Message boards :
CMS Application :
No Tasks
Message board moderation
Author | Message |
---|---|
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
No Boinc-cms tasks on the server status page availabe. |
Send message Joined: 15 Apr 15 Posts: 38 Credit: 227,251 RAC: 0 |
No Boinc-cms tasks on the server status page availabe. Will the server default to the other applications that have work available, to maximize donor efficiency? Thanks. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
Under"Your Account" and "Preferences for this project" there are tick-boxes, where you can select, which apps you want to run. After saving the change, you must update the project in boinc, for it to take effect. |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
No Boinc-cms tasks on the server status page availabe. There are now, just in time for Le Weekend, comme ils disent à Genève. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
We are kind of getting low on CMS-tasks. Please refill. Thanks. |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
We are kind of getting low on CMS-tasks. I was just waiting for your reminder! ;-) [Edit] Well, how's about that? Looking at the time-stamps I think I got in before your post -- by a time measured in seconds... [/Edit] |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
How did that go....Great minds..... There are still a number of jobs in WNPostproc state on dashboard. Is that real or a glitch? |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
How did that go....Great minds..... I usually find Dashboard not that reliable for that particular statistic. Here's what condor is reporting at the moment for the previous batch: [cms005@lcggwms02:~] > ./stats.sh 160806_154814:ireid_crab_BPH-RunIISummer15GS-00046_M 118 NodeStatus = 3; /* "STATUS_SUBMITTED" */ 9687 NodeStatus = 5; /* "STATUS_DONE" */ 195 NodeStatus = 6; /* "STATUS_ERROR" */ while Dashboard is saying 8 pending + 113 running = 121 submitted, 9617 done, 198 failed, 48 WNPostProc and 16 unknown, so on the server the jobs in the last two categories seem to actually have been moved to "done". Commumications glitches, I expect. |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
New batch submitted. I'll have to work out a way to avoid doing this at weekends... :-) |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
Oops! Sorry, I had a hell of a trip back from Ambleside yesterday, involving a taxi, four mainline trains, an Overground train, an Underground train and two buses... So I somehow misread the number of jobs left last night, and the queue ran dry while I slept. Full again now. |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
Looks like we are going to need a new batch of work fairly soon...next 24h or so. (Weekend, again) |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
Looks like we are going to need a new batch of work fairly soon...next 24h or so. Yes, I know. We've picked up a few heavy hitters on the production project. One calls itself WLCG Performance-Test Cluster and has been running up to 8 instances on up to 8 or 9 machines! I like to let things run close to the end to avoid "wasting" the 7-day expiry time on my Grid proxy certificates, but when a batch of 10K jobs takes only 4 days now, that's less of a problem. 1200 jobs to go now, so that's about 9 hours at the current rate; I may as well slap a new batch in now (I'd settled on batches of 10,000 jobs before I learnt that that is the CRAB3 limit anyway!). I think we are nearly up to the 1 million filtered events that were originally requested for our current workflow, so I'll contact the B-physics group next week to see if they have anything else suitable and "interesting" to run. We have a paper in preparation about the project but I'm afraid I'm the bottleneck as my "daytime" job keeps intruding with urgent interventions. |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
I've submitted a new batch of jobs, but it seems to be held up in the server, so there's a chance we may run out of jobs overnight. |
Send message Joined: 13 Feb 15 Posts: 1188 Credit: 861,609 RAC: 15 |
... but it seems to be held up in the server, .... https://lhcathome.cern.ch/vLHCathome-dev/server_status.php |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
... but it seems to be held up in the server, .... I meant the CRAB server. I keep getting this: [eesridr@pion:src] > crab status CRAB project directory: /home/eesridr/CMS_at_Home/CMSSW_7_1_22/src/crab_projects/crab_BPH-RunIISummer15GS-00046_AO Task name: 161103_181449:ireid_crab_BPH-RunIISummer15GS-00046_AO Grid scheduler: lcggwms02.gridpp.rl.ac.uk Task status: NEW on command SUBMIT Dashboard monitoring URL: http://dashb-cms-job.cern.ch/dashboard/templates/task-analysis/#user=ireid&table=Mains&pattern=161103_181449%3Aireid_crab_BPH-RunIISummer15GS-00046_AO No jobs created yet! Usually I get an error(!) for "crab status" when I've had a successful submission. |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
Our long-suffering CRAB operative has confirmed the problem, and is looking for the cause. Thanks, Stefano! |
Send message Joined: 20 Jan 15 Posts: 1139 Credit: 8,310,612 RAC: 444 |
Our long-suffering CRAB operative has confirmed the problem, and is looking for the cause. We seem to have new jobs again. |
Send message Joined: 8 Apr 15 Posts: 781 Credit: 12,362,663 RAC: 4,061 |
Yes so far so good........I was worried late last night when ALL the Cern project sites were shut down.......well except the Sixtrack LHC site. Mad Scientist For Life |
Send message Joined: 17 Aug 15 Posts: 62 Credit: 296,695 RAC: 0 |
I still have one task not being able to report. Feeder is not running. Tullio |
Send message Joined: 16 Aug 15 Posts: 966 Credit: 1,211,816 RAC: 0 |
|
©2024 CERN