Message boards :
Number crunching :
w8_job_tracking jobs need higher rsc_fpops_est
Message board moderation
Author | Message |
---|---|
Send message Joined: 17 Jul 05 Posts: 102 Credit: 542,016 RAC: 0 |
Those things run 10+ hours on my C2Q 9400, compared to other LHC jobs their estimated runtime is much too low (I think it should be ~5 times as high as it is now). Not a big problem as long as rsc_fpops_bound is sufficient, the scheduler might deliver too much work to a machine though if the runtime is underestimated so much. |
Send message Joined: 12 Jul 11 Posts: 857 Credit: 1,619,050 RAC: 0 |
Interesting; I shall have a look. Must be doing a lot of beam-beam I suspect. Will report back. Eric. |
Send message Joined: 1 Mar 07 Posts: 47 Credit: 32,356 RAC: 0 |
It's a bit of a problem for my old Athlon http://lhcathomeclassic.cern.ch/sixtrack/show_host_detail.php?hostid=9947112, especially when it only runs 2 or 3 days a week. e.g. Task http://lhcathomeclassic.cern.ch/sixtrack/workunit.php?wuid=16183943. It's currently at 96.6% complete, 37 hours elapsed, BOINC estimate to completion 1 hour 12 minutes, BoincLogX estimate 5 hrs 3 mins. [edit] Now up to 99.0% [/edit] |
Send message Joined: 1 Mar 07 Posts: 47 Credit: 32,356 RAC: 0 |
My task completed and validated, 3.5 hours after deadline! I also noticed that mine was a "w9_job_tracking" task, the title of this thread is "w8_job_tracking" Name w9_job_tracking_bb_np_nt_dq-4_100Hz_1__1__s__62.31_60.32__2_4__6__87_1_sixvf_boinc58_1 Workunit 16183943 Created 1 Apr 2014, 18:57:17 UTC Sent 1 Apr 2014, 18:58:45 UTC Received 9 Apr 2014, 14:08:09 UTC Server state Over Outcome Success Client state Done Exit status 0 (0x0) Computer ID 9947112 Report deadline 9 Apr 2014, 10:30:59 UTC Run time 139,112.83 CPU time 96,048.67 Validate state Valid Credit 319.08 Application version SixTrack v446.03 |
©2024 CERN