Atlas@home

Gilthanis

Gilthanis

[H]ard|DCer of the Year - 2014
Joined
Jan 29, 2006
Messages
8,735
David Cameron (admin) has asked for donors to bring more resources to help them finish up several important work units.

The current set of ATLAS@Home work units are quite important to the experiment and would like to get them finished as quickly as possible. Therefore if you have more CPU to donate to ATLAS@Home over the next couple of weeks to crunch through these WU it would be very much appreciated! There are currently around 7000 WU left to crunch in this set and we will provide regular updates of how many are left to go.

Many of the server-side scalability issues have been addressed and we are confident that we can handle more concurrent WU at this time. However the vboxwrapper is still having issues in some cases, so if you notice that you have WUs that are stalled or WUs that consume very small amount of cpu for more than 30 minutes, please abort them since they will most likely not succeed. The expected cputime usage of the WUs varies from 6 to 36 hour, so please ignore the WU progress as reported by the client.

Thank you in advance for your help!
Click to expand...

I will warn that this project:
1. Requires Virtualbox to be installed.
2. Uses quite a bit of RAM. Potentially 2GB+ per work unit.
3. Work units can actually download additional data while processing.
4. OS needs to be 64bit.

http://atlasathome.cern.ch/forum_thread.php?id=164#1321
 
I just told F@H to stop when it finishes the current WUs, and I am downloading BOINC now. This evening I should be able to dedicate 4-6 4Ghz AMD FX cores to ATLAS for a bit.
 
If you are new to BOINC, this project may not be the best first experience. But if you are willing to give it a whirl... just let me know if you need help. :)
 
Once I realized it just takes a while to download the WUs, it was running with little difficulty. It is up to 6% on some of them already, and my system is running much quieter than with F@H at full blast, so I may be able to watch a movie or something. :)
 
Good to hear. Keep us posted on if you see anything quirky. This is an Alpha/BETA project after all that should eventually get merged with their vLHC project. But who knows when that will be.
 
Dear volunteers,

First of all we would like to warmly thank all the volunteers how have contributed to the ATLAS@home project; below a few news and prospects for the next weeks.

o The BOINC server is experiencing load issues since several days which are being addressed by CERN IT. It is hoped that a the situation will be back to normal in the next days.

o BOINC results have passed ATLAS validation. It took longer than expected for various reasons : a dedicated sophisticated procedure has been developed to ensure that statistically BOINC simulation does not introduce any bias, in the course of the validation procedure several issues were found in the validation tools themselves. Now we are happy to announce that BOINC is fully validated for ATLAS simulation.

o As you may know, the LHC is about to deliver collisions at an increased energy. We have stopped submitting WUs, waiting for the queue of tasks to drain. In the next days, a new version of the ATLAS simulation will be used and a campaign of simulation corresponding to the new accelerator conditions will be launched. We shall keep you informed!

o Taking advantage of the new simulation campaign, a updated version of the vboxwrapper will be introduced as well.

Again thank you to all of you for your contribution to the ATLAS simulation effort.

Regards
Click to expand...

http://atlasathome.cern.ch/forum_thread.php?id=281
 
Front page news
Maintenance starting June 18, 10:30 CET
Dear all,

There will be a maintenance operation to get a separate NFS
server VM for ATLAS and Sixtrack tomorrow at 10:30 CET.

We will take care of starting and stopping BOINC. Normally this should
take less than 30 minutes (time to change a DNS alias.)

Regards 17 Jun 2015, 17:12:04 UTC · Comment
Click to expand...
 
Hi all,

Next week (starting 22 Feb) our ATLAS colleagues in the US will get their hands on 100,000 CPU cores from Amazon EC2 for a few days to run ATLAS simulation. In combination with this we are going to push all the other ATLAS resources we have in order to break the record of concurrent simulation tasks running. Can you guys spread the word around to get people to contribute a bit more to ATLAS@Home next week?

You can see the number of tasks running per site for the last month on this page: ATLAS Job Activities (ATLAS@Home is "BOINC"). Thanks in advance for your help!
Click to expand...

Can we beat the ATLAS record?

Caution!!

This project is very resource intensive.
1. Make sure you have at least 2.5GB of RAM/core (or work unit you run). More would be better. Faster the RAM the better the results too.
2. Make sure you have a stable internet connection
3. If you have data limits you may want to avoid running the project.
4. Do NOT interrupt the work units once they start as I have found the work units do NOT seem to respond well to it. If the work units fail, they may or may not auto abort.
5. You need to have VT-x, AMDv, or SVM turned on in the BIOS.
6. You have to have Virtualbox installed as the BOINC work units will run a Virtualbox instance for each work unit.
7. Unless you have an app_config file set up to limit the number of work units, BOINC may try to download and run work units up to the number of cores/threads that you have allowed BOINC to use in your preferences.
 
You must log in or register to reply here.
Back
Top