app reporting negative CPU
Message boards :
Number crunching :
app reporting negative CPU
Message board moderation
| Author | Message |
|---|---|
zombie67 [MM] Send message Joined: 29 Aug 11 Posts: 38 Credit: 13,384,348 RAC: 0 
        
|
I wonder if this is a clue for why the CPU time is so under-reported, which leads to credits being under awarded? Notice how small the CPU time is compared with the run time? This is with a 6 core machine, so CPU time *should* be ~5-6x the run time. This is the task info: http://yafu.dyndns.org/yafu/result.php?resultid=654613 Name yafu_C106_1330051806_419_0 This is what the messages tab says: Sun 26 Feb 2012 08:42:31 AM PST yafu Starting yafu_C105_1330175706_21_0 Reno, NV Team: SETI.USA 
|
 yoyo_rknVolunteer moderator Project administrator Project developer Project tester Volunteer developer Volunteer tester Project scientist Send message Joined: 22 Aug 11 Posts: 725 Credit: 16,445,605 RAC: 1 
    
|
1) Don't know why a negative CPU is reported. The App doesn't do it. 2) As I understand David, the CPU time is not used to calculate the creditnew. They use elapsed time. yoyo |
|
zombie67 [MM] Send message Joined: 29 Aug 11 Posts: 38 Credit: 13,384,348 RAC: 0
|
1) Don't know why a negative CPU is reported. The App doesn't do it. Okay. That is just the message that BOINC is saying "app reporting negative CPU". But something is obviously wrong for BOINC to be saying that, right? 2) As I understand David, the CPU time is not used to calculate the creditnew. They use elapsed time. CreditNew has to account for the multiple CPUs somehow, right? Otherwise a machine using a single CPU for (say) 4 hours, vs. a machine using 4 CPUs for 4 hours, vs. a machine using 8 CPUs for 4 hours, all three would be awarded the same credit. So how are multiple CPUs accounted for with MT tasks, if not from the CPU time? Reno, NV Team: SETI.USA
|
|
yoyo_rkn Volunteer moderator Project administrator Project developer Project tester Volunteer developer Volunteer tester Project scientist Send message Joined: 22 Aug 11 Posts: 725 Credit: 16,445,605 RAC: 1
|
David wrotes, that CPU time isn't considered by creditnew. Creditnew just uses elapsed time. I didn't implemented creditnew and do not exactly know how it works, but david stated that it works also for MT apps. I could for instance use elapsed time and multiply this by number of cores if the MT plan class is used. yoyo |
|
zombie67 [MM] Send message Joined: 29 Aug 11 Posts: 38 Credit: 13,384,348 RAC: 0
|
Hi Yoyo, I read those messages. And after reviewing the numbers a bit more, I think DA is right. CPU time is not considered. Thanks for looking into this! But something seriously funky is going on. Here are the results from one of my machines that has been running long enough for "credit learning" to have stabilized. It is a 6 thread machine. I took the last 20 valid tasks, stuck them in a spreadsheet, and then sorted by credit/hour/thread. Notice the CPU time does not correlate at all. But also notice the highest c/h/t is ~4x the lowest. How can that possibly be? I know DA said that CreditNew "makes no promises about individual jobs or about credit/hour", but 4x variation? Without rhyme or reason? This is ridiculous! I know, not your problem. You are just running the stock code. I guess I am just venting about CreditNew (again). FWIW, POEM tried to implement CreditNew, and had to give up. They switched to fixed credits. Not an option here, of course. Task#___WU#__________Run______CPU___Credit__c/h/t 657265__646256______3.06_____0.00_____0.13__25 657175__646166_____64.18_____4.93_____2.79__26 657191__646182____136.35_____9.21_____5.93__26 657174__646165___2738.73___293.34___119.13__26 657208__646199___3478.18___435.78____151.3__26 657264__646255_____99.31___432.82_____4.32__26 657225__646216___2719.29___440.37___118.29__26 657266__646257______2.04_____0.00_____0.09__26 657207__646198______2.04_____0.00_____0.09__26 657205__646196______2.06_____0.01_____0.17__50 657206__646197___2939.35___438.17___255.66__52 657268__646259_____93.28_____9.55____11.26__72 657269__646260______3.06_____0.01_____0.37__73 657211__646202______2.06_____0.01_____0.25__73 657216__646207____150.39_____8.57____18.33__73 657212__646203______2.04_____0.01_____0.25__74 657210__646201______2.04_____0.01_____0.25__74 657273__646264___2915.89___505.35___376.28__77 657158__646149____148.41____11.55____20.56__83 657160__646151___3046.91___497.82___480.02__95 ________________18548.67__3087.51__1565.47__51 Reno, NV Team: SETI.USA
|
|
Matthias Lehmkuhl Send message Joined: 7 Oct 11 Posts: 33 Credit: 2,093,932 RAC: 2,662
  
|
Have the same on my Win 32bit system 5261 yafu 08.03.2012 08:50:12 app reporting negative CPU: -1.000000 5262 yafu 08.03.2012 08:50:13 app reporting negative CPU: -1.000000 5263 yafu 08.03.2012 08:50:15 app reporting negative CPU: -1.000000 5264 yafu 08.03.2012 08:50:16 app reporting negative CPU: -1.000000 5265 yafu 08.03.2012 08:50:17 app reporting negative CPU: -1.000000 5266 yafu 08.03.2012 08:50:19 app reporting negative CPU: -1.000000 5267 yafu 08.03.2012 08:50:21 app reporting negative CPU: -1.000000 (Source BoincTasks 1.30) and additional the CPU time from this Clients http://yafu.dyndns.org/yafu/show_host_detail.php?hostid=1397 looks odd: 49,608,850,000,000,002,062,079,553,705,230,327,939,012,244,050,246,630,076,053,444,726,129,259,448,365,759,310,372,025,402,006,571,171,104,113,704,985,190,252,068,262,607,526,028,929,981,786,202,945,530,141,718,177,165,791,531,672,456,687,243,103,819,024,234,355,563,543,094,541,295,064,874,358,731,130,323,253,196,581,666,553,856.00 I've seen this only for the 32Bit App YAFU v130.02 (mt) The results are validated with credit. Edit: the shown runtime is normal. Matthias |
|
frankhagen Send message Joined: 2 Sep 11 Posts: 6 Credit: 2,081,426 RAC: 0
|
|
Datenschutz / Privacy Copyright © 2011-2024 Rechenkraft.net e.V. & yoyo