Message boards : Number crunching : Error reported by file upload server: Server is out of disk space
Message board moderation
| Author | Message |
|---|---|
|
Send message Joined: 27 Sep 08 Posts: 931 Credit: 780,987,563 RAC: 81,604    |
As title |
|
Send message Joined: 14 Jan 10 Posts: 1551 Credit: 10,067,691 RAC: 816  |
Solved for the moment . . . |
|
Send message Joined: 16 Nov 25 Posts: 3 Credit: 3,232,836 RAC: 15,231  
|
The problem seems to have appeared again today with ATLAS tasks. jeu. 19 mars 2026 17:37:40 | LHC@home | [error] Error reported by file upload server: Server is out of disk space jeu. 19 mars 2026 17:37:40 | LHC@home | Temporarily failed upload of XaMKDmA05M9nsSi4ap6QjLDmwznN0nGgGQJmIVkRDmh31LDmqjhiln_0_r2007412987_ATLAS_result: transient upload error |
 Send message Joined: 17 Oct 11 Posts: 13 Credit: 1,568,472 RAC: 4,436  
|
Not just atlas :( ---------- 24/7 Crunching since 2011 ----------- DSKAG Austria: http://www.dskag.at 
|
|
Send message Joined: 18 Dec 15 Posts: 1978 Credit: 160,452,304 RAC: 49,488
|
what surprises me is that so far no one over there seems to have noticed that the disks are full :-( Besides, I wonder how this can happen - are there no alert provisions in place, e.g. automatic notification to the person in charge once the disks reach a certain filling percentage, or other things (blinking light, sound alarm, ... :-) |
|
Send message Joined: 7 Aug 13 Posts: 6 Credit: 1,134,166 RAC: 9,090 
|
I have same questions) |
|
Send message Joined: 17 Oct 11 Posts: 13 Credit: 1,568,472 RAC: 4,436
|
We just can wait and hope, weekend is coming :/ But yeah in most projects i wonder sometimes, but then i realize they does no have the personal for such things, but CERN? O.o Set up a PRTG instance or somethin for your IT Support. ---------- 24/7 Crunching since 2011 ----------- DSKAG Austria: http://www.dskag.at
|
|
Send message Joined: 18 Dec 15 Posts: 1978 Credit: 160,452,304 RAC: 49,488
|
In reply to dskagcommunity's message of 20 Mar 2026: We just can wait and hope, weekend is coming :/I am used to the "disk full" problem with GPUGRID - there is happens quite often, and I am wondering that still they haven't set up procedures to avoid this problem (However, they seem to have quite different problems lately - the availability of tasks has decreaded markedly within the past 1 year - sometimes I have the impression that the project does no longer exist). But that CERN would ever run out of disk space - that's new to me :-) |
|
Send message Joined: 18 Dec 15 Posts: 1978 Credit: 160,452,304 RAC: 49,488
|
short time ago, back-upped tasks started to upload :-) However, no new ones available for download :-( |
|
Send message Joined: 4 Mar 20 Posts: 23 Credit: 7,998,613 RAC: 8,357
|
Happening again. 25/03/2026 19:42:19 | LHC@home | [error] Error reported by file upload server: Server is out of disk space |
|
Send message Joined: 18 Dec 15 Posts: 1978 Credit: 160,452,304 RAC: 49,488
|
same here :-( Unbelieveable that there is no pre-alert system in place. What has changed vis-a-vis all the years before? I don't remember having experienced this problem at any earlier time. |
|
Send message Joined: 17 Oct 11 Posts: 13 Credit: 1,568,472 RAC: 4,436
|
Ooohhh boiiiiiiii ---------- 24/7 Crunching since 2011 ----------- DSKAG Austria: http://www.dskag.at
|
|
Send message Joined: 7 Aug 13 Posts: 6 Credit: 1,134,166 RAC: 9,090
|
same here |
 Magic Quantum Mechanic Send message Joined: 24 Oct 04 Posts: 1300 Credit: 95,664,935 RAC: 22,681
|
I have 2 -dev Dockers and one Docker for here that have been trying to send in for a couple hours but no luck (and some 8-core Atlas) |
|
Send message Joined: 5 Apr 25 Posts: 82 Credit: 2,389,259 RAC: 7,919  
|
In reply to Magic Quantum Mechanic's message of 25 Mar 2026: (and some 8-core Atlas) I'll take the opportunity to veer off-topic a bit. Is it worth trying to run 8-core ATLAS instead of quad? Does CPU efficiency remain linear? At one point I set the max # to 8 but still kept getting quads (on a 8C/16T CPU) so I reverted the settings and left it at 4. 
|
|
Send message Joined: 14 Jan 10 Posts: 1551 Credit: 10,067,691 RAC: 816 |
In reply to Magic Quantum Mechanic's message of 25 Mar 2026: I have 2 -dev Dockers and one Docker for here that have been trying to send in for a couple hours but no luck (and some 8-core Atlas)Sending Theory results to the dev-system is no problem for me. What I've understood, that there's a problem with storage further in the chain for ATLAS jobs that should be transferrred from the BOINC server to their system. |
|
Send message Joined: 5 Apr 25 Posts: 82 Credit: 2,389,259 RAC: 7,919
|
Managed to upload and report 4 of 8 tasks waiting. Now the disk is full again. Retries sometimes help, maybe they started clearing up the clutter. After a few minutes and a few more retries: 8/8
|
|
Magic Quantum Mechanic Send message Joined: 24 Oct 04 Posts: 1300 Credit: 95,664,935 RAC: 22,681
|
In reply to Crystal Pellet's message of 26 Mar 2026: In reply to Magic Quantum Mechanic's message of 25 Mar 2026: It was a certain time that they would not send them in where I would get it at -dev for both Docker and Atlas 3/25/2026 11:23:21 PM | lhcathome-dev | Backing off 04:32:12 on upload of Theory_2922-4790729-720_0_r950267645_result But since I am always awake and checking after 3am I tried and they are all sent in finally.......although uploads of Atlas from my Starlink is a bit slow and about twice as long as a d/l But they are in and I am going to run a few less right now than usual for a while It was during a time when you didn't have any to send in at dev Edit ; it just did it again at -dev with a Docker 3/26/2026 4:23:11 AM | lhcathome-dev | Backing off 00:15:31 on upload of Theory_2922-4896208-720_0_r1298637244_result Internet speed test 263.3 Mbps download 13.4 Mbps upload ..........(4:30am goodnight) |
 Send message Joined: 28 Sep 04 Posts: 802 Credit: 65,414,561 RAC: 24,704
|
Upload server has some new error: 5007 LHC@home 27-03-2026 10:34 [error] Error reported by file upload server: EOF on socket read : asked for 262144, got 46720 
|
©2026 CERN