1) Message boards : ATLAS application : ATLAS problem - long running but not using any CPU (Message 41595)
Posted 15 Feb 2020 by hsdecalc
Post:
A lot of informations are here: Checklist Version 3 for Atlas@Home..
Xml-file must be created if you want modifiy some preferences.
Create it in folder ..:\BOINC\projects\lhcathome.cern.ch_lhcathome\app_config.xml.
Example:

<app_config>
<app>
<name>ATLAS</name>
<max_concurrent>1</max_concurrent>
</app>
<!-- 3000 + (900 * Cores) = 2c=4800,3c=5700, 4c=6600 -->
<app_version>
<app_name>ATLAS</app_name>
<avg_ncpus>4.000000</avg_ncpus>
<max_ncpus>4.000000</max_ncpus>
<plan_class>vbox64_mt_mcore_atlas</plan_class>
<cmdline>--memory_size_mb 6600</cmdline>
</app_version>
<project_max_concurrent>2</project_max_concurrent>
</app_config>
2) Message boards : ATLAS application : ATLAS problem - long running but not using any CPU (Message 41503)
Posted 9 Feb 2020 by hsdecalc
Post:
Hi, in my cases there is insufficient memory available. See post ..crappy task
There are also jobs running from the project "Amicable Numbers" and they need a huge amount of memory.
So I have to switch between these projects manually..
Why can't Atlas catch the problem and stop execution (not enough memory)?
3) Message boards : ATLAS application : Another crappy task (Message 41321)
Posted 21 Jan 2020 by hsdecalc
Post:
Some Atlas-jobs on two of my PCs didn't start their work (comp. 10569623 and 10382024). They run endless, doing nothing.
I see two types of errors in the log files (stderr.txt or VBox.log):

1. Samples like this:
2020-01-18 06:57:59 (9840): Guest Log: Checking CVMFS...
2020-01-18 06:58:00 (9840): Guest Log: Failed to check CVMFS, check output from cvmfs_config probe:
2020-01-18 06:58:01 (9840): Guest Log: Probing /cvmfs/atlas.cern.ch... Failed!
2020-01-18 06:58:01 (9840): Guest Log: Probing /cvmfs/atlas-condb.cern.ch... Failed!
2020-01-18 06:58:01 (9840): Guest Log: Probing /cvmfs/grid.cern.ch... Failed!
2020-01-18 06:58:11 (9840): Guest Log: VBoxService 5.2.32 r132073 (verbosity: 0) linux.amd64 (Jul 12 2019 10:32:28) release log
2020-01-18 06:58:11 (9840): Guest Log: 00:00:00.000172 main Log opened 2020-01-18T06:58:09.566143000Z
2020-01-18 06:58:11 (9840): Guest Log: 00:00:00.000279 main OS Product: Linux
2020-01-18 06:58:11 (9840): Guest Log: 00:00:00.000316 main OS Release: 3.10.0-957.27.2.el7.x86_64


and never this lines:

00:00:30.325812 VMMDev: Guest Log: CVMFS is ok

The tasks probably have not enougth memory:

00:00:00.435418 Host RAM: 16294MB (15.9GB) total, 4069MB (3.9GB) available
00:00:00.435420 Executable: C:\Program Files\Oracle\VirtualBox\VBoxHeadless.exe
00:00:00.435421 Process ID: 6892
or
00:00:00.936929 Host RAM: 16294MB (15.9GB) total, 3608MB (3.5GB) available
00:00:00.936931 Executable: C:\Program Files\Oracle\VirtualBox\VBoxHeadless.exe
00:00:00.936931 Process ID: 15204


2. A second type, with enougth memory (8.2GB) is here:

00:00:32.202025 VMMDev: Guest Log: Checking CVMFS...
00:00:39.401098 VMMDev: Guest Log: VBoxService 5.2.32 r132073 (verbosity: 0) linux.amd64 (Jul 12 2019 10:32:28) release log
00:00:39.401126 VMMDev: Guest Log: 00:00:00.000235 main Log opened 2020-01-20T13:43:51.889924000Z
00:00:39.401187 VMMDev: Guest Log: 00:00:00.000347 main OS Product: Linux
00:00:39.401221 VMMDev: Guest Log: 00:00:00.000383 main OS Release: 3.10.0-957.27.2.el7.x86_64
00:00:39.401350 VMMDev: Guest Log: 00:00:00.000510 main OS Version: #1 SMP Mon Jul 29 17:46:05 UTC 2019
00:00:39.401388 VMMDev: Guest Log: 00:00:00.000550 main Executable: /opt/VBoxGuestAdditions-5.2.32/sbin/VBoxService
00:00:39.401399 VMMDev: Guest Log: 00:00:00.000550 main Process ID: 1540
00:00:39.401407 VMMDev: Guest Log: 00:00:00.000551 main Package type: LINUX_64BITS_GENERIC
00:00:39.402401 VMMDev: Guest Log: 00:00:00.001548 main 5.2.32 r132073 started. Verbose level = 0
00:00:39.403521 Guest Control: GUEST_MSG_REPORT_FEATURES: 0x1, 0x8000000000000000
00:00:49.405064 VMMDev: Guest Log: 00:00:10.004191 timesync vgsvcTimeSyncWorker: Radical guest time change: -3 607 552 511 000ns (GuestNow=1 579 524 224 340 661 000 ns GuestLast=1 579 527 831 893 172 000 ns fSetTimeLastLoop=true )
00:10:10.286013 Display::i_handleDisplayResize: uScreenId=0 pvVRAM=000000000afc0000 w=800 h=600 bpp=0 cbLine=0xC80 flags=0x5 origin=0,0
05:36:04.375518 Changing the VM state from 'RUNNING' to 'SUSPENDING'
05:36:04.418269 PDMR3Suspend: 42 532 011 ns run time
05:36:04.418314 Changing the VM state from 'SUSPENDING' to 'SUSPENDED'

------------------------------------------------------------------------------------------------------

I checked according to the checklist:
My AntiVirus ignores the BOINC_Data-Directory. I reinstalled Boinc and different versions of VM.
What else could help here.

Older results (last 30 days) with errors are:
https://lhcathome.cern.ch/lhcathome/result.php?resultid=257971613
https://lhcathome.cern.ch/lhcathome/result.php?resultid=257349880
https://lhcathome.cern.ch/lhcathome/result.php?resultid=257189343
https://lhcathome.cern.ch/lhcathome/result.php?resultid=256751957
https://lhcathome.cern.ch/lhcathome/result.php?resultid=258528225
https://lhcathome.cern.ch/lhcathome/result.php?resultid=258573637
https://lhcathome.cern.ch/lhcathome/result.php?resultid=259458789
4) Questions and Answers : Preferences : CPU does not have hardware virtualization, but changing properties does not work. (Message 39167)
Posted 22 Jun 2019 by hsdecalc
Post:
I checked again, Hyper-V service task where in the tasklist. Hyper-V was still installed.
I checked it some days before, but maybe at the wrong pc, I use Teamviewer to control my PCs.
I remove the feature, reboot, now ok, got ATLAS-jobs.
Thanks.
5) Questions and Answers : Preferences : CPU does not have hardware virtualization, but changing properties does not work. (Message 39164)
Posted 22 Jun 2019 by hsdecalc
Post:
Thanks, Bios is ok, VT-X is enabled, since years.
The PC was okay until a few weeks ago. I only got Sixtrack WUs, no Simulation?!
I checked it too with "LeoMoon CPU-V.exe". All green.
How can I remove the PC from LHC and add it as a new CPU?

I try to connect to http://boinc.berkeley.edu/, to download a new version. But it is offline since yesterday?

I try to install Boinc later.
6) Questions and Answers : Preferences : CPU does not have hardware virtualization, but changing properties does not work. (Message 39160)
Posted 21 Jun 2019 by hsdecalc
Post:
I don't get VM Tasks. The cause is:

In your BOINC_Data-Directory you will find a client_state.xml. Open this with a simple editor and search for:
<p_vm_extensions_disabled>1</p_vm_extensions_disabled>


I use this pc for many years with vm=on/ok.
- I check my bios=ok, removed the PC form LHC in Boincstats, removed the project LHC from the PC,
- closed Boinc, changed the value to 0/zero, start Boinc, add PC,...

But the information for this host didn't change, still:
Virtualization Virtualbox (6.0.8) installed, CPU does not have hardware virtualization support
File client_state.xml ist now ok.

How can you update the preferences of this host?

My client_state.xml:
<client_state>
<host_info>
<timezone>7200</timezone>
<domain_name>CRUNCHER</domain_name>
<ip_addr>192.168.56.1</ip_addr>
<host_cpid>50...</host_cpid>
<p_ncpus>12</p_ncpus>
<p_vendor>GenuineIntel</p_vendor>
<p_model>Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz [Family 6 Model 63 Stepping 2]</p_model>
<p_features>fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush acpi mmx fxsr sse sse2 ss htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes f16c rdrandsyscall nx lm avx avx2 tm2 pbe fsgsbase bmi1 smep bmi2</p_features>
<p_fpops>4334152082.423791</p_fpops>
<p_iops>16775523389.069212</p_iops>
<p_membw>100000000.000000</p_membw>
<p_calculated>1561142428.989729</p_calculated>
<p_vm_extensions_disabled>0</p_vm_extensions_disabled>
<m_nbytes>17086554112.000000</m_nbytes>
<m_cache>262144.000000</m_cache>
<m_swap>20685266944.000000</m_swap>
<d_total>645921767424.000000</d_total>
<d_free>154504527872.000000</d_free>
<os_name>Microsoft Windows 10</os_name>
<os_version>Professional x64 Edition, (10.00.18362.00)</os_version>
<n_usable_coprocs>1</n_usable_coprocs>
<wsl_available>1</wsl_available>
<wsl>
<distro>
<distro_name>Ubuntu</distro_name>
<name>Linux Ubuntu</name>
<version>Ubuntu 16.04.3 LTS [4.4.0-18362-Microsoft]</version>
<is_default>1</is_default>
</distro>
</wsl>
<virtualbox_version>6.0.8</virtualbox_version>
<coprocs>
<coproc_cuda>
7) Message boards : ATLAS application : Uploads of finished tasks not possible since last night (Message 33316)
Posted 13 Dec 2017 by hsdecalc
Post:
Still have four tasks, which are not uploaded. Stops at 100% or less or does not start. No upload at the moment.
8) Message boards : Number crunching : No Tasks Available (CMS, Theory) (Message 28700)
Posted 28 Jan 2017 by hsdecalc
Post:
This morning I got four LHCb tasks (for the first time since three days) - sent: 28 Jan 2017, 6:11:57 UTC
Server Status:

Tasks by application
Application Unsent In progress Runtime of last 100 tasks in hours:
SixTrack 218897 275922 0.54 (0.01 - 93.22) 5504
sixtracktest 0 0 --- 0
CMS Simulation 100 3854 14.77 (0.47 - 18.24) 95
LHCb Simulation 95 734 14.33 (3.28 - 36.1) 51
Theory Simulation 100 3933 12.45 (0.41 - 18.33) 110
ATLAS Simulation 11 121 2.1 (0.31 - 8.04) 11
9) Message boards : Number crunching : No Tasks Available (CMS, Theory) (Message 28697)
Posted 27 Jan 2017 by hsdecalc
Post:
Since Jan 25nd on one pc I get no xxx Simulations tasks. I reboot it twice.

27.01.2017 19:16:03 | LHC@home | Sending scheduler request: Requested by user.
27.01.2017 19:16:03 | LHC@home | Requesting new tasks for CPU
27.01.2017 19:16:04 | LHC@home | Scheduler request completed: got 0 new tasks
27.01.2017 19:16:04 | LHC@home | No tasks sent
27.01.2017 19:16:04 | LHC@home | No tasks are available for CMS Simulation
27.01.2017 19:16:04 | LHC@home | No tasks are available for LHCb Simulation
27.01.2017 19:16:04 | LHC@home | No tasks are available for Theory Simulation
27.01.2017 19:16:04 | LHC@home | No tasks are available for ATLAS Simulation
27.01.2017 19:16:04 | LHC@home | New computer location: work


I changed the location to "nothing" (which allows all applications) and in a second I got 39 SixTrack tasks:

27.01.2017 19:27:21 | LHC@home | update requested by user
27.01.2017 19:27:22 | LHC@home | Sending scheduler request: Requested by user.
27.01.2017 19:27:22 | LHC@home | Requesting new tasks for CPU
27.01.2017 19:27:24 | LHC@home | Scheduler request completed: got 39 new tasks
27.01.2017 19:27:24 | LHC@home | New computer location:
27.01.2017 19:27:26 | LHC@home | Started download of w1_chrom-12.0-40.0__26__s__64.27_59.295__4_5__5__45_1_sixvf_boinc3064.zip
27.01.2017 19:27:26 | LHC@home | Started download of w1_chrom-12.0-40.0__26__s__64.27_59.295__4_5__5__60_1_sixvf_boinc3066.zip


I'm getting further on no CMS/LHCb/..tasks.
On a second PC I got one Theory Simulation task at 27 Jan 2017, 10:20:15. This is the only one since three days.
Both PC with Win10 and VM 5.1.10.

Server Status:

Aufgaben pro Anwendung
Anwendung Ungesendet In Bearbeitung Laufzeiten der letzten 100 Aufgaben in h: durchschnitt,
SixTrack 378520 247879 0.51 (0 - 80.22) 3511
sixtracktest 0 0 --- 0
CMS Simulation 100 3921 15.5 (0.24 - 23.51) 73
LHCb Simulation 100 572 13.54 (1.19 - 36.09) 61
Theory Simulation 100 3839 12.31 (0.41 - 24.06) 115
ATLAS Simulation 110 64 1.7 (0.19 - 4.69) 6

10) Message boards : Number crunching : Got to much tasks, runing 5 times longer as predict. (Message 27680)
Posted 30 Jan 2016 by hsdecalc
Post:
On my Win10 PC with 3.3Ghz i7-CPU I've got >120 tasks with a estimated time of 00:09:57 (SixTrack 451.07 (sse2))
But they needs about 50 minutes each! I earn only 38 credits.
Is this ok?

82931746 39269091 10382024 29 Jan 2016, 20:42:59 UTC 30 Jan 2016, 9:42:51 UTC Fertig und Bestätigt 2,791.31 2,680.05 38.16 SixTrack v451.07 (sse2)



©2024 CERN