Message boards :
Number crunching :
Postponed: VM job unmanageble, restarting later ?????
Message board moderation
Previous · 1 · 2
Author | Message |
---|---|
Send message Joined: 26 Mar 16 Posts: 30 Credit: 1,258,609 RAC: 0 ![]() ![]() |
NOW that is an acceptable answer ! Thank you for explaining the real thing ! Why does LHC bother with us at all ? One should not confuse the complexity of physics (-projects) with the simplicity of VirtualBox. Have a nice Sunday. |
Send message Joined: 26 Mar 16 Posts: 30 Credit: 1,258,609 RAC: 0 ![]() ![]() |
On the Top500 list IBM has reached the top with its Summit computer, which makes large use of nVidia Tesla GPU boards at 200 petaflops. The second is a Chinese supercomputer which was first last time, the third is another American computer, Sierra. The Piz Daint Swiss computer which was third is now sixth, the best Italian is thirteenth. Things change rapidly in the supercomputer world. Thanks - but has nothing to do with this thread ... Over and out. |
Send message Joined: 26 Mar 16 Posts: 30 Credit: 1,258,609 RAC: 0 ![]() ![]() |
This is the type of answers we all love ! Seems like you have been personally insulted ... But, just try to have a nice day ! Over and out. |
Send message Joined: 13 Apr 18 Posts: 443 Credit: 8,438,885 RAC: 0 ![]() ![]() |
Seems like you have been personally insulted ... ROFLMAO. Seems like you came here to rant over what you aren't talented enough to fix rather than learn how to fix it. You have an even nicer day. |
Send message Joined: 26 Mar 16 Posts: 30 Credit: 1,258,609 RAC: 0 ![]() ![]() |
Witzbold |
![]() ![]() Send message Joined: 13 Jul 05 Posts: 27 Credit: 392,531 RAC: 0 ![]() ![]() |
Had this "unmanageble" also. Exiting Boinc and restarting to restart the LHC Atlas jobs. I've 32GB and it never exceeded 1gb for atlas 8 cores and stopped and in the end the unit failed with NO credit. No I just marked again "keep no-gpu-jobs" in memory and sudden cpu increases to +95% (never saw this with LHC VM job before) in use while it was 10 when unmarked and not yet stopped so maybe this is it?!?!?! . ![]() ![]() |
Send message Joined: 2 May 07 Posts: 2260 Credit: 175,581,097 RAC: 15,522 ![]() ![]() ![]() |
196 (0x000000C4) EXIT_DISK_LIMIT_EXCEEDED |
![]() ![]() Send message Joined: 24 Oct 04 Posts: 1193 Credit: 58,985,736 RAC: 64,019 ![]() ![]() |
https://lhcathome.cern.ch/lhcathome/result.php?resultid=206268165 I would start by updating the version of VB https://www.virtualbox.org/wiki/Downloads And it is a good idea to let a single task like that to run without suspending and restarting since Atlas tasks don't like doing that and we have easier to run tasks here too. |
![]() ![]() Send message Joined: 18 Dec 16 Posts: 123 Credit: 37,495,365 RAC: 0 ![]() ![]() |
Hi, I had the same issue on one of my computers. I was using: - BOINC 7.10.2. - VirtualBox 5.2.8. - SSD for ProgramData/BOINC I have tried various tricks to solve the problem with no success. After reading this thread I finally decided to uninstall BOINC and VirtualBox and install the following conf: - BOINC 7.12.1. - VirtualBox 5.2.18. - Hard Disk for ProgramData/BOINC I am not sure which of those changes actually fixed the problem of those unmanageable VMs, but the new install works fine now for ATLAS. Hoping it helps. Herve We are the product of random evolution. |
Send message Joined: 12 Feb 14 Posts: 72 Credit: 4,639,155 RAC: 0 ![]() ![]() |
I have noticed that quitting BOINC, waiting for all of the tasks to cleanly shut down and get saved to disk, and then restarting BOINC fixes all of the work units affected by this problem. However, it does not prevent new work units from getting this problem. |
Send message Joined: 11 Apr 17 Posts: 39 Credit: 7,735,161 RAC: 0 ![]() ![]() |
Maybe a viewpoint could be: If the LHC devs don't want to support us peons (in the LHC programmers grand scheme), why should we spend our money, our compute time, our electricity charges -- supporting THEM? Volunteers, spending real money, supporting a project that doesn't support US? Is this where we are now? I wonder just what percentage of LHC computer needs are solved by thousands of people spending so much time and money to further science. |
Send message Joined: 2 May 07 Posts: 2260 Credit: 175,581,097 RAC: 15,522 ![]() ![]() ![]() |
David, You have found this Project yourself and you can leave it yourself if you want! |
Send message Joined: 11 Apr 17 Posts: 39 Credit: 7,735,161 RAC: 0 ![]() ![]() |
Everyone else and I are fully aware of that option, thank you very much. It is kind of you to remind us all. But not really helpful. |
©2025 CERN