Development for LHC@home

I'm up to run-13 in about an hour, each one takes about 4 minutes !

Reached run 29, one each 3 minutes.
Tullio

Doesn't seem to use much CPU (13%). Is that a sign of a problem?

Is that on your host machine or in the ALT+F3 VM console?
Of course, if it's an 8-core machine, Task Manager will show 12 or 13% for a full core's usage...

That was in BoincTasks v. 1.67, but for the ALT+3, mostly zero, up to one moment 20.5%. Seems like no work is being done.

Yes, run-number logs are being kept now - I'm up to run-5. But the contents seem the same as before. What, in particular, would you like us to watch out for?

I've got a run-1 directory, but nothing for the job that's now running. :-(

I'm up to run-57, but they're all very similar, like

	cron-stderr	20-Aug-2015 17:41	7.1K	 
	cron-stdout	20-Aug-2015 17:42	48K	 
	glidein-stderr	20-Aug-2015 17:39	38K	 
	glidein-stdout	20-Aug-2015 17:39	6.5K

I'm waiting for the file sizes to change before I read through another set.

Tasks are 'passing through' about once every two minutes, but I don't think I'd say they were 'lasting' that long. Condor lasts for about 5 seconds, and the rest is setup, error, sleep.

Doesn't seem to use much CPU (13%). Is that a sign of a problem?

Is that on your host machine or in the ALT+F3 VM console?
Of course, if it's an 8-core machine, Task Manager will show 12 or 13% for a full core's usage...

That was in BoincTasks v. 1.67, but for the ALT+3, mostly zero, up to one moment 20.5%. Seems like no work is being done.

I'm running CMS on two machines - an 8-core hyperthreaded i7 with VBox 4.3.26, and a true 4-core i5 with VBox 5.0.2

The older VBox on the i7 is showing similar CPU %ages - mostly 9%-10%, occasional spikes higher. The newer VBox seems to have higher overheads, in the 25%-30% range.

I'm using similar monitoring to rbpeake - BoincView. Both programs report CPU usage per core - on a scale up to 100% - so these are all 'low' CPU utilisation, unlike any similar percentages displayed by Task Manager on multi-core machines.

All the figures I've given are for today, when the VMs have been essentially idle because of the broken agent. Earlier in the week, when real jobs were running, CPU usage was mostly in the high 90s, and occasionally reached a full 100% (or 1.0000, as BoincView displays the fraction).

I have not seen ANY changes in the past few hours.
Are mods actually being applied?

If not, why do we need all these logs?

Laurence, Ivan,

I feel it wouldn't be good to post a lot of logs here; perhaps you want us to E-Mail you some logs.

Tell us, which and how many logs you are interested and an E-Mail-Adress where to send them.

Fact is, until now my Laptop doesn't do any usefull work and I haven't seen cmsRun since more than 24 hours now.

Laurence, Ivan,

I feel it wouldn't be good to post a lot of logs here; perhaps you want us to E-Mail you some logs.

Tell us, which and how many logs you are interested and an E-Mail-Adress where to send them.

Fact is, until now my Laptop doesn't do any usefull work and I haven't seen cmsRun since more than 24 hours now.

I believe that some of the logs are returned, as Laurence was talking about using them for accounting.
Personally, I'm in much the same boat as you, tho' I do get cmsRun on my SLC6 box. Something with job submission is broken, and I need to hear back from RAL admins to see whether it's at their end or mine. I'm giving up for now, as I want to get away before the gates are locked and I have to take the long way home. Suggest people let things lie until tomorrow -- I'm bushed!

---

Okay, then for today: Good night !

Richard Haselgrove wrote:

Earlier in the week, when real jobs were running, CPU usage was mostly in the high 90s, and occasionally reached a full 100% (or 1.0000, as BoincView displays the fraction).

Yeah, the good old days.
The task I returned 3 days ago even had 97% CPU performance over 91,444.93 wallclock seconds.
Those were the days.

I'm very confused. Easily done, so please be patient.

On the single host I have running at the moment (553) cmsRun is happily
chugging through jobs (by "job" I mean 200 events) taking 20-30 mins using
up to 97% cpu. Am I using the new agent that seems to be causing so much
trouble? How do I find out?

From the timestamps on the run_0 and run_1 subdirectories (that's as far as it's
got) a run takes three hours.

The only thing that seems odd here is the logging, there are similar files in /logs as well as in run_0 and run_1 with some updated and others not but that could simply be the time taken to update the files together with the workings of the browser cache. Maybe thay will sort themselves out.

Sounds like you hit the jackpot !

What are the lottery numbers for the next draw ?

run1, run2 etc. are test logs for diagnostic purposes.

You are lucky, yours is running. I have not been able to crunch anything, as, i believe, most users have not, due to the bug, that prevents work from being transferred to the users Computers.

I understand the looping issue that some have been experiencing and will push a fix ASAP. Hopefully everything will be fine in the morning.

I understand the looping issue that some have been experiencing and will push a fix ASAP. Hopefully everything will be fine in the morning.

OK, Laurence, see you then. I couldn't do anything from home anyway, my broadband is down to 240 at times -- that's 240 B/s, not 240 kB/s...

---

I understand the looping issue that some have been experiencing and will push a fix ASAP. Hopefully everything will be fine in the morning.

HEUREKA, you got it !

My Laptop is back in crunching, cmsRun with 100% CPU-Usage

I will take a look to my desktop

I wouldn't call it broadband ...

I will take a look to my desktop

It needed a kick, but now crunching again

Mine is working now! Well done!!

Me too! At least, BoincView has 'gone green' with 100% CPU efficiency. It's after midnight here, so I haven't gone down into the cellar to inspect the console output directly.