Report all problems here...........

Message boards : Number crunching : Report all problems here...........
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · 9 · 10 · Next

AuthorMessage
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 1014205 - Posted: 10 Jul 2010, 7:53:16 UTC - in response to Message 1014203.  

Anybody else test this yet?
I am hoping that the limit may be lifted in the morning and I will not have to resort to transferring VLARs back to my GPUs. But, as they are crunch-only rigs, I could do so and not have to worry about the slowdown caused by VLAR work being done by the GPU....


just abort them in this situation. sorry wingmen but is what the project has forced us to do if you want gpu work, i don't feel guilty doing it anymore.

unless it is during the 3D outage, then it may be beneficial...

I refuse to abort them....just against my policy of not cherry picking Seti work...somebody's gotta crunch them and if the servers send 'em my way I will do so.
I had enough GPU work to get through the outage, but now that we are in the recovery phase and the CPU/GPU limit split did not work quite the way it was intended, they are waiting on the lifting of the limit to cache up again.

And it's quite possible, depending on the work mix being issued when that happens, that they may get a snootfull of VLARs anyway.

At some point, they will probably have to process some.
And at some point, the Lunatics crew will probably get a better handle on getting the GPUs to deal with them without such a processing penalty.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1014205 · Report as offensive
Profile Link
Avatar

Send message
Joined: 18 Sep 03
Posts: 834
Credit: 1,807,369
RAC: 0
Germany
Message 1014206 - Posted: 10 Jul 2010, 7:54:03 UTC - in response to Message 1013913.  

Has anyone of you tried what I have written above? I have done something similar with ready crunched WUs, when we had upload problems.

Any Ghost WUs shown in the task lists probably do not affect the limits. AFAICT the limit logic does not do a database query to find out how many are in progress (that would be expensive like the "resend lost work" feature). So it is based on information in the request, IOW the work the host does know about.
                                                                  Joe

If the information is taken from the request, then anyone who like experiments and knows how to edit the client_state could "move out" all (or at least most) of the VLARs and later move them back (after he got some WUs for the GPU).


ID: 1014206 · Report as offensive
Profile MadMaC
Volunteer tester
Avatar

Send message
Joined: 4 Apr 01
Posts: 201
Credit: 47,158,217
RAC: 0
United Kingdom
Message 1014218 - Posted: 10 Jul 2010, 8:35:24 UTC

I think editing the client_state is beyond most people here...

ID: 1014218 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 1014220 - Posted: 10 Jul 2010, 8:40:15 UTC - in response to Message 1014218.  

I think editing the client_state is beyond most people here...

And probably should be, as one slip can wipe out your Boinc installation.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1014220 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 19012
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1014222 - Posted: 10 Jul 2010, 8:48:30 UTC
Last modified: 10 Jul 2010, 8:49:13 UTC

It's all lies,

10/07/2010 09:37:29 SETI@home Requesting new tasks for CPU
10/07/2010 09:37:34 SETI@home Scheduler request completed: got 1 new tasks
10/07/2010 09:37:36 SETI@home Started download of ap_05no09ah_B5_P0_00009_20100709_08745.wu
10/07/2010 09:37:49 SETI@home Sending scheduler request: To fetch work.
10/07/2010 09:37:49 SETI@home Requesting new tasks for CPU
10/07/2010 09:37:55 SETI@home Scheduler request completed: got 0 new tasks
10/07/2010 09:37:55 SETI@home Message from server: No work sent
10/07/2010 09:37:55 SETI@home Message from server: This computer has reached a limit on tasks in progress
10/07/2010 09:38:02 SETI@home Finished download of ap_05no09ah_B5_P0_00009_20100709_08745.wu

But Application Details says

SETI@home Enhanced (anonymous platform, nvidia GPU)
Number of tasks completed 21683
Max tasks per day 187
Number of tasks today 0
Consecutive valid tasks 91
Average turnaround time 11.34 days

Astropulse v505 (anonymous platform, CPU)
Number of tasks completed 0
Max tasks per day 100
Number of tasks today 1
Consecutive valid tasks 0
Average turnaround time 0.00 days

As the AP V505 'Number of tasks today' is the one d/load as shown in msg's. Then why the "Message from server: This computer has reached a limit on tasks in progress"

Me thinks someone or something has lost his/her/its logic.

edit] Times sre UTC+1
ID: 1014222 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 1014233 - Posted: 10 Jul 2010, 9:09:53 UTC - in response to Message 1014222.  

Me thinks someone or something has lost his/her/its logic.

Yes, it's you ;-)

The message has nothing to do with the application details but with the 5-tasks-per-core/140-tasks-per-machine limits, and that machine has far more than 140 tasks in progress.

Gruß,
Gundolf
Computer sind nicht alles im Leben. (Kleiner Scherz)

SETI@home classic workunits 3,758
SETI@home classic CPU time 66,520 hours
ID: 1014233 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 19012
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1014249 - Posted: 10 Jul 2010, 10:11:09 UTC - in response to Message 1014233.  

Me thinks someone or something has lost his/her/its logic.

Yes, it's you ;-)

The message has nothing to do with the application details but with the 5-tasks-per-core/140-tasks-per-machine limits, and that machine has far more than 140 tasks in progress.

Gruß,
Gundolf

No it doesn't, it has less than 50.

If it did have more than 140 then why did it allow the download a few minutes before I posted?
ID: 1014249 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 1014256 - Posted: 10 Jul 2010, 10:30:18 UTC - in response to Message 1014249.  

No it doesn't, it has less than 50.

If it did have more than 140 then why did it allow the download a few minutes before I posted?

Okay, I can only go by the task list of that host, and there are more than seven pages à twenty tasks in progress.

Does it perhaps have about twenty CPU-tasks aboard? (I won't go through the task list to count them:-)

Gruß,
Gundolf
ID: 1014256 · Report as offensive
W-K 666 Project Donor
Volunteer tester

Send message
Joined: 18 May 99
Posts: 19012
Credit: 40,757,560
RAC: 67
United Kingdom
Message 1014259 - Posted: 10 Jul 2010, 10:36:17 UTC - in response to Message 1014256.  
Last modified: 10 Jul 2010, 10:38:25 UTC

No it doesn't, it has less than 50.

If it did have more than 140 then why did it allow the download a few minutes before I posted?

Okay, I can only go by the task list of that host, and there are more than seven pages à twenty tasks in progress.

Does it perhaps have about twenty CPU-tasks aboard? (I won't go through the task list to count them:-)

Gruß,
Gundolf

The accurate breakdown of tasks is 9 cpu tasks, of which 4 are being crunched, 39 GPU tasks, including the one that is being crunched.

There are also 3 Beta tasks waiting to report, but the Beta servers are still down.

Edit] The cpu tasks that are on the computer, 8 were downloaded yesterday (Berkeley time) and one today.
ID: 1014259 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 1014264 - Posted: 10 Jul 2010, 10:53:33 UTC - in response to Message 1014259.  

The accurate breakdown of tasks is 9 cpu tasks, of which 4 are being crunched, 39 GPU tasks, including the one that is being crunched.

Okay, if we are still talking about the same host (see links in my previous posts) then I'm out of ideas (other than ghosts, see Richard's and Joe's posts). :-(

Gruß,
Gundolf
ID: 1014264 · Report as offensive
Profile hiamps
Volunteer tester
Avatar

Send message
Joined: 23 May 99
Posts: 4292
Credit: 72,971,319
RAC: 0
United States
Message 1014373 - Posted: 10 Jul 2010, 17:32:52 UTC

This error says it is CPU but I can't figure it out. I don't think I have seen this. I have turned all my GPU's to stock and toned down my CPU overclock a lot...

Stderr output
<core_client_version>6.10.58</core_client_version>
<![CDATA[
<message>
- exit code -6 (0xfffffffa)
</message>
<stderr_txt>
setiathome_CUDA: Found 3 CUDA device(s):
Device 1: GeForce GTX 285, 1007 MiB, regsPerBlock 16384
computeCap 1.3, multiProcs 30
clockRate = 1476000
Device 2: GeForce GTX 260, 879 MiB, regsPerBlock 16384
computeCap 1.3, multiProcs 27
clockRate = 1242000
Device 3: GeForce GTX 275, 879 MiB, regsPerBlock 16384
computeCap 1.3, multiProcs 30
clockRate = 1476000
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce GTX 285 is okay
SETI@home using CUDA accelerated device GeForce GTX 285
Priority of process raised successfully
Priority of worker thread raised successfully
size 8 fft, is a freaky powerspectrum
size 16 fft, is a cufft plan
size 32 fft, is a cufft plan
size 64 fft, is a cufft plan
size 128 fft, is a cufft plan
size 256 fft, is a freaky powerspectrum
size 512 fft, is a freaky powerspectrum
size 1024 fft, is a freaky powerspectrum
size 2048 fft, is a cufft plan
size 4096 fft, is a cufft plan
size 8192 fft, is a cufft plan
size 16384 fft, is a cufft plan
size 32768 fft, is a cufft plan
size 65536 fft, is a cufft plan
size 131072 fft, is a cufft plan

) _ _ _)_ o _ _
(__ (_( ) ) (_( (_ ( (_ (
not bad for a human... _)

Multibeam x32f Preview, Cuda 3.1

Work Unit Info:
...............
WU true angle range is : 0.448164
SETI@home error -6 Bad workunit header
!swi.data_type || !found || !swi.nsamples
File: ..\seti_header.cpp
Line: 204


</stderr_txt>
]]>

Official Abuser of Boinc Buttons...
And no good credit hound!
ID: 1014373 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 1014386 - Posted: 10 Jul 2010, 17:56:44 UTC - in response to Message 1014373.  
Last modified: 10 Jul 2010, 17:57:34 UTC

This error says it is CPU but I can't figure it out.

Nope, it's GPU:
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce GTX 285 is okay
SETI@home using CUDA accelerated device GeForce GTX 285
...............
WU true angle range is : 0.448164
SETI@home error -6 Bad workunit header
!swi.data_type || !found || !swi.nsamples
File: ..\seti_header.cpp
Line: 204


</stderr_txt>
]]>

And somehow, the other text doesn't sound like stock, but that's just a feeling.

-6 is normally a VLARkill, but 0.44 is not VLAR.

Gruß,
Gundolf
ID: 1014386 · Report as offensive
Profile hiamps
Volunteer tester
Avatar

Send message
Joined: 23 May 99
Posts: 4292
Credit: 72,971,319
RAC: 0
United States
Message 1014398 - Posted: 10 Jul 2010, 18:40:03 UTC - in response to Message 1014386.  

This error says it is CPU but I can't figure it out.

Nope, it's GPU:
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce GTX 285 is okay
SETI@home using CUDA accelerated device GeForce GTX 285
...............
WU true angle range is : 0.448164
SETI@home error -6 Bad workunit header
!swi.data_type || !found || !swi.nsamples
File: ..\seti_header.cpp
Line: 204


</stderr_txt>
]]>

And somehow, the other text doesn't sound like stock, but that's just a feeling.

-6 is normally a VLARkill, but 0.44 is not VLAR.

Gruß,
Gundolf

A strange one...I do not use the VLarKill so it can't be that...

1652179463 630363314 6 Jul 2010 15:14:55 UTC 9 Jul 2010 20:41:22 UTC Error while computing 0.00 0.00 --- SETI@home Enhanced
Anonymous platform (CPU)
Official Abuser of Boinc Buttons...
And no good credit hound!
ID: 1014398 · Report as offensive
Garry Webb

Send message
Joined: 25 Aug 99
Posts: 40
Credit: 13,561,408
RAC: 0
United States
Message 1014408 - Posted: 10 Jul 2010, 19:07:03 UTC

Having major problems with one of my cuda machines. I detached the nasty little bugger from the project so that the tasks could be reassigned. I truely did not want to do this, however it is better that some one else have the opportunity to do the work while I get this old machine back up to functiong properly.
ID: 1014408 · Report as offensive
Profile perryjay
Volunteer tester
Avatar

Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 20,676,751
RAC: 0
United States
Message 1014414 - Posted: 10 Jul 2010, 19:21:18 UTC - in response to Message 1014408.  

Here's hoping you get it back up and crunching while you can still get work before the next outage.


PROUD MEMBER OF Team Starfire World BOINC
ID: 1014414 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1014482 - Posted: 10 Jul 2010, 22:27:50 UTC

Just had 4 hours of severe thunderstorms. Had to close everything down.
If you live in the North of The Netherlands, be warned. It's really bad what's coming towards you.

Earlier today I had already set to only do work between 8pm and 9am, as during the day, with living room temps in the 30s Celsius it's not nice to have PCs add heat to that. ;-)
ID: 1014482 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1014488 - Posted: 10 Jul 2010, 22:46:39 UTC - in response to Message 1014482.  
Last modified: 10 Jul 2010, 22:47:01 UTC

with living room temps in the 30s Celsius it's not nice to have PCs add heat to that. ;-)

I think the temperature in my room has only dropped below 28°c 4 or 5 times so far this year. Most of the time it's around 32°c
Grant
Darwin NT
ID: 1014488 · Report as offensive
Josef W. Segur
Volunteer developer
Volunteer tester

Send message
Joined: 30 Oct 99
Posts: 4504
Credit: 1,414,761
RAC: 0
United States
Message 1014494 - Posted: 10 Jul 2010, 23:09:10 UTC - in response to Message 1014373.  

...
SETI@home error -6 Bad workunit header
!swi.data_type || !found || !swi.nsamples
File: ..\seti_header.cpp
Line: 204
...

That is a true Bad workunit header error. Because two other hosts did not see the error, IMO the most likely explanation is the WU file got corrupted somehow. Less likely, though of course possible, is a bug in the x32f build you're testing for Jason. The servers of course only know it was sent to be done on CPU, not that you had Rescheduled it to GPU.
                                                              Joe
ID: 1014494 · Report as offensive
Garry Webb

Send message
Joined: 25 Aug 99
Posts: 40
Credit: 13,561,408
RAC: 0
United States
Message 1014498 - Posted: 10 Jul 2010, 23:22:31 UTC - in response to Message 1014413.  

The VLAR kills were early work before I installed the no kill version of Lunatics.

The problem seems to be the computer itself. Not the nvidia card. It kept stopping processing and gave a msg that nvp 4 was at fault. Soo, suspect that the nvidia program was causing the computer to malfunction. Still working on the OS.
ID: 1014498 · Report as offensive
Garry Webb

Send message
Joined: 25 Aug 99
Posts: 40
Credit: 13,561,408
RAC: 0
United States
Message 1014499 - Posted: 10 Jul 2010, 23:26:36 UTC - in response to Message 1014414.  

Probably not, That's Ok though. I have two others that will not cache more than a days worth of wu's with the extra wu cache set at 10 days.

Berk says I have reached my daily limit on those two.
ID: 1014499 · Report as offensive
Previous · 1 . . . 4 · 5 · 6 · 7 · 8 · 9 · 10 · Next

Message boards : Number crunching : Report all problems here...........


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.