Difference between revisions of "Atlas:Analysis ST 2009 Errors"

Un article de lcgwiki.
Jump to: navigation, search
(Comments and Errors follow-up)
 
(15 intermediate revisions by the same user not shown)
Ligne 1: Ligne 1:
30.01.09
+
--[[User:Chollet|Chollet]] 14:24, 15 mai 2009 (CEST)
 +
== Errors follow-up - Known issues ==
 +
* '''Corrupted input AOD files found'''
 +
  AOD.027097._37998.pool.root 
 +
  AOD.027579._24654.pool.root
 +
  AOD.027076._10514.pool.root
 +
- Badread error example
 +
rfio:clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-30/AOD.027579._24654.pool.root.2781052.0 at byte:32849441, branch:m_genParticles.m_endVtx, entry:217, badread=0
 +
- To check if the file is corrupted on SE or not, please refer to ATLAS procedure
 +
(requests an certificate approved by ATLAS) defined here: <br>
 +
https://twiki.cern.ch/twiki/bin/view/Atlas/DDMOperationProcedures#Checksum_error_triggered_by_dq2
 +
* IN2P3-CPPM / IN2P3-LPC :  '''overload of lcg-gt during SURL to TURL conversion'''
 +
Jobs running forever with error, killed by the batch system.
 +
The error should at least be catched by Ganga - Savannah ticket opened :
 +
https://savannah.cern.ch/bugs/index.php?48537
 +
  send2nsd: NS009 - fatal configuration error: Host unknown:  dpnshome.in2p3.fr
 +
  send2dpm: DP000 - disk pool manager not running on marwn04.in2p3.fr
 +
This arrive for 13 jobs, all starts running nearly at the same time Thu Jan 29 22:37:53 and run in error around Jan 30 00:21.
 +
I have put two of this stdout, stderr there :<br>
 +
http://marwww.in2p3.fr/~knoops/752629.marce01.in2p3.fr/<br>
 +
http://marwww.in2p3.fr/~knoops/752631.marce01.in2p3.fr/<br>
 +
Heavy load of the local DPM server observed at that time.
  
== Comments and Errors follow-up ==
+
* IN2P3-LAPP : during ST125, 30/01/09 '''jobs still running after 2500 minutes, failing to connect to LFC''' with the message :
*http://atlas-ganga-storage.cern.ch/test_124/  DQ2_LOCAL (rfio)
 
*http://atlas-ganga-storage.cern.ch/test_125/  FILESTAGER (lcg_cp)
 
'''Note that ATLAS Production was ON on the FR-Cloud on January 29'''
 
 
 
* IN2P3-LPC_MCDISK: f(w)  - Errors due to the load induced by MC production running at that time. Then ST tests jobs (2 x 50 jobs added)were aborted with an "Unspecified gridmanager error" logged by WMS.<br>
 
In fact, the submission to the batch system was failing because the '''max. total number of jobs (GlueCEPolicyMaxTotalJobs) was reached '''. Probably this value is not looked at as it could be before submission by WMS. <br>
 
Jan 29 23:54:46 clrlcgce03 lcgpbs:internal_ FAILED during submission
 
to batch system lcgpbs(Maximum number of jobs already in queue)..
 
This limitation has been removed by site.
 
* IN2P3-CPPM_MCDISK:  The same problem has in previous test. Jobs running forever with error ."send2dpm: DP000 - disk pool manager not running on marwn04.in2p3.fr ". This arrive for 13 jobs, all starts running nearly at the same time Thu Jan 29 22:37:53 and run in error around Jan 30 00:21. I have put two of this stdout, stderr there
 
http://marwww.in2p3.fr/~knoops/752629.marce01.in2p3.fr/
 
http://marwww.in2p3.fr/~knoops/752631.marce01.in2p3.fr/
 
The load of the local DPM server was around 9 at that time.
 
 
 
* IN2P3-LAPP : during ST125, 30/01/09 jobs still running after 2500 minutes, failing to connect to LFC with the message :
 
 
  send2nsd: NS002 - send error : _Csec_recv_token: Received magic:30e1301 expecting ca03
 
  send2nsd: NS002 - send error : _Csec_recv_token: Received magic:30e1301 expecting ca03
 
  cannot connect to LFC  
 
  cannot connect to LFC  

Latest revision as of 13:25, 15 mai 2009

--Chollet 14:24, 15 mai 2009 (CEST)

Errors follow-up - Known issues

  • Corrupted input AOD files found
 AOD.027097._37998.pool.root  
 AOD.027579._24654.pool.root 
 AOD.027076._10514.pool.root

- Badread error example

rfio:clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-30/AOD.027579._24654.pool.root.2781052.0 at byte:32849441, branch:m_genParticles.m_endVtx, entry:217, badread=0

- To check if the file is corrupted on SE or not, please refer to ATLAS procedure (requests an certificate approved by ATLAS) defined here:
https://twiki.cern.ch/twiki/bin/view/Atlas/DDMOperationProcedures#Checksum_error_triggered_by_dq2

  • IN2P3-CPPM / IN2P3-LPC : overload of lcg-gt during SURL to TURL conversion

Jobs running forever with error, killed by the batch system. The error should at least be catched by Ganga - Savannah ticket opened : https://savannah.cern.ch/bugs/index.php?48537

 send2nsd: NS009 - fatal configuration error: Host unknown:  dpnshome.in2p3.fr
 send2dpm: DP000 - disk pool manager not running on marwn04.in2p3.fr 

This arrive for 13 jobs, all starts running nearly at the same time Thu Jan 29 22:37:53 and run in error around Jan 30 00:21. I have put two of this stdout, stderr there :
http://marwww.in2p3.fr/~knoops/752629.marce01.in2p3.fr/
http://marwww.in2p3.fr/~knoops/752631.marce01.in2p3.fr/
Heavy load of the local DPM server observed at that time.

  • IN2P3-LAPP : during ST125, 30/01/09 jobs still running after 2500 minutes, failing to connect to LFC with the message :
send2nsd: NS002 - send error : _Csec_recv_token: Received magic:30e1301 expecting ca03
cannot connect to LFC 

Service was up and running fine at that time Is it due to an expired proxy ?

  • RO_07 : ST jobs can not store the output locally and are always using the fail-over storing output files in Lyon

still configuration problem with the USERDISK token on tbit00.nipne.ro SE ?

lcg-cr --vo atlas -s ATLASUSERDISK  -t 2400 -d srm://tbit00.nipne.ro/dpm/.....
dpm_getspacetoken: Unknown user space token description