The simulator has logging outputs that the normal client does not have.
But this is the idea I was trying to get across.
jm7
"Paul D. Buck"
<p.d.b...@comcast
.net> To
David Anderson
01/08/2010 01:31 <[email protected]>
PM cc
[email protected], BOINC
Developers Mailing List
<[email protected]>
Subject
Re: [boinc_dev] [boinc_alpha] EDF
and multi CPU tasks.
If the simulation ran as a task under the real BOINC then it could.
In other words, the simulator would be an application run under BOINC in
which each simulation run (or run set) would be a separate task.
I join BOINC project and as new schedulers are to be tried tasks would be
issued and run by the people that are attached. Returned results would
show the effects of the changes.
To make this work of course the client and thus the simulator would need to
have additional logging outputs as I have suggested in other posts. We
currently do not keep any sort of history information log as to what was
done when and how and in conjunction with what other projects...
On Jan 8, 2010, at 10:20 AM, David Anderson wrote:
> I don't understand what you mean.
> Simulation lets you study the interactions of
> long/short jobs, multithread jobs, GPU jobs, multiple projects, etc.,
> quickly and with quantitative and reproducible results.
> Anything involving the real BOINC client doesn't have these properties.
>
> [email protected] wrote:
>> It would be good if we had a suite of tests to run CPU schedulers
through
>> and a proposed CPU scheduler change could be tested quickly. I proposed
>> setting this up as the "BOINC" project tasks. The memorex in this case
>> could get us answers about the effectiveness much faster than live does.
>> The problem is that the edge conditions do not happen frequently. Most
of
>> the time on most machines any CPU scheduler will work. It is only
>> sometimes that there is a major problem where some task will be reported
>> weeks late, or a resource is ignored for a day or two...
>>
> _______________________________________________
> boinc_dev mailing list
> [email protected]
> http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev
> To unsubscribe, visit the above URL and
> (near bottom of page) enter your email address.
_______________________________________________
boinc_dev mailing list
[email protected]
http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev
To unsubscribe, visit the above URL and
(near bottom of page) enter your email address.
