Message boards : Number crunching : New Work Available Jan 2009
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Ocean Archer
Avatar

Send message
Joined: 13 Jul 05
Posts: 143
Credit: 263,300
RAC: 0
Message 20910 - Posted: 8 Jan 2009, 17:56:35 UTC

Ooooohh ...

Lots of new work becoming available. Thank you so much


If I've lived this long, I've gotta be that old
ID: 20910 · Report as offensive     Reply Quote
Profile Paul D. Buck

Send message
Joined: 2 Sep 04
Posts: 545
Credit: 148,912
RAC: 0
Message 20911 - Posted: 8 Jan 2009, 19:48:49 UTC

Um where did you see this news?
ID: 20911 · Report as offensive     Reply Quote
Michael Karlinsky
Avatar

Send message
Joined: 18 Sep 04
Posts: 163
Credit: 1,203,029
RAC: 145
Message 20912 - Posted: 8 Jan 2009, 20:20:38 UTC - in response to Message 20911.  

Um where did you see this news?


Um, as of now:


Server Status
Up, 41019 workunits to crunch
54863 workunits in progress
9 concurrent connections


Michael
Team Linux Users Everywhere
ID: 20912 · Report as offensive     Reply Quote
Profile Reeltime

Send message
Joined: 2 Jan 09
Posts: 2
Credit: 185,305
RAC: 0
Message 20914 - Posted: 9 Jan 2009, 0:29:20 UTC

88k wus to send
ID: 20914 · Report as offensive     Reply Quote
CharlyD

Send message
Joined: 1 Dec 06
Posts: 20
Credit: 12,307
RAC: 9
Message 20915 - Posted: 9 Jan 2009, 0:44:11 UTC

but i get none!
ID: 20915 · Report as offensive     Reply Quote
Profile Reeltime

Send message
Joined: 2 Jan 09
Posts: 2
Credit: 185,305
RAC: 0
Message 20917 - Posted: 9 Jan 2009, 1:11:09 UTC

Thats strange, theres plenty out there 92k at the moment, have you tried resetting the project?
ID: 20917 · Report as offensive     Reply Quote
Profile Yank
Avatar

Send message
Joined: 21 Nov 05
Posts: 64
Credit: 1,979,861
RAC: 0
Message 20918 - Posted: 9 Jan 2009, 2:45:23 UTC - in response to Message 20915.  

but i get none!


Is/are your computer/s available to receive them? It may be that you are loaded up on your computer with other projects. Many work units are now available., the most I have seen in some time.

ID: 20918 · Report as offensive     Reply Quote
Profile Paul D. Buck

Send message
Joined: 2 Sep 04
Posts: 545
Credit: 148,912
RAC: 0
Message 20919 - Posted: 9 Jan 2009, 4:06:07 UTC - in response to Message 20918.  

but i get none!


Is/are your computer/s available to receive them? It may be that you are loaded up on your computer with other projects. Many work units are now available., the most I have seen in some time.


I am gtting oneies and twosies ... sigh ...

I wish work was more continuous ...

Another place where Resource Share does not really work well ... I have similar problems with SIMAP though I can usually get a nice load of work from them ...
ID: 20919 · Report as offensive     Reply Quote
Richard Haselgrove

Send message
Joined: 27 Oct 07
Posts: 185
Credit: 3,297,428
RAC: 0
Message 20922 - Posted: 9 Jan 2009, 11:56:54 UTC - in response to Message 20919.  

I am gtting oneies and twosies ... sigh ...

I wish work was more continuous ...

Another place where Resource Share does not really work well ... I have similar problems with SIMAP though I can usually get a nice load of work from them ...

There is a deliberate policy in place on this project, which limits work supply to:

* no more than 2 tasks per scheduler request
* 15 minute interval between work requests
* daily quota of 10 tasks/CPU

I think the policy is a good one - it stops the power crunchers hoovering up all the available new work and sitting on it for days on end, and leaves some crumbs available for everyone else.
ID: 20922 · Report as offensive     Reply Quote
Profile Paul D. Buck

Send message
Joined: 2 Sep 04
Posts: 545
Credit: 148,912
RAC: 0
Message 20923 - Posted: 9 Jan 2009, 12:24:38 UTC - in response to Message 20922.  

I am gtting oneies and twosies ... sigh ...

I wish work was more continuous ...

Another place where Resource Share does not really work well ... I have similar problems with SIMAP though I can usually get a nice load of work from them ...

There is a deliberate policy in place on this project, which limits work supply to:

* no more than 2 tasks per scheduler request
* 15 minute interval between work requests
* daily quota of 10 tasks/CPU

I think the policy is a good one - it stops the power crunchers hoovering up all the available new work and sitting on it for days on end, and leaves some crumbs available for everyone else.


Yeah, I saw sometnign about that in another thread ... I guess at least I am getting some work and I should be content with that ...

And without restrictions like these the guys with the mega-farms would get all the work ... Shoot in a month or two my wife is going to have me down to only 4 machines ... sigh ... well maybe by then the i7 will be available in dual CPU configuration and that will be a machine to build ... 16 virtual CPUs ... that is something to look forward too ...
ID: 20923 · Report as offensive     Reply Quote
Keith T.
Avatar

Send message
Joined: 1 Mar 07
Posts: 47
Credit: 32,179
RAC: 14
Message 20949 - Posted: 11 Jan 2009, 14:49:38 UTC

11 Jan 2009 14:41:30 UTC

Results ready to send 0

The biggest WU batch in recent history has just run out.

http://bluenorthernsoftware.com/scarecrow/lhcstats/lstat.html shows that this batch lasted over 3 days.

I hope that we lots more similar batches in 2009.

Keith.
ID: 20949 · Report as offensive     Reply Quote
Profile Clank [MM]

Send message
Joined: 8 Nov 08
Posts: 2
Credit: 1,014,205
RAC: 0
Message 21080 - Posted: 21 Jan 2009, 6:00:30 UTC - in response to Message 20922.  



* no more than 2 tasks per scheduler request

Not true, I have 2 machines that can grab 20-40 at a time and 2 machines that will never go past 4. I have not figured out what causes the difference though.

ID: 21080 · Report as offensive     Reply Quote
Richard Haselgrove

Send message
Joined: 27 Oct 07
Posts: 185
Credit: 3,297,428
RAC: 0
Message 21082 - Posted: 21 Jan 2009, 11:40:16 UTC - in response to Message 21080.  
Last modified: 21 Jan 2009, 11:44:34 UTC

* no more than 2 tasks per scheduler request

Not true, I have 2 machines that can grab 20-40 at a time and 2 machines that will never go past 4. I have not figured out what causes the difference though.

Interesting. Which machines get the big allocation, and which are restricted? We may be able to work it out.

Edit - 9762403 and 9769638 are the two which currently have a lot of work queued up, but their caches were filled two at a time, at 15 minute intervals, as I originally described.
ID: 21082 · Report as offensive     Reply Quote

Message boards : Number crunching : New Work Available Jan 2009


©2020 CERN