1) Message boards : ATLAS application : VirtualBox 5.2 (Message 36385)
Posted 1 day ago by Toby Broom
Post:
Yes, I did both, I allow 100% of CPU usage so it's likely to do with that?
2) Message boards : Number crunching : Change Request for the Term "Max # CPUs" (Message 36359)
Posted 4 days ago by Toby Broom
Post:
It's the stock config from BOINC.

I think we discussed this a long time ago the purpose of a job to try and stop people computers being swamped with work, for example if you ran 8, 8core tasks on your computer then it would lockup either from ram usage or cpu usage. So the project can set the defaults to be 1job and 1core then people can dial it up from there.


BOINC does a poor job with this as we all think abouts tasks as this is what the UI shows in client. When the project submits the work it's called a job hence the naming.

Also for ATLAS, unlimited jobs/tasks is not actually unlimited jobs/tasks, so even more confusing.
3) Message boards : ATLAS application : VirtualBox 5.2 (Message 36346)
Posted 5 days ago by Toby Broom
Post:
Personally the 5.2.16 gives many unmanageable errors with ATLAS. The CMS, LHCb, Theory have no issues.

The 5.1.38 works well for all tasks.

I don't think others have computers that can run so many WU at once?
4) Message boards : Sixtrack Application : What tipe of simulation my computer doses? (Message 36321)
Posted 6 days ago by Toby Broom
Post:
How about this if your more of a physics person?

http://sixtrack.web.cern.ch/SixTrack/docs/physics_full/manual.php

or this

http://lhcathome.web.cern.ch/projects/sixtrack/sixtrack-and-numerical-simulations

Correct it simulates which particles will be lost depending on the magnetic fields

The VirtualBox tasks are running well for me, be aware ATLAS raised the ram requirement to 3.9GB for a single core task scaling from there.
5) Message boards : Number crunching : "Waiting for memory" - although enough RAM available (Message 36312)
Posted 6 days ago by Toby Broom
Post:
I my opinion it's the responsibility of the project team to set it correctly, not BOINC. Since it's configerable on a per job basis. I don't think BOINC knows for any WU not just Virtual ones. Maybe the required ram? as you said this isn't valid for VMs.

The limits on WU are also a project configuration topic too, since theory allows more than one WU if the 1 core setting is selected as you would expect.

You could run 3 six cores with 3 in the queue.
Core/WU	        WS MB	     BOINC Use	 GB         Running	 Queued
1	         3900	       3.8	             1	           0
2	         4800	       4.7           	     1	           0
3	         5700	       5.6	             3        	   0
4	         6600	       6.4	             4	           0
5	         7500	       7.3	             4	           1
6	         8400	       8.2	             3	           3
7	         9300	       9.1	             3	           4
8	        10200	      10.0	             3	           5
6) Message boards : Number crunching : "Waiting for memory" - although enough RAM available (Message 36288)
Posted 7 days ago by Toby Broom
Post:
The memory in app config is not known by boinc, boinc uses the working set defined by the project to calculate if it has enough free ram to start another task.

You can try to tune the number of cores on the web to match the working set in the appconfig or you can choose 1 core on the web and force more cores with appconfig. With the 2nd option now you have to be careful that boinc doesn't start too many tasks and over load the ram on your computer.


Since the project by default use 4800MB, you could stop using the appconfig and go with websettings, although the 2core will use 5700MB under new rules.
7) Message boards : CMS Application : no new WUs available (Message 36281)
Posted 7 days ago by Toby Broom
Post:
The CMS team said they have to totally overall the VM innards, so I assume there would be a whole load of errors, until they get it all worked out.
8) Message boards : Number crunching : fubar host of the day (Message 36211)
Posted 11 days ago by Toby Broom
Post:
Sorry, I read something over on the main boinc forums about issues with gridcoin and the use of account mangers in a non-standard manner.


Looks like I bade a bad assumption
9) Message boards : Number crunching : fubar host of the day (Message 36205)
Posted 11 days ago by Toby Broom
Post:
I'm think for gridcoin it because the users are automatically added to this project without really knowing so they don't realize they need virtualbox.
10) Message boards : Number crunching : Host won't download new tasks (Message 36204)
Posted 11 days ago by Toby Broom
Post:
I can defiantly not recommend 5.2.x for ATLAS, for the other project it looks OK.
11) Message boards : Number crunching : VirtualBox needed? (Message 36158)
Posted 13 days ago by Toby Broom
Post:
It's normal to have these left over files, they don't seem to cause any problems
12) Message boards : ATLAS application : Atlas tasks "Postponed: VM job unmanageable, restarting later." (Message 36153)
Posted 13 days ago by Toby Broom
Post:
I guess my previous actions were the best. As if we don't try and work around the issues and stop working for the project then they would address the request that we have.

I only run one core task on my machines as it the most efficient, I have one that run dual core as there is a limit on the number of tasks that you can run. compared to the other projects I don't contribute much to ATLAS as it's not possible to configure my computers to do more when shared with the other projects.

I expected it to work well as it was working well before so that set my expectations, hence the roll back.

If the task is postponed then in my experience it's never come back from that state, I think if you restart Boinc, then it will come back. The biggest problem with that state is it stops boinc from getting new tasks so when left un-managed it drains the queue
13) Message boards : Cafe LHC : Rewards (Message 36150)
Posted 13 days ago by Toby Broom
Post:


Treats from the project
14) Message boards : ATLAS application : Atlas tasks "Postponed: VM job unmanageable, restarting later." (Message 36149)
Posted 13 days ago by Toby Broom
Post:
Since I'm on windows, I made a Powershell script that runs and aborts the stuck tasks automatically.

I downgraded to the 5.1.x Vbox and this improved things as well I think.
15) Message boards : ATLAS application : Non-zero return code from EVNTtoHITS (65) (Error code 65) (Message 36142)
Posted 14 days ago by Toby Broom
Post:
I rolled back to 5.1.38 and these HITS issues look better on my computers
16) Message boards : CMS Application : no new WUs available (Message 36130)
Posted 14 days ago by Toby Broom
Post:
Hi All,

I talked with CMS team, there is a very small amount of work so they need the BOINC side enabled to test things. As you know BOINC and the science projects are only loosely linked so we see this observed behavior.


As before if it bothers you then disable the project or you can help the team develop the new CMS backend links to BOINC.
17) Message boards : ATLAS application : Non-zero return code from EVNTtoHITS (65) (Error code 65) (Message 36079)
Posted 18 days ago by Toby Broom
Post:
I didn't try to setup on my Linux box as it one of the weaker computers I have so I just use it for sixtrack.

I used the app_config with my windows ones but since you can configure the setting completely it again make it a challenge to configure as required, e.g the working set is wrong so it blocks other work etc.
18) Message boards : Sixtrack Application : What tipe of simulation my computer doses? (Message 36078)
Posted 18 days ago by Toby Broom
Post:
here is a description of what is does

http://lhcathome.web.cern.ch/projects/sixtrack

If you want to review the code and really see what it does:

http://sixtrack.web.cern.ch/SixTrack/
19) Message boards : ATLAS application : Non-zero return code from EVNTtoHITS (65) (Error code 65) (Message 36075)
Posted 18 days ago by Toby Broom
Post:
You can run multiple on windows too, its pretty much same procedure as with Linux.

All of my tasks created no HITS files, so I gave up on ATLAS again for a bit, it was working fine but they make a pain to setup.
20) Message boards : ATLAS application : New BOINC 7.12.1 causing "Postponed: Communication with VM Hypervisor failed" errors (Message 36047)
Posted 19 days ago by Toby Broom
Post:
I managed to run a few with success, I have virtual box 5.2.16.

What I have found for my computer with ATLAS is it's very sensitive, when I ran 1 core wu then I think it could not handle running many VMs at the same time, as per you I have plenty resources etc. with 2 CPU WU's I seem to be having less issues.


Next 20


©2018 CERN