Request for more crunching in next week or two


Advanced search

Message boards : News : Request for more crunching in next week or two

1 · 2 · Next
Author Message
David Cameron
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 13 May 14
Posts: 252
Credit: 2,028,082
RAC: 0
    
Message 1321 - Posted: 15 Nov 2014, 14:38:35 UTC

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!

Profile Yeti
Avatar
Send message
Joined: 20 Jul 14
Posts: 699
Credit: 22,597,832
RAC: 1
    
Message 1324 - Posted: 15 Nov 2014, 23:23:45 UTC

I have posted your request in 3 bigger crunching communities, perhaps we can activate some more crunching by this.

But, it is not easy, to find crunchers with x64 boxes, that are willing to install / use VirtualBox with 2 GB RAM per Task and have to accept that your WU Downloads more data from Internet itself ...

So far, as I know, these are the hardest conditions for crunchers among all boinc-projects. That makes it not easy to motivate more crunchers

Profile MAGIC Quantum Mechanic
Avatar
Send message
Joined: 4 Jul 14
Posts: 331
Credit: 485,372
RAC: 0
    
Message 1325 - Posted: 16 Nov 2014, 3:22:38 UTC

The regulars here are running 24/7 for you David

The longer tasks do take a while but the current version is running for me with no problems.
____________

Toby Broom
Send message
Joined: 1 Jul 14
Posts: 70
Credit: 12,032,688
RAC: 0
    
Message 1326 - Posted: 16 Nov 2014, 4:17:35 UTC

Put more cores to work, will add some more machines tomorrow

Toby Broom
Send message
Joined: 1 Jul 14
Posts: 70
Credit: 12,032,688
RAC: 0
    
Message 1327 - Posted: 16 Nov 2014, 4:17:37 UTC

Put more cores to work, will add some more machines tomorrow

Profile tullio
Send message
Joined: 27 Jun 14
Posts: 256
Credit: 289,886
RAC: 0
    
Message 1328 - Posted: 16 Nov 2014, 5:09:49 UTC

Don't shoot the cruncher, he does what he can.
Tullio

Profile Yeti
Avatar
Send message
Joined: 20 Jul 14
Posts: 699
Credit: 22,597,832
RAC: 1
    
Message 1329 - Posted: 16 Nov 2014, 8:45:49 UTC - in response to Message 1328.

Don't shoot the cruncher, he does what he can.
Tullio

Same here. I have already dedicated all machines that are capabable for Atlas to crunch Atlas.

Profile Jim1348
Send message
Joined: 15 Nov 14
Posts: 111
Credit: 1,319,885
RAC: 0
    
Message 1330 - Posted: 16 Nov 2014, 9:17:10 UTC

I just happened to join yesterday. So I now have 3 Haswell cores on it, and will add more when an additional 8 GB of DDR3 memory arrives. I am glad to find a project that makes good use of it.

Profile Phil1966
Send message
Joined: 14 Jun 14
Posts: 39
Credit: 1,185,758
RAC: 0
    
Message 1331 - Posted: 16 Nov 2014, 11:48:03 UTC

Hello !

Your message was forwarded on "L'Alliance Francophone"'s forums by Modesti.

Have dedicated 7 threads of my 4770K to ATLAS, but not easy to identify which WU
consumes small amount of CPU ...

Will check outcome in about 1 hour and post info here.

After 15 mins, 7 WUs, CPU use still very low.

Best,

Phil1966

Profile Phil1966
Send message
Joined: 14 Jun 14
Posts: 39
Credit: 1,185,758
RAC: 0
    
Message 1332 - Posted: 16 Nov 2014, 12:43:48 UTC
Last modified: 16 Nov 2014, 12:50:00 UTC

Crunchbox =

MB : ASUS Z87 PRO / BIOS 2103
CPU : i7 4770K @ 3.9 Ghz
WC AIO : Cooler Master 120V
RAM : DDR3 Corsair vengeance 2 x 8 go 1600 Mhz CL10 LP
W7 Ultimate
BOINC : 7.4.27
VB : 4.3.12 r937333

Running 7 WU's since 1 hour

RAM use : 12.4 / 13 Go
CPU use : Min 45 % - Max 75 % / AVG 65 % only
CPU Temp : 40°
CPU Power use : 70W
MB : Temp : 44° = 14° hother than usually / normaly !

Progress : about 5 %

NB last core supports a GPU project, with low CPU use.

rbpeake
Send message
Joined: 27 Jun 14
Posts: 86
Credit: 8,794,961
RAC: 0
    
Message 1339 - Posted: 17 Nov 2014, 16:26:25 UTC - in response to Message 1321.
Last modified: 17 Nov 2014, 16:28:20 UTC

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.

Does this mean you have validated the results obtained from BOINC (completed your validation study)?

Thanks!

David Cameron
Project administrator
Project developer
Project tester
Project scientist
Send message
Joined: 13 May 14
Posts: 252
Credit: 2,028,082
RAC: 0
    
Message 1340 - Posted: 17 Nov 2014, 18:46:28 UTC - in response to Message 1339.

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.

Does this mean you have validated the results obtained from BOINC (completed your validation study)?

Thanks!


Not yet. There are around 6000 WU left to process which are part of this particular validation study, but this one turns out to be more urgent than the others, hence the request for more crunchers.

Toby Broom
Send message
Joined: 1 Jul 14
Posts: 70
Credit: 12,032,688
RAC: 0
    
Message 1346 - Posted: 18 Nov 2014, 0:52:46 UTC

I added a couple more machine, that are high power.

Toby Broom
Send message
Joined: 1 Jul 14
Posts: 70
Credit: 12,032,688
RAC: 0
    
Message 1395 - Posted: 21 Nov 2014, 13:12:13 UTC

How are we doing on the 7000?

Tom*
Send message
Joined: 28 Jun 14
Posts: 118
Credit: 8,761,428
RAC: 1
    
Message 1397 - Posted: 21 Nov 2014, 15:03:51 UTC

With the large increase in validate errors and four retries/resends I hope the

7000 doesn't turn into the 28000.:-( Even though the errors only take 15

minutes, or worse that the errors are a new issue?

Profile Jim1348
Send message
Joined: 15 Nov 14
Posts: 111
Credit: 1,319,885
RAC: 0
    
Message 1398 - Posted: 21 Nov 2014, 16:53:17 UTC - in response to Message 1397.
Last modified: 21 Nov 2014, 16:54:31 UTC

I got 4 validate errors on work units that finished about 01:30 local time, and got a BSOD and reboot at the same time. Maybe running BOINC as a service would help?

Note: all the others who got these WUs errored out too.

Profile Yeti
Avatar
Send message
Joined: 20 Jul 14
Posts: 699
Credit: 22,597,832
RAC: 1
    
Message 1399 - Posted: 21 Nov 2014, 17:05:01 UTC - in response to Message 1398.

The ratio from WU-Time to CPU-Time is not okay at your results

Did you change anything at 19./20. this month?

Profile Jim1348
Send message
Joined: 15 Nov 14
Posts: 111
Credit: 1,319,885
RAC: 0
    
Message 1400 - Posted: 21 Nov 2014, 17:32:46 UTC - in response to Message 1399.
Last modified: 21 Nov 2014, 17:48:38 UTC

It is probably because I started running CPU projects on six cores of my i7-4771 (though ATLAS was limited to 5 cores), plus using two others to support my HD 7790s on Einstein. I was originally on only 4 cores, and am now limiting it to that again, mainly to see if that prevents BSODs. If necessary, I will try a service install. I can't afford BSODs on this machine.

Profile MAGIC Quantum Mechanic
Avatar
Send message
Joined: 4 Jul 14
Posts: 331
Credit: 485,372
RAC: 0
    
Message 1401 - Posted: 21 Nov 2014, 22:21:19 UTC

Task Status

It looks like all the tasks I have running right now are the longer ones but once they finish there should still be quite a few left.

Toby Broom
Send message
Joined: 1 Jul 14
Posts: 70
Credit: 12,032,688
RAC: 0
    
Message 1403 - Posted: 21 Nov 2014, 23:26:43 UTC - in response to Message 1398.

I find running BOINC as service is bad news

1 · 2 · Next

Message boards : News : Request for more crunching in next week or two