Constellation is down since Monday, without any information.

No upload and no website.

Regarding the policy change, as I said earlier, I asked about it (thinking it was a bug), but David Anderson said it was not a bug. The logic is: If you have 8 CPUs, and 8 CPU tasks, and several GPU tasks, and the only way they can get done before deadlines is if you run those 8 CPU tasks NOW (EDF / High Priority), then they get priority over your GPU tasks, because spending CPUs on GPU tasks would make some of those CPUs miss deadline.

Making deadlines (of any task type), takes priority over scheduling GPUs.

You're welcome to request, in an Alpha Mailing List email, some sort of cc_config entry to override that behavior. I will be sticking with the current behavior, as I think it is correct, albeit odd.

Regarding your issue with weird scheduling decisions. What was the order the tasks were assigned to you? In same or different scheduler requests? What was the order the tasks had all of their input files downloaded?

Is it possible that your non-OWS tasks already had processes created (ie were running?) If not, then, I guess I still haven't figured out how it chooses :)

So this leads me to believe that, maybe it's likely that completion estimation got screwed up on either the application that went EDF, or one of the other applications that you had tasks for.

The real problem you are having is: Why does it think it can't make the deadline on these jobs? Or, better yet, why does it run other CPU jobs first? That may boil down to things like "were the running CPU jobs in the middle of a non-checkpointed timeslice?" and "were the running CPU jobs running for a project that had higher resource share setting" and "were the running CPU jobs running for a project that had a lower Recent Estimated Credit (REC) than what was needed to meet resource share?" I know the documentation doesn't really specify that, but it's true.

Is this comment from the same as the Ed A on the alpha mail list? My post was a correction, in case a reader flips through with search and uses the wrong code! Thanks though for pointing out what the topic originally was ;>)

Since when I made this post and because many don't do the famous RTFM, it came out that nvidia and ati has to be capitalized in the type line. The wiki was corrected [with the question by the dev., why this could have been wrongly documented for so long], of course others asking then why it's case sensitive... well, at least now we know why there was loads of headscratching and unexplained behavior ;D. The option now [should] read [with one of the 3 generally referenced GPU brands]

I had high hopes for 7.0.45. Unfortunately work fetch has not improved and the exclusions problem has not been helped at all.

You will have to email the BOINC Alpha email list about that, as else the developers will not know about it.

Add logs with appropriate debug flags enabled to show what you see.
If necessary add screen shots, but when you do, add David as a CC as the list will drop these attachments.

Also version 7.0.4x introduces the new app_config.xml mechanism, by which you can set stuff like number of a particular app to run on one gpu without a full app_info. Perhaps you can try setting the exclusions in that file and see if the results are any different?