Message boards :
Number crunching :
Looooong WU time
Message board moderation
Author | Message |
---|---|
Send message Joined: 15 Jul 11 Posts: 1 Credit: 27,596,442 RAC: 5,880 |
I just received a WU that I aborted due to an 11 day completion time. It came in and took over my system running both CPU's at high priority: 8/28/2011 12:04:53 PM | Milkyway@home | Sending scheduler request: To fetch work. 8/28/2011 12:04:53 PM | Milkyway@home | Requesting new tasks for CPU 8/28/2011 12:04:54 PM | Milkyway@home | Scheduler request completed: got 1 new tasks 8/28/2011 12:04:57 PM | Milkyway@home | Starting task ps_nbody_test3_1898001_0 using milkyway_nbody version 66 It estimated 1031 hours to complete .when I got it |
Send message Joined: 28 Mar 09 Posts: 68 Credit: 1,003,982,681 RAC: 0 |
I've had the same problem with n-body workunits. Thought it was only me. After 12hrs on 8 cores only 50% done, etc. I also just abort them. Had one that slipped by and took 19000 seconds to finish and it validated as well. Then the next dozen will take the "normal" time of 3 to 24 minutes. Been happening for the past two weeks and I have been changing memory, updating Boinc, etc. to no avail. Glad I'm not the only one. |
Send message Joined: 12 Nov 07 Posts: 2425 Credit: 524,164 RAC: 0 |
The Nbody estimates are waaayyyyy off. I get 5-600 hours estimate and they complete in 20 min to 40 hours. No way to tell aside from running the tasks. Doesn't expecting the unexpected make the unexpected the expected? If it makes sense, DON'T do it. |
©2024 Astroinformatics Group