LHC@home

I was not even aware that Theory now again can run on more than 1 core; I think this was the case long time ago (if I remember right, but I might be mistaken), and then Theory was switched back to 1 core only.

Here you see a Theory task that ran on 2 cores: https://lhcathome.cern.ch/lhcathome/result.php?resultid=414709237
Run time 3 hours 37 min 42 sec
CPU time 4 hours 8 min 22 sec
No big advantage and BOINC very often don't report the right CPU-time used, but equals elapsed and cpu-time.
In the result:
2024-10-04 03:43:06 (1376): Setting Memory Size for VM. (768MB)
2024-10-04 03:43:07 (1376): Setting CPU Count for VM. (2)

Please check at console 2 if the VM uses lots of RAM/swap.
If so, you may try a higher RAM value via app_config.xml.

(Console 3:) I already had set 768 MB for the Theory VMs. A running Herwig7 shows within the VM:
KiB Mem: 744976 total, 65940 free, 387080 used 291020 buff/cache
KiB Swap: 1048572 total, 871920 free. 176652 used. 203840 avail Mem

This doesn't look too bad.
A bit more (e.g. up to a total of 1 GB) may result in a greater cache (good for CVMFS) but as long as the used swap remains stable don't expect a significant increase in performance.

I was not even aware that Theory now again can run on more than 1 core; I think this was the case long time ago (if I remember right, but I might be mistaken), and then Theory was switched back to 1 core only.

Here you see a Theory task that ran on 2 cores: https://lhcathome.cern.ch/lhcathome/result.php?resultid=414709237
Run time 3 hours 37 min 42 sec
CPU time 4 hours 8 min 22 sec
No big advantage and BOINC very often don't report the right CPU-time used, but equals elapsed and cpu-time.
In the result:
2024-10-04 03:43:06 (1376): Setting Memory Size for VM. (768MB)
2024-10-04 03:43:07 (1376): Setting CPU Count for VM. (2)

Theory is still a 1-core app at the project server (prod).
Hence, the VMs should also be configured as 1-core VMs.
Otherwise you may get unwanted side effects like the one already mentioned or even a performance decrease.
Yes, VirtualBox needs much more cycles to control multicore VMs than to control 1-core VMs.

===> [runRivet] Wed Oct 9 07:34:01 UTC 2024 [boinc pp z1j 8000 30 - herwig7 7.2.1 nlo 100000 6]

EXIT_DISK_LIMIT_EXCEEDED ==> https://lhcathome.cern.ch/lhcathome/result.php?resultid=414826538

From BOINC's event log: LHC@home 09 Oct 15:22:51 Aborting task Theory_2794-3267759-6_2: exceeded disk limit: 7653.58MB > 7629.39MB

...
EXIT_DISK_LIMIT_EXCEEDED ==> https://lhcathome.cern.ch/lhcathome/result.php?resultid=414826538

as I mentioned earlier today: Herwig7 should not be sent out - they seem to have some problems

...
EXIT_DISK_LIMIT_EXCEEDED ==> https://lhcathome.cern.ch/lhcathome/result.php?resultid=414826538

as I mentioned earlier today: Herwig7 should not be sent out - they seem to have some problems

A tad long running but they seem okay on Native.

count me in
exceeded disk limit: 7641.76MB > 7629.39MB
https://lhcathome.cern.ch/lhcathome/result.php?resultid=414871107
Name: Theory_2794-3259275-214_0
Runtime 4 Tage 1 Stunden 38 min. 25 sek.
CPU time 3 Tage 17 Stunden 36 min. 11 sek.

---

Matthias

Boincmanager Diskdefinition. Have 125 GByte as default and yours?
15.10.2024 16:08:46 | | - max disk usage: 125.00 GB

Boincmanager Diskdefinition. Have 125 GByte as default and yours?
15.10.2024 16:08:46 | | - max disk usage: 125.00 GB

'exceeded disk limit' is not caused due to reserving too less disk space for BOINC.

There is a server setting coming with each task.
This setting (rsc_disk_bound - for Theory 8000000000 bytes) let abort that task, when the total disk space in the slot (including subdirs) used for that task is exceeded

This one ended after 35 hours and just started the event processing without a valid result: https://lhcathome.cern.ch/lhcathome/result.php?resultid=415017176