Message boards : Number crunching : Enhancement Request: Server Status
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 27953 - Posted: 25 Nov 2016, 9:16:52 UTC

As you now bring all LHC-Projects together it gets more and more needed:

An entry on the Server-Status-Page (or a new separate page) that shows real Data that is available to crunch, but not only how much BOINC-Conatiner-WUs are available.

Then the Users can avoid to try to crunch sub-projects that do not really have work

At the moment I`m writing this people download and crunch LHCb-WUs, but it seems that there is no real work available. No user can identify if he has a problem or CERN has a problem and that is not really satisfying !


Supporting BOINC, a great concept !
ID: 27953 · 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 27954 - Posted: 25 Nov 2016, 10:49:08 UTC - in response to Message 27953.  

Thanks Yeti, good suggestion. Sixtrack is on and off with batches of jobs, while our VM applications in principle should have work all the time.

I have flagged the LHCb application as "Beta" for now, and the issue you mention should be followed up by our colleagues.
ID: 27954 · Report as offensive     Reply Quote
ivan
Volunteer moderator
Project tester
Volunteer developer
Volunteer tester
Project scientist
Avatar

Send message
Joined: 29 Aug 05
Posts: 998
Credit: 6,264,307
RAC: 71
Message 27964 - Posted: 25 Nov 2016, 20:12:39 UTC - in response to Message 27954.  

For the moment, you can get the minimum number of queued CMS jobs (not CMS@Home tasks) on the CMS Jobs Page. If the number queued is less than ~1000, then that is all that's left in the queue and I need to submit more. If it's ~1000, there are an indeterminate number of jobs still waiting to go in the queue; if its more than ~1000 then there is another batch submitted, the excess being the number left in the current batch.
I daresay Laurence can copy Andrew's technique for making these figures available when we transfer from the RAL HTCondor server to one at CERN (we're ironing out the kinks in my being able to submit to the new server at the moment).
ID: 27964 · Report as offensive     Reply Quote

Message boards : Number crunching : Enhancement Request: Server Status


©2024 CERN