Message boards :
Number crunching :
Results not uploading?
Message board moderation
Author | Message |
---|---|
Send message Joined: 19 Nov 11 Posts: 9 Credit: 112,578 RAC: 0 |
I have pasted 40 lines from my Event Log below. Most of them are from Einstein@Home because they illustrate the difference between E@H and M@H. I draw your attention to the lines in bold. The last two bold E@H lines indicate the resuming and completion of WU ending in 1264_1. These are followed by lines showing upload of the results from that WU. The bold M@H lines also indicate the starting or resuming of WUs, along with lines indicating their completion, but there are no lines indicating upload of results. Would somebody, perhaps a moderator or administrator, please tell us the reason for the difference? TIA 12/3/2011 2:29:41 AM | Milkyway@home | Resuming task nbody-rebuild-clr_327415_3 using milkyway_nbody version 66 12/3/2011 2:50:44 AM | Milkyway@home | Sending scheduler request: To fetch work. 12/3/2011 2:50:44 AM | Milkyway@home | Reporting 1 completed tasks, requesting new tasks for NVIDIA GPU 12/3/2011 2:50:47 AM | Milkyway@home | Scheduler request completed: got 1 new tasks 12/3/2011 2:56:51 AM | Milkyway@home | Computation for task ps_separation_82_2s_coadd_1_5836_0 finished 12/3/2011 2:56:51 AM | Einstein@Home | Restarting task p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1 using einsteinbinary_BRP4 version 100 12/3/2011 3:33:31 AM | Einstein@Home | Resuming task LATeah0069S_864.0_196250_0.0_0 using hsgamma_FGRP1 version 23 12/3/2011 3:33:31 AM | Einstein@Home | Resuming task h1_0411.95_S6GC1__1344_S6BucketA_1 using einstein_S6Bucket version 101 12/3/2011 3:33:31 AM | Einstein@Home | Resuming task LATeah0069S_864.0_453600_0.0_0 using hsgamma_FGRP1 version 23 12/3/2011 3:33:31 AM | Einstein@Home | Resuming task LATeah0069S_928.0_104650_0.0_1 using hsgamma_FGRP1 version 23 12/3/2011 3:51:38 AM | Milkyway@home | Sending scheduler request: To fetch work. 12/3/2011 3:51:38 AM | Milkyway@home | Reporting 1 completed tasks, requesting new tasks for NVIDIA GPU 12/3/2011 3:51:40 AM | Milkyway@home | Scheduler request completed: got 1 new tasks 12/3/2011 3:57:04 AM | Milkyway@home | Starting task ps_separation_82_2s_mix0_2_978029_1 using milkyway version 82 12/3/2011 4:34:05 AM | Milkyway@home | Resuming task nbody-rebuild-clr_327415_3 using milkyway_nbody version 66 12/3/2011 4:48:46 AM | Milkyway@home | Computation for task nbody-rebuild-clr_327415_3 finished 12/3/2011 4:48:46 AM | Einstein@Home | Resuming task LATeah0069S_864.0_196250_0.0_0 using hsgamma_FGRP1 version 23 12/3/2011 4:48:46 AM | Einstein@Home | Resuming task h1_0411.95_S6GC1__1344_S6BucketA_1 using einstein_S6Bucket version 101 12/3/2011 4:48:46 AM | Milkyway@home | Starting task ps_separation_82_2s_mix1_2_1014840_1 using milkyway version 88 12/3/2011 4:48:46 AM | Milkyway@home | Starting task ps_separation_82_2s_mix3_2_952042_1 using milkyway version 88 12/3/2011 4:58:09 AM | Milkyway@home | Computation for task ps_separation_82_2s_mix0_2_978029_1 finished 12/3/2011 4:58:09 AM | Einstein@Home | Restarting task p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1 using einsteinbinary_BRP4 version 100 12/3/2011 5:00:54 AM | Einstein@Home | Computation for task p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1 finished 12/3/2011 5:00:54 AM | Einstein@Home | Starting task p2030.20100913.G48.73+01.03.S.b4s0g0.00000_1704_1 using einsteinbinary_BRP4 version 100 12/3/2011 5:00:57 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_0 12/3/2011 5:00:57 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_1 12/3/2011 5:00:59 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_0 12/3/2011 5:00:59 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_1 12/3/2011 5:00:59 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_2 12/3/2011 5:00:59 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_3 12/3/2011 5:01:01 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_2 12/3/2011 5:01:01 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_3 12/3/2011 5:01:01 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_4 12/3/2011 5:01:01 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_5 12/3/2011 5:01:03 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_4 12/3/2011 5:01:03 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_5 12/3/2011 5:01:03 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_6 12/3/2011 5:01:03 AM | Einstein@Home | Started upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_7 12/3/2011 5:01:05 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_6 12/3/2011 5:01:05 AM | Einstein@Home | Finished upload of p2030.20100913.G44.55+00.20.S.b5s0g0.00000_1264_1_7 |
Send message Joined: 30 Dec 07 Posts: 311 Credit: 149,490,184 RAC: 0 |
Perhaps http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=2346&nowrap=true#47592 may help explain. |
Send message Joined: 19 Nov 11 Posts: 9 Credit: 112,578 RAC: 0 |
So if I understood correctly, that's just the way M@H does it. I also thought I read that this is a time saving measure. But if that is the case there is still something I don't understand...doesn't it take the same length of time to send results back whether or not there is a printout? |
Send message Joined: 12 Nov 07 Posts: 2425 Credit: 524,164 RAC: 0 |
but there are no lines indicating upload of results. MW changed awhile back. It doesn't use a seperate command(right word?) to upload the results. It does it when it talks to the server at one time. It was done to help take some strain off of the server. I believe MW also doesn't create a seperate result file now. Since it doesn't do the uploading seperate you don't see it in Boinc. Doesn't expecting the unexpected make the unexpected the expected? If it makes sense, DON'T do it. |
Send message Joined: 19 Nov 11 Posts: 9 Credit: 112,578 RAC: 0 |
Thank you both for the explanation. Steve |
Send message Joined: 30 Dec 07 Posts: 311 Credit: 149,490,184 RAC: 0 |
I am not certain of the details of how it works but my understanding is that one of the reasons it is done this way is to reduce load on the MilkyWay server. Due to GPU tasks being processed very quickly combined with a small cache of tasks allowed means computers with one or more fast GPUs are contacting the MilkyWay server very frequently. If a separate upload is not required it reduces the number of times the server needs to be contacted by each computer and hence reduces server load. Edit: I see banditwolf has already explained. |
Send message Joined: 19 Nov 11 Posts: 9 Credit: 112,578 RAC: 0 |
Thanks. That makes a lot of sense. |
©2024 Astroinformatics Group