding protons with protons. The Computer Centre will provide only about 20 percent of the processing power used to examine the LHC data, with the rest coming from the LHC Computing Grid, a dedicated network of more than 100,000 processors. The grid is linked to the centre through dedicated 10-gigabit-per-second connections. It can handle about 50,000 users at once, sharing out bandwidth and processing power between scientists. To store the huge amount of data the LHC produces, the centre owns 8 petabytes of hard disks and 18 petabytes of magnetic tapes. This will increase to 16 petabytes of hard disks and 30 petabytes of tapes by the end of the year. Check out the photos, enjoy!

(more…)

CPU capacity required at CERN =)

The four detectors of the LHC project.

CERN Computer Centre. PC Farms: Inexpensive mass market components (running Scientific Linux CERN - recompiled RHEL).

For more posters & photos, check out the CERN section @ my photo Gallery.

In a few hours I’ll be boarding on the airplane and flying to Geneva, Switzerland.. CERN here I come again! =) More to follow..

Well, well, well… LHC switched on, world still here… Unfortunately for some no black holes were created and Satan didn’t use it as an inter-dimensional stargate to Earth. hahaha =) Therefore, if you’re reading this…the world hasn’t ended and unfortunately it’s not going to within the next 2-3 months. Why? LHC kaput…!

What is LHC@home?

LHC@home is a volunteer computing programme that enables you to contribute idle time on your computer to help physicists develop and exploit particle accelerators, such as CERN’s Large Hadron Collider (LHC).

Most of the scientific computing challenges that the LHC experiments are facing will require access to huge amounts of storage, the LHC will produce 15 Petabytes (15 million Gigabytes) of data per year. These data requirements mean that most analysis programmes cannot be run on individual PCs. This is why CERN is leading the development of Grid computing, which links hundreds of major computing centres around the world.

However, there are some exceptions where volunteer computing makes sense for the LHC. In particular, volunteer computing is good for tasks which need a lot of computing power but relatively little data transfer. In 2004, CERN’s IT Department became interested in evaluating the sort of technology (BOINC) that is used by volunteer computing projects like SETI@home. LHC@home became the overall title for these efforts;

This project uses BOINC. If you’re already running BOINC, select Attach to Project. If not, you will need to download BOINC (Fedora users: sudo yum install boinc-client boinc-manager).

So what are you waiting for? Join LHC@home now!!

Make sure you join the LHC@home Fedora Project Group.

Famous, famous LHC =p

If you’re reading this.. the world hasn’t ended (yet!)

I get the feeling that everyone is quite surprised and extremely relieved that both beams have successfully circulated the LHC today. The party has really started in the central control room. Its important that both beams have successfully circulated because it means that there are no major technical issues with it. The LHC has truly been born!

Today’s a big day for the universe as we know it: Scientists will attempt to re-create the aftermath of the Big Bang in the world’s most ambitious scientific experiment and it starts in 3 minutes!!

Click here for live webcast!

at last..

Click here if you’re new to Grids.
Click here to learn the basics (how to get a Grid Certificate, how to join a virtual organisation and so on).
a) First you need to install OpenAFS click here for more info
b) $ source /afs/cern.ch/project/gd/LCG-share/sl4/etc/profile.d/grid_env.sh
This will work out-of-the-box. You may want to add the above line to your .bashrc file. There’s no need to install anything LCG-specific on your fedora because you will be using CERN’s libraries, python, glite and etc.
for example:

[spoilt@prodigy ~]$ uname -a
Linux prodigy 2.6.25.10-86.fc9.x86_64 #1 SMP Mon Jul 7 20:23:46 EDT 2008 x86_64 x86_64 x86_64 GNU/Linux
[spoilt@prodigy ~]$ which voms-proxy-init
/usr/bin/which: no voms-proxy-init in (/usr/lib64/qt-3.3/bin:/usr/kerberos/bin:/usr/lib64/ccache:/usr/local/bin:/bin:/usr/bin:/home/spoilt/bin)
[spoilt@prodigy ~]$ source /afs/cern.ch/project/gd/LCG-share/sl4/etc/profile.d/grid_env.sh
[spoilt@prodigy ~]$ which voms-proxy-init
/afs/cern.ch/project/gd/LCG-share/3.1.14-0/glite/bin/voms-proxy-init
[spoilt@prodigy ~]$ voms-proxy-init
Enter GRID pass phrase:
Your identity: /DC=ch/DC=cern/OU=Organic Units/OU=Users/CN=ekaravak/CN=xxxxxx/CN=Edward Karavakis
Creating proxy ………………………………………………. Done
Your proxy is valid until Thu Jul 17 11:35:26 2008


Now you’re ready to run your echo “Hello World” to the Grid