Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 

Quick Go »
No member browsing this thread
Thread Status: Active
Total posts in this thread: 3
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 1036 times and has 2 replies Next Thread
Sekerob
Ace Cruncher
Joined: Jul 24, 2005
Post Count: 20043
Status: Offline
Reply to this Post  Reply with Quote 
WCG Performance Analysis, Week 2-08, from the outside in.

Someone joked about that a few weeks ago, so lets see if some response can be extracted from the community.

This weeks and the previous one showed a stronger decline of the Dengue (DDDT) work distribution and shortening of the average run time to now 1.15 hours. The project work unit count graph shows kind of a roller-coaster in the quantitative department (yellow). It may have been in part due to the substantially longer run times for AIDS (FA@H) nearing the average of 10.5 hours (dark blue), but now trending back a bit. Longer AIDS jobs on BOINC would translate to less of the other projects getting a chance. Meantime Proteome Folding (HPF2-Green) had a slight drought running out of work on the old UD client which left extra time for the AIDS jobs, the only other project left on the old agent. Other than that, African Climate runs very low profile and flat at 100-200 work units a day. Probably we completed about 55-60% for this specific South African related part. The Cancer project is somewhere 2.5.% The run time average with a fairly constant work volume suggests members are gradually finding which machines are best at this long running project (except for AC@H all present WCG project are long-er). Typically the weekend shows a production dip due in part to switching office machines off and in part machines that unattended do not send all the completed work back immediately. This usually results in a Monday statistics spike.

Empowering myself, changed all my machine profiles from 'all projects' to what they're best at given the different cpu generations and ensured that each project does get a fairly equal contribution regardless the knreed joystick effects :). Maybe one day we are able to set it in the web-profiles.

Saturday/Sunday netted a combined 401 CPU years, an all time record, so we seem to line ourselved up for the next target of breaking thru the 1,500 CPU Years Week technical resistance point (this is not about currency trading :-)

All that said, Have a good crunching week....

(The below graphs and more can be found in the Start Here forum: http://www.worldcommunitygrid.org/forums/wcg/viewthread?thread=15583 )






----------------------------------------
WCG Global & Research > Make Proposal Help: Start Here!
Please help to make the Forums an enjoyable experience for All!
[Jan 14, 2008 8:10:46 PM]   Link   Report threatening or abusive post: please login first  Go to top 
Dataman
Ace Cruncher
Joined: Nov 16, 2004
Post Count: 4865
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: WCG Performance Analysis, Week 2-08, from the outside in.

Hey, Thanks Sek. Good information.

flag
----------------------------------------


[Jan 15, 2008 2:23:14 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: WCG Performance Analysis, Week 2-08, from the outside in.

any tips on how to figure out what kind of project will run most efficiently on my machines? I have a intel p4 @ 3.6 ghz and an AMD laptop at 2.4 ghz.
[Jan 15, 2008 2:47:33 AM]   Link   Report threatening or abusive post: please login first  Go to top 
[ Jump to Last Post ]
Post new Thread