Message boards : Number crunching : Please give the scheduler a kick ...
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Yeti
Volunteer moderator
Avatar

Send message
Joined: 2 Sep 04
Posts: 453
Credit: 193,369,412
RAC: 10,065
Message 34146 - Posted: 29 Jan 2018, 17:17:33 UTC

... so that it hands out work again:

4907 LHC@home 29-01-2018 18:10 update requested by user
4908 LHC@home 29-01-2018 18:10 Sending scheduler request: Requested by user.
4909 LHC@home 29-01-2018 18:10 Requesting new tasks for CPU
4910 LHC@home 29-01-2018 18:10 Scheduler request completed: got 0 new tasks
4911 LHC@home 29-01-2018 18:10 No tasks sent
4912 LHC@home 29-01-2018 18:10 No tasks are available for SixTrack
4913 LHC@home 29-01-2018 18:10 No tasks are available for ATLAS Simulation

There is plenty of work for Sixtrack


Supporting BOINC, a great concept !
ID: 34146 · Report as offensive     Reply Quote
Toby Broom
Volunteer moderator

Send message
Joined: 27 Sep 08
Posts: 798
Credit: 644,686,111
RAC: 235,437
Message 34148 - Posted: 29 Jan 2018, 18:46:29 UTC

Mine were bad this morning but now they are OK so kick was provided?
ID: 34148 · Report as offensive     Reply Quote
Erich56

Send message
Joined: 18 Dec 15
Posts: 1686
Credit: 100,340,244
RAC: 101,857
Message 34151 - Posted: 29 Jan 2018, 19:28:23 UTC - in response to Message 34148.  

... so kick was provided?
from what I just read in the Sixtrack thread - it improved only for short time around early afternoon, and than it got worse again :-(
ID: 34151 · Report as offensive     Reply Quote
marmot
Avatar

Send message
Joined: 5 Nov 15
Posts: 144
Credit: 6,301,268
RAC: 0
Message 34161 - Posted: 30 Jan 2018, 4:50:28 UTC

Got 4 Sixtrack to d/l today...

When I manually update the feeder will send down 1 Sixtrack and 16+ Theory.
ID: 34161 · Report as offensive     Reply Quote
Alessio Mereghetti
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist

Send message
Joined: 29 Feb 16
Posts: 157
Credit: 2,659,975
RAC: 0
Message 34164 - Posted: 30 Jan 2018, 7:48:08 UTC - in response to Message 34161.  
Last modified: 30 Jan 2018, 7:48:18 UTC

ID: 34164 · Report as offensive     Reply Quote
Erich56

Send message
Joined: 18 Dec 15
Posts: 1686
Credit: 100,340,244
RAC: 101,857
Message 34278 - Posted: 5 Feb 2018, 6:12:01 UTC

Since last night, there is no single "unsent" task available for any sub-project.
Besides, none of the finished and uploaded tasks have been validated for 3 days now.

Could someone from CERN/LHC please give us any information about what's going on?
ID: 34278 · Report as offensive     Reply Quote
Profile Nils Høimyr
Volunteer moderator
Project administrator
Project developer
Project tester

Send message
Joined: 15 Jul 05
Posts: 242
Credit: 5,800,306
RAC: 0
Message 34279 - Posted: 5 Feb 2018, 6:55:59 UTC

Our server daemons have been restarted now. It seems the transitioner ran into problems, but this does not explain why we ran out of tasks. We are looking into this, task generation should resume soon.
ID: 34279 · Report as offensive     Reply Quote
computezrmle
Volunteer moderator
Volunteer developer
Volunteer tester
Help desk expert
Avatar

Send message
Joined: 15 Jun 08
Posts: 2386
Credit: 222,896,878
RAC: 138,200
Message 34280 - Posted: 5 Feb 2018, 7:16:11 UTC - in response to Message 34279.  

Our server daemons have been restarted now.

Good morning Nils,

can you tell us something regarding the tasks (mainly ATLAS) that have been marked "invalid" (I'm sure falsely) during the weekend?
I guess they will never be rewarded, will they?

Beside that:
The access to at least parts of the task lists through the website is very sluggish.
Is there still a database performance problem?
ID: 34280 · Report as offensive     Reply Quote
Erich56

Send message
Joined: 18 Dec 15
Posts: 1686
Credit: 100,340,244
RAC: 101,857
Message 34281 - Posted: 5 Feb 2018, 7:35:22 UTC

On the Server Status Page, as of as of 5 Feb 2018, 7:09:41 UTC, ALL services are shown as "not running".
What does this mean? Maintenence work, or a total breakdown?
ID: 34281 · Report as offensive     Reply Quote
Profile Nils Høimyr
Volunteer moderator
Project administrator
Project developer
Project tester

Send message
Joined: 15 Jul 05
Posts: 242
Credit: 5,800,306
RAC: 0
Message 34283 - Posted: 5 Feb 2018, 8:19:13 UTC - in response to Message 34281.  

Maintenance as the transitioner is stuck following the DB issues last week. Ref. news.
ID: 34283 · Report as offensive     Reply Quote
David Cameron
Project administrator
Project developer
Project scientist

Send message
Joined: 13 May 14
Posts: 387
Credit: 15,314,184
RAC: 0
Message 34285 - Posted: 5 Feb 2018, 8:50:23 UTC - in response to Message 34280.  

can you tell us something regarding the tasks (mainly ATLAS) that have been marked "invalid" (I'm sure falsely) during the weekend?
I guess they will never be rewarded, will they?


This was an unfortunate side-effect of the server daemons getting stuck. The WU failed validation because the results had already been deleted by the time the validation happened. For now I've turned off the cleaning of ATLAS results until things are back up and running.
ID: 34285 · Report as offensive     Reply Quote
Erich56

Send message
Joined: 18 Dec 15
Posts: 1686
Credit: 100,340,244
RAC: 101,857
Message 34404 - Posted: 19 Feb 2018, 5:15:57 UTC

Since last night, NO tasks available at all, from all sub-projects. What's going on?
ID: 34404 · Report as offensive     Reply Quote
ivan
Volunteer moderator
Project tester
Volunteer developer
Volunteer tester
Project scientist
Avatar

Send message
Joined: 29 Aug 05
Posts: 997
Credit: 6,264,307
RAC: 71
Message 34408 - Posted: 19 Feb 2018, 10:48:00 UTC - in response to Message 34404.  

Since last night, NO tasks available at all, from all sub-projects. What's going on?

CMS is down for a WMAgent update. No ideas about the rest...
ID: 34408 · Report as offensive     Reply Quote
Erich56

Send message
Joined: 18 Dec 15
Posts: 1686
Credit: 100,340,244
RAC: 101,857
Message 34413 - Posted: 19 Feb 2018, 11:26:50 UTC - in response to Message 34408.  

CMS is down for a WMAgent update. No ideas about the rest...
Thanks, Ivan, for your reply. I knew about the CMS downtime (after heaving read your yesterday's postings in the CMS thread).
Meanwhile, LHCb and Theory are back.
ID: 34413 · Report as offensive     Reply Quote
Hona

Send message
Joined: 29 Sep 04
Posts: 5
Credit: 3,043,759
RAC: 0
Message 34414 - Posted: 19 Feb 2018, 11:28:17 UTC

Since last night, NO tasks available at all, from all sub-projects. What's going on?


Getting "Theory" tasks is no problem on my side.
Two at 01:39 UTC and one in the morning.
ID: 34414 · Report as offensive     Reply Quote

Message boards : Number crunching : Please give the scheduler a kick ...


©2024 CERN