Message boards : Number crunching : Exceeding maxium disk space.
Message board moderation

To post messages, you must log in.

AuthorMessage
paperdragon
Avatar

Send message
Joined: 2 Aug 05
Posts: 13
Credit: 190,657
RAC: 0
Message 21247 - Posted: 24 Feb 2009, 20:25:50 UTC

The 6 work units I have just run, all errored on \\\'maxium disk space exceed\\\'

They are running program: sixtrack_4.67_windows_intelx86
OS is: Windows XP Pro, SP2.

http://lhcathome.cern.ch/lhcathome/result.php?resultid=17852851
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17852103
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17847028
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17847026
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17844539
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17836758


You like Myst? Uru Live returns! www.urulive.com
ID: 21247 · Report as offensive     Reply Quote
watnou

Send message
Joined: 1 Sep 04
Posts: 101
Credit: 1,395,204
RAC: 0
Message 21248 - Posted: 24 Feb 2009, 21:12:19 UTC

i had a handfull of wu\'s too.
some are successfull
but 2 where in an error state with the same error msg

ID: 21248 · Report as offensive     Reply Quote
Profile Grubix

Send message
Joined: 3 Jul 08
Posts: 20
Credit: 8,281,604
RAC: 0
Message 21250 - Posted: 24 Feb 2009, 22:26:22 UTC
Last modified: 24 Feb 2009, 22:30:14 UTC

I have the same problem:

--------------------------------
Di 24 Feb 2009 18:59:55 CET||Preferences limit memory usage when active to 1414.21MB
Di 24 Feb 2009 18:59:55 CET||Preferences limit memory usage when idle to 1590.98MB
Di 24 Feb 2009 18:59:55 CET||Preferences limit disk usage to 10.00GB
Di 24 Feb 2009 19:00:17 CET|lhcathome|Aborting task w1_lhc_t1__54__s__64.31_59.32__16_17__5__75_1_sixvf_boinc4482_1: exceeded disk limit: 36.97MB > 28.61MB
Di 24 Feb 2009 19:01:18 CET|lhcathome|Computation for task w1_lhc_t1__54__s__64.31_59.32__16_17__5__75_1_sixvf_boinc4482_1 finished
Di 24 Feb 2009 19:01:20 CET|lhcathome|Started upload of w1_lhc_t1__54__s__64.31_59.32__16_17__5__75_1_sixvf_boinc4482_1_0
Di 24 Feb 2009 19:01:21 CET|lhcathome|Finished upload of w1_lhc_t1__54__s__64.31_59.32__16_17__5__75_1_sixvf_boinc4482_1_0
Di 24 Feb 2009 19:05:17 CET|lhcathome|Aborting task w1_lhc_t1__54__s__64.31_59.32__17_18__5__15_1_sixvf_boinc4483_0: exceeded disk limit: 39.64MB > 28.61MB
Di 24 Feb 2009 19:06:17 CET|lhcathome|Computation for task w1_lhc_t1__54__s__64.31_59.32__17_18__5__15_1_sixvf_boinc4483_0 finished
Di 24 Feb 2009 19:06:20 CET|lhcathome|Started upload of w1_lhc_t1__54__s__64.31_59.32__17_18__5__15_1_sixvf_boinc4483_0_0
Di 24 Feb 2009 19:06:23 CET|lhcathome|Finished upload of w1_lhc_t1__54__s__64.31_59.32__17_18__5__15_1_sixvf_boinc4483_0_0
Di 24 Feb 2009 19:11:34 CET|lhcathome|Sending scheduler request: To report completed tasks.  Requesting 128002 seconds of work, reporting 2 completed tasks
--------------------------------


The computer runs Ubuntu 8.10, has 2GB RAM an the BOINC-Client can use 10GB disk space.

Is this a misconfiguration of the client or the server? The 28.61MB do not seem a value of my computer.

Have a nice day, Grubix.
ID: 21250 · Report as offensive     Reply Quote
Profile dr_mabuse
Avatar

Send message
Joined: 30 Dec 05
Posts: 57
Credit: 835,284
RAC: 0
Message 21252 - Posted: 25 Feb 2009, 1:44:13 UTC

Ihave the same problem with my last 3 runs under Windows XP Pro SP3 with BOINC 6.4.5. Never had this problem before, even not on climateprediction what takes much more disk space.
********
24.02.2009 17:56:11|lhcathome|Starting w1_lhc_t1__3__s__64.31_59.32__8_9__5__60_1_sixvf_boinc361_3
24.02.2009 17:56:11|lhcathome|Starting task w1_lhc_t1__3__s__64.31_59.32__8_9__5__60_1_sixvf_boinc361_3 using sixtrack version 467
***
24.02.2009 18:22:32|lhcathome|Aborting task w1_lhc_t1__3__s__64.31_59.32__8_9__5__60_1_sixvf_boinc361_3: exceeded disk limit: 38.99MB > 28.61MB
****************
24.02.2009 19:17:11|lhcathome|Starting w1_lhc_t1__10__s__64.31_59.32__9_10__5__60_1_sixvf_boinc926_2
24.02.2009 19:17:11|lhcathome|Starting task w1_lhc_t1__10__s__64.31_59.32__9_10__5__60_1_sixvf_boinc926_2 using sixtrack version 467
***
24.02.2009 18:22:32|lhcathome|Aborting task w1_lhc_t1__3__s__64.31_59.32__8_9__5__60_1_sixvf_boinc361_3: exceeded disk limit: 38.99MB > 28.61MB
*********************
So what could nI do ? Is it the new Sixtrack or is it the new BOINC version ?
Thanks for quick help
Dr.Mabuse
ID: 21252 · Report as offensive     Reply Quote
Brian Silvers

Send message
Joined: 3 Jan 07
Posts: 124
Credit: 7,065
RAC: 0
Message 21256 - Posted: 25 Feb 2009, 12:59:18 UTC

To be clear, the tasks were run on the very old sixtrack 4.67 (Windows systems anyway).
ID: 21256 · Report as offensive     Reply Quote
J Langley

Send message
Joined: 31 Dec 05
Posts: 68
Credit: 8,691
RAC: 0
Message 21258 - Posted: 25 Feb 2009, 22:49:06 UTC - in response to Message 21254.  


It is not a problem with your settings. There is nothing you can do.


Very probably true, but something strange is happening. Check out: http://lhcathome.cern.ch/lhcathome/workunit.php?wuid=3480776

My task finished okay, but first wingman failed with disk space error.

It will be interesting to see what happens to the new wingman\'s result.

ID: 21258 · Report as offensive     Reply Quote
J Langley

Send message
Joined: 31 Dec 05
Posts: 68
Credit: 8,691
RAC: 0
Message 21260 - Posted: 26 Feb 2009, 7:39:37 UTC - in response to Message 21258.  

The WU I mentioned failed on all XP hosts that attempted it, but completed okay on Vista hosts...
ID: 21260 · Report as offensive     Reply Quote
tpieloni

Send message
Joined: 26 Feb 09
Posts: 2
Credit: 0
RAC: 0
Message 21263 - Posted: 26 Feb 2009, 10:31:26 UTC - in response to Message 21247.  

Dear volunteers,
the problem of exceeding disk space comes from an error I have made in the job submission w1_lhc_t1 study.
I was asking for storing too much output and this was going beyond the defined limit of 26.81 MB.
The problem appeared not for all jobs submitted due to the specific physics case.
I have re-submitted the same cases with modified outputs to stay inside the limit that\'s why they have finished successfully in a second try.
Sorry for the inconvenience.
Thanks for your CPUs I hope to make a good use of them.




The 6 work units I have just run, all errored on \\\\\\\'maxium disk space exceed\\\\\\\'

They are running program: sixtrack_4.67_windows_intelx86
OS is: Windows XP Pro, SP2.

http://lhcathome.cern.ch/lhcathome/result.php?resultid=17852851
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17852103
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17847028
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17847026
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17844539
http://lhcathome.cern.ch/lhcathome/result.php?resultid=17836758

ID: 21263 · Report as offensive     Reply Quote
J Langley

Send message
Joined: 31 Dec 05
Posts: 68
Credit: 8,691
RAC: 0
Message 21265 - Posted: 26 Feb 2009, 12:10:31 UTC - in response to Message 21263.  


I have re-submitted the same cases with modified outputs to stay inside the limit that\\\'s why they have finished successfully in a second try.


I\'m not sure that explains the WU I mentioned. My computer got one of the 2 IRs, when the XP host failed I suppose it is possible that subsequent hosts picked up the modified cases, but my computer successfully crunched the original job (there is no \"Cancelled by server\" task), and all subsequent hosts also failed until the WU reached another host running Vista.

If the WUs were faulty surely they should fail on all hosts? So far it looks like XP hosts and Linux hosts all aborted, but Vista hosts all completed okay. This is a little worrying. (Can anyone show a successful unit from the intiial batch on an XP host or a Linux host?)

Are we seeing another HR scenario where the same science app behaves differently on different hosts?
ID: 21265 · Report as offensive     Reply Quote
Profile The Gas Giant

Send message
Joined: 2 Sep 04
Posts: 309
Credit: 715,258
RAC: 0
Message 21269 - Posted: 26 Feb 2009, 19:13:54 UTC
Last modified: 26 Feb 2009, 19:15:47 UTC

I've had 2 wu's fail out with this error and 1 complete satisfactorily, which was strange since all but two other clients reported errors. So I wonder what causes some wu's to crucnh to completion while the exact same wu errors out on other machines?

This is a case in point.
ID: 21269 · Report as offensive     Reply Quote
J Langley

Send message
Joined: 31 Dec 05
Posts: 68
Credit: 8,691
RAC: 0
Message 21270 - Posted: 26 Feb 2009, 19:22:06 UTC - in response to Message 21268.  

Good thought.

Perhaps someone with a dual-boot machine can check what the BOINC client reports at startup - do the spaces reported match?
ID: 21270 · Report as offensive     Reply Quote
J Langley

Send message
Joined: 31 Dec 05
Posts: 68
Credit: 8,691
RAC: 0
Message 21271 - Posted: 26 Feb 2009, 19:28:01 UTC - in response to Message 21269.  

Well that disproves my theory - your WU shows XP machine completing okay.

This is strange.

Perhaps tpieloni can check whether the successful runs submitted files close to the limit?
ID: 21271 · Report as offensive     Reply Quote
noderaser
Avatar

Send message
Joined: 4 Oct 05
Posts: 32
Credit: 344,444
RAC: 0
Message 21280 - Posted: 3 Mar 2009, 3:10:45 UTC - in response to Message 21263.  

Dear volunteers,
the problem of exceeding disk space comes from an error I have made in the job submission w1_lhc_t1 study.
I was asking for storing too much output and this was going beyond the defined limit of 26.81 MB.
The problem appeared not for all jobs submitted due to the specific physics case.
I have re-submitted the same cases with modified outputs to stay inside the limit that\\\'s why they have finished successfully in a second try.
Sorry for the inconvenience.
Thanks for your CPUs I hope to make a good use of them.


Who is this? Actually someone at CERN/LHC? If so, please stop by every now and then! Having interaction with the people who get the data our computers crunch makes the masses very happy, and might attract new users or increase your resource share. To be honest, I\'ve been thinking about dropping this project from my repertoire because of the lack of input from admins, devs and scientists.

Side note: If there has been involvement and I\'ve been to stupid/distracted to notice, perhaps using the \"Project administrator/developer/scientist\" tags would help. I\'ve seen them in other project forums, although I\'m not sure if they are included in the version of BOINC that you\'re running. IIRC, Naesan has them but no one else.
Click here to see My Detailed BOINC Stats
ID: 21280 · Report as offensive     Reply Quote
tpieloni

Send message
Joined: 26 Feb 09
Posts: 2
Credit: 0
RAC: 0
Message 21286 - Posted: 4 Mar 2009, 17:14:04 UTC - in response to Message 21280.  

Yes, I am from CERN/LHC and I am new with LHC@home...
I am running some studies for the LHC and trying to learning how to use this powerful pool of CPUs.
I will try to stop by the forum every now and then to update you on the outcomes of the study.
Let\\\'s keep running.

ID: 21286 · Report as offensive     Reply Quote
Profile The Gas Giant

Send message
Joined: 2 Sep 04
Posts: 309
Credit: 715,258
RAC: 0
Message 21293 - Posted: 6 Mar 2009, 2:53:05 UTC - in response to Message 21286.  

Yes, I am from CERN/LHC and I am new with LHC@home...
I am running some studies for the LHC and trying to learning how to use this powerful pool of CPUs.
I will try to stop by the forum every now and then to update you on the outcomes of the study.
Let\'s keep running.


Excellent. Welcome from us all!
ID: 21293 · Report as offensive     Reply Quote

Message boards : Number crunching : Exceeding maxium disk space.


©2024 CERN