| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
| World Community Grid Forums
|
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 29
|
|
| Author |
|
|
knreed
Former World Community Grid Tech Joined: Nov 8, 2004 Post Count: 4504 Status: Offline Project Badges:
|
Yes - 'repair' jobs will use 5.15 as well.
|
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Just started getting the BIG 5.15 work units.
![]() |
||
|
|
Dataman
Ace Cruncher Joined: Nov 16, 2004 Post Count: 4865 Status: Offline Project Badges:
|
Just started getting the BIG 5.15 work units. ![]() Me too. 3 to 4 times bigger. ![]() ![]() ![]() |
||
|
|
littlepeaks
Veteran Cruncher USA Joined: Apr 28, 2007 Post Count: 748 Status: Offline Project Badges:
|
Hmmm-- I just got a new DDDT WU -- says "to completion" is 4:55:48.
----------------------------------------What's strange is the WU before it is a FAAH, which also has a "to completion" time of 4:55:48. Wonder what's up with that. I think it would statistically be an unlikely event to have two consecutive WUs with identical estimated completion times down to the second. [Edit 2 times, last edit by littlepeaks at Mar 5, 2008 2:38:02 AM] |
||
|
|
knreed
Former World Community Grid Tech Joined: Nov 8, 2004 Post Count: 4504 Status: Offline Project Badges:
|
There are statistics and then there are statistics......
In this particular case, I used the estimated duration for the FightAIDS@Home workunits for the 'BIG' Dengue Fever workunits until the auto-estimating utility produces realistic numbers for DDDT. The DDDT workunits should be about the same duration as the FAAH workunits so using the same value is reasonable. We will allow the auto-estimating utility to start providing the values on DDDT on Thursday or Friday this week when we start getting a steady stream of results back. |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
As for those with slower machines that struggle to complete workunits on time. We are working with BOINC to put in place the ability to send shorter workunits to slower machines (slower meaning either they are less powerful or they aren't very often) and larger workunits to more powerful machines. This will meet both our need for a lower transaction rate to keep load on the database at an acceptable level but also make best use of all of the computers that are contributing. This issue is very important to us so please do not think that we are ignoring the problems with workunit duration and deadlines. We are updating our BOINC server code in a little bit to include the latest code from BOINC. This is the first step. BOINC has been working to implement a better mechanism for matching workunits to the different computers. Once they finish the basic mechanism, we will be enhancing it to allow for matching workunits based on duration. Will there be an option to choose what size workunits my pc will get? Because that would be just awesome! |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Sadly not any time soon - but don't discount the possibility altogether.
|
||
|
|
Sekerob
Ace Cruncher Joined: Jul 24, 2005 Post Count: 20043 Status: Offline |
Hi Jonathan,
----------------------------------------The logic is being put in place to let the servers decide what 'lighter' work is suitable for 'lighter' machines or heavy for heavy. Asking for 'only short', is not like a chopper that can be applied like they do on Rosetta where you can specify the run time between 1 and 24 hours. HPF2 would have that theoretical capability.... it's long ways. And putting on my Dr hat, guess what happens if a WCG Challenge is organized on 'Results'.ttyl
WCG
Please help to make the Forums an enjoyable experience for All! |
||
|
|
alpage2
Cruncher Joined: Dec 18, 2005 Post Count: 2 Status: Offline Project Badges:
|
As for those with slower machines that struggle to complete workunits on time. We are working with BOINC to put in place the ability to send shorter workunits to slower machines (slower meaning either they are less powerful or they aren't very often) and larger workunits to more powerful machines. This will meet both our need for a lower transaction rate to keep load on the database at an acceptable level but also make best use of all of the computers that are contributing. This issue is very important to us so please do not think that we are ignoring the problems with workunit duration and deadlines. We are updating our BOINC server code in a little bit to include the latest code from BOINC. This is the first step. BOINC has been working to implement a better mechanism for matching workunits to the different computers. Once they finish the basic mechanism, we will be enhancing it to allow for matching workunits based on duration. This is good news. In addition to a high-end desktop PC which accepts all projects, I have a 400MHz laptop which runs 3-4 hours daily, and it was able to complete the short DDDT work units just in time, in 1 week. Until the new method of matching work units to machine speeds/durations is available, the laptop will have to retire from WCG, but hopefully, not for too long ;-) Alan |
||
|
|
|