LHC@home

The cleanup script is stuck due to load ...

which I can fully believe; that's why I was so surprised that even more new tasks (3257 are available right now, according to the info from the Server Status Page) were bumped into the mills - which is bound to be counter-productive in such a situation.

the upload server obviously was switched on again.
And, how nice, two of my finished tasked were uploaded. For the others, same thing happens as on Tuesday, right after the problems began: the upload progresses to 100%, then it stays there for a while, and then it's reset to 0.00% :-(

problem of http ?? for upload-error

http://boinc.berkeley.edu/dev/forum_thread.php?id=954

problem of http ??

whatever the problem really is - stopping the server for some time delivered good results for very short time only.
Since hours, the uploads again don't work :-(

it's not a good idea to place new Atlas Task on server.
Even the new once placed today run into the upload failure.
So the size of the problem will increase only.

I finally aborted all four of my stuck ATLAS tasks (two on each of two machines). I didn't even get an acknowledgement back that they had been aborted.
I think they are dead to the world.

it's not a good idea to place new Atlas Task on server.
Even the new once placed today run into the upload failure.
So the size of the problem will increase only.

I guess they want to reach the 25.000 task mark by all means. Even knowing that this doesn't make any sense in the current situation :-(

I finally aborted all four of my stuck ATLAS tasks

I'll also change to other projects. Even more that most probably not much will happen over the upcoming weekend.

Well speak of the devil. After aborting my ATLAS tasks (VBox), they sent me "2.52 ATLAS Simulation (native_mt)" for my Ubuntu machine.

It was worth the trouble.

Some progress, perhaps... I've manged to upload and report six of eight tasks that were stuck uploading. The two that are still there were the first ones to get stuck, I believe.

+1

47290 LHC@home 12/15/2017 5:42:38 PM Temporarily failed upload of 63gNDml8GirnDDn7oo6G73TpABFKDmABFKDmrUNKDmABFKDm1XIRLo_1_r1909933188_ATLAS_result: transient HTTP error

This one is still stuck for me. Others have uploaded since.

After all this I now get this message
12/15/2017 8:44:05 PM | LHC@home | [error] Error reported by file upload server: Server is out of disk space


What gives? multiple new upload servers and no disk space????

Meanwhile, all my ATLAS tasks (the "old" ones as well as the new ones) are in backoff status. Regardless of how often I push the "retry now" button, they fall back to backoff within 1 or 2 seconds. So the whole upload system seems to have broken down by now. No wonder though, after despite of the problems that persisted since Tuesday, more and more new tasks were and are still bumped into the pipeline (a procedure which I find very unprofessional).

Some of my "waiting" tasks have their deadline later today, so they will become invalid, and all these many hours of crunching time finally was for nothing :-(

Since we are having the weekend now, I suspect that nothing will happen till Monday, or even later. And so, many more tasks from many volunteers will meanwhile reach their deadline and hence become invalid. And many more tasks will increase the queue of tasks waiting for upload - everyone can imagine the overload that is bound to follow.
Does this all make any sense?

Erich,
your first ATLAS getting out of the Time-limit is on Monday.
The problem of Atlas is at the moment the upload-Server.
Download is ok, running the tasks is ok. Last night some tasks had uploaded.
So, when we have luck, there is someone in Cern-IT working today, otherwise monday.

I have been patient as requested, but I still can't upload:

16/12/2017 08:29:55 | LHC@home | Started upload of 4FYKDm9M7irnSu7Ccp2YYBZmABFKDmABFKDmStGKDmABFKDm3GgJWn_1_r494246443_ATLAS_result
16/12/2017 08:29:58 | LHC@home | [error] Error reported by file upload server: Server is out of disk space
16/12/2017 08:29:58 | LHC@home | Temporarily failed upload of 4FYKDm9M7irnSu7Ccp2YYBZmABFKDmABFKDmStGKDmABFKDm3GgJWn_1_r494246443_ATLAS_result: transient upload error
16/12/2017 08:29:58 | LHC@home | Backing off 04:46:25 on upload of 4FYKDm9M7irnSu7Ccp2YYBZmABFKDmABFKDmStGKDmABFKDm3GgJWn_1_r494246443_ATLAS_result

We stopped submitting new tasks yesterday afternoon but there are still a few left in the queue.

The upload server got completely full so I'm cleaning it now - there is an automatic cleaning tool but it wasn't cleaning enough to handle the huge volumes of data we got this week.

It is clear we have reached the limits of the current infrastructure (thank you all for getting us to these limits :) , but early in the new year we will move to different filesystems which will handle this load much better.

We'll do our best to make that fall over ASAP, I'm sure :)
Thank you for coming out on a Saturday morning with the drain cleaning rods.

It is clear we have reached the limits of the current infrastructure (thank you all for getting us to these limits :) , but early in the new year we will move to different filesystems which will handle this load much better.

Erich, your first ATLAS getting out of the Time-limit is on Monday.

that's what is shown in the list here on the Homepage. However, in the BOINC Manager, today's date is indicated as deadline. No idea how this discrepancy comes about, plus no idea which date finally will be the valid one.

Last night some tasks had uploaded

none of mine, unfortunately :-(

Good News: My first three native ATLAS on my two Ubuntu machines ran properly and completed without error.
They averaged about 3 1/2 hours on two cores per work unit (i7-4770, i7-4790).

Bad News: They are stuck in upload also.

May the New Year bring us some joy.

David wrote:

The upload server got completely full so I'm cleaning it now

any results yet?