Message boards :
Number crunching :
canceled deadline because of re-sent function
Message board moderation
Author | Message |
---|---|
Sutaru Tsureku Send message Joined: 6 Apr 07 Posts: 7105 Credit: 147,663,825 RAC: 5 |
I looked to the WUs/results of one of my machines and found something strange. The machine DLed two .vlar WUs (normally nothing unusual ;-) , but they had only ~ 7 mins deadline.. - hmm.. what? 8-O wuid=728232605 wuid=728232450 Hmm.. - this destroy the daily WU quota - normally not a big deal, but if this will happen more times.. then yes. :-| Why happened this? Is somewhere maybe a bigger problem (S@h server)? - Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. - |
Josef W. Segur Send message Joined: 30 Oct 99 Posts: 4504 Credit: 1,414,761 RAC: 0 |
At 18 Apr 2011 19:04:11 UTC the Scheduler tried to tell your host to download those WUs for CPU, but something went wrong and they were ghosted. At about 18 Apr 2011 19:10:57 UTC the host again asked for work, at least partially for GPU work. The resend lost results logic kicked in and considered sending those VLARs to your GPU, but because that's not allowed it instead expired them immediately so another host will do the work. The method of keeping VLARs off CUDA GPUs does not have the additional complexity needed to see if the request is also asking for CPU work and shift to that. I doubt if Dr. Anderson would consider it a large enough issue to justify spending time figuring out and implementing changes to fix it. Joe |
Dimly Lit Lightbulb 😀 Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1 |
This isn't a vlar but the run time is a bit comical. http://setiathome.berkeley.edu/workunit.php?wuid=723808560 |
-BeNt- Send message Joined: 17 Oct 99 Posts: 1234 Credit: 10,116,112 RAC: 0 |
This isn't a vlar but the run time is a bit comical. http://setiathome.berkeley.edu/workunit.php?wuid=723808560 Not as funny as mine! 9 seconds and it validated with someone else. http://setiathome.berkeley.edu/workunit.php?wuid=727194627 Traveling through space at ~67,000mph! |
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
|
Dimly Lit Lightbulb 😀 Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1 |
Not as funny as mine! 9 seconds and it validated with someone else. Nine seconds? *shakes head* :) |
Sutaru Tsureku Send message Joined: 6 Apr 07 Posts: 7105 Credit: 147,663,825 RAC: 5 |
Please stay on topic. At 18 Apr 2011 19:04:11 UTC the Scheduler tried to tell your host to download those WUs for CPU, but something went wrong and they were ghosted. At about 18 Apr 2011 19:10:57 UTC the host again asked for work, at least partially for GPU work. The resend lost results logic kicked in and considered sending those VLARs to your GPU, but because that's not allowed it instead expired them immediately so another host will do the work. Thanks! I looked now to the stdoutdae file and found: . .. 18-Apr-2011 21:03:31 [SETI@home] Reporting 1 completed tasks, requesting new tasks for CPU and NVIDIA GPU 18-Apr-2011 21:03:34 [SETI@home] Finished upload of 19au10ab.18697.22348.14.10.74_2_0 18-Apr-2011 21:04:28 [SETI@home] Computation for task 19au10ab.18697.22348.14.10.246_2 finished 18-Apr-2011 21:04:28 [SETI@home] Starting 19au10ab.18697.22348.14.10.241_2 18-Apr-2011 21:04:28 [SETI@home] Starting task 19au10ab.18697.22348.14.10.241_2 using setiathome_enhanced version 609 18-Apr-2011 21:04:30 [SETI@home] Started upload of 19au10ab.18697.22348.14.10.246_2_0 18-Apr-2011 21:04:37 [SETI@home] Finished upload of 19au10ab.18697.22348.14.10.246_2_0 18-Apr-2011 21:09:10 [SETI@home] Scheduler request failed: Timeout was reached 18-Apr-2011 21:09:22 [---] Project communication failed: attempting access to reference site 18-Apr-2011 21:09:24 [---] Internet access OK - project servers may be temporarily down. 18-Apr-2011 21:10:15 [SETI@home] Reporting 3 completed tasks, requesting new tasks for CPU and NVIDIA GPU 18-Apr-2011 21:10:16 [SETI@home] Computation for task 19au10ab.18697.22348.14.10.241_2 finished 18-Apr-2011 21:10:16 [SETI@home] Starting 19au10ab.18697.22348.14.10.179_2 18-Apr-2011 21:10:16 [SETI@home] Starting task 19au10ab.18697.22348.14.10.179_2 using setiathome_enhanced version 609 18-Apr-2011 21:10:19 [SETI@home] Started upload of 19au10ab.18697.22348.14.10.241_2_0 18-Apr-2011 21:10:54 [SETI@home] Finished upload of 19au10ab.18697.22348.14.10.241_2_0 18-Apr-2011 21:11:05 [SETI@home] Scheduler request completed: got 20 new tasks 18-Apr-2011 21:11:05 [SETI@home] Didn't resend lost task 03dc10ac.13650.3339.11.10.174.vlar_1 (expired) 18-Apr-2011 21:11:05 [SETI@home] Didn't resend lost task 03dc10ac.13650.3339.11.10.220.vlar_1 (expired) 18-Apr-2011 21:11:05 [SETI@home] Resent lost task 19se10ab.6555.1703.15.10.204_1 18-Apr-2011 21:11:05 [SETI@home] Resent lost task 11se10ab.12905.1294.16.10.76_1 .. . [UTC + 02:00, Germany currently MEST] If this happens very rarely, hmm.. O.K., but if this will happen more times and not only on my hosts ;-) , hmm - then maybe Dr. Anderson should look to it.. Members, tell us your same experiences.. - Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. - |
aaronh Send message Joined: 27 Oct 99 Posts: 169 Credit: 1,442,686 RAC: 0 |
<offtopic> Nine seconds is slow!Not as funny as mine! 9 seconds and it validated with someone else.Nine seconds? *shakes head* :) My quickest WU currently validated is an overflowed GPU task with 7.18 seconds runtime (1.17 seconds CPU). Unvalidated, also a GPU task that overflowed at 6.18 seconds.</offtopic> |
Sutaru Tsureku Send message Joined: 6 Apr 07 Posts: 7105 Credit: 147,663,825 RAC: 5 |
Please stay on topic. If you would like to talk about 'who have the fastest -9 overflow result', feel free and open a new thread. EDIT of the title of this thread from: .vlar WUs with ~ 7 mins deadline? to: canceled deadline because of re-sent function - Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. - |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Please stay on topic. This is the same item that was brought up in another thread at the end of March. I think having resend enabled and a few ghost vlar tasks getting expired is better than not having resend enabled. I did a test with a VLAR task that was sent to my ATI GPU. Workunit 727623280 and it looks like ATI GPUs doesn't get the VLAR GPU instant timeout applied to them. 4/19/2011 8:39:33 PM SETI@home Message from server: Resent lost task 19fe11af.18246.53611.7.10.166.vlar_0 SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Kevin Olley Send message Joined: 3 Aug 99 Posts: 906 Credit: 261,085,289 RAC: 572 |
That sounds good to me, Since then I have had no more occurances of extremely short timed WU's, VLAR or normal. I only use 3 cores on my CPU (99% of the processors), and I only do VLAR's or AP's on these cores, all normal or VHAR's are Rescheduled to GPU's, so since then I have seen a few VLAR's come and go. Kevin |
©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.