Message boards : Number crunching : Actual LHC data to crunch?
Message board moderation

To post messages, you must log in.

Previous · 1 · 2

AuthorMessage
Profile Ocean Archer
Avatar

Send message
Joined: 13 Jul 05
Posts: 143
Credit: 263,300
RAC: 0
Message 20380 - Posted: 15 Sep 2008, 15:47:18 UTC

Dagorath --

Is it possible that the fourth and fifth crunchers are not continuously attached to the Internet? Perhaps they connect only once a day, or maybe even once every other day, because they utilize a dial-up connection.

I grant you, that the method being used may not be the most efficient, but it does work (most of the time).

Like you, I do not get all the WUs that I can handle, but I do get some, and remember, I FREELY DONATE MY TIME TO THIS PROJECT (among others). Last time I looked, there is nobody holding a revolver to my head, and forcing me to make time available on my machines. I am here BY MY OWN CHOICE. If I feel at any time, that my services are being mis-used, there\'s a button on the PROJECTS page of BOINC called DETACH ... I understand it works very well




If I've lived this long, I've gotta be that old
ID: 20380 · Report as offensive     Reply Quote
Grutte Pier [Wa oars]~GP500

Send message
Joined: 22 Jan 06
Posts: 21
Credit: 125,903
RAC: 0
Message 20383 - Posted: 15 Sep 2008, 19:31:54 UTC

1/ no money:

it could actually save money, by not letting it on the grid you save computing power.

2/ subsets wu\'s : why can\'t they be split up, 10 MB peaces.


3/ person to do so, see point 1.



\"To get money you have too spend money.\"



ID: 20383 · Report as offensive     Reply Quote
computerguy09

Send message
Joined: 26 Oct 04
Posts: 6
Credit: 1,696,248
RAC: 0
Message 20510 - Posted: 24 Sep 2008, 19:43:28 UTC - in response to Message 20383.  

1/ no money:

it could actually save money, by not letting it on the grid you save computing power.

2/ subsets wu\\\'s : why can\\\'t they be split up, 10 MB peaces.


3/ person to do so, see point 1.



\\\"To get money you have too spend money.\\\"



I got several of those WUs recently. And since the machine that I\'ve made available currently to LHC is a slower box, I wasn\'t one of the first to complete a WU. My machine checks in with LHC@HOME frequently, and so got the request from the server to cancel the processing of that WU.

So, even though some of the \"extra\" time wasn\'t used, the project was nice enough to let me know it didn\'t need it. That\'s better than letting me finish the whole WU and then not give me credit. It\'s a good balance.

Mark
ID: 20510 · Report as offensive     Reply Quote
Speedy

Send message
Joined: 28 Jul 05
Posts: 37
Credit: 451,635
RAC: 20
Message 20662 - Posted: 16 Oct 2008, 1:21:46 UTC
Last modified: 16 Oct 2008, 1:23:55 UTC

I was searching around on the net and I found a Cern Press Release Witch says they are processing 250,000 jobs a day. I just wish we had big enough processes to help. What ever work this project gives me i\'m glad to crunch, I\'ve had 3 work units today so far.
speedy

Have A Crunching Good day
ID: 20662 · Report as offensive     Reply Quote
Klimax

Send message
Joined: 27 Apr 07
Posts: 18
Credit: 9,970
RAC: 0
Message 20672 - Posted: 19 Oct 2008, 6:52:56 UTC

Is it not possible to split data as EAH did?They have huge amount of data from all detectors,which they split into number of small batches.

Or required set of data for each WU is still too big?(Like it has to have data from all instruments used for collecting data)

I think that since there are going to be many runs/collisions,that each one might not to be so data-intesive,so each WU could be then one/two runs.
ID: 20672 · Report as offensive     Reply Quote
tullio

Send message
Joined: 19 Feb 08
Posts: 708
Credit: 4,336,250
RAC: 0
Message 20674 - Posted: 19 Oct 2008, 13:02:18 UTC

I don\'t think it is a technical problem but a mentality problem. Being a (retired) physicist myself, I know they don\'t want, as a class, to give their precious data to the populace. But they shall have to do it. See David Anderson\'s article posted on the BOINC home page.
Tullio
ID: 20674 · Report as offensive     Reply Quote
tullio

Send message
Joined: 19 Feb 08
Posts: 708
Credit: 4,336,250
RAC: 0
Message 20676 - Posted: 19 Oct 2008, 18:29:53 UTC - in response to Message 20675.  
Last modified: 19 Oct 2008, 18:31:44 UTC

I don\\\\\\\'t think it is a technical problem but a mentality problem.


Wrong. It\\\'s a technical problem. We simply don\\\'t have the bandwidth. They have already explained that. When is it going to sink in?


My ADSL has 7 Mbit/s, but big cities in Italy reach 20 Mbit/s. Fastweb is offering fiber to the home in selected cities. Once fiber is installed there is no limit to bandwidth.
Tullio
ID: 20676 · Report as offensive     Reply Quote
tullio

Send message
Joined: 19 Feb 08
Posts: 708
Credit: 4,336,250
RAC: 0
Message 20678 - Posted: 19 Oct 2008, 21:36:41 UTC - in response to Message 20677.  

I don\\\\\\\'t think it is a technical problem but a mentality problem.


Wrong. It\\\\\\\'s a technical problem. We simply don\\\\\\\'t have the bandwidth. They have already explained that. When is it going to sink in?


My ADSL has 7 Mbit/s, but big cities in Italy reach 20 Mbit/s.


Apparently the IT people at CERN think that\\\\\\\'s not enough. Do you know something they don\\\\\\\'t know?

Fastweb is offering fiber to the home in selected cities. Once fiber is installed there is no limit to bandwidth.
Tullio


Wonderful! When enough BOINCer get fibre to their homes and a GPU in their box CERN might change their policy. The reality of today\\\\\\\'s world is that CERN thinks our resources are inadquate and they are probably right. So why not crunch some other worthy projects along with the LHC tasks you get and be happy about it.


I am crunching Einstein@home, QMC@home, climateprediction.net, CPDN Beta and SETI@home on my AMD Opteron 1210 running Linux at 1.8 GHz. Cheers.
Tullio
ID: 20678 · Report as offensive     Reply Quote
Toby Broom
Volunteer moderator

Send message
Joined: 27 Sep 08
Posts: 798
Credit: 644,806,690
RAC: 229,904
Message 20702 - Posted: 27 Oct 2008, 22:14:14 UTC

It\\\'s a shame we can\\\'t crunch actual LHC data, the ~ 2Tflops that the user contribute isn\\\'t bad, if everyone gave 1Gb of space there would eb a few Tb of storage.
ID: 20702 · Report as offensive     Reply Quote
Previous · 1 · 2

Message boards : Number crunching : Actual LHC data to crunch?


©2024 CERN