Message boards :
ATLAS application :
Download failures
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 8 · Next
Author | Message |
---|---|
Send message Joined: 13 Apr 18 Posts: 443 Credit: 8,438,885 RAC: 0 |
There doesn't seem to be a fundamental problem. Internally everything seems to work fine. This result uploaded 143M in 14s. We are monitoring the transfers and will post some details on failures shortly. Check this host and this host. There is a problem. If your monitoring tools aren't seeing a problem then, with all due respect, your monitoring tools are broken. |
Send message Joined: 2 May 07 Posts: 2193 Credit: 173,356,490 RAC: 51,097 |
Is there a permission issue with the scheduler? Now since three days 87 download errors with http-Error! It needs some investigation, please. |
Send message Joined: 15 Jun 08 Posts: 2509 Credit: 248,921,808 RAC: 129,940 |
Error rate "download error" (last 24 h) ATLAS: 62 % other projects: 0 % |
Send message Joined: 13 May 14 Posts: 387 Credit: 15,314,184 RAC: 0 |
There are actually two problems at the moment: - The instant download failures are caused by the database problem we had last week which wiped all running and recently completed WU. Basically BOINC is generating new WU for tasks which already finished before the database accident, and for those tasks the input was already deleted. These are relatively harmless since the failure is instant. - The stalled transfer problem, when downloads start and the at some point stop working. This problem is worse because it can be many hours before the transfers succeed. We currently don't know the reason for this problem but we are investigating. |
Send message Joined: 24 Oct 04 Posts: 1156 Credit: 52,919,269 RAC: 63,376 |
Yes David as you probably know the Atlas multi-cores are running with no problems over at -dev with Linux and Windows with the ATLAS Simulation v0.50 (native_mt) x86_64-pc-linux-gnu and v0.51 (vbox64_mt_mcore_atlas) windows_x86_64 .....so 1.01 is having a problem at the server since none of the OS versions work here right now. I only tried it once to see if it was all OS's and what part of the planet since that is a problem once in a while (server hand shaking) But Theory, SixTrack and LHCb work here fine. |
Send message Joined: 15 Nov 14 Posts: 602 Credit: 24,371,321 RAC: 0 |
I only tried it once to see if it was all OS's and what part of the planet since that is a problem once in a while (server hand shaking). I just reattached, and the .vdi (ATLASM_2017_03_01.vdi) downloaded OK at 2500 Kbps (Ubuntu 16.04, i7-4790). All the others did too, except: "BJAODmuhrwsnyYickojUe11pABFKDmABFKDmIeJZDmABFKDmO06ZKm_EVNT.14296435._001513.pool.root.1" is now down to 20 Kbps, and slowing down. This is in eastern Pennsylvania. EDIT: I just attached a Win7 64-bit machine to LHCb, and LHCb_2017_12_14.vdi is now stuck at 9% downloaded. All the other downloaded OK. Whether this is related to ATLAS is another question. |
Send message Joined: 20 Jun 14 Posts: 380 Credit: 238,712 RAC: 0 |
The instant download failures issues should now be resolved. There may still be a few but the number of failures should be much less. We are still investigating the slowing downloads. |
Send message Joined: 19 Feb 08 Posts: 708 Credit: 4,336,250 RAC: 0 |
Two Atlas tasks downloaded on my Windows 10 PC. One downloaded OK, ran and validated with no HITS file, as usual on this PC. The other is stuck. Tullio |
Send message Joined: 15 Nov 14 Posts: 602 Credit: 24,371,321 RAC: 0 |
Two native ATLAS just downloaded here without a problem. |
Send message Joined: 2 May 07 Posts: 2193 Credit: 173,356,490 RAC: 51,097 |
Have today some download-failure 8.30 UTC. Upload stops also. |
Send message Joined: 9 Dec 14 Posts: 202 Credit: 2,533,875 RAC: 0 |
|
Send message Joined: 19 Feb 08 Posts: 708 Credit: 4,336,250 RAC: 0 |
All Atlas downloads fail on my Windows 10 PC. I have not changed anything. Tullio |
Send message Joined: 14 Jan 10 Posts: 1378 Credit: 9,162,540 RAC: 5,071 |
LHC@home 23 Aug 13:20:14 CEST Finished download of jlQNDmympCtnlyackoJh5iwnABFKDmABFKDmZFEODmABFKDmHuy9Eo_EVNT.14808120._000761.pool.root.1 LHC@home 23 Aug 13:20:23 CEST Finished download of APMMDmOezCtnyYickojUe11pABFKDmABFKDmhA5ODmABFKDmCh75un_EVNT.14808120._000793.pool.root.1 |
Send message Joined: 19 Feb 08 Posts: 708 Credit: 4,336,250 RAC: 0 |
One more download failure. The other is running. Tullio |
Send message Joined: 18 Dec 15 Posts: 1752 Credit: 115,677,783 RAC: 87,041 |
hm, strange. All my ATLAS downloads are okay. |
Send message Joined: 16 May 14 Posts: 15 Credit: 7,357,879 RAC: 0 |
i'm getting this on both atlas and lhc downloads 8/23/2018 9:34:11 AM | LHC@home | Giving up on download of w-c5_-0.012_job.B1inj_c5_-0.012.2938__47__s__64.28_59.31__6.1_8.1__6__27_1_sixvf_boinc8042.zip: permanent HTTP error |
Send message Joined: 27 Sep 08 Posts: 823 Credit: 684,419,576 RAC: 144,190 |
I see the issue with sixtrack |
Send message Joined: 13 Apr 18 Posts: 443 Credit: 8,438,885 RAC: 0 |
Numerous download errors here too. |
Send message Joined: 14 Jan 10 Posts: 1378 Credit: 9,162,540 RAC: 5,071 |
Me too now: 24 Aug 06:56:24 CEST Giving up on download of AIMNDmexGDtnlyackoJh5iwnABFKDmABFKDmHlEVDmABFKDmU9wZOo_EVNT.15161510._000143.pool.root.1: permanent HTTP error 24 Aug 06:56:24 CEST Giving up on download of AIMNDmexGDtnlyackoJh5iwnABFKDmABFKDmHlEVDmABFKDmU9wZOo_input.tar.gz: permanent HTTP error 24 Aug 06:56:27 CEST Giving up on download of rte_AIMNDmexGDtnlyackoJh5iwnABFKDmABFKDmHlEVDmABFKDmU9wZOo.tar.gz: permanent HTTP error 24 Aug 06:56:27 CEST Giving up on download of boinc_job_script.1gxrGC: permanent HTTP error |
Send message Joined: 15 Jun 08 Posts: 2509 Credit: 248,921,808 RAC: 129,940 |
Here too. It can be seen on all of my hosts and Sixtrack is also affected. Typical log entries: Fr 24 Aug 2018 06:22:48 CEST | LHC@home | Scheduler request completed: got 1 new tasks Fr 24 Aug 2018 06:22:50 CEST | LHC@home | Started download of IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin_EVNT.15161510._000139.pool.root.1 Fr 24 Aug 2018 06:22:50 CEST | LHC@home | Started download of IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin_input.tar.gz Fr 24 Aug 2018 06:22:52 CEST | LHC@home | Giving up on download of IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin_EVNT.15161510._000139.pool.root.1: permanent HTTP error Fr 24 Aug 2018 06:22:52 CEST | LHC@home | Giving up on download of IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin_input.tar.gz: permanent HTTP error Fr 24 Aug 2018 06:22:52 CEST | LHC@home | Started download of rte_IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin.tar.gz Fr 24 Aug 2018 06:22:52 CEST | LHC@home | Started download of boinc_job_script.ma5FQa Fr 24 Aug 2018 06:22:54 CEST | LHC@home | Giving up on download of rte_IVlKDmIiGDtnlyackoJh5iwnABFKDmABFKDmmGAVDmABFKDmpPIvin.tar.gz: permanent HTTP error Fr 24 Aug 2018 06:22:54 CEST | LHC@home | Giving up on download of boinc_job_script.ma5FQa: permanent HTTP error Same host was succesful just a few minutes later: Fr 24 Aug 2018 06:34:39 CEST | LHC@home | Scheduler request completed: got 1 new tasks Fr 24 Aug 2018 06:34:41 CEST | LHC@home | Started download of KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo_EVNT.15161510._000103.pool.root.1 Fr 24 Aug 2018 06:34:41 CEST | LHC@home | Started download of KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo_input.tar.gz Fr 24 Aug 2018 06:34:43 CEST | LHC@home | Finished download of KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo_input.tar.gz Fr 24 Aug 2018 06:34:43 CEST | LHC@home | Started download of rte_KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo.tar.gz Fr 24 Aug 2018 06:34:44 CEST | LHC@home | Finished download of rte_KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo.tar.gz Fr 24 Aug 2018 06:34:44 CEST | LHC@home | Started download of boinc_job_script.qkP1OA Fr 24 Aug 2018 06:34:45 CEST | LHC@home | Finished download of boinc_job_script.qkP1OA Fr 24 Aug 2018 06:35:06 CEST | LHC@home | Finished download of KlZNDmTQADtnlyackoJh5iwnABFKDmABFKDml1KTDmABFKDmSU8xVo_EVNT.15161510._000103.pool.root.1 |
©2024 CERN