[One thread on Einstein and the other one on Seti to reduce overhead and bottlenecks...
How are you doing that? I badly want to do that on my Gallatin host, so I can raise the SETI resource fraction without losing the huge mixed-ap benefit. I run tx36 client.
I'm on the same boat... I put
Einstein@Home,SETI@Home
on the truxoft_prefs.xml file.
I got an averege improvement from 55 min to 40 min/WU in E@H, and from 115 min to 82 min in S@H - using the same versions (Trux SS3 and U41.04).
[One thread on Einstein and the other one on Seti to reduce overhead and bottlenecks...
How are you doing that? I badly want to do that on my Gallatin host, so I can raise the SETI resource fraction without losing the huge mixed-ap benefit. I run tx36 client.
I'm on the same boat... I put
Einstein@Home,SETI@Home
on the truxoft_prefs.xml file.
I got an averege improvement from 55 min to 40 min/WU in E@H, and from 115 min to 82 min in S@H - using the same versions (Trux SS3 and U41.04).
This is the right and the only way to work well with the two logical cores of our processors:
1) HT activated!
2) Cpu_affinity in Truxoft Manager
3) Two different projects carried on simultaneously.
Following the expriences of the other forum users is the best strategy to achieve some pleasant results!!
Just be warnned that if you use the "all" flag here and are not using optimized science apps for the other projects trux will over-claim for these projects. You can also use a single (or multiple) project name such as einstein@home if this is the only project you are working on with an optimized application.
There are 10^11 stars in the galaxy. That used to be a huge number. But it's only a hundred billion. It's less than the national deficit! We used to call them astronomical numbers. Now we should call them economical numbers. - Richard Feynman
How are you doing that? I badly want to do that on my Gallatin host, so I can raise the SETI resource fraction without losing the huge mixed-ap benefit. I run tx36 client.
I just figured this out today myself. Open Windows Task Manager (XP) and right click on the app exe. It will open a menu with "Set Affinity" at the bottom. Set one app to CPU 0 and the other to CPU 1.
I tried that after you posted. The trouble is that I think that affinity only applies to the currently running copy of the task, and evaporates when the science ap finishes the result in progress and the client starts another. I followed your suggestion a few hours ago, and already just now I saw two Alberts running. Pity, that would have been easy.
I just figured this out today myself. Open Windows Task Manager (XP) and right click on the app exe. It will open a menu with "Set Affinity" at the bottom. Set one app to CPU 0 and the other to CPU 1.
I tried that after you posted. The trouble is that I think that affinity only applies to the currently running copy of the task, and evaporates when the science ap finishes the result in progress and the client starts another. I followed your suggestion a few hours ago, and already just now I saw two Alberts running. Pity, that would have been easy.
Yes, I appologize for that. ExtraTerrestrial Apes brought that to my attention 4 posts later in this thread.
Maybe I should of stuck to the U.41.02/03 version, my second result of the U.41.04 version has gone waacky, it was at a hundred percent completion, and BOINC stopped to resume an xtremlabs WU, upon resuming the Einstein WU still showing CPU time of 1 hr 7 minutes went to 0% completion, and time left went to 3 more hours...I double checked, its the same work unit, since boinc hasn't sent off any completed workunits within the past hour.
RE: RE: [One thread on
)
I'm on the same boat... I put
Einstein@Home,SETI@Home
on the truxoft_prefs.xml file.
I got an averege improvement from 55 min to 40 min/WU in E@H, and from 115 min to 82 min in S@H - using the same versions (Trux SS3 and U41.04).
RE: RE: RE: [One thread
)
This is the right and the only way to work well with the two logical cores of our processors:
1) HT activated!
2) Cpu_affinity in Truxoft Manager
3) Two different projects carried on simultaneously.
Following the expriences of the other forum users is the best strategy to achieve some pleasant results!!
Best regards!
Luca B. from Italy
Can anyone post how the
)
Can anyone post how the global_prefs in Trux Boinc should look like?
I want to run Einstein on 1 cpu and Rosetta on the other (HT).
Hopfull.
Anders n
RE: Can anyone post how the
)
all
Einstein@Home,SETI@Home
This is my setting for Einstein@Home & SETI@Home
So you just need to change the SETI@Home to Rosetta@Home
Hopefully this will work, good luck!! :)
RE: all Just be
)
Just be warnned that if you use the "all" flag here and are not using optimized science apps for the other projects trux will over-claim for these projects. You can also use a single (or multiple) project name such as einstein@home if this is the only project you are working on with an optimized application.
There are 10^11 stars in the galaxy. That used to be a huge number. But it's only a hundred billion. It's less than the national deficit! We used to call them astronomical numbers. Now we should call them economical numbers. - Richard Feynman
RE: all
)
This is in the truxoft_prefs.xml ?
How about the global_prefs.xml
And yes I only want to run optimesed on Einstein.
Anders n
Edit What I am really after is to run only 1 Einsten WU at a time.
Crunching time gets really low then.
RE: This is in the
)
Yes, this is the truxoft_prefs.xml file
No changes needed for global_prefs.xml
EDIT: And as Dave said, if you only optimised client for Einstein, then you should change the all to einstein@home
RE: RE: How are you doing
)
I tried that after you posted. The trouble is that I think that affinity only applies to the currently running copy of the task, and evaporates when the science ap finishes the result in progress and the client starts another. I followed your suggestion a few hours ago, and already just now I saw two Alberts running. Pity, that would have been easy.
RE: RE: I just figured
)
Yes, I appologize for that. ExtraTerrestrial Apes brought that to my attention 4 posts later in this thread.
Maybe I should of stuck to
)
Maybe I should of stuck to the U.41.02/03 version, my second result of the U.41.04 version has gone waacky, it was at a hundred percent completion, and BOINC stopped to resume an xtremlabs WU, upon resuming the Einstein WU still showing CPU time of 1 hr 7 minutes went to 0% completion, and time left went to 3 more hours...I double checked, its the same work unit, since boinc hasn't sent off any completed workunits within the past hour.
Human Stupidity Is Infinite...