Message boards :
News :
Jobs incoming!
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · Next
Author | Message |
---|---|
Send message Joined: 8 Apr 15 Posts: 755 Credit: 11,757,890 RAC: 5,927 |
I only have 3 of my hosts running here right now but they are doing fine and no errors or invalids. (Win10 and Win7) The only time I have a problem is with VB if the power shuts down without a *suspend* Some will start over at 0% or just computer error but I always have mine running 24/7 as long as the power doesn't go out. Mad Scientist For Life |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Yeti, Magic: we just have to take the rough with the smooth! Thanks for your efforts. |
Send message Joined: 20 May 15 Posts: 217 Credit: 5,906,114 RAC: 15,478 |
At the moment I'm sitting in the damp UK but this point in the boot.log is when I move to what I expect is a nice sunny beach in the Pacific region... This problem has now gone away. Not sure if you had done something your end or it was what I did yesterday but I no longer move to another time zone :-) |
Send message Joined: 13 Feb 15 Posts: 1185 Credit: 850,190 RAC: 1,017 |
ivan on 3 Sep 2015, 9:48:41 UTC wrote: ... so I submitted another 1,000 jobs the same as the last batch. That lasted a bit over 30 hours; hopefully this lot will get us into next week. Since we're in the next week and I don't get jobs, I suppose we're out of work . . . |
Send message Joined: 9 Apr 15 Posts: 57 Credit: 230,221 RAC: 0 |
Since we're in the next week and I don't get jobs, I suppose we're out of work . . . Its Early Monday Morning in Beautiful Downtown Uxbridge, let Ivan finish his coffee and croissants before logging in and adding more jobs! |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Yep, just four jobs running. I'll slip a new batch in ASAP. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
Hi Ivan, is it possible to put an indicator of jobs available on the SSP? The "Tasks ready to send" is a pointless figure. |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Yep, just four jobs running. I'll slip a new batch in ASAP. Having trouble with the submission, bear with me... |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Hi Ivan, It should be possible -- how to actually do it is another matter! I'll give it some thought. |
Send message Joined: 29 May 15 Posts: 147 Credit: 2,842,484 RAC: 0 |
Yep, just four jobs running. I'll slip a new batch in ASAP. Today after work I'm leaving the Office for a 1 week trip with my bike; let my Clients run CMS or should I Switch to other Projects for this time ? |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Yep, just four jobs running. I'll slip a new batch in ASAP. Probably best to switch to other projects in case we get glitches. I had to submit this new batch 6 or 7 times before it finally went through. |
Send message Joined: 13 Feb 15 Posts: 1185 Credit: 850,190 RAC: 1,017 |
I had to submit this new batch 6 or 7 times before it finally went through.Confirming that the 1st new cmsRun started. Same kind of jobs, Ivan - 25 records each? How many jobs did you throw into this batch? Edit: My own answer: Other kind of jobs! 1 record is much faster processed. |
Send message Joined: 29 May 15 Posts: 147 Credit: 2,842,484 RAC: 0 |
Probably best to switch to other projects in case we get glitches Okay, my Clients will crunch up to the end of the 24-hours of the BOINC-WU and then Switch back to vLHC. See you after my holidays |
Send message Joined: 13 Feb 15 Posts: 1185 Credit: 850,190 RAC: 1,017 |
Same kind of jobs, Ivan - 25 records each? My own answer again: 250 events/records in 1 job. |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
Same kind of jobs, Ivan - 25 records each? Yes, these are "minimum bias" events, basically background, so they are faster than the complex T-Tbar events we ran last week. |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
How are people finding these jobs? The output files are a bit larger than I was expecting, what sort of run-times are you getting per job? Ah, found it in Dashboard -- quite a spread, minimum 26', maximum 4h16'. |
Send message Joined: 20 Mar 15 Posts: 243 Credit: 886,442 RAC: 67 |
There's quite a spread in the individual record times, too. Casually watching a job here I saw times from 25s to 150s. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
I am seeing it skipping run-directories. run-1, run-2, run-4, run-6... No gaps in time. Is that normal? Times between 1h 20 to 2h10 per job (250 events) Upload size: about 78 Mbytes/job |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
There's quite a spread in the individual record times, too. Yeah, that's normal; basically it depends on the number of secondaries produced in the collision. The more specialised investigations like the T-Tbar stuff creates special interactions, with MinBias we take everything so there's a certain probability we will indeed produce, say, a MinBias interaction or something else of comparable complexity. |
Send message Joined: 20 Jan 15 Posts: 1129 Credit: 7,952,692 RAC: 2,986 |
I am seeing it skipping run-directories. Upload size is what I'm seeing. Can't say about the run-number skipping, that'll have to wait for Laurence to comment, but so long as there's job-running continuity I'm not very worried. I think the numbering is just a convenience for the glide-in, I only see the returned result with its job number in the queue. I don't think the failure rate is significantly different from last week, so we may not be at the sweet-spot, but we're far from failure. |
©2024 CERN